occitan whisper small ft

.gitignore

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

README.md

@@ -0,0 +1,85 @@
+---
+license: apache-2.0
+tags:
+- whisper-event
+- generated_from_trainer
+datasets:
+- google/fleurs
+metrics:
+- wer
+model-index:
+- name: Whisper_small_Occitan
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: google/fleurs 
+      type: google/fleurs
+      config: oc_fr
+      split: test
+    metrics:
+    - name: Wer
+      type: wer
+      value: 39.84848484848485
+---
+
+<!-- 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_Occitan
+
+This model is a fine-tuned version of [bofenghuang/whisper-small-cv11-french](https://huggingface.co/bofenghuang/whisper-small-cv11-french) on the google/fleurs oc_fr dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1744
+- Wer: 39.8485
+
+## 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: 2000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.0087        | 30.77  | 400  | 1.1744          | 39.8485 |
+| 0.001         | 61.54  | 800  | 1.2807          | 39.8939 |
+| 0.0005        | 92.31  | 1200 | 1.3227          | 40.3447 |
+| 0.0004        | 123.08 | 1600 | 1.3445          | 40.1098 |
+| 0.0003        | 153.85 | 2000 | 1.3524          | 40.0492 |
+
+
+### 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": 153.85,
+    "eval_loss": 1.1743659973144531,
+    "eval_runtime": 222.4939,
+    "eval_samples_per_second": 4.486,
+    "eval_steps_per_second": 0.072,
+    "eval_wer": 39.84848484848485,
+    "train_loss": 0.1594467444368638,
+    "train_runtime": 4489.5772,
+    "train_samples_per_second": 28.51,
+    "train_steps_per_second": 0.445
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "bofenghuang/whisper-small-cv11-french",
+  "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": 0.0,
+  "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": 153.85,
+    "eval_loss": 1.1743659973144531,
+    "eval_runtime": 222.4939,
+    "eval_samples_per_second": 4.486,
+    "eval_steps_per_second": 0.072,
+    "eval_wer": 39.84848484848485
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d918fd93d9f398a546a81a5dbe676ab524df43e86d16d18f81eecc979a1e6e6
+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-french",
+  "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": 153.85,
+    "train_loss": 0.1594467444368638,
+    "train_runtime": 4489.5772,
+    "train_samples_per_second": 28.51,
+    "train_steps_per_second": 0.445
+}

trainer_state.json

@@ -0,0 +1,550 @@
+{
+  "best_metric": 39.84848484848485,
+  "best_model_checkpoint": "./whisper-small-occitan/checkpoint-400",
+  "epoch": 153.84615384615384,
+  "global_step": 2000,
+  "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": 2.9498,
+      "step": 25
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 9.600000000000001e-07,
+      "loss": 2.4926,
+      "step": 50
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 1.46e-06,
+      "loss": 1.8745,
+      "step": 75
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 1.9600000000000003e-06,
+      "loss": 1.4577,
+      "step": 100
+    },
+    {
+      "epoch": 9.62,
+      "learning_rate": 2.46e-06,
+      "loss": 1.1073,
+      "step": 125
+    },
+    {
+      "epoch": 11.54,
+      "learning_rate": 2.96e-06,
+      "loss": 0.8437,
+      "step": 150
+    },
+    {
+      "epoch": 13.46,
+      "learning_rate": 3.46e-06,
+      "loss": 0.6607,
+      "step": 175
+    },
+    {
+      "epoch": 15.38,
+      "learning_rate": 3.96e-06,
+      "loss": 0.4703,
+      "step": 200
+    },
+    {
+      "epoch": 17.31,
