luxembourgish whisper small ft

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,90 @@
+---
+license: apache-2.0
+tags:
+- whisper-event
+- generated_from_trainer
+datasets:
+- google/fleurs
+metrics:
+- wer
+model-index:
+- name: Whisper small Luxembourgish
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: google/fleurs lb_lu
+      type: google/fleurs
+      config: lb_lu
+      split: test
+    metrics:
+    - name: Wer
+      type: wer
+      value: 39.49904580152672
+---
+
+<!-- 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. -->
+
+# Whisper small Luxembourgish
+
+This model is a fine-tuned version of [bofenghuang/whisper-small-cv11-german-punct](https://huggingface.co/bofenghuang/whisper-small-cv11-german-punct) on the google/fleurs lb_lu dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1857
+- Wer: 39.4990
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 5000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.0618        | 38.46  | 500  | 1.0104          | 43.2968 |
+| 0.0055        | 76.92  | 1000 | 1.0684          | 40.1288 |
+| 0.0024        | 115.38 | 1500 | 1.1056          | 40.9447 |
+| 0.0014        | 153.85 | 2000 | 1.1280          | 39.7615 |
+| 0.0013        | 192.31 | 2500 | 1.1415          | 39.9857 |
+| 0.0008        | 230.77 | 3000 | 1.1573          | 39.7996 |
+| 0.0006        | 269.23 | 3500 | 1.1682          | 40.0095 |
+| 0.0006        | 307.69 | 4000 | 1.1769          | 39.7233 |
+| 0.0005        | 346.15 | 4500 | 1.1826          | 39.5134 |
+| 0.0004        | 384.62 | 5000 | 1.1857          | 39.4990 |
+
+
+### Framework versions
+
+- Transformers 4.25.1
+- Pytorch 1.13.0+cu117
+- Datasets 2.7.1
+- Tokenizers 0.13.2

added_tokens.json

@@ -0,0 +1,109 @@
+{
+  "<|af|>": 50327,
+  "<|am|>": 50334,
+  "<|ar|>": 50272,
+  "<|as|>": 50350,
+  "<|az|>": 50304,
+  "<|ba|>": 50355,
+  "<|be|>": 50330,
+  "<|bg|>": 50292,
+  "<|bn|>": 50302,
+  "<|bo|>": 50347,
+  "<|br|>": 50309,
+  "<|bs|>": 50315,
+  "<|ca|>": 50270,
+  "<|cs|>": 50283,
+  "<|cy|>": 50297,
+  "<|da|>": 50285,
+  "<|de|>": 50261,
+  "<|el|>": 50281,
+  "<|endoftext|>": 50257,
+  "<|en|>": 50259,
+  "<|es|>": 50262,
+  "<|et|>": 50307,
+  "<|eu|>": 50310,
+  "<|fa|>": 50300,
+  "<|fi|>": 50277,
+  "<|fo|>": 50338,
+  "<|fr|>": 50265,
+  "<|gl|>": 50319,
+  "<|gu|>": 50333,
+  "<|haw|>": 50352,
+  "<|ha|>": 50354,
+  "<|hi|>": 50276,
+  "<|hr|>": 50291,
+  "<|ht|>": 50339,
+  "<|hu|>": 50286,
+  "<|hy|>": 50312,
+  "<|id|>": 50275,
+  "<|is|>": 50311,
+  "<|it|>": 50274,
+  "<|iw|>": 50279,
+  "<|ja|>": 50266,
+  "<|jw|>": 50356,
+  "<|ka|>": 50329,
+  "<|kk|>": 50316,
+  "<|km|>": 50323,
+  "<|kn|>": 50306,
+  "<|ko|>": 50264,
+  "<|la|>": 50294,
+  "<|lb|>": 50345,
+  "<|ln|>": 50353,
+  "<|lo|>": 50336,
+  "<|lt|>": 50293,
+  "<|lv|>": 50301,
+  "<|mg|>": 50349,
+  "<|mi|>": 50295,
+  "<|mk|>": 50308,
+  "<|ml|>": 50296,
+  "<|mn|>": 50314,
+  "<|mr|>": 50320,
+  "<|ms|>": 50282,
+  "<|mt|>": 50343,
+  "<|my|>": 50346,
+  "<|ne|>": 50313,
+  "<|nl|>": 50271,
+  "<|nn|>": 50342,
+  "<|nocaptions|>": 50362,
+  "<|notimestamps|>": 50363,
+  "<|no|>": 50288,
+  "<|oc|>": 50328,
+  "<|pa|>": 50321,
+  "<|pl|>": 50269,
+  "<|ps|>": 50340,
+  "<|pt|>": 50267,
+  "<|ro|>": 50284,
+  "<|ru|>": 50263,
+  "<|sa|>": 50344,
+  "<|sd|>": 50332,
+  "<|si|>": 50322,
+  "<|sk|>": 50298,
+  "<|sl|>": 50305,
+  "<|sn|>": 50324,
+  "<|so|>": 50326,
+  "<|sq|>": 50317,
+  "<|sr|>": 50303,
+  "<|startoflm|>": 50360,
+  "<|startofprev|>": 50361,
+  "<|startoftranscript|>": 50258,
+  "<|su|>": 50357,
+  "<|sv|>": 50273,
+  "<|sw|>": 50318,
+  "<|ta|>": 50287,
+  "<|te|>": 50299,
+  "<|tg|>": 50331,
+  "<|th|>": 50289,
+  "<|tk|>": 50341,
+  "<|tl|>": 50348,
+  "<|transcribe|>": 50359,
+  "<|translate|>": 50358,
+  "<|tr|>": 50268,
+  "<|tt|>": 50351,
+  "<|uk|>": 50280,
+  "<|ur|>": 50290,
+  "<|uz|>": 50337,
+  "<|vi|>": 50278,
+  "<|yi|>": 50335,
+  "<|yo|>": 50325,
+  "<|zh|>": 50260
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 384.62,
+    "eval_loss": 1.1857084035873413,
+    "eval_runtime": 213.8456,
+    "eval_samples_per_second": 4.368,
+    "eval_steps_per_second": 0.07,
+    "eval_wer": 39.49904580152672,
+    "train_loss": 0.1333366625772789,
+    "train_runtime": 10216.7319,
+    "train_samples_per_second": 31.321,
+    "train_steps_per_second": 0.489
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "bofenghuang/whisper-small-cv11-german-punct",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.05,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "use_cache": false,
