0 bleu

eng-nah-svo-translation/README.md

@@ -1,6 +1,4 @@
 ---
-license: apache-2.0
-base_model: Helsinki-NLP/opus-mt-en-fr
 tags:
 - translation
 - generated_from_trainer
@@ -16,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # eng-nah-svo-translation
 
-This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7505
+- Loss: 0.3041
 - Bleu: 0.0
 
 ## Model description

eng-nah-svo-translation/checkpoint-228/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
+  "_name_or_path": "eng-nah-svo-translation",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "swish",

eng-nah-svo-translation/checkpoint-228/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59bd8d6a5080deae89e2f3af738d6e660f46d2030518a0b4eaba82fdb6509383
+oid sha256:5190a17f19275c1af2d846140e4909e9d083e4c4f44fbfb42acad0530b174290
 size 597088389

eng-nah-svo-translation/checkpoint-228/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c630d8e9c4466cfe5d61bacf6d7fe1ac796efef22faf9503d8fc73e57d641f6
+oid sha256:140fc7491625eee2830a2bfde50a63b78cd6939bed1b4abeb189be50ab10980f
 size 298763205

eng-nah-svo-translation/checkpoint-228/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a721cf0d37771b1d7220d33b1f17366183f3d518b2432e040b875a92c5be520b
+oid sha256:06a45c37f0e7284c095b4b503ffa422c6b8f2791990e008912c3c06d6db7d538
 size 4219

eng-nah-svo-translation/checkpoint-456/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
+  "_name_or_path": "eng-nah-svo-translation",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "swish",

eng-nah-svo-translation/checkpoint-456/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e43e1b1fcf506facd572f3acb3d20cfee480bceb3b99287aefb50fee0d941268
+oid sha256:7de8c09d2c5d4f0096b953c55e83345013e4bcfb30df1f8899d8a579b549de65
 size 597088389

eng-nah-svo-translation/checkpoint-456/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a52afa6f3c380dd31b380fb49419dd696f4b16855b1a1ccf159d762c25153e7
+oid sha256:ef15720547c6e860442101e376eaa81dc981ef8521399ce751cfaf29fc229213
 size 298763205

eng-nah-svo-translation/checkpoint-456/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a721cf0d37771b1d7220d33b1f17366183f3d518b2432e040b875a92c5be520b
+oid sha256:06a45c37f0e7284c095b4b503ffa422c6b8f2791990e008912c3c06d6db7d538
 size 4219

eng-nah-svo-translation/checkpoint-684/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
+  "_name_or_path": "eng-nah-svo-translation",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "swish",

eng-nah-svo-translation/checkpoint-684/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eac5f706f0d09f4867580538158e03c320797c1671d0b3f38cad52bfa2874d1d
+oid sha256:19578c8bd50d0d5922742f052fdb7391eec55dd2ab281226cdcae8cd78356dd9
 size 597088389

eng-nah-svo-translation/checkpoint-684/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8668eed40a7cfcfc0587457eb0a6d8466a902ba9586f114dd71080246ca1b412
+oid sha256:9f62408ea2e275aed7548ea31e37c534dd035154b3999483e0ed481c2dd1f9e2
 size 298763205

eng-nah-svo-translation/checkpoint-684/trainer_state.json

@@ -11,7 +11,7 @@
     {
       "epoch": 2.19,
       "learning_rate": 5.380116959064328e-06,
-      "loss": 1.2688,
+      "loss": 0.2276,
       "step": 500
     }
   ],

eng-nah-svo-translation/checkpoint-684/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a721cf0d37771b1d7220d33b1f17366183f3d518b2432e040b875a92c5be520b
+oid sha256:06a45c37f0e7284c095b4b503ffa422c6b8f2791990e008912c3c06d6db7d538
 size 4219

eng-nah-svo-translation/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
+  "_name_or_path": "eng-nah-svo-translation",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "swish",

eng-nah-svo-translation/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8668eed40a7cfcfc0587457eb0a6d8466a902ba9586f114dd71080246ca1b412
+oid sha256:9f62408ea2e275aed7548ea31e37c534dd035154b3999483e0ed481c2dd1f9e2
 size 298763205

eng-nah-svo-translation/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a721cf0d37771b1d7220d33b1f17366183f3d518b2432e040b875a92c5be520b
+oid sha256:06a45c37f0e7284c095b4b503ffa422c6b8f2791990e008912c3c06d6db7d538
 size 4219

myerrors_1556.out

@@ -0,0 +1,22 @@
+
+
+
+Traceback (most recent call last):
+  File "/mnt/storage/aatherton/hf_synth_trans/synth_translation.py", line 72, in <module>
+    model = AutoModelForSeq2SeqLM.from_pretrained(model_checkpoint)
+            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/auto/auto_factory.py", line 482, in from_pretrained
+    config, kwargs = AutoConfig.from_pretrained(
+                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/auto/configuration_auto.py", line 1007, in from_pretrained
+    config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
+                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/configuration_utils.py", line 620, in get_config_dict
+    config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
+                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/configuration_utils.py", line 675, in _get_config_dict
+    resolved_config_file = cached_file(
+                           ^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/utils/hub.py", line 399, in cached_file
+    raise EnvironmentError(
+OSError: eng-nah-svo-cpt does not appear to have a file named config.json. Checkout 'https://huggingface.co/eng-nah-svo-cpt/None' for available files.

myerrors_1557.out

@@ -0,0 +1,40 @@
+Traceback (most recent call last):
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/huggingface_hub-0.17.1-py3.8.egg/huggingface_hub/utils/_errors.py", line 261, in hf_raise_for_status
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/requests/models.py", line 1021, in raise_for_status
+    raise HTTPError(http_error_msg, response=self)
+requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/eng-nah-svo-cpt/resolve/main/tokenizer_config.json
+
+The above exception was the direct cause of the following exception:
+
+Traceback (most recent call last):
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/utils/hub.py", line 428, in cached_file
+    resolved_file = hf_hub_download(
+                    ^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/huggingface_hub-0.17.1-py3.8.egg/huggingface_hub/utils/_validators.py", line 118, in _inner_fn
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/huggingface_hub-0.17.1-py3.8.egg/huggingface_hub/file_download.py", line 1344, in hf_hub_download
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/huggingface_hub-0.17.1-py3.8.egg/huggingface_hub/file_download.py", line 1230, in hf_hub_download
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/huggingface_hub-0.17.1-py3.8.egg/huggingface_hub/utils/_validators.py", line 118, in _inner_fn
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/huggingface_hub-0.17.1-py3.8.egg/huggingface_hub/file_download.py", line 1606, in get_hf_file_metadata
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/huggingface_hub-0.17.1-py3.8.egg/huggingface_hub/utils/_errors.py", line 293, in hf_raise_for_status
+huggingface_hub.utils._errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-65078ad3-69f0105f790b8b472eceb3d6;305708a1-7612-4fce-92cd-fb302d6700cd)
+
+Repository Not Found for url: https://huggingface.co/eng-nah-svo-cpt/resolve/main/tokenizer_config.json.
+Please make sure you specified the correct `repo_id` and `repo_type`.
+If you are trying to access a private or gated repo, make sure you are authenticated.
+
+The above exception was the direct cause of the following exception:
+
+Traceback (most recent call last):
+  File "/mnt/storage/aatherton/hf_synth_trans/synth_translation.py", line 40, in <module>
+    tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
+                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/auto/tokenization_auto.py", line 677, in from_pretrained
+    tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs)
+                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/auto/tokenization_auto.py", line 510, in get_tokenizer_config
+    resolved_config_file = cached_file(
+                           ^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/utils/hub.py", line 449, in cached_file
+    raise EnvironmentError(
+OSError: eng-nah-svo-cpt is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
+If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=<your_token>`

myerrors_1558.out

@@ -0,0 +1,101 @@
+
+You're using a GPT2TokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [0,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [1,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [2,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [3,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [4,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [5,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [6,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [7,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [8,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [9,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [10,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [11,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [12,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [13,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [14,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [15,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [16,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [17,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [18,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [19,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [20,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [21,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [22,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [23,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [24,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [25,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [26,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [27,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [28,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [29,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [30,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+/opt/conda/conda-bld/pytorch_1682343995622/work/aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [237,0,0], thread: [31,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
+Traceback (most recent call last):
+  File "/mnt/storage/aatherton/hf_synth_trans/synth_translation.py", line 132, in <module>
+    trainer.evaluate(max_length=max_length)
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/trainer_seq2seq.py", line 159, in evaluate
+    return super().evaluate(eval_dataset, ignore_keys=ignore_keys, metric_key_prefix=metric_key_prefix)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/trainer.py", line 2972, in evaluate
+    output = eval_loop(
+             ^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/trainer.py", line 3161, in evaluation_loop
+    loss, logits, labels = self.prediction_step(model, inputs, prediction_loss_only, ignore_keys=ignore_keys)
+                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/trainer_seq2seq.py", line 282, in prediction_step
+    generated_tokens = self.model.generate(**inputs, **gen_kwargs)
+                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
+    return func(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/generation/utils.py", line 1596, in generate
+    return self.greedy_search(
+           ^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/generation/utils.py", line 2444, in greedy_search
+    outputs = self(
+              ^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
+    return forward_call(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/bert/modeling_bert.py", line 1235, in forward
+    outputs = self.bert(
+              ^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
+    return forward_call(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/bert/modeling_bert.py", line 1022, in forward
+    encoder_outputs = self.encoder(
+                      ^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
+    return forward_call(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/bert/modeling_bert.py", line 612, in forward
+    layer_outputs = layer_module(
+                    ^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
+    return forward_call(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/bert/modeling_bert.py", line 497, in forward
+    self_attention_outputs = self.attention(
+                             ^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
+    return forward_call(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/bert/modeling_bert.py", line 427, in forward
+    self_outputs = self.self(
+                   ^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
+    return forward_call(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/bert/modeling_bert.py", line 286, in forward
+    mixed_query_layer = self.query(hidden_states)
+                        ^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
+    return forward_call(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/nn/modules/linear.py", line 114, in forward
+    return F.linear(input, self.weight, self.bias)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+RuntimeError: CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling `cublasCreate(handle)`

myerrors_1559.out

@@ -0,0 +1,3 @@
+
+You're using a GPT2TokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
+
  0%|          | 0/16 [00:00<?, ?it/s]
 12%|█▎        | 2/16 [00:04<00:30,  2.17s/it]
 19%|█▉        | 3/16 [00:08<00:39,  3.07s/it]slurmstepd-dl: error: *** JOB 1559 ON dl CANCELLED AT 2023-09-17T19:27:45 ***

myerrors_1560.out

@@ -0,0 +1,2 @@
+You're using a GPT2TokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
+
  0%|          | 0/16 [00:00<?, ?it/s]
 12%|█▎        | 2/16 [00:04<00:31,  2.27s/it]
 19%|█▉        | 3/16 [00:08<00:40,  3.15s/it]
 25%|██▌       | 4/16 [00:13<00:43,  3.60s/it]slurmstepd-dl: error: *** JOB 1560 ON dl CANCELLED AT 2023-09-17T19:31:19 ***

myerrors_1561.out

@@ -0,0 +1,161 @@
+You're using a GPT2TokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
+
  0%|          | 0/16 [00:00<?, ?it/s]
 12%|█▎        | 2/16 [00:04<00:31,  2.23s/it]
 19%|█▉        | 3/16 [00:08<00:40,  3.14s/it]
 25%|██▌       | 4/16 [00:13<00:43,  3.62s/it]
 31%|███▏      | 5/16 [00:17<00:42,  3.87s/it]
 38%|███▊      | 6/16 [00:21<00:40,  4.03s/it]
 44%|████▍     | 7/16 [00:26<00:37,  4.13s/it]
 50%|█████     | 8/16 [00:30<00:33,  4.20s/it]
 56%|█████▋    | 9/16 [00:35<00:29,  4.24s/it]
 62%|██████▎   | 10/16 [00:39<00:25,  4.29s/it]
 69%|██████▉   | 11/16 [00:43<00:21,  4.31s/it]
 75%|███████▌  | 12/16 [00:48<00:17,  4.32s/it]
 81%|████████▏ | 13/16 [00:52<00:12,  4.33s/it]
 88%|████████▊ | 14/16 [00:56<00:08,  4.33s/it]
 94%|█████████▍| 15/16 [01:01<00:04,  4.34s/it]
+
  0%|          | 0/684 [00:00<?, ?it/s]
  0%|          | 1/684 [00:00<02:36,  4.35it/s]
  0%|          | 3/684 [00:00<01:15,  9.01it/s]
  1%|          | 5/684 [00:00<01:02, 10.94it/s]
  1%|          | 7/684 [00:00<00:56, 12.01it/s]
  1%|▏         | 9/684 [00:00<00:53, 12.63it/s]
  2%|▏         | 11/684 [00:00<00:51, 13.00it/s]
  2%|▏         | 13/684 [00:01<00:50, 13.29it/s]
  2%|▏         | 15/684 [00:01<00:49, 13.50it/s]
  2%|▏         | 17/684 [00:01<00:49, 13.57it/s]
  3%|▎         | 19/684 [00:01<00:49, 13.57it/s]
  3%|▎         | 21/684 [00:01<00:48, 13.63it/s]
  3%|▎         | 23/684 [00:01<00:48, 13.61it/s]
  4%|▎         | 25/684 [00:01<00:48, 13.70it/s]
  4%|▍         | 27/684 [00:02<00:48, 13.68it/s]
  4%|▍         | 29/684 [00:02<00:47, 13.73it/s]
  5%|▍         | 31/684 [00:02<00:47, 13.70it/s]
  5%|▍         | 33/684 [00:02<00:47, 13.70it/s]
  5%|▌         | 35/684 [00:02<00:47, 13.74it/s]
  5%|▌         | 37/684 [00:02<00:47, 13.71it/s]
  6%|▌         | 39/684 [00:02<00:47, 13.71it/s]
  6%|▌         | 41/684 [00:03<00:46, 13.75it/s]
  6%|▋         | 43/684 [00:03<00:46, 13.73it/s]
  7%|▋         | 45/684 [00:03<00:46, 13.73it/s]
  7%|▋         | 47/684 [00:03<00:46, 13.74it/s]
  7%|▋         | 49/684 [00:03<00:46, 13.77it/s]
  7%|▋         | 51/684 [00:03<00:45, 13.77it/s]
  8%|▊         | 53/684 [00:04<00:45, 13.76it/s]
  8%|▊         | 55/684 [00:04<00:45, 13.76it/s]
  8%|▊         | 57/684 [00:04<00:45, 13.72it/s]
  9%|▊         | 59/684 [00:04<00:45, 13.69it/s]
  9%|▉         | 61/684 [00:04<00:45, 13.70it/s]
  9%|▉         | 63/684 [00:04<00:45, 13.70it/s]
 10%|▉         | 65/684 [00:04<00:45, 13.74it/s]
 10%|▉         | 67/684 [00:05<00:44, 13.71it/s]
 10%|█         | 69/684 [00:05<00:44, 13.71it/s]
 10%|█         | 71/684 [00:05<00:44, 13.69it/s]
 11%|█         | 73/684 [00:05<00:44, 13.65it/s]
 11%|█         | 75/684 [00:05<00:44, 13.70it/s]
 11%|█▏        | 77/684 [00:05<00:44, 13.71it/s]
 12%|█▏        | 79/684 [00:05<00:43, 13.75it/s]
 12%|█▏        | 81/684 [00:06<00:43, 13.71it/s]
 12%|█▏        | 83/684 [00:06<00:43, 13.76it/s]
 12%|█▏        | 85/684 [00:06<00:43, 13.79it/s]
 13%|█▎        | 87/684 [00:06<00:43, 13.75it/s]
 13%|█▎        | 89/684 [00:06<00:43, 13.75it/s]
 13%|█▎        | 91/684 [00:06<00:43, 13.79it/s]
 14%|█▎        | 93/684 [00:06<00:43, 13.72it/s]
 14%|█▍        | 95/684 [00:07<00:42, 13.77it/s]
 14%|█▍        | 97/684 [00:07<00:42, 13.68it/s]
 14%|█▍        | 99/684 [00:07<00:42, 13.73it/s]
 15%|█▍        | 101/684 [00:07<00:42, 13.73it/s]
 15%|█▌        | 103/684 [00:07<00:42, 13.73it/s]
 15%|█▌        | 105/684 [00:07<00:42, 13.76it/s]
 16%|█▌        | 107/684 [00:07<00:41, 13.76it/s]
 16%|█▌        | 109/684 [00:08<00:41, 13.74it/s]
 16%|█▌        | 111/684 [00:08<00:42, 13.58it/s]
 17%|█▋        | 113/684 [00:08<00:41, 13.75it/s]
 17%|█▋        | 115/684 [00:08<00:41, 13.78it/s]
 17%|█▋        | 117/684 [00:08<00:41, 13.76it/s]
 17%|█▋        | 119/684 [00:08<00:41, 13.75it/s]
 18%|█▊        | 121/684 [00:08<00:41, 13.72it/s]
 18%|█▊        | 123/684 [00:09<00:40, 13.76it/s]
 18%|█▊        | 125/684 [00:09<00:40, 13.76it/s]
 19%|█▊        | 127/684 [00:09<00:40, 13.75it/s]
 19%|█▉        | 129/684 [00:09<00:40, 13.71it/s]
 19%|█▉        | 131/684 [00:09<00:40, 13.80it/s]
 19%|█▉        | 133/684 [00:09<00:39, 13.78it/s]
 20%|█▉        | 135/684 [00:09<00:39, 13.76it/s]
 20%|██        | 137/684 [00:10<00:39, 13.69it/s]
 20%|██        | 139/684 [00:10<00:39, 13.73it/s]
 21%|██        | 141/684 [00:10<00:39, 13.74it/s]
 21%|██        | 143/684 [00:10<00:39, 13.68it/s]
 21%|██        | 145/684 [00:10<00:39, 13.72it/s]
 21%|██▏       | 147/684 [00:10<00:39, 13.68it/s]
 22%|██▏       | 149/684 [00:10<00:38, 13.74it/s]
 22%|██▏       | 151/684 [00:11<00:38, 13.74it/s]
 22%|██▏       | 153/684 [00:11<00:38, 13.77it/s]
 23%|██▎       | 155/684 [00:11<00:38, 13.72it/s]
 23%|██▎       | 157/684 [00:11<00:38, 13.74it/s]
 23%|██▎       | 159/684 [00:11<00:38, 13.75it/s]
 24%|██▎       | 161/684 [00:11<00:37, 13.77it/s]
 24%|██▍       | 163/684 [00:12<00:37, 13.74it/s]
 24%|██▍       | 165/684 [00:12<00:37, 13.77it/s]
 24%|██▍       | 167/684 [00:12<00:37, 13.77it/s]
 25%|██▍       | 169/684 [00:12<00:37, 13.78it/s]
 25%|██▌       | 171/684 [00:12<00:37, 13.80it/s]
 25%|██▌       | 173/684 [00:12<00:37, 13.76it/s]
 26%|██▌       | 175/684 [00:12<00:36, 13.78it/s]
 26%|██▌       | 177/684 [00:13<00:36, 13.82it/s]
 26%|██▌       | 179/684 [00:13<00:36, 13.78it/s]
 26%|██▋       | 181/684 [00:13<00:36, 13.80it/s]
 27%|██▋       | 183/684 [00:13<00:36, 13.74it/s]
 27%|██▋       | 185/684 [00:13<00:36, 13.76it/s]
 27%|██▋       | 187/684 [00:13<00:36, 13.73it/s]
 28%|██▊       | 189/684 [00:13<00:35, 13.75it/s]
 28%|██▊       | 191/684 [00:14<00:35, 13.76it/s]
 28%|██▊       | 193/684 [00:14<00:35, 13.75it/s]
 29%|██▊       | 195/684 [00:14<00:35, 13.76it/s]
 29%|██▉       | 197/684 [00:14<00:35, 13.77it/s]
 29%|██▉       | 199/684 [00:14<00:35, 13.77it/s]
 29%|██▉       | 201/684 [00:14<00:35, 13.78it/s]
 30%|██▉       | 203/684 [00:14<00:34, 13.79it/s]
 30%|██▉       | 205/684 [00:15<00:34, 13.71it/s]
 30%|███       | 207/684 [00:15<00:34, 13.73it/s]
 31%|███       | 209/684 [00:15<00:34, 13.76it/s]
 31%|███       | 211/684 [00:15<00:34, 13.69it/s]
 31%|███       | 213/684 [00:15<00:34, 13.74it/s]
 31%|███▏      | 215/684 [00:15<00:34, 13.71it/s]
 32%|███▏      | 217/684 [00:15<00:34, 13.71it/s]
 32%|███▏      | 219/684 [00:16<00:33, 13.76it/s]
 32%|███▏      | 221/684 [00:16<00:34, 13.57it/s]
 33%|███▎      | 223/684 [00:16<00:33, 13.77it/s]
 33%|███▎      | 225/684 [00:16<00:33, 13.76it/s]
 33%|███▎      | 227/684 [00:16<00:33, 13.77it/s]
 33%|███▎      | 229/684 [00:19<03:03,  2.49it/s]
 34%|███▍      | 231/684 [00:19<02:16,  3.33it/s]
 34%|███▍      | 233/684 [00:19<01:43,  4.35it/s]
 34%|███▍      | 235/684 [00:19<01:21,  5.48it/s]
 35%|███▍      | 237/684 [00:19<01:06,  6.70it/s]
 35%|███▍      | 239/684 [00:19<00:56,  7.87it/s]
 35%|███▌      | 241/684 [00:19<00:50,  8.78it/s]
 36%|███▌      | 243/684 [00:20<00:45,  9.63it/s]
 36%|███▌      | 245/684 [00:20<00:42, 10.44it/s]
 36%|███▌      | 247/684 [00:20<00:39, 10.97it/s]
 36%|███▋      | 249/684 [00:20<00:37, 11.64it/s]
 37%|███▋      | 251/684 [00:20<00:36, 11.91it/s]
 37%|███▋      | 253/684 [00:20<00:34, 12.47it/s]
 37%|███▋      | 255/684 [00:20<00:34, 12.58it/s]
 38%|███▊      | 257/684 [00:21<00:33, 12.89it/s]
 38%|███▊      | 259/684 [00:21<00:33, 12.81it/s]
 38%|███▊      | 261/684 [00:21<00:32, 13.00it/s]
 38%|███▊      | 263/684 [00:21<00:32, 13.01it/s]
 39%|███▊      | 265/684 [00:21<00:31, 13.31it/s]
 39%|███▉      | 267/684 [00:21<00:31, 13.04it/s]
 39%|███▉      | 269/684 [00:22<00:31, 13.21it/s]
 40%|███▉      | 271/684 [00:22<00:31, 12.98it/s]
 40%|███▉      | 273/684 [00:22<00:31, 13.21it/s]
 40%|████      | 275/684 [00:22<00:31, 13.04it/s]
 40%|████      | 277/684 [00:22<00:30, 13.37it/s]
 41%|████      | 279/684 [00:22<00:30, 13.21it/s]
 41%|████      | 281/684 [00:22<00:31, 12.98it/s]
 41%|████▏     | 283/684 [00:23<00:30, 12.99it/s]
 42%|████▏     | 285/684 [00:23<00:31, 12.86it/s]
 42%|████▏     | 287/684 [00:23<00:30, 13.02it/s]
 42%|████▏     | 289/684 [00:23<00:30, 12.90it/s]
 43%|████▎     | 291/684 [00:23<00:30, 13.07it/s]
 43%|████▎     | 293/684 [00:23<00:29, 13.10it/s]
 43%|████▎     | 295/684 [00:23<00:29, 13.24it/s]
 43%|████▎     | 297/684 [00:24<00:29, 13.28it/s]
 44%|████▎     | 299/684 [00:24<00:29, 13.25it/s]
 44%|████▍     | 301/684 [00:24<00:29, 13.05it/s]
 44%|████▍     | 303/684 [00:24<00:28, 13.17it/s]
 45%|████▍     | 305/684 [00:24<00:29, 13.00it/s]
 45%|████▍     | 307/684 [00:24<00:28, 13.16it/s]
 45%|████▌     | 309/684 [00:25<00:28, 13.15it/s]
 45%|████▌     | 311/684 [00:25<00:28, 13.09it/s]
 46%|████▌     | 313/684 [00:25<00:27, 13.46it/s]
 46%|████▌     | 315/684 [00:25<00:28, 13.14it/s]
 46%|████▋     | 317/684 [00:25<00:28, 13.03it/s]
 47%|████▋     | 319/684 [00:25<00:27, 13.29it/s]
 47%|████▋     | 321/684 [00:25<00:27, 13.39it/s]
 47%|████▋     | 323/684 [00:26<00:26, 13.64it/s]
 48%|████▊     | 325/684 [00:26<00:26, 13.76it/s]
 48%|████▊     | 327/684 [00:26<00:25, 13.84it/s]
 48%|████▊     | 329/684 [00:26<00:25, 13.88it/s]
 48%|████▊     | 331/684 [00:26<00:25, 13.94it/s]
 49%|████▊     | 333/684 [00:26<00:25, 13.93it/s]
 49%|████▉     | 335/684 [00:26<00:25, 13.92it/s]
 49%|████▉     | 337/684 [00:27<00:24, 13.92it/s]
 50%|████▉     | 339/684 [00:27<00:24, 13.90it/s]
 50%|████▉     | 341/684 [00:27<00:24, 13.89it/s]
 50%|█████     | 343/684 [00:27<00:24, 13.89it/s]
 50%|█████     | 345/684 [00:27<00:24, 13.92it/s]
 51%|█████     | 347/684 [00:27<00:24, 13.92it/s]
 51%|█████     | 349/684 [00:27<00:24, 13.90it/s]
 51%|█████▏    | 351/684 [00:28<00:23, 13.92it/s]
 52%|█████▏    | 353/684 [00:28<00:23, 13.90it/s]
 52%|█████▏    | 355/684 [00:28<00:23, 13.93it/s]
 52%|█████▏    | 357/684 [00:28<00:23, 13.93it/s]
 52%|█████▏    | 359/684 [00:28<00:23, 13.89it/s]
 53%|█████▎    | 361/684 [00:28<00:23, 13.93it/s]
 53%|█████▎    | 363/684 [00:28<00:23, 13.96it/s]
 53%|█████▎    | 365/684 [00:29<00:22, 14.00it/s]
 54%|█████▎    | 367/684 [00:29<00:22, 13.97it/s]
 54%|█████▍    | 369/684 [00:29<00:22, 13.96it/s]
 54%|█████▍    | 371/684 [00:29<00:22, 13.98it/s]
 55%|█████▍    | 373/684 [00:29<00:22, 13.96it/s]
 55%|█████▍    | 375/684 [00:29<00:22, 13.94it/s]
 55%|█████▌    | 377/684 [00:29<00:22, 13.94it/s]
 55%|█████▌    | 379/684 [00:30<00:21, 13.93it/s]
 56%|█████▌    | 381/684 [00:30<00:21, 13.97it/s]
 56%|█████▌    | 383/684 [00:30<00:21, 13.95it/s]
 56%|█████▋    | 385/684 [00:30<00:21, 13.93it/s]
 57%|█████▋    | 387/684 [00:30<00:21, 13.94it/s]
 57%|█████▋    | 389/684 [00:30<00:21, 13.92it/s]
 57%|█████▋    | 391/684 [00:30<00:21, 13.91it/s]
 57%|█████▋    | 393/684 [00:31<00:20, 13.94it/s]
 58%|█████▊    | 395/684 [00:31<00:20, 13.94it/s]
 58%|█████▊    | 397/684 [00:31<00:20, 13.95it/s]
 58%|█████▊    | 399/684 [00:31<00:20, 13.97it/s]
 59%|█████▊    | 401/684 [00:31<00:20, 13.96it/s]
 59%|█████▉    | 403/684 [00:31<00:20, 13.95it/s]
 59%|█████▉    | 405/684 [00:31<00:20, 13.92it/s]
 60%|█████▉    | 407/684 [00:32<00:19, 13.95it/s]
 60%|█████▉    | 409/684 [00:32<00:19, 13.96it/s]
 60%|██████    | 411/684 [00:32<00:19, 13.97it/s]
 60%|██████    | 413/684 [00:32<00:19, 13.96it/s]
 61%|██████    | 415/684 [00:32<00:19, 13.97it/s]
 61%|██████    | 417/684 [00:32<00:19, 13.95it/s]
 61%|██████▏   | 419/684 [00:32<00:18, 13.98it/s]
 62%|██████▏   | 421/684 [00:33<00:18, 13.98it/s]
 62%|██████▏   | 423/684 [00:33<00:18, 14.01it/s]
 62%|██████▏   | 425/684 [00:33<00:18, 14.01it/s]
 62%|██████▏   | 427/684 [00:33<00:18, 14.01it/s]
 63%|██████▎   | 429/684 [00:33<00:18, 14.02it/s]
 63%|██████▎   | 431/684 [00:33<00:18, 14.01it/s]
 63%|██████▎   | 433/684 [00:33<00:17, 14.01it/s]
 64%|██████▎   | 435/684 [00:34<00:17, 13.99it/s]
 64%|██████▍   | 437/684 [00:34<00:17, 13.97it/s]
 64%|██████▍   | 439/684 [00:34<00:17, 14.00it/s]
 64%|██████▍   | 441/684 [00:34<00:17, 13.98it/s]
 65%|██████▍   | 443/684 [00:34<00:17, 13.99it/s]
 65%|██████▌   | 445/684 [00:34<00:17, 14.00it/s]
 65%|██████▌   | 447/684 [00:34<00:16, 14.01it/s]
 66%|██████▌   | 449/684 [00:35<00:16, 14.01it/s]
 66%|██████▌   | 451/684 [00:35<00:16, 14.02it/s]
 66%|██████▌   | 453/684 [00:35<00:16, 13.99it/s]
 67%|██████▋   | 455/684 [00:35<00:16, 14.00it/s]
 67%|██████▋   | 457/684 [00:38<01:45,  2.16it/s]
 67%|██████▋   | 459/684 [00:38<01:17,  2.89it/s]
 67%|██████▋   | 461/684 [00:38<00:58,  3.79it/s]
 68%|██████▊   | 463/684 [00:38<00:45,  4.82it/s]
 68%|██████▊   | 465/684 [00:38<00:37,  5.87it/s]
 68%|██████▊   | 467/684 [00:39<00:31,  6.95it/s]
 69%|██████▊   | 469/684 [00:39<00:27,  7.95it/s]
 69%|██████▉   | 471/684 [00:39<00:24,  8.86it/s]
 69%|██████▉   | 473/684 [00:39<00:21,  9.72it/s]
 69%|██████▉   | 475/684 [00:39<00:20, 10.45it/s]
 70%|██████▉   | 477/684 [00:39<00:18, 11.14it/s]
 70%|███████   | 479/684 [00:40<00:17, 11.50it/s]
 70%|███████   | 481/684 [00:40<00:16, 12.13it/s]
 71%|███████   | 483/684 [00:40<00:16, 12.41it/s]
 71%|███████   | 485/684 [00:40<00:15, 12.78it/s]
 71%|███████   | 487/684 [00:40<00:15, 12.57it/s]
 71%|███████▏  | 489/684 [00:40<00:15, 12.50it/s]
 72%|███████▏  | 491/684 [00:40<00:14, 12.98it/s]
 72%|███████▏  | 493/684 [00:41<00:14, 12.79it/s]
 72%|███████▏  | 495/684 [00:41<00:14, 13.26it/s]
 73%|███████▎  | 497/684 [00:41<00:14, 12.91it/s]
 73%|███████▎  | 499/684 [00:41<00:14, 13.12it/s]
                                                 
 73%|███████▎  | 500/684 [00:41<00:14, 13.12it/s]
 73%|███████▎  | 501/684 [00:41<00:14, 12.84it/s]
 74%|███████▎  | 503/684 [00:41<00:14, 12.80it/s]
 74%|███████▍  | 505/684 [00:42<00:13, 12.84it/s]
 74%|███████▍  | 507/684 [00:42<00:14, 12.49it/s]
 74%|███████▍  | 509/684 [00:42<00:13, 12.92it/s]
 75%|███████▍  | 511/684 [00:42<00:13, 12.59it/s]
 75%|███████▌  | 513/684 [00:42<00:13, 12.52it/s]
 75%|███████▌  | 515/684 [00:42<00:13, 12.82it/s]
 76%|███████▌  | 517/684 [00:42<00:13, 12.62it/s]
 76%|███████▌  | 519/684 [00:43<00:13, 12.46it/s]
 76%|███████▌  | 521/684 [00:43<00:13, 12.47it/s]
 76%|███████▋  | 523/684 [00:43<00:12, 12.43it/s]
 77%|███████▋  | 525/684 [00:43<00:12, 12.42it/s]
 77%|███████▋  | 527/684 [00:43<00:12, 12.23it/s]
 77%|███████▋  | 529/684 [00:43<00:12, 12.67it/s]
 78%|███████▊  | 531/684 [00:44<00:12, 12.63it/s]
 78%|███████▊  | 533/684 [00:44<00:11, 13.03it/s]
 78%|███████▊  | 535/684 [00:44<00:11, 13.21it/s]
 79%|███████▊  | 537/684 [00:44<00:11, 13.19it/s]
 79%|███████▉  | 539/684 [00:44<00:10, 13.54it/s]
 79%|███████▉  | 541/684 [00:44<00:10, 13.65it/s]
 79%|███████▉  | 543/684 [00:44<00:10, 13.71it/s]
 80%|███████▉  | 545/684 [00:45<00:10, 13.73it/s]
 80%|███████▉  | 547/684 [00:45<00:09, 13.74it/s]
 80%|████████  | 549/684 [00:45<00:09, 13.76it/s]
 81%|████████  | 551/684 [00:45<00:09, 13.79it/s]
 81%|████████  | 553/684 [00:45<00:09, 13.78it/s]
 81%|████████  | 555/684 [00:45<00:09, 13.78it/s]
 81%|████████▏ | 557/684 [00:46<00:09, 13.79it/s]
 82%|████████▏ | 559/684 [00:46<00:09, 13.82it/s]
 82%|████████▏ | 561/684 [00:46<00:08, 13.77it/s]
 82%|████████▏ | 563/684 [00:46<00:08, 13.84it/s]
 83%|████████▎ | 565/684 [00:46<00:08, 13.79it/s]
 83%|████████▎ | 567/684 [00:46<00:08, 13.80it/s]
 83%|████████▎ | 569/684 [00:46<00:08, 13.82it/s]
 83%|████████▎ | 571/684 [00:47<00:08, 13.76it/s]
 84%|████████▍ | 573/684 [00:47<00:08, 13.70it/s]
 84%|████████▍ | 575/684 [00:47<00:07, 13.65it/s]
 84%|████████▍ | 577/684 [00:47<00:07, 13.65it/s]
 85%|████████▍ | 579/684 [00:47<00:07, 13.62it/s]
 85%|████████▍ | 581/684 [00:47<00:07, 13.52it/s]
 85%|████████▌ | 583/684 [00:47<00:07, 13.44it/s]
 86%|████████▌ | 585/684 [00:48<00:07, 13.53it/s]
 86%|████████▌ | 587/684 [00:48<00:07, 13.52it/s]
 86%|████████▌ | 589/684 [00:48<00:07, 13.50it/s]
 86%|████████▋ | 591/684 [00:48<00:06, 13.44it/s]
 87%|████████▋ | 593/684 [00:48<00:06, 13.53it/s]
 87%|████████▋ | 595/684 [00:48<00:06, 13.67it/s]
 87%|████████▋ | 597/684 [00:48<00:06, 13.64it/s]
 88%|████████▊ | 599/684 [00:49<00:06, 13.68it/s]
 88%|████████▊ | 601/684 [00:49<00:06, 13.68it/s]
 88%|████████▊ | 603/684 [00:49<00:05, 13.73it/s]
 88%|████████▊ | 605/684 [00:49<00:05, 13.71it/s]
 89%|████████▊ | 607/684 [00:49<00:05, 13.74it/s]
 89%|████████▉ | 609/684 [00:49<00:05, 13.79it/s]
 89%|████████▉ | 611/684 [00:49<00:05, 13.74it/s]
 90%|████████▉ | 613/684 [00:50<00:05, 13.73it/s]
 90%|████████▉ | 615/684 [00:50<00:05, 13.74it/s]
 90%|█████████ | 617/684 [00:50<00:04, 13.87it/s]
 90%|█████████ | 619/684 [00:50<00:04, 13.93it/s]
 91%|█████████ | 621/684 [00:50<00:04, 13.84it/s]
 91%|█████████ | 623/684 [00:50<00:04, 13.82it/s]
 91%|█████████▏| 625/684 [00:50<00:04, 13.86it/s]
 92%|█████████▏| 627/684 [00:51<00:04, 13.80it/s]
 92%|█████████▏| 629/684 [00:51<00:03, 13.84it/s]
 92%|█████████▏| 631/684 [00:51<00:03, 13.79it/s]
 93%|█████████▎| 633/684 [00:51<00:03, 13.77it/s]
 93%|█████████▎| 635/684 [00:51<00:03, 13.75it/s]
 93%|████████���▎| 637/684 [00:51<00:03, 13.74it/s]
 93%|█████████▎| 639/684 [00:51<00:03, 13.77it/s]
 94%|█████████▎| 641/684 [00:52<00:03, 13.73it/s]
 94%|█████████▍| 643/684 [00:52<00:02, 13.68it/s]
 94%|█████████▍| 645/684 [00:52<00:02, 13.70it/s]
 95%|█████████▍| 647/684 [00:52<00:02, 13.74it/s]
 95%|█████████▍| 649/684 [00:52<00:02, 13.74it/s]
 95%|█████████▌| 651/684 [00:52<00:02, 13.76it/s]
 95%|█████████▌| 653/684 [00:53<00:02, 13.74it/s]
 96%|█████████▌| 655/684 [00:53<00:02, 13.73it/s]
 96%|█████████▌| 657/684 [00:53<00:01, 13.71it/s]
 96%|█████████▋| 659/684 [00:53<00:01, 13.75it/s]
 97%|█████████▋| 661/684 [00:53<00:01, 13.71it/s]
 97%|█████████▋| 663/684 [00:53<00:01, 13.71it/s]
 97%|█████████▋| 665/684 [00:53<00:01, 13.72it/s]
 98%|█████████▊| 667/684 [00:54<00:01, 13.74it/s]
 98%|█████████▊| 669/684 [00:54<00:01, 13.85it/s]
 98%|█████████▊| 671/684 [00:54<00:00, 13.80it/s]
 98%|█████████▊| 673/684 [00:54<00:00, 13.78it/s]
 99%|█████████▊| 675/684 [00:54<00:00, 13.76it/s]
 99%|█████████▉| 677/684 [00:54<00:00, 13.79it/s]
 99%|█████████▉| 679/684 [00:54<00:00, 13.78it/s]
                                                 
