Model save

README.md

@@ -0,0 +1,81 @@
+---
+license: mit
+base_model: distil-whisper/distil-large-v3
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_16_1
+metrics:
+- wer
+model-index:
+- name: distil-whisper/distil-large-v3
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_16_1
+      type: common_voice_16_1
+      config: hi
+      split: test
+      args: hi
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.3297535347291973
+---
+
+<!-- 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. -->
+
+# distil-whisper/distil-large-v3
+
+This model is a fine-tuned version of [distil-whisper/distil-large-v3](https://huggingface.co/distil-whisper/distil-large-v3) on the common_voice_16_1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6148
+- Wer: 0.3298
+
+## 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: 0.0001
+- train_batch_size: 32
+- eval_batch_size: 32
+- 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: 5000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.125         | 4.5   | 1000 | 0.4658          | 0.4300 |
+| 0.0412        | 9.01  | 2000 | 0.5247          | 0.3960 |
+| 0.0077        | 13.51 | 3000 | 0.5476          | 0.3535 |
+| 0.0007        | 18.02 | 4000 | 0.5731          | 0.3398 |
+| 0.0001        | 22.52 | 5000 | 0.6148          | 0.3298 |
+
+
+### Framework versions
+
+- Transformers 4.40.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.1

generation_config.json

@@ -0,0 +1,267 @@
+{
+  "alignment_heads": [
+    [
+      7,
+      0
+    ],
+    [
+      10,
+      17
+    ],
+    [
+      12,
+      18
+    ],
+    [
+      13,
+      12
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      21,
+      4
+    ],
+    [
+      24,
+      1
+    ],
+    [
+      25,
+      6
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50360
+    ]
+  ],
+  "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,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "language": "hindi",
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50364,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50362,
+  "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,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.40.0.dev0"
+}

wandb/debug-internal.log

@@ -37987,3 +37987,30 @@
 2024-03-28 02:05:23,448 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: status_report
 2024-03-28 02:05:23,986 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
 2024-03-28 02:05:23,996 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:26,479 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:26,488 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:28,507 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: status_report
+2024-03-28 02:05:28,512 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:28,522 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:29,499 INFO    Thread-13 :1893870 [dir_watcher.py:_on_file_modified():288] file/dir modified: /home/sanchit/distil-large-v3-hi-ft/wandb/run-20240327_190418-lwtbcr8s/files/output.log
+2024-03-28 02:05:31,004 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:31,065 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:33,084 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:33,508 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: status_report
+2024-03-28 02:05:34,135 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:34,923 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: internal_messages
+2024-03-28 02:05:34,923 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: stop_status
+2024-03-28 02:05:34,924 DEBUG   SenderThread:1893870 [sender.py:send_request():409] send_request: stop_status
+2024-03-28 02:05:37,473 ERROR   gpu       :1893870 [interfaces.py:aggregate():161] Failed to serialize metric: division by zero
+2024-03-28 02:05:37,491 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:37,500 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:37,502 INFO    Thread-13 :1893870 [dir_watcher.py:_on_file_modified():288] file/dir modified: /home/sanchit/distil-large-v3-hi-ft/wandb/run-20240327_190418-lwtbcr8s/files/output.log
+2024-03-28 02:05:39,139 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: status_report
+2024-03-28 02:05:40,156 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:40,364 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:43,193 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:43,203 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:44,977 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: status_report
+2024-03-28 02:05:45,225 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:45,237 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:45,504 INFO    Thread-13 :1893870 [dir_watcher.py:_on_file_modified():288] file/dir modified: /home/sanchit/distil-large-v3-hi-ft/wandb/run-20240327_190418-lwtbcr8s/files/output.log

