From 36f8fe9f4184c35463332fa0d792410cdbc51e4b Mon Sep 17 00:00:00 2001
From: ModelHub XC <noreply@modelhub.org.cn>
Date: Tue, 19 May 2026 07:18:58 +0800
Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?=
 =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?=
 =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Model: alinerodrigues/wav2vec2-large-xlsr-mecita-coraa-portuguese-2-all-03
Source: Original Platform
---
 .gitattributes           |  35 ++
 .gitignore               |   1 +
 README.md                | 125 +++++
 added_tokens.json        |   4 +
 all_results.json         |  16 +
 config.json              | 115 +++++
 eval_results.json        |  10 +
 preprocessor_config.json |  10 +
 pytorch_model.bin        |   3 +
 special_tokens_map.json  |  22 +
 tokenizer_config.json    |  12 +
 train_results.json       |   9 +
 trainer_state.json       | 985 +++++++++++++++++++++++++++++++++++++++
 training_args.bin        |   3 +
 vocab.json               |  40 ++
 15 files changed, 1390 insertions(+)
 create mode 100644 .gitattributes
 create mode 100644 .gitignore
 create mode 100644 README.md
 create mode 100644 added_tokens.json
 create mode 100644 all_results.json
 create mode 100644 config.json
 create mode 100644 eval_results.json
 create mode 100644 preprocessor_config.json
 create mode 100644 pytorch_model.bin
 create mode 100644 special_tokens_map.json
 create mode 100644 tokenizer_config.json
 create mode 100644 train_results.json
 create mode 100644 trainer_state.json
 create mode 100644 training_args.bin
 create mode 100644 vocab.json

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..a6344aa
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..0348ea9
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+checkpoint-*/
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..1d5c557
--- /dev/null
+++ b/README.md
@@ -0,0 +1,125 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: wav2vec2-large-xlsr-mecita-coraa-portuguese-2-all-03
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# wav2vec2-large-xlsr-mecita-coraa-portuguese-2-all-03
+
+This model is a fine-tuned version of [Edresson/wav2vec2-large-xlsr-coraa-portuguese](https://huggingface.co/Edresson/wav2vec2-large-xlsr-coraa-portuguese) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1350
+- Wer: 0.0841
+- Cer: 0.0261
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
+| 28.65         | 1.0   | 86   | 3.1940          | 1.0    | 1.0    |
+| 8.1771        | 2.0   | 172  | 2.9853          | 1.0    | 1.0    |
+| 3.0358        | 3.0   | 258  | 2.8955          | 1.0    | 1.0    |
+| 2.9359        | 4.0   | 344  | 2.9086          | 1.0    | 1.0    |
+| 2.9026        | 5.0   | 430  | 2.6946          | 0.9998 | 0.9998 |
+| 2.4934        | 6.0   | 516  | 0.9106          | 0.4944 | 0.1257 |
+| 1.1576        | 7.0   | 602  | 0.4618          | 0.2291 | 0.0627 |
+| 1.1576        | 8.0   | 688  | 0.3427          | 0.1871 | 0.0538 |
+| 0.7498        | 9.0   | 774  | 0.2838          | 0.1673 | 0.0480 |
+| 0.5493        | 10.0  | 860  | 0.2504          | 0.1490 | 0.0442 |
+| 0.4735        | 11.0  | 946  | 0.2318          | 0.1388 | 0.0412 |
+| 0.4183        | 12.0  | 1032 | 0.2174          | 0.1215 | 0.0374 |
+| 0.3924        | 13.0  | 1118 | 0.2019          | 0.1127 | 0.0357 |
+| 0.3497        | 14.0  | 1204 | 0.1876          | 0.1112 | 0.0343 |
+| 0.3497        | 15.0  | 1290 | 0.1865          | 0.1110 | 0.0351 |
+| 0.3335        | 16.0  | 1376 | 0.1759          | 0.1065 | 0.0328 |
+| 0.3259        | 17.0  | 1462 | 0.1718          | 0.0941 | 0.0310 |
+| 0.2822        | 18.0  | 1548 | 0.1664          | 0.0965 | 0.0307 |
+| 0.2689        | 19.0  | 1634 | 0.1638          | 0.0951 | 0.0302 |
+| 0.262         | 20.0  | 1720 | 0.1616          | 0.0937 | 0.0307 |
+| 0.2623        | 21.0  | 1806 | 0.1574          | 0.0927 | 0.0299 |
+| 0.2623        | 22.0  | 1892 | 0.1559          | 0.0944 | 0.0306 |
+| 0.2344        | 23.0  | 1978 | 0.1538          | 0.0920 | 0.0293 |
+| 0.2315        | 24.0  | 2064 | 0.1533          | 0.0927 | 0.0298 |
+| 0.2411        | 25.0  | 2150 | 0.1520          | 0.0908 | 0.0294 |
+| 0.2102        | 26.0  | 2236 | 0.1496          | 0.0922 | 0.0297 |
+| 0.2115        | 27.0  | 2322 | 0.1473          | 0.0979 | 0.0298 |
+| 0.2139        | 28.0  | 2408 | 0.1496          | 0.0958 | 0.0300 |
+| 0.2139        | 29.0  | 2494 | 0.1446          | 0.0903 | 0.0289 |
+| 0.2218        | 30.0  | 2580 | 0.1482          | 0.0913 | 0.0291 |
