Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,49 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "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": 4,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "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_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": 50257,
+  "scale_embedding": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

generation_config.json

@@ -0,0 +1,153 @@
+{
+  "alignment_heads": [
+    [
+      2,
+      4
+    ],
+    [
+      2,
+      11
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      6
+    ],
+    [
+      3,
+      11
+    ],
+    [
+      3,
+      14
+    ]
+  ],
+  "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,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "language": null,
+  "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": [],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.57.6"
+}

last-checkpoint/config.json

@@ -0,0 +1,49 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "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": 4,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "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_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": 50257,
+  "scale_embedding": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,153 @@
+{
+  "alignment_heads": [
+    [
+      2,
+      4
+    ],
+    [
+      2,
+      11
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      6
+    ],
+    [
+      3,
+      11
+    ],
+    [
+      3,
+      14
+    ]
+  ],
+  "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,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "language": null,
+  "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": [],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.57.6"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a56e81ab23069fbc84195cd9cd9762105457218ac981b3737121e7de157135d
+size 3235581408

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad546a58334e69a8a870e95ac7a4069c0eb495da97ac93ed045441bf4b5270c
+size 6456162404

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e705f7675b2c80315b5cd86571ad816699bf1cc7133e8dc09788ff9f72a51ea
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4685d01f9af7705ed368c2e14746c924e8ab5b543491c7aaf3a485ffd2286367
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,332 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 37.735849056603776,
+  "eval_steps": 1000,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 10.858407020568848,
+      "learning_rate": 6.125000000000001e-07,
+      "loss": 1.1316,
+      "step": 50
+    },
+    {
+      "epoch": 1.8867924528301887,
+      "grad_norm": 8.325432777404785,
+      "learning_rate": 1.2375e-06,
+      "loss": 0.7915,
+      "step": 100
+    },
+    {
+      "epoch": 2.830188679245283,
+      "grad_norm": 7.2042646408081055,
+      "learning_rate": 1.8625000000000002e-06,
+      "loss": 0.6265,
+      "step": 150
+    },
+    {
+      "epoch": 3.7735849056603774,
+      "grad_norm": 6.165217399597168,
+      "learning_rate": 2.4875000000000003e-06,
+      "loss": 0.4784,
+      "step": 200
+    },
+    {
+      "epoch": 4.716981132075472,
+      "grad_norm": 7.30438756942749,
+      "learning_rate": 3.1125000000000007e-06,
+      "loss": 0.3557,
+      "step": 250
+    },
+    {
+      "epoch": 5.660377358490566,
+      "grad_norm": 6.9144978523254395,
+      "learning_rate": 3.7375000000000006e-06,
+      "loss": 0.2607,
+      "step": 300
+    },
+    {
+      "epoch": 6.60377358490566,
+      "grad_norm": 3.8254449367523193,
+      "learning_rate": 4.362500000000001e-06,
+      "loss": 0.1868,
+      "step": 350
+    },
+    {
+      "epoch": 7.547169811320755,
+      "grad_norm": 6.7695722579956055,
+      "learning_rate": 4.987500000000001e-06,
+      "loss": 0.129,
+      "step": 400
+    },
+    {
+      "epoch": 8.49056603773585,
+      "grad_norm": 3.909433364868164,
+      "learning_rate": 4.974479166666667e-06,
+      "loss": 0.0836,
+      "step": 450