+  "vocab_size": 51865
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 384.62,
+    "eval_loss": 1.1857084035873413,
+    "eval_runtime": 213.8456,
+    "eval_samples_per_second": 4.368,
+    "eval_steps_per_second": 0.07,
+    "eval_wer": 39.49904580152672
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36ec53bd91df964dcb36a9053ebd4cd31fabda5aa4fc6d29e9980d8f7926d1c6
+size 967102601

special_tokens_map.json

@@ -0,0 +1,133 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|startoftranscript|>",
+    "<|en|>",
+    "<|zh|>",
+    "<|de|>",
+    "<|es|>",
+    "<|ru|>",
+    "<|ko|>",
+    "<|fr|>",
+    "<|ja|>",
+    "<|pt|>",
+    "<|tr|>",
+    "<|pl|>",
+    "<|ca|>",
+    "<|nl|>",
+    "<|ar|>",
+    "<|sv|>",
+    "<|it|>",
+    "<|id|>",
+    "<|hi|>",
+    "<|fi|>",
+    "<|vi|>",
+    "<|iw|>",
+    "<|uk|>",
+    "<|el|>",
+    "<|ms|>",
+    "<|cs|>",
+    "<|ro|>",
+    "<|da|>",
+    "<|hu|>",
+    "<|ta|>",
+    "<|no|>",
+    "<|th|>",
+    "<|ur|>",
+    "<|hr|>",
+    "<|bg|>",
+    "<|lt|>",
+    "<|la|>",
+    "<|mi|>",
+    "<|ml|>",
+    "<|cy|>",
+    "<|sk|>",
+    "<|te|>",
+    "<|fa|>",
+    "<|lv|>",
+    "<|bn|>",
+    "<|sr|>",
+    "<|az|>",
+    "<|sl|>",
+    "<|kn|>",
+    "<|et|>",
+    "<|mk|>",
+    "<|br|>",
+    "<|eu|>",
+    "<|is|>",
+    "<|hy|>",
+    "<|ne|>",
+    "<|mn|>",
+    "<|bs|>",
+    "<|kk|>",
+    "<|sq|>",
+    "<|sw|>",
+    "<|gl|>",
+    "<|mr|>",
+    "<|pa|>",
+    "<|si|>",
+    "<|km|>",
+    "<|sn|>",
+    "<|yo|>",
+    "<|so|>",
+    "<|af|>",
+    "<|oc|>",
+    "<|ka|>",
+    "<|be|>",
+    "<|tg|>",
+    "<|sd|>",
+    "<|gu|>",
+    "<|am|>",
+    "<|yi|>",
+    "<|lo|>",
+    "<|uz|>",
+    "<|fo|>",
+    "<|ht|>",
+    "<|ps|>",
+    "<|tk|>",
+    "<|nn|>",
+    "<|mt|>",
+    "<|sa|>",
+    "<|lb|>",
+    "<|my|>",
+    "<|bo|>",
+    "<|tl|>",
+    "<|mg|>",
+    "<|as|>",
+    "<|tt|>",
+    "<|haw|>",
+    "<|ln|>",
+    "<|ha|>",
+    "<|ba|>",
+    "<|jw|>",
+    "<|su|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nocaptions|>",
+    "<|notimestamps|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,36 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "bofenghuang/whisper-small-cv11-german-punct",
+  "pad_token": null,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "WhisperTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 384.62,
+    "train_loss": 0.1333366625772789,
+    "train_runtime": 10216.7319,
+    "train_samples_per_second": 31.321,
+    "train_steps_per_second": 0.489
+}

trainer_state.json

@@ -0,0 +1,1315 @@
+{
+  "best_metric": 39.49904580152672,
+  "best_model_checkpoint": "./whisper-small-luxembourgish/checkpoint-5000",
+  "epoch": 384.61538461538464,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.92,
+      "learning_rate": 4.6000000000000004e-07,
+      "loss": 4.8461,
+      "step": 25
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 9.600000000000001e-07,
+      "loss": 4.2362,
+      "step": 50
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 1.46e-06,
+      "loss": 3.3754,
+      "step": 75
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 1.9600000000000003e-06,
+      "loss": 2.6567,
+      "step": 100
+    },
+    {
+      "epoch": 9.62,
+      "learning_rate": 2.46e-06,
+      "loss": 2.1373,
+      "step": 125
+    },
+    {
+      "epoch": 11.54,
+      "learning_rate": 2.96e-06,
+      "loss": 1.7558,
+      "step": 150
+    },
+    {
+      "epoch": 13.46,
+      "learning_rate": 3.44e-06,
+      "loss": 1.4408,
+      "step": 175
+    },
+    {
+      "epoch": 15.38,
+      "learning_rate": 3.94e-06,
+      "loss": 1.1918,
+      "step": 200
+    },
+    {
+      "epoch": 17.31,
+      "learning_rate": 4.440000000000001e-06,
+      "loss": 0.9837,
+      "step": 225
+    },
+    {
+      "epoch": 19.23,
+      "learning_rate": 4.94e-06,
+      "loss": 0.8003,
+      "step": 250
+    },
+    {
+      "epoch": 21.15,
+      "learning_rate": 5.4400000000000004e-06,
+      "loss": 0.6536,
+      "step": 275
+    },
+    {
+      "epoch": 23.08,
+      "learning_rate": 5.94e-06,
+      "loss": 0.5275,
+      "step": 300
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 6.440000000000001e-06,
+      "loss": 0.4145,
+      "step": 325
+    },
+    {
+      "epoch": 26.92,
+      "learning_rate": 6.9400000000000005e-06,