+
  0%|          | 0/16 [00:00<?, ?it/s]
 12%|█▎        | 2/16 [00:04<00:30,  2.18s/it]
 19%|█▉        | 3/16 [00:08<00:40,  3.09s/it]
 25%|██▌       | 4/16 [00:13<00:42,  3.55s/it]
 31%|███▏      | 5/16 [00:17<00:42,  3.83s/it]
 38%|███▊      | 6/16 [00:21<00:40,  4.01s/it]
 44%|████▍     | 7/16 [00:26<00:37,  4.12s/it]
 50%|█████     | 8/16 [00:30<00:33,  4.19s/it]
 56%|█████▋    | 9/16 [00:34<00:29,  4.24s/it]
 62%|██████▎   | 10/16 [00:39<00:25,  4.28s/it]
 69%|██████▉   | 11/16 [00:43<00:21,  4.30s/it]
 75%|███████▌  | 12/16 [00:47<00:17,  4.32s/it]
 81%|████████▏ | 13/16 [00:52<00:12,  4.33s/it]
 88%|████████▊ | 14/16 [00:56<00:08,  4.34s/it]
 94%|█████████▍| 15/16 [01:00<00:04,  4.35s/it]
+/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/optimization.py:411: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
+  warnings.warn(
+/mnt/storage/aatherton/hf_eng_fra_trans is already a clone of https://huggingface.co/aatherton2024/hf_eng_fra_trans. Make sure you pull the latest changes with `repo.git_pull()`.
+
  0%|          | 0/2736 [00:00<?, ?it/s]
  0%|          | 1/2736 [00:00<05:01,  9.08it/s]
  0%|          | 3/2736 [00:00<04:14, 10.73it/s]
  0%|          | 5/2736 [00:00<03:59, 11.40it/s]
  0%|          | 7/2736 [00:00<03:56, 11.55it/s]
  0%|          | 9/2736 [00:00<03:53, 11.66it/s]
  0%|          | 11/2736 [00:00<03:53, 11.68it/s]
  0%|          | 13/2736 [00:01<03:51, 11.76it/s]
  1%|          | 15/2736 [00:01<03:51, 11.74it/s]
  1%|          | 17/2736 [00:01<03:49, 11.84it/s]
  1%|          | 19/2736 [00:01<03:49, 11.84it/s]
  1%|          | 21/2736 [00:01<03:49, 11.84it/s]
  1%|          | 23/2736 [00:01<03:50, 11.80it/s]
  1%|          | 25/2736 [00:02<03:48, 11.85it/s]
  1%|          | 27/2736 [00:02<03:46, 11.94it/s]
  1%|          | 29/2736 [00:02<03:43, 12.11it/s]
  1%|          | 31/2736 [00:02<03:41, 12.22it/s]
  1%|          | 33/2736 [00:02<03:39, 12.32it/s]
  1%|▏         | 35/2736 [00:02<03:37, 12.40it/s]
  1%|▏         | 37/2736 [00:03<03:38, 12.38it/s]
  1%|▏         | 39/2736 [00:03<03:36, 12.48it/s]
  1%|▏         | 41/2736 [00:03<03:37, 12.40it/s]
  2%|▏         | 43/2736 [00:03<03:35, 12.47it/s]
  2%|▏         | 45/2736 [00:03<03:34, 12.52it/s]
  2%|▏         | 47/2736 [00:03<03:34, 12.55it/s]
  2%|▏         | 49/2736 [00:04<03:36, 12.42it/s]
  2%|▏         | 51/2736 [00:04<03:35, 12.44it/s]
  2%|▏         | 53/2736 [00:04<03:36, 12.40it/s]
  2%|▏         | 55/2736 [00:04<03:35, 12.46it/s]
  2%|▏         | 57/2736 [00:04<03:35, 12.44it/s]
  2%|▏         | 59/2736 [00:04<03:34, 12.51it/s]
  2%|▏         | 61/2736 [00:05<03:33, 12.53it/s]
  2%|▏         | 63/2736 [00:05<03:34, 12.44it/s]
  2%|▏         | 65/2736 [00:05<03:33, 12.49it/s]
  2%|▏         | 67/2736 [00:05<03:35, 12.40it/s]
  3%|▎         | 69/2736 [00:05<03:33, 12.48it/s]
  3%|▎         | 71/2736 [00:05<03:32, 12.57it/s]
  3%|▎         | 73/2736 [00:05<03:31, 12.59it/s]
  3%|▎         | 75/2736 [00:06<03:30, 12.64it/s]
  3%|▎         | 77/2736 [00:06<03:31, 12.59it/s]
  3%|▎         | 79/2736 [00:06<03:30, 12.63it/s]
  3%|▎         | 81/2736 [00:06<03:31, 12.57it/s]
  3%|▎         | 83/2736 [00:06<03:31, 12.53it/s]
  3%|▎         | 85/2736 [00:06<03:32, 12.45it/s]
  3%|▎         | 87/2736 [00:07<03:31, 12.50it/s]
  3%|▎         | 89/2736 [00:07<03:32, 12.45it/s]
  3%|▎         | 91/2736 [00:07<03:32, 12.43it/s]
  3%|▎         | 93/2736 [00:07<03:34, 12.35it/s]
  3%|▎         | 95/2736 [00:07<03:34, 12.30it/s]
  4%|▎         | 97/2736 [00:07<03:33, 12.38it/s]
  4%|▎         | 99/2736 [00:08<03:34, 12.31it/s]
  4%|▎         | 101/2736 [00:08<03:34, 12.28it/s]
  4%|▍         | 103/2736 [00:08<03:33, 12.36it/s]
  4%|▍         | 105/2736 [00:08<03:31, 12.46it/s]
  4%|▍         | 107/2736 [00:08<03:29, 12.53it/s]
  4%|▍         | 109/2736 [00:08<03:30, 12.50it/s]
  4%|▍         | 111/2736 [00:09<03:29, 12.53it/s]
  4%|▍         | 113/2736 [00:09<03:28, 12.57it/s]
  4%|▍         | 115/2736 [00:09<03:29, 12.54it/s]
  4%|▍         | 117/2736 [00:09<03:27, 12.62it/s]
  4%|▍         | 119/2736 [00:09<03:27, 12.64it/s]
  4%|▍         | 121/2736 [00:09<03:26, 12.64it/s]
  4%|▍         | 123/2736 [00:09<03:26, 12.65it/s]
  5%|▍         | 125/2736 [00:10<03:26, 12.64it/s]
  5%|▍         | 127/2736 [00:10<03:27, 12.56it/s]
  5%|▍         | 129/2736 [00:10<03:27, 12.57it/s]
  5%|▍         | 131/2736 [00:10<03:28, 12.51it/s]
  5%|▍         | 133/2736 [00:10<03:27, 12.52it/s]
  5%|▍         | 135/2736 [00:10<03:29, 12.43it/s]
  5%|▌         | 137/2736 [00:11<03:28, 12.48it/s]
  5%|▌         | 139/2736 [00:11<03:29, 12.41it/s]
  5%|▌         | 141/2736 [00:11<03:27, 12.52it/s]
  5%|▌         | 143/2736 [00:11<03:27, 12.52it/s]
  5%|▌         | 145/2736 [00:11<03:27, 12.47it/s]
  5%|▌         | 147/2736 [00:11<03:26, 12.51it/s]
  5%|▌         | 149/2736 [00:12<03:26, 12.53it/s]
  6%|▌         | 151/2736 [00:12<03:27, 12.49it/s]
  6%|▌         | 153/2736 [00:12<03:25, 12.54it/s]
  6%|▌         | 155/2736 [00:12<03:25, 12.56it/s]
  6%|▌         | 157/2736 [00:12<03:26, 12.49it/s]
  6%|▌         | 159/2736 [00:12<03:25, 12.57it/s]
  6%|▌         | 161/2736 [00:13<03:24, 12.58it/s]
  6%|▌         | 163/2736 [00:13<03:25, 12.50it/s]
  6%|▌         | 165/2736 [00:13<03:25, 12.49it/s]
  6%|▌         | 167/2736 [00:13<03:25, 12.52it/s]
  6%|▌         | 169/2736 [00:13<03:24, 12.54it/s]
  6%|▋         | 171/2736 [00:13<03:24, 12.55it/s]
  6%|▋         | 173/2736 [00:13<03:25, 12.47it/s]
  6%|▋         | 175/2736 [00:14<03:24, 12.51it/s]
  6%|▋         | 177/2736 [00:14<03:25, 12.43it/s]
  7%|▋         | 179/2736 [00:14<03:24, 12.48it/s]
  7%|▋         | 181/2736 [00:14<03:25, 12.41it/s]
  7%|▋         | 183/2736 [00:14<03:24, 12.49it/s]
  7%|▋         | 185/2736 [00:14<03:26, 12.35it/s]
  7%|▋         | 187/2736 [00:15<03:26, 12.33it/s]
  7%|▋         | 189/2736 [00:15<03:25, 12.41it/s]
  7%|▋         | 191/2736 [00:15<03:24, 12.42it/s]
  7%|▋         | 193/2736 [00:15<03:24, 12.46it/s]
  7%|▋         | 195/2736 [00:15<03:23, 12.50it/s]
  7%|▋         | 197/2736 [00:15<03:24, 12.42it/s]
  7%|▋         | 199/2736 [00:16<03:23, 12.48it/s]
  7%|▋         | 201/2736 [00:16<03:23, 12.47it/s]
  7%|▋         | 203/2736 [00:16<03:22, 12.50it/s]
  7%|▋         | 205/2736 [00:16<03:21, 12.59it/s]
  8%|▊         | 207/2736 [00:16<03:22, 12.48it/s]
  8%|▊         | 209/2736 [00:16<03:21, 12.54it/s]
  8%|▊         | 211/2736 [00:17<03:21, 12.53it/s]
  8%|▊         | 213/2736 [00:17<03:21, 12.51it/s]
  8%|▊         | 215/2736 [00:17<03:22, 12.45it/s]
  8%|▊         | 217/2736 [00:17<03:21, 12.50it/s]
  8%|▊         | 219/2736 [00:17<03:20, 12.55it/s]
  8%|▊         | 221/2736 [00:17<03:19, 12.60it/s]
  8%|▊         | 223/2736 [00:17<03:21, 12.50it/s]
  8%|▊         | 225/2736 [00:18<03:19, 12.58it/s]
  8%|▊         | 227/2736 [00:18<03:19, 12.57it/s]
  8%|▊         | 229/2736 [00:18<03:21, 12.47it/s]
  8%|▊         | 231/2736 [00:18<03:19, 12.54it/s]
  9%|▊         | 233/2736 [00:18<03:19, 12.56it/s]
  9%|▊         | 235/2736 [00:18<03:19, 12.51it/s]
  9%|▊         | 237/2736 [00:19<03:19, 12.52it/s]
  9%|▊         | 239/2736 [00:19<03:18, 12.57it/s]
  9%|▉         | 241/2736 [00:19<03:20, 12.47it/s]
  9%|▉         | 243/2736 [00:19<03:19, 12.52it/s]
  9%|▉         | 245/2736 [00:19<03:20, 12.45it/s]
  9%|▉         | 247/2736 [00:19<03:18, 12.55it/s]
  9%|▉         | 249/2736 [00:20<03:18, 12.55it/s]
  9%|▉         | 251/2736 [00:20<03:18, 12.54it/s]
  9%|▉         | 253/2736 [00:20<03:17, 12.56it/s]
  9%|▉         | 255/2736 [00:20<03:17, 12.56it/s]
  9%|▉         | 257/2736 [00:20<03:17, 12.58it/s]
  9%|▉         | 259/2736 [00:20<03:17, 12.54it/s]
 10%|▉         | 261/2736 [00:21<03:17, 12.52it/s]
 10%|▉         | 263/2736 [00:21<03:17, 12.55it/s]
 10%|▉         | 265/2736 [00:21<03:18, 12.44it/s]
 10%|▉         | 267/2736 [00:21<03:17, 12.51it/s]
 10%|▉         | 269/2736 [00:21<03:18, 12.41it/s]
 10%|▉         | 271/2736 [00:21<03:17, 12.48it/s]
 10%|▉         | 273/2736 [00:21<03:17, 12.48it/s]
 10%|█         | 275/2736 [00:22<03:17, 12.43it/s]
 10%|█         | 277/2736 [00:22<03:16, 12.51it/s]
 10%|█         | 279/2736 [00:22<03:16, 12.50it/s]
 10%|█         | 281/2736 [00:22<03:17, 12.44it/s]
 10%|█         | 283/2736 [00:22<03:16, 12.48it/s]
 10%|█         | 285/2736 [00:22<03:17, 12.43it/s]
 10%|█         | 287/2736 [00:23<03:15, 12.50it/s]
 11%|█         | 289/2736 [00:23<03:16, 12.43it/s]
 11%|█         | 291/2736 [00:23<03:15, 12.53it/s]
 11%|█         | 293/2736 [00:23<03:17, 12.38it/s]
 11%|█         | 295/2736 [00:23<03:15, 12.47it/s]
 11%|█         | 297/2736 [00:23<03:14, 12.51it/s]
 11%|█         | 299/2736 [00:24<03:15, 12.50it/s]
 11%|█         | 301/2736 [00:24<03:16, 12.39it/s]
 11%|█         | 303/2736 [00:24<03:14, 12.50it/s]
 11%|█         | 305/2736 [00:24<03:15, 12.45it/s]
 11%|█         | 307/2736 [00:24<03:14, 12.47it/s]
 11%|█▏        | 309/2736 [00:24<03:14, 12.50it/s]
 11%|█▏        | 311/2736 [00:25<03:14, 12.47it/s]
 11%|█▏        | 313/2736 [00:25<03:13, 12.50it/s]
 12%|█▏        | 315/2736 [00:25<03:13, 12.49it/s]
 12%|█▏        | 317/2736 [00:25<03:13, 12.49it/s]
 12%|█▏        | 319/2736 [00:25<03:12, 12.55it/s]
 12%|█▏        | 321/2736 [00:25<03:13, 12.45it/s]
 12%|█▏        | 323/2736 [00:25<03:13, 12.48it/s]
 12%|█▏        | 325/2736 [00:26<03:14, 12.38it/s]
 12%|█▏        | 327/2736 [00:26<03:15, 12.33it/s]
 12%|█▏        | 329/2736 [00:26<03:13, 12.44it/s]
 12%|█▏        | 331/2736 [00:26<03:12, 12.49it/s]
 12%|█▏        | 333/2736 [00:26<03:12, 12.46it/s]
 12%|█▏        | 335/2736 [00:26<03:12, 12.45it/s]
 12%|█▏        | 337/2736 [00:27<03:12, 12.49it/s]
 12%|█▏        | 339/2736 [00:27<03:10, 12.56it/s]
 12%|█▏        | 341/2736 [00:27<03:10, 12.57it/s]
 13%|█▎        | 343/2736 [00:27<03:11, 12.50it/s]
 13%|█▎        | 345/2736 [00:27<03:10, 12.55it/s]
 13%|█▎        | 347/2736 [00:27<03:10, 12.57it/s]
 13%|█▎        | 349/2736 [00:28<03:10, 12.50it/s]
 13%|█▎        | 351/2736 [00:28<03:10, 12.54it/s]
 13%|█▎        | 353/2736 [00:28<03:11, 12.46it/s]
 13%|█▎        | 355/2736 [00:28<03:10, 12.53it/s]
 13%|█▎        | 357/2736 [00:28<03:10, 12.49it/s]
 13%|█▎        | 359/2736 [00:28<03:09, 12.57it/s]
 13%|█▎        | 361/2736 [00:29<03:09, 12.53it/s]
 13%|█▎        | 363/2736 [00:29<03:08, 12.57it/s]
 13%|█▎        | 365/2736 [00:29<03:08, 12.57it/s]
 13%|█▎        | 367/2736 [00:29<03:09, 12.49it/s]
 13%|█▎        | 369/2736 [00:29<03:09, 12.52it/s]
 14%|█▎        | 371/2736 [00:29<03:09, 12.49it/s]
 14%|█▎        | 373/2736 [00:29<03:08, 12.51it/s]
 14%|█▎        | 375/2736 [00:30<03:08, 12.55it/s]
 14%|█▍        | 377/2736 [00:30<03:08, 12.50it/s]
 14%|█▍        | 379/2736 [00:30<03:08, 12.47it/s]
 14%|█▍        | 381/2736 [00:30<03:08, 12.51it/s]
 14%|█▍        | 383/2736 [00:30<03:07, 12.58it/s]
 14%|█▍        | 385/2736 [00:30<03:06, 12.58it/s]
 14%|█▍        | 387/2736 [00:31<03:07, 12.51it/s]
 14%|█▍        | 389/2736 [00:31<03:07, 12.55it/s]
 14%|█▍        | 391/2736 [00:31<03:07, 12.53it/s]
 14%|█▍        | 393/2736 [00:31<03:06, 12.54it/s]
 14%|█▍        | 395/2736 [00:31<03:05, 12.60it/s]
 15%|█▍        | 397/2736 [00:31<03:05, 12.60it/s]
 15%|█▍        | 399/2736 [00:32<03:06, 12.56it/s]
 15%|█▍        | 401/2736 [00:32<03:05, 12.57it/s]
 15%|█▍        | 403/2736 [00:32<03:06, 12.53it/s]
 15%|█▍        | 405/2736 [00:32<03:05, 12.54it/s]
 15%|█▍        | 407/2736 [00:32<03:05, 12.57it/s]
 15%|█▍        | 409/2736 [00:32<03:06, 12.50it/s]
 15%|█▌        | 411/2736 [00:33<03:05, 12.55it/s]
 15%|█▌        | 413/2736 [00:33<03:04, 12.60it/s]
 15%|█▌        | 415/2736 [00:33<03:06, 12.45it/s]
 15%|█▌        | 417/2736 [00:33<03:06, 12.40it/s]
 15%|█▌        | 419/2736 [00:33<03:05, 12.46it/s]
 15%|█▌        | 421/2736 [00:33<03:05, 12.50it/s]
 15%|█▌        | 423/2736 [00:33<03:06, 12.41it/s]
 16%|█▌        | 425/2736 [00:34<03:05, 12.46it/s]
 16%|█▌        | 427/2736 [00:34<03:05, 12.41it/s]
 16%|█▌        | 429/2736 [00:34<03:04, 12.48it/s]
 16%|█▌        | 431/2736 [00:34<03:05, 12.40it/s]
 16%|█▌        | 433/2736 [00:34<03:04, 12.49it/s]
 16%|█▌        | 435/2736 [00:34<03:04, 12.47it/s]
 16%|█▌        | 437/2736 [00:35<03:03, 12.51it/s]
 16%|█▌        | 439/2736 [00:35<03:03, 12.53it/s]
 16%|█▌        | 441/2736 [00:35<03:02, 12.54it/s]
 16%|█▌        | 443/2736 [00:35<03:03, 12.48it/s]
 16%|█▋        | 445/2736 [00:35<03:02, 12.55it/s]
 16%|█▋        | 447/2736 [00:35<03:02, 12.54it/s]
 16%|█▋        | 449/2736 [00:36<03:02, 12.50it/s]
 16%|█▋        | 451/2736 [00:36<03:01, 12.56it/s]
 17%|█▋        | 453/2736 [00:36<03:03, 12.46it/s]
 17%|█▋        | 455/2736 [00:36<03:02, 12.51it/s]
 17%|█▋        | 457/2736 [00:36<03:01, 12.53it/s]
 17%|█▋        | 459/2736 [00:36<03:02, 12.48it/s]
 17%|█▋        | 461/2736 [00:37<03:01, 12.52it/s]
 17%|█▋        | 463/2736 [00:37<03:00, 12.57it/s]
 17%|█▋        | 465/2736 [00:37<03:02, 12.48it/s]
 17%|█▋        | 467/2736 [00:37<03:00, 12.56it/s]
 17%|█▋        | 469/2736 [00:37<03:00, 12.55it/s]
 17%|█▋        | 471/2736 [00:37<02:59, 12.62it/s]
 17%|█▋        | 473/2736 [00:37<02:58, 12.65it/s]
 17%|█▋        | 475/2736 [00:38<02:58, 12.69it/s]
 17%|█▋        | 477/2736 [00:38<02:58, 12.64it/s]
 18%|█▊        | 479/2736 [00:38<02:59, 12.56it/s]
 18%|█▊        | 481/2736 [00:38<02:59, 12.55it/s]
 18%|█▊        | 483/2736 [00:38<02:59, 12.55it/s]
 18%|█▊        | 485/2736 [00:38<02:59, 12.57it/s]
 18%|█▊        | 487/2736 [00:39<02:58, 12.60it/s]
 18%|█▊        | 489/2736 [00:39<02:57, 12.63it/s]
 18%|█▊        | 491/2736 [00:39<02:58, 12.56it/s]
 18%|█▊        | 493/2736 [00:39<02:58, 12.55it/s]
 18%|█▊        | 495/2736 [00:39<02:57, 12.60it/s]
 18%|█▊        | 497/2736 [00:39<02:59, 12.48it/s]
 18%|█▊        | 499/2736 [00:40<02:58, 12.56it/s]
 18%|█▊        | 501/2736 [00:40<02:59, 12.44it/s]
 18%|█▊        | 503/2736 [00:40<02:59, 12.44it/s]
 18%|█▊        | 505/2736 [00:40<02:58, 12.48it/s]
 19%|█▊        | 507/2736 [00:40<02:57, 12.53it/s]
 19%|█▊        | 509/2736 [00:40<02:59, 12.38it/s]
 19%|█▊        | 511/2736 [00:41<02:58, 12.44it/s]
 19%|█▉        | 513/2736 [00:41<02:59, 12.42it/s]
 19%|█▉        | 515/2736 [00:41<02:58, 12.44it/s]
 19%|█▉        | 517/2736 [00:41<02:58, 12.41it/s]
 19%|█▉        | 519/2736 [00:41<02:58, 12.40it/s]
 19%|█▉        | 521/2736 [00:41<02:58, 12.44it/s]
 19%|█▉        | 523/2736 [00:41<02:56, 12.52it/s]
 19%|█▉        | 525/2736 [00:42<02:56, 12.54it/s]
 19%|█▉        | 527/2736 [00:42<02:57, 12.46it/s]
 19%|█▉        | 529/2736 [00:42<02:56, 12.54it/s]
 19%|█▉        | 531/2736 [00:42<02:57, 12.45it/s]
 19%|█▉        | 533/2736 [00:42<02:55, 12.52it/s]
 20%|█▉        | 535/2736 [00:42<02:55, 12.55it/s]
 20%|█▉        | 537/2736 [00:43<02:56, 12.48it/s]
 20%|█▉        | 539/2736 [00:43<02:55, 12.53it/s]
 20%|█▉        | 541/2736 [00:43<02:56, 12.46it/s]
 20%|█▉        | 543/2736 [00:43<02:55, 12.52it/s]
 20%|█▉        | 545/2736 [00:43<02:55, 12.46it/s]
 20%|█▉        | 547/2736 [00:43<02:54, 12.54it/s]
 20%|██        | 549/2736 [00:44<02:54, 12.53it/s]
 20%|██        | 551/2736 [00:44<02:55, 12.48it/s]
 20%|██        | 553/2736 [00:44<02:54, 12.48it/s]
 20%|██        | 555/2736 [00:44<02:55, 12.42it/s]
 20%|██        | 557/2736 [00:44<02:54, 12.51it/s]
 20%|██        | 559/2736 [00:44<02:55, 12.44it/s]
 21%|██        | 561/2736 [00:45<02:54, 12.49it/s]
 21%|██        | 563/2736 [00:45<02:54, 12.42it/s]
 21%|██        | 565/2736 [00:45<02:53, 12.50it/s]
 21%|██        | 567/2736 [00:45<02:52, 12.57it/s]
 21%|██        | 569/2736 [00:45<02:53, 12.52it/s]
 21%|██        | 571/2736 [00:45<02:52, 12.53it/s]
 21%|██        | 573/2736 [00:45<02:52, 12.52it/s]
 21%|██        | 575/2736 [00:46<02:51, 12.62it/s]
 21%|██        | 577/2736 [00:46<02:52, 12.52it/s]
 21%|██        | 579/2736 [00:46<02:51, 12.56it/s]
 21%|██        | 581/2736 [00:46<02:52, 12.46it/s]
 21%|██▏       | 583/2736 [00:46<02:53, 12.44it/s]
 21%|██▏       | 585/2736 [00:46<02:51, 12.51it/s]
 21%|██▏       | 587/2736 [00:47<02:51, 12.52it/s]
 22%|██▏       | 589/2736 [00:47<02:50, 12.59it/s]
 22%|██▏       | 591/2736 [00:47<02:51, 12.49it/s]
 22%|██▏       | 593/2736 [00:47<02:51, 12.53it/s]
 22%|██▏       | 595/2736 [00:47<02:51, 12.46it/s]
 22%|██▏       | 597/2736 [00:47<02:50, 12.52it/s]
 22%|██▏       | 599/2736 [00:48<02:50, 12.52it/s]
 22%|██▏       | 601/2736 [00:48<02:51, 12.46it/s]
 22%|██▏       | 603/2736 [00:48<02:50, 12.51it/s]
 22%|██▏       | 605/2736 [00:48<02:51, 12.46it/s]
 22%|██▏       | 607/2736 [00:48<02:50, 12.52it/s]
 22%|██▏       | 609/2736 [00:48<02:50, 12.48it/s]
 22%|██▏       | 611/2736 [00:49<02:50, 12.49it/s]
 22%|██▏       | 613/2736 [00:49<02:50, 12.42it/s]
 22%|██▏       | 615/2736 [00:49<02:50, 12.47it/s]
 23%|██▎       | 617/2736 [00:49<02:49, 12.52it/s]
 23%|██▎       | 619/2736 [00:49<02:49, 12.47it/s]
 23%|██▎       | 621/2736 [00:49<02:48, 12.53it/s]
 23%|██▎       | 623/2736 [00:49<02:50, 12.43it/s]
 23%|██▎       | 625/2736 [00:50<02:48, 12.51it/s]
 23%|██▎       | 627/2736 [00:50<02:48, 12.53it/s]
 23%|██▎       | 629/2736 [00:50<02:48, 12.47it/s]
 23%|██▎       | 631/2736 [00:50<02:48, 12.51it/s]
 23%|██▎       | 633/2736 [00:50<02:48, 12.47it/s]
 23%|██▎       | 635/2736 [00:50<02:48, 12.45it/s]
 23%|██▎       | 637/2736 [00:51<02:48, 12.47it/s]
 23%|██▎       | 639/2736 [00:51<02:49, 12.40it/s]
 23%|██▎       | 641/2736 [00:51<02:47, 12.49it/s]
 24%|██▎       | 643/2736 [00:51<02:48, 12.44it/s]
 24%|██▎       | 645/2736 [00:51<02:47, 12.49it/s]
 24%|██▎       | 647/2736 [00:51<02:46, 12.54it/s]
 24%|██▎       | 649/2736 [00:52<02:46, 12.50it/s]
 24%|██▍       | 651/2736 [00:52<02:46, 12.56it/s]
 24%|██▍       | 653/2736 [00:52<02:46, 12.54it/s]
 24%|██▍       | 655/2736 [00:52<02:46, 12.49it/s]
 24%|██▍       | 657/2736 [00:52<02:45, 12.54it/s]
 24%|██▍       | 659/2736 [00:52<02:46, 12.45it/s]
 24%|██▍       | 661/2736 [00:53<02:46, 12.50it/s]
 24%|██▍       | 663/2736 [00:53<02:45, 12.53it/s]
 24%|██▍       | 665/2736 [00:53<02:46, 12.46it/s]
 24%|██▍       | 667/2736 [00:53<02:45, 12.53it/s]
 24%|██▍       | 669/2736 [00:53<02:46, 12.44it/s]
 25%|██▍       | 671/2736 [00:53<02:45, 12.50it/s]
 25%|██▍       | 673/2736 [00:53<02:44, 12.55it/s]
 25%|██▍       | 675/2736 [00:54<02:45, 12.47it/s]
 25%|██▍       | 677/2736 [00:54<02:44, 12.51it/s]
 25%|██▍       | 679/2736 [00:54<02:45, 12.45it/s]
 25%|██▍       | 681/2736 [00:54<02:44, 12.53it/s]
 25%|██▍       | 683/2736 [00:54<02:44, 12.45it/s]
 25%|██▌       | 685/2736 [00:54<02:44, 12.51it/s]
 25%|██▌       | 687/2736 [00:55<02:43, 12.50it/s]
 25%|██▌       | 689/2736 [00:55<02:43, 12.50it/s]
 25%|██▌       | 691/2736 [00:55<02:43, 12.53it/s]
 25%|██▌       | 693/2736 [00:55<02:44, 12.46it/s]
 25%|██▌       | 695/2736 [00:55<02:43, 12.51it/s]
 25%|██▌       | 697/2736 [00:55<02:44, 12.43it/s]
 26%|██▌       | 699/2736 [00:56<02:42, 12.52it/s]
 26%|██▌       | 701/2736 [00:56<02:43, 12.44it/s]
 26%|██▌       | 703/2736 [00:56<02:42, 12.54it/s]
 26%|██▌       | 705/2736 [00:56<02:42, 12.50it/s]
 26%|██▌       | 707/2736 [00:56<02:41, 12.53it/s]
 26%|██▌       | 709/2736 [00:56<02:41, 12.58it/s]
 26%|██▌       | 711/2736 [00:57<02:41, 12.55it/s]
 26%|██▌       | 713/2736 [00:57<02:42, 12.49it/s]
 26%|██▌       | 715/2736 [00:57<02:41, 12.52it/s]
 26%|██▌       | 717/2736 [00:57<02:41, 12.47it/s]
 26%|██▋       | 719/2736 [00:57<02:40, 12.55it/s]
 26%|██▋       | 721/2736 [00:57<02:41, 12.47it/s]
 26%|██▋       | 723/2736 [00:57<02:40, 12.53it/s]
 26%|██▋       | 725/2736 [00:58<02:41, 12.46it/s]
 27%|██▋       | 727/2736 [00:58<02:40, 12.52it/s]
 27%|██▋       | 729/2736 [00:58<02:40, 12.49it/s]
 27%|██▋       | 731/2736 [00:58<02:40, 12.52it/s]
 27%|██▋       | 733/2736 [00:58<02:39, 12.58it/s]
 27%|██▋       | 735/2736 [00:58<02:40, 12.49it/s]
 27%|██▋       | 737/2736 [00:59<02:39, 12.53it/s]
 27%|██▋       | 739/2736 [00:59<02:39, 12.55it/s]
 27%|██▋       | 741/2736 [00:59<02:39, 12.50it/s]
 27%|██▋       | 743/2736 [00:59<02:38, 12.56it/s]
 27%|██▋       | 745/2736 [00:59<02:39, 12.51it/s]
 27%|██▋       | 747/2736 [00:59<02:38, 12.52it/s]
 27%|██▋       | 749/2736 [01:00<02:37, 12.59it/s]
 27%|██▋       | 751/2736 [01:00<02:38, 12.54it/s]
 28%|██▊       | 753/2736 [01:00<02:37, 12.59it/s]
 28%|██▊       | 755/2736 [01:00<02:36, 12.62it/s]
 28%|██▊       | 757/2736 [01:00<02:38, 12.51it/s]
 28%|██▊       | 759/2736 [01:00<02:37, 12.55it/s]
 28%|██▊       | 761/2736 [01:01<02:37, 12.52it/s]
 28%|██▊       | 763/2736 [01:01<02:37, 12.57it/s]
 28%|██▊       | 765/2736 [01:01<02:36, 12.61it/s]
 28%|██▊       | 767/2736 [01:01<02:35, 12.63it/s]
 28%|██▊       | 769/2736 [01:01<02:37, 12.50it/s]
 28%|██▊       | 771/2736 [01:01<02:36, 12.58it/s]
 28%|██▊       | 773/2736 [01:01<02:37, 12.50it/s]
 28%|██▊       | 775/2736 [01:02<02:36, 12.55it/s]
 28%|██▊       | 777/2736 [01:02<02:37, 12.42it/s]
 28%|██▊       | 779/2736 [01:02<02:36, 12.51it/s]
 29%|██▊       | 781/2736 [01:02<02:37, 12.44it/s]
 29%|██▊       | 783/2736 [01:02<02:36, 12.51it/s]
 29%|██▊       | 785/2736 [01:02<02:35, 12.56it/s]
 29%|██▉       | 787/2736 [01:03<02:36, 12.49it/s]
 29%|██▉       | 789/2736 [01:03<02:35, 12.50it/s]
 29%|██▉       | 791/2736 [01:03<02:36, 12.43it/s]
 29%|██▉       | 793/2736 [01:03<02:35, 12.51it/s]
 29%|██▉       | 795/2736 [01:03<02:35, 12.44it/s]
 29%|██▉       | 797/2736 [01:03<02:35, 12.49it/s]
 29%|██▉       | 799/2736 [01:04<02:34, 12.56it/s]
 29%|██▉       | 801/2736 [01:04<02:34, 12.49it/s]
 29%|██▉       | 803/2736 [01:04<02:34, 12.54it/s]
 29%|██▉       | 805/2736 [01:04<02:33, 12.55it/s]
 29%|██▉       | 807/2736 [01:04<02:34, 12.49it/s]
 30%|██▉       | 809/2736 [01:04<02:33, 12.57it/s]
 30%|██▉       | 811/2736 [01:05<02:33, 12.53it/s]
 30%|██▉       | 813/2736 [01:05<02:32, 12.59it/s]
 30%|██▉       | 815/2736 [01:05<02:32, 12.58it/s]
 30%|██▉       | 817/2736 [01:05<02:32, 12.59it/s]
 30%|██▉       | 819/2736 [01:05<02:32, 12.53it/s]
 30%|███       | 821/2736 [01:05<02:32, 12.54it/s]
 30%|███       | 823/2736 [01:05<02:32, 12.58it/s]
 30%|███       | 825/2736 [01:06<02:32, 12.52it/s]
 30%|███       | 827/2736 [01:06<02:31, 12.56it/s]
 30%|███       | 829/2736 [01:06<02:31, 12.60it/s]
 30%|███       | 831/2736 [01:06<02:31, 12.58it/s]
 30%|███       | 833/2736 [01:06<02:31, 12.59it/s]
 31%|███       | 835/2736 [01:06<02:30, 12.62it/s]
 31%|███       | 837/2736 [01:07<02:30, 12.63it/s]
 31%|███       | 839/2736 [01:07<02:30, 12.61it/s]
 31%|███       | 841/2736 [01:07<02:30, 12.60it/s]
 31%|███       | 843/2736 [01:07<02:30, 12.57it/s]
 31%|███       | 845/2736 [01:07<02:29, 12.62it/s]
 31%|███       | 847/2736 [01:07<02:30, 12.53it/s]
 31%|███       | 849/2736 [01:08<02:30, 12.52it/s]
 31%|███       | 851/2736 [01:08<02:29, 12.59it/s]
 31%|███       | 853/2736 [01:08<02:29, 12.58it/s]
 31%|███▏      | 855/2736 [01:08<02:29, 12.60it/s]
 31%|███▏      | 857/2736 [01:08<02:29, 12.61it/s]
 31%|███▏      | 859/2736 [01:08<02:28, 12.61it/s]
 31%|███▏      | 861/2736 [01:08<02:28, 12.62it/s]
 32%|███▏      | 863/2736 [01:09<02:29, 12.52it/s]
 32%|███▏      | 865/2736 [01:09<02:29, 12.55it/s]
 32%|███▏      | 867/2736 [01:09<02:29, 12.52it/s]
 32%|███▏      | 869/2736 [01:09<02:28, 12.55it/s]
 32%|███▏      | 871/2736 [01:09<02:28, 12.59it/s]
 32%|███▏      | 873/2736 [01:09<02:29, 12.50it/s]
 32%|███▏      | 875/2736 [01:10<02:27, 12.58it/s]
 32%|███▏      | 877/2736 [01:10<02:28, 12.48it/s]
 32%|███▏      | 879/2736 [01:10<02:28, 12.53it/s]
 32%|███▏      | 881/2736 [01:10<02:29, 12.44it/s]
 32%|███▏      | 883/2736 [01:10<02:28, 12.50it/s]
 32%|███▏      | 885/2736 [01:10<02:27, 12.52it/s]
 32%|███▏      | 887/2736 [01:11<02:28, 12.46it/s]
 32%|███▏      | 889/2736 [01:11<02:27, 12.56it/s]
 33%|███▎      | 891/2736 [01:11<02:27, 12.54it/s]
 33%|███▎      | 893/2736 [01:11<02:27, 12.50it/s]
 33%|███▎      | 895/2736 [01:11<02:26, 12.55it/s]
 33%|███▎      | 897/2736 [01:11<02:26, 12.52it/s]
 33%|███▎      | 899/2736 [01:12<02:26, 12.54it/s]
 33%|███▎      | 901/2736 [01:12<02:25, 12.61it/s]
 33%|███▎      | 903/2736 [01:12<02:26, 12.51it/s]
 33%|███▎      | 905/2736 [01:12<02:26, 12.53it/s]
 33%|███▎      | 907/2736 [01:12<02:26, 12.51it/s]
 33%|███▎      | 909/2736 [01:12<02:25, 12.53it/s]
 33%|███▎      | 911/2736 [01:12<02:25, 12.57it/s]
+
  0%|          | 0/126 [00:00<?, ?it/s]
+
  1%|          | 1/126 [00:01<02:48,  1.35s/it]
+
  2%|▏         | 2/126 [00:02<02:41,  1.30s/it]
+
  2%|▏         | 3/126 [00:03<02:36,  1.27s/it]
+
  3%|▎         | 4/126 [00:05<02:33,  1.26s/it]
+
  4%|▍         | 5/126 [00:06<02:31,  1.25s/it]
+
  5%|▍         | 6/126 [00:07<02:29,  1.24s/it]
+
  6%|▌         | 7/126 [00:08<02:27,  1.24s/it]
+
  6%|▋         | 8/126 [00:10<02:25,  1.24s/it]
+
  7%|▋         | 9/126 [00:11<02:24,  1.23s/it]
+
  8%|▊         | 10/126 [00:12<02:23,  1.23s/it]
+
  9%|▊         | 11/126 [00:13<02:21,  1.23s/it]
 33%|███▎      | 912/2736 [01:27<02:25, 12.57it/s]
+
 10%|▉         | 12/126 [00:14<02:20,  1.23s/it]
+
 10%|█         | 13/126 [00:16<02:19,  1.23s/it]
+
 11%|█         | 14/126 [00:17<02:17,  1.23s/it]
+
 12%|█▏        | 15/126 [00:18<02:16,  1.23s/it]
+
 13%|█▎        | 16/126 [00:19<02:15,  1.23s/it]
+
 13%|█▎        | 17/126 [00:21<02:14,  1.23s/it]
+
 14%|█▍        | 18/126 [00:22<02:13,  1.23s/it]
+
 15%|█▌        | 19/126 [00:23<02:11,  1.23s/it]
+
 16%|█▌        | 20/126 [00:24<02:10,  1.23s/it]
+
 17%|█▋        | 21/126 [00:26<02:09,  1.23s/it]
+
 17%|█▋        | 22/126 [00:27<02:07,  1.23s/it]
+
 18%|█▊        | 23/126 [00:28<02:06,  1.23s/it]
+
 19%|█▉        | 24/126 [00:29<02:05,  1.23s/it]
+
 20%|█▉        | 25/126 [00:30<02:04,  1.23s/it]
+
 21%|██        | 26/126 [00:32<02:03,  1.23s/it]
+
 21%|██▏       | 27/126 [00:33<02:02,  1.23s/it]