+| 0.1982        | 31.0  | 2666 | 0.1439          | 0.0891 | 0.0284 |
+| 0.196         | 32.0  | 2752 | 0.1428          | 0.0934 | 0.0286 |
+| 0.1846        | 33.0  | 2838 | 0.1404          | 0.0906 | 0.0281 |
+| 0.1873        | 34.0  | 2924 | 0.1395          | 0.0856 | 0.0272 |
+| 0.1854        | 35.0  | 3010 | 0.1354          | 0.0846 | 0.0268 |
+| 0.1854        | 36.0  | 3096 | 0.1359          | 0.0858 | 0.0271 |
+| 0.1851        | 37.0  | 3182 | 0.1356          | 0.0903 | 0.0276 |
+| 0.1733        | 38.0  | 3268 | 0.1380          | 0.0851 | 0.0270 |
+| 0.1781        | 39.0  | 3354 | 0.1359          | 0.0813 | 0.0258 |
+| 0.1821        | 40.0  | 3440 | 0.1383          | 0.0863 | 0.0274 |
+| 0.1724        | 41.0  | 3526 | 0.1377          | 0.0822 | 0.0265 |
+| 0.1591        | 42.0  | 3612 | 0.1379          | 0.0844 | 0.0266 |
+| 0.1591        | 43.0  | 3698 | 0.1350          | 0.0841 | 0.0261 |
+| 0.168         | 44.0  | 3784 | 0.1362          | 0.0846 | 0.0265 |
+| 0.162         | 45.0  | 3870 | 0.1353          | 0.0820 | 0.0266 |
+| 0.145         | 46.0  | 3956 | 0.1414          | 0.0849 | 0.0270 |
+| 0.1639        | 47.0  | 4042 | 0.1400          | 0.0837 | 0.0266 |
+| 0.1572        | 48.0  | 4128 | 0.1387          | 0.0815 | 0.0261 |
+| 0.14          | 49.0  | 4214 | 0.1384          | 0.0822 | 0.0258 |
+| 0.1473        | 50.0  | 4300 | 0.1399          | 0.0827 | 0.0265 |
+| 0.1473        | 51.0  | 4386 | 0.1408          | 0.0822 | 0.0265 |
+| 0.1722        | 52.0  | 4472 | 0.1411          | 0.0851 | 0.0267 |
+| 0.1518        | 53.0  | 4558 | 0.1410          | 0.0860 | 0.0273 |
+| 0.1506        | 54.0  | 4644 | 0.1403          | 0.0858 | 0.0270 |
+| 0.1442        | 55.0  | 4730 | 0.1380          | 0.0832 | 0.0262 |
+| 0.1427        | 56.0  | 4816 | 0.1395          | 0.0815 | 0.0265 |
+| 0.132         | 57.0  | 4902 | 0.1384          | 0.0813 | 0.0259 |
+| 0.132         | 58.0  | 4988 | 0.1353          | 0.0818 | 0.0261 |
+| 0.1374        | 59.0  | 5074 | 0.1405          | 0.0834 | 0.0265 |
+| 0.1318        | 60.0  | 5160 | 0.1383          | 0.0811 | 0.0258 |
+| 0.1339        | 61.0  | 5246 | 0.1386          | 0.0813 | 0.0261 |
+| 0.1346        | 62.0  | 5332 | 0.1399          | 0.0801 | 0.0253 |
+| 0.1261        | 63.0  | 5418 | 0.1430          | 0.0832 | 0.0263 |
+
+
+### Framework versions
+
+- Transformers 4.28.0
+- Pytorch 2.1.1+cu121
+- Datasets 2.15.0
+- Tokenizers 0.13.3
diff --git a/added_tokens.json b/added_tokens.json
new file mode 100644
index 0000000..108cfe3
--- /dev/null
+++ b/added_tokens.json
@@ -0,0 +1,4 @@
+{
+  "</s>": 39,
+  "<s>": 38
+}
diff --git a/all_results.json b/all_results.json
new file mode 100644
index 0000000..578f51d
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,16 @@
+{
+    "epoch": 63.0,
+    "eval_cer": 0.026103252866895722,
+    "eval_loss": 0.1349739283323288,
+    "eval_runtime": 19.6884,
+    "eval_samples": 341,
+    "eval_samples_per_second": 17.32,
+    "eval_steps_per_second": 2.184,
+    "eval_wer": 0.08414547183265986,
+    "total_flos": 4.528287283105284e+19,
+    "train_loss": 0.5869265782432654,
+    "train_runtime": 15592.601,
+    "train_samples": 2743,
+    "train_samples_per_second": 17.592,
+    "train_steps_per_second": 0.552
+}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..11a8c75
--- /dev/null
+++ b/config.json
@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "Edresson/wav2vec2-large-xlsr-coraa-portuguese",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.1,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 37,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 40,
+  "xvector_output_dim": 512
+}
diff --git a/eval_results.json b/eval_results.json
new file mode 100644
index 0000000..5f67152
--- /dev/null
+++ b/eval_results.json
@@ -0,0 +1,10 @@
+{
+    "epoch": 63.0,
+    "eval_cer": 0.026103252866895722,
+    "eval_loss": 0.1349739283323288,
+    "eval_runtime": 19.6884,
+    "eval_samples": 341,
+    "eval_samples_per_second": 17.32,
+    "eval_steps_per_second": 2.184,
+    "eval_wer": 0.08414547183265986
+}
\ No newline at end of file
diff --git a/preprocessor_config.json b/preprocessor_config.json
new file mode 100644
index 0000000..67dee51
--- /dev/null
+++ b/preprocessor_config.json
@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}
diff --git a/pytorch_model.bin b/pytorch_model.bin
new file mode 100644
index 0000000..e2bc7a9
--- /dev/null
+++ b/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd59575bfc6ca53907a672f0103555f624e070ff1d9760045d09dee55d1b4fd5