+      "loss": 0.3276,
+      "step": 350
+    },
+    {
+      "epoch": 28.85,
+      "learning_rate": 7.440000000000001e-06,
+      "loss": 0.2468,
+      "step": 375
+    },
+    {
+      "epoch": 30.77,
+      "learning_rate": 7.94e-06,
+      "loss": 0.1902,
+      "step": 400
+    },
+    {
+      "epoch": 32.69,
+      "learning_rate": 8.44e-06,
+      "loss": 0.1433,
+      "step": 425
+    },
+    {
+      "epoch": 34.62,
+      "learning_rate": 8.94e-06,
+      "loss": 0.1093,
+      "step": 450
+    },
+    {
+      "epoch": 36.54,
+      "learning_rate": 9.440000000000001e-06,
+      "loss": 0.0794,
+      "step": 475
+    },
+    {
+      "epoch": 38.46,
+      "learning_rate": 9.940000000000001e-06,
+      "loss": 0.0618,
+      "step": 500
+    },
+    {
+      "epoch": 38.46,
+      "eval_loss": 1.0103791952133179,
+      "eval_runtime": 234.5133,
+      "eval_samples_per_second": 3.983,
+      "eval_steps_per_second": 0.064,
+      "eval_wer": 43.29675572519084,
+      "step": 500
+    },
+    {
+      "epoch": 40.38,
+      "learning_rate": 9.951111111111111e-06,
+      "loss": 0.0472,
+      "step": 525
+    },
+    {
+      "epoch": 42.31,
+      "learning_rate": 9.895555555555557e-06,
+      "loss": 0.037,
+      "step": 550
+    },
+    {
+      "epoch": 44.23,
+      "learning_rate": 9.84e-06,
+      "loss": 0.0296,
+      "step": 575
+    },
+    {
+      "epoch": 46.15,
+      "learning_rate": 9.784444444444445e-06,
+      "loss": 0.0232,
+      "step": 600
+    },
+    {
+      "epoch": 48.08,
+      "learning_rate": 9.72888888888889e-06,
+      "loss": 0.02,
+      "step": 625
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 9.673333333333334e-06,
+      "loss": 0.0175,
+      "step": 650
+    },
+    {
+      "epoch": 51.92,
+      "learning_rate": 9.617777777777778e-06,
+      "loss": 0.0147,
+      "step": 675
+    },
+    {
+      "epoch": 53.85,
+      "learning_rate": 9.562222222222223e-06,
+      "loss": 0.0134,
+      "step": 700
+    },
+    {
+      "epoch": 55.77,
+      "learning_rate": 9.506666666666667e-06,
+      "loss": 0.0119,
+      "step": 725
+    },
+    {
+      "epoch": 57.69,
+      "learning_rate": 9.451111111111112e-06,
+      "loss": 0.0105,
+      "step": 750
+    },
+    {
+      "epoch": 59.62,
+      "learning_rate": 9.395555555555556e-06,
+      "loss": 0.0098,
+      "step": 775
+    },
+    {
+      "epoch": 61.54,
+      "learning_rate": 9.340000000000002e-06,
+      "loss": 0.0089,
+      "step": 800
+    },
+    {
+      "epoch": 63.46,
+      "learning_rate": 9.284444444444444e-06,
+      "loss": 0.0084,
+      "step": 825
+    },
+    {
+      "epoch": 65.38,
+      "learning_rate": 9.22888888888889e-06,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 67.31,
+      "learning_rate": 9.173333333333334e-06,
+      "loss": 0.0072,
+      "step": 875
+    },
+    {
+      "epoch": 69.23,
+      "learning_rate": 9.117777777777778e-06,
+      "loss": 0.0065,
+      "step": 900
+    },
+    {
+      "epoch": 71.15,
+      "learning_rate": 9.062222222222224e-06,
+      "loss": 0.0057,
+      "step": 925
+    },
+    {
+      "epoch": 73.08,
+      "learning_rate": 9.006666666666666e-06,
+      "loss": 0.0054,
+      "step": 950
+    },
+    {
+      "epoch": 75.0,
+      "learning_rate": 8.951111111111112e-06,
+      "loss": 0.0054,
+      "step": 975
+    },
+    {
+      "epoch": 76.92,
+      "learning_rate": 8.895555555555556e-06,
+      "loss": 0.0055,
+      "step": 1000
+    },
+    {
+      "epoch": 76.92,
+      "eval_loss": 1.068424105644226,
+      "eval_runtime": 214.8424,
+      "eval_samples_per_second": 4.347,
+      "eval_steps_per_second": 0.07,
+      "eval_wer": 40.12881679389313,
+      "step": 1000
+    },
+    {
+      "epoch": 78.85,
+      "learning_rate": 8.84e-06,
+      "loss": 0.0049,
+      "step": 1025
+    },
+    {
+      "epoch": 80.77,
+      "learning_rate": 8.784444444444446e-06,
+      "loss": 0.0044,
+      "step": 1050
+    },
+    {
+      "epoch": 82.69,
+      "learning_rate": 8.72888888888889e-06,
+      "loss": 0.0041,
+      "step": 1075
+    },
+    {
+      "epoch": 84.62,
+      "learning_rate": 8.673333333333334e-06,
+      "loss": 0.0038,
+      "step": 1100
+    },
+    {
+      "epoch": 86.54,
+      "learning_rate": 8.617777777777778e-06,
+      "loss": 0.0043,
+      "step": 1125
+    },
+    {
+      "epoch": 88.46,
+      "learning_rate": 8.562222222222224e-06,
