End of training

README.md

@@ -0,0 +1,63 @@
+---
+language:
+- hi
+license: apache-2.0
+base_model: openai/whisper-small
+tags:
+- hf-asr-leaderboard
+- generated_from_trainer
+datasets:
+- mozilla-foundation/common_voice_11_0
+model-index:
+- name: Whisper Small sv-SE default
+  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. -->
+
+# Whisper Small sv-SE default
+
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.2926
+- eval_wer: 93.8211
+- eval_runtime: 3457.4984
+- eval_samples_per_second: 1.466
+- eval_steps_per_second: 0.183
+- epoch: 2.59
+- step: 2000
+
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 4000
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

generation_config.json

@@ -0,0 +1,263 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|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,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|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,
+    "<|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,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 1,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.37.0.dev0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae5dbbc57608432a5a0c6ad5b14a2fb72860337e33f495c4a4460cd8fc115a4a
+oid sha256:33561a4cea0de4f32510dac4f7a878b38e5a3002930b85f13c4f2182273732ba
 size 966995080

runs/Jan15_06-20-37_ff8e71b02c7b/events.out.tfevents.1705299649.ff8e71b02c7b.5016.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9da7e7e2057d82395a66610c67cb141907d89d9511565f7715ea1e1ba11aed
-size 18381
+oid sha256:e2bd02df63f0845b60df2605336f19e48df1cc71c44f87433ee0c3cc28c2708e
+size 18538

runs/checkpoint-2000/config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "openai/whisper-small",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "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,
+  "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_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

runs/checkpoint-2000/generation_config.json

@@ -0,0 +1,263 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|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,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|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,
+    "<|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,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 1,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.37.0.dev0"
+}

runs/checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5dbbc57608432a5a0c6ad5b14a2fb72860337e33f495c4a4460cd8fc115a4a
+size 966995080

runs/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:032256abe3a92e59da6e6c4bc3e9b28471398bcfbef4fe28eb42510b884c22b5
+size 1925064044

runs/checkpoint-2000/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa131b1b19ffaf82f661066d702d457162e5d38c85d7e947e66a47635d27005
+size 14244

runs/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a5273daf07ac4539c46a1b62f5c68d48b779caf533ede5c15649352cd663e5
+size 1064