+size 1262066282
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..5dd6921
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..92ac3ab
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}
diff --git a/train_results.json b/train_results.json
new file mode 100644
index 0000000..aef1d07
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,9 @@
+{
+    "epoch": 63.0,
+    "total_flos": 4.528287283105284e+19,
+    "train_loss": 0.5869265782432654,
+    "train_runtime": 15592.601,
+    "train_samples": 2743,
+    "train_samples_per_second": 17.592,
+    "train_steps_per_second": 0.552
+}
\ No newline at end of file
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..7948a26
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,985 @@
+{
+  "best_metric": 0.1349739283323288,
+  "best_model_checkpoint": "wav2vec2-large-xlsr-mecita-coraa-portuguese-2-all-03/checkpoint-3698",
+  "epoch": 63.0,
+  "global_step": 5418,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 3e-05,
+      "loss": 28.65,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_cer": 1.0,
+      "eval_loss": 3.1940298080444336,
+      "eval_runtime": 19.0983,
+      "eval_samples_per_second": 17.855,
+      "eval_steps_per_second": 2.252,
+      "eval_wer": 1.0,
+      "step": 86
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.966511627906977e-05,
+      "loss": 8.1771,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_cer": 1.0,
+      "eval_loss": 2.9853453636169434,
+      "eval_runtime": 18.8941,
+      "eval_samples_per_second": 18.048,
+      "eval_steps_per_second": 2.276,
+      "eval_wer": 1.0,
+      "step": 172
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.9316279069767443e-05,
+      "loss": 3.0358,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "eval_cer": 1.0,
+      "eval_loss": 2.895540237426758,
+      "eval_runtime": 19.0821,
+      "eval_samples_per_second": 17.87,
+      "eval_steps_per_second": 2.253,
+      "eval_wer": 1.0,
+      "step": 258
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 2.8967441860465116e-05,
+      "loss": 2.9359,
+      "step": 300
+    },
+    {
+      "epoch": 4.0,
+      "eval_cer": 1.0,
+      "eval_loss": 2.9086179733276367,
+      "eval_runtime": 19.1659,
+      "eval_samples_per_second": 17.792,
+      "eval_steps_per_second": 2.244,
+      "eval_wer": 1.0,
+      "step": 344
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 2.861860465116279e-05,
+      "loss": 2.9026,
+      "step": 400
+    },
+    {
+      "epoch": 5.0,
+      "eval_cer": 0.9998215162197135,
+      "eval_loss": 2.694617509841919,
+      "eval_runtime": 18.8982,
+      "eval_samples_per_second": 18.044,
+      "eval_steps_per_second": 2.275,
+      "eval_wer": 0.9997623009270263,
+      "step": 430
+    },
+    {
+      "epoch": 5.81,
+      "learning_rate": 2.8269767441860464e-05,
+      "loss": 2.4934,
+      "step": 500
+    },
+    {
+      "epoch": 6.0,
+      "eval_cer": 0.1256525813216724,
+      "eval_loss": 0.9106346964836121,
+      "eval_runtime": 18.9322,
+      "eval_samples_per_second": 18.012,
+      "eval_steps_per_second": 2.271,
+      "eval_wer": 0.49441407178512004,
+      "step": 516
+    },
+    {
+      "epoch": 6.98,
+      "learning_rate": 2.7920930232558138e-05,
+      "loss": 1.1576,
+      "step": 600
+    },
+    {
+      "epoch": 7.0,
+      "eval_cer": 0.06273704877069296,
+      "eval_loss": 0.4618076980113983,
+      "eval_runtime": 19.1545,
+      "eval_samples_per_second": 17.803,
+      "eval_steps_per_second": 2.245,
+      "eval_wer": 0.22914190634656526,
+      "step": 602
+    },
+    {
+      "epoch": 8.0,
+      "eval_cer": 0.05381285975636964,
+      "eval_loss": 0.3426876664161682,
+      "eval_runtime": 19.3029,
+      "eval_samples_per_second": 17.666,
+      "eval_steps_per_second": 2.228,
+      "eval_wer": 0.18706917043023533,
+      "step": 688
+    },
+    {
+      "epoch": 8.14,
+      "learning_rate": 2.7572093023255812e-05,
+      "loss": 0.7498,
+      "step": 700
+    },
+    {
+      "epoch": 9.0,
+      "eval_cer": 0.04801213689705948,
+      "eval_loss": 0.283805251121521,
+      "eval_runtime": 18.9222,
+      "eval_samples_per_second": 18.021,
+      "eval_steps_per_second": 2.272,
+      "eval_wer": 0.16734014737342523,
+      "step": 774
+    },
+    {
+      "epoch": 9.3,
+      "learning_rate": 2.722325581395349e-05,
+      "loss": 0.5493,
+      "step": 800
+    },
+    {
+      "epoch": 10.0,
+      "eval_cer": 0.04417473562090045,