+      "learning_rate": 4.4600000000000005e-06,
+      "loss": 0.3189,
+      "step": 225
+    },
+    {
+      "epoch": 19.23,
+      "learning_rate": 4.960000000000001e-06,
+      "loss": 0.216,
+      "step": 250
+    },
+    {
+      "epoch": 21.15,
+      "learning_rate": 5.460000000000001e-06,
+      "loss": 0.1373,
+      "step": 275
+    },
+    {
+      "epoch": 23.08,
+      "learning_rate": 5.9600000000000005e-06,
+      "loss": 0.0764,
+      "step": 300
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 6.460000000000001e-06,
+      "loss": 0.0448,
+      "step": 325
+    },
+    {
+      "epoch": 26.92,
+      "learning_rate": 6.96e-06,
+      "loss": 0.0252,
+      "step": 350
+    },
+    {
+      "epoch": 28.85,
+      "learning_rate": 7.4600000000000006e-06,
+      "loss": 0.0138,
+      "step": 375
+    },
+    {
+      "epoch": 30.77,
+      "learning_rate": 7.960000000000002e-06,
+      "loss": 0.0087,
+      "step": 400
+    },
+    {
+      "epoch": 30.77,
+      "eval_loss": 1.1743659973144531,
+      "eval_runtime": 223.5812,
+      "eval_samples_per_second": 4.464,
+      "eval_steps_per_second": 0.072,
+      "eval_wer": 39.84848484848485,
+      "step": 400
+    },
+    {
+      "epoch": 32.69,
+      "learning_rate": 8.46e-06,
+      "loss": 0.0057,
+      "step": 425
+    },
+    {
+      "epoch": 34.62,
+      "learning_rate": 8.96e-06,
+      "loss": 0.0044,
+      "step": 450
+    },
+    {
+      "epoch": 36.54,
+      "learning_rate": 9.460000000000001e-06,
+      "loss": 0.0036,
+      "step": 475
+    },
+    {
+      "epoch": 38.46,
+      "learning_rate": 9.960000000000001e-06,
+      "loss": 0.0029,
+      "step": 500
+    },
+    {
+      "epoch": 40.38,
+      "learning_rate": 9.846666666666668e-06,
+      "loss": 0.0025,
+      "step": 525
+    },
+    {
+      "epoch": 42.31,
+      "learning_rate": 9.68e-06,
+      "loss": 0.0022,
+      "step": 550
+    },
+    {
+      "epoch": 44.23,
+      "learning_rate": 9.513333333333334e-06,
+      "loss": 0.002,
+      "step": 575
+    },
+    {
+      "epoch": 46.15,
+      "learning_rate": 9.346666666666666e-06,
+      "loss": 0.0017,
+      "step": 600
+    },
+    {
+      "epoch": 48.08,
+      "learning_rate": 9.180000000000002e-06,
+      "loss": 0.0016,
+      "step": 625
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 9.013333333333334e-06,
+      "loss": 0.0014,
+      "step": 650
+    },
+    {
+      "epoch": 51.92,
+      "learning_rate": 8.846666666666668e-06,
+      "loss": 0.0013,
+      "step": 675
+    },
+    {
+      "epoch": 53.85,
+      "learning_rate": 8.68e-06,
+      "loss": 0.0012,
+      "step": 700
+    },
+    {
+      "epoch": 55.77,
+      "learning_rate": 8.513333333333335e-06,
+      "loss": 0.0012,
+      "step": 725
+    },
+    {
+      "epoch": 57.69,
+      "learning_rate": 8.346666666666668e-06,
+      "loss": 0.0011,
+      "step": 750
+    },
+    {
+      "epoch": 59.62,
+      "learning_rate": 8.18e-06,
+      "loss": 0.001,
+      "step": 775
+    },
+    {
+      "epoch": 61.54,
+      "learning_rate": 8.013333333333333e-06,
+      "loss": 0.001,
+      "step": 800
+    },
+    {
+      "epoch": 61.54,
+      "eval_loss": 1.2807344198226929,
+      "eval_runtime": 249.8649,
+      "eval_samples_per_second": 3.994,
+      "eval_steps_per_second": 0.064,
+      "eval_wer": 39.89393939393939,
+      "step": 800
+    },
+    {
+      "epoch": 63.46,
+      "learning_rate": 7.846666666666667e-06,
+      "loss": 0.0009,
+      "step": 825
+    },
+    {
+      "epoch": 65.38,
