Upload epoch_1 checkpoint

epoch_1/config.json

@@ -0,0 +1,59 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "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_hidden_layers": 24,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

epoch_1/generation_config.json

@@ -0,0 +1,268 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "encoder_repetition_penalty": 1.0,
+  "eos_token_id": 50257,
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  "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",
+  "length_penalty": 1.0,
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "no_timestamps_token_id": 50363,
+  "num_assistant_tokens": 20,
+  "num_assistant_tokens_schedule": "constant",
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "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
+  ],
+  "target_lookbehind": 10,
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.3.0",
+  "typical_p": 1.0,
+  "use_cache": true
+}

epoch_1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d0093e7814048ec4e174db0e0334b77055185ead1b05db7d5462ae8493aae37
+size 3055544304

epoch_1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb1d69e7529095311ac58ad4fce47936f558d381ab9adeb215a84d4e52c4a6ce
+size 6111664103

epoch_1/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
+}

epoch_1/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d2872bbf2fe421153c33cba24bcd331b63744af0fad4f1c4b7bff5c592adf6b
+size 15728

epoch_1/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93bebc8a433b23f0be924f8c1227ed9a26e1df5a47fb4d702b02067d642367dd
+size 15728

epoch_1/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b1bba981fafc1bac2742000863b05a08fa588fc00d0da221882e922eee4142
+size 15728

epoch_1/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e746df61af8766201639c1ec027afb9b36c01e1db0321429faa0fab9f36336
+size 15728

epoch_1/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4aa9a57f3f124adf5df4dc334ab891b934a0cd47037c33b7ff8909ead65dab
+size 15728

epoch_1/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5c5aa3dbdb44c3bc59311f6a1a30b9b234fefc3960aeecddce855a2a575d12
+size 15728

epoch_1/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a8943ca4c355cce508e21b07bcb991a848aa5c4857996e67ea9c072f576ef9
+size 15728

epoch_1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:666e7231f4fdfcea31839b69cc565889eab525e6f0790bc11fe8a1d359666323
+size 1064

epoch_1/tokenizer_config.json

@@ -0,0 +1,127 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "<|startoftranscript|>",
+    "<|en|>",
+    "<|zh|>",
+    "<|de|>",
+    "<|es|>",
+    "<|ru|>",
+    "<|ko|>",
+    "<|fr|>",
+    "<|ja|>",
+    "<|pt|>",
+    "<|tr|>",
+    "<|pl|>",
+    "<|ca|>",
+    "<|nl|>",
+    "<|ar|>",
+    "<|sv|>",
+    "<|it|>",
+    "<|id|>",
+    "<|hi|>",
+    "<|fi|>",
+    "<|vi|>",
+    "<|he|>",
+    "<|uk|>",
+    "<|el|>",
+    "<|ms|>",
+    "<|cs|>",
+    "<|ro|>",
+    "<|da|>",
+    "<|hu|>",
+    "<|ta|>",
+    "<|no|>",
+    "<|th|>",
+    "<|ur|>",
+    "<|hr|>",
+    "<|bg|>",
+    "<|lt|>",
+    "<|la|>",
+    "<|mi|>",
+    "<|ml|>",
+    "<|cy|>",
+    "<|sk|>",
+    "<|te|>",
+    "<|fa|>",
+    "<|lv|>",
+    "<|bn|>",
+    "<|sr|>",
+    "<|az|>",
+    "<|sl|>",
+    "<|kn|>",
+    "<|et|>",
+    "<|mk|>",
+    "<|br|>",
+    "<|eu|>",
+    "<|is|>",
+    "<|hy|>",
+    "<|ne|>",
+    "<|mn|>",
+    "<|bs|>",
+    "<|kk|>",
+    "<|sq|>",
+    "<|sw|>",
+    "<|gl|>",
+    "<|mr|>",
+    "<|pa|>",
+    "<|si|>",
+    "<|km|>",
+    "<|sn|>",
+    "<|yo|>",
+    "<|so|>",
+    "<|af|>",
+    "<|oc|>",
+    "<|ka|>",
+    "<|be|>",
+    "<|tg|>",
+    "<|sd|>",
+    "<|gu|>",
+    "<|am|>",
+    "<|yi|>",
+    "<|lo|>",
+    "<|uz|>",
+    "<|fo|>",
+    "<|ht|>",
+    "<|ps|>",
+    "<|tk|>",
+    "<|nn|>",
+    "<|mt|>",
+    "<|sa|>",
+    "<|lb|>",
+    "<|my|>",
+    "<|bo|>",
+    "<|tl|>",
+    "<|mg|>",
+    "<|as|>",
+    "<|tt|>",
+    "<|haw|>",
+    "<|ln|>",
+    "<|ha|>",
+    "<|ba|>",
+    "<|jw|>",
+    "<|su|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nocaptions|>",
+    "<|notimestamps|>"
+  ],
+  "is_local": false,
+  "language": "hindi",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "predict_timestamps": false,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "task": "transcribe",
+  "tokenizer_class": "WhisperTokenizer",
+  "unk_token": "<|endoftext|>"
+}