+      "eval_loss": 0.25037863850593567,
+      "eval_runtime": 19.1667,
+      "eval_samples_per_second": 17.791,
+      "eval_steps_per_second": 2.243,
+      "eval_wer": 0.14903731875445686,
+      "step": 860
+    },
+    {
+      "epoch": 10.47,
+      "learning_rate": 2.6874418604651163e-05,
+      "loss": 0.4735,
+      "step": 900
+    },
+    {
+      "epoch": 11.0,
+      "eval_cer": 0.041185132301102136,
+      "eval_loss": 0.23181051015853882,
+      "eval_runtime": 18.9289,
+      "eval_samples_per_second": 18.015,
+      "eval_steps_per_second": 2.272,
+      "eval_wer": 0.1388162586165914,
+      "step": 946
+    },
+    {
+      "epoch": 11.63,
+      "learning_rate": 2.6525581395348837e-05,
+      "loss": 0.4183,
+      "step": 1000
+    },
+    {
+      "epoch": 12.0,
+      "eval_cer": 0.037392351970014726,
+      "eval_loss": 0.2174120843410492,
+      "eval_runtime": 18.9003,
+      "eval_samples_per_second": 18.042,
+      "eval_steps_per_second": 2.275,
+      "eval_wer": 0.12146422628951747,
+      "step": 1032
+    },
+    {
+      "epoch": 12.79,
+      "learning_rate": 2.617674418604651e-05,
+      "loss": 0.3924,
+      "step": 1100
+    },
+    {
+      "epoch": 13.0,
+      "eval_cer": 0.03565213511222168,
+      "eval_loss": 0.20193208754062653,
+      "eval_runtime": 19.1675,
+      "eval_samples_per_second": 17.791,
+      "eval_steps_per_second": 2.243,
+      "eval_wer": 0.1126693605894937,
+      "step": 1118
+    },
+    {
+      "epoch": 13.95,
+      "learning_rate": 2.5827906976744185e-05,
+      "loss": 0.3497,
+      "step": 1200
+    },
+    {
+      "epoch": 14.0,
+      "eval_cer": 0.03431350676007318,
+      "eval_loss": 0.18761980533599854,
+      "eval_runtime": 19.269,
+      "eval_samples_per_second": 17.697,
+      "eval_steps_per_second": 2.232,
+      "eval_wer": 0.11124316615165201,
+      "step": 1204
+    },
+    {
+      "epoch": 15.0,
+      "eval_cer": 0.03507206282629066,
+      "eval_loss": 0.18645305931568146,
+      "eval_runtime": 18.9659,
+      "eval_samples_per_second": 17.98,
+      "eval_steps_per_second": 2.267,
+      "eval_wer": 0.1110054670786784,
+      "step": 1290
+    },
+    {
+      "epoch": 15.12,
+      "learning_rate": 2.5479069767441862e-05,
+      "loss": 0.3335,
+      "step": 1300
+    },
+    {
+      "epoch": 16.0,
+      "eval_cer": 0.0327517736825666,
+      "eval_loss": 0.17586949467658997,
+      "eval_runtime": 19.1261,
+      "eval_samples_per_second": 17.829,
+      "eval_steps_per_second": 2.248,
+      "eval_wer": 0.1064891846921797,
+      "step": 1376
+    },
+    {
+      "epoch": 16.28,
+      "learning_rate": 2.5130232558139536e-05,
+      "loss": 0.3259,
+      "step": 1400
+    },
+    {
+      "epoch": 17.0,
+      "eval_cer": 0.031011556824773547,
+      "eval_loss": 0.17175641655921936,
+      "eval_runtime": 18.8952,
+      "eval_samples_per_second": 18.047,
+      "eval_steps_per_second": 2.276,
+      "eval_wer": 0.0941288328975517,
+      "step": 1462
+    },
+    {
+      "epoch": 17.44,
+      "learning_rate": 2.478139534883721e-05,
+      "loss": 0.2822,
+      "step": 1500
+    },
+    {
+      "epoch": 18.0,
+      "eval_cer": 0.03074383115434385,
+      "eval_loss": 0.1663752645254135,
+      "eval_runtime": 19.0306,
+      "eval_samples_per_second": 17.919,
+      "eval_steps_per_second": 2.26,
+      "eval_wer": 0.09650582362728785,
+      "step": 1548
+    },
+    {
+      "epoch": 18.6,
+      "learning_rate": 2.4432558139534884e-05,
+      "loss": 0.2689,
+      "step": 1600
+    },
+    {
+      "epoch": 19.0,
+      "eval_cer": 0.030163758868412834,
+      "eval_loss": 0.16375425457954407,
+      "eval_runtime": 19.1028,
+      "eval_samples_per_second": 17.851,
+      "eval_steps_per_second": 2.251,
+      "eval_wer": 0.09507962918944617,
+      "step": 1634
+    },
+    {
+      "epoch": 19.77,
+      "learning_rate": 2.4083720930232558e-05,
+      "loss": 0.262,
+      "step": 1700
+    },
+    {
+      "epoch": 20.0,
+      "eval_cer": 0.030699210209272233,
+      "eval_loss": 0.1615932136774063,
+      "eval_runtime": 18.925,
+      "eval_samples_per_second": 18.019,
+      "eval_steps_per_second": 2.272,
+      "eval_wer": 0.09365343475160447,
+      "step": 1720
+    },
+    {
+      "epoch": 20.93,
+      "learning_rate": 2.373488372093023e-05,
+      "loss": 0.2623,
+      "step": 1800
+    },
+    {
+      "epoch": 21.0,
+      "eval_cer": 0.029896033197983132,
+      "eval_loss": 0.1573890894651413,