+      "learning_rate": 7.680000000000001e-06,
+      "loss": 0.0009,
+      "step": 850
+    },
+    {
+      "epoch": 67.31,
+      "learning_rate": 7.513333333333334e-06,
+      "loss": 0.0008,
+      "step": 875
+    },
+    {
+      "epoch": 69.23,
+      "learning_rate": 7.346666666666668e-06,
+      "loss": 0.0008,
+      "step": 900
+    },
+    {
+      "epoch": 71.15,
+      "learning_rate": 7.180000000000001e-06,
+      "loss": 0.0007,
+      "step": 925
+    },
+    {
+      "epoch": 73.08,
+      "learning_rate": 7.0133333333333345e-06,
+      "loss": 0.0007,
+      "step": 950
+    },
+    {
+      "epoch": 75.0,
+      "learning_rate": 6.846666666666667e-06,
+      "loss": 0.0007,
+      "step": 975
+    },
+    {
+      "epoch": 76.92,
+      "learning_rate": 6.680000000000001e-06,
+      "loss": 0.0007,
+      "step": 1000
+    },
+    {
+      "epoch": 78.85,
+      "learning_rate": 6.513333333333333e-06,
+      "loss": 0.0006,
+      "step": 1025
+    },
+    {
+      "epoch": 80.77,
+      "learning_rate": 6.346666666666668e-06,
+      "loss": 0.0006,
+      "step": 1050
+    },
+    {
+      "epoch": 82.69,
+      "learning_rate": 6.18e-06,
+      "loss": 0.0006,
+      "step": 1075
+    },
+    {
+      "epoch": 84.62,
+      "learning_rate": 6.013333333333335e-06,
+      "loss": 0.0006,
+      "step": 1100
+    },
+    {
+      "epoch": 86.54,
+      "learning_rate": 5.846666666666667e-06,
+      "loss": 0.0006,
+      "step": 1125
+    },
+    {
+      "epoch": 88.46,
+      "learning_rate": 5.68e-06,
+      "loss": 0.0005,
+      "step": 1150
+    },
+    {
+      "epoch": 90.38,
+      "learning_rate": 5.513333333333334e-06,
+      "loss": 0.0005,
+      "step": 1175
+    },
+    {
+      "epoch": 92.31,
+      "learning_rate": 5.346666666666667e-06,
+      "loss": 0.0005,
+      "step": 1200
+    },
+    {
+      "epoch": 92.31,
+      "eval_loss": 1.3227487802505493,
+      "eval_runtime": 267.0559,
+      "eval_samples_per_second": 3.737,
+      "eval_steps_per_second": 0.06,
+      "eval_wer": 40.34469696969697,
+      "step": 1200
+    },
+    {
+      "epoch": 94.23,
+      "learning_rate": 5.18e-06,
+      "loss": 0.0005,
+      "step": 1225
+    },
+    {
+      "epoch": 96.15,
+      "learning_rate": 5.013333333333333e-06,
+      "loss": 0.0005,
+      "step": 1250
+    },
+    {
+      "epoch": 98.08,
+      "learning_rate": 4.846666666666667e-06,
+      "loss": 0.0005,
+      "step": 1275
+    },
+    {
+      "epoch": 100.0,
+      "learning_rate": 4.680000000000001e-06,
+      "loss": 0.0005,
+      "step": 1300
+    },
+    {
+      "epoch": 101.92,
+      "learning_rate": 4.513333333333333e-06,
+      "loss": 0.0005,
+      "step": 1325
+    },
+    {
+      "epoch": 103.85,
+      "learning_rate": 4.346666666666667e-06,
+      "loss": 0.0004,
+      "step": 1350
+    },
+    {
+      "epoch": 105.77,
+      "learning_rate": 4.18e-06,
+      "loss": 0.0004,
+      "step": 1375
+    },
+    {
+      "epoch": 107.69,
+      "learning_rate": 4.013333333333334e-06,
+      "loss": 0.0004,
+      "step": 1400
+    },
+    {
+      "epoch": 109.62,
+      "learning_rate": 3.8466666666666665e-06,
+      "loss": 0.0004,
+      "step": 1425
+    },
+    {
+      "epoch": 111.54,
+      "learning_rate": 3.6800000000000003e-06,
+      "loss": 0.0004,
+      "step": 1450
+    },
+    {
+      "epoch": 113.46,
+      "learning_rate": 3.5133333333333337e-06,
+      "loss": 0.0004,
+      "step": 1475
+    },
+    {
+      "epoch": 115.38,
+      "learning_rate": 3.346666666666667e-06,