runs/checkpoint-2000/trainer_state.json

@@ -0,0 +1,519 @@
+{
+  "best_metric": 78.71259175607001,
+  "best_model_checkpoint": "./whisper-small-sv-SE/checkpoint-1000",
+  "epoch": 2.5873221216041395,
+  "eval_steps": 1000,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.2000000000000006e-07,
+      "loss": 4.3361,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.200000000000001e-07,
+      "loss": 3.3355,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.42e-06,
+      "loss": 2.4315,
+      "step": 75
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9200000000000003e-06,
+      "loss": 1.508,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.42e-06,
+      "loss": 1.1369,
+      "step": 125
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.92e-06,
+      "loss": 1.015,
+      "step": 150
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.4200000000000007e-06,
+      "loss": 0.9493,
+      "step": 175
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 3.920000000000001e-06,
+      "loss": 0.8579,
+      "step": 200
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.42e-06,
+      "loss": 0.7383,
+      "step": 225
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.92e-06,
+      "loss": 0.5942,
+      "step": 250
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 5.420000000000001e-06,
+      "loss": 0.4352,
+      "step": 275
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 5.92e-06,
+      "loss": 0.339,
+      "step": 300
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.42e-06,
+      "loss": 0.2966,
+      "step": 325
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 6.92e-06,
+      "loss": 0.3068,
+      "step": 350
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.420000000000001e-06,
+      "loss": 0.3,
+      "step": 375
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 7.92e-06,
+      "loss": 0.3098,
+      "step": 400
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.42e-06,
+      "loss": 0.2948,
+      "step": 425
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.920000000000001e-06,
+      "loss": 0.2956,
+      "step": 450
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.42e-06,
+      "loss": 0.2939,
+      "step": 475
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.920000000000002e-06,
+      "loss": 0.2952,
+      "step": 500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.940000000000001e-06,
+      "loss": 0.3004,
+      "step": 525
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.86857142857143e-06,
+      "loss": 0.3134,
+      "step": 550
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.797142857142858e-06,
+      "loss": 0.3292,
+      "step": 575
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.725714285714287e-06,
+      "loss": 0.3134,
+      "step": 600
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.654285714285716e-06,
+      "loss": 0.3138,
+      "step": 625
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 9.582857142857143e-06,
+      "loss": 0.289,
+      "step": 650
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.511428571428572e-06,
+      "loss": 0.2953,
+      "step": 675
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.440000000000001e-06,
+      "loss": 0.2828,
+      "step": 700
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.368571428571428e-06,
+      "loss": 0.3016,
+      "step": 725
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.297142857142857e-06,
+      "loss": 0.293,
+      "step": 750
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.225714285714286e-06,
+      "loss": 0.2724,
+      "step": 775
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.154285714285715e-06,
+      "loss": 0.1415,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.082857142857143e-06,
+      "loss": 0.1465,
+      "step": 825
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 9.011428571428572e-06,
+      "loss": 0.132,
+      "step": 850
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.94e-06,
+      "loss": 0.132,
+      "step": 875
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.86857142857143e-06,
+      "loss": 0.1295,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 8.797142857142857e-06,
+      "loss": 0.156,
+      "step": 925
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 8.725714285714286e-06,
+      "loss": 0.1439,
+      "step": 950
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 8.654285714285715e-06,
+      "loss": 0.1668,
+      "step": 975
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 8.582857142857144e-06,
+      "loss": 0.1451,
+      "step": 1000
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.2990506589412689,
+      "eval_runtime": 3103.9764,
+      "eval_samples_per_second": 1.633,
+      "eval_steps_per_second": 0.204,
+      "eval_wer": 78.71259175607001,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 8.511428571428571e-06,
+      "loss": 0.1358,
+      "step": 1025
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 8.44e-06,
+      "loss": 0.1354,
+      "step": 1050
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 8.36857142857143e-06,
+      "loss": 0.1492,
+      "step": 1075
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 8.297142857142859e-06,
+      "loss": 0.1438,
+      "step": 1100
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 8.225714285714288e-06,
+      "loss": 0.1339,
+      "step": 1125
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 8.154285714285715e-06,
+      "loss": 0.1451,
+      "step": 1150
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 8.082857142857144e-06,
+      "loss": 0.1432,
+      "step": 1175
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 8.011428571428573e-06,
+      "loss": 0.1312,
+      "step": 1200
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 7.94e-06,
+      "loss": 0.1397,
+      "step": 1225
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.86857142857143e-06,
+      "loss": 0.1381,
+      "step": 1250
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 7.797142857142858e-06,
+      "loss": 0.1456,
+      "step": 1275
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 7.725714285714286e-06,
+      "loss": 0.1463,
+      "step": 1300
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 7.654285714285715e-06,
+      "loss": 0.1284,
+      "step": 1325
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.5828571428571444e-06,
+      "loss": 0.1539,
+      "step": 1350
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.511428571428572e-06,
+      "loss": 0.1409,
+      "step": 1375
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.440000000000001e-06,
+      "loss": 0.1391,
+      "step": 1400
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.36857142857143e-06,
+      "loss": 0.1319,
+      "step": 1425
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 7.297142857142858e-06,
+      "loss": 0.1238,
+      "step": 1450
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 7.225714285714286e-06,
+      "loss": 0.1491,
+      "step": 1475
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 7.154285714285715e-06,
+      "loss": 0.1459,
+      "step": 1500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 7.082857142857143e-06,
+      "loss": 0.1535,
+      "step": 1525
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 7.011428571428572e-06,
+      "loss": 0.1379,
+      "step": 1550
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 6.9400000000000005e-06,
+      "loss": 0.0538,
+      "step": 1575
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 6.868571428571429e-06,
+      "loss": 0.0532,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 6.797142857142858e-06,
+      "loss": 0.056,
+      "step": 1625
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 6.725714285714287e-06,
+      "loss": 0.0512,
+      "step": 1650
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 6.654285714285716e-06,
+      "loss": 0.0568,
+      "step": 1675
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 6.582857142857143e-06,
+      "loss": 0.0485,
+      "step": 1700
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 6.511428571428572e-06,
+      "loss": 0.0587,
+      "step": 1725
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 6.440000000000001e-06,
+      "loss": 0.0537,
+      "step": 1750
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 6.368571428571429e-06,
+      "loss": 0.052,
+      "step": 1775
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 6.297142857142857e-06,
+      "loss": 0.0504,
+      "step": 1800
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 6.225714285714286e-06,
+      "loss": 0.0587,
+      "step": 1825
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 6.1542857142857145e-06,
+      "loss": 0.0493,
+      "step": 1850
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 6.0828571428571435e-06,
+      "loss": 0.0514,
+      "step": 1875
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 6.011428571428572e-06,
+      "loss": 0.0487,
+      "step": 1900
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 5.94e-06,
+      "loss": 0.0555,
+      "step": 1925
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 5.868571428571429e-06,
+      "loss": 0.0495,
+      "step": 1950
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 5.797142857142858e-06,
+      "loss": 0.0523,
+      "step": 1975
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 5.725714285714287e-06,
+      "loss": 0.0515,
+      "step": 2000
+    },
+    {
+      "epoch": 2.59,
+      "eval_loss": 0.29257670044898987,
+      "eval_runtime": 3457.4984,
+      "eval_samples_per_second": 1.466,
+      "eval_steps_per_second": 0.183,
+      "eval_wer": 93.82108574655157,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 1000,
+  "total_flos": 9.23011544383488e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

runs/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c8cad5a4b3452268d8a7a2e6ec443c8fe1edca06260dcaa02ed7b4b25a505a
+size 4856