epoch_1/trainer_state.json

@@ -0,0 +1,409 @@
+{
+  "best_global_step": 1298,
+  "best_metric": 23.27414889831906,
+  "best_model_checkpoint": "./whisper_s_punjabi_ddp_4gpu/checkpoint-1298",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1298,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01926040061633282,
+      "grad_norm": 58.414207458496094,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 7.913150634765625,
+      "step": 25
+    },
+    {
+      "epoch": 0.03852080123266564,
+      "grad_norm": 18.150222778320312,
+      "learning_rate": 1.6333333333333335e-06,
+      "loss": 5.986227416992188,
+      "step": 50
+    },
+    {
+      "epoch": 0.05778120184899846,
+      "grad_norm": 14.175592422485352,
+      "learning_rate": 2.466666666666667e-06,
+      "loss": 4.43172119140625,
+      "step": 75
+    },
+    {
+      "epoch": 0.07704160246533127,
+      "grad_norm": 16.95926284790039,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 3.4311566162109375,
+      "step": 100
+    },
+    {
+      "epoch": 0.0963020030816641,
+      "grad_norm": 9.69564151763916,
+      "learning_rate": 4.133333333333333e-06,
+      "loss": 2.0594117736816404,
+      "step": 125
+    },
+    {
+      "epoch": 0.11556240369799692,
+      "grad_norm": 10.076292991638184,
+      "learning_rate": 4.966666666666667e-06,
+      "loss": 1.8318702697753906,
+      "step": 150
+    },
+    {
+      "epoch": 0.13482280431432975,
+      "grad_norm": 9.035318374633789,
+      "learning_rate": 5.8e-06,
+      "loss": 1.7396725463867186,
+      "step": 175
+    },
+    {
+      "epoch": 0.15408320493066255,
+      "grad_norm": 10.635228157043457,
+      "learning_rate": 6.633333333333334e-06,
+      "loss": 1.6932928466796875,
+      "step": 200
+    },
+    {
+      "epoch": 0.17334360554699538,
+      "grad_norm": 10.217312812805176,
+      "learning_rate": 7.4666666666666675e-06,
+      "loss": 1.6321292114257813,
+      "step": 225
+    },
+    {
+      "epoch": 0.1926040061633282,
+      "grad_norm": 11.088924407958984,
+      "learning_rate": 8.3e-06,
+      "loss": 1.5770054626464844,
+      "step": 250
+    },
+    {
+      "epoch": 0.211864406779661,
+      "grad_norm": 10.08351993560791,
+      "learning_rate": 9.133333333333335e-06,
+      "loss": 1.5158828735351562,
+      "step": 275
+    },
+    {
+      "epoch": 0.23112480739599384,
+      "grad_norm": 9.66342544555664,
+      "learning_rate": 9.966666666666667e-06,
+      "loss": 1.5335569763183594,
+      "step": 300
+    },
+    {
+      "epoch": 0.25038520801232667,
+      "grad_norm": 10.034809112548828,
+      "learning_rate": 9.981072555205049e-06,
+      "loss": 1.4476705932617187,
+      "step": 325
+    },
+    {
+      "epoch": 0.2696456086286595,
+      "grad_norm": 7.876269817352295,
+      "learning_rate": 9.961356466876972e-06,
+      "loss": 1.4681803894042968,
+      "step": 350
+    },
+    {
+      "epoch": 0.2889060092449923,
+      "grad_norm": 10.250846862792969,
+      "learning_rate": 9.941640378548896e-06,
+      "loss": 1.437877197265625,
+      "step": 375
+    },
+    {
+      "epoch": 0.3081664098613251,
+      "grad_norm": 9.018561363220215,
+      "learning_rate": 9.921924290220821e-06,
+      "loss": 1.3937382507324219,
+      "step": 400
+    },
+    {
+      "epoch": 0.3274268104776579,
+      "grad_norm": 8.793310165405273,
+      "learning_rate": 9.902208201892746e-06,
+      "loss": 1.3915924072265624,
+      "step": 425
+    },
+    {
+      "epoch": 0.34668721109399075,