+      "loss": 0.0004,
+      "step": 1500
+    },
+    {
+      "epoch": 117.31,
+      "learning_rate": 3.1800000000000005e-06,
+      "loss": 0.0004,
+      "step": 1525
+    },
+    {
+      "epoch": 119.23,
+      "learning_rate": 3.013333333333334e-06,
+      "loss": 0.0004,
+      "step": 1550
+    },
+    {
+      "epoch": 121.15,
+      "learning_rate": 2.8466666666666672e-06,
+      "loss": 0.0004,
+      "step": 1575
+    },
+    {
+      "epoch": 123.08,
+      "learning_rate": 2.68e-06,
+      "loss": 0.0004,
+      "step": 1600
+    },
+    {
+      "epoch": 123.08,
+      "eval_loss": 1.344544768333435,
+      "eval_runtime": 249.8728,
+      "eval_samples_per_second": 3.994,
+      "eval_steps_per_second": 0.064,
+      "eval_wer": 40.109848484848484,
+      "step": 1600
+    },
+    {
+      "epoch": 125.0,
+      "learning_rate": 2.5133333333333336e-06,
+      "loss": 0.0004,
+      "step": 1625
+    },
+    {
+      "epoch": 126.92,
+      "learning_rate": 2.346666666666667e-06,
+      "loss": 0.0004,
+      "step": 1650
+    },
+    {
+      "epoch": 128.85,
+      "learning_rate": 2.1800000000000003e-06,
+      "loss": 0.0004,
+      "step": 1675
+    },
+    {
+      "epoch": 130.77,
+      "learning_rate": 2.0133333333333337e-06,
+      "loss": 0.0004,
+      "step": 1700
+    },
+    {
+      "epoch": 132.69,
+      "learning_rate": 1.8466666666666668e-06,
+      "loss": 0.0004,
+      "step": 1725
+    },
+    {
+      "epoch": 134.62,
+      "learning_rate": 1.6800000000000002e-06,
+      "loss": 0.0004,
+      "step": 1750
+    },
+    {
+      "epoch": 136.54,
+      "learning_rate": 1.5133333333333334e-06,
+      "loss": 0.0004,
+      "step": 1775
+    },
+    {
+      "epoch": 138.46,
+      "learning_rate": 1.3466666666666668e-06,
+      "loss": 0.0003,
+      "step": 1800
+    },
+    {
+      "epoch": 140.38,
+      "learning_rate": 1.1800000000000001e-06,
+      "loss": 0.0003,
+      "step": 1825
+    },
+    {
+      "epoch": 142.31,
+      "learning_rate": 1.0133333333333333e-06,
+      "loss": 0.0003,
+      "step": 1850
+    },
+    {
+      "epoch": 144.23,
+      "learning_rate": 8.466666666666668e-07,
+      "loss": 0.0003,
+      "step": 1875
+    },
+    {
+      "epoch": 146.15,
+      "learning_rate": 6.800000000000001e-07,
+      "loss": 0.0003,
+      "step": 1900
+    },
+    {
+      "epoch": 148.08,
+      "learning_rate": 5.133333333333334e-07,
+      "loss": 0.0003,
+      "step": 1925
+    },
+    {
+      "epoch": 150.0,
+      "learning_rate": 3.466666666666667e-07,
+      "loss": 0.0003,
+      "step": 1950
+    },
+    {
+      "epoch": 151.92,
+      "learning_rate": 1.8e-07,
+      "loss": 0.0003,
+      "step": 1975
+    },
+    {
+      "epoch": 153.85,
+      "learning_rate": 1.3333333333333334e-08,
+      "loss": 0.0003,
+      "step": 2000
+    },
+    {
+      "epoch": 153.85,
+      "eval_loss": 1.3523659706115723,
+      "eval_runtime": 249.9178,
+      "eval_samples_per_second": 3.993,
+      "eval_steps_per_second": 0.064,
+      "eval_wer": 40.04924242424243,
+      "step": 2000
+    },
+    {
+      "epoch": 153.85,
+      "step": 2000,
+      "total_flos": 3.69389315127509e+19,
+      "train_loss": 0.1594467444368638,
+      "train_runtime": 4489.5772,
+      "train_samples_per_second": 28.51,
+      "train_steps_per_second": 0.445
+    }
+  ],
+  "max_steps": 2000,
+  "num_train_epochs": 154,
+  "total_flos": 3.69389315127509e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5592f015b5fd817dce99a7feb0fceb7884ee60457495e1032bd70f340b167bc1
+size 3579