Upload checkpoint-1301

checkpoint-1301/config.json

@@ -0,0 +1,152 @@
+{
+  "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": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 24,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "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_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": 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
+  ],
+  "tie_word_embeddings": true,
+  "transformers_version": "5.4.0",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

checkpoint-1301/generation_config.json

@@ -0,0 +1,241 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "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
+  },
+  "language": "Hindi",
+  "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": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "5.4.0"
+}

checkpoint-1301/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b30c4d8f195ad17409c60a6061fe988f95932b2bc20a0ba91769986beb987e2
+size 3055544304

checkpoint-1301/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd808ed3c4749f47c4eb66c22dacb355323082d8b21b9c9cb9a35bdb5fe19a30
+size 6111697804

checkpoint-1301/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "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,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

checkpoint-1301/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:922703b76f16a3621b9938d26bcd34ae3df3df20f00bf96c30623a87455327be
+size 16389

checkpoint-1301/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db001b611791a1d79823cfb761e4b611b36401e7b1d986cb0290a0d8c6d5933d
+size 16389

checkpoint-1301/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:385e4f47213365173508f52a36703225379cdfda0386750104eacc9f62d45f2b
+size 16389

checkpoint-1301/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:823c438ad0862766a508dde1042fae55c6ff0231d394d15753d60687ceeee549
+size 16389

checkpoint-1301/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c96969351c1a2ce0e82dac94200f611740bc87e2d23bb54e34bd8315c9450d5f
+size 16389

checkpoint-1301/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d4a5beb33bc575f79d043c72bda5211234e44f497bd491cf0d0bd0893b2c86
+size 16389

checkpoint-1301/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e8b68bfd43416649c83ec36a227b7c0a5587be9fa6f8c781ee7b0beb3d82bf9
+size 16389

checkpoint-1301/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9647dc5dc73f77fdb90020e284e7ea969b0fd96c82d656c3b41ec98d7cefe40
+size 16389

checkpoint-1301/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c4ab99fb5d6eb17d08f18d1bbbbd0aa06b521d49952102885c7fa2ecdfa321d
+size 1465