wandb/run-20240327_190418-lwtbcr8s/files/output.log

@@ -5764,3 +5764,18 @@ Non-default generation parameters: {'max_length': 448, 'begin_suppress_tokens':
 Training completed. Do not forget to share your model on huggingface.co/models =)
 100%|█████████████████████████████████████████████████████████████████████████████| 5000/5000 [6:59:41<00:00,  5.04s/it]
 [INFO|trainer.py:4001] 2024-03-28 02:04:00,440 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
+{'train_runtime': 25183.0848, 'train_samples_per_second': 6.353, 'train_steps_per_second': 0.199, 'train_loss': 0.15328583015645855, 'epoch': 22.52}
+[INFO|trainer.py:3235] 2024-03-28 02:05:27,505 >> Saving model checkpoint to ./
+[WARNING|configuration_utils.py:447] 2024-03-28 02:05:27,505 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
+Non-default generation parameters: {'max_length': 448, 'begin_suppress_tokens': [220, 50257]}
+[INFO|configuration_utils.py:471] 2024-03-28 02:05:27,506 >> Configuration saved in ./config.json
+[INFO|configuration_utils.py:697] 2024-03-28 02:05:27,507 >> Configuration saved in ./generation_config.json
+[INFO|modeling_utils.py:2475] 2024-03-28 02:05:34,921 >> Model weights saved in ./model.safetensors
+[INFO|feature_extraction_utils.py:424] 2024-03-28 02:05:34,923 >> Feature extractor saved in ./preprocessor_config.json
+[INFO|trainer.py:3235] 2024-03-28 02:05:34,924 >> Saving model checkpoint to ./
+[WARNING|configuration_utils.py:447] 2024-03-28 02:05:34,924 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
+Non-default generation parameters: {'max_length': 448, 'begin_suppress_tokens': [220, 50257]}
+[INFO|configuration_utils.py:471] 2024-03-28 02:05:34,925 >> Configuration saved in ./config.json
+[INFO|configuration_utils.py:697] 2024-03-28 02:05:34,926 >> Configuration saved in ./generation_config.json
+[INFO|modeling_utils.py:2475] 2024-03-28 02:05:42,975 >> Model weights saved in ./model.safetensors
+[INFO|feature_extraction_utils.py:424] 2024-03-28 02:05:42,976 >> Feature extractor saved in ./preprocessor_config.json

wandb/run-20240327_190418-lwtbcr8s/logs/debug-internal.log

@@ -37987,3 +37987,30 @@
 2024-03-28 02:05:23,448 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: status_report
 2024-03-28 02:05:23,986 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
 2024-03-28 02:05:23,996 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:26,479 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:26,488 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:28,507 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: status_report
+2024-03-28 02:05:28,512 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:28,522 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:29,499 INFO    Thread-13 :1893870 [dir_watcher.py:_on_file_modified():288] file/dir modified: /home/sanchit/distil-large-v3-hi-ft/wandb/run-20240327_190418-lwtbcr8s/files/output.log
+2024-03-28 02:05:31,004 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:31,065 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:33,084 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:33,508 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: status_report
+2024-03-28 02:05:34,135 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:34,923 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: internal_messages
+2024-03-28 02:05:34,923 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: stop_status
+2024-03-28 02:05:34,924 DEBUG   SenderThread:1893870 [sender.py:send_request():409] send_request: stop_status
+2024-03-28 02:05:37,473 ERROR   gpu       :1893870 [interfaces.py:aggregate():161] Failed to serialize metric: division by zero
+2024-03-28 02:05:37,491 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:37,500 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:37,502 INFO    Thread-13 :1893870 [dir_watcher.py:_on_file_modified():288] file/dir modified: /home/sanchit/distil-large-v3-hi-ft/wandb/run-20240327_190418-lwtbcr8s/files/output.log
+2024-03-28 02:05:39,139 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: status_report
+2024-03-28 02:05:40,156 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:40,364 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:43,193 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:43,203 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:44,977 DEBUG   HandlerThread:1893870 [handler.py:handle_request():146] handle_request: status_report
+2024-03-28 02:05:45,225 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:45,237 ERROR   gpu       :1893870 [interfaces.py:monitor():144] Failed to sample metric: Not Supported
+2024-03-28 02:05:45,504 INFO    Thread-13 :1893870 [dir_watcher.py:_on_file_modified():288] file/dir modified: /home/sanchit/distil-large-v3-hi-ft/wandb/run-20240327_190418-lwtbcr8s/files/output.log

wandb/run-20240327_190418-lwtbcr8s/run-lwtbcr8s.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1393642b3724d50ee1c65a1f63d69a1ba871fe44cbe3d6bf0f7ea5b339b70ec5
-size 6043771
+oid sha256:2a502992b600b6f3e077e321535ba1bc5376c9e17acb1ddd34f38b6dccb0d4a4
+size 6062379