+      "loss": 0.0042,
+      "step": 1150
+    },
+    {
+      "epoch": 90.38,
+      "learning_rate": 8.506666666666668e-06,
+      "loss": 0.0036,
+      "step": 1175
+    },
+    {
+      "epoch": 92.31,
+      "learning_rate": 8.451111111111112e-06,
+      "loss": 0.0034,
+      "step": 1200
+    },
+    {
+      "epoch": 94.23,
+      "learning_rate": 8.395555555555557e-06,
+      "loss": 0.0037,
+      "step": 1225
+    },
+    {
+      "epoch": 96.15,
+      "learning_rate": 8.34e-06,
+      "loss": 0.0032,
+      "step": 1250
+    },
+    {
+      "epoch": 98.08,
+      "learning_rate": 8.284444444444446e-06,
+      "loss": 0.0028,
+      "step": 1275
+    },
+    {
+      "epoch": 100.0,
+      "learning_rate": 8.22888888888889e-06,
+      "loss": 0.0029,
+      "step": 1300
+    },
+    {
+      "epoch": 101.92,
+      "learning_rate": 8.173333333333334e-06,
+      "loss": 0.0028,
+      "step": 1325
+    },
+    {
+      "epoch": 103.85,
+      "learning_rate": 8.11777777777778e-06,
+      "loss": 0.0028,
+      "step": 1350
+    },
+    {
+      "epoch": 105.77,
+      "learning_rate": 8.062222222222222e-06,
+      "loss": 0.0027,
+      "step": 1375
+    },
+    {
+      "epoch": 107.69,
+      "learning_rate": 8.006666666666667e-06,
+      "loss": 0.003,
+      "step": 1400
+    },
+    {
+      "epoch": 109.62,
+      "learning_rate": 7.951111111111111e-06,
+      "loss": 0.0027,
+      "step": 1425
+    },
+    {
+      "epoch": 111.54,
+      "learning_rate": 7.895555555555557e-06,
+      "loss": 0.0023,
+      "step": 1450
+    },
+    {
+      "epoch": 113.46,
+      "learning_rate": 7.840000000000001e-06,
+      "loss": 0.0023,
+      "step": 1475
+    },
+    {
+      "epoch": 115.38,
+      "learning_rate": 7.784444444444445e-06,
+      "loss": 0.0024,
+      "step": 1500
+    },
+    {
+      "epoch": 115.38,
+      "eval_loss": 1.105582594871521,
+      "eval_runtime": 233.1089,
+      "eval_samples_per_second": 4.007,
+      "eval_steps_per_second": 0.064,
+      "eval_wer": 40.94465648854962,
+      "step": 1500
+    },
+    {
+      "epoch": 117.31,
+      "learning_rate": 7.72888888888889e-06,
+      "loss": 0.0022,
+      "step": 1525
+    },
+    {
+      "epoch": 119.23,
+      "learning_rate": 7.673333333333333e-06,
+      "loss": 0.0021,
+      "step": 1550
+    },
+    {
+      "epoch": 121.15,
+      "learning_rate": 7.617777777777778e-06,
+      "loss": 0.002,
+      "step": 1575
+    },
+    {
+      "epoch": 123.08,
+      "learning_rate": 7.562222222222223e-06,
+      "loss": 0.0021,
+      "step": 1600
+    },
+    {
+      "epoch": 125.0,
+      "learning_rate": 7.506666666666668e-06,
+      "loss": 0.0019,
+      "step": 1625
+    },
+    {
+      "epoch": 126.92,
+      "learning_rate": 7.451111111111111e-06,
+      "loss": 0.0023,
+      "step": 1650
+    },
+    {
+      "epoch": 128.85,
+      "learning_rate": 7.395555555555556e-06,
+      "loss": 0.0016,
+      "step": 1675
+    },
+    {
+      "epoch": 130.77,
+      "learning_rate": 7.340000000000001e-06,
+      "loss": 0.002,
+      "step": 1700
+    },
+    {
+      "epoch": 132.69,
+      "learning_rate": 7.284444444444445e-06,
+      "loss": 0.0024,
+      "step": 1725
+    },
+    {
+      "epoch": 134.62,
+      "learning_rate": 7.22888888888889e-06,
+      "loss": 0.0022,
+      "step": 1750
+    },
+    {
+      "epoch": 136.54,
+      "learning_rate": 7.173333333333335e-06,
+      "loss": 0.0023,
+      "step": 1775
+    },
+    {
+      "epoch": 138.46,
+      "learning_rate": 7.117777777777778e-06,
+      "loss": 0.0019,
+      "step": 1800
+    },
+    {
+      "epoch": 140.38,
+      "learning_rate": 7.062222222222223e-06,
+      "loss": 0.0017,
+      "step": 1825
+    },
+    {
+      "epoch": 142.31,
+      "learning_rate": 7.006666666666667e-06,
+      "loss": 0.0016,
+      "step": 1850
+    },
+    {
+      "epoch": 144.23,
+      "learning_rate": 6.951111111111112e-06,
+      "loss": 0.0015,
+      "step": 1875
+    },
+    {
+      "epoch": 146.15,
+      "learning_rate": 6.8955555555555565e-06,
+      "loss": 0.0015,
+      "step": 1900
+    },
+    {
+      "epoch": 148.08,
+      "learning_rate": 6.8400000000000014e-06,
+      "loss": 0.0015,
+      "step": 1925
+    },
+    {
+      "epoch": 150.0,
+      "learning_rate": 6.784444444444445e-06,
+      "loss": 0.0016,
+      "step": 1950
+    },
+    {
+      "epoch": 151.92,