+      "eval_runtime": 18.8701,
+      "eval_samples_per_second": 18.071,
+      "eval_steps_per_second": 2.279,
+      "eval_wer": 0.09270263845971001,
+      "step": 1806
+    },
+    {
+      "epoch": 22.0,
+      "eval_cer": 0.030565347374057382,
+      "eval_loss": 0.15589450299739838,
+      "eval_runtime": 19.0532,
+      "eval_samples_per_second": 17.897,
+      "eval_steps_per_second": 2.257,
+      "eval_wer": 0.09436653197052532,
+      "step": 1892
+    },
+    {
+      "epoch": 22.09,
+      "learning_rate": 2.338604651162791e-05,
+      "loss": 0.2344,
+      "step": 1900
+    },
+    {
+      "epoch": 23.0,
+      "eval_cer": 0.029315960912052116,
+      "eval_loss": 0.15381626784801483,
+      "eval_runtime": 19.0478,
+      "eval_samples_per_second": 17.902,
+      "eval_steps_per_second": 2.257,
+      "eval_wer": 0.09198954124078916,
+      "step": 1978
+    },
+    {
+      "epoch": 23.26,
+      "learning_rate": 2.3037209302325583e-05,
+      "loss": 0.2315,
+      "step": 2000
+    },
+    {
+      "epoch": 24.0,
+      "eval_cer": 0.0298067913078399,
+      "eval_loss": 0.1532616764307022,
+      "eval_runtime": 19.3337,
+      "eval_samples_per_second": 17.638,
+      "eval_steps_per_second": 2.224,
+      "eval_wer": 0.09270263845971001,
+      "step": 2064
+    },
+    {
+      "epoch": 24.42,
+      "learning_rate": 2.2688372093023257e-05,
+      "loss": 0.2411,
+      "step": 2100
+    },
+    {
+      "epoch": 25.0,
+      "eval_cer": 0.029360581857123733,
+      "eval_loss": 0.15203775465488434,
+      "eval_runtime": 18.8831,
+      "eval_samples_per_second": 18.058,
+      "eval_steps_per_second": 2.277,
+      "eval_wer": 0.09080104587592108,
+      "step": 2150
+    },
+    {
+      "epoch": 25.58,
+      "learning_rate": 2.233953488372093e-05,
+      "loss": 0.2102,
+      "step": 2200
+    },
+    {
+      "epoch": 26.0,
+      "eval_cer": 0.02971754941769667,
+      "eval_loss": 0.14963804185390472,
+      "eval_runtime": 18.9765,
+      "eval_samples_per_second": 17.97,
+      "eval_steps_per_second": 2.266,
+      "eval_wer": 0.09222724031376278,
+      "step": 2236
+    },
+    {
+      "epoch": 26.74,
+      "learning_rate": 2.1990697674418605e-05,
+      "loss": 0.2115,
+      "step": 2300
+    },
+    {
+      "epoch": 27.0,
+      "eval_cer": 0.029762170362768285,
+      "eval_loss": 0.1473499834537506,
+      "eval_runtime": 18.9863,
+      "eval_samples_per_second": 17.96,
+      "eval_steps_per_second": 2.265,
+      "eval_wer": 0.09793201806512955,
+      "step": 2322
+    },
+    {
+      "epoch": 27.91,
+      "learning_rate": 2.1641860465116282e-05,
+      "loss": 0.2139,
+      "step": 2400
+    },
+    {
+      "epoch": 28.0,
+      "eval_cer": 0.029985275088126366,
+      "eval_loss": 0.14958611130714417,
+      "eval_runtime": 18.9624,
+      "eval_samples_per_second": 17.983,
+      "eval_steps_per_second": 2.268,
+      "eval_wer": 0.095792726408367,
+      "step": 2408
+    },
+    {
+      "epoch": 29.0,
+      "eval_cer": 0.02886975146133595,
+      "eval_loss": 0.14455682039260864,
+      "eval_runtime": 19.1059,
+      "eval_samples_per_second": 17.848,
+      "eval_steps_per_second": 2.251,
+      "eval_wer": 0.09032564772997385,
+      "step": 2494
+    },
+    {
+      "epoch": 29.07,
+      "learning_rate": 2.1293023255813956e-05,
+      "loss": 0.2218,
+      "step": 2500
+    },
+    {
+      "epoch": 30.0,
+      "eval_cer": 0.029137477131765652,
+      "eval_loss": 0.1481563001871109,
+      "eval_runtime": 19.0476,
+      "eval_samples_per_second": 17.903,
+      "eval_steps_per_second": 2.258,
+      "eval_wer": 0.09127644402186831,
+      "step": 2580
+    },
+    {
+      "epoch": 30.23,
+      "learning_rate": 2.094418604651163e-05,
+      "loss": 0.1982,
+      "step": 2600
+    },
+    {
+      "epoch": 31.0,
+      "eval_cer": 0.02837892106554817,
+      "eval_loss": 0.14385315775871277,
+      "eval_runtime": 18.9549,
+      "eval_samples_per_second": 17.99,
+      "eval_steps_per_second": 2.269,
+      "eval_wer": 0.08913715236510578,
+      "step": 2666
+    },
+    {
+      "epoch": 31.4,
+      "learning_rate": 2.0595348837209304e-05,
+      "loss": 0.196,
+      "step": 2700
+    },
+    {
+      "epoch": 32.0,
+      "eval_cer": 0.02860202579090625,
+      "eval_loss": 0.14276552200317383,
+      "eval_runtime": 19.1086,
+      "eval_samples_per_second": 17.845,
+      "eval_steps_per_second": 2.25,
+      "eval_wer": 0.09341573567863086,
+      "step": 2752
