Training in progress, step 45, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "bofenghuang/whisper-large-v3-french",
+  "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": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.05,
+  "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": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,256 @@
+{
+  "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,
+  "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": "french",
+  "max_initial_timestamp_index": 1,
+  "max_length": 448,
+  "no_timestamps_token_id": 50364,
+  "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,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.44.2"
+}

last-checkpoint/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:136aaac03e9d76cd1348df695814bed28652b20e0fa4648e20701e392a6ae989
+size 4993448880

last-checkpoint/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd9dd8efe5536c464c83e5269170a2dbc43f2538c7df60259bf4e03174c8e6e
+size 1180663192

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ce15fe41a7453085bcda5984c5e51715054f45c901b0653def326046fda8fc
+size 12333660476

last-checkpoint/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "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
+}

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97a171fb2792666e67f18bce12c4b2862ee26c37dcd62701789ac0e99ad23b2
+size 15984

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586529547f2ee5d9085ff31c92b08050f8f8117a1f4dd38ca10669c063663963
+size 15984

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9012ff54b350a810b7d0de148e490d5dce337289be45e3ac50b6d9063c1796ee
+size 15984

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216fcc833b2104ef6ca49e67a58555cf8ca00f937c97320f754ad60e737cacfe
+size 15984

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc8c29ba8b5f3540460bf5faf04472f1ff9cdbec422a29381ccdbc3aab18bdd
+size 15984

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c184dca57c75c916dcf080520944a1033b875cc56402d585cd34174789a49f
+size 15984

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc637152896cae2051b4b5050c18ba52844c6c9aec5072d4a18116534fdf4680
+size 15984

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55dc5ecad8620cd564c42ca1861f86bff06a7a8d41c237b865e054ebc08ff619
+size 15984