+      "grad_norm": 9.753164291381836,
+      "learning_rate": 9.88249211356467e-06,
+      "loss": 1.3350201416015626,
+      "step": 450
+    },
+    {
+      "epoch": 0.3659476117103236,
+      "grad_norm": 9.90793514251709,
+      "learning_rate": 9.862776025236594e-06,
+      "loss": 1.3452024841308594,
+      "step": 475
+    },
+    {
+      "epoch": 0.3852080123266564,
+      "grad_norm": 7.425978660583496,
+      "learning_rate": 9.843059936908518e-06,
+      "loss": 1.3636004638671875,
+      "step": 500
+    },
+    {
+      "epoch": 0.40446841294298924,
+      "grad_norm": 7.5032501220703125,
+      "learning_rate": 9.823343848580441e-06,
+      "loss": 1.337528076171875,
+      "step": 525
+    },
+    {
+      "epoch": 0.423728813559322,
+      "grad_norm": 8.89260482788086,
+      "learning_rate": 9.803627760252366e-06,
+      "loss": 1.3338491821289062,
+      "step": 550
+    },
+    {
+      "epoch": 0.44298921417565484,
+      "grad_norm": 8.321249008178711,
+      "learning_rate": 9.783911671924291e-06,
+      "loss": 1.333787384033203,
+      "step": 575
+    },
+    {
+      "epoch": 0.4622496147919877,
+      "grad_norm": 8.888858795166016,
+      "learning_rate": 9.764195583596216e-06,
+      "loss": 1.3222378540039061,
+      "step": 600
+    },
+    {
+      "epoch": 0.4815100154083205,
+      "grad_norm": 7.648203372955322,
+      "learning_rate": 9.74447949526814e-06,
+      "loss": 1.3167262268066406,
+      "step": 625
+    },
+    {
+      "epoch": 0.5007704160246533,
+      "grad_norm": 6.553903102874756,
+      "learning_rate": 9.724763406940063e-06,
+      "loss": 1.298903045654297,
+      "step": 650
+    },
+    {
+      "epoch": 0.5200308166409862,
+      "grad_norm": 7.545315265655518,
+      "learning_rate": 9.705047318611988e-06,
+      "loss": 1.266801223754883,
+      "step": 675
+    },
+    {
+      "epoch": 0.539291217257319,
+      "grad_norm": 7.492407321929932,
+      "learning_rate": 9.685331230283911e-06,
+      "loss": 1.2619186401367188,
+      "step": 700
+    },
+    {
+      "epoch": 0.5585516178736518,
+      "grad_norm": 6.489583969116211,
+      "learning_rate": 9.665615141955836e-06,
+      "loss": 1.2714739990234376,
+      "step": 725
+    },
+    {
+      "epoch": 0.5778120184899846,
+      "grad_norm": 8.90630054473877,
+      "learning_rate": 9.64589905362776e-06,
+      "loss": 1.2946762084960937,
+      "step": 750
+    },
+    {
+      "epoch": 0.5970724191063174,
+      "grad_norm": 7.635409832000732,
+      "learning_rate": 9.626182965299686e-06,
+      "loss": 1.269822463989258,
+      "step": 775
+    },
+    {
+      "epoch": 0.6163328197226502,
+      "grad_norm": 7.459207534790039,
+      "learning_rate": 9.60646687697161e-06,
+      "loss": 1.2825979614257812,
+      "step": 800
+    },
+    {
+      "epoch": 0.635593220338983,
+      "grad_norm": 8.159686088562012,
+      "learning_rate": 9.586750788643533e-06,
+      "loss": 1.2717716217041015,
+      "step": 825
+    },
+    {
+      "epoch": 0.6548536209553159,
+      "grad_norm": 6.630347728729248,
+      "learning_rate": 9.567034700315458e-06,
+      "loss": 1.252648162841797,
+      "step": 850
+    },
+    {
+      "epoch": 0.6741140215716487,
+      "grad_norm": 7.215192794799805,
+      "learning_rate": 9.547318611987383e-06,
+      "loss": 1.252330093383789,
+      "step": 875
+    },
+    {
+      "epoch": 0.6933744221879815,
+      "grad_norm": 8.178110122680664,
+      "learning_rate": 9.527602523659308e-06,