+      "learning_rate": 6.7288888888888895e-06,
+      "loss": 0.0016,
+      "step": 1975
+    },
+    {
+      "epoch": 153.85,
+      "learning_rate": 6.6733333333333335e-06,
+      "loss": 0.0014,
+      "step": 2000
+    },
+    {
+      "epoch": 153.85,
+      "eval_loss": 1.1279563903808594,
+      "eval_runtime": 214.9694,
+      "eval_samples_per_second": 4.345,
+      "eval_steps_per_second": 0.07,
+      "eval_wer": 39.76145038167939,
+      "step": 2000
+    },
+    {
+      "epoch": 155.77,
+      "learning_rate": 6.617777777777778e-06,
+      "loss": 0.0017,
+      "step": 2025
+    },
+    {
+      "epoch": 157.69,
+      "learning_rate": 6.562222222222223e-06,
+      "loss": 0.0014,
+      "step": 2050
+    },
+    {
+      "epoch": 159.62,
+      "learning_rate": 6.5066666666666665e-06,
+      "loss": 0.0013,
+      "step": 2075
+    },
+    {
+      "epoch": 161.54,
+      "learning_rate": 6.451111111111111e-06,
+      "loss": 0.0015,
+      "step": 2100
+    },
+    {
+      "epoch": 163.46,
+      "learning_rate": 6.395555555555556e-06,
+      "loss": 0.0013,
+      "step": 2125
+    },
+    {
+      "epoch": 165.38,
+      "learning_rate": 6.34e-06,
+      "loss": 0.0013,
+      "step": 2150
+    },
+    {
+      "epoch": 167.31,
+      "learning_rate": 6.284444444444445e-06,
+      "loss": 0.0012,
+      "step": 2175
+    },
+    {
+      "epoch": 169.23,
+      "learning_rate": 6.22888888888889e-06,
+      "loss": 0.0012,
+      "step": 2200
+    },
+    {
+      "epoch": 171.15,
+      "learning_rate": 6.173333333333333e-06,
+      "loss": 0.0011,
+      "step": 2225
+    },
+    {
+      "epoch": 173.08,
+      "learning_rate": 6.117777777777778e-06,
+      "loss": 0.0012,
+      "step": 2250
+    },
+    {
+      "epoch": 175.0,
+      "learning_rate": 6.062222222222223e-06,
+      "loss": 0.0015,
+      "step": 2275
+    },
+    {
+      "epoch": 176.92,
+      "learning_rate": 6.006666666666667e-06,
+      "loss": 0.0012,
+      "step": 2300
+    },
+    {
+      "epoch": 178.85,
+      "learning_rate": 5.951111111111112e-06,
+      "loss": 0.0012,
+      "step": 2325
+    },
+    {
+      "epoch": 180.77,
+      "learning_rate": 5.895555555555557e-06,
+      "loss": 0.0012,
+      "step": 2350
+    },
+    {
+      "epoch": 182.69,
+      "learning_rate": 5.84e-06,
+      "loss": 0.0013,
+      "step": 2375
+    },
+    {
+      "epoch": 184.62,
+      "learning_rate": 5.784444444444445e-06,
+      "loss": 0.0012,
+      "step": 2400
+    },
+    {
+      "epoch": 186.54,
+      "learning_rate": 5.72888888888889e-06,
+      "loss": 0.0013,
+      "step": 2425
+    },
+    {
+      "epoch": 188.46,
+      "learning_rate": 5.673333333333334e-06,
+      "loss": 0.0012,
+      "step": 2450
+    },
+    {
+      "epoch": 190.38,
+      "learning_rate": 5.617777777777779e-06,
+      "loss": 0.001,
+      "step": 2475
+    },
+    {
+      "epoch": 192.31,
+      "learning_rate": 5.562222222222222e-06,
+      "loss": 0.0013,
+      "step": 2500
+    },
+    {
+      "epoch": 192.31,
+      "eval_loss": 1.141483187675476,
+      "eval_runtime": 232.4147,
+      "eval_samples_per_second": 4.019,
+      "eval_steps_per_second": 0.065,
+      "eval_wer": 39.98568702290076,
+      "step": 2500
+    },
+    {
+      "epoch": 194.23,
+      "learning_rate": 5.506666666666667e-06,
+      "loss": 0.001,
+      "step": 2525
+    },
+    {
+      "epoch": 196.15,
+      "learning_rate": 5.451111111111112e-06,
+      "loss": 0.0012,
+      "step": 2550
+    },
+    {
+      "epoch": 198.08,
+      "learning_rate": 5.3955555555555565e-06,
+      "loss": 0.0013,
+      "step": 2575
+    },
+    {
+      "epoch": 200.0,
+      "learning_rate": 5.3400000000000005e-06,
+      "loss": 0.0009,
+      "step": 2600
+    },
+    {
+      "epoch": 201.92,
+      "learning_rate": 5.2844444444444454e-06,
+      "loss": 0.0008,
+      "step": 2625
+    },
+    {
+      "epoch": 203.85,
+      "learning_rate": 5.228888888888889e-06,
+      "loss": 0.001,
+      "step": 2650
+    },
+    {
+      "epoch": 205.77,
+      "learning_rate": 5.1733333333333335e-06,
+      "loss": 0.0009,
+      "step": 2675
+    },
+    {
+      "epoch": 207.69,
+      "learning_rate": 5.117777777777778e-06,
+      "loss": 0.001,
+      "step": 2700
+    },
+    {
+      "epoch": 209.62,
+      "learning_rate": 5.062222222222222e-06,
+      "loss": 0.0011,
+      "step": 2725
+    },
+    {
+      "epoch": 211.54,