+    },
+    {
+      "epoch": 32.56,
+      "learning_rate": 2.0246511627906977e-05,
+      "loss": 0.1846,
+      "step": 2800
+    },
+    {
+      "epoch": 33.0,
+      "eval_cer": 0.028111195395118468,
+      "eval_loss": 0.14039289951324463,
+      "eval_runtime": 19.1208,
+      "eval_samples_per_second": 17.834,
+      "eval_steps_per_second": 2.249,
+      "eval_wer": 0.09056334680294748,
+      "step": 2838
+    },
+    {
+      "epoch": 33.72,
+      "learning_rate": 1.9897674418604655e-05,
+      "loss": 0.1873,
+      "step": 2900
+    },
+    {
+      "epoch": 34.0,
+      "eval_cer": 0.02717415554861452,
+      "eval_loss": 0.1395137906074524,
+      "eval_runtime": 19.1432,
+      "eval_samples_per_second": 17.813,
+      "eval_steps_per_second": 2.246,
+      "eval_wer": 0.08557166627050154,
+      "step": 2924
+    },
+    {
+      "epoch": 34.88,
+      "learning_rate": 1.954883720930233e-05,
+      "loss": 0.1854,
+      "step": 3000
+    },
+    {
+      "epoch": 35.0,
+      "eval_cer": 0.02677256704296997,
+      "eval_loss": 0.1353740692138672,
+      "eval_runtime": 19.2143,
+      "eval_samples_per_second": 17.747,
+      "eval_steps_per_second": 2.238,
+      "eval_wer": 0.08462086997860709,
+      "step": 3010
+    },
+    {
+      "epoch": 36.0,
+      "eval_cer": 0.027129534603542903,
+      "eval_loss": 0.1359284222126007,
+      "eval_runtime": 19.183,
+      "eval_samples_per_second": 17.776,
+      "eval_steps_per_second": 2.242,
+      "eval_wer": 0.08580936534347516,
+      "step": 3096
+    },
+    {
+      "epoch": 36.05,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.1851,
+      "step": 3100
+    },
+    {
+      "epoch": 37.0,
+      "eval_cer": 0.027620364999330686,
+      "eval_loss": 0.13563700020313263,
+      "eval_runtime": 19.0319,
+      "eval_samples_per_second": 17.917,
+      "eval_steps_per_second": 2.259,
+      "eval_wer": 0.09032564772997385,
+      "step": 3182
+    },
+    {
+      "epoch": 37.21,
+      "learning_rate": 1.8851162790697673e-05,
+      "loss": 0.1733,
+      "step": 3200
+    },
+    {
+      "epoch": 38.0,
+      "eval_cer": 0.02704029271339967,
+      "eval_loss": 0.13802382349967957,
+      "eval_runtime": 19.2183,
+      "eval_samples_per_second": 17.744,
+      "eval_steps_per_second": 2.237,
+      "eval_wer": 0.08509626812455431,
+      "step": 3268
+    },
+    {
+      "epoch": 38.37,
+      "learning_rate": 1.8502325581395347e-05,
+      "loss": 0.1781,
+      "step": 3300
+    },
+    {
+      "epoch": 39.0,
+      "eval_cer": 0.02583552719646602,
+      "eval_loss": 0.13587680459022522,
+      "eval_runtime": 19.0209,
+      "eval_samples_per_second": 17.928,
+      "eval_steps_per_second": 2.261,
+      "eval_wer": 0.08129308295697647,
+      "step": 3354
+    },
+    {
+      "epoch": 39.53,
+      "learning_rate": 1.815348837209302e-05,
+      "loss": 0.1821,
+      "step": 3400
+    },
+    {
+      "epoch": 40.0,
+      "eval_cer": 0.027441881219044218,
+      "eval_loss": 0.13828882575035095,
+      "eval_runtime": 19.1283,
+      "eval_samples_per_second": 17.827,
+      "eval_steps_per_second": 2.248,
+      "eval_wer": 0.08628476348942239,
+      "step": 3440
+    },
+    {
+      "epoch": 40.7,
+      "learning_rate": 1.7804651162790698e-05,
+      "loss": 0.1724,
+      "step": 3500
+    },
+    {
+      "epoch": 41.0,
+      "eval_cer": 0.02650484137254027,
+      "eval_loss": 0.13766087591648102,
+      "eval_runtime": 19.2872,
+      "eval_samples_per_second": 17.68,
+      "eval_steps_per_second": 2.229,
+      "eval_wer": 0.08224387924887093,
+      "step": 3526
+    },
+    {
+      "epoch": 41.86,
+      "learning_rate": 1.7455813953488372e-05,
+      "loss": 0.1591,
+      "step": 3600
+    },
+    {
+      "epoch": 42.0,
+      "eval_cer": 0.026594083262683504,
+      "eval_loss": 0.13794943690299988,
+      "eval_runtime": 19.0157,
+      "eval_samples_per_second": 17.933,
+      "eval_steps_per_second": 2.261,
+      "eval_wer": 0.08438317090563346,
+      "step": 3612
+    },
+    {
+      "epoch": 43.0,
+      "eval_cer": 0.026103252866895722,
+      "eval_loss": 0.1349739283323288,
+      "eval_runtime": 18.9996,
+      "eval_samples_per_second": 17.948,
+      "eval_steps_per_second": 2.263,
+      "eval_wer": 0.08414547183265986,
+      "step": 3698
+    },
+    {
+      "epoch": 43.02,
+      "learning_rate": 1.7106976744186046e-05,
+      "loss": 0.168,
+      "step": 3700
+    },
+    {
+      "epoch": 44.0,