+
 22%|██▏       | 28/126 [00:34<02:00,  1.23s/it]
+
 23%|██▎       | 29/126 [00:35<01:59,  1.23s/it]
+
 24%|██▍       | 30/126 [00:37<01:57,  1.23s/it]
+
 25%|██▍       | 31/126 [00:38<01:56,  1.23s/it]
+
 25%|██▌       | 32/126 [00:39<01:55,  1.23s/it]
+
 26%|██▌       | 33/126 [00:40<01:54,  1.23s/it]
+
 27%|██▋       | 34/126 [00:42<01:53,  1.23s/it]
+
 28%|██▊       | 35/126 [00:43<01:52,  1.23s/it]
+
 29%|██▊       | 36/126 [00:44<01:50,  1.23s/it]
+
 29%|██▉       | 37/126 [00:45<01:49,  1.23s/it]
+
 30%|███       | 38/126 [00:46<01:48,  1.23s/it]
+
 31%|███       | 39/126 [00:48<01:47,  1.24s/it]
+
 32%|███▏      | 40/126 [00:49<01:46,  1.24s/it]
+
 33%|███▎      | 41/126 [00:50<01:44,  1.24s/it]
+
 33%|███▎      | 42/126 [00:51<01:43,  1.23s/it]
+
 34%|███▍      | 43/126 [00:53<01:42,  1.23s/it]
+
 35%|███▍      | 44/126 [00:54<01:40,  1.23s/it]
+
 36%|███▌      | 45/126 [00:55<01:39,  1.23s/it]
+
 37%|███▋      | 46/126 [00:56<01:38,  1.23s/it]
+
 37%|███▋      | 47/126 [00:58<01:37,  1.23s/it]
+
 38%|███▊      | 48/126 [00:59<01:35,  1.23s/it]
+
 39%|███▉      | 49/126 [01:00<01:34,  1.23s/it]
+
 40%|███▉      | 50/126 [01:01<01:33,  1.23s/it]
+
 40%|████      | 51/126 [01:02<01:32,  1.23s/it]
+
 41%|████▏     | 52/126 [01:04<01:30,  1.23s/it]
+
 42%|████▏     | 53/126 [01:05<01:29,  1.23s/it]
+
 43%|████▎     | 54/126 [01:06<01:28,  1.23s/it]
+
 44%|████▎     | 55/126 [01:07<01:27,  1.23s/it]
+
 44%|████▍     | 56/126 [01:09<01:26,  1.23s/it]
+
 45%|████▌     | 57/126 [01:10<01:24,  1.23s/it]
+
 46%|████▌     | 58/126 [01:11<01:23,  1.23s/it]
+
 47%|████▋     | 59/126 [01:12<01:22,  1.23s/it]
+
 48%|████▊     | 60/126 [01:14<01:21,  1.23s/it]
+
 48%|████▊     | 61/126 [01:15<01:19,  1.23s/it]
+
 49%|████▉     | 62/126 [01:16<01:18,  1.23s/it]
+
 50%|█████     | 63/126 [01:17<01:17,  1.23s/it]
+
 51%|█████     | 64/126 [01:18<01:16,  1.23s/it]
+
 52%|█████▏    | 65/126 [01:20<01:14,  1.23s/it]
+
 52%|█████▏    | 66/126 [01:21<01:13,  1.23s/it]
+
 53%|█████▎    | 67/126 [01:22<01:12,  1.23s/it]
+
 54%|█████▍    | 68/126 [01:23<01:11,  1.23s/it]
+
 55%|█████▍    | 69/126 [01:25<01:10,  1.23s/it]
+
 56%|█████▌    | 70/126 [01:26<01:08,  1.23s/it]
+
 56%|█████▋    | 71/126 [01:27<01:07,  1.23s/it]
+
 57%|█████▋    | 72/126 [01:28<01:06,  1.23s/it]
+
 58%|█████▊    | 73/126 [01:30<01:05,  1.23s/it]
+
 59%|█████▊    | 74/126 [01:31<01:04,  1.23s/it]
+
 60%|█████▉    | 75/126 [01:32<01:02,  1.23s/it]
+
 60%|██████    | 76/126 [01:33<01:01,  1.23s/it]
+
 61%|██████    | 77/126 [01:34<01:00,  1.23s/it]
+
 62%|██████▏   | 78/126 [01:36<00:59,  1.23s/it]
+
 63%|██████▎   | 79/126 [01:37<00:57,  1.23s/it]
+
 63%|██████▎   | 80/126 [01:38<00:56,  1.23s/it]
+
 64%|██████▍   | 81/126 [01:39<00:55,  1.23s/it]
+
 65%|██████▌   | 82/126 [01:41<00:54,  1.23s/it]
+
 66%|██████▌   | 83/126 [01:42<00:52,  1.23s/it]
+
 67%|██████▋   | 84/126 [01:43<00:51,  1.23s/it]
+
 67%|██████▋   | 85/126 [01:44<00:50,  1.23s/it]
+
 68%|██████▊   | 86/126 [01:46<00:49,  1.23s/it]
+
 69%|██████▉   | 87/126 [01:47<00:47,  1.23s/it]
+
 70%|██████▉   | 88/126 [01:48<00:46,  1.23s/it]
+
 71%|███████   | 89/126 [01:49<00:45,  1.23s/it]
+
 71%|███████▏  | 90/126 [01:50<00:44,  1.23s/it]
+
 72%|███████▏  | 91/126 [01:52<00:43,  1.23s/it]
+
 73%|███████▎  | 92/126 [01:53<00:41,  1.23s/it]
+
 74%|███████▍  | 93/126 [01:54<00:40,  1.23s/it]
+
 75%|███████▍  | 94/126 [01:55<00:39,  1.23s/it]
+
 75%|███████▌  | 95/126 [01:57<00:38,  1.23s/it]
+
 76%|███████▌  | 96/126 [01:58<00:36,  1.23s/it]
+
 77%|███████▋  | 97/126 [01:59<00:35,  1.23s/it]
+
 78%|███████▊  | 98/126 [02:00<00:34,  1.23s/it]
+
 79%|███████▊  | 99/126 [02:02<00:33,  1.23s/it]
+
 79%|███████▉  | 100/126 [02:03<00:31,  1.23s/it]
+
 80%|████████  | 101/126 [02:04<00:30,  1.23s/it]
+
 81%|████████  | 102/126 [02:05<00:29,  1.23s/it]
+
 82%|████████▏ | 103/126 [02:06<00:28,  1.23s/it]
+
 83%|████████▎ | 104/126 [02:08<00:27,  1.23s/it]
+
 83%|████████▎ | 105/126 [02:09<00:25,  1.23s/it]
+
 84%|████████▍ | 106/126 [02:10<00:24,  1.23s/it]
+
 85%|████████▍ | 107/126 [02:11<00:23,  1.23s/it]
+
 86%|████████▌ | 108/126 [02:13<00:22,  1.23s/it]
+
 87%|████████▋ | 109/126 [02:14<00:20,  1.23s/it]
+
 87%|████████▋ | 110/126 [02:15<00:19,  1.23s/it]
+
 88%|████████▊ | 111/126 [02:16<00:18,  1.23s/it]
+
 89%|████████▉ | 112/126 [02:18<00:17,  1.23s/it]
+
 90%|████████▉ | 113/126 [02:19<00:16,  1.23s/it]
+
 90%|█████████ | 114/126 [02:20<00:14,  1.23s/it]
+
 91%|█████████▏| 115/126 [02:21<00:13,  1.23s/it]
+
 92%|█████████▏| 116/126 [02:22<00:12,  1.23s/it]
+
 93%|█████████▎| 117/126 [02:24<00:11,  1.23s/it]
+
 94%|█████████▎| 118/126 [02:25<00:09,  1.23s/it]
+
 94%|█████████▍| 119/126 [02:26<00:08,  1.23s/it]
+
 95%|█████████▌| 120/126 [02:27<00:07,  1.23s/it]
+
 96%|█████████▌| 121/126 [02:29<00:06,  1.23s/it]
+
 97%|█████████▋| 122/126 [02:30<00:04,  1.23s/it]
+
 98%|█████████▊| 123/126 [02:31<00:03,  1.23s/it]
+
 98%|█████████▊| 124/126 [02:32<00:02,  1.23s/it]
 98%|█████████▊| 124/126 [02:32<00:02,  1.23s/it]
+Traceback (most recent call last):
+  File "/mnt/storage/aatherton/hf_synth_trans/synth_translation.py", line 219, in <module>
+    for batch in tqdm(eval_dataloader):
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/tqdm/std.py", line 1178, in __iter__
+    for obj in iterable:
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/accelerate/data_loader.py", line 394, in __iter__
+    next_batch = next(dataloader_iter)
+                 ^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 633, in __next__
+    data = self._next_data()
+           ^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 677, in _next_data
+    data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/utils/data/_utils/fetch.py", line 54, in fetch
+    return self.collate_fn(data)
+           ^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/data/data_collator.py", line 600, in __call__
+    decoder_input_ids = self.model.prepare_decoder_input_ids_from_labels(labels=features["labels"])
+                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/marian/modeling_marian.py", line 1527, in prepare_decoder_input_ids_from_labels
+    return shift_tokens_right(labels, self.config.pad_token_id, self.config.decoder_start_token_id)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/marian/modeling_marian.py", line 66, in shift_tokens_right
+    shifted_input_ids[:, 0] = decoder_start_token_id
+    ~~~~~~~~~~~~~~~~~^^^^^^
+IndexError: index 0 is out of bounds for dimension 1 with size 0
+
 33%|███▎      | 912/2736 [03:46<07:32,  4.03it/s]

myerrors_1562.out

@@ -0,0 +1,8 @@
+You're using a GPT2TokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
+
  0%|          | 0/16 [00:00<?, ?it/s]
 12%|█▎        | 2/16 [00:04<00:30,  2.21s/it]
 19%|█▉        | 3/16 [00:08<00:40,  3.10s/it]
 25%|██▌       | 4/16 [00:13<00:42,  3.55s/it]
 31%|███▏      | 5/16 [00:17<00:41,  3.82s/it]
 38%|███▊      | 6/16 [00:21<00:39,  3.98s/it]
 44%|████▍     | 7/16 [00:26<00:36,  4.09s/it]
 50%|█████     | 8/16 [00:30<00:33,  4.16s/it]
 56%|█████▋    | 9/16 [00:34<00:29,  4.21s/it]
 62%|██████▎   | 10/16 [00:38<00:25,  4.24s/it]
 69%|██████▉   | 11/16 [00:43<00:21,  4.27s/it]
 75%|███████▌  | 12/16 [00:47<00:17,  4.28s/it]
 81%|████████▏ | 13/16 [00:51<00:12,  4.30s/it]
 88%|████████▊ | 14/16 [00:56<00:08,  4.30s/it]
 94%|█████████▍| 15/16 [01:00<00:04,  4.31s/it]
+
  0%|          | 0/684 [00:00<?, ?it/s]
  0%|          | 1/684 [00:00<02:35,  4.39it/s]
  0%|          | 3/684 [00:00<01:18,  8.73it/s]
  1%|          | 5/684 [00:00<01:03, 10.71it/s]
  1%|          | 7/684 [00:00<00:57, 11.86it/s]
  1%|▏         | 9/684 [00:00<00:53, 12.54it/s]
  2%|▏         | 11/684 [00:00<00:52, 12.92it/s]
  2%|▏         | 13/684 [00:01<00:50, 13.23it/s]
  2%|▏         | 15/684 [00:01<00:50, 13.36it/s]
  2%|▏         | 17/684 [00:01<00:49, 13.47it/s]
  3%|▎         | 19/684 [00:01<00:48, 13.61it/s]
  3%|▎         | 21/684 [00:01<00:48, 13.64it/s]
  3%|▎         | 23/684 [00:01<00:48, 13.63it/s]
  4%|▎         | 25/684 [00:01<00:48, 13.72it/s]
  4%|▍         | 27/684 [00:02<00:47, 13.73it/s]
  4%|▍         | 29/684 [00:02<00:47, 13.71it/s]
  5%|▍         | 31/684 [00:02<00:47, 13.76it/s]
  5%|▍         | 33/684 [00:02<00:47, 13.71it/s]
  5%|▌         | 35/684 [00:02<00:47, 13.76it/s]
  5%|▌         | 37/684 [00:02<00:47, 13.77it/s]
  6%|▌         | 39/684 [00:02<00:46, 13.74it/s]
  6%|▌         | 41/684 [00:03<00:46, 13.74it/s]
  6%|▋         | 43/684 [00:03<00:46, 13.73it/s]
  7%|▋         | 45/684 [00:03<00:46, 13.71it/s]
  7%|▋         | 47/684 [00:03<00:46, 13.77it/s]
  7%|▋         | 49/684 [00:03<00:46, 13.72it/s]
  7%|▋         | 51/684 [00:03<00:46, 13.70it/s]
  8%|▊         | 53/684 [00:04<00:45, 13.78it/s]
  8%|▊         | 55/684 [00:04<00:45, 13.76it/s]
  8%|▊         | 57/684 [00:04<00:45, 13.72it/s]
  9%|▊         | 59/684 [00:04<00:45, 13.77it/s]
  9%|▉         | 61/684 [00:04<00:45, 13.76it/s]
  9%|▉         | 63/684 [00:04<00:45, 13.74it/s]
 10%|▉         | 65/684 [00:04<00:44, 13.78it/s]
 10%|▉         | 67/684 [00:05<00:44, 13.76it/s]
 10%|█         | 69/684 [00:05<00:44, 13.74it/s]
 10%|█         | 71/684 [00:05<00:44, 13.76it/s]
 11%|█         | 73/684 [00:05<00:44, 13.78it/s]
 11%|█         | 75/684 [00:05<00:44, 13.79it/s]
 11%|█▏        | 77/684 [00:05<00:44, 13.78it/s]
 12%|█▏        | 79/684 [00:05<00:44, 13.72it/s]
 12%|█▏        | 81/684 [00:06<00:43, 13.78it/s]
 12%|█▏        | 83/684 [00:06<00:43, 13.76it/s]
 12%|█▏        | 85/684 [00:06<00:43, 13.73it/s]
 13%|█▎        | 87/684 [00:06<00:43, 13.72it/s]
 13%|█▎        | 89/684 [00:06<00:43, 13.74it/s]
 13%|█▎        | 91/684 [00:06<00:43, 13.71it/s]
 14%|█▎        | 93/684 [00:06<00:43, 13.72it/s]
 14%|█▍        | 95/684 [00:07<00:42, 13.75it/s]
 14%|█▍        | 97/684 [00:07<00:42, 13.78it/s]
 14%|█▍        | 99/684 [00:07<00:42, 13.81it/s]
 15%|█▍        | 101/684 [00:07<00:42, 13.81it/s]
 15%|█▌        | 103/684 [00:07<00:42, 13.79it/s]
 15%|█▌        | 105/684 [00:07<00:41, 13.79it/s]
 16%|█▌        | 107/684 [00:07<00:41, 13.77it/s]
 16%|█▌        | 109/684 [00:08<00:41, 13.80it/s]
 16%|█▌        | 111/684 [00:08<00:41, 13.80it/s]
 17%|█▋        | 113/684 [00:08<00:41, 13.78it/s]
 17%|█▋        | 115/684 [00:08<00:41, 13.78it/s]
 17%|█▋        | 117/684 [00:08<00:40, 13.83it/s]
 17%|█▋        | 119/684 [00:08<00:41, 13.73it/s]
 18%|█▊        | 121/684 [00:08<00:40, 13.75it/s]
 18%|█▊        | 123/684 [00:09<00:40, 13.75it/s]
 18%|█▊        | 125/684 [00:09<00:40, 13.76it/s]
 19%|█▊        | 127/684 [00:09<00:40, 13.79it/s]
 19%|█▉        | 129/684 [00:09<00:40, 13.76it/s]
 19%|█▉        | 131/684 [00:09<00:40, 13.74it/s]
 19%|█▉        | 133/684 [00:09<00:40, 13.73it/s]
 20%|█▉        | 135/684 [00:09<00:40, 13.71it/s]
 20%|██        | 137/684 [00:10<00:39, 13.69it/s]
 20%|██        | 139/684 [00:10<00:39, 13.71it/s]
 21%|██        | 141/684 [00:10<00:39, 13.72it/s]
 21%|██        | 143/684 [00:10<00:39, 13.71it/s]
 21%|██        | 145/684 [00:10<00:39, 13.72it/s]
 21%|██▏       | 147/684 [00:10<00:39, 13.75it/s]
 22%|██▏       | 149/684 [00:10<00:38, 13.86it/s]
 22%|██▏       | 151/684 [00:11<00:38, 13.77it/s]
 22%|██▏       | 153/684 [00:11<00:38, 13.82it/s]
 23%|██▎       | 155/684 [00:11<00:38, 13.88it/s]
 23%|██▎       | 157/684 [00:11<00:37, 13.99it/s]
 23%|██▎       | 159/684 [00:11<00:37, 13.88it/s]
 24%|██▎       | 161/684 [00:11<00:37, 13.85it/s]
 24%|██▍       | 163/684 [00:12<00:37, 13.77it/s]
 24%|██▍       | 165/684 [00:12<00:37, 13.71it/s]
 24%|██▍       | 167/684 [00:12<00:37, 13.71it/s]
 25%|██▍       | 169/684 [00:12<00:37, 13.78it/s]
 25%|██▌       | 171/684 [00:12<00:37, 13.79it/s]
 25%|██▌       | 173/684 [00:12<00:36, 13.82it/s]
 26%|██▌       | 175/684 [00:12<00:36, 13.80it/s]
 26%|██▌       | 177/684 [00:13<00:36, 13.77it/s]
 26%|██▌       | 179/684 [00:13<00:36, 13.77it/s]
 26%|██▋       | 181/684 [00:13<00:36, 13.78it/s]
 27%|██▋       | 183/684 [00:13<00:36, 13.76it/s]
 27%|██▋       | 185/684 [00:13<00:36, 13.76it/s]
 27%|██▋       | 187/684 [00:13<00:36, 13.75it/s]
 28%|██▊       | 189/684 [00:13<00:36, 13.75it/s]
 28%|██▊       | 191/684 [00:14<00:35, 13.75it/s]
 28%|██▊       | 193/684 [00:14<00:35, 13.76it/s]
 29%|██▊       | 195/684 [00:14<00:35, 13.75it/s]
 29%|██▉       | 197/684 [00:14<00:35, 13.76it/s]
 29%|██▉       | 199/684 [00:14<00:35, 13.77it/s]
 29%|██▉       | 201/684 [00:14<00:35, 13.78it/s]
 30%|██▉       | 203/684 [00:14<00:34, 13.77it/s]
 30%|██▉       | 205/684 [00:15<00:34, 13.75it/s]
 30%|███       | 207/684 [00:15<00:34, 13.79it/s]
 31%|███       | 209/684 [00:15<00:34, 13.77it/s]
 31%|███       | 211/684 [00:15<00:34, 13.77it/s]
 31%|███       | 213/684 [00:15<00:34, 13.78it/s]
 31%|███▏      | 215/684 [00:15<00:34, 13.75it/s]
 32%|███▏      | 217/684 [00:15<00:33, 13.85it/s]
 32%|███▏      | 219/684 [00:16<00:33, 13.82it/s]
 32%|███▏      | 221/684 [00:16<00:33, 13.77it/s]
 33%|███▎      | 223/684 [00:16<00:33, 13.76it/s]
 33%|███▎      | 225/684 [00:16<00:33, 13.76it/s]
 33%|███▎      | 227/684 [00:16<00:33, 13.82it/s]
 33%|███▎      | 229/684 [00:19<03:24,  2.22it/s]
 34%|███▍      | 231/684 [00:19<02:32,  2.97it/s]
 34%|███▍      | 233/684 [00:19<01:55,  3.90it/s]
 34%|███▍      | 235/684 [00:19<01:30,  4.96it/s]
 35%|███▍      | 237/684 [00:19<01:13,  6.09it/s]
 35%|███▍      | 239/684 [00:20<01:01,  7.22it/s]
 35%|███▌      | 241/684 [00:20<00:53,  8.22it/s]
 36%|███▌      | 243/684 [00:20<00:47,  9.25it/s]
 36%|███▌      | 245/684 [00:20<00:43, 10.11it/s]
 36%|███▌      | 247/684 [00:20<00:40, 10.91it/s]
 36%|███▋      | 249/684 [00:20<00:38, 11.29it/s]
 37%|███▋      | 251/684 [00:20<00:36, 11.91it/s]
 37%|███▋      | 253/684 [00:21<00:35, 12.08it/s]
 37%|███▋      | 255/684 [00:21<00:34, 12.56it/s]
 38%|███▊      | 257/684 [00:21<00:33, 12.63it/s]
 38%|███▊      | 259/684 [00:21<00:32, 13.01it/s]
 38%|███▊      | 261/684 [00:21<00:32, 12.92it/s]
 38%|███▊      | 263/684 [00:21<00:31, 13.21it/s]
 39%|███▊      | 265/684 [00:22<00:32, 12.93it/s]
 39%|███▉      | 267/684 [00:22<00:31, 13.30it/s]
 39%|███▉      | 269/684 [00:22<00:30, 13.51it/s]
 40%|███▉      | 271/684 [00:22<00:31, 13.30it/s]
 40%|███▉      | 273/684 [00:22<00:31, 13.14it/s]
 40%|████      | 275/684 [00:22<00:30, 13.32it/s]
 40%|████      | 277/684 [00:22<00:31, 12.97it/s]
 41%|████      | 279/684 [00:23<00:31, 12.95it/s]
 41%|████      | 281/684 [00:23<00:30, 13.06it/s]
 41%|████▏     | 283/684 [00:23<00:30, 13.29it/s]
 42%|████▏     | 285/684 [00:23<00:30, 13.09it/s]
 42%|████▏     | 287/684 [00:23<00:29, 13.36it/s]
 42%|████▏     | 289/684 [00:23<00:30, 13.13it/s]
 43%|████▎     | 291/684 [00:24<00:30, 12.97it/s]
 43%|████▎     | 293/684 [00:24<00:29, 13.22it/s]
 43%|████▎     | 295/684 [00:24<00:29, 13.04it/s]
 43%|████▎     | 297/684 [00:24<00:29, 13.11it/s]
 44%|████▎     | 299/684 [00:24<00:29, 12.96it/s]
 44%|████▍     | 301/684 [00:24<00:29, 13.16it/s]
 44%|████▍     | 303/684 [00:24<00:28, 13.37it/s]
 45%|████▍     | 305/684 [00:25<00:29, 12.93it/s]
 45%|████▍     | 307/684 [00:25<00:29, 13.00it/s]
 45%|████▌     | 309/684 [00:25<00:29, 12.85it/s]
 45%|████▌     | 311/684 [00:25<00:29, 12.75it/s]
 46%|████▌     | 313/684 [00:25<00:28, 13.03it/s]
 46%|████▌     | 315/684 [00:25<00:28, 13.04it/s]
 46%|████▋     | 317/684 [00:26<00:27, 13.17it/s]
 47%|████▋     | 319/684 [00:26<00:27, 13.04it/s]
 47%|████▋     | 321/684 [00:26<00:27, 13.27it/s]
 47%|████▋     | 323/684 [00:26<00:27, 13.35it/s]
 48%|██��█▊     | 325/684 [00:26<00:26, 13.48it/s]
 48%|████▊     | 327/684 [00:26<00:26, 13.29it/s]
 48%|████▊     | 329/684 [00:26<00:26, 13.34it/s]
 48%|████▊     | 331/684 [00:27<00:26, 13.48it/s]
 49%|████▊     | 333/684 [00:27<00:25, 13.58it/s]
 49%|████▉     | 335/684 [00:27<00:25, 13.67it/s]
 49%|████▉     | 337/684 [00:27<00:25, 13.71it/s]
 50%|████▉     | 339/684 [00:27<00:25, 13.75it/s]
 50%|████▉     | 341/684 [00:27<00:25, 13.70it/s]
 50%|█████     | 343/684 [00:27<00:24, 13.71it/s]
 50%|█████     | 345/684 [00:28<00:24, 13.73it/s]
 51%|█████     | 347/684 [00:28<00:24, 13.72it/s]
 51%|█████     | 349/684 [00:28<00:24, 13.71it/s]
 51%|█████▏    | 351/684 [00:28<00:24, 13.70it/s]
 52%|█████▏    | 353/684 [00:28<00:24, 13.72it/s]
 52%|█████▏    | 355/684 [00:28<00:24, 13.70it/s]
 52%|█████▏    | 357/684 [00:28<00:23, 13.74it/s]
 52%|█████▏    | 359/684 [00:29<00:23, 13.74it/s]
 53%|█████▎    | 361/684 [00:29<00:23, 13.73it/s]
 53%|█████▎    | 363/684 [00:29<00:23, 13.71it/s]
 53%|█████▎    | 365/684 [00:29<00:23, 13.73it/s]
 54%|█████▎    | 367/684 [00:29<00:23, 13.74it/s]
 54%|█████▍    | 369/684 [00:29<00:22, 13.72it/s]
 54%|█████▍    | 371/684 [00:29<00:22, 13.74it/s]
 55%|█████▍    | 373/684 [00:30<00:22, 13.80it/s]
 55%|█████▍    | 375/684 [00:30<00:22, 13.88it/s]
 55%|█████▌    | 377/684 [00:30<00:22, 13.93it/s]
 55%|█████▌    | 379/684 [00:30<00:22, 13.82it/s]
 56%|█████▌    | 381/684 [00:30<00:21, 13.79it/s]
 56%|█████▌    | 383/684 [00:30<00:21, 13.77it/s]
 56%|█████▋    | 385/684 [00:30<00:21, 13.74it/s]
 57%|█████▋    | 387/684 [00:31<00:21, 13.74it/s]
 57%|█████▋    | 389/684 [00:31<00:21, 13.75it/s]
 57%|█████▋    | 391/684 [00:31<00:21, 13.74it/s]
 57%|█████▋    | 393/684 [00:31<00:21, 13.69it/s]
 58%|█████▊    | 395/684 [00:31<00:21, 13.75it/s]
 58%|█████▊    | 397/684 [00:31<00:20, 13.74it/s]
 58%|█████▊    | 399/684 [00:31<00:20, 13.68it/s]
 59%|█████▊    | 401/684 [00:32<00:20, 13.69it/s]
 59%|█████▉    | 403/684 [00:32<00:20, 13.70it/s]
 59%|█████▉    | 405/684 [00:32<00:20, 13.74it/s]
 60%|█████▉    | 407/684 [00:32<00:20, 13.73it/s]
 60%|█████▉    | 409/684 [00:32<00:19, 13.77it/s]
 60%|██████    | 411/684 [00:32<00:19, 13.87it/s]
 60%|██████    | 413/684 [00:33<00:19, 13.96it/s]
 61%|██████    | 415/684 [00:33<00:19, 13.95it/s]
 61%|██████    | 417/684 [00:33<00:19, 13.88it/s]
 61%|██████▏   | 419/684 [00:33<00:19, 13.86it/s]
 62%|██████▏   | 421/684 [00:33<00:18, 14.00it/s]
 62%|██████▏   | 423/684 [00:33<00:18, 13.99it/s]
 62%|██████▏   | 425/684 [00:33<00:18, 14.04it/s]
 62%|██████▏   | 427/684 [00:34<00:18, 14.01it/s]
 63%|██████▎   | 429/684 [00:34<00:18, 13.96it/s]
 63%|██████▎   | 431/684 [00:34<00:18, 13.91it/s]
 63%|██████▎   | 433/684 [00:34<00:18, 13.87it/s]
 64%|██████▎   | 435/684 [00:34<00:17, 13.85it/s]
 64%|██████▍   | 437/684 [00:34<00:17, 13.80it/s]
 64%|██████▍   | 439/684 [00:34<00:17, 13.80it/s]
 64%|██████▍   | 441/684 [00:35<00:17, 13.80it/s]
 65%|██████▍   | 443/684 [00:35<00:17, 13.81it/s]
 65%|██████▌   | 445/684 [00:35<00:17, 13.83it/s]
 65%|██████▌   | 447/684 [00:35<00:16, 13.96it/s]
 66%|██████▌   | 449/684 [00:35<00:16, 13.96it/s]
 66%|██████▌   | 451/684 [00:35<00:16, 13.89it/s]
 66%|██████▌   | 453/684 [00:35<00:16, 13.87it/s]
 67%|██████▋   | 455/684 [00:36<00:16, 13.85it/s]
 67%|██████▋   | 457/684 [00:38<01:32,  2.44it/s]
 67%|██████▋   | 459/684 [00:38<01:09,  3.24it/s]
 67%|██████▋   | 461/684 [00:38<00:53,  4.20it/s]
 68%|██████▊   | 463/684 [00:38<00:41,  5.29it/s]
 68%|██████▊   | 465/684 [00:39<00:34,  6.37it/s]
 68%|██████▊   | 467/684 [00:39<00:28,  7.51it/s]
 69%|██████▊   | 469/684 [00:39<00:25,  8.53it/s]
 69%|██████▉   | 471/684 [00:39<00:22,  9.52it/s]
 69%|██████▉   | 473/684 [00:39<00:20, 10.06it/s]
 69%|██████▉   | 475/684 [00:39<00:19, 10.69it/s]
 70%|██████▉   | 477/684 [00:39<00:18, 11.19it/s]
 70%|███████   | 479/684 [00:40<00:18, 11.27it/s]
 70%|███████   | 481/684 [00:40<00:17, 11.78it/s]
 71%|███████   | 483/684 [00:40<00:17, 11.77it/s]
 71%|███████   | 485/684 [00:40<00:16, 12.00it/s]
 71%|███████   | 487/684 [00:40<00:16, 12.10it/s]
 71%|███████▏  | 489/684 [00:40<00:16, 12.10it/s]
 72%|███████▏  | 491/684 [00:41<00:15, 12.24it/s]
 72%|███████▏  | 493/684 [00:41<00:15, 12.17it/s]
 72%|███████▏  | 495/684 [00:41<00:15, 12.41it/s]
 73%|███████▎  | 497/684 [00:41<00:15, 12.44it/s]
 73%|███████▎  | 499/684 [00:41<00:14, 12.39it/s]
                                                 
 73%|███████▎  | 500/684 [00:41<00:14, 12.39it/s]
 73%|███████▎  | 501/684 [00:41<00:15, 12.18it/s]
 74%|███████▎  | 503/684 [00:42<00:14, 12.57it/s]
 74%|███████▍  | 505/684 [00:42<00:14, 12.54it/s]
 74%|███████▍  | 507/684 [00:42<00:14, 12.49it/s]
 74%|███████▍  | 509/684 [00:42<00:14, 12.21it/s]
 75%|███████▍  | 511/684 [00:42<00:13, 12.73it/s]
 75%|███████▌  | 513/684 [00:42<00:13, 12.47it/s]
 75%|███████▌  | 515/684 [00:43<00:13, 12.57it/s]
 76%|███████▌  | 517/684 [00:43<00:12, 12.88it/s]
 76%|███████▌  | 519/684 [00:43<00:12, 12.69it/s]
 76%|███████▌  | 521/684 [00:43<00:12, 12.72it/s]
 76%|███████▋  | 523/684 [00:43<00:12, 12.72it/s]
 77%|███████▋  | 525/684 [00:43<00:12, 12.68it/s]
 77%|███████▋  | 527/684 [00:43<00:12, 13.03it/s]
 77%|███████▋  | 529/684 [00:44<00:11, 13.00it/s]
 78%|███████▊  | 531/684 [00:44<00:11, 13.22it/s]
 78%|███████▊  | 533/684 [00:44<00:11, 13.03it/s]
 78%|███████▊  | 535/684 [00:44<00:11, 13.08it/s]
 79%|███████▊  | 537/684 [00:44<00:10, 13.41it/s]
 79%|███████▉  | 539/684 [00:44<00:10, 13.41it/s]
 79%|███████▉  | 541/684 [00:45<00:10, 13.43it/s]
 79%|███████▉  | 543/684 [00:45<00:10, 13.44it/s]
 80%|███████▉  | 545/684 [00:45<00:10, 13.45it/s]
 80%|███████▉  | 547/684 [00:45<00:10, 13.45it/s]
 80%|████████  | 549/684 [00:45<00:10, 13.40it/s]
 81%|████████  | 551/684 [00:45<00:09, 13.37it/s]
 81%|████████  | 553/684 [00:45<00:09, 13.40it/s]
 81%|████████  | 555/684 [00:46<00:09, 13.43it/s]
 81%|████████▏ | 557/684 [00:46<00:09, 13.47it/s]
 82%|████████▏ | 559/684 [00:46<00:09, 13.49it/s]
 82%|████████▏ | 561/684 [00:46<00:09, 13.46it/s]
 82%|████████▏ | 563/684 [00:46<00:08, 13.47it/s]
 83%|████████▎ | 565/684 [00:46<00:08, 13.40it/s]
 83%|████████▎ | 567/684 [00:46<00:08, 13.42it/s]
 83%|████████▎ | 569/684 [00:47<00:08, 13.46it/s]
 83%|████████▎ | 571/684 [00:47<00:08, 13.47it/s]
 84%|████████▍ | 573/684 [00:47<00:08, 13.51it/s]
 84%|████████▍ | 575/684 [00:47<00:08, 13.49it/s]
 84%|████████▍ | 577/684 [00:47<00:07, 13.53it/s]
 85%|████████▍ | 579/684 [00:47<00:07, 13.25it/s]
 85%|████████▍ | 581/684 [00:48<00:07, 13.30it/s]
 85%|████████▌ | 583/684 [00:48<00:07, 13.36it/s]
 86%|████████▌ | 585/684 [00:48<00:07, 13.39it/s]
 86%|████████▌ | 587/684 [00:48<00:07, 13.44it/s]
 86%|████████▌ | 589/684 [00:48<00:07, 13.44it/s]
 86%|████████▋ | 591/684 [00:48<00:06, 13.38it/s]
 87%|████████▋ | 593/684 [00:48<00:06, 13.39it/s]
 87%|████████▋ | 595/684 [00:49<00:06, 13.40it/s]
 87%|████████▋ | 597/684 [00:49<00:06, 13.48it/s]
 88%|████████▊ | 599/684 [00:49<00:06, 13.50it/s]
 88%|████████▊ | 601/684 [00:49<00:06, 13.51it/s]
 88%|████████▊ | 603/684 [00:49<00:05, 13.53it/s]
 88%|████████▊ | 605/684 [00:49<00:05, 13.52it/s]
 89%|████████▊ | 607/684 [00:49<00:05, 13.63it/s]
 89%|████████▉ | 609/684 [00:50<00:05, 13.73it/s]
 89%|████████▉ | 611/684 [00:50<00:05, 13.76it/s]
 90%|████████▉ | 613/684 [00:50<00:05, 13.87it/s]
 90%|████████▉ | 615/684 [00:50<00:04, 13.84it/s]
 90%|█████████ | 617/684 [00:50<00:04, 13.75it/s]
 90%|█████████ | 619/684 [00:50<00:04, 13.68it/s]
 91%|█████████ | 621/684 [00:50<00:04, 13.65it/s]
 91%|█████████ | 623/684 [00:51<00:04, 13.61it/s]
 91%|█████████▏| 625/684 [00:51<00:04, 13.57it/s]
 92%|█████████▏| 627/684 [00:51<00:04, 13.52it/s]
 92%|█████████▏| 629/684 [00:51<00:04, 13.50it/s]
 92%|█████████▏| 631/684 [00:51<00:03, 13.49it/s]
 93%|█████████▎| 633/684 [00:51<00:03, 13.51it/s]
 93%|█████████▎| 635/684 [00:51<00:03, 13.57it/s]
 93%|█████████▎| 637/684 [00:52<00:03, 13.58it/s]
 93%|█████████▎| 639/684 [00:52<00:03, 13.60it/s]
 94%|█████████▎| 641/684 [00:52<00:03, 13.62it/s]
 94%|█████████▍| 643/684 [00:52<00:03, 13.60it/s]
 94%|█████████▍| 645/684 [00:52<00:02, 13.63it/s]
 95%|█████████▍| 647/684 [00:52<00:02, 13.65it/s]
 95%|█████████▍| 649/684 [00:53<00:02, 13.66it/s]
 95%|█████████▌| 651/684 [00:53<00:02, 13.68it/s]
 95%|█████████▌| 653/684 [00:53<00:02, 13.67it/s]
 96%|█████████▌| 655/684 [00:53<00:02, 13.66it/s]
 96%|█████████▌| 657/684 [00:53<00:01, 13.67it/s]
 96%|█████████▋| 659/684 [00:53<00:01, 13.66it/s]
 97%|█████████▋| 661/684 [00:53<00:01, 13.69it/s]
 97%|█████████▋| 663/684 [00:54<00:01, 13.61it/s]
 97%|█████████▋| 665/684 [00:54<00:01, 13.62it/s]
 98%|█████████▊| 667/684 [00:54<00:01, 13.59it/s]
 98%|█████████▊| 669/684 [00:54<00:01, 13.59it/s]
 98%|█████████▊| 671/684 [00:54<00:00, 13.62it/s]
 98%|█████████▊| 673/684 [00:54<00:00, 13.55it/s]
 99%|█████████▊| 675/684 [00:54<00:00, 13.56it/s]
 99%|█████████▉| 677/684 [00:55<00:00, 13.58it/s]
 99%|█████████▉| 679/684 [00:55<00:00, 13.57it/s]
                                                 
+
  0%|          | 0/16 [00:00<?, ?it/s]
 12%|█▎        | 2/16 [00:04<00:30,  2.16s/it]
 19%|█▉        | 3/16 [00:08<00:39,  3.06s/it]
 25%|██▌       | 4/16 [00:12<00:42,  3.53s/it]
 31%|███▏      | 5/16 [00:17<00:41,  3.81s/it]
 38%|███▊      | 6/16 [00:21<00:39,  3.98s/it]
 44%|████▍     | 7/16 [00:25<00:36,  4.08s/it]
 50%|█████     | 8/16 [00:30<00:33,  4.16s/it]
 56%|█████▋    | 9/16 [00:34<00:29,  4.21s/it]
 62%|██████▎   | 10/16 [00:38<00:25,  4.24s/it]
 69%|██████▉   | 11/16 [00:43<00:21,  4.27s/it]
 75%|███████▌  | 12/16 [00:47<00:17,  4.29s/it]
 81%|████████▏ | 13/16 [00:51<00:12,  4.29s/it]
 88%|████████▊ | 14/16 [00:56<00:08,  4.30s/it]
 94%|█████████▍| 15/16 [01:00<00:04,  4.31s/it]
+/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/optimization.py:411: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
+  warnings.warn(
+/mnt/storage/aatherton/hf_eng_fra_trans is already a clone of https://huggingface.co/aatherton2024/hf_eng_fra_trans. Make sure you pull the latest changes with `repo.git_pull()`.
+
  0%|          | 0/2736 [00:00<?, ?it/s]
  0%|          | 1/2736 [00:00<04:54,  9.28it/s]
  0%|          | 3/2736 [00:00<04:05, 11.14it/s]