+      "learning_rate": 5.006666666666667e-06,
+      "loss": 0.001,
+      "step": 2750
+    },
+    {
+      "epoch": 213.46,
+      "learning_rate": 4.951111111111111e-06,
+      "loss": 0.0011,
+      "step": 2775
+    },
+    {
+      "epoch": 215.38,
+      "learning_rate": 4.895555555555556e-06,
+      "loss": 0.0009,
+      "step": 2800
+    },
+    {
+      "epoch": 217.31,
+      "learning_rate": 4.84e-06,
+      "loss": 0.001,
+      "step": 2825
+    },
+    {
+      "epoch": 219.23,
+      "learning_rate": 4.784444444444445e-06,
+      "loss": 0.0009,
+      "step": 2850
+    },
+    {
+      "epoch": 221.15,
+      "learning_rate": 4.728888888888889e-06,
+      "loss": 0.001,
+      "step": 2875
+    },
+    {
+      "epoch": 223.08,
+      "learning_rate": 4.673333333333333e-06,
+      "loss": 0.001,
+      "step": 2900
+    },
+    {
+      "epoch": 225.0,
+      "learning_rate": 4.617777777777778e-06,
+      "loss": 0.0007,
+      "step": 2925
+    },
+    {
+      "epoch": 226.92,
+      "learning_rate": 4.562222222222222e-06,
+      "loss": 0.0012,
+      "step": 2950
+    },
+    {
+      "epoch": 228.85,
+      "learning_rate": 4.506666666666667e-06,
+      "loss": 0.0008,
+      "step": 2975
+    },
+    {
+      "epoch": 230.77,
+      "learning_rate": 4.451111111111112e-06,
+      "loss": 0.0008,
+      "step": 3000
+    },
+    {
+      "epoch": 230.77,
+      "eval_loss": 1.15729820728302,
+      "eval_runtime": 233.5472,
+      "eval_samples_per_second": 3.999,
+      "eval_steps_per_second": 0.064,
+      "eval_wer": 39.79961832061068,
+      "step": 3000
+    },
+    {
+      "epoch": 232.69,
+      "learning_rate": 4.395555555555556e-06,
+      "loss": 0.0011,
+      "step": 3025
+    },
+    {
+      "epoch": 234.62,
+      "learning_rate": 4.34e-06,
+      "loss": 0.0009,
+      "step": 3050
+    },
+    {
+      "epoch": 236.54,
+      "learning_rate": 4.284444444444445e-06,
+      "loss": 0.0009,
+      "step": 3075
+    },
+    {
+      "epoch": 238.46,
+      "learning_rate": 4.228888888888889e-06,
+      "loss": 0.0007,
+      "step": 3100
+    },
+    {
+      "epoch": 240.38,
+      "learning_rate": 4.173333333333334e-06,
+      "loss": 0.0009,
+      "step": 3125
+    },
+    {
+      "epoch": 242.31,
+      "learning_rate": 4.117777777777779e-06,
+      "loss": 0.0008,
+      "step": 3150
+    },
+    {
+      "epoch": 244.23,
+      "learning_rate": 4.062222222222223e-06,
+      "loss": 0.0007,
+      "step": 3175
+    },
+    {
+      "epoch": 246.15,
+      "learning_rate": 4.006666666666667e-06,
+      "loss": 0.0007,
+      "step": 3200
+    },
+    {
+      "epoch": 248.08,
+      "learning_rate": 3.951111111111112e-06,
+      "loss": 0.0006,
+      "step": 3225
+    },
+    {
+      "epoch": 250.0,
+      "learning_rate": 3.895555555555556e-06,
+      "loss": 0.0007,
+      "step": 3250
+    },
+    {
+      "epoch": 251.92,
+      "learning_rate": 3.8400000000000005e-06,
+      "loss": 0.0009,
+      "step": 3275
+    },
+    {
+      "epoch": 253.85,
+      "learning_rate": 3.784444444444445e-06,
+      "loss": 0.0006,
+      "step": 3300
+    },
+    {
+      "epoch": 255.77,
+      "learning_rate": 3.728888888888889e-06,
+      "loss": 0.0006,
+      "step": 3325
+    },
+    {
+      "epoch": 257.69,
+      "learning_rate": 3.673333333333334e-06,
+      "loss": 0.0008,
+      "step": 3350
+    },
+    {
+      "epoch": 259.62,
+      "learning_rate": 3.617777777777778e-06,
+      "loss": 0.0006,
+      "step": 3375
+    },
+    {
+      "epoch": 261.54,
+      "learning_rate": 3.5622222222222224e-06,
+      "loss": 0.0006,
+      "step": 3400
+    },
+    {
+      "epoch": 263.46,
+      "learning_rate": 3.5066666666666673e-06,
+      "loss": 0.0006,
+      "step": 3425
+    },
+    {
+      "epoch": 265.38,
+      "learning_rate": 3.4511111111111113e-06,
+      "loss": 0.0007,
+      "step": 3450
+    },
+    {
+      "epoch": 267.31,
+      "learning_rate": 3.3955555555555558e-06,
+      "loss": 0.0006,
+      "step": 3475
+    },
+    {
+      "epoch": 269.23,
+      "learning_rate": 3.3400000000000006e-06,
+      "loss": 0.0006,
+      "step": 3500
+    },
+    {
+      "epoch": 269.23,
+      "eval_loss": 1.168186902999878,
+      "eval_runtime": 232.6129,
+      "eval_samples_per_second": 4.015,
+      "eval_steps_per_second": 0.064,
+      "eval_wer": 40.00954198473283,
+      "step": 3500
+    },
+    {
+      "epoch": 271.15,
