Model save

runs/Jun26_13-58-09_bharatsahaiyak-test/events.out.tfevents.1719413026.bharatsahaiyak-test.1356323.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5414cd9913029bfa66b316fd8c26426ccc17704fb1509e18d6919ed613b332eb
+size 6020

whisper-tiny-hindi-checkpoint-chunk-10/config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "openai/whisper-tiny",
+  "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": 384,
+  "decoder_attention_heads": 6,
+  "decoder_ffn_dim": 1536,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.1,
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 1536,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "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": 4,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

whisper-tiny-hindi-checkpoint-chunk-10/generation_config.json

@@ -0,0 +1,248 @@
+{
+  "alignment_heads": [
+    [
+      2,
+      2
+    ],
+    [
+      3,
+      0
+    ],
+    [
+      3,
+      2
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      4
+    ],
+    [
+      3,
+      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": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "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": "4.41.1"
+}

whisper-tiny-hindi-checkpoint-chunk-10/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
+}

whisper-tiny-hindi-checkpoint-chunk-10/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be302553c4eadd11f987e45d1a709ba97362714e3d8b3bb19794e15c3d08d52f
+size 151099494

whisper-tiny-hindi-checkpoint-chunk-10/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21be1e79938b339a6279236c12d4ab03a265c6a80902c0f43f588a41011103a2
+size 5240

whisper-tiny-hindi-checkpoint-chunk-9/trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_metric": 73.71718882303134,
+  "best_model_checkpoint": "./whisper-tiny-hindi2_test/checkpoint-120",
+  "epoch": 4.920634920634921,
+  "eval_steps": 40,
+  "global_step": 155,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": Infinity,
+      "learning_rate": 2.043269230769231e-06,
+      "loss": 3.3856,
+      "step": 20
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "grad_norm": 12.90635871887207,
+      "learning_rate": 4.447115384615384e-06,
+      "loss": 2.2169,
+      "step": 40
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "eval_loss": 1.7869399785995483,
+      "eval_runtime": 509.7564,
+      "eval_samples_per_second": 1.962,
+      "eval_steps_per_second": 0.49,
+      "eval_wer": 241.5580016934801,
+      "step": 40
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 8.530549049377441,
+      "learning_rate": 6.850961538461537e-06,
+      "loss": 1.4435,
+      "step": 60
+    },
+    {
+      "epoch": 2.5396825396825395,
+      "grad_norm": 7.451807022094727,
+      "learning_rate": 9.254807692307693e-06,
+      "loss": 1.0037,
+      "step": 80
+    },
+    {
+      "epoch": 2.5396825396825395,
+      "eval_loss": 0.8910112380981445,
+      "eval_runtime": 318.2676,
+      "eval_samples_per_second": 3.142,
+      "eval_steps_per_second": 0.786,
+      "eval_wer": 78.55207451312447,
+      "step": 80
+    },
+    {
+      "epoch": 3.1746031746031744,
+      "grad_norm": 6.283768177032471,
+      "learning_rate": 1.1658653846153846e-05,
+      "loss": 0.7501,
+      "step": 100
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "grad_norm": 6.983267307281494,
+      "learning_rate": 1.40625e-05,
+      "loss": 0.5907,
+      "step": 120
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "eval_loss": 0.624940812587738,
+      "eval_runtime": 318.0146,
+      "eval_samples_per_second": 3.145,
+      "eval_steps_per_second": 0.786,
+      "eval_wer": 73.71718882303134,
+      "step": 120
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 5.939335346221924,
+      "learning_rate": 1.646634615384615e-05,
+      "loss": 0.4806,
+      "step": 140
+    },
+    {
+      "epoch": 4.920634920634921,
+      "step": 155,
+      "total_flos": 1.2132186587136e+17,
+      "train_loss": 1.3161909626376245,
+      "train_runtime": 1802.5104,
+      "train_samples_per_second": 2.774,
+      "train_steps_per_second": 0.086
+    },
+    {
+      "epoch": 4.920634920634921,
+      "step": 155,
+      "total_flos": 1.2132186587136e+17,
+      "train_loss": 0.0,
+      "train_runtime": 0.1541,
+      "train_samples_per_second": 32447.028,
+      "train_steps_per_second": 1005.858
+    },
+    {
+      "epoch": 4.920634920634921,
+      "step": 155,
+      "total_flos": 1.2132186587136e+17,
+      "train_loss": 0.0,
+      "train_runtime": 0.2109,
+      "train_samples_per_second": 23707.402,
+      "train_steps_per_second": 734.929
+    },
+    {
+      "epoch": 4.920634920634921,
+      "step": 155,
+      "total_flos": 1.2132186587136e+17,
+      "train_loss": 0.0,
+      "train_runtime": 0.17,
+      "train_samples_per_second": 29405.194,
+      "train_steps_per_second": 911.561
+    },
+    {
+      "epoch": 4.920634920634921,
+      "step": 155,
+      "total_flos": 1.2132186587136e+17,
+      "train_loss": 0.0,
+      "train_runtime": 0.1766,
+      "train_samples_per_second": 28306.956,
+      "train_steps_per_second": 877.516
+    },
+    {
+      "epoch": 4.920634920634921,
+      "step": 155,
+      "total_flos": 1.2132186587136e+17,
+      "train_loss": 0.0,
+      "train_runtime": 0.1713,
+      "train_samples_per_second": 29193.689,
+      "train_steps_per_second": 905.004
+    },
+    {
+      "epoch": 4.920634920634921,
+      "step": 155,
+      "total_flos": 1.2132186587136e+17,
+      "train_loss": 0.0,
+      "train_runtime": 0.1661,
+      "train_samples_per_second": 30110.469,
+      "train_steps_per_second": 933.425
+    },
+    {
+      "epoch": 4.920634920634921,
+      "step": 155,
+      "total_flos": 1.2132186587136e+17,
+      "train_loss": 0.0,
+      "train_runtime": 0.1725,
+      "train_samples_per_second": 28992.337,
+      "train_steps_per_second": 898.762
+    },
+    {
+      "epoch": 4.920634920634921,
+      "step": 155,
+      "total_flos": 1.2132186587136e+17,
+      "train_loss": 0.0,
+      "train_runtime": 0.1816,
+      "train_samples_per_second": 27529.483,
+      "train_steps_per_second": 853.414
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 155,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2132186587136e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}