checkpoint-1301/trainer_state.json

@@ -0,0 +1,216 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1301,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03843197540353574,
+      "grad_norm": 24.96473503112793,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 6.548916015625,
+      "step": 50
+    },
+    {
+      "epoch": 0.07686395080707148,
+      "grad_norm": 15.567505836486816,
+      "learning_rate": 1.4142857142857144e-06,
+      "loss": 4.4738397216796875,
+      "step": 100
+    },
+    {
+      "epoch": 0.11529592621060722,
+      "grad_norm": 13.502691268920898,
+      "learning_rate": 2.1285714285714287e-06,
+      "loss": 3.2899395751953127,
+      "step": 150
+    },
+    {
+      "epoch": 0.15372790161414296,
+      "grad_norm": 9.215691566467285,
+      "learning_rate": 2.8428571428571432e-06,
+      "loss": 2.035605621337891,
+      "step": 200
+    },
+    {
+      "epoch": 0.1921598770176787,
+      "grad_norm": 9.399081230163574,
+      "learning_rate": 3.5571428571428573e-06,
+      "loss": 1.7253753662109375,
+      "step": 250
+    },
+    {
+      "epoch": 0.23059185242121444,
+      "grad_norm": 9.485953330993652,
+      "learning_rate": 4.271428571428572e-06,
+      "loss": 1.5824163818359376,
+      "step": 300
+    },
+    {
+      "epoch": 0.2690238278247502,
+      "grad_norm": 8.881640434265137,
+      "learning_rate": 4.9857142857142855e-06,
+      "loss": 1.4994566345214844,
+      "step": 350
+    },
+    {
+      "epoch": 0.3074558032282859,
+      "grad_norm": 9.438455581665039,
+      "learning_rate": 5.7e-06,
+      "loss": 1.4217744445800782,
+      "step": 400
+    },
+    {
+      "epoch": 0.3458877786318217,
+      "grad_norm": 8.401183128356934,
+      "learning_rate": 6.4142857142857154e-06,
+      "loss": 1.378076934814453,
+      "step": 450
+    },
+    {
+      "epoch": 0.3843197540353574,
+      "grad_norm": 9.6310396194458,
+      "learning_rate": 7.1285714285714295e-06,
+      "loss": 1.3310549926757813,
+      "step": 500
+    },
+    {
+      "epoch": 0.42275172943889316,
+      "grad_norm": 9.117944717407227,
+      "learning_rate": 7.842857142857143e-06,
+      "loss": 1.2295526123046876,
+      "step": 550
+    },
+    {
+      "epoch": 0.4611837048424289,
+      "grad_norm": 7.5970072746276855,
+      "learning_rate": 8.557142857142858e-06,
+      "loss": 1.2381634521484375,
+      "step": 600
+    },
+    {
+      "epoch": 0.49961568024596464,
+      "grad_norm": 8.406278610229492,
+      "learning_rate": 9.271428571428573e-06,
+      "loss": 1.2207740783691405,
+      "step": 650
+    },
+    {
+      "epoch": 0.5380476556495004,
+      "grad_norm": 7.469017028808594,
+      "learning_rate": 9.985714285714286e-06,
+      "loss": 1.2070553588867188,
+      "step": 700
+    },
+    {
+      "epoch": 0.5764796310530361,
+      "grad_norm": 7.842820167541504,
+      "learning_rate": 9.960194963444355e-06,
+      "loss": 1.1306779479980469,
+      "step": 750
+    },
+    {
+      "epoch": 0.6149116064565718,
+      "grad_norm": 8.229959487915039,
+      "learning_rate": 9.9195775792039e-06,
+      "loss": 1.140580825805664,
+      "step": 800
+    },
+    {
+      "epoch": 0.6533435818601077,
+      "grad_norm": 7.585798740386963,
+      "learning_rate": 9.878960194963446e-06,
+      "loss": 1.105696334838867,
+      "step": 850
+    },
+    {
+      "epoch": 0.6917755572636434,
+      "grad_norm": 7.848736763000488,
+      "learning_rate": 9.838342810722991e-06,
+      "loss": 1.0822959899902345,
+      "step": 900
+    },
+    {
+      "epoch": 0.7302075326671791,
+      "grad_norm": 7.353982448577881,
+      "learning_rate": 9.797725426482535e-06,
+      "loss": 1.0581134796142577,
+      "step": 950
+    },
+    {
+      "epoch": 0.7686395080707148,
+      "grad_norm": 6.863584518432617,
+      "learning_rate": 9.75710804224208e-06,
+      "loss": 1.0602525329589845,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8070714834742506,
+      "grad_norm": 7.096811294555664,
+      "learning_rate": 9.716490658001624e-06,
+      "loss": 1.045466766357422,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8455034588777863,
+      "grad_norm": 7.295511245727539,
+      "learning_rate": 9.67587327376117e-06,
+      "loss": 1.0288179016113281,
+      "step": 1100
+    },
+    {
+      "epoch": 0.883935434281322,
+      "grad_norm": 6.594845771789551,
+      "learning_rate": 9.635255889520715e-06,
+      "loss": 1.0182283782958985,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9223674096848578,
+      "grad_norm": 6.083802700042725,
+      "learning_rate": 9.594638505280261e-06,
+      "loss": 1.0005873107910157,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9607993850883936,
+      "grad_norm": 6.480014801025391,
+      "learning_rate": 9.554021121039807e-06,
+      "loss": 1.0233656311035155,
+      "step": 1250
+    },
+    {
+      "epoch": 0.9992313604919293,
+      "grad_norm": 7.135806083679199,
+      "learning_rate": 9.51340373679935e-06,
+      "loss": 1.0027877807617187,
+      "step": 1300
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 13010,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6995929579968895e+20,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1301/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee3bcd14a0b55278a89671dd7c00d9c4f80d655c6b999121882d6d90242f8b0
+size 5329