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28cd49e70cf75978d3b28339cf8bc7b7b0cadfaac3f28de30e15cbc23c18fb4c
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,357 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.903225806451613,
+  "eval_steps": 25,
+  "global_step": 45,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": 16.263925552368164,
+      "learning_rate": 2e-08,
+      "loss": 1.0729,
+      "step": 1
+    },
+    {
+      "epoch": 0.12903225806451613,
+      "grad_norm": 15.569890975952148,
+      "learning_rate": 4e-08,
+      "loss": 1.0929,
+      "step": 2
+    },
+    {
+      "epoch": 0.1935483870967742,
+      "grad_norm": 15.694029808044434,
+      "learning_rate": 6.000000000000001e-08,
+      "loss": 1.0362,
+      "step": 3
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 15.513921737670898,
+      "learning_rate": 8e-08,
+      "loss": 1.0052,
+      "step": 4
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 15.743331909179688,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 1.1178,
+      "step": 5
+    },
+    {
+      "epoch": 0.3870967741935484,
+      "grad_norm": 16.06720733642578,
+      "learning_rate": 1.2000000000000002e-07,
+      "loss": 1.0321,
+      "step": 6
+    },
+    {
+      "epoch": 0.45161290322580644,
+      "grad_norm": 15.027511596679688,
+      "learning_rate": 1.4e-07,
+      "loss": 1.0152,
+      "step": 7
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 14.32020092010498,
+      "learning_rate": 1.6e-07,
+      "loss": 0.9654,
+      "step": 8
+    },
+    {
+      "epoch": 0.5806451612903226,
+      "grad_norm": 15.439043045043945,
+      "learning_rate": 1.8e-07,
+      "loss": 1.075,
+      "step": 9
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 14.999131202697754,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 1.0716,
+      "step": 10
+    },
+    {
+      "epoch": 0.7096774193548387,
+      "grad_norm": 16.290178298950195,
+      "learning_rate": 2.2e-07,
+      "loss": 1.0812,
+      "step": 11
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 14.786846160888672,
+      "learning_rate": 2.4000000000000003e-07,
+      "loss": 1.0195,
+      "step": 12
+    },
+    {
+      "epoch": 0.8387096774193549,
+      "grad_norm": 14.242819786071777,
+      "learning_rate": 2.6e-07,
+      "loss": 1.0387,
+      "step": 13
+    },
+    {
+      "epoch": 0.9032258064516129,
+      "grad_norm": 14.889954566955566,
+      "learning_rate": 2.8e-07,
+      "loss": 1.0225,
+      "step": 14
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 14.033804893493652,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 1.0133,
+      "step": 15
+    },
+    {
+      "epoch": 1.032258064516129,
+      "grad_norm": 12.08979606628418,
+      "learning_rate": 3.2e-07,
+      "loss": 0.9071,
+      "step": 16
+    },
+    {
+      "epoch": 1.096774193548387,
+      "grad_norm": 12.912490844726562,
+      "learning_rate": 3.4000000000000003e-07,
+      "loss": 0.9406,
+      "step": 17
+    },
+    {
+      "epoch": 1.1612903225806452,
+      "grad_norm": 11.380302429199219,
+      "learning_rate": 3.6e-07,
+      "loss": 0.8034,
+      "step": 18
+    },
+    {
+      "epoch": 1.2258064516129032,
+      "grad_norm": 10.891118049621582,
+      "learning_rate": 3.8e-07,
+      "loss": 0.8207,
+      "step": 19
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 10.069238662719727,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 0.7648,
+      "step": 20
+    },
+    {
+      "epoch": 1.3548387096774195,
+      "grad_norm": 9.952157020568848,
+      "learning_rate": 4.2000000000000006e-07,
+      "loss": 0.7792,
+      "step": 21
+    },
+    {
+      "epoch": 1.4193548387096775,
+      "grad_norm": 7.719379901885986,
+      "learning_rate": 4.4e-07,
+      "loss": 0.713,
+      "step": 22
+    },
+    {
+      "epoch": 1.4838709677419355,
+      "grad_norm": 7.5698652267456055,
+      "learning_rate": 4.6000000000000004e-07,
+      "loss": 0.6835,
+      "step": 23
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 7.659738540649414,
+      "learning_rate": 4.800000000000001e-07,
+      "loss": 0.6648,
+      "step": 24
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 6.6802978515625,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.5569,
+      "step": 25
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "eval_loss": 0.6629915237426758,
+      "eval_runtime": 31.5479,
+      "eval_samples_per_second": 1.268,
+      "eval_steps_per_second": 0.063,
+      "eval_wer": 27.715877437325904,
+      "step": 25
+    },
+    {
+      "epoch": 1.6774193548387095,
+      "grad_norm": 6.86961555480957,
+      "learning_rate": 5.2e-07,
+      "loss": 0.554,
+      "step": 26
+    },
+    {
+      "epoch": 1.7419354838709677,
+      "grad_norm": 6.661825180053711,
+      "learning_rate": 5.4e-07,
+      "loss": 0.5482,
+      "step": 27
+    },
+    {
+      "epoch": 1.8064516129032258,
+      "grad_norm": 6.358301639556885,
+      "learning_rate": 5.6e-07,
+      "loss": 0.5294,
+      "step": 28
+    },
+    {
+      "epoch": 1.870967741935484,
+      "grad_norm": 5.148527145385742,
+      "learning_rate": 5.800000000000001e-07,
+      "loss": 0.4651,
+      "step": 29
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 4.679035663604736,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.489,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.639977931976318,
+      "learning_rate": 6.200000000000001e-07,
+      "loss": 0.4821,
+      "step": 31
+    },
+    {
+      "epoch": 2.064516129032258,
+      "grad_norm": 3.959872007369995,
+      "learning_rate": 6.4e-07,
+      "loss": 0.3762,
+      "step": 32
+    },
+    {
+      "epoch": 2.129032258064516,
+      "grad_norm": 3.4068374633789062,
+      "learning_rate": 6.6e-07,
+      "loss": 0.3502,
+      "step": 33
+    },
+    {
+      "epoch": 2.193548387096774,
+      "grad_norm": 3.4941601753234863,
+      "learning_rate": 6.800000000000001e-07,
+      "loss": 0.4505,
+      "step": 34
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 2.954697370529175,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 0.4029,
+      "step": 35
+    },
+    {
+      "epoch": 2.3225806451612905,
+      "grad_norm": 2.55094838142395,
+      "learning_rate": 7.2e-07,
+      "loss": 0.2733,
+      "step": 36
+    },
+    {
+      "epoch": 2.3870967741935485,
+      "grad_norm": 2.4865736961364746,
+      "learning_rate": 7.4e-07,
+      "loss": 0.2705,
+      "step": 37
+    },
+    {
+      "epoch": 2.4516129032258065,
+      "grad_norm": 2.5212318897247314,
+      "learning_rate": 7.6e-07,
+      "loss": 0.2608,
+      "step": 38
+    },
+    {
+      "epoch": 2.5161290322580645,
+      "grad_norm": 2.3191308975219727,
+      "learning_rate": 7.8e-07,
+      "loss": 0.276,
+      "step": 39
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 2.3392505645751953,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 0.2623,
+      "step": 40
+    },
+    {
+      "epoch": 2.6451612903225805,
+      "grad_norm": 2.3466882705688477,
+      "learning_rate": 8.200000000000001e-07,
+      "loss": 0.3,
+      "step": 41
+    },
+    {
+      "epoch": 2.709677419354839,
+      "grad_norm": 2.310439109802246,
+      "learning_rate": 8.400000000000001e-07,
+      "loss": 0.2774,
+      "step": 42
+    },
+    {
+      "epoch": 2.774193548387097,
+      "grad_norm": 2.1097171306610107,
+      "learning_rate": 8.6e-07,
+      "loss": 0.3094,
+      "step": 43
+    },
+    {
+      "epoch": 2.838709677419355,
+      "grad_norm": 2.0742061138153076,
+      "learning_rate": 8.8e-07,
+      "loss": 0.2375,
+      "step": 44
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 2.2318801879882812,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 0.2883,
+      "step": 45
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 45,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9569589502890476e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898b3f82ddf2ce5a61ebc637223b078f8d8d696b5da1406ae04e69cde773dd9b
+size 5432