+      "eval_cer": 0.02650484137254027,
+      "eval_loss": 0.1362057477235794,
+      "eval_runtime": 19.2987,
+      "eval_samples_per_second": 17.67,
+      "eval_steps_per_second": 2.228,
+      "eval_wer": 0.08462086997860709,
+      "step": 3784
+    },
+    {
+      "epoch": 44.19,
+      "learning_rate": 1.675813953488372e-05,
+      "loss": 0.162,
+      "step": 3800
+    },
+    {
+      "epoch": 45.0,
+      "eval_cer": 0.02663870420775512,
+      "eval_loss": 0.13529056310653687,
+      "eval_runtime": 19.8929,
+      "eval_samples_per_second": 17.142,
+      "eval_steps_per_second": 2.162,
+      "eval_wer": 0.08200618017589731,
+      "step": 3870
+    },
+    {
+      "epoch": 45.35,
+      "learning_rate": 1.6409302325581394e-05,
+      "loss": 0.145,
+      "step": 3900
+    },
+    {
+      "epoch": 46.0,
+      "eval_cer": 0.026995671768328053,
+      "eval_loss": 0.14138084650039673,
+      "eval_runtime": 19.2935,
+      "eval_samples_per_second": 17.674,
+      "eval_steps_per_second": 2.229,
+      "eval_wer": 0.08485856905158069,
+      "step": 3956
+    },
+    {
+      "epoch": 46.51,
+      "learning_rate": 1.606046511627907e-05,
+      "loss": 0.1639,
+      "step": 4000
+    },
+    {
+      "epoch": 47.0,
+      "eval_cer": 0.026594083262683504,
+      "eval_loss": 0.13999956846237183,
+      "eval_runtime": 19.0568,
+      "eval_samples_per_second": 17.894,
+      "eval_steps_per_second": 2.256,
+      "eval_wer": 0.08367007368671261,
+      "step": 4042
+    },
+    {
+      "epoch": 47.67,
+      "learning_rate": 1.5711627906976745e-05,
+      "loss": 0.1572,
+      "step": 4100
+    },
+    {
+      "epoch": 48.0,
+      "eval_cer": 0.026058631921824105,
+      "eval_loss": 0.1387248933315277,
+      "eval_runtime": 19.0666,
+      "eval_samples_per_second": 17.885,
+      "eval_steps_per_second": 2.255,
+      "eval_wer": 0.08153078202995008,
+      "step": 4128
+    },
+    {
+      "epoch": 48.84,
+      "learning_rate": 1.536279069767442e-05,
+      "loss": 0.14,
+      "step": 4200
+    },
+    {
+      "epoch": 49.0,
+      "eval_cer": 0.02583552719646602,
+      "eval_loss": 0.1383592039346695,
+      "eval_runtime": 19.025,
+      "eval_samples_per_second": 17.924,
+      "eval_steps_per_second": 2.26,
+      "eval_wer": 0.08224387924887093,
+      "step": 4214
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 1.5013953488372093e-05,
+      "loss": 0.1473,
+      "step": 4300
+    },
+    {
+      "epoch": 50.0,
+      "eval_cer": 0.026549462317611888,
+      "eval_loss": 0.13988161087036133,
+      "eval_runtime": 19.1678,
+      "eval_samples_per_second": 17.79,
+      "eval_steps_per_second": 2.243,
+      "eval_wer": 0.08271927739481816,
+      "step": 4300
+    },
+    {
+      "epoch": 51.0,
+      "eval_cer": 0.02650484137254027,
+      "eval_loss": 0.14077438414096832,
+      "eval_runtime": 19.0777,
+      "eval_samples_per_second": 17.874,
+      "eval_steps_per_second": 2.254,
+      "eval_wer": 0.08224387924887093,
+      "step": 4386
+    },
+    {
+      "epoch": 51.16,
+      "learning_rate": 1.4665116279069768e-05,
+      "loss": 0.1722,
+      "step": 4400
+    },
+    {
+      "epoch": 52.0,
+      "eval_cer": 0.026683325152826738,
+      "eval_loss": 0.1410902589559555,
+      "eval_runtime": 19.0905,
+      "eval_samples_per_second": 17.862,
+      "eval_steps_per_second": 2.252,
+      "eval_wer": 0.08509626812455431,
+      "step": 4472
+    },
+    {
+      "epoch": 52.33,
+      "learning_rate": 1.4316279069767442e-05,
+      "loss": 0.1518,
+      "step": 4500
+    },
+    {
+      "epoch": 53.0,
+      "eval_cer": 0.02730801838382937,
+      "eval_loss": 0.14102402329444885,
+      "eval_runtime": 19.0143,
+      "eval_samples_per_second": 17.934,
+      "eval_steps_per_second": 2.261,
+      "eval_wer": 0.08604706441644877,
+      "step": 4558
+    },
+    {
+      "epoch": 53.49,
+      "learning_rate": 1.3967441860465116e-05,
+      "loss": 0.1506,
+      "step": 4600
+    },
+    {
+      "epoch": 54.0,
+      "eval_cer": 0.02704029271339967,
+      "eval_loss": 0.14034318923950195,
+      "eval_runtime": 19.0734,
+      "eval_samples_per_second": 17.878,
+      "eval_steps_per_second": 2.254,
+      "eval_wer": 0.08580936534347516,
+      "step": 4644
+    },
+    {
+      "epoch": 54.65,
+      "learning_rate": 1.3618604651162792e-05,
+      "loss": 0.1442,
+      "step": 4700
+    },
+    {
+      "epoch": 55.0,
+      "eval_cer": 0.02623711570211057,