  0%|          | 5/2736 [00:00<03:53, 11.68it/s]
  0%|          | 7/2736 [00:00<03:46, 12.05it/s]
  0%|          | 9/2736 [00:00<03:45, 12.11it/s]
  0%|          | 11/2736 [00:00<03:42, 12.27it/s]
  0%|          | 13/2736 [00:01<03:41, 12.27it/s]
  1%|          | 15/2736 [00:01<03:40, 12.36it/s]
  1%|          | 17/2736 [00:01<03:38, 12.42it/s]
  1%|          | 19/2736 [00:01<03:39, 12.40it/s]
  1%|          | 21/2736 [00:01<03:38, 12.43it/s]
  1%|          | 23/2736 [00:01<03:37, 12.49it/s]
  1%|          | 25/2736 [00:02<03:36, 12.55it/s]
  1%|          | 27/2736 [00:02<03:35, 12.58it/s]
  1%|          | 29/2736 [00:02<03:34, 12.62it/s]
  1%|          | 31/2736 [00:02<03:34, 12.59it/s]
  1%|          | 33/2736 [00:02<03:35, 12.52it/s]
  1%|▏         | 35/2736 [00:02<03:35, 12.52it/s]
  1%|▏         | 37/2736 [00:02<03:35, 12.52it/s]
  1%|▏         | 39/2736 [00:03<03:38, 12.36it/s]
  1%|▏         | 41/2736 [00:03<03:39, 12.26it/s]
  2%|▏         | 43/2736 [00:03<03:39, 12.28it/s]
  2%|▏         | 45/2736 [00:03<03:38, 12.34it/s]slurmstepd-dl: error: *** JOB 1562 ON dl CANCELLED AT 2023-09-17T19:46:47 ***

myerrors_1563.out

@@ -0,0 +1,161 @@
+You're using a GPT2TokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
+
  0%|          | 0/16 [00:00<?, ?it/s]
 12%|█▎        | 2/16 [00:04<00:31,  2.24s/it]
 19%|█▉        | 3/16 [00:08<00:40,  3.13s/it]
 25%|██▌       | 4/16 [00:13<00:43,  3.59s/it]
 31%|███▏      | 5/16 [00:17<00:42,  3.84s/it]
 38%|███▊      | 6/16 [00:21<00:39,  4.00s/it]
 44%|████▍     | 7/16 [00:26<00:37,  4.12s/it]
 50%|█████     | 8/16 [00:30<00:33,  4.20s/it]
 56%|█████▋    | 9/16 [00:34<00:29,  4.25s/it]
 62%|██████▎   | 10/16 [00:39<00:25,  4.29s/it]
 69%|██████▉   | 11/16 [00:43<00:21,  4.31s/it]
 75%|███████▌  | 12/16 [00:48<00:17,  4.32s/it]
 81%|████████▏ | 13/16 [00:52<00:13,  4.34s/it]
 88%|████████▊ | 14/16 [00:56<00:08,  4.34s/it]
 94%|█████████▍| 15/16 [01:01<00:04,  4.35s/it]
+
  0%|          | 0/684 [00:00<?, ?it/s]
  0%|          | 1/684 [00:00<02:37,  4.33it/s]
  0%|          | 3/684 [00:00<01:17,  8.83it/s]
  1%|          | 5/684 [00:00<01:02, 10.79it/s]
  1%|          | 7/684 [00:00<00:57, 11.87it/s]
  1%|▏         | 9/684 [00:00<00:54, 12.47it/s]
  2%|▏         | 11/684 [00:00<00:52, 12.89it/s]
  2%|▏         | 13/684 [00:01<00:51, 13.12it/s]
  2%|▏         | 15/684 [00:01<00:50, 13.31it/s]
  2%|▏         | 17/684 [00:01<00:49, 13.43it/s]
  3%|▎         | 19/684 [00:01<00:49, 13.52it/s]
  3%|▎         | 21/684 [00:01<00:48, 13.59it/s]
  3%|▎         | 23/684 [00:01<00:48, 13.60it/s]
  4%|▎         | 25/684 [00:01<00:48, 13.61it/s]
  4%|▍         | 27/684 [00:02<00:48, 13.66it/s]
  4%|▍         | 29/684 [00:02<00:47, 13.67it/s]
  5%|▍         | 31/684 [00:02<00:47, 13.69it/s]
  5%|▍         | 33/684 [00:02<00:47, 13.65it/s]
  5%|▌         | 35/684 [00:02<00:46, 13.82it/s]
  5%|▌         | 37/684 [00:02<00:46, 13.93it/s]
  6%|▌         | 39/684 [00:02<00:46, 13.98it/s]
  6%|▌         | 41/684 [00:03<00:45, 14.01it/s]
  6%|▋         | 43/684 [00:03<00:45, 14.04it/s]
  7%|▋         | 45/684 [00:03<00:45, 13.94it/s]
  7%|▋         | 47/684 [00:03<00:45, 13.90it/s]
  7%|▋         | 49/684 [00:03<00:45, 13.83it/s]
  7%|▋         | 51/684 [00:03<00:45, 13.85it/s]
  8%|▊         | 53/684 [00:03<00:45, 13.88it/s]
  8%|▊         | 55/684 [00:04<00:45, 13.77it/s]
  8%|▊         | 57/684 [00:04<00:45, 13.78it/s]
  9%|▊         | 59/684 [00:04<00:45, 13.77it/s]
  9%|▉         | 61/684 [00:04<00:45, 13.84it/s]
  9%|▉         | 63/684 [00:04<00:44, 13.94it/s]
 10%|▉         | 65/684 [00:04<00:44, 13.99it/s]
 10%|▉         | 67/684 [00:05<00:44, 14.01it/s]
 10%|█         | 69/684 [00:05<00:43, 14.00it/s]
 10%|█         | 71/684 [00:05<00:43, 14.09it/s]
 11%|█         | 73/684 [00:05<00:43, 14.03it/s]
 11%|█         | 75/684 [00:05<00:43, 13.96it/s]
 11%|█▏        | 77/684 [00:05<00:43, 13.85it/s]
 12%|█▏        | 79/684 [00:05<00:43, 13.86it/s]
 12%|█▏        | 81/684 [00:06<00:43, 13.81it/s]
 12%|█▏        | 83/684 [00:06<00:43, 13.85it/s]
 12%|█▏        | 85/684 [00:06<00:43, 13.82it/s]
 13%|█▎        | 87/684 [00:06<00:43, 13.80it/s]
 13%|█▎        | 89/684 [00:06<00:43, 13.78it/s]
 13%|█▎        | 91/684 [00:06<00:43, 13.78it/s]
 14%|█▎        | 93/684 [00:06<00:42, 13.82it/s]
 14%|█▍        | 95/684 [00:07<00:42, 13.83it/s]
 14%|█▍        | 97/684 [00:07<00:42, 13.84it/s]
 14%|█▍        | 99/684 [00:07<00:42, 13.76it/s]
 15%|█▍        | 101/684 [00:07<00:42, 13.76it/s]
 15%|█▌        | 103/684 [00:07<00:42, 13.74it/s]
 15%|█▌        | 105/684 [00:07<00:42, 13.76it/s]
 16%|█▌        | 107/684 [00:07<00:41, 13.82it/s]
 16%|█▌        | 109/684 [00:08<00:41, 13.78it/s]
 16%|█▌        | 111/684 [00:08<00:41, 13.76it/s]
 17%|█▋        | 113/684 [00:08<00:41, 13.74it/s]
 17%|█▋        | 115/684 [00:08<00:41, 13.79it/s]
 17%|█▋        | 117/684 [00:08<00:41, 13.73it/s]
 17%|█▋        | 119/684 [00:08<00:40, 13.81it/s]
 18%|█▊        | 121/684 [00:08<00:40, 13.77it/s]
 18%|█▊        | 123/684 [00:09<00:40, 13.76it/s]
 18%|█▊        | 125/684 [00:09<00:40, 13.83it/s]
 19%|█▊        | 127/684 [00:09<00:39, 13.98it/s]
 19%|█▉        | 129/684 [00:09<00:39, 13.93it/s]
 19%|█▉        | 131/684 [00:09<00:39, 13.85it/s]
 19%|█▉        | 133/684 [00:09<00:39, 13.80it/s]
 20%|█▉        | 135/684 [00:09<00:39, 13.78it/s]
 20%|██        | 137/684 [00:10<00:39, 13.74it/s]
 20%|██        | 139/684 [00:10<00:39, 13.78it/s]
 21%|██        | 141/684 [00:10<00:39, 13.79it/s]
 21%|██        | 143/684 [00:10<00:39, 13.76it/s]
 21%|██        | 145/684 [00:10<00:39, 13.75it/s]
 21%|██▏       | 147/684 [00:10<00:38, 13.77it/s]
 22%|██▏       | 149/684 [00:10<00:40, 13.20it/s]
 22%|██▏       | 151/684 [00:11<00:39, 13.33it/s]
 22%|██▏       | 153/684 [00:11<00:39, 13.50it/s]
 23%|██▎       | 155/684 [00:11<00:38, 13.57it/s]
 23%|██▎       | 157/684 [00:11<00:38, 13.62it/s]
 23%|██▎       | 159/684 [00:11<00:38, 13.72it/s]
 24%|██▎       | 161/684 [00:11<00:37, 13.80it/s]
 24%|██▍       | 163/684 [00:11<00:37, 13.76it/s]
 24%|██▍       | 165/684 [00:12<00:37, 13.76it/s]
 24%|██▍       | 167/684 [00:12<00:37, 13.78it/s]
 25%|██▍       | 169/684 [00:12<00:37, 13.83it/s]
 25%|██▌       | 171/684 [00:12<00:36, 13.96it/s]
 25%|██▌       | 173/684 [00:12<00:36, 13.89it/s]
 26%|██▌       | 175/684 [00:12<00:36, 13.85it/s]
 26%|██▌       | 177/684 [00:12<00:36, 13.85it/s]
 26%|██▌       | 179/684 [00:13<00:36, 13.81it/s]
 26%|██▋       | 181/684 [00:13<00:36, 13.78it/s]
 27%|██▋       | 183/684 [00:13<00:36, 13.83it/s]
 27%|██▋       | 185/684 [00:13<00:36, 13.82it/s]
 27%|██▋       | 187/684 [00:13<00:36, 13.79it/s]
 28%|██▊       | 189/684 [00:13<00:35, 13.78it/s]
 28%|██▊       | 191/684 [00:14<00:35, 13.76it/s]
 28%|██▊       | 193/684 [00:14<00:35, 13.74it/s]
 29%|██▊       | 195/684 [00:14<00:35, 13.72it/s]
 29%|██▉       | 197/684 [00:14<00:35, 13.78it/s]
 29%|██▉       | 199/684 [00:14<00:35, 13.78it/s]
 29%|██▉       | 201/684 [00:14<00:35, 13.78it/s]
 30%|██▉       | 203/684 [00:14<00:34, 13.77it/s]
 30%|██▉       | 205/684 [00:15<00:34, 13.76it/s]
 30%|███       | 207/684 [00:15<00:34, 13.72it/s]
 31%|███       | 209/684 [00:15<00:34, 13.75it/s]
 31%|███       | 211/684 [00:15<00:34, 13.77it/s]
 31%|███       | 213/684 [00:15<00:34, 13.80it/s]
 31%|███▏      | 215/684 [00:15<00:34, 13.78it/s]
 32%|███▏      | 217/684 [00:15<00:33, 13.77it/s]
 32%|███▏      | 219/684 [00:16<00:33, 13.78it/s]
 32%|███▏      | 221/684 [00:16<00:33, 13.74it/s]
 33%|███▎      | 223/684 [00:16<00:33, 13.77it/s]
 33%|███▎      | 225/684 [00:16<00:34, 13.45it/s]
 33%|███▎      | 227/684 [00:16<00:34, 13.25it/s]
 33%|███▎      | 229/684 [00:18<03:04,  2.46it/s]
 34%|███▍      | 231/684 [00:19<02:18,  3.27it/s]
 34%|███▍      | 233/684 [00:19<01:46,  4.23it/s]
 34%|███▍      | 235/684 [00:19<01:23,  5.36it/s]
 35%|███▍      | 237/684 [00:19<01:08,  6.56it/s]
 35%|███▍      | 239/684 [00:19<00:58,  7.63it/s]
 35%|███▌      | 241/684 [00:19<00:50,  8.81it/s]
 36%|███▌      | 243/684 [00:20<00:46,  9.58it/s]
 36%|███▌      | 245/684 [00:20<00:41, 10.59it/s]
 36%|███▌      | 247/684 [00:20<00:39, 11.09it/s]
 36%|███▋      | 249/684 [00:20<00:37, 11.68it/s]
 37%|███▋      | 251/684 [00:20<00:36, 11.84it/s]
 37%|███▋      | 253/684 [00:20<00:35, 12.10it/s]
 37%|███▋      | 255/684 [00:20<00:34, 12.27it/s]
 38%|███▊      | 257/684 [00:21<00:34, 12.51it/s]
 38%|███▊      | 259/684 [00:21<00:33, 12.71it/s]
 38%|███▊      | 261/684 [00:21<00:32, 13.07it/s]
 38%|███▊      | 263/684 [00:21<00:31, 13.27it/s]
 39%|███▊      | 265/684 [00:21<00:32, 13.00it/s]
 39%|███▉      | 267/684 [00:21<00:31, 13.29it/s]
 39%|███▉      | 269/684 [00:22<00:30, 13.48it/s]
 40%|███▉      | 271/684 [00:22<00:31, 13.23it/s]
 40%|███▉      | 273/684 [00:22<00:31, 13.24it/s]
 40%|████      | 275/684 [00:22<00:31, 13.16it/s]
 40%|████      | 277/684 [00:22<00:30, 13.48it/s]
 41%|████      | 279/684 [00:22<00:30, 13.15it/s]
 41%|████      | 281/684 [00:22<00:30, 13.02it/s]
 41%|████▏     | 283/684 [00:23<00:30, 13.35it/s]
 42%|████▏     | 285/684 [00:23<00:29, 13.50it/s]
 42%|████▏     | 287/684 [00:23<00:30, 13.23it/s]
 42%|████▏     | 289/684 [00:23<00:29, 13.48it/s]
 43%|████▎     | 291/684 [00:23<00:29, 13.19it/s]
 43%|████▎     | 293/684 [00:23<00:29, 13.46it/s]
 43%|████▎     | 295/684 [00:23<00:29, 13.08it/s]
 43%|████▎     | 297/684 [00:24<00:29, 12.94it/s]
 44%|████▎     | 299/684 [00:24<00:29, 13.03it/s]
 44%|████▍     | 301/684 [00:24<00:29, 12.85it/s]
 44%|████▍     | 303/684 [00:24<00:29, 12.70it/s]
 45%|████▍     | 305/684 [00:24<00:30, 12.35it/s]
 45%|████▍     | 307/684 [00:24<00:30, 12.26it/s]
 45%|████▌     | 309/684 [00:25<00:30, 12.17it/s]
 45%|████▌     | 311/684 [00:25<00:31, 12.02it/s]
 46%|████▌     | 313/684 [00:25<00:30, 12.10it/s]
 46%|████▌     | 315/684 [00:25<00:30, 12.19it/s]
 46%|████▋     | 317/684 [00:25<00:30, 12.20it/s]
 47%|████▋     | 319/684 [00:25<00:30, 12.06it/s]
 47%|████▋     | 321/684 [00:26<00:29, 12.33it/s]
 47%|████▋     | 323/684 [00:26<00:28, 12.50it/s]
 48%|████▊     | 325/684 [00:26<00:27, 12.84it/s]
 48%|████▊     | 327/684 [00:26<00:27, 13.08it/s]
 48%|████▊     | 329/684 [00:26<00:26, 13.26it/s]
 48%|████▊     | 331/684 [00:26<00:26, 13.41it/s]
 49%|████▊     | 333/684 [00:26<00:25, 13.51it/s]
 49%|████▉     | 335/684 [00:27<00:25, 13.65it/s]
 49%|████▉     | 337/684 [00:27<00:25, 13.77it/s]
 50%|████▉     | 339/684 [00:27<00:24, 13.83it/s]
 50%|████▉     | 341/684 [00:27<00:24, 13.80it/s]
 50%|█████     | 343/684 [00:27<00:24, 13.75it/s]
 50%|█████     | 345/684 [00:27<00:24, 13.78it/s]
 51%|█████     | 347/684 [00:28<00:24, 13.72it/s]
 51%|█████     | 349/684 [00:28<00:24, 13.71it/s]
 51%|█████▏    | 351/684 [00:28<00:24, 13.73it/s]
 52%|█████▏    | 353/684 [00:28<00:24, 13.67it/s]
 52%|█████▏    | 355/684 [00:28<00:24, 13.67it/s]
 52%|█████▏    | 357/684 [00:28<00:23, 13.69it/s]
 52%|█████▏    | 359/684 [00:28<00:23, 13.69it/s]
 53%|█████▎    | 361/684 [00:29<00:23, 13.73it/s]
 53%|█████▎    | 363/684 [00:29<00:23, 13.73it/s]
 53%|█████▎    | 365/684 [00:29<00:23, 13.71it/s]
 54%|█████▎    | 367/684 [00:29<00:23, 13.73it/s]
 54%|█████▍    | 369/684 [00:29<00:23, 13.66it/s]
 54%|█████▍    | 371/684 [00:29<00:22, 13.65it/s]
 55%|█████▍    | 373/684 [00:29<00:22, 13.70it/s]
 55%|█████▍    | 375/684 [00:30<00:22, 13.65it/s]
 55%|█████▌    | 377/684 [00:30<00:22, 13.73it/s]
 55%|█████▌    | 379/684 [00:30<00:22, 13.69it/s]
 56%|█████▌    | 381/684 [00:30<00:22, 13.73it/s]
 56%|█████▌    | 383/684 [00:30<00:21, 13.74it/s]
 56%|█████▋    | 385/684 [00:30<00:21, 13.77it/s]
 57%|█████▋    | 387/684 [00:30<00:21, 13.78it/s]
 57%|█████▋    | 389/684 [00:31<00:21, 13.78it/s]
 57%|█████▋    | 391/684 [00:31<00:21, 13.76it/s]
 57%|█████▋    | 393/684 [00:31<00:21, 13.74it/s]
 58%|█████▊    | 395/684 [00:31<00:21, 13.75it/s]
 58%|█████▊    | 397/684 [00:31<00:20, 13.76it/s]
 58%|█████▊    | 399/684 [00:31<00:20, 13.78it/s]
 59%|█████▊    | 401/684 [00:31<00:20, 13.85it/s]
 59%|█████▉    | 403/684 [00:32<00:20, 13.75it/s]
 59%|█████▉    | 405/684 [00:32<00:20, 13.77it/s]
 60%|█████▉    | 407/684 [00:32<00:20, 13.73it/s]
 60%|█████▉    | 409/684 [00:32<00:20, 13.75it/s]
 60%|██████    | 411/684 [00:32<00:19, 13.70it/s]
 60%|██████    | 413/684 [00:32<00:19, 13.70it/s]
 61%|██████    | 415/684 [00:32<00:19, 13.72it/s]
 61%|██████    | 417/684 [00:33<00:19, 13.78it/s]
 61%|██████▏   | 419/684 [00:33<00:18, 13.97it/s]
 62%|██████▏   | 421/684 [00:33<00:18, 13.89it/s]
 62%|██████▏   | 423/684 [00:33<00:18, 13.84it/s]
 62%|██████▏   | 425/684 [00:33<00:18, 13.75it/s]
 62%|██████▏   | 427/684 [00:33<00:18, 13.74it/s]
 63%|██████▎   | 429/684 [00:33<00:18, 13.75it/s]
 63%|██████▎   | 431/684 [00:34<00:18, 13.72it/s]
 63%|██████▎   | 433/684 [00:34<00:18, 13.75it/s]
 64%|██████▎   | 435/684 [00:34<00:18, 13.76it/s]
 64%|██████▍   | 437/684 [00:34<00:17, 13.74it/s]
 64%|██████▍   | 439/684 [00:34<00:17, 13.75it/s]
 64%|██████▍   | 441/684 [00:34<00:17, 13.74it/s]
 65%|██████▍   | 443/684 [00:34<00:17, 13.75it/s]
 65%|██████▌   | 445/684 [00:35<00:17, 13.79it/s]
 65%|██████▌   | 447/684 [00:35<00:16, 13.96it/s]
 66%|██████▌   | 449/684 [00:35<00:16, 13.92it/s]
 66%|██████▌   | 451/684 [00:35<00:16, 13.83it/s]
 66%|██████▌   | 453/684 [00:35<00:16, 13.80it/s]
 67%|██████▋   | 455/684 [00:35<00:16, 13.74it/s]
 67%|██████▋   | 457/684 [00:38<01:31,  2.49it/s]
 67%|██████▋   | 459/684 [00:38<01:08,  3.31it/s]
 67%|██████▋   | 461/684 [00:38<00:52,  4.28it/s]
 68%|██████▊   | 463/684 [00:38<00:41,  5.39it/s]
 68%|██████▊   | 465/684 [00:38<00:33,  6.52it/s]
 68%|██████▊   | 467/684 [00:38<00:28,  7.69it/s]
 69%|██████▊   | 469/684 [00:39<00:24,  8.67it/s]
 69%|██████▉   | 471/684 [00:39<00:22,  9.63it/s]
 69%|██████▉   | 473/684 [00:39<00:20, 10.16it/s]
 69%|██████▉   | 475/684 [00:39<00:19, 10.79it/s]
 70%|██████▉   | 477/684 [00:39<00:18, 11.25it/s]
 70%|███████   | 479/684 [00:39<00:18, 11.22it/s]
 70%|███████   | 481/684 [00:40<00:17, 11.51it/s]
 71%|███████   | 483/684 [00:40<00:17, 11.64it/s]
 71%|███████   | 485/684 [00:40<00:17, 11.63it/s]
 71%|███████   | 487/684 [00:40<00:16, 11.81it/s]
 71%|███████▏  | 489/684 [00:40<00:15, 12.42it/s]
 72%|███████▏  | 491/684 [00:40<00:15, 12.31it/s]
 72%|███████▏  | 493/684 [00:41<00:15, 12.35it/s]
 72%|███████▏  | 495/684 [00:41<00:14, 12.83it/s]
 73%|███████▎  | 497/684 [00:41<00:14, 12.73it/s]
 73%|███████▎  | 499/684 [00:41<00:14, 13.01it/s]
                                                 
 73%|███████▎  | 500/684 [00:41<00:14, 13.01it/s]
 73%|███████▎  | 501/684 [00:41<00:14, 12.73it/s]
 74%|███████▎  | 503/684 [00:41<00:14, 12.82it/s]
 74%|███████▍  | 505/684 [00:41<00:13, 12.99it/s]
 74%|███████▍  | 507/684 [00:42<00:13, 12.67it/s]
 74%|███████▍  | 509/684 [00:42<00:13, 12.86it/s]
 75%|███████▍  | 511/684 [00:42<00:13, 12.84it/s]
 75%|███████▌  | 513/684 [00:42<00:13, 12.96it/s]
 75%|███████▌  | 515/684 [00:42<00:13, 12.77it/s]
 76%|███████▌  | 517/684 [00:42<00:12, 12.88it/s]
 76%|███████▌  | 519/684 [00:43<00:12, 12.99it/s]
 76%|███████▌  | 521/684 [00:43<00:12, 12.77it/s]
 76%|███████▋  | 523/684 [00:43<00:12, 13.11it/s]
 77%|███████▋  | 525/684 [00:43<00:12, 12.88it/s]
 77%|███████▋  | 527/684 [00:43<00:12, 12.81it/s]
 77%|███████▋  | 529/684 [00:43<00:11, 13.01it/s]
 78%|███████▊  | 531/684 [00:43<00:11, 13.12it/s]
 78%|███████▊  | 533/684 [00:44<00:11, 13.01it/s]
 78%|███████▊  | 535/684 [00:44<00:11, 13.22it/s]
 79%|███████▊  | 537/684 [00:44<00:10, 13.44it/s]
 79%|███████▉  | 539/684 [00:44<00:10, 13.60it/s]
 79%|███████▉  | 541/684 [00:44<00:10, 13.77it/s]
 79%|███████▉  | 543/684 [00:44<00:10, 13.71it/s]
 80%|███████▉  | 545/684 [00:45<00:10, 13.81it/s]
 80%|███████▉  | 547/684 [00:45<00:09, 13.92it/s]
 80%|████████  | 549/684 [00:45<00:09, 13.89it/s]
 81%|████████  | 551/684 [00:45<00:09, 13.99it/s]
 81%|████████  | 553/684 [00:45<00:09, 14.05it/s]
 81%|████████  | 555/684 [00:45<00:09, 14.03it/s]
 81%|████████▏ | 557/684 [00:45<00:09, 14.07it/s]
 82%|████████▏ | 559/684 [00:46<00:08, 13.97it/s]
 82%|████████▏ | 561/684 [00:46<00:08, 13.87it/s]
 82%|████████▏ | 563/684 [00:46<00:08, 13.92it/s]
 83%|████████▎ | 565/684 [00:46<00:08, 13.98it/s]
 83%|████████▎ | 567/684 [00:46<00:08, 13.94it/s]
 83%|████████▎ | 569/684 [00:46<00:08, 14.01it/s]
 83%|████████▎ | 571/684 [00:46<00:08, 13.98it/s]
 84%|████████▍ | 573/684 [00:47<00:08, 13.86it/s]
 84%|████████▍ | 575/684 [00:47<00:07, 13.80it/s]
 84%|████████▍ | 577/684 [00:47<00:07, 13.70it/s]
 85%|████████▍ | 579/684 [00:47<00:07, 13.63it/s]
 85%|████████▍ | 581/684 [00:47<00:07, 13.63it/s]
 85%|████████▌ | 583/684 [00:47<00:07, 13.66it/s]
 86%|████████▌ | 585/684 [00:47<00:07, 13.74it/s]
 86%|████████▌ | 587/684 [00:48<00:06, 13.87it/s]
 86%|████████▌ | 589/684 [00:48<00:06, 13.83it/s]
 86%|████████▋ | 591/684 [00:48<00:06, 13.76it/s]
 87%|████████▋ | 593/684 [00:48<00:06, 13.71it/s]
 87%|████████▋ | 595/684 [00:48<00:06, 13.70it/s]
 87%|████████▋ | 597/684 [00:48<00:06, 13.64it/s]
 88%|████████▊ | 599/684 [00:48<00:06, 13.63it/s]
 88%|████████▊ | 601/684 [00:49<00:06, 13.58it/s]
 88%|████████▊ | 603/684 [00:49<00:05, 13.56it/s]
 88%|████████▊ | 605/684 [00:49<00:05, 13.56it/s]
 89%|████████▊ | 607/684 [00:49<00:05, 13.75it/s]
 89%|████████▉ | 609/684 [00:49<00:05, 13.76it/s]
 89%|████████▉ | 611/684 [00:49<00:05, 13.72it/s]
 90%|████████▉ | 613/684 [00:49<00:05, 13.69it/s]
 90%|████████▉ | 615/684 [00:50<00:04, 13.93it/s]
 90%|█████████ | 617/684 [00:50<00:04, 14.00it/s]
 90%|█████████ | 619/684 [00:50<00:04, 13.96it/s]
 91%|█████████ | 621/684 [00:50<00:04, 14.03it/s]
 91%|█████████ | 623/684 [00:50<00:04, 13.93it/s]
 91%|█████████▏| 625/684 [00:50<00:04, 13.94it/s]
 92%|█████████▏| 627/684 [00:50<00:04, 13.77it/s]
 92%|█████████▏| 629/684 [00:51<00:03, 13.82it/s]
 92%|█████████▏| 631/684 [00:51<00:03, 13.82it/s]
 93%|█████████▎| 633/684 [00:51<00:03, 13.70it/s]
 93%|█████████▎| 635/684 [00:51<00:03, 13.63it/s]
 93%|████████���▎| 637/684 [00:51<00:03, 13.64it/s]
 93%|█████████▎| 639/684 [00:51<00:03, 13.62it/s]
 94%|█████████▎| 641/684 [00:51<00:03, 13.69it/s]
 94%|█████████▍| 643/684 [00:52<00:02, 13.81it/s]
 94%|█████████▍| 645/684 [00:52<00:02, 13.73it/s]
 95%|█████████▍| 647/684 [00:52<00:02, 13.71it/s]
 95%|█████████▍| 649/684 [00:52<00:02, 13.68it/s]
 95%|█████████▌| 651/684 [00:52<00:02, 13.60it/s]
 95%|█████████▌| 653/684 [00:52<00:02, 13.53it/s]
 96%|█████████▌| 655/684 [00:52<00:02, 13.53it/s]
 96%|█████████▌| 657/684 [00:53<00:01, 13.55it/s]
 96%|█████████▋| 659/684 [00:53<00:01, 13.53it/s]
 97%|█████████▋| 661/684 [00:53<00:01, 13.51it/s]
 97%|█████████▋| 663/684 [00:53<00:01, 13.52it/s]
 97%|█████████▋| 665/684 [00:53<00:01, 13.48it/s]
 98%|█████████▊| 667/684 [00:53<00:01, 13.35it/s]
 98%|█████████▊| 669/684 [00:54<00:01, 13.33it/s]
 98%|█████████▊| 671/684 [00:54<00:00, 13.38it/s]
 98%|█████████▊| 673/684 [00:54<00:00, 13.40it/s]
 99%|█████████▊| 675/684 [00:54<00:00, 13.43it/s]
 99%|█████████▉| 677/684 [00:54<00:00, 13.49it/s]
 99%|█████████▉| 679/684 [00:54<00:00, 13.49it/s]
                                                 
+
  0%|          | 0/16 [00:00<?, ?it/s]
 12%|█▎        | 2/16 [00:04<00:30,  2.21s/it]
 19%|█▉        | 3/16 [00:08<00:40,  3.12s/it]
 25%|██▌       | 4/16 [00:13<00:43,  3.59s/it]
 31%|███▏      | 5/16 [00:17<00:42,  3.88s/it]
 38%|███▊      | 6/16 [00:22<00:40,  4.06s/it]
 44%|████▍     | 7/16 [00:26<00:37,  4.17s/it]
 50%|█████     | 8/16 [00:30<00:33,  4.24s/it]
 56%|█████▋    | 9/16 [00:35<00:30,  4.29s/it]
 62%|██████▎   | 10/16 [00:39<00:25,  4.32s/it]
 69%|██████▉   | 11/16 [00:44<00:21,  4.35s/it]
 75%|███████▌  | 12/16 [00:48<00:17,  4.36s/it]
 81%|████████▏ | 13/16 [00:52<00:13,  4.38s/it]
 88%|████████▊ | 14/16 [00:57<00:08,  4.39s/it]
 94%|█████████▍| 15/16 [01:01<00:04,  4.40s/it]
+/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/optimization.py:411: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
+  warnings.warn(
+/mnt/storage/aatherton/hf_eng_fra_trans is already a clone of https://huggingface.co/aatherton2024/hf_eng_fra_trans. Make sure you pull the latest changes with `repo.git_pull()`.
+
  0%|          | 0/2736 [00:00<?, ?it/s]
  0%|          | 2/2736 [00:00<03:57, 11.51it/s]
  0%|          | 4/2736 [00:00<03:49, 11.89it/s]
  0%|          | 6/2736 [00:00<03:47, 12.00it/s]
  0%|          | 8/2736 [00:00<03:46, 12.05it/s]
  0%|          | 10/2736 [00:00<03:43, 12.21it/s]
  0%|          | 12/2736 [00:00<03:43, 12.19it/s]
  1%|          | 14/2736 [00:01<03:43, 12.16it/s]
  1%|          | 16/2736 [00:01<03:43, 12.19it/s]
  1%|          | 18/2736 [00:01<03:41, 12.25it/s]
  1%|          | 20/2736 [00:01<03:42, 12.21it/s]
  1%|          | 22/2736 [00:01<03:43, 12.16it/s]
  1%|          | 24/2736 [00:01<03:43, 12.16it/s]
  1%|          | 26/2736 [00:02<03:41, 12.26it/s]
  1%|          | 28/2736 [00:02<03:41, 12.24it/s]
  1%|          | 30/2736 [00:02<03:41, 12.21it/s]
  1%|          | 32/2736 [00:02<03:41, 12.20it/s]
  1%|          | 34/2736 [00:02<03:40, 12.28it/s]
  1%|▏         | 36/2736 [00:02<03:39, 12.30it/s]
  1%|▏         | 38/2736 [00:03<03:38, 12.35it/s]
  1%|▏         | 40/2736 [00:03<03:39, 12.31it/s]
  2%|▏         | 42/2736 [00:03<03:39, 12.25it/s]
  2%|▏         | 44/2736 [00:03<03:37, 12.37it/s]
  2%|▏         | 46/2736 [00:03<03:37, 12.38it/s]
  2%|▏         | 48/2736 [00:03<03:36, 12.42it/s]
  2%|▏         | 50/2736 [00:04<03:35, 12.47it/s]
  2%|▏         | 52/2736 [00:04<03:36, 12.40it/s]
  2%|▏         | 54/2736 [00:04<03:35, 12.45it/s]
  2%|▏         | 56/2736 [00:04<03:36, 12.39it/s]
  2%|▏         | 58/2736 [00:04<03:35, 12.44it/s]
  2%|▏         | 60/2736 [00:04<03:36, 12.38it/s]
  2%|▏         | 62/2736 [00:05<03:36, 12.36it/s]
  2%|▏         | 64/2736 [00:05<03:35, 12.38it/s]
  2%|▏         | 66/2736 [00:05<03:36, 12.32it/s]
  2%|▏         | 68/2736 [00:05<03:37, 12.25it/s]
  3%|▎         | 70/2736 [00:05<03:35, 12.35it/s]
  3%|▎         | 72/2736 [00:05<03:35, 12.36it/s]
  3%|▎         | 74/2736 [00:06<03:34, 12.40it/s]
  3%|▎         | 76/2736 [00:06<03:36, 12.27it/s]
  3%|▎         | 78/2736 [00:06<03:37, 12.24it/s]
  3%|▎         | 80/2736 [00:06<03:36, 12.28it/s]
  3%|▎         | 82/2736 [00:06<03:35, 12.30it/s]
  3%|▎         | 84/2736 [00:06<03:37, 12.22it/s]
  3%|▎         | 86/2736 [00:07<03:36, 12.25it/s]
  3%|▎         | 88/2736 [00:07<03:34, 12.34it/s]
  3%|▎         | 90/2736 [00:07<03:35, 12.28it/s]
  3%|▎         | 92/2736 [00:07<03:34, 12.33it/s]
  3%|▎         | 94/2736 [00:07<03:34, 12.32it/s]
  4%|▎         | 96/2736 [00:07<03:34, 12.29it/s]
  4%|▎         | 98/2736 [00:07<03:35, 12.27it/s]
  4%|▎         | 100/2736 [00:08<03:33, 12.36it/s]
  4%|▎         | 102/2736 [00:08<03:33, 12.32it/s]
  4%|▍         | 104/2736 [00:08<03:32, 12.40it/s]
  4%|▍         | 106/2736 [00:08<03:33, 12.32it/s]
  4%|▍         | 108/2736 [00:08<03:34, 12.25it/s]
  4%|▍         | 110/2736 [00:08<03:35, 12.20it/s]
  4%|▍         | 112/2736 [00:09<03:32, 12.36it/s]
  4%|▍         | 114/2736 [00:09<03:33, 12.28it/s]
  4%|▍         | 116/2736 [00:09<03:33, 12.26it/s]
  4%|▍         | 118/2736 [00:09<03:32, 12.33it/s]
  4%|▍         | 120/2736 [00:09<03:32, 12.30it/s]
  4%|▍         | 122/2736 [00:09<03:31, 12.36it/s]
  5%|▍         | 124/2736 [00:10<03:31, 12.33it/s]
  5%|▍         | 126/2736 [00:10<03:32, 12.28it/s]
  5%|▍         | 128/2736 [00:10<03:31, 12.33it/s]
  5%|▍         | 130/2736 [00:10<03:30, 12.36it/s]
  5%|▍         | 132/2736 [00:10<03:29, 12.41it/s]
  5%|▍         | 134/2736 [00:10<03:30, 12.35it/s]
  5%|▍         | 136/2736 [00:11<03:29, 12.41it/s]
  5%|▌         | 138/2736 [00:11<03:30, 12.34it/s]
  5%|▌         | 140/2736 [00:11<03:28, 12.45it/s]
  5%|▌         | 142/2736 [00:11<03:29, 12.38it/s]
  5%|▌         | 144/2736 [00:11<03:28, 12.44it/s]
  5%|▌         | 146/2736 [00:11<03:29, 12.37it/s]
  5%|▌         | 148/2736 [00:12<03:27, 12.45it/s]
  5%|▌         | 150/2736 [00:12<03:28, 12.39it/s]
  6%|▌         | 152/2736 [00:12<03:29, 12.33it/s]
  6%|▌         | 154/2736 [00:12<03:30, 12.25it/s]
  6%|▌         | 156/2736 [00:12<03:31, 12.21it/s]
  6%|▌         | 158/2736 [00:12<03:29, 12.32it/s]
  6%|▌         | 160/2736 [00:13<03:29, 12.31it/s]
  6%|▌         | 162/2736 [00:13<03:27, 12.42it/s]
  6%|▌         | 164/2736 [00:13<03:28, 12.34it/s]
  6%|▌         | 166/2736 [00:13<03:27, 12.40it/s]
  6%|▌         | 168/2736 [00:13<03:27, 12.38it/s]
  6%|▌         | 170/2736 [00:13<03:28, 12.34it/s]
  6%|▋         | 172/2736 [00:13<03:26, 12.41it/s]
  6%|▋         | 174/2736 [00:14<03:27, 12.34it/s]
  6%|▋         | 176/2736 [00:14<03:29, 12.24it/s]
  7%|▋         | 178/2736 [00:14<03:29, 12.21it/s]
  7%|▋         | 180/2736 [00:14<03:28, 12.25it/s]
  7%|▋         | 182/2736 [00:14<03:27, 12.33it/s]
  7%|▋         | 184/2736 [00:14<03:27, 12.27it/s]
  7%|▋         | 186/2736 [00:15<03:26, 12.35it/s]
  7%|▋         | 188/2736 [00:15<03:27, 12.28it/s]
  7%|▋         | 190/2736 [00:15<03:27, 12.26it/s]
  7%|▋         | 192/2736 [00:15<03:27, 12.24it/s]
  7%|▋         | 194/2736 [00:15<03:25, 12.35it/s]
  7%|▋         | 196/2736 [00:15<03:24, 12.40it/s]
  7%|▋         | 198/2736 [00:16<03:25, 12.38it/s]
  7%|▋         | 200/2736 [00:16<03:23, 12.45it/s]
  7%|▋         | 202/2736 [00:16<03:24, 12.37it/s]
  7%|▋         | 204/2736 [00:16<03:25, 12.30it/s]
  8%|▊         | 206/2736 [00:16<03:24, 12.38it/s]
  8%|▊         | 208/2736 [00:16<03:24, 12.34it/s]
  8%|▊         | 210/2736 [00:17<03:23, 12.42it/s]
  8%|▊         | 212/2736 [00:17<03:24, 12.35it/s]
  8%|▊         | 214/2736 [00:17<03:23, 12.37it/s]
  8%|▊         | 216/2736 [00:17<03:24, 12.35it/s]
  8%|▊         | 218/2736 [00:17<03:24, 12.29it/s]
  8%|▊         | 220/2736 [00:17<03:22, 12.41it/s]