+      "learning_rate": 3.2844444444444447e-06,
+      "loss": 0.0007,
+      "step": 3525
+    },
+    {
+      "epoch": 273.08,
+      "learning_rate": 3.228888888888889e-06,
+      "loss": 0.0005,
+      "step": 3550
+    },
+    {
+      "epoch": 275.0,
+      "learning_rate": 3.173333333333334e-06,
+      "loss": 0.0005,
+      "step": 3575
+    },
+    {
+      "epoch": 276.92,
+      "learning_rate": 3.117777777777778e-06,
+      "loss": 0.0005,
+      "step": 3600
+    },
+    {
+      "epoch": 278.85,
+      "learning_rate": 3.0622222222222225e-06,
+      "loss": 0.0006,
+      "step": 3625
+    },
+    {
+      "epoch": 280.77,
+      "learning_rate": 3.0066666666666674e-06,
+      "loss": 0.0005,
+      "step": 3650
+    },
+    {
+      "epoch": 282.69,
+      "learning_rate": 2.9511111111111114e-06,
+      "loss": 0.0008,
+      "step": 3675
+    },
+    {
+      "epoch": 284.62,
+      "learning_rate": 2.895555555555556e-06,
+      "loss": 0.0005,
+      "step": 3700
+    },
+    {
+      "epoch": 286.54,
+      "learning_rate": 2.84e-06,
+      "loss": 0.0007,
+      "step": 3725
+    },
+    {
+      "epoch": 288.46,
+      "learning_rate": 2.784444444444445e-06,
+      "loss": 0.0005,
+      "step": 3750
+    },
+    {
+      "epoch": 290.38,
+      "learning_rate": 2.7288888888888893e-06,
+      "loss": 0.0005,
+      "step": 3775
+    },
+    {
+      "epoch": 292.31,
+      "learning_rate": 2.6733333333333333e-06,
+      "loss": 0.0005,
+      "step": 3800
+    },
+    {
+      "epoch": 294.23,
+      "learning_rate": 2.617777777777778e-06,
+      "loss": 0.0006,
+      "step": 3825
+    },
+    {
+      "epoch": 296.15,
+      "learning_rate": 2.5622222222222226e-06,
+      "loss": 0.0005,
+      "step": 3850
+    },
+    {
+      "epoch": 298.08,
+      "learning_rate": 2.5066666666666667e-06,
+      "loss": 0.0005,
+      "step": 3875
+    },
+    {
+      "epoch": 300.0,
+      "learning_rate": 2.451111111111111e-06,
+      "loss": 0.0004,
+      "step": 3900
+    },
+    {
+      "epoch": 301.92,
+      "learning_rate": 2.3955555555555556e-06,
+      "loss": 0.0006,
+      "step": 3925
+    },
+    {
+      "epoch": 303.85,
+      "learning_rate": 2.3400000000000005e-06,
+      "loss": 0.0012,
+      "step": 3950
+    },
+    {
+      "epoch": 305.77,
+      "learning_rate": 2.2844444444444445e-06,
+      "loss": 0.0006,
+      "step": 3975
+    },
+    {
+      "epoch": 307.69,
+      "learning_rate": 2.228888888888889e-06,
+      "loss": 0.0006,
+      "step": 4000
+    },
+    {
+      "epoch": 307.69,
+      "eval_loss": 1.1769174337387085,
+      "eval_runtime": 230.6249,
+      "eval_samples_per_second": 4.05,
+      "eval_steps_per_second": 0.065,
+      "eval_wer": 39.72328244274809,
+      "step": 4000
+    },
+    {
+      "epoch": 309.62,
+      "learning_rate": 2.1733333333333334e-06,
+      "loss": 0.0004,
+      "step": 4025
+    },
+    {
+      "epoch": 311.54,
+      "learning_rate": 2.117777777777778e-06,
+      "loss": 0.0007,
+      "step": 4050
+    },
+    {
+      "epoch": 313.46,
+      "learning_rate": 2.0622222222222223e-06,
+      "loss": 0.0005,
+      "step": 4075
+    },
+    {
+      "epoch": 315.38,
+      "learning_rate": 2.006666666666667e-06,
+      "loss": 0.0005,
+      "step": 4100
+    },
+    {
+      "epoch": 317.31,
+      "learning_rate": 1.9511111111111113e-06,
+      "loss": 0.0008,
+      "step": 4125
+    },
+    {
+      "epoch": 319.23,
+      "learning_rate": 1.8955555555555557e-06,
+      "loss": 0.0006,
+      "step": 4150
+    },
+    {
+      "epoch": 321.15,
+      "learning_rate": 1.8400000000000002e-06,
+      "loss": 0.0005,
+      "step": 4175
+    },
+    {
+      "epoch": 323.08,
+      "learning_rate": 1.7844444444444444e-06,
+      "loss": 0.0006,
+      "step": 4200
+    },
+    {
+      "epoch": 325.0,
+      "learning_rate": 1.728888888888889e-06,
+      "loss": 0.0004,
+      "step": 4225
+    },
+    {
+      "epoch": 326.92,
+      "learning_rate": 1.6733333333333335e-06,
+      "loss": 0.0005,
+      "step": 4250
+    },
+    {
+      "epoch": 328.85,
+      "learning_rate": 1.6177777777777778e-06,
+      "loss": 0.0005,
+      "step": 4275
+    },
+    {
+      "epoch": 330.77,
+      "learning_rate": 1.5622222222222225e-06,
+      "loss": 0.0004,
+      "step": 4300
+    },
+    {
+      "epoch": 332.69,
+      "learning_rate": 1.506666666666667e-06,
+      "loss": 0.0005,
+      "step": 4325