+      "eval_loss": 0.1380011886358261,
+      "eval_runtime": 19.092,
+      "eval_samples_per_second": 17.861,
+      "eval_steps_per_second": 2.252,
+      "eval_wer": 0.08319467554076539,
+      "step": 4730
+    },
+    {
+      "epoch": 55.81,
+      "learning_rate": 1.3269767441860466e-05,
+      "loss": 0.1427,
+      "step": 4800
+    },
+    {
+      "epoch": 56.0,
+      "eval_cer": 0.026549462317611888,
+      "eval_loss": 0.13952679932117462,
+      "eval_runtime": 19.0512,
+      "eval_samples_per_second": 17.899,
+      "eval_steps_per_second": 2.257,
+      "eval_wer": 0.08153078202995008,
+      "step": 4816
+    },
+    {
+      "epoch": 56.98,
+      "learning_rate": 1.292093023255814e-05,
+      "loss": 0.132,
+      "step": 4900
+    },
+    {
+      "epoch": 57.0,
+      "eval_cer": 0.025924769086609255,
+      "eval_loss": 0.13835428655147552,
+      "eval_runtime": 19.1303,
+      "eval_samples_per_second": 17.825,
+      "eval_steps_per_second": 2.248,
+      "eval_wer": 0.08129308295697647,
+      "step": 4902
+    },
+    {
+      "epoch": 58.0,
+      "eval_cer": 0.026058631921824105,
+      "eval_loss": 0.1352924406528473,
+      "eval_runtime": 19.3096,
+      "eval_samples_per_second": 17.66,
+      "eval_steps_per_second": 2.227,
+      "eval_wer": 0.0817684811029237,
+      "step": 4988
+    },
+    {
+      "epoch": 58.14,
+      "learning_rate": 1.2572093023255815e-05,
+      "loss": 0.1374,
+      "step": 5000
+    },
+    {
+      "epoch": 59.0,
+      "eval_cer": 0.02650484137254027,
+      "eval_loss": 0.140494242310524,
+      "eval_runtime": 19.0811,
+      "eval_samples_per_second": 17.871,
+      "eval_steps_per_second": 2.254,
+      "eval_wer": 0.08343237461373901,
+      "step": 5074
+    },
+    {
+      "epoch": 59.3,
+      "learning_rate": 1.2223255813953489e-05,
+      "loss": 0.1318,
+      "step": 5100
+    },
+    {
+      "epoch": 60.0,
+      "eval_cer": 0.02583552719646602,
+      "eval_loss": 0.1383277028799057,
+      "eval_runtime": 19.2077,
+      "eval_samples_per_second": 17.753,
+      "eval_steps_per_second": 2.239,
+      "eval_wer": 0.08105538388400285,
+      "step": 5160
+    },
+    {
+      "epoch": 60.47,
+      "learning_rate": 1.1874418604651165e-05,
+      "loss": 0.1339,
+      "step": 5200
+    },
+    {
+      "epoch": 61.0,
+      "eval_cer": 0.026058631921824105,
+      "eval_loss": 0.1385628879070282,
+      "eval_runtime": 19.3076,
+      "eval_samples_per_second": 17.661,
+      "eval_steps_per_second": 2.227,
+      "eval_wer": 0.08129308295697647,
+      "step": 5246
+    },
+    {
+      "epoch": 61.63,
+      "learning_rate": 1.1525581395348838e-05,
+      "loss": 0.1346,
+      "step": 5300
+    },
+    {
+      "epoch": 62.0,
+      "eval_cer": 0.025255454910535005,
+      "eval_loss": 0.13994893431663513,
+      "eval_runtime": 19.1977,
+      "eval_samples_per_second": 17.763,
+      "eval_steps_per_second": 2.24,
+      "eval_wer": 0.0801045875921084,
+      "step": 5332
+    },
+    {
+      "epoch": 62.79,
+      "learning_rate": 1.117674418604651e-05,
+      "loss": 0.1261,
+      "step": 5400
+    },
+    {
+      "epoch": 63.0,
+      "eval_cer": 0.026326357592253803,
+      "eval_loss": 0.14302104711532593,
+      "eval_runtime": 19.1245,
+      "eval_samples_per_second": 17.831,
+      "eval_steps_per_second": 2.248,
+      "eval_wer": 0.08319467554076539,
+      "step": 5418
+    },
+    {
+      "epoch": 63.0,
+      "step": 5418,
+      "total_flos": 4.528287283105284e+19,
+      "train_loss": 0.5869265782432654,
+      "train_runtime": 15592.601,
+      "train_samples_per_second": 17.592,
+      "train_steps_per_second": 0.552
+    }
+  ],
+  "max_steps": 8600,
+  "num_train_epochs": 100,
+  "total_flos": 4.528287283105284e+19,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000..e7252af
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75c59abd06b31b46e227d628454cffd80945cc4970276f6cbd005afdf2cabb7
+size 4088
diff --git a/vocab.json b/vocab.json
new file mode 100644
index 0000000..127f7d9
--- /dev/null
+++ b/vocab.json
@@ -0,0 +1,40 @@
+{
+  "[PAD]": 37,
+  "[UNK]": 36,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "j": 10,
+  "l": 11,
+  "m": 12,
+  "n": 13,
+  "o": 14,
+  "p": 15,
+  "q": 16,
+  "r": 17,
+  "s": 18,
+  "t": 19,
+  "u": 20,
+  "v": 21,
+  "x": 22,
+  "z": 23,
+  "|": 0,
+  "à": 24,
+  "á": 25,
+  "â": 26,
+  "ã": 27,
+  "ç": 28,
+  "é": 29,
+  "ê": 30,
+  "í": 31,
+  "ó": 32,
+  "ô": 33,
+  "õ": 34,
+  "ú": 35
+}