  8%|▊         | 222/2736 [00:18<03:23, 12.33it/s]
  8%|▊         | 224/2736 [00:18<03:22, 12.41it/s]
  8%|▊         | 226/2736 [00:18<03:23, 12.35it/s]
  8%|▊         | 228/2736 [00:18<03:24, 12.29it/s]
  8%|▊         | 230/2736 [00:18<03:21, 12.41it/s]
  8%|▊         | 232/2736 [00:18<03:23, 12.33it/s]
  9%|▊         | 234/2736 [00:19<03:22, 12.34it/s]
  9%|▊         | 236/2736 [00:19<03:21, 12.39it/s]
  9%|▊         | 238/2736 [00:19<03:22, 12.33it/s]
  9%|▉         | 240/2736 [00:19<03:21, 12.36it/s]
  9%|▉         | 242/2736 [00:19<03:22, 12.35it/s]
  9%|▉         | 244/2736 [00:19<03:22, 12.33it/s]
  9%|▉         | 246/2736 [00:19<03:21, 12.36it/s]
  9%|▉         | 248/2736 [00:20<03:22, 12.28it/s]
  9%|▉         | 250/2736 [00:20<03:20, 12.38it/s]
  9%|▉         | 252/2736 [00:20<03:21, 12.32it/s]
  9%|▉         | 254/2736 [00:20<03:21, 12.31it/s]
  9%|▉         | 256/2736 [00:20<03:20, 12.36it/s]
  9%|▉         | 258/2736 [00:20<03:21, 12.32it/s]
 10%|▉         | 260/2736 [00:21<03:19, 12.39it/s]
 10%|▉         | 262/2736 [00:21<03:20, 12.33it/s]
 10%|▉         | 264/2736 [00:21<03:19, 12.39it/s]
 10%|▉         | 266/2736 [00:21<03:20, 12.32it/s]
 10%|▉         | 268/2736 [00:21<03:18, 12.46it/s]
 10%|▉         | 270/2736 [00:21<03:19, 12.37it/s]
 10%|▉         | 272/2736 [00:22<03:20, 12.29it/s]
 10%|█         | 274/2736 [00:22<03:19, 12.36it/s]
 10%|█         | 276/2736 [00:22<03:20, 12.30it/s]
 10%|█         | 278/2736 [00:22<03:18, 12.40it/s]
 10%|█         | 280/2736 [00:22<03:19, 12.33it/s]
 10%|█         | 282/2736 [00:22<03:18, 12.34it/s]
 10%|█         | 284/2736 [00:23<03:18, 12.38it/s]
 10%|█         | 286/2736 [00:23<03:18, 12.32it/s]
 11%|█         | 288/2736 [00:23<03:17, 12.40it/s]
 11%|█         | 290/2736 [00:23<03:16, 12.43it/s]
 11%|█         | 292/2736 [00:23<03:16, 12.46it/s]
 11%|█         | 294/2736 [00:23<03:15, 12.48it/s]
 11%|█         | 296/2736 [00:24<03:16, 12.45it/s]
 11%|█         | 298/2736 [00:24<03:15, 12.46it/s]
 11%|█         | 300/2736 [00:24<03:15, 12.45it/s]
 11%|█         | 302/2736 [00:24<03:14, 12.52it/s]
 11%|█         | 304/2736 [00:24<03:16, 12.39it/s]
 11%|█         | 306/2736 [00:24<03:16, 12.35it/s]
 11%|█▏        | 308/2736 [00:24<03:16, 12.37it/s]
 11%|█▏        | 310/2736 [00:25<03:15, 12.40it/s]
 11%|█▏        | 312/2736 [00:25<03:15, 12.40it/s]
 11%|█▏        | 314/2736 [00:25<03:15, 12.39it/s]
 12%|█▏        | 316/2736 [00:25<03:14, 12.43it/s]
 12%|█▏        | 318/2736 [00:25<03:14, 12.43it/s]
 12%|█▏        | 320/2736 [00:25<03:14, 12.43it/s]
 12%|█▏        | 322/2736 [00:26<03:15, 12.35it/s]
 12%|█▏        | 324/2736 [00:26<03:13, 12.44it/s]
 12%|█▏        | 326/2736 [00:26<03:15, 12.35it/s]
 12%|█▏        | 328/2736 [00:26<03:15, 12.30it/s]
 12%|█▏        | 330/2736 [00:26<03:14, 12.40it/s]
 12%|█▏        | 332/2736 [00:26<03:14, 12.34it/s]
 12%|█▏        | 334/2736 [00:27<03:13, 12.44it/s]
 12%|█▏        | 336/2736 [00:27<03:14, 12.36it/s]
 12%|█▏        | 338/2736 [00:27<03:12, 12.43it/s]
 12%|█▏        | 340/2736 [00:27<03:13, 12.37it/s]
 12%|█▎        | 342/2736 [00:27<03:13, 12.40it/s]
 13%|█▎        | 344/2736 [00:27<03:13, 12.35it/s]
 13%|█▎        | 346/2736 [00:28<03:14, 12.29it/s]
 13%|█▎        | 348/2736 [00:28<03:14, 12.30it/s]
 13%|█▎        | 350/2736 [00:28<03:12, 12.37it/s]
 13%|█▎        | 352/2736 [00:28<03:13, 12.30it/s]
 13%|█▎        | 354/2736 [00:28<03:11, 12.42it/s]
 13%|█▎        | 356/2736 [00:28<03:13, 12.32it/s]
 13%|█▎        | 358/2736 [00:29<03:11, 12.39it/s]
 13%|█▎        | 360/2736 [00:29<03:12, 12.33it/s]
 13%|█▎        | 362/2736 [00:29<03:12, 12.34it/s]
 13%|█▎        | 364/2736 [00:29<03:11, 12.37it/s]
 13%|█▎        | 366/2736 [00:29<03:12, 12.31it/s]
 13%|█▎        | 368/2736 [00:29<03:10, 12.41it/s]
 14%|█▎        | 370/2736 [00:29<03:12, 12.31it/s]
 14%|█▎        | 372/2736 [00:30<03:12, 12.31it/s]
 14%|█▎        | 374/2736 [00:30<03:10, 12.38it/s]
 14%|█▎        | 376/2736 [00:30<03:11, 12.32it/s]
 14%|█▍        | 378/2736 [00:30<03:10, 12.41it/s]
 14%|█▍        | 380/2736 [00:30<03:11, 12.33it/s]
 14%|█▍        | 382/2736 [00:30<03:12, 12.25it/s]
 14%|█▍        | 384/2736 [00:31<03:11, 12.27it/s]
 14%|█▍        | 386/2736 [00:31<03:10, 12.33it/s]
 14%|█▍        | 388/2736 [00:31<03:11, 12.28it/s]
 14%|█▍        | 390/2736 [00:31<03:11, 12.25it/s]
 14%|█▍        | 392/2736 [00:31<03:10, 12.28it/s]
 14%|█▍        | 394/2736 [00:31<03:09, 12.33it/s]
 14%|█▍        | 396/2736 [00:32<03:10, 12.26it/s]
 15%|█▍        | 398/2736 [00:32<03:10, 12.29it/s]
 15%|█▍        | 400/2736 [00:32<03:09, 12.34it/s]
 15%|█▍        | 402/2736 [00:32<03:09, 12.29it/s]
 15%|█▍        | 404/2736 [00:32<03:08, 12.39it/s]
 15%|█▍        | 406/2736 [00:32<03:09, 12.31it/s]
 15%|█▍        | 408/2736 [00:33<03:07, 12.41it/s]
 15%|█▍        | 410/2736 [00:33<03:08, 12.36it/s]
 15%|█▌        | 412/2736 [00:33<03:06, 12.44it/s]
 15%|█▌        | 414/2736 [00:33<03:07, 12.37it/s]
 15%|█▌        | 416/2736 [00:33<03:08, 12.31it/s]
 15%|█▌        | 418/2736 [00:33<03:06, 12.42it/s]
 15%|█▌        | 420/2736 [00:34<03:07, 12.37it/s]
 15%|█▌        | 422/2736 [00:34<03:07, 12.32it/s]
 15%|█▌        | 424/2736 [00:34<03:06, 12.39it/s]
 16%|█▌        | 426/2736 [00:34<03:07, 12.35it/s]
 16%|█▌        | 428/2736 [00:34<03:06, 12.40it/s]
 16%|█▌        | 430/2736 [00:34<03:06, 12.37it/s]
 16%|█▌        | 432/2736 [00:35<03:05, 12.39it/s]
 16%|█▌        | 434/2736 [00:35<03:05, 12.39it/s]
 16%|█▌        | 436/2736 [00:35<03:06, 12.34it/s]
 16%|█▌        | 438/2736 [00:35<03:05, 12.41it/s]
 16%|█▌        | 440/2736 [00:35<03:05, 12.35it/s]
 16%|█▌        | 442/2736 [00:35<03:07, 12.25it/s]
 16%|█▌        | 444/2736 [00:35<03:06, 12.28it/s]
 16%|█▋        | 446/2736 [00:36<03:05, 12.35it/s]
 16%|█▋        | 448/2736 [00:36<03:04, 12.40it/s]
 16%|█▋        | 450/2736 [00:36<03:04, 12.36it/s]
 17%|█▋        | 452/2736 [00:36<03:05, 12.30it/s]
 17%|█▋        | 454/2736 [00:36<03:06, 12.25it/s]
 17%|█▋        | 456/2736 [00:36<03:04, 12.37it/s]
 17%|█▋        | 458/2736 [00:37<03:05, 12.31it/s]
 17%|█▋        | 460/2736 [00:37<03:03, 12.37it/s]
 17%|█▋        | 462/2736 [00:37<03:05, 12.29it/s]
 17%|█▋        | 464/2736 [00:37<03:05, 12.23it/s]
 17%|█▋        | 466/2736 [00:37<03:05, 12.22it/s]
 17%|█▋        | 468/2736 [00:37<03:05, 12.20it/s]
 17%|█▋        | 470/2736 [00:38<03:03, 12.33it/s]
 17%|█▋        | 472/2736 [00:38<03:03, 12.31it/s]
 17%|█▋        | 474/2736 [00:38<03:03, 12.34it/s]
 17%|█▋        | 476/2736 [00:38<03:03, 12.34it/s]
 17%|█▋        | 478/2736 [00:38<03:02, 12.36it/s]
 18%|█▊        | 480/2736 [00:38<03:01, 12.43it/s]
 18%|█▊        | 482/2736 [00:39<03:02, 12.37it/s]
 18%|█▊        | 484/2736 [00:39<03:02, 12.31it/s]
 18%|█▊        | 486/2736 [00:39<03:02, 12.32it/s]
 18%|█▊        | 488/2736 [00:39<03:01, 12.35it/s]
 18%|█▊        | 490/2736 [00:39<03:02, 12.30it/s]
 18%|█▊        | 492/2736 [00:39<03:01, 12.39it/s]
 18%|█▊        | 494/2736 [00:40<03:01, 12.34it/s]
 18%|█▊        | 496/2736 [00:40<03:02, 12.29it/s]
 18%|█▊        | 498/2736 [00:40<03:02, 12.25it/s]
 18%|█▊        | 500/2736 [00:40<03:01, 12.29it/s]
 18%|█▊        | 502/2736 [00:40<03:00, 12.35it/s]
 18%|█▊        | 504/2736 [00:40<03:01, 12.30it/s]
 18%|█▊        | 506/2736 [00:41<03:00, 12.37it/s]
 19%|█▊        | 508/2736 [00:41<03:02, 12.24it/s]
 19%|█▊        | 510/2736 [00:41<03:00, 12.35it/s]
 19%|█▊        | 512/2736 [00:41<03:01, 12.28it/s]
 19%|█▉        | 514/2736 [00:41<03:01, 12.27it/s]
 19%|█▉        | 516/2736 [00:41<02:59, 12.34it/s]
 19%|█▉        | 518/2736 [00:41<02:59, 12.34it/s]
 19%|█▉        | 520/2736 [00:42<02:58, 12.41it/s]
 19%|█▉        | 522/2736 [00:42<02:59, 12.37it/s]
 19%|█▉        | 524/2736 [00:42<02:57, 12.48it/s]
 19%|█▉        | 526/2736 [00:42<02:56, 12.50it/s]
 19%|█▉        | 528/2736 [00:42<02:57, 12.44it/s]
 19%|█▉        | 530/2736 [00:42<02:56, 12.53it/s]
 19%|█▉        | 532/2736 [00:43<02:55, 12.56it/s]
 20%|█▉        | 534/2736 [00:43<02:56, 12.45it/s]
 20%|█▉        | 536/2736 [00:43<02:56, 12.46it/s]
 20%|█▉        | 538/2736 [00:43<02:57, 12.39it/s]
 20%|█▉        | 540/2736 [00:43<02:56, 12.43it/s]
 20%|█▉        | 542/2736 [00:43<02:57, 12.38it/s]
 20%|█▉        | 544/2736 [00:44<02:57, 12.36it/s]
 20%|█▉        | 546/2736 [00:44<02:56, 12.39it/s]
 20%|██        | 548/2736 [00:44<02:56, 12.39it/s]
 20%|██        | 550/2736 [00:44<02:56, 12.39it/s]
 20%|██        | 552/2736 [00:44<02:57, 12.33it/s]
 20%|██        | 554/2736 [00:44<02:57, 12.27it/s]
 20%|██        | 556/2736 [00:45<02:55, 12.40it/s]
 20%|██        | 558/2736 [00:45<02:55, 12.39it/s]
 20%|██        | 560/2736 [00:45<02:55, 12.43it/s]
 21%|██        | 562/2736 [00:45<02:55, 12.39it/s]
 21%|██        | 564/2736 [00:45<02:54, 12.44it/s]
 21%|██        | 566/2736 [00:45<02:55, 12.40it/s]
 21%|██        | 568/2736 [00:46<02:54, 12.45it/s]
 21%|██        | 570/2736 [00:46<02:55, 12.35it/s]
 21%|██        | 572/2736 [00:46<02:53, 12.44it/s]
 21%|██        | 574/2736 [00:46<02:54, 12.37it/s]
 21%|██        | 576/2736 [00:46<02:53, 12.45it/s]
 21%|██        | 578/2736 [00:46<02:54, 12.40it/s]
 21%|██        | 580/2736 [00:46<02:54, 12.34it/s]
 21%|██▏       | 582/2736 [00:47<02:53, 12.43it/s]
 21%|██▏       | 584/2736 [00:47<02:54, 12.35it/s]
 21%|██▏       | 586/2736 [00:47<02:53, 12.40it/s]
 21%|██▏       | 588/2736 [00:47<02:54, 12.32it/s]
 22%|██▏       | 590/2736 [00:47<02:55, 12.26it/s]
 22%|██▏       | 592/2736 [00:47<02:53, 12.38it/s]
 22%|██▏       | 594/2736 [00:48<02:53, 12.32it/s]
 22%|██▏       | 596/2736 [00:48<02:54, 12.27it/s]
 22%|██▏       | 598/2736 [00:48<02:52, 12.39it/s]
 22%|██▏       | 600/2736 [00:48<02:53, 12.32it/s]
 22%|██▏       | 602/2736 [00:48<02:52, 12.35it/s]
 22%|██▏       | 604/2736 [00:48<02:52, 12.39it/s]
 22%|██▏       | 606/2736 [00:49<02:51, 12.41it/s]
 22%|██▏       | 608/2736 [00:49<02:51, 12.42it/s]
 22%|██▏       | 610/2736 [00:49<02:50, 12.46it/s]
 22%|██▏       | 612/2736 [00:49<02:50, 12.42it/s]
 22%|██▏       | 614/2736 [00:49<02:50, 12.44it/s]
 23%|██▎       | 616/2736 [00:49<02:51, 12.35it/s]
 23%|██▎       | 618/2736 [00:50<02:50, 12.44it/s]
 23%|██▎       | 620/2736 [00:50<02:51, 12.36it/s]
 23%|██▎       | 622/2736 [00:50<02:49, 12.46it/s]
 23%|██▎       | 624/2736 [00:50<02:50, 12.37it/s]
 23%|██▎       | 626/2736 [00:50<02:51, 12.33it/s]
 23%|██▎       | 628/2736 [00:50<02:49, 12.41it/s]
 23%|██▎       | 630/2736 [00:51<02:50, 12.34it/s]
 23%|██▎       | 632/2736 [00:51<02:50, 12.34it/s]
 23%|██▎       | 634/2736 [00:51<02:49, 12.39it/s]
 23%|██▎       | 636/2736 [00:51<02:49, 12.36it/s]
 23%|██▎       | 638/2736 [00:51<02:48, 12.42it/s]
 23%|██▎       | 640/2736 [00:51<02:49, 12.34it/s]
 23%|██▎       | 642/2736 [00:51<02:48, 12.45it/s]
 24%|██▎       | 644/2736 [00:52<02:49, 12.37it/s]
 24%|██▎       | 646/2736 [00:52<02:47, 12.49it/s]
 24%|██▎       | 648/2736 [00:52<02:48, 12.39it/s]
 24%|██▍       | 650/2736 [00:52<02:47, 12.45it/s]
 24%|██▍       | 652/2736 [00:52<02:48, 12.36it/s]
 24%|██▍       | 654/2736 [00:52<02:49, 12.31it/s]
 24%|██▍       | 656/2736 [00:53<02:47, 12.40it/s]
 24%|██▍       | 658/2736 [00:53<02:47, 12.38it/s]
 24%|██▍       | 660/2736 [00:53<02:47, 12.43it/s]
 24%|██▍       | 662/2736 [00:53<02:48, 12.34it/s]
 24%|██▍       | 664/2736 [00:53<02:46, 12.42it/s]
 24%|██▍       | 666/2736 [00:53<02:47, 12.32it/s]
 24%|██▍       | 668/2736 [00:54<02:47, 12.33it/s]
 24%|██▍       | 670/2736 [00:54<02:47, 12.37it/s]
 25%|██▍       | 672/2736 [00:54<02:47, 12.31it/s]
 25%|██▍       | 674/2736 [00:54<02:47, 12.32it/s]
 25%|██▍       | 676/2736 [00:54<02:46, 12.36it/s]
 25%|██▍       | 678/2736 [00:54<02:45, 12.44it/s]
 25%|██▍       | 680/2736 [00:55<02:46, 12.37it/s]
 25%|██▍       | 682/2736 [00:55<02:46, 12.36it/s]
 25%|██▌       | 684/2736 [00:55<02:45, 12.38it/s]
 25%|██▌       | 686/2736 [00:55<02:45, 12.37it/s]
 25%|██▌       | 688/2736 [00:55<02:45, 12.39it/s]
 25%|██▌       | 690/2736 [00:55<02:45, 12.33it/s]
 25%|██▌       | 692/2736 [00:56<02:45, 12.37it/s]
 25%|██▌       | 694/2736 [00:56<02:45, 12.35it/s]
 25%|██▌       | 696/2736 [00:56<02:42, 12.53it/s]
 26%|██▌       | 698/2736 [00:56<02:33, 13.32it/s]
 26%|██▌       | 700/2736 [00:56<02:37, 12.95it/s]
 26%|██▌       | 702/2736 [00:56<02:38, 12.87it/s]
 26%|██▌       | 704/2736 [00:56<02:40, 12.65it/s]
 26%|██▌       | 706/2736 [00:57<02:40, 12.62it/s]
 26%|██▌       | 708/2736 [00:57<02:42, 12.47it/s]
 26%|██▌       | 710/2736 [00:57<02:41, 12.53it/s]
 26%|██▌       | 712/2736 [00:57<02:42, 12.43it/s]
 26%|██▌       | 714/2736 [00:57<02:42, 12.41it/s]
 26%|██▌       | 716/2736 [00:57<02:42, 12.43it/s]
 26%|██▌       | 718/2736 [00:58<02:43, 12.34it/s]
 26%|██▋       | 720/2736 [00:58<02:43, 12.29it/s]
 26%|██▋       | 722/2736 [00:58<02:42, 12.37it/s]
 26%|██▋       | 724/2736 [00:58<02:43, 12.31it/s]
 27%|██▋       | 726/2736 [00:58<02:42, 12.35it/s]
 27%|██▋       | 728/2736 [00:58<02:42, 12.39it/s]
 27%|██▋       | 730/2736 [00:59<02:42, 12.32it/s]
 27%|██▋       | 732/2736 [00:59<02:43, 12.26it/s]
 27%|██▋       | 734/2736 [00:59<02:41, 12.37it/s]
 27%|██▋       | 736/2736 [00:59<02:42, 12.33it/s]
 27%|██▋       | 738/2736 [00:59<02:42, 12.28it/s]
 27%|██▋       | 740/2736 [00:59<02:43, 12.24it/s]
 27%|██▋       | 742/2736 [01:00<02:41, 12.33it/s]
 27%|██▋       | 744/2736 [01:00<02:41, 12.31it/s]
 27%|██▋       | 746/2736 [01:00<02:40, 12.43it/s]
 27%|██▋       | 748/2736 [01:00<02:41, 12.33it/s]
 27%|██▋       | 750/2736 [01:00<02:37, 12.58it/s]
 27%|██▋       | 752/2736 [01:00<02:29, 13.26it/s]
 28%|██▊       | 754/2736 [01:00<02:30, 13.16it/s]
 28%|██▊       | 756/2736 [01:01<02:34, 12.84it/s]
 28%|██▊       | 758/2736 [01:01<02:34, 12.81it/s]
 28%|██▊       | 760/2736 [01:01<02:36, 12.66it/s]
 28%|██▊       | 762/2736 [01:01<02:36, 12.65it/s]
 28%|██▊       | 764/2736 [01:01<02:36, 12.60it/s]
 28%|██▊       | 766/2736 [01:01<02:36, 12.58it/s]
 28%|██▊       | 768/2736 [01:02<02:36, 12.54it/s]
 28%|██▊       | 770/2736 [01:02<02:36, 12.52it/s]
 28%|██▊       | 772/2736 [01:02<02:36, 12.56it/s]
 28%|██▊       | 774/2736 [01:02<02:36, 12.53it/s]
 28%|██▊       | 776/2736 [01:02<02:36, 12.51it/s]
 28%|██▊       | 778/2736 [01:02<02:36, 12.52it/s]
 29%|██▊       | 780/2736 [01:03<02:36, 12.46it/s]
 29%|██▊       | 782/2736 [01:03<02:36, 12.47it/s]
 29%|██▊       | 784/2736 [01:03<02:36, 12.46it/s]
 29%|██▊       | 786/2736 [01:03<02:36, 12.44it/s]
 29%|██▉       | 788/2736 [01:03<02:36, 12.45it/s]
 29%|██▉       | 790/2736 [01:03<02:35, 12.53it/s]
 29%|██▉       | 792/2736 [01:04<02:36, 12.42it/s]
 29%|██▉       | 794/2736 [01:04<02:35, 12.47it/s]
 29%|██▉       | 796/2736 [01:04<02:36, 12.39it/s]
 29%|██▉       | 798/2736 [01:04<02:36, 12.39it/s]
 29%|██▉       | 800/2736 [01:04<02:36, 12.38it/s]
 29%|██▉       | 802/2736 [01:04<02:36, 12.32it/s]
 29%|██▉       | 804/2736 [01:05<02:36, 12.32it/s]
 29%|██▉       | 806/2736 [01:05<02:27, 13.04it/s]
 30%|██▉       | 808/2736 [01:05<02:25, 13.24it/s]
 30%|██▉       | 810/2736 [01:05<02:29, 12.89it/s]
 30%|██▉       | 812/2736 [01:05<02:31, 12.71it/s]
 30%|██▉       | 814/2736 [01:05<02:31, 12.66it/s]
 30%|██▉       | 816/2736 [01:05<02:33, 12.50it/s]
 30%|██▉       | 818/2736 [01:06<02:34, 12.40it/s]
 30%|██▉       | 820/2736 [01:06<02:33, 12.47it/s]
 30%|███       | 822/2736 [01:06<02:34, 12.38it/s]
 30%|███       | 824/2736 [01:06<02:34, 12.38it/s]
 30%|███       | 826/2736 [01:06<02:33, 12.42it/s]
 30%|███       | 828/2736 [01:06<02:33, 12.46it/s]
 30%|███       | 830/2736 [01:07<02:34, 12.37it/s]
 30%|███       | 832/2736 [01:07<02:33, 12.38it/s]
 30%|███       | 834/2736 [01:07<02:33, 12.40it/s]
 31%|███       | 836/2736 [01:07<02:33, 12.38it/s]
 31%|███       | 838/2736 [01:07<02:33, 12.37it/s]
 31%|███       | 840/2736 [01:07<02:33, 12.33it/s]
 31%|███       | 842/2736 [01:08<02:34, 12.24it/s]
 31%|███       | 844/2736 [01:08<02:34, 12.21it/s]
 31%|███       | 846/2736 [01:08<02:33, 12.31it/s]
 31%|███       | 848/2736 [01:08<02:33, 12.27it/s]
 31%|███       | 850/2736 [01:08<02:34, 12.24it/s]
 31%|███       | 852/2736 [01:08<02:32, 12.35it/s]
 31%|███       | 854/2736 [01:09<02:33, 12.29it/s]
 31%|███▏      | 856/2736 [01:09<02:33, 12.27it/s]
 31%|███▏      | 858/2736 [01:09<02:33, 12.22it/s]
 31%|███▏      | 860/2736 [01:09<02:24, 12.96it/s]
 32%|███▏      | 862/2736 [01:09<02:21, 13.28it/s]
 32%|███▏      | 864/2736 [01:09<02:24, 12.99it/s]
 32%|███▏      | 866/2736 [01:09<02:27, 12.72it/s]
 32%|███▏      | 868/2736 [01:10<02:27, 12.63it/s]
 32%|███▏      | 870/2736 [01:10<02:28, 12.58it/s]
 32%|███▏      | 872/2736 [01:10<02:29, 12.43it/s]
 32%|███▏      | 874/2736 [01:10<02:29, 12.48it/s]
 32%|███▏      | 876/2736 [01:10<02:30, 12.36it/s]
 32%|███▏      | 878/2736 [01:10<02:29, 12.42it/s]
 32%|███▏      | 880/2736 [01:11<02:30, 12.34it/s]
 32%|███▏      | 882/2736 [01:11<02:31, 12.26it/s]
 32%|███▏      | 884/2736 [01:11<02:29, 12.37it/s]
 32%|███▏      | 886/2736 [01:11<02:30, 12.31it/s]
 32%|███▏      | 888/2736 [01:11<02:30, 12.27it/s]
 33%|███▎      | 890/2736 [01:11<02:30, 12.23it/s]
 33%|███▎      | 892/2736 [01:12<02:30, 12.21it/s]
 33%|███▎      | 894/2736 [01:12<02:29, 12.35it/s]
 33%|███▎      | 896/2736 [01:12<02:29, 12.31it/s]
 33%|███▎      | 898/2736 [01:12<02:28, 12.36it/s]
 33%|███▎      | 900/2736 [01:12<02:28, 12.35it/s]
 33%|███▎      | 902/2736 [01:12<02:29, 12.30it/s]
 33%|███▎      | 904/2736 [01:13<02:27, 12.40it/s]
 33%|███▎      | 906/2736 [01:13<02:28, 12.32it/s]
 33%|███▎      | 908/2736 [01:13<02:27, 12.40it/s]
 33%|███▎      | 910/2736 [01:13<02:28, 12.32it/s]
 33%|███▎      | 912/2736 [01:13<02:27, 12.36it/s]
+
  0%|          | 0/126 [00:00<?, ?it/s]
+
  1%|          | 1/126 [00:01<02:40,  1.29s/it]
+
  2%|▏         | 2/126 [00:02<02:36,  1.26s/it]
+
  2%|▏         | 3/126 [00:03<02:34,  1.26s/it]
+
  3%|▎         | 4/126 [00:05<02:32,  1.25s/it]
+
  4%|▍         | 5/126 [00:06<02:30,  1.24s/it]
+
  5%|▍         | 6/126 [00:07<02:28,  1.24s/it]
+
  6%|▌         | 7/126 [00:08<02:27,  1.24s/it]
+
  6%|▋         | 8/126 [00:09<02:26,  1.24s/it]
+
  7%|▋         | 9/126 [00:11<02:24,  1.24s/it]
+
  8%|▊         | 10/126 [00:12<02:23,  1.24s/it]
+
  9%|▊         | 11/126 [00:13<02:22,  1.24s/it]
 33%|███▎      | 912/2736 [01:27<02:27, 12.36it/s]
+
 10%|▉         | 12/126 [00:14<02:20,  1.24s/it]
+
 10%|█         | 13/126 [00:16<02:19,  1.24s/it]
+
 11%|█         | 14/126 [00:17<02:18,  1.23s/it]
+
 12%|█▏        | 15/126 [00:18<02:17,  1.24s/it]
+
 13%|█▎        | 16/126 [00:19<02:15,  1.24s/it]
+
 13%|█▎        | 17/126 [00:21<02:14,  1.24s/it]
+
 14%|█▍        | 18/126 [00:22<02:13,  1.24s/it]
+
 15%|█▌        | 19/126 [00:23<02:12,  1.24s/it]
+
 16%|█▌        | 20/126 [00:24<02:11,  1.24s/it]
+
 17%|█▋        | 21/126 [00:26<02:09,  1.24s/it]
+
 17%|█▋        | 22/126 [00:27<02:08,  1.24s/it]
+
 18%|█▊        | 23/126 [00:28<02:07,  1.24s/it]
+
 19%|█▉        | 24/126 [00:29<02:06,  1.24s/it]
+
 20%|█▉        | 25/126 [00:30<02:04,  1.24s/it]
+
 21%|██        | 26/126 [00:32<02:03,  1.24s/it]
+
 21%|██▏       | 27/126 [00:33<02:02,  1.24s/it]
+
 22%|██▏       | 28/126 [00:34<02:01,  1.24s/it]
+
 23%|██▎       | 29/126 [00:35<02:00,  1.24s/it]
+
 24%|██▍       | 30/126 [00:37<01:58,  1.24s/it]
+
 25%|██▍       | 31/126 [00:38<01:57,  1.24s/it]
+
 25%|██▌       | 32/126 [00:39<01:56,  1.24s/it]
+
 26%|██▌       | 33/126 [00:40<01:55,  1.24s/it]
+
 27%|██▋       | 34/126 [00:42<01:53,  1.24s/it]
+
 28%|██▊       | 35/126 [00:43<01:52,  1.24s/it]
+
 29%|██▊       | 36/126 [00:44<01:51,  1.24s/it]
+
 29%|██▉       | 37/126 [00:45<01:50,  1.24s/it]
+
 30%|███       | 38/126 [00:47<01:48,  1.24s/it]
+
 31%|███       | 39/126 [00:48<01:47,  1.24s/it]
+
 32%|███▏      | 40/126 [00:49<01:46,  1.24s/it]
+
 33%|███▎      | 41/126 [00:50<01:45,  1.24s/it]
+
 33%|███▎      | 42/126 [00:52<01:44,  1.24s/it]
+
 34%|███▍      | 43/126 [00:53<01:42,  1.24s/it]
+
 35%|███▍      | 44/126 [00:54<01:41,  1.24s/it]
+
 36%|███▌      | 45/126 [00:55<01:40,  1.24s/it]
+
 37%|███▋      | 46/126 [00:56<01:39,  1.24s/it]
+
 37%|███▋      | 47/126 [00:58<01:37,  1.24s/it]
+
 38%|███▊      | 48/126 [00:59<01:36,  1.24s/it]
+
 39%|███▉      | 49/126 [01:00<01:35,  1.24s/it]
+
 40%|███▉      | 50/126 [01:01<01:34,  1.24s/it]
+
 40%|████      | 51/126 [01:03<01:32,  1.24s/it]
+
 41%|████▏     | 52/126 [01:04<01:31,  1.24s/it]
+
 42%|████▏     | 53/126 [01:05<01:30,  1.24s/it]
+
 43%|████▎     | 54/126 [01:06<01:29,  1.24s/it]
+
 44%|████▎     | 55/126 [01:08<01:27,  1.24s/it]
+
 44%|████▍     | 56/126 [01:09<01:26,  1.24s/it]
+
 45%|████▌     | 57/126 [01:10<01:25,  1.24s/it]
+
 46%|████▌     | 58/126 [01:11<01:24,  1.24s/it]
+
 47%|████▋     | 59/126 [01:13<01:22,  1.24s/it]
+
 48%|████▊     | 60/126 [01:14<01:21,  1.24s/it]
+
 48%|████▊     | 61/126 [01:15<01:20,  1.24s/it]
+
 49%|████▉     | 62/126 [01:16<01:19,  1.24s/it]
+
 50%|█████     | 63/126 [01:18<01:17,  1.24s/it]
+
 51%|█████     | 64/126 [01:19<01:16,  1.24s/it]
+
 52%|█████▏    | 65/126 [01:20<01:15,  1.24s/it]
+
 52%|█████▏    | 66/126 [01:21<01:14,  1.24s/it]
+
 53%|█████▎    | 67/126 [01:22<01:13,  1.24s/it]
+
 54%|█████▍    | 68/126 [01:24<01:11,  1.24s/it]
+
 55%|█████▍    | 69/126 [01:25<01:10,  1.24s/it]
+
 56%|█████▌    | 70/126 [01:26<01:08,  1.23s/it]
+
 56%|█████▋    | 71/126 [01:27<01:07,  1.22s/it]
+
 57%|█████▋    | 72/126 [01:29<01:05,  1.21s/it]
+
 58%|█████▊    | 73/126 [01:30<01:04,  1.21s/it]
+
 59%|█████▊    | 74/126 [01:31<01:02,  1.20s/it]
+
 60%|█████▉    | 75/126 [01:32<01:01,  1.20s/it]
+
 60%|██████    | 76/126 [01:33<01:00,  1.20s/it]
+
 61%|██████    | 77/126 [01:35<00:58,  1.20s/it]
+
 62%|██████▏   | 78/126 [01:36<00:57,  1.20s/it]
+
 63%|██████▎   | 79/126 [01:37<00:56,  1.20s/it]
+
 63%|██████▎   | 80/126 [01:38<00:55,  1.20s/it]
+
 64%|██████▍   | 81/126 [01:39<00:53,  1.20s/it]
+
 65%|██████▌   | 82/126 [01:41<00:52,  1.20s/it]
+
 66%|██████▌   | 83/126 [01:42<00:51,  1.20s/it]
+
 67%|██████▋   | 84/126 [01:43<00:50,  1.20s/it]
+
 67%|██████▋   | 85/126 [01:44<00:49,  1.20s/it]
+
 68%|██████▊   | 86/126 [01:45<00:47,  1.20s/it]
+
 69%|██████▉   | 87/126 [01:47<00:46,  1.20s/it]
+
 70%|██████▉   | 88/126 [01:48<00:45,  1.20s/it]
+
 71%|███████   | 89/126 [01:49<00:44,  1.20s/it]
+
 71%|███████▏  | 90/126 [01:50<00:43,  1.20s/it]
+
 72%|███████▏  | 91/126 [01:51<00:41,  1.20s/it]
+
 73%|███████▎  | 92/126 [01:53<00:40,  1.20s/it]
+
 74%|███████▍  | 93/126 [01:54<00:39,  1.20s/it]
+
 75%|███████▍  | 94/126 [01:55<00:38,  1.20s/it]
+
 75%|███████▌  | 95/126 [01:56<00:37,  1.20s/it]
+
 76%|███████▌  | 96/126 [01:57<00:35,  1.20s/it]
+
 77%|███████▋  | 97/126 [01:59<00:34,  1.20s/it]
+
 78%|███████▊  | 98/126 [02:00<00:33,  1.20s/it]
+
 79%|███████▊  | 99/126 [02:01<00:32,  1.20s/it]
+
 79%|███████▉  | 100/126 [02:02<00:31,  1.20s/it]
+
 80%|████████  | 101/126 [02:03<00:29,  1.20s/it]
+
 81%|████████  | 102/126 [02:05<00:28,  1.20s/it]
+
 82%|████████▏ | 103/126 [02:06<00:27,  1.20s/it]
+
 83%|████████▎ | 104/126 [02:07<00:26,  1.20s/it]
+
 83%|████████▎ | 105/126 [02:08<00:25,  1.20s/it]
+
 84%|████████▍ | 106/126 [02:09<00:23,  1.20s/it]
+
 85%|████████▍ | 107/126 [02:11<00:22,  1.20s/it]
+
 86%|████████▌ | 108/126 [02:12<00:21,  1.20s/it]
+
 87%|████████▋ | 109/126 [02:13<00:20,  1.21s/it]
+
 87%|████████▋ | 110/126 [02:14<00:19,  1.22s/it]
+
 88%|████████▊ | 111/126 [02:15<00:18,  1.22s/it]
+
 89%|████████▉ | 112/126 [02:17<00:17,  1.23s/it]
+
 90%|████████▉ | 113/126 [02:18<00:16,  1.23s/it]
+
 90%|█████████ | 114/126 [02:19<00:14,  1.23s/it]
+
 91%|█████████▏| 115/126 [02:20<00:13,  1.24s/it]
+
 92%|█████████▏| 116/126 [02:22<00:12,  1.24s/it]
+
 93%|█████████▎| 117/126 [02:23<00:11,  1.24s/it]
+
 94%|█████████▎| 118/126 [02:24<00:09,  1.24s/it]
+
 94%|█████████▍| 119/126 [02:25<00:08,  1.24s/it]
+
 95%|█████████▌| 120/126 [02:27<00:07,  1.24s/it]
+
 96%|█████████▌| 121/126 [02:28<00:06,  1.24s/it]
+
 97%|█████████▋| 122/126 [02:29<00:04,  1.24s/it]
+
 98%|█████████▊| 123/126 [02:30<00:03,  1.24s/it]
+
 98%|█████████▊| 124/126 [02:32<00:02,  1.24s/it]
 98%|█████████▊| 124/126 [02:32<00:02,  1.23s/it]
+Traceback (most recent call last):
+  File "/mnt/storage/aatherton/hf_synth_trans/synth_translation.py", line 217, in <module>
+    for batch in tqdm(eval_dataloader):
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/tqdm/std.py", line 1178, in __iter__
+    for obj in iterable:
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/accelerate/data_loader.py", line 394, in __iter__
+    next_batch = next(dataloader_iter)
+                 ^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 633, in __next__
+    data = self._next_data()
+           ^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 677, in _next_data
+    data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/utils/data/_utils/fetch.py", line 54, in fetch
+    return self.collate_fn(data)
+           ^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/data/data_collator.py", line 600, in __call__
+    decoder_input_ids = self.model.prepare_decoder_input_ids_from_labels(labels=features["labels"])
+                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/marian/modeling_marian.py", line 1527, in prepare_decoder_input_ids_from_labels
+    return shift_tokens_right(labels, self.config.pad_token_id, self.config.decoder_start_token_id)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/marian/modeling_marian.py", line 66, in shift_tokens_right
+    shifted_input_ids[:, 0] = decoder_start_token_id
+    ~~~~~~~~~~~~~~~~~^^^^^^
+IndexError: index 0 is out of bounds for dimension 1 with size 0
+
 33%|███▎      | 912/2736 [03:45<07:31,  4.04it/s]