+    },
+    {
+      "epoch": 334.62,
+      "learning_rate": 1.4511111111111112e-06,
+      "loss": 0.0004,
+      "step": 4350
+    },
+    {
+      "epoch": 336.54,
+      "learning_rate": 1.3955555555555556e-06,
+      "loss": 0.0005,
+      "step": 4375
+    },
+    {
+      "epoch": 338.46,
+      "learning_rate": 1.34e-06,
+      "loss": 0.0005,
+      "step": 4400
+    },
+    {
+      "epoch": 340.38,
+      "learning_rate": 1.2844444444444445e-06,
+      "loss": 0.0004,
+      "step": 4425
+    },
+    {
+      "epoch": 342.31,
+      "learning_rate": 1.228888888888889e-06,
+      "loss": 0.0007,
+      "step": 4450
+    },
+    {
+      "epoch": 344.23,
+      "learning_rate": 1.1733333333333335e-06,
+      "loss": 0.0005,
+      "step": 4475
+    },
+    {
+      "epoch": 346.15,
+      "learning_rate": 1.117777777777778e-06,
+      "loss": 0.0005,
+      "step": 4500
+    },
+    {
+      "epoch": 346.15,
+      "eval_loss": 1.1825743913650513,
+      "eval_runtime": 213.818,
+      "eval_samples_per_second": 4.368,
+      "eval_steps_per_second": 0.07,
+      "eval_wer": 39.51335877862596,
+      "step": 4500
+    },
+    {
+      "epoch": 348.08,
+      "learning_rate": 1.0622222222222222e-06,
+      "loss": 0.0004,
+      "step": 4525
+    },
+    {
+      "epoch": 350.0,
+      "learning_rate": 1.0066666666666668e-06,
+      "loss": 0.0004,
+      "step": 4550
+    },
+    {
+      "epoch": 351.92,
+      "learning_rate": 9.511111111111111e-07,
+      "loss": 0.0005,
+      "step": 4575
+    },
+    {
+      "epoch": 353.85,
+      "learning_rate": 8.955555555555557e-07,
+      "loss": 0.0004,
+      "step": 4600
+    },
+    {
+      "epoch": 355.77,
+      "learning_rate": 8.400000000000001e-07,
+      "loss": 0.0005,
+      "step": 4625
+    },
+    {
+      "epoch": 357.69,
+      "learning_rate": 7.844444444444445e-07,
+      "loss": 0.0005,
+      "step": 4650
+    },
+    {
+      "epoch": 359.62,
+      "learning_rate": 7.28888888888889e-07,
+      "loss": 0.0004,
+      "step": 4675
+    },
+    {
+      "epoch": 361.54,
+      "learning_rate": 6.733333333333334e-07,
+      "loss": 0.0004,
+      "step": 4700
+    },
+    {
+      "epoch": 363.46,
+      "learning_rate": 6.177777777777778e-07,
+      "loss": 0.0005,
+      "step": 4725
+    },
+    {
+      "epoch": 365.38,
+      "learning_rate": 5.622222222222223e-07,
+      "loss": 0.0004,
+      "step": 4750
+    },
+    {
+      "epoch": 367.31,
+      "learning_rate": 5.066666666666667e-07,
+      "loss": 0.0004,
+      "step": 4775
+    },
+    {
+      "epoch": 369.23,
+      "learning_rate": 4.511111111111111e-07,
+      "loss": 0.0004,
+      "step": 4800
+    },
+    {
+      "epoch": 371.15,
+      "learning_rate": 3.9555555555555557e-07,
+      "loss": 0.0005,
+      "step": 4825
+    },
+    {
+      "epoch": 373.08,
+      "learning_rate": 3.4000000000000003e-07,
+      "loss": 0.0004,
+      "step": 4850
+    },
+    {
+      "epoch": 375.0,
+      "learning_rate": 2.844444444444445e-07,
+      "loss": 0.0004,
+      "step": 4875
+    },
+    {
+      "epoch": 376.92,
+      "learning_rate": 2.2888888888888892e-07,
+      "loss": 0.0004,
+      "step": 4900
+    },
+    {
+      "epoch": 378.85,
+      "learning_rate": 1.7333333333333335e-07,
+      "loss": 0.0004,
+      "step": 4925
+    },
+    {
+      "epoch": 380.77,
+      "learning_rate": 1.1777777777777778e-07,
+      "loss": 0.0004,
+      "step": 4950
+    },
+    {
+      "epoch": 382.69,
+      "learning_rate": 6.222222222222223e-08,
+      "loss": 0.0003,
+      "step": 4975
+    },
+    {
+      "epoch": 384.62,
+      "learning_rate": 6.666666666666667e-09,
+      "loss": 0.0004,
+      "step": 5000
+    },
+    {
+      "epoch": 384.62,
+      "eval_loss": 1.1857084035873413,
+      "eval_runtime": 215.5395,
+      "eval_samples_per_second": 4.333,
+      "eval_steps_per_second": 0.07,
+      "eval_wer": 39.49904580152672,
+      "step": 5000
+    },
+    {
+      "epoch": 384.62,
+      "step": 5000,
+      "total_flos": 9.013099041721103e+19,
+      "train_loss": 0.1333366625772789,
+      "train_runtime": 10216.7319,
+      "train_samples_per_second": 31.321,
+      "train_steps_per_second": 0.489
+    }
+  ],
+  "max_steps": 5000,
+  "num_train_epochs": 385,
+  "total_flos": 9.013099041721103e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0680d2a16c810c2400a084f2b7de138d0f8ab68bf2c7adbf716295a0dd49f891
+size 3579