+      "loss": 1.2153298187255859,
+      "step": 900
+    },
+    {
+      "epoch": 0.7126348228043143,
+      "grad_norm": 6.375010013580322,
+      "learning_rate": 9.50788643533123e-06,
+      "loss": 1.2400372314453125,
+      "step": 925
+    },
+    {
+      "epoch": 0.7318952234206472,
+      "grad_norm": 8.464449882507324,
+      "learning_rate": 9.488170347003155e-06,
+      "loss": 1.2374497222900391,
+      "step": 950
+    },
+    {
+      "epoch": 0.75115562403698,
+      "grad_norm": 6.5914764404296875,
+      "learning_rate": 9.46845425867508e-06,
+      "loss": 1.2367049407958985,
+      "step": 975
+    },
+    {
+      "epoch": 0.7704160246533128,
+      "grad_norm": 6.147579193115234,
+      "learning_rate": 9.448738170347003e-06,
+      "loss": 1.2031460571289063,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7896764252696457,
+      "grad_norm": 6.786445617675781,
+      "learning_rate": 9.429022082018928e-06,
+      "loss": 1.1893964385986329,
+      "step": 1025
+    },
+    {
+      "epoch": 0.8089368258859785,
+      "grad_norm": 5.8521504402160645,
+      "learning_rate": 9.409305993690853e-06,
+      "loss": 1.1855683898925782,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8281972265023112,
+      "grad_norm": 5.927206993103027,
+      "learning_rate": 9.389589905362777e-06,
+      "loss": 1.2393891906738281,
+      "step": 1075
+    },
+    {
+      "epoch": 0.847457627118644,
+      "grad_norm": 7.765108108520508,
+      "learning_rate": 9.369873817034702e-06,
+      "loss": 1.2078982543945314,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8667180277349769,
+      "grad_norm": 6.578537464141846,
+      "learning_rate": 9.350157728706625e-06,
+      "loss": 1.2135992431640625,
+      "step": 1125
+    },
+    {
+      "epoch": 0.8859784283513097,
+      "grad_norm": 6.826841831207275,
+      "learning_rate": 9.33044164037855e-06,
+      "loss": 1.2246592712402344,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9052388289676425,
+      "grad_norm": 5.9232611656188965,
+      "learning_rate": 9.310725552050473e-06,
+      "loss": 1.2366727447509767,
+      "step": 1175
+    },
+    {
+      "epoch": 0.9244992295839753,
+      "grad_norm": 6.405348777770996,
+      "learning_rate": 9.291009463722398e-06,
+      "loss": 1.1822604370117187,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9437596302003082,
+      "grad_norm": 7.846672534942627,
+      "learning_rate": 9.271293375394322e-06,
+      "loss": 1.1902696228027343,
+      "step": 1225
+    },
+    {
+      "epoch": 0.963020030816641,
+      "grad_norm": 6.556903839111328,
+      "learning_rate": 9.251577287066247e-06,
+      "loss": 1.2147691345214844,
+      "step": 1250
+    },
+    {
+      "epoch": 0.9822804314329738,
+      "grad_norm": 6.414576530456543,
+      "learning_rate": 9.231861198738172e-06,
+      "loss": 1.1895433044433594,
+      "step": 1275
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1692090779542923,
+      "eval_runtime": 1293.6351,
+      "eval_samples_per_second": 18.724,
+      "eval_steps_per_second": 0.084,
+      "eval_wer": 23.27414889831906,
+      "step": 1298
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 12980,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.225571898389535e+20,
+  "train_batch_size": 24,
+  "trial_name": null,
+  "trial_params": null
+}

epoch_1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e155e74e3785317024df094dc43f1bddfeb30257cc366390dc0635ed1f1d3b
+size 4984