myerrors_1564.out

@@ -0,0 +1,161 @@
+You're using a GPT2TokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
+
  0%|          | 0/16 [00:00<?, ?it/s]
 12%|█▎        | 2/16 [00:04<00:32,  2.29s/it]
 19%|█▉        | 3/16 [00:08<00:40,  3.15s/it]
 25%|██▌       | 4/16 [00:13<00:43,  3.59s/it]
 31%|███▏      | 5/16 [00:17<00:42,  3.85s/it]
 38%|███▊      | 6/16 [00:21<00:40,  4.01s/it]
 44%|████▍     | 7/16 [00:26<00:37,  4.12s/it]
 50%|█████     | 8/16 [00:30<00:33,  4.18s/it]
 56%|█████▋    | 9/16 [00:34<00:29,  4.23s/it]
 62%|██████▎   | 10/16 [00:39<00:25,  4.26s/it]
 69%|██████▉   | 11/16 [00:43<00:21,  4.28s/it]
 75%|███████▌  | 12/16 [00:47<00:17,  4.29s/it]
 81%|████████▏ | 13/16 [00:52<00:12,  4.31s/it]
 88%|████████▊ | 14/16 [00:56<00:08,  4.31s/it]
 94%|█████████▍| 15/16 [01:00<00:04,  4.32s/it]
+
  0%|          | 0/684 [00:00<?, ?it/s]
  0%|          | 1/684 [00:00<02:38,  4.31it/s]
  0%|          | 3/684 [00:00<01:17,  8.82it/s]
  1%|          | 5/684 [00:00<01:02, 10.82it/s]
  1%|          | 7/684 [00:00<00:57, 11.88it/s]
  1%|▏         | 9/684 [00:00<00:53, 12.54it/s]
  2%|▏         | 11/684 [00:00<00:52, 12.94it/s]
  2%|▏         | 13/684 [00:01<00:51, 13.15it/s]
  2%|▏         | 15/684 [00:01<00:50, 13.32it/s]
  2%|▏         | 17/684 [00:01<00:49, 13.49it/s]
  3%|▎         | 19/684 [00:01<00:49, 13.57it/s]
  3%|▎         | 21/684 [00:01<00:48, 13.58it/s]
  3%|▎         | 23/684 [00:01<00:48, 13.64it/s]
  4%|▎         | 25/684 [00:01<00:48, 13.71it/s]
  4%|▍         | 27/684 [00:02<00:47, 13.74it/s]
  4%|▍         | 29/684 [00:02<00:47, 13.69it/s]
  5%|▍         | 31/684 [00:02<00:47, 13.78it/s]
  5%|▍         | 33/684 [00:02<00:47, 13.80it/s]
  5%|▌         | 35/684 [00:02<00:47, 13.76it/s]
  5%|▌         | 37/684 [00:02<00:47, 13.76it/s]
  6%|▌         | 39/684 [00:02<00:46, 13.73it/s]
  6%|▌         | 41/684 [00:03<00:46, 13.74it/s]
  6%|▋         | 43/684 [00:03<00:46, 13.71it/s]
  7%|▋         | 45/684 [00:03<00:46, 13.77it/s]
  7%|▋         | 47/684 [00:03<00:46, 13.68it/s]
  7%|▋         | 49/684 [00:03<00:46, 13.77it/s]
  7%|▋         | 51/684 [00:03<00:45, 13.79it/s]
  8%|▊         | 53/684 [00:04<00:45, 13.81it/s]
  8%|▊         | 55/684 [00:04<00:45, 13.78it/s]
  8%|▊         | 57/684 [00:04<00:45, 13.77it/s]
  9%|▊         | 59/684 [00:04<00:45, 13.73it/s]
  9%|▉         | 61/684 [00:04<00:45, 13.72it/s]
  9%|▉         | 63/684 [00:04<00:45, 13.74it/s]
 10%|▉         | 65/684 [00:04<00:44, 13.76it/s]
 10%|▉         | 67/684 [00:05<00:44, 13.77it/s]
 10%|█         | 69/684 [00:05<00:44, 13.78it/s]
 10%|█         | 71/684 [00:05<00:44, 13.76it/s]
 11%|█         | 73/684 [00:05<00:44, 13.76it/s]
 11%|█         | 75/684 [00:05<00:44, 13.78it/s]
 11%|█▏        | 77/684 [00:05<00:44, 13.76it/s]
 12%|█▏        | 79/684 [00:05<00:43, 13.76it/s]
 12%|█▏        | 81/684 [00:06<00:43, 13.77it/s]
 12%|█▏        | 83/684 [00:06<00:43, 13.76it/s]
 12%|█▏        | 85/684 [00:06<00:43, 13.75it/s]
 13%|█▎        | 87/684 [00:06<00:43, 13.79it/s]
 13%|█▎        | 89/684 [00:06<00:43, 13.76it/s]
 13%|█▎        | 91/684 [00:06<00:43, 13.74it/s]
 14%|█▎        | 93/684 [00:06<00:43, 13.74it/s]
 14%|█▍        | 95/684 [00:07<00:42, 13.79it/s]
 14%|█▍        | 97/684 [00:07<00:42, 13.75it/s]
 14%|█▍        | 99/684 [00:07<00:42, 13.77it/s]
 15%|█▍        | 101/684 [00:07<00:42, 13.76it/s]
 15%|█▌        | 103/684 [00:07<00:42, 13.68it/s]
 15%|█▌        | 105/684 [00:07<00:42, 13.78it/s]
 16%|█▌        | 107/684 [00:07<00:41, 13.83it/s]
 16%|█▌        | 109/684 [00:08<00:41, 13.74it/s]
 16%|█▌        | 111/684 [00:08<00:41, 13.76it/s]
 17%|█▋        | 113/684 [00:08<00:41, 13.81it/s]
 17%|█▋        | 115/684 [00:08<00:41, 13.81it/s]
 17%|█▋        | 117/684 [00:08<00:41, 13.79it/s]
 17%|█▋        | 119/684 [00:08<00:41, 13.76it/s]
 18%|█▊        | 121/684 [00:08<00:41, 13.73it/s]
 18%|█▊        | 123/684 [00:09<00:40, 13.76it/s]
 18%|█▊        | 125/684 [00:09<00:40, 13.76it/s]
 19%|█▊        | 127/684 [00:09<00:40, 13.70it/s]
 19%|█▉        | 129/684 [00:09<00:40, 13.74it/s]
 19%|█▉        | 131/684 [00:09<00:40, 13.76it/s]
 19%|█▉        | 133/684 [00:09<00:40, 13.70it/s]
 20%|█▉        | 135/684 [00:09<00:40, 13.72it/s]
 20%|██        | 137/684 [00:10<00:39, 13.74it/s]
 20%|██        | 139/684 [00:10<00:39, 13.78it/s]
 21%|██        | 141/684 [00:10<00:39, 13.78it/s]
 21%|██        | 143/684 [00:10<00:39, 13.81it/s]
 21%|██        | 145/684 [00:10<00:39, 13.79it/s]
 21%|██▏       | 147/684 [00:10<00:39, 13.76it/s]
 22%|██▏       | 149/684 [00:10<00:38, 13.78it/s]
 22%|██▏       | 151/684 [00:11<00:38, 13.80it/s]
 22%|██▏       | 153/684 [00:11<00:38, 13.79it/s]
 23%|██▎       | 155/684 [00:11<00:38, 13.78it/s]
 23%|██▎       | 157/684 [00:11<00:38, 13.76it/s]
 23%|██▎       | 159/684 [00:11<00:38, 13.74it/s]
 24%|██▎       | 161/684 [00:11<00:38, 13.72it/s]
 24%|██▍       | 163/684 [00:12<00:37, 13.74it/s]
 24%|██▍       | 165/684 [00:12<00:37, 13.69it/s]
 24%|██▍       | 167/684 [00:12<00:37, 13.69it/s]
 25%|██▍       | 169/684 [00:12<00:37, 13.72it/s]
 25%|██▌       | 171/684 [00:12<00:37, 13.76it/s]
 25%|██▌       | 173/684 [00:12<00:37, 13.74it/s]
 26%|██▌       | 175/684 [00:12<00:36, 13.78it/s]
 26%|██▌       | 177/684 [00:13<00:36, 13.76it/s]
 26%|██▌       | 179/684 [00:13<00:36, 13.76it/s]
 26%|██▋       | 181/684 [00:13<00:36, 13.79it/s]
 27%|██▋       | 183/684 [00:13<00:36, 13.82it/s]
 27%|██▋       | 185/684 [00:13<00:36, 13.80it/s]
 27%|██▋       | 187/684 [00:13<00:35, 13.90it/s]
 28%|██▊       | 189/684 [00:13<00:35, 14.01it/s]
 28%|██▊       | 191/684 [00:14<00:35, 13.91it/s]
 28%|██▊       | 193/684 [00:14<00:35, 13.88it/s]
 29%|██▊       | 195/684 [00:14<00:35, 13.85it/s]
 29%|██▉       | 197/684 [00:14<00:35, 13.77it/s]
 29%|██▉       | 199/684 [00:14<00:35, 13.79it/s]
 29%|██▉       | 201/684 [00:14<00:35, 13.72it/s]
 30%|██▉       | 203/684 [00:14<00:34, 13.76it/s]
 30%|██▉       | 205/684 [00:15<00:34, 13.77it/s]
 30%|███       | 207/684 [00:15<00:34, 13.76it/s]
 31%|███       | 209/684 [00:15<00:34, 13.72it/s]
 31%|███       | 211/684 [00:15<00:34, 13.74it/s]
 31%|███       | 213/684 [00:15<00:34, 13.74it/s]
 31%|███▏      | 215/684 [00:15<00:34, 13.79it/s]
 32%|███▏      | 217/684 [00:15<00:33, 13.82it/s]
 32%|███▏      | 219/684 [00:16<00:33, 13.80it/s]
 32%|███▏      | 221/684 [00:16<00:33, 13.79it/s]
 33%|███▎      | 223/684 [00:16<00:33, 13.77it/s]
 33%|███▎      | 225/684 [00:16<00:33, 13.75it/s]
 33%|███▎      | 227/684 [00:16<00:33, 13.72it/s]
 33%|███▎      | 229/684 [00:19<03:06,  2.43it/s]
 34%|███▍      | 231/684 [00:19<02:19,  3.24it/s]
 34%|███▍      | 233/684 [00:19<01:47,  4.21it/s]
 34%|███▍      | 235/684 [00:19<01:24,  5.33it/s]
 35%|███▍      | 237/684 [00:19<01:08,  6.50it/s]
 35%|███▍      | 239/684 [00:19<00:59,  7.53it/s]
 35%|███▌      | 241/684 [00:19<00:50,  8.72it/s]
 36%|███▌      | 243/684 [00:20<00:46,  9.51it/s]
 36%|███▌      | 245/684 [00:20<00:41, 10.56it/s]
 36%|███▌      | 247/684 [00:20<00:38, 11.48it/s]
 36%|███▋      | 249/684 [00:20<00:37, 11.74it/s]
 37%|███▋      | 251/684 [00:20<00:35, 12.10it/s]
 37%|███▋      | 253/684 [00:20<00:34, 12.50it/s]
 37%|███▋      | 255/684 [00:21<00:34, 12.45it/s]
 38%|███▊      | 257/684 [00:21<00:33, 12.84it/s]
 38%|███▊      | 259/684 [00:21<00:32, 13.18it/s]
 38%|███▊      | 261/684 [00:21<00:32, 12.98it/s]
 38%|███▊      | 263/684 [00:21<00:31, 13.16it/s]
 39%|███▊      | 265/684 [00:21<00:32, 12.88it/s]
 39%|███▉      | 267/684 [00:21<00:32, 12.88it/s]
 39%|███▉      | 269/684 [00:22<00:32, 12.92it/s]
 40%|███▉      | 271/684 [00:22<00:31, 12.94it/s]
 40%|███▉      | 273/684 [00:22<00:31, 13.00it/s]
 40%|████      | 275/684 [00:22<00:32, 12.76it/s]
 40%|████      | 277/684 [00:22<00:31, 13.11it/s]
 41%|████      | 279/684 [00:22<00:31, 12.92it/s]
 41%|████      | 281/684 [00:22<00:30, 13.14it/s]
 41%|████▏     | 283/684 [00:23<00:29, 13.38it/s]
 42%|████▏     | 285/684 [00:23<00:30, 13.18it/s]
 42%|████▏     | 287/684 [00:23<00:30, 13.23it/s]
 42%|████▏     | 289/684 [00:23<00:30, 13.00it/s]
 43%|████▎     | 291/684 [00:23<00:29, 13.19it/s]
 43%|████▎     | 293/684 [00:23<00:30, 12.88it/s]
 43%|████▎     | 295/684 [00:24<00:29, 13.30it/s]
 43%|████▎     | 297/684 [00:24<00:29, 13.08it/s]
 44%|████▎     | 299/684 [00:24<00:29, 13.24it/s]
 44%|████▍     | 301/684 [00:24<00:29, 13.08it/s]
 44%|████▍     | 303/684 [00:24<00:28, 13.17it/s]
 45%|████▍     | 305/684 [00:24<00:28, 13.44it/s]
 45%|████▍     | 307/684 [00:24<00:28, 13.05it/s]
 45%|████▌     | 309/684 [00:25<00:28, 13.09it/s]
 45%|████▌     | 311/684 [00:25<00:28, 12.95it/s]
 46%|████▌     | 313/684 [00:25<00:27, 13.31it/s]
 46%|████▌     | 315/684 [00:25<00:27, 13.53it/s]
 46%|████▋     | 317/684 [00:25<00:26, 13.69it/s]
 47%|████▋     | 319/684 [00:25<00:27, 13.35it/s]
 47%|████▋     | 321/684 [00:26<00:27, 13.34it/s]
 47%|████▋     | 323/684 [00:26<00:27, 13.18it/s]
 48%|████▊     | 325/684 [00:26<00:27, 13.28it/s]
 48%|████▊     | 327/684 [00:26<00:26, 13.39it/s]
 48%|████▊     | 329/684 [00:26<00:27, 13.11it/s]
 48%|████▊     | 331/684 [00:26<00:26, 13.30it/s]
 49%|████▊     | 333/684 [00:26<00:26, 13.49it/s]
 49%|████▉     | 335/684 [00:27<00:25, 13.62it/s]
 49%|████▉     | 337/684 [00:27<00:25, 13.76it/s]
 50%|████▉     | 339/684 [00:27<00:24, 13.83it/s]
 50%|████▉     | 341/684 [00:27<00:24, 13.87it/s]
 50%|█████     | 343/684 [00:27<00:24, 13.92it/s]
 50%|█████     | 345/684 [00:27<00:24, 13.95it/s]
 51%|█████     | 347/684 [00:27<00:24, 13.97it/s]
 51%|█████     | 349/684 [00:28<00:23, 13.97it/s]
 51%|█████▏    | 351/684 [00:28<00:23, 13.99it/s]
 52%|█████▏    | 353/684 [00:28<00:23, 13.97it/s]
 52%|█████▏    | 355/684 [00:28<00:23, 13.99it/s]
 52%|█████▏    | 357/684 [00:28<00:23, 14.00it/s]
 52%|█████▏    | 359/684 [00:28<00:23, 13.99it/s]
 53%|█████▎    | 361/684 [00:28<00:23, 14.01it/s]
 53%|█████▎    | 363/684 [00:29<00:22, 14.04it/s]
 53%|█████▎    | 365/684 [00:29<00:22, 14.00it/s]
 54%|█████▎    | 367/684 [00:29<00:22, 14.00it/s]
 54%|█████▍    | 369/684 [00:29<00:22, 14.03it/s]
 54%|█████▍    | 371/684 [00:29<00:22, 14.04it/s]
 55%|█████▍    | 373/684 [00:29<00:22, 14.00it/s]
 55%|█████▍    | 375/684 [00:29<00:22, 14.04it/s]
 55%|█████▌    | 377/684 [00:30<00:21, 14.01it/s]
 55%|█████▌    | 379/684 [00:30<00:21, 14.01it/s]
 56%|█████▌    | 381/684 [00:30<00:21, 14.03it/s]
 56%|█████▌    | 383/684 [00:30<00:21, 14.05it/s]
 56%|█████▋    | 385/684 [00:30<00:21, 14.07it/s]
 57%|█████▋    | 387/684 [00:30<00:21, 14.05it/s]
 57%|█████▋    | 389/684 [00:30<00:21, 14.04it/s]
 57%|█████▋    | 391/684 [00:31<00:20, 14.06it/s]
 57%|█████▋    | 393/684 [00:31<00:20, 14.04it/s]
 58%|█████▊    | 395/684 [00:31<00:20, 14.05it/s]
 58%|█████▊    | 397/684 [00:31<00:20, 14.00it/s]
 58%|█████▊    | 399/684 [00:31<00:20, 14.03it/s]
 59%|█████▊    | 401/684 [00:31<00:20, 14.04it/s]
 59%|█████▉    | 403/684 [00:31<00:20, 14.03it/s]
 59%|█████▉    | 405/684 [00:32<00:19, 14.03it/s]
 60%|█████▉    | 407/684 [00:32<00:19, 14.02it/s]
 60%|█████▉    | 409/684 [00:32<00:19, 14.01it/s]
 60%|██████    | 411/684 [00:32<00:19, 14.01it/s]
 60%|██████    | 413/684 [00:32<00:19, 14.02it/s]
 61%|██████    | 415/684 [00:32<00:19, 14.04it/s]
 61%|██████    | 417/684 [00:32<00:19, 14.00it/s]
 61%|██████▏   | 419/684 [00:33<00:18, 14.02it/s]
 62%|██████▏   | 421/684 [00:33<00:18, 14.04it/s]
 62%|██████▏   | 423/684 [00:33<00:18, 14.04it/s]
 62%|██████▏   | 425/684 [00:33<00:18, 14.04it/s]
 62%|██████▏   | 427/684 [00:33<00:18, 14.03it/s]
 63%|██████▎   | 429/684 [00:33<00:18, 14.03it/s]
 63%|██████▎   | 431/684 [00:33<00:17, 14.06it/s]
 63%|██████▎   | 433/684 [00:34<00:17, 14.04it/s]
 64%|██████▎   | 435/684 [00:34<00:17, 14.05it/s]
 64%|██████▍   | 437/684 [00:34<00:17, 14.06it/s]
 64%|██████▍   | 439/684 [00:34<00:17, 14.04it/s]
 64%|██████▍   | 441/684 [00:34<00:17, 14.04it/s]
 65%|██████▍   | 443/684 [00:34<00:17, 14.03it/s]
 65%|██████▌   | 445/684 [00:34<00:17, 14.03it/s]
 65%|██████▌   | 447/684 [00:35<00:16, 14.05it/s]
 66%|██████▌   | 449/684 [00:35<00:16, 14.04it/s]
 66%|██████▌   | 451/684 [00:35<00:16, 14.05it/s]
 66%|██████▌   | 453/684 [00:35<00:16, 14.04it/s]
 67%|██████▋   | 455/684 [00:35<00:16, 14.04it/s]
 67%|██████▋   | 457/684 [00:37<01:32,  2.46it/s]
 67%|██████▋   | 459/684 [00:38<01:08,  3.26it/s]
 67%|██████▋   | 461/684 [00:38<00:52,  4.25it/s]
 68%|██████▊   | 463/684 [00:38<00:41,  5.37it/s]
 68%|██████▊   | 465/684 [00:38<00:33,  6.52it/s]
 68%|██████▊   | 467/684 [00:38<00:28,  7.65it/s]
 69%|██████▊   | 469/684 [00:38<00:24,  8.70it/s]
 69%|██████▉   | 471/684 [00:39<00:21,  9.75it/s]
 69%|██████▉   | 473/684 [00:39<00:20, 10.45it/s]
 69%|██████▉   | 475/684 [00:39<00:18, 11.16it/s]
 70%|██████▉   | 477/684 [00:39<00:17, 11.70it/s]
 70%|███████   | 479/684 [00:39<00:17, 11.93it/s]
 70%|███████   | 481/684 [00:39<00:16, 12.38it/s]
 71%|███████   | 483/684 [00:39<00:16, 12.40it/s]
 71%|███████   | 485/684 [00:40<00:15, 12.77it/s]
 71%|███████   | 487/684 [00:40<00:15, 12.71it/s]
 71%|███████▏  | 489/684 [00:40<00:15, 12.92it/s]
 72%|███████▏  | 491/684 [00:40<00:15, 12.71it/s]
 72%|███████▏  | 493/684 [00:40<00:14, 12.90it/s]
 72%|███████▏  | 495/684 [00:40<00:14, 12.79it/s]
 73%|███████▎  | 497/684 [00:41<00:14, 12.73it/s]
 73%|███████▎  | 499/684 [00:41<00:14, 12.89it/s]
                                                 
 73%|███████▎  | 500/684 [00:41<00:14, 12.89it/s]
 73%|███████▎  | 501/684 [00:41<00:14, 12.80it/s]
 74%|███████▎  | 503/684 [00:41<00:13, 13.07it/s]
 74%|███████▍  | 505/684 [00:41<00:13, 12.84it/s]
 74%|███████▍  | 507/684 [00:41<00:13, 12.65it/s]
 74%|███████▍  | 509/684 [00:41<00:13, 12.93it/s]
 75%|███████▍  | 511/684 [00:42<00:13, 12.84it/s]
 75%|███████▌  | 513/684 [00:42<00:13, 12.85it/s]
 75%|███████▌  | 515/684 [00:42<00:12, 13.07it/s]
 76%|███████▌  | 517/684 [00:42<00:13, 12.72it/s]
 76%|███████▌  | 519/684 [00:42<00:12, 12.94it/s]
 76%|███████▌  | 521/684 [00:42<00:12, 12.83it/s]
 76%|███████▋  | 523/684 [00:43<00:12, 13.07it/s]
 77%|███████▋  | 525/684 [00:43<00:12, 12.95it/s]
 77%|███████▋  | 527/684 [00:43<00:11, 13.21it/s]
 77%|███████▋  | 529/684 [00:43<00:11, 12.94it/s]
 78%|███████▊  | 531/684 [00:43<00:11, 12.88it/s]
 78%|███████▊  | 533/684 [00:43<00:11, 13.08it/s]
 78%|███████▊  | 535/684 [00:43<00:11, 13.27it/s]
 79%|███████▊  | 537/684 [00:44<00:11, 13.34it/s]
 79%|███████▉  | 539/684 [00:44<00:10, 13.48it/s]
 79%|███████▉  | 541/684 [00:44<00:10, 13.61it/s]
 79%|███████▉  | 543/684 [00:44<00:10, 13.76it/s]
 80%|███████▉  | 545/684 [00:44<00:10, 13.83it/s]
 80%|███████▉  | 547/684 [00:44<00:09, 13.85it/s]
 80%|████████  | 549/684 [00:44<00:09, 13.93it/s]
 81%|████████  | 551/684 [00:45<00:09, 13.96it/s]
 81%|████████  | 553/684 [00:45<00:09, 13.97it/s]
 81%|████████  | 555/684 [00:45<00:09, 13.99it/s]
 81%|████████▏ | 557/684 [00:45<00:09, 14.01it/s]
 82%|████████▏ | 559/684 [00:45<00:08, 14.03it/s]
 82%|████████▏ | 561/684 [00:45<00:08, 13.99it/s]
 82%|████████▏ | 563/684 [00:45<00:08, 14.02it/s]
 83%|████████▎ | 565/684 [00:46<00:08, 14.03it/s]
 83%|████████▎ | 567/684 [00:46<00:08, 14.04it/s]
 83%|████████▎ | 569/684 [00:46<00:08, 14.03it/s]
 83%|████████▎ | 571/684 [00:46<00:08, 14.04it/s]
 84%|████████▍ | 573/684 [00:46<00:07, 14.05it/s]
 84%|████████▍ | 575/684 [00:46<00:07, 14.06it/s]
 84%|████████▍ | 577/684 [00:46<00:07, 14.17it/s]
 85%|████████▍ | 579/684 [00:47<00:07, 14.17it/s]
 85%|████████▍ | 581/684 [00:47<00:07, 14.17it/s]
 85%|████████▌ | 583/684 [00:47<00:07, 14.14it/s]
 86%|████████▌ | 585/684 [00:47<00:07, 14.10it/s]
 86%|████████▌ | 587/684 [00:47<00:06, 14.08it/s]
 86%|████████▌ | 589/684 [00:47<00:06, 14.08it/s]
 86%|████████▋ | 591/684 [00:47<00:06, 14.09it/s]
 87%|████████▋ | 593/684 [00:48<00:06, 14.10it/s]
 87%|████████▋ | 595/684 [00:48<00:06, 14.07it/s]
 87%|████████▋ | 597/684 [00:48<00:06, 14.08it/s]
 88%|████████▊ | 599/684 [00:48<00:06, 14.06it/s]
 88%|████████▊ | 601/684 [00:48<00:05, 14.14it/s]
 88%|████████▊ | 603/684 [00:48<00:05, 14.14it/s]
 88%|████████▊ | 605/684 [00:48<00:05, 14.15it/s]
 89%|████████▊ | 607/684 [00:49<00:05, 14.16it/s]
 89%|████████▉ | 609/684 [00:49<00:05, 14.17it/s]
 89%|████████▉ | 611/684 [00:49<00:05, 14.15it/s]
 90%|████████▉ | 613/684 [00:49<00:05, 14.12it/s]
 90%|████████▉ | 615/684 [00:49<00:04, 14.11it/s]
 90%|█████████ | 617/684 [00:49<00:04, 14.10it/s]
 90%|█████████ | 619/684 [00:49<00:04, 14.08it/s]
 91%|█████████ | 621/684 [00:50<00:04, 14.07it/s]
 91%|█████████ | 623/684 [00:50<00:04, 14.07it/s]
 91%|█████████▏| 625/684 [00:50<00:04, 14.06it/s]
 92%|█████████▏| 627/684 [00:50<00:04, 14.05it/s]
 92%|█████████▏| 629/684 [00:50<00:03, 14.04it/s]
 92%|█████████▏| 631/684 [00:50<00:03, 14.03it/s]
 93%|█████████▎| 633/684 [00:50<00:03, 14.04it/s]
 93%|█████████▎| 635/684 [00:51<00:03, 14.02it/s]
 93%|████████���▎| 637/684 [00:51<00:03, 14.04it/s]
 93%|█████████▎| 639/684 [00:51<00:03, 14.03it/s]
 94%|█████████▎| 641/684 [00:51<00:03, 14.01it/s]
 94%|█████████▍| 643/684 [00:51<00:02, 14.03it/s]
 94%|█████████▍| 645/684 [00:51<00:02, 14.06it/s]
 95%|█████████▍| 647/684 [00:51<00:02, 14.08it/s]
 95%|█████████▍| 649/684 [00:52<00:02, 14.11it/s]
 95%|█████████▌| 651/684 [00:52<00:02, 14.13it/s]
 95%|█████████▌| 653/684 [00:52<00:02, 14.09it/s]
 96%|█████████▌| 655/684 [00:52<00:02, 14.08it/s]
 96%|█████████▌| 657/684 [00:52<00:01, 14.08it/s]
 96%|█████████▋| 659/684 [00:52<00:01, 14.06it/s]
 97%|█████████▋| 661/684 [00:52<00:01, 14.08it/s]
 97%|█████████▋| 663/684 [00:53<00:01, 14.08it/s]
 97%|█████████▋| 665/684 [00:53<00:01, 14.06it/s]
 98%|█████████▊| 667/684 [00:53<00:01, 14.10it/s]
 98%|█████████▊| 669/684 [00:53<00:01, 14.09it/s]
 98%|█████████▊| 671/684 [00:53<00:00, 14.09it/s]
 98%|█████████▊| 673/684 [00:53<00:00, 14.09it/s]
 99%|█████████▊| 675/684 [00:53<00:00, 14.08it/s]
 99%|█████████▉| 677/684 [00:54<00:00, 14.07it/s]
 99%|█████████▉| 679/684 [00:54<00:00, 14.06it/s]
                                                 
+
  0%|          | 0/16 [00:00<?, ?it/s]
 12%|█▎        | 2/16 [00:04<00:30,  2.17s/it]
 19%|█▉        | 3/16 [00:08<00:39,  3.08s/it]
 25%|██▌       | 4/16 [00:13<00:42,  3.54s/it]
 31%|███▏      | 5/16 [00:17<00:42,  3.85s/it]
 38%|███▊      | 6/16 [00:21<00:40,  4.03s/it]
 44%|████▍     | 7/16 [00:26<00:37,  4.14s/it]
 50%|█████     | 8/16 [00:30<00:33,  4.21s/it]
 56%|█████▋    | 9/16 [00:34<00:29,  4.27s/it]
 62%|██████▎   | 10/16 [00:39<00:25,  4.30s/it]
 69%|██████▉   | 11/16 [00:43<00:21,  4.32s/it]
 75%|███████▌  | 12/16 [00:48<00:17,  4.34s/it]
 81%|████████▏ | 13/16 [00:52<00:13,  4.35s/it]
 88%|████████▊ | 14/16 [00:56<00:08,  4.36s/it]
 94%|█████████▍| 15/16 [01:01<00:04,  4.36s/it]
+/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/optimization.py:411: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
+  warnings.warn(
+/mnt/storage/aatherton/hf_eng_fra_trans is already a clone of https://huggingface.co/aatherton2024/hf_eng_fra_trans. Make sure you pull the latest changes with `repo.git_pull()`.
+
  0%|          | 0/2736 [00:00<?, ?it/s]
  0%|          | 1/2736 [00:00<04:35,  9.94it/s]
  0%|          | 3/2736 [00:00<03:57, 11.52it/s]
  0%|          | 5/2736 [00:00<03:49, 11.91it/s]
  0%|          | 7/2736 [00:00<03:36, 12.59it/s]
  0%|          | 9/2736 [00:00<03:38, 12.48it/s]
  0%|          | 11/2736 [00:00<03:37, 12.50it/s]
  0%|          | 13/2736 [00:01<03:39, 12.41it/s]
  1%|          | 15/2736 [00:01<03:40, 12.33it/s]
  1%|          | 17/2736 [00:01<03:39, 12.38it/s]
  1%|          | 19/2736 [00:01<03:38, 12.44it/s]
  1%|          | 21/2736 [00:01<03:38, 12.44it/s]
  1%|          | 23/2736 [00:01<03:40, 12.29it/s]
  1%|          | 25/2736 [00:02<03:38, 12.40it/s]
  1%|          | 27/2736 [00:02<03:39, 12.34it/s]
  1%|          | 29/2736 [00:02<03:38, 12.38it/s]
  1%|          | 31/2736 [00:02<03:37, 12.44it/s]
  1%|          | 33/2736 [00:02<03:41, 12.18it/s]
  1%|▏         | 35/2736 [00:02<03:43, 12.10it/s]
  1%|▏         | 37/2736 [00:03<03:40, 12.23it/s]
  1%|▏         | 39/2736 [00:03<03:40, 12.25it/s]
  1%|▏         | 41/2736 [00:03<03:37, 12.36it/s]
  2%|▏         | 43/2736 [00:03<03:36, 12.42it/s]
  2%|▏         | 45/2736 [00:03<03:36, 12.44it/s]
  2%|▏         | 47/2736 [00:03<03:35, 12.50it/s]
  2%|▏         | 49/2736 [00:03<03:34, 12.53it/s]
  2%|▏         | 51/2736 [00:04<03:34, 12.51it/s]
  2%|▏         | 53/2736 [00:04<03:34, 12.52it/s]
  2%|▏         | 55/2736 [00:04<03:34, 12.51it/s]
  2%|▏         | 57/2736 [00:04<03:35, 12.45it/s]
  2%|▏         | 59/2736 [00:04<03:36, 12.37it/s]
  2%|▏         | 61/2736 [00:04<03:37, 12.28it/s]
  2%|▏         | 63/2736 [00:05<03:37, 12.29it/s]
  2%|▏         | 65/2736 [00:05<03:36, 12.35it/s]
  2%|▏         | 67/2736 [00:05<03:37, 12.28it/s]
  3%|▎         | 69/2736 [00:05<03:35, 12.35it/s]
  3%|▎         | 71/2736 [00:05<03:36, 12.32it/s]
  3%|▎         | 73/2736 [00:05<03:36, 12.28it/s]
  3%|▎         | 75/2736 [00:06<03:34, 12.39it/s]
  3%|▎         | 77/2736 [00:06<03:36, 12.31it/s]
  3%|▎         | 79/2736 [00:06<03:34, 12.39it/s]
  3%|▎         | 81/2736 [00:06<03:34, 12.40it/s]
  3%|▎         | 83/2736 [00:06<03:33, 12.40it/s]
  3%|▎         | 85/2736 [00:06<03:36, 12.26it/s]
  3%|▎         | 87/2736 [00:07<03:34, 12.34it/s]
  3%|▎         | 89/2736 [00:07<03:35, 12.30it/s]
  3%|▎         | 91/2736 [00:07<03:33, 12.37it/s]
  3%|▎         | 93/2736 [00:07<03:33, 12.40it/s]
  3%|▎         | 95/2736 [00:07<03:33, 12.39it/s]
  4%|▎         | 97/2736 [00:07<03:32, 12.41it/s]
  4%|▎         | 99/2736 [00:08<03:31, 12.45it/s]
  4%|▎         | 101/2736 [00:08<03:30, 12.51it/s]
  4%|▍         | 103/2736 [00:08<03:30, 12.50it/s]
  4%|▍         | 105/2736 [00:08<03:29, 12.54it/s]
  4%|▍         | 107/2736 [00:08<03:29, 12.55it/s]
  4%|▍         | 109/2736 [00:08<03:29, 12.55it/s]
  4%|▍         | 111/2736 [00:08<03:28, 12.57it/s]
  4%|▍         | 113/2736 [00:09<03:29, 12.54it/s]
  4%|▍         | 115/2736 [00:09<03:29, 12.54it/s]
  4%|▍         | 117/2736 [00:09<03:28, 12.54it/s]
  4%|▍         | 119/2736 [00:09<03:29, 12.51it/s]
  4%|▍         | 121/2736 [00:09<03:28, 12.55it/s]
  4%|▍         | 123/2736 [00:09<03:28, 12.52it/s]
  5%|▍         | 125/2736 [00:10<03:28, 12.53it/s]
  5%|▍         | 127/2736 [00:10<03:28, 12.53it/s]
  5%|▍         | 129/2736 [00:10<03:27, 12.55it/s]
  5%|▍         | 131/2736 [00:10<03:27, 12.56it/s]
  5%|▍         | 133/2736 [00:10<03:28, 12.51it/s]
  5%|▍         | 135/2736 [00:10<03:26, 12.57it/s]
  5%|▌         | 137/2736 [00:11<03:26, 12.58it/s]
  5%|▌         | 139/2736 [00:11<03:26, 12.60it/s]
  5%|▌         | 141/2736 [00:11<03:25, 12.61it/s]
  5%|▌         | 143/2736 [00:11<03:26, 12.55it/s]
  5%|▌         | 145/2736 [00:11<03:26, 12.55it/s]
  5%|▌         | 147/2736 [00:11<03:26, 12.51it/s]
  5%|▌         | 149/2736 [00:11<03:26, 12.53it/s]
  6%|▌         | 151/2736 [00:12<03:26, 12.53it/s]
  6%|▌         | 153/2736 [00:12<03:25, 12.56it/s]
  6%|▌         | 155/2736 [00:12<03:25, 12.55it/s]
  6%|▌         | 157/2736 [00:12<03:25, 12.55it/s]
  6%|▌         | 159/2736 [00:12<03:26, 12.48it/s]
  6%|▌         | 161/2736 [00:12<03:25, 12.54it/s]
  6%|▌         | 163/2736 [00:13<03:26, 12.45it/s]
  6%|▌         | 165/2736 [00:13<03:25, 12.50it/s]
  6%|▌         | 167/2736 [00:13<03:27, 12.37it/s]
  6%|▌         | 169/2736 [00:13<03:26, 12.45it/s]
  6%|▋         | 171/2736 [00:13<03:26, 12.40it/s]
  6%|▋         | 173/2736 [00:13<03:25, 12.49it/s]
  6%|▋         | 175/2736 [00:14<03:26, 12.38it/s]
  6%|▋         | 177/2736 [00:14<03:26, 12.42it/s]
  7%|▋         | 179/2736 [00:14<03:25, 12.43it/s]
  7%|▋         | 181/2736 [00:14<03:24, 12.51it/s]
  7%|▋         | 183/2736 [00:14<03:23, 12.52it/s]
  7%|▋         | 185/2736 [00:14<03:25, 12.42it/s]
  7%|▋         | 187/2736 [00:15<03:24, 12.45it/s]
  7%|▋         | 189/2736 [00:15<03:25, 12.42it/s]
  7%|▋         | 191/2736 [00:15<03:23, 12.50it/s]
  7%|▋         | 193/2736 [00:15<03:24, 12.41it/s]
  7%|▋         | 195/2736 [00:15<03:24, 12.43it/s]
  7%|▋         | 197/2736 [00:15<03:24, 12.41it/s]
  7%|▋         | 199/2736 [00:16<03:24, 12.40it/s]
  7%|▋         | 201/2736 [00:16<03:23, 12.44it/s]
  7%|▋         | 203/2736 [00:16<03:25, 12.31it/s]
  7%|▋         | 205/2736 [00:16<03:25, 12.35it/s]
  8%|▊         | 207/2736 [00:16<03:24, 12.37it/s]
  8%|▊         | 209/2736 [00:16<03:23, 12.43it/s]
  8%|▊         | 211/2736 [00:16<03:23, 12.39it/s]
  8%|▊         | 213/2736 [00:17<03:25, 12.30it/s]
  8%|▊         | 215/2736 [00:17<03:23, 12.40it/s]
  8%|▊         | 217/2736 [00:17<03:24, 12.35it/s]
  8%|▊         | 219/2736 [00:17<03:22, 12.44it/s]
  8%|▊         | 221/2736 [00:17<03:22, 12.42it/s]
  8%|▊         | 223/2736 [00:17<03:22, 12.43it/s]
  8%|▊         | 225/2736 [00:18<03:20, 12.52it/s]
  8%|▊         | 227/2736 [00:18<03:21, 12.45it/s]
  8%|▊         | 229/2736 [00:18<03:20, 12.52it/s]
  8%|▊         | 231/2736 [00:18<03:20, 12.48it/s]
  9%|▊         | 233/2736 [00:18<03:20, 12.48it/s]
  9%|▊         | 235/2736 [00:18<03:19, 12.52it/s]
  9%|▊         | 237/2736 [00:19<03:20, 12.45it/s]
  9%|▊         | 239/2736 [00:19<03:21, 12.37it/s]
  9%|▉         | 241/2736 [00:19<03:20, 12.44it/s]
  9%|▉         | 243/2736 [00:19<03:21, 12.40it/s]
  9%|▉         | 245/2736 [00:19<03:20, 12.45it/s]
  9%|▉         | 247/2736 [00:19<03:20, 12.44it/s]
  9%|▉         | 249/2736 [00:20<03:19, 12.44it/s]
  9%|▉         | 251/2736 [00:20<03:21, 12.35it/s]
  9%|▉         | 253/2736 [00:20<03:20, 12.40it/s]
  9%|▉         | 255/2736 [00:20<03:21, 12.31it/s]
  9%|▉         | 257/2736 [00:20<03:21, 12.29it/s]
  9%|▉         | 259/2736 [00:20<03:21, 12.32it/s]
 10%|▉         | 261/2736 [00:21<03:20, 12.32it/s]
 10%|▉         | 263/2736 [00:21<03:20, 12.31it/s]
 10%|▉         | 265/2736 [00:21<03:19, 12.38it/s]
 10%|▉         | 267/2736 [00:21<03:21, 12.28it/s]
 10%|▉         | 269/2736 [00:21<03:21, 12.23it/s]
 10%|▉         | 271/2736 [00:21<03:19, 12.36it/s]
 10%|▉         | 273/2736 [00:21<03:19, 12.33it/s]
 10%|█         | 275/2736 [00:22<03:18, 12.42it/s]
 10%|█         | 277/2736 [00:22<03:18, 12.41it/s]
 10%|█         | 279/2736 [00:22<03:17, 12.45it/s]
 10%|█         | 281/2736 [00:22<03:17, 12.44it/s]
 10%|█         | 283/2736 [00:22<03:17, 12.44it/s]
 10%|█         | 285/2736 [00:22<03:17, 12.40it/s]
 10%|█         | 287/2736 [00:23<03:16, 12.45it/s]
 11%|█         | 289/2736 [00:23<03:16, 12.48it/s]
 11%|█         | 291/2736 [00:23<03:16, 12.46it/s]
 11%|█         | 293/2736 [00:23<03:16, 12.43it/s]
 11%|█         | 295/2736 [00:23<03:17, 12.38it/s]
 11%|█         | 297/2736 [00:23<03:16, 12.39it/s]
 11%|█         | 299/2736 [00:24<03:17, 12.33it/s]
 11%|█         | 301/2736 [00:24<03:16, 12.37it/s]
 11%|█         | 303/2736 [00:24<03:17, 12.33it/s]
 11%|█         | 305/2736 [00:24<03:17, 12.30it/s]
 11%|█         | 307/2736 [00:24<03:15, 12.40it/s]
 11%|█▏        | 309/2736 [00:24<03:14, 12.47it/s]
 11%|█▏        | 311/2736 [00:25<03:16, 12.37it/s]
 11%|█▏        | 313/2736 [00:25<03:16, 12.31it/s]
 12%|█▏        | 315/2736 [00:25<03:15, 12.39it/s]
 12%|█▏        | 317/2736 [00:25<03:16, 12.31it/s]
 12%|█▏        | 319/2736 [00:25<03:17, 12.23it/s]
 12%|█▏        | 321/2736 [00:25<03:15, 12.37it/s]
 12%|█▏        | 323/2736 [00:26<03:15, 12.33it/s]
 12%|█▏        | 325/2736 [00:26<03:16, 12.25it/s]
 12%|█▏        | 327/2736 [00:26<03:16, 12.23it/s]
 12%|█▏        | 329/2736 [00:26<03:14, 12.38it/s]
 12%|█▏        | 331/2736 [00:26<03:14, 12.35it/s]
 12%|█▏        | 333/2736 [00:26<03:15, 12.32it/s]
 12%|█▏        | 335/2736 [00:26<03:13, 12.43it/s]
 12%|█▏        | 337/2736 [00:27<03:14, 12.36it/s]
 12%|█▏        | 339/2736 [00:27<03:12, 12.48it/s]
 12%|█▏        | 341/2736 [00:27<03:11, 12.49it/s]
 13%|█▎        | 343/2736 [00:27<03:10, 12.55it/s]
 13%|█▎        | 345/2736 [00:27<03:10, 12.53it/s]
 13%|█▎        | 347/2736 [00:27<03:11, 12.48it/s]
 13%|█▎        | 349/2736 [00:28<03:11, 12.47it/s]
 13%|█▎        | 351/2736 [00:28<03:09, 12.56it/s]
 13%|█▎        | 353/2736 [00:28<03:11, 12.44it/s]
 13%|█▎        | 355/2736 [00:28<03:10, 12.49it/s]
 13%|█▎        | 357/2736 [00:28<03:11, 12.42it/s]
 13%|█▎        | 359/2736 [00:28<03:10, 12.48it/s]
 13%|█▎        | 361/2736 [00:29<03:10, 12.48it/s]
 13%|█▎        | 363/2736 [00:29<03:10, 12.43it/s]
 13%|█▎        | 365/2736 [00:29<03:09, 12.49it/s]
 13%|█▎        | 367/2736 [00:29<03:10, 12.41it/s]
 13%|█▎        | 369/2736 [00:29<03:10, 12.41it/s]
 14%|█▎        | 371/2736 [00:29<03:09, 12.46it/s]
 14%|█▎        | 373/2736 [00:30<03:10, 12.43it/s]
 14%|█▎        | 375/2736 [00:30<03:09, 12.44it/s]
 14%|█▍        | 377/2736 [00:30<03:09, 12.45it/s]
 14%|█▍        | 379/2736 [00:30<03:09, 12.42it/s]
 14%|█▍        | 381/2736 [00:30<03:10, 12.34it/s]
 14%|█▍        | 383/2736 [00:30<03:09, 12.41it/s]
 14%|█▍        | 385/2736 [00:31<03:10, 12.37it/s]
 14%|█▍        | 387/2736 [00:31<03:09, 12.36it/s]
 14%|█▍        | 389/2736 [00:31<03:09, 12.41it/s]
 14%|█▍        | 391/2736 [00:31<03:10, 12.34it/s]
 14%|█▍        | 393/2736 [00:31<03:08, 12.41it/s]
 14%|█▍        | 395/2736 [00:31<03:09, 12.36it/s]
 15%|█▍        | 397/2736 [00:31<03:08, 12.43it/s]
 15%|█▍        | 399/2736 [00:32<03:08, 12.37it/s]
 15%|█▍        | 401/2736 [00:32<03:08, 12.36it/s]
 15%|█▍        | 403/2736 [00:32<03:08, 12.36it/s]
 15%|█▍        | 405/2736 [00:32<03:08, 12.34it/s]
 15%|█▍        | 407/2736 [00:32<03:07, 12.41it/s]
 15%|█▍        | 409/2736 [00:32<03:06, 12.49it/s]
 15%|█▌        | 411/2736 [00:33<03:05, 12.51it/s]
 15%|█▌        | 413/2736 [00:33<03:06, 12.45it/s]
 15%|█▌        | 415/2736 [00:33<03:06, 12.42it/s]
 15%|█▌        | 417/2736 [00:33<03:06, 12.44it/s]
 15%|█▌        | 419/2736 [00:33<03:05, 12.47it/s]
 15%|█▌        | 421/2736 [00:33<03:06, 12.40it/s]
 15%|█▌        | 423/2736 [00:34<03:06, 12.43it/s]
 16%|█▌        | 425/2736 [00:34<03:06, 12.42it/s]
 16%|█▌        | 427/2736 [00:34<03:06, 12.40it/s]
 16%|█▌        | 429/2736 [00:34<03:05, 12.41it/s]
 16%|█▌        | 431/2736 [00:34<03:05, 12.40it/s]
 16%|█▌        | 433/2736 [00:34<03:05, 12.43it/s]
 16%|█▌        | 435/2736 [00:35<03:05, 12.44it/s]
 16%|█▌        | 437/2736 [00:35<03:04, 12.45it/s]
 16%|█▌        | 439/2736 [00:35<03:04, 12.46it/s]
 16%|█▌        | 441/2736 [00:35<03:04, 12.42it/s]
 16%|█▌        | 443/2736 [00:35<03:03, 12.50it/s]
 16%|█▋        | 445/2736 [00:35<03:03, 12.51it/s]
 16%|█▋        | 447/2736 [00:36<03:04, 12.38it/s]
 16%|█▋        | 449/2736 [00:36<03:05, 12.34it/s]
 16%|█▋        | 451/2736 [00:36<03:04, 12.38it/s]
 17%|█▋        | 453/2736 [00:36<03:03, 12.43it/s]
 17%|█▋        | 455/2736 [00:36<03:04, 12.37it/s]
 17%|█▋        | 457/2736 [00:36<03:03, 12.40it/s]
 17%|█▋        | 459/2736 [00:36<03:04, 12.35it/s]
 17%|█▋        | 461/2736 [00:37<03:02, 12.46it/s]
 17%|█▋        | 463/2736 [00:37<03:03, 12.38it/s]
 17%|█▋        | 465/2736 [00:37<03:02, 12.44it/s]
 17%|█▋        | 467/2736 [00:37<03:03, 12.35it/s]
 17%|█▋        | 469/2736 [00:37<03:02, 12.41it/s]
 17%|█▋        | 471/2736 [00:37<03:03, 12.38it/s]
 17%|█▋        | 473/2736 [00:38<03:02, 12.42it/s]
 17%|█▋        | 475/2736 [00:38<03:02, 12.36it/s]
 17%|█▋        | 477/2736 [00:38<03:02, 12.38it/s]
 18%|█▊        | 479/2736 [00:38<03:02, 12.39it/s]
 18%|█▊        | 481/2736 [00:38<03:02, 12.34it/s]
 18%|█▊        | 483/2736 [00:38<03:01, 12.41it/s]
 18%|█▊        | 485/2736 [00:39<03:01, 12.42it/s]
 18%|█▊        | 487/2736 [00:39<03:01, 12.39it/s]
 18%|█▊        | 489/2736 [00:39<03:00, 12.47it/s]
 18%|█▊        | 491/2736 [00:39<03:00, 12.43it/s]
 18%|█▊        | 493/2736 [00:39<02:59, 12.47it/s]
 18%|█▊        | 495/2736 [00:39<03:00, 12.45it/s]
 18%|█▊        | 497/2736 [00:40<02:59, 12.46it/s]
 18%|█▊        | 499/2736 [00:40<02:58, 12.50it/s]
 18%|█▊        | 501/2736 [00:40<02:59, 12.45it/s]
 18%|█▊        | 503/2736 [00:40<02:58, 12.48it/s]
 18%|█▊        | 505/2736 [00:40<02:57, 12.56it/s]
 19%|█▊        | 507/2736 [00:40<02:57, 12.53it/s]
 19%|█▊        | 509/2736 [00:40<02:58, 12.45it/s]
 19%|█▊        | 511/2736 [00:41<02:57, 12.50it/s]
 19%|█▉        | 513/2736 [00:41<02:58, 12.48it/s]
 19%|█▉        | 515/2736 [00:41<02:57, 12.53it/s]
 19%|█▉        | 517/2736 [00:41<02:57, 12.53it/s]
 19%|█▉        | 519/2736 [00:41<02:56, 12.53it/s]
 19%|█▉        | 521/2736 [00:41<02:56, 12.52it/s]
 19%|█▉        | 523/2736 [00:42<02:56, 12.54it/s]
 19%|█▉        | 525/2736 [00:42<02:57, 12.48it/s]
 19%|█▉        | 527/2736 [00:42<02:56, 12.52it/s]
 19%|█▉        | 529/2736 [00:42<02:57, 12.44it/s]
 19%|█▉        | 531/2736 [00:42<02:56, 12.49it/s]
 19%|█▉        | 533/2736 [00:42<02:55, 12.54it/s]
 20%|█▉        | 535/2736 [00:43<02:56, 12.44it/s]
 20%|█▉        | 537/2736 [00:43<02:56, 12.46it/s]
 20%|█▉        | 539/2736 [00:43<02:56, 12.47it/s]
 20%|█▉        | 541/2736 [00:43<02:56, 12.41it/s]
 20%|█▉        | 543/2736 [00:43<02:56, 12.45it/s]
 20%|█▉        | 545/2736 [00:43<02:55, 12.47it/s]
 20%|█▉        | 547/2736 [00:44<02:56, 12.42it/s]
 20%|██        | 549/2736 [00:44<02:56, 12.41it/s]
 20%|██        | 551/2736 [00:44<02:56, 12.41it/s]
 20%|██        | 553/2736 [00:44<02:55, 12.43it/s]
 20%|██        | 555/2736 [00:44<02:55, 12.40it/s]
 20%|██        | 557/2736 [00:44<02:56, 12.33it/s]
 20%|██        | 559/2736 [00:45<02:55, 12.39it/s]
 21%|██        | 561/2736 [00:45<02:56, 12.33it/s]
 21%|██        | 563/2736 [00:45<02:55, 12.41it/s]
 21%|██        | 565/2736 [00:45<02:55, 12.37it/s]
 21%|██        | 567/2736 [00:45<02:54, 12.43it/s]
 21%|██        | 569/2736 [00:45<02:55, 12.36it/s]
 21%|██        | 571/2736 [00:45<02:54, 12.41it/s]
 21%|██        | 573/2736 [00:46<02:54, 12.38it/s]
 21%|██        | 575/2736 [00:46<02:53, 12.48it/s]
 21%|██        | 577/2736 [00:46<02:54, 12.34it/s]
 21%|██        | 579/2736 [00:46<02:54, 12.33it/s]
 21%|██        | 581/2736 [00:46<02:53, 12.42it/s]
 21%|██▏       | 583/2736 [00:46<02:54, 12.34it/s]
 21%|██▏       | 585/2736 [00:47<02:52, 12.44it/s]
 21%|██▏       | 587/2736 [00:47<02:53, 12.36it/s]
 22%|██▏       | 589/2736 [00:47<02:52, 12.46it/s]
 22%|██▏       | 591/2736 [00:47<02:53, 12.39it/s]
 22%|██▏       | 593/2736 [00:47<02:51, 12.49it/s]
 22%|██▏       | 595/2736 [00:47<02:51, 12.47it/s]
 22%|██▏       | 597/2736 [00:48<02:51, 12.44it/s]
 22%|██▏       | 599/2736 [00:48<02:52, 12.40it/s]
 22%|██▏       | 601/2736 [00:48<02:52, 12.40it/s]
 22%|██▏       | 603/2736 [00:48<02:50, 12.49it/s]
 22%|██▏       | 605/2736 [00:48<02:51, 12.40it/s]
 22%|██▏       | 607/2736 [00:48<02:51, 12.42it/s]
 22%|██▏       | 609/2736 [00:49<02:51, 12.39it/s]
 22%|██▏       | 611/2736 [00:49<02:51, 12.41it/s]
 22%|██▏       | 613/2736 [00:49<02:51, 12.39it/s]
 22%|██▏       | 615/2736 [00:49<02:49, 12.48it/s]
 23%|██▎       | 617/2736 [00:49<02:50, 12.44it/s]
 23%|██▎       | 619/2736 [00:49<02:49, 12.47it/s]
 23%|██▎       | 621/2736 [00:49<02:49, 12.48it/s]
 23%|██▎       | 623/2736 [00:50<02:49, 12.46it/s]
 23%|██▎       | 625/2736 [00:50<02:49, 12.49it/s]
 23%|██▎       | 627/2736 [00:50<02:50, 12.40it/s]
 23%|██▎       | 629/2736 [00:50<02:48, 12.48it/s]
 23%|██▎       | 631/2736 [00:50<02:48, 12.46it/s]
 23%|██▎       | 633/2736 [00:50<02:48, 12.48it/s]
 23%|██▎       | 635/2736 [00:51<02:47, 12.51it/s]
 23%|██▎       | 637/2736 [00:51<02:48, 12.44it/s]
 23%|██▎       | 639/2736 [00:51<02:47, 12.49it/s]
 23%|██▎       | 641/2736 [00:51<02:49, 12.38it/s]
 24%|██▎       | 643/2736 [00:51<02:47, 12.46it/s]
 24%|██▎       | 645/2736 [00:51<02:48, 12.38it/s]
 24%|██▎       | 647/2736 [00:52<02:47, 12.45it/s]
 24%|██▎       | 649/2736 [00:52<02:48, 12.40it/s]
 24%|██▍       | 651/2736 [00:52<02:47, 12.46it/s]
 24%|██▍       | 653/2736 [00:52<02:47, 12.41it/s]
 24%|██▍       | 655/2736 [00:52<02:46, 12.48it/s]
 24%|██▍       | 657/2736 [00:52<02:47, 12.40it/s]
 24%|██▍       | 659/2736 [00:53<02:47, 12.40it/s]
 24%|██▍       | 661/2736 [00:53<02:46, 12.45it/s]
 24%|██▍       | 663/2736 [00:53<02:45, 12.49it/s]
 24%|██▍       | 665/2736 [00:53<02:45, 12.53it/s]
 24%|██▍       | 667/2736 [00:53<02:46, 12.43it/s]
 24%|██▍       | 669/2736 [00:53<02:45, 12.48it/s]
 25%|██▍       | 671/2736 [00:54<02:46, 12.40it/s]
 25%|██▍       | 673/2736 [00:54<02:45, 12.46it/s]
 25%|██▍       | 675/2736 [00:54<02:46, 12.38it/s]
 25%|██▍       | 677/2736 [00:54<02:45, 12.42it/s]
 25%|██▍       | 679/2736 [00:54<02:46, 12.37it/s]
 25%|██▍       | 681/2736 [00:54<02:44, 12.46it/s]
 25%|██▍       | 683/2736 [00:54<02:46, 12.37it/s]
 25%|██▌       | 685/2736 [00:55<02:44, 12.44it/s]
 25%|██▌       | 687/2736 [00:55<02:45, 12.39it/s]
 25%|██▌       | 689/2736 [00:55<02:45, 12.36it/s]
 25%|██▌       | 691/2736 [00:55<02:44, 12.40it/s]
 25%|██▌       | 693/2736 [00:55<02:43, 12.48it/s]
 25%|██▌       | 695/2736 [00:55<02:44, 12.39it/s]
 25%|██▌       | 697/2736 [00:56<02:44, 12.43it/s]
 26%|██▌       | 699/2736 [00:56<02:44, 12.40it/s]
 26%|██▌       | 701/2736 [00:56<02:45, 12.33it/s]
 26%|██▌       | 703/2736 [00:56<02:43, 12.41it/s]
 26%|██▌       | 705/2736 [00:56<02:43, 12.39it/s]
 26%|██▌       | 707/2736 [00:56<02:43, 12.42it/s]
 26%|██▌       | 709/2736 [00:57<02:43, 12.42it/s]
 26%|██▌       | 711/2736 [00:57<02:42, 12.46it/s]
 26%|██▌       | 713/2736 [00:57<02:41, 12.49it/s]
 26%|██▌       | 715/2736 [00:57<02:41, 12.48it/s]
 26%|██▌       | 717/2736 [00:57<02:42, 12.39it/s]
 26%|██▋       | 719/2736 [00:57<02:41, 12.46it/s]
 26%|██▋       | 721/2736 [00:58<02:42, 12.38it/s]
 26%|██▋       | 723/2736 [00:58<02:41, 12.46it/s]
 26%|██▋       | 725/2736 [00:58<02:40, 12.52it/s]
 27%|██▋       | 727/2736 [00:58<02:41, 12.43it/s]
 27%|██▋       | 729/2736 [00:58<02:43, 12.28it/s]
 27%|██▋       | 731/2736 [00:58<02:43, 12.26it/s]
 27%|██▋       | 733/2736 [00:59<02:43, 12.21it/s]
 27%|██▋       | 735/2736 [00:59<02:41, 12.35it/s]
 27%|██▋       | 737/2736 [00:59<02:42, 12.33it/s]
 27%|██▋       | 739/2736 [00:59<02:40, 12.41it/s]
 27%|██▋       | 741/2736 [00:59<02:42, 12.31it/s]
 27%|██▋       | 743/2736 [00:59<02:41, 12.36it/s]
 27%|██▋       | 745/2736 [00:59<02:41, 12.34it/s]
 27%|██▋       | 747/2736 [01:00<02:39, 12.44it/s]
 27%|██▋       | 749/2736 [01:00<02:40, 12.37it/s]
 27%|██▋       | 751/2736 [01:00<02:39, 12.48it/s]
 28%|██▊       | 753/2736 [01:00<02:40, 12.35it/s]
 28%|██▊       | 755/2736 [01:00<02:41, 12.29it/s]
 28%|██▊       | 757/2736 [01:00<02:40, 12.34it/s]
 28%|██▊       | 759/2736 [01:01<02:39, 12.36it/s]
 28%|██▊       | 761/2736 [01:01<02:38, 12.43it/s]
 28%|██▊       | 763/2736 [01:01<02:39, 12.36it/s]
 28%|██▊       | 765/2736 [01:01<02:38, 12.45it/s]
 28%|██▊       | 767/2736 [01:01<02:39, 12.36it/s]
 28%|██▊       | 769/2736 [01:01<02:37, 12.46it/s]
 28%|██▊       | 771/2736 [01:02<02:38, 12.42it/s]
 28%|██▊       | 773/2736 [01:02<02:37, 12.45it/s]
 28%|██▊       | 775/2736 [01:02<02:37, 12.43it/s]
 28%|██▊       | 777/2736 [01:02<02:37, 12.45it/s]
 28%|██▊       | 779/2736 [01:02<02:36, 12.52it/s]
 29%|██▊       | 781/2736 [01:02<02:36, 12.49it/s]
 29%|██▊       | 783/2736 [01:03<02:36, 12.45it/s]
 29%|██▊       | 785/2736 [01:03<02:36, 12.49it/s]
 29%|██▉       | 787/2736 [01:03<02:36, 12.44it/s]
 29%|██▉       | 789/2736 [01:03<02:35, 12.53it/s]
 29%|██▉       | 791/2736 [01:03<02:36, 12.44it/s]
 29%|██▉       | 793/2736 [01:03<02:35, 12.49it/s]
 29%|██▉       | 795/2736 [01:04<02:35, 12.51it/s]
 29%|██▉       | 797/2736 [01:04<02:35, 12.44it/s]
 29%|██▉       | 799/2736 [01:04<02:34, 12.50it/s]
 29%|██▉       | 801/2736 [01:04<02:35, 12.42it/s]
 29%|██▉       | 803/2736 [01:04<02:35, 12.47it/s]
 29%|██▉       | 805/2736 [01:04<02:34, 12.49it/s]
 29%|██▉       | 807/2736 [01:04<02:34, 12.50it/s]
 30%|██▉       | 809/2736 [01:05<02:34, 12.50it/s]
 30%|██▉       | 811/2736 [01:05<02:33, 12.54it/s]
 30%|██▉       | 813/2736 [01:05<02:33, 12.50it/s]
 30%|██▉       | 815/2736 [01:05<02:33, 12.52it/s]
 30%|██▉       | 817/2736 [01:05<02:32, 12.58it/s]
 30%|██▉       | 819/2736 [01:05<02:32, 12.55it/s]
 30%|███       | 821/2736 [01:06<02:32, 12.53it/s]
 30%|███       | 823/2736 [01:06<02:32, 12.55it/s]
 30%|███       | 825/2736 [01:06<02:32, 12.54it/s]
 30%|███       | 827/2736 [01:06<02:32, 12.53it/s]
 30%|███       | 829/2736 [01:06<02:32, 12.54it/s]
 30%|███       | 831/2736 [01:06<02:31, 12.54it/s]
 30%|███       | 833/2736 [01:07<02:32, 12.51it/s]
 31%|███       | 835/2736 [01:07<02:31, 12.52it/s]
 31%|███       | 837/2736 [01:07<02:31, 12.52it/s]
 31%|███       | 839/2736 [01:07<02:31, 12.56it/s]
 31%|███       | 841/2736 [01:07<02:31, 12.55it/s]
 31%|███       | 843/2736 [01:07<02:31, 12.49it/s]
 31%|███       | 845/2736 [01:08<02:31, 12.52it/s]
 31%|███       | 847/2736 [01:08<02:31, 12.44it/s]
 31%|███       | 849/2736 [01:08<02:31, 12.50it/s]
 31%|███       | 851/2736 [01:08<02:30, 12.51it/s]
 31%|███       | 853/2736 [01:08<02:30, 12.54it/s]
 31%|███▏      | 855/2736 [01:08<02:29, 12.54it/s]
 31%|███▏      | 857/2736 [01:08<02:29, 12.53it/s]
 31%|███▏      | 859/2736 [01:09<02:29, 12.55it/s]
 31%|███▏      | 861/2736 [01:09<02:29, 12.52it/s]
 32%|███▏      | 863/2736 [01:09<02:29, 12.51it/s]
 32%|███▏      | 865/2736 [01:09<02:29, 12.52it/s]
 32%|███▏      | 867/2736 [01:09<02:29, 12.54it/s]
 32%|███▏      | 869/2736 [01:09<02:28, 12.55it/s]
 32%|███▏      | 871/2736 [01:10<02:28, 12.58it/s]
 32%|███▏      | 873/2736 [01:10<02:28, 12.54it/s]
 32%|███▏      | 875/2736 [01:10<02:30, 12.41it/s]
 32%|███▏      | 877/2736 [01:10<02:30, 12.34it/s]
 32%|███▏      | 879/2736 [01:10<02:29, 12.43it/s]
 32%|███▏      | 881/2736 [01:10<02:30, 12.35it/s]
 32%|███▏      | 883/2736 [01:11<02:29, 12.43it/s]
 32%|███▏      | 885/2736 [01:11<02:29, 12.41it/s]
 32%|███▏      | 887/2736 [01:11<02:28, 12.42it/s]
 32%|███▏      | 889/2736 [01:11<02:28, 12.46it/s]
 33%|███▎      | 891/2736 [01:11<02:28, 12.42it/s]
 33%|███▎      | 893/2736 [01:11<02:27, 12.46it/s]
 33%|███▎      | 895/2736 [01:12<02:27, 12.48it/s]
 33%|███▎      | 897/2736 [01:12<02:28, 12.42it/s]
 33%|███▎      | 899/2736 [01:12<02:27, 12.42it/s]
 33%|███▎      | 901/2736 [01:12<02:27, 12.44it/s]
 33%|███▎      | 903/2736 [01:12<02:27, 12.44it/s]
 33%|███▎      | 905/2736 [01:12<02:27, 12.45it/s]
 33%|███▎      | 907/2736 [01:12<02:27, 12.39it/s]
 33%|███▎      | 909/2736 [01:13<02:26, 12.46it/s]
 33%|███▎      | 911/2736 [01:13<02:26, 12.44it/s]
+
  0%|          | 0/126 [00:00<?, ?it/s]
+
  1%|          | 1/126 [00:02<04:43,  2.27s/it]
+
  2%|▏         | 2/126 [00:03<03:28,  1.68s/it]
+
  2%|▏         | 3/126 [00:04<03:02,  1.48s/it]
+
  3%|▎         | 4/126 [00:06<02:49,  1.39s/it]
+
  4%|▍         | 5/126 [00:07<02:41,  1.34s/it]
+
  5%|▍         | 6/126 [00:08<02:36,  1.31s/it]
+
  6%|▌         | 7/126 [00:09<02:33,  1.29s/it]
+
  6%|▋         | 8/126 [00:11<02:31,  1.28s/it]
+
  7%|▋         | 9/126 [00:12<02:28,  1.27s/it]
+
  8%|▊         | 10/126 [00:13<02:26,  1.26s/it]
+
  9%|▊         | 11/126 [00:14<02:24,  1.26s/it]
 33%|███▎      | 912/2736 [01:28<02:26, 12.44it/s]
+
 10%|▉         | 12/126 [00:16<02:23,  1.26s/it]
+
 10%|█         | 13/126 [00:17<02:20,  1.25s/it]
+
 11%|█         | 14/126 [00:18<02:18,  1.23s/it]
+
 12%|█▏        | 15/126 [00:19<02:17,  1.24s/it]
+
 13%|█▎        | 16/126 [00:20<02:16,  1.24s/it]
+
 13%|█▎        | 17/126 [00:22<02:15,  1.25s/it]
+
 14%|█▍        | 18/126 [00:23<02:14,  1.25s/it]
+
 15%|█▌        | 19/126 [00:24<02:13,  1.24s/it]
+
 16%|█▌        | 20/126 [00:25<02:11,  1.24s/it]
+
 17%|█▋        | 21/126 [00:27<02:10,  1.24s/it]
+
 17%|█▋        | 22/126 [00:28<02:09,  1.25s/it]
+
 18%|█▊        | 23/126 [00:29<02:08,  1.25s/it]
+
 19%|█▉        | 24/126 [00:30<02:07,  1.25s/it]
+
 20%|█▉        | 25/126 [00:32<02:07,  1.26s/it]
+
 21%|██        | 26/126 [00:33<02:04,  1.24s/it]
+
 21%|██▏       | 27/126 [00:34<02:01,  1.23s/it]
+
 22%|██▏       | 28/126 [00:35<01:59,  1.22s/it]
+
 23%|██▎       | 29/126 [00:37<01:58,  1.22s/it]
+
 24%|██▍       | 30/126 [00:38<01:56,  1.21s/it]
+
 25%|██▍       | 31/126 [00:39<01:55,  1.21s/it]
+
 25%|██▌       | 32/126 [00:40<01:53,  1.21s/it]
+
 26%|██▌       | 33/126 [00:41<01:52,  1.21s/it]
+
 27%|██▋       | 34/126 [00:43<01:50,  1.20s/it]
+
 28%|██▊       | 35/126 [00:44<01:49,  1.20s/it]
+
 29%|██▊       | 36/126 [00:45<01:47,  1.20s/it]
+
 29%|██▉       | 37/126 [00:46<01:46,  1.20s/it]
+
 30%|███       | 38/126 [00:47<01:45,  1.20s/it]
+
 31%|███       | 39/126 [00:49<01:44,  1.20s/it]
+
 32%|███▏      | 40/126 [00:50<01:43,  1.20s/it]
+
 33%|███▎      | 41/126 [00:51<01:42,  1.20s/it]
+
 33%|███▎      | 42/126 [00:52<01:40,  1.20s/it]
+
 34%|███▍      | 43/126 [00:53<01:39,  1.20s/it]
+
 35%|███▍      | 44/126 [00:55<01:38,  1.20s/it]
+
 36%|███▌      | 45/126 [00:56<01:37,  1.20s/it]
+
 37%|███▋      | 46/126 [00:57<01:36,  1.20s/it]
+
 37%|███▋      | 47/126 [00:58<01:34,  1.20s/it]
+
 38%|███▊      | 48/126 [00:59<01:35,  1.23s/it]
+
 39%|███▉      | 49/126 [01:01<01:34,  1.22s/it]
+
 40%|███▉      | 50/126 [01:02<01:32,  1.21s/it]
+
 40%|████      | 51/126 [01:03<01:30,  1.21s/it]
+
 41%|████▏     | 52/126 [01:04<01:29,  1.21s/it]
+
 42%|████▏     | 53/126 [01:05<01:27,  1.20s/it]
+
 43%|████▎     | 54/126 [01:07<01:26,  1.20s/it]
+
 44%|████▎     | 55/126 [01:08<01:25,  1.20s/it]
+
 44%|████▍     | 56/126 [01:09<01:24,  1.20s/it]
+
 45%|████▌     | 57/126 [01:10<01:23,  1.20s/it]
+
 46%|████▌     | 58/126 [01:11<01:21,  1.20s/it]
+
 47%|████▋     | 59/126 [01:13<01:20,  1.20s/it]
+
 48%|████▊     | 60/126 [01:14<01:19,  1.20s/it]
+
 48%|████▊     | 61/126 [01:15<01:18,  1.20s/it]
+
 49%|████▉     | 62/126 [01:16<01:16,  1.20s/it]
+
 50%|█████     | 63/126 [01:17<01:15,  1.20s/it]
+
 51%|█████     | 64/126 [01:19<01:14,  1.20s/it]
+
 52%|█████▏    | 65/126 [01:20<01:13,  1.20s/it]
+
 52%|█████▏    | 66/126 [01:21<01:11,  1.20s/it]
+
 53%|█████▎    | 67/126 [01:22<01:10,  1.20s/it]
+
 54%|█████▍    | 68/126 [01:23<01:09,  1.20s/it]
+
 55%|█████▍    | 69/126 [01:25<01:08,  1.20s/it]
+
 56%|█████▌    | 70/126 [01:26<01:07,  1.20s/it]
+
 56%|█████▋    | 71/126 [01:27<01:05,  1.20s/it]
+
 57%|█████▋    | 72/126 [01:28<01:04,  1.20s/it]
+
 58%|█████▊    | 73/126 [01:29<01:03,  1.20s/it]
+
 59%|█████▊    | 74/126 [01:31<01:02,  1.20s/it]
+
 60%|█████▉    | 75/126 [01:32<01:01,  1.20s/it]
+
 60%|██████    | 76/126 [01:33<00:59,  1.20s/it]
+
 61%|██████    | 77/126 [01:34<00:58,  1.20s/it]
+
 62%|██████▏   | 78/126 [01:35<00:57,  1.20s/it]
+
 63%|██████▎   | 79/126 [01:37<00:56,  1.21s/it]
+
 63%|██████▎   | 80/126 [01:38<00:55,  1.21s/it]
+
 64%|██████▍   | 81/126 [01:39<00:54,  1.20s/it]
+
 65%|██████▌   | 82/126 [01:40<00:52,  1.20s/it]
+
 66%|██████▌   | 83/126 [01:41<00:51,  1.20s/it]
+
 67%|██████▋   | 84/126 [01:43<00:50,  1.20s/it]
+
 67%|██████▋   | 85/126 [01:44<00:49,  1.20s/it]
+
 68%|██████▊   | 86/126 [01:45<00:48,  1.21s/it]
+
 69%|██████▉   | 87/126 [01:46<00:46,  1.20s/it]
+
 70%|██████▉   | 88/126 [01:47<00:45,  1.20s/it]
+
 71%|███████   | 89/126 [01:49<00:44,  1.20s/it]
+
 71%|███████▏  | 90/126 [01:50<00:43,  1.20s/it]
+
 72%|███████▏  | 91/126 [01:51<00:41,  1.20s/it]
+
 73%|███████▎  | 92/126 [01:52<00:40,  1.20s/it]
+
 74%|███████▍  | 93/126 [01:53<00:39,  1.19s/it]
+
 75%|███████▍  | 94/126 [01:55<00:38,  1.19s/it]
+
 75%|███████▌  | 95/126 [01:56<00:37,  1.20s/it]
+
 76%|███████▌  | 96/126 [01:57<00:35,  1.20s/it]
+
 77%|███████▋  | 97/126 [01:58<00:34,  1.20s/it]
+
 78%|███████▊  | 98/126 [01:59<00:33,  1.20s/it]
+
 79%|███████▊  | 99/126 [02:01<00:32,  1.20s/it]
+
 79%|███████▉  | 100/126 [02:02<00:31,  1.20s/it]
+
 80%|████████  | 101/126 [02:03<00:29,  1.20s/it]
+
 81%|████████  | 102/126 [02:04<00:28,  1.20s/it]
+
 82%|████████▏ | 103/126 [02:05<00:27,  1.20s/it]
+
 83%|████████▎ | 104/126 [02:07<00:26,  1.20s/it]
+
 83%|████████▎ | 105/126 [02:08<00:25,  1.20s/it]
+
 84%|████████▍ | 106/126 [02:09<00:23,  1.20s/it]
+
 85%|████████▍ | 107/126 [02:10<00:22,  1.20s/it]
+
 86%|████████▌ | 108/126 [02:11<00:21,  1.20s/it]
+
 87%|████████▋ | 109/126 [02:13<00:20,  1.20s/it]
+
 87%|████████▋ | 110/126 [02:14<00:19,  1.20s/it]
+
 88%|████████▊ | 111/126 [02:15<00:18,  1.20s/it]
+
 89%|████████▉ | 112/126 [02:16<00:16,  1.20s/it]
+
 90%|████████▉ | 113/126 [02:17<00:15,  1.20s/it]
+
 90%|█████████ | 114/126 [02:19<00:14,  1.20s/it]
+
 91%|█████████▏| 115/126 [02:20<00:13,  1.21s/it]
+
 92%|█████████▏| 116/126 [02:21<00:12,  1.21s/it]
+
 93%|█████████▎| 117/126 [02:22<00:10,  1.21s/it]
+
 94%|█████████▎| 118/126 [02:23<00:09,  1.20s/it]
+
 94%|█████████▍| 119/126 [02:25<00:08,  1.20s/it]
+
 95%|█████████▌| 120/126 [02:26<00:07,  1.20s/it]
+
 96%|█████████▌| 121/126 [02:27<00:06,  1.20s/it]
+
 97%|█████████▋| 122/126 [02:28<00:04,  1.20s/it]
+
 98%|█████████▊| 123/126 [02:29<00:03,  1.20s/it]
+
 98%|█████████▊| 124/126 [02:31<00:02,  1.20s/it]
 98%|█████████▊| 124/126 [02:31<00:02,  1.22s/it]
+Traceback (most recent call last):
+  File "/mnt/storage/aatherton/hf_synth_trans/synth_translation.py", line 217, in <module>
+    for batch in tqdm(eval_dataloader):
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/tqdm/std.py", line 1178, in __iter__
+    for obj in iterable:
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/accelerate/data_loader.py", line 394, in __iter__
+    next_batch = next(dataloader_iter)
+                 ^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 633, in __next__
+    data = self._next_data()
+           ^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 677, in _next_data
+    data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/torch/utils/data/_utils/fetch.py", line 54, in fetch
+    return self.collate_fn(data)
+           ^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/data/data_collator.py", line 600, in __call__
+    decoder_input_ids = self.model.prepare_decoder_input_ids_from_labels(labels=features["labels"])
+                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/marian/modeling_marian.py", line 1527, in prepare_decoder_input_ids_from_labels
+    return shift_tokens_right(labels, self.config.pad_token_id, self.config.decoder_start_token_id)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/mnt/storage/aatherton/anaconda3/envs/nmt/lib/python3.11/site-packages/transformers/models/marian/modeling_marian.py", line 66, in shift_tokens_right
+    shifted_input_ids[:, 0] = decoder_start_token_id
+    ~~~~~~~~~~~~~~~~~^^^^^^
+IndexError: index 0 is out of bounds for dimension 1 with size 0
+
 33%|███▎      | 912/2736 [03:44<07:29,  4.06it/s]

myoutput_1558.out

@@ -0,0 +1,4 @@
+
+
+
+evaluate1

myoutput_1559.out

@@ -0,0 +1,4 @@
+
+
+
+evaluate1

myoutput_1560.out

@@ -0,0 +1,4 @@
+
+
+
+evaluate1

myoutput_1561.out

@@ -0,0 +1,8 @@
+
+
+
+evaluate1
+trainer train 1
+{'loss': 0.6532, 'learning_rate': 5.380116959064328e-06, 'epoch': 2.19}
+{'train_runtime': 57.6599, 'train_samples_per_second': 379.397, 'train_steps_per_second': 11.863, 'train_loss': 0.6262621963233278, 'epoch': 3.0}
+evaluate 2

myoutput_1562.out

@@ -0,0 +1,10 @@
+
+
+
+evaluate1
+{'eval_loss': 0.5364619493484497, 'eval_bleu': 0.0, 'eval_runtime': 69.2839, 'eval_samples_per_second': 14.448, 'eval_steps_per_second': 0.231}
+trainer train 1
+{'loss': 0.4504, 'learning_rate': 5.380116959064328e-06, 'epoch': 2.19}
+{'train_runtime': 58.3552, 'train_samples_per_second': 374.877, 'train_steps_per_second': 11.721, 'train_loss': 0.4447354879992747, 'epoch': 3.0}
+evaluate 2
+{'eval_loss': 0.411633163690567, 'eval_bleu': 0.0, 'eval_runtime': 68.1275, 'eval_samples_per_second': 14.693, 'eval_steps_per_second': 0.235, 'epoch': 3.0}

myoutput_1563.out

@@ -0,0 +1,61 @@
+
+
+
+MarianMTModel(
+  (model): MarianModel(
+    (shared): Embedding(59514, 512, padding_idx=59513)
+    (encoder): MarianEncoder(
+      (embed_tokens): Embedding(59514, 512, padding_idx=59513)
+      (embed_positions): MarianSinusoidalPositionalEmbedding(512, 512)
+      (layers): ModuleList(
+        (0-5): 6 x MarianEncoderLayer(
+          (self_attn): MarianAttention(
+            (k_proj): Linear(in_features=512, out_features=512, bias=True)
+            (v_proj): Linear(in_features=512, out_features=512, bias=True)
+            (q_proj): Linear(in_features=512, out_features=512, bias=True)
+            (out_proj): Linear(in_features=512, out_features=512, bias=True)
+          )
+          (self_attn_layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (activation_fn): SiLUActivation()
+          (fc1): Linear(in_features=512, out_features=2048, bias=True)
+          (fc2): Linear(in_features=2048, out_features=512, bias=True)
+          (final_layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+        )
+      )
+    )
+    (decoder): MarianDecoder(
+      (embed_tokens): Embedding(59514, 512, padding_idx=59513)
+      (embed_positions): MarianSinusoidalPositionalEmbedding(512, 512)
+      (layers): ModuleList(
+        (0-5): 6 x MarianDecoderLayer(
+          (self_attn): MarianAttention(
+            (k_proj): Linear(in_features=512, out_features=512, bias=True)
+            (v_proj): Linear(in_features=512, out_features=512, bias=True)
+            (q_proj): Linear(in_features=512, out_features=512, bias=True)
+            (out_proj): Linear(in_features=512, out_features=512, bias=True)
+          )
+          (activation_fn): SiLUActivation()
+          (self_attn_layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (encoder_attn): MarianAttention(
+            (k_proj): Linear(in_features=512, out_features=512, bias=True)
+            (v_proj): Linear(in_features=512, out_features=512, bias=True)
+            (q_proj): Linear(in_features=512, out_features=512, bias=True)
+            (out_proj): Linear(in_features=512, out_features=512, bias=True)
+          )
+          (encoder_attn_layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (fc1): Linear(in_features=512, out_features=2048, bias=True)
+          (fc2): Linear(in_features=2048, out_features=512, bias=True)
+          (final_layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+        )
+      )
+    )
+  )
+  (lm_head): Linear(in_features=512, out_features=59514, bias=False)
+)
+evaluate1
+{'eval_loss': 0.411633163690567, 'eval_bleu': 0.0, 'eval_runtime': 69.9028, 'eval_samples_per_second': 14.32, 'eval_steps_per_second': 0.229}
+trainer train 1
+{'loss': 0.3189, 'learning_rate': 5.380116959064328e-06, 'epoch': 2.19}
+{'train_runtime': 57.9326, 'train_samples_per_second': 377.611, 'train_steps_per_second': 11.807, 'train_loss': 0.3294184054547583, 'epoch': 3.0}
+evaluate 2
+{'eval_loss': 0.33941635489463806, 'eval_bleu': 0.0, 'eval_runtime': 69.4586, 'eval_samples_per_second': 14.411, 'eval_steps_per_second': 0.23, 'epoch': 3.0}

myoutput_1564.out

@@ -0,0 +1,61 @@
+
+
+
+MarianMTModel(
+  (model): MarianModel(
+    (shared): Embedding(59514, 512, padding_idx=59513)
+    (encoder): MarianEncoder(
+      (embed_tokens): Embedding(59514, 512, padding_idx=59513)
+      (embed_positions): MarianSinusoidalPositionalEmbedding(512, 512)
+      (layers): ModuleList(
+        (0-5): 6 x MarianEncoderLayer(
+          (self_attn): MarianAttention(
+            (k_proj): Linear(in_features=512, out_features=512, bias=True)
+            (v_proj): Linear(in_features=512, out_features=512, bias=True)
+            (q_proj): Linear(in_features=512, out_features=512, bias=True)
+            (out_proj): Linear(in_features=512, out_features=512, bias=True)
+          )
+          (self_attn_layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (activation_fn): SiLUActivation()
+          (fc1): Linear(in_features=512, out_features=2048, bias=True)
+          (fc2): Linear(in_features=2048, out_features=512, bias=True)
+          (final_layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+        )
+      )
+    )
+    (decoder): MarianDecoder(
+      (embed_tokens): Embedding(59514, 512, padding_idx=59513)
+      (embed_positions): MarianSinusoidalPositionalEmbedding(512, 512)
+      (layers): ModuleList(
+        (0-5): 6 x MarianDecoderLayer(
+          (self_attn): MarianAttention(
+            (k_proj): Linear(in_features=512, out_features=512, bias=True)
+            (v_proj): Linear(in_features=512, out_features=512, bias=True)
+            (q_proj): Linear(in_features=512, out_features=512, bias=True)
+            (out_proj): Linear(in_features=512, out_features=512, bias=True)
+          )
+          (activation_fn): SiLUActivation()
+          (self_attn_layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (encoder_attn): MarianAttention(
+            (k_proj): Linear(in_features=512, out_features=512, bias=True)
+            (v_proj): Linear(in_features=512, out_features=512, bias=True)
+            (q_proj): Linear(in_features=512, out_features=512, bias=True)
+            (out_proj): Linear(in_features=512, out_features=512, bias=True)
+          )
+          (encoder_attn_layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (fc1): Linear(in_features=512, out_features=2048, bias=True)
+          (fc2): Linear(in_features=2048, out_features=512, bias=True)
+          (final_layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+        )
+      )
+    )
+  )
+  (lm_head): Linear(in_features=512, out_features=59514, bias=False)
+)
+evaluate1
+{'eval_loss': 0.3534283936023712, 'eval_bleu': 0.0, 'eval_runtime': 69.9139, 'eval_samples_per_second': 14.318, 'eval_steps_per_second': 0.229}
+trainer train 1
+{'loss': 0.2276, 'learning_rate': 5.380116959064328e-06, 'epoch': 2.19}
+{'train_runtime': 56.8014, 'train_samples_per_second': 385.131, 'train_steps_per_second': 12.042, 'train_loss': 0.2556379162080107, 'epoch': 3.0}
+evaluate 2
+{'eval_loss': 0.30410629510879517, 'eval_bleu': 0.0, 'eval_runtime': 69.9679, 'eval_samples_per_second': 14.307, 'eval_steps_per_second': 0.229, 'epoch': 3.0}

synth_translation.py

@@ -21,9 +21,9 @@ from torch import Tensor
 #load in dataset, setup tokenizer
 
 raw_datasets = load_dataset("aatherton2024/eng-nah-svo")
-model_checkpoint = "aatherton2024/eng-nah-svo-cpt"
+model_checkpoint = "eng-nah-svo-cpt"
 
-if False:
+if True:
     def get_training_corpus(raw_datasets):
         return (
             raw_datasets["train"][i : i + 1000]
@@ -65,12 +65,10 @@ if False:
 else:
     from transformers import BertConfig, BertLMHeadModel
     from transformers import AutoModel
-    # config = BertConfig(tokenizer.vocab_size, hidden_size=300,
-    #                     num_hidden_layers=2, num_attention_heads=2, is_decoder=True,
-    #                     add_cross_attention=True)
-    # model = BertLMHeadModel(config)
-    #model = AutoModel.from_pretrained("bert-base-cased")
-    model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-fr")
+
+    model = AutoModelForSeq2SeqLM.from_pretrained("eng-nah-svo-translation")
+    print(model)
+    #model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-fr")
 
 #data collator takes tokenizer and the model to deal with padding for dynamic batching
 data_collator = DataCollatorForSeq2Seq(tokenizer, model=model)
@@ -129,11 +127,11 @@ trainer = Seq2SeqTrainer(
 )
 
 print("evaluate1")
-trainer.evaluate(max_length=max_length)
+print(trainer.evaluate(max_length=max_length))
 print("trainer train 1")
 trainer.train()
 print("evaluate 2")
-trainer.evaluate(max_length=max_length)
+print(trainer.evaluate(max_length=max_length))
 trainer.push_to_hub(tags="translation", commit_message="Training complete")
 
 
@@ -149,7 +147,7 @@ eval_dataloader = DataLoader(
     tokenized_datasets["test"], collate_fn=data_collator, batch_size=8
 )
 
-model = AutoModelForSeq2SeqLM.from_pretrained(model_checkpoint)
+model = AutoModelForSeq2SeqLM.from_pretrained("eng-nah-svo-translation")
 
 
 optimizer = AdamW(model.parameters(), lr=2e-5)