+    },
+    {
+      "epoch": 9.433962264150944,
+      "grad_norm": 2.8024463653564453,
+      "learning_rate": 4.948437500000001e-06,
+      "loss": 0.0623,
+      "step": 500
+    },
+    {
+      "epoch": 10.377358490566039,
+      "grad_norm": 3.1148290634155273,
+      "learning_rate": 4.922395833333334e-06,
+      "loss": 0.0449,
+      "step": 550
+    },
+    {
+      "epoch": 11.320754716981131,
+      "grad_norm": 3.5211942195892334,
+      "learning_rate": 4.896354166666667e-06,
+      "loss": 0.0326,
+      "step": 600
+    },
+    {
+      "epoch": 12.264150943396226,
+      "grad_norm": 2.1357016563415527,
+      "learning_rate": 4.870312500000001e-06,
+      "loss": 0.025,
+      "step": 650
+    },
+    {
+      "epoch": 13.20754716981132,
+      "grad_norm": 1.8676131963729858,
+      "learning_rate": 4.844270833333334e-06,
+      "loss": 0.0178,
+      "step": 700
+    },
+    {
+      "epoch": 14.150943396226415,
+      "grad_norm": 0.7540724873542786,
+      "learning_rate": 4.818229166666667e-06,
+      "loss": 0.0163,
+      "step": 750
+    },
+    {
+      "epoch": 15.09433962264151,
+      "grad_norm": 1.1834070682525635,
+      "learning_rate": 4.7921875000000004e-06,
+      "loss": 0.0126,
+      "step": 800
+    },
+    {
+      "epoch": 16.037735849056602,
+      "grad_norm": 0.48137524724006653,
+      "learning_rate": 4.766145833333333e-06,
+      "loss": 0.0107,
+      "step": 850
+    },
+    {
+      "epoch": 16.9811320754717,
+      "grad_norm": 0.6699841022491455,
+      "learning_rate": 4.740104166666667e-06,
+      "loss": 0.0092,
+      "step": 900
+    },
+    {
+      "epoch": 17.92452830188679,
+      "grad_norm": 1.3291574716567993,
+      "learning_rate": 4.7140625e-06,
+      "loss": 0.0085,
+      "step": 950
+    },
+    {
+      "epoch": 18.867924528301888,
+      "grad_norm": 0.5217491388320923,
+      "learning_rate": 4.688020833333334e-06,
+      "loss": 0.0074,
+      "step": 1000
+    },
+    {
+      "epoch": 18.867924528301888,
+      "eval_loss": 0.8626004457473755,
+      "eval_runtime": 63.9053,
+      "eval_samples_per_second": 3.411,
+      "eval_steps_per_second": 0.11,
+      "eval_wer": 16.528681253696035,
+      "step": 1000
+    },
+    {
+      "epoch": 19.81132075471698,
+      "grad_norm": 2.132632255554199,
+      "learning_rate": 4.661979166666667e-06,
+      "loss": 0.0061,
+      "step": 1050
+    },
+    {
+      "epoch": 20.754716981132077,
+      "grad_norm": 7.051727294921875,
+      "learning_rate": 4.635937500000001e-06,
+      "loss": 0.0059,
+      "step": 1100
+    },
+    {
+      "epoch": 21.69811320754717,
+      "grad_norm": 0.7320095896720886,
+      "learning_rate": 4.609895833333334e-06,
+      "loss": 0.006,
+      "step": 1150
+    },
+    {
+      "epoch": 22.641509433962263,
+      "grad_norm": 0.42237502336502075,
+      "learning_rate": 4.583854166666667e-06,
+      "loss": 0.0057,
+      "step": 1200
+    },
+    {
+      "epoch": 23.58490566037736,
+      "grad_norm": 0.3902667462825775,
+      "learning_rate": 4.557812500000001e-06,
+      "loss": 0.0034,
+      "step": 1250
+    },
+    {
+      "epoch": 24.528301886792452,
+      "grad_norm": 3.1811842918395996,
+      "learning_rate": 4.531770833333334e-06,
+      "loss": 0.0049,
+      "step": 1300
+    },
+    {
+      "epoch": 25.471698113207548,
+      "grad_norm": 0.10800601541996002,
+      "learning_rate": 4.505729166666667e-06,
+      "loss": 0.0028,
+      "step": 1350
+    },
+    {
+      "epoch": 26.41509433962264,
+      "grad_norm": 0.05746890977025032,
+      "learning_rate": 4.4796875000000005e-06,
+      "loss": 0.0023,
+      "step": 1400
+    },
+    {
+      "epoch": 27.358490566037737,
+      "grad_norm": 4.796151161193848,
+      "learning_rate": 4.4536458333333334e-06,
+      "loss": 0.0028,
+      "step": 1450
+    },
+    {
+      "epoch": 28.30188679245283,
+      "grad_norm": 1.0416622161865234,
+      "learning_rate": 4.427604166666667e-06,
+      "loss": 0.0035,
+      "step": 1500
+    },
+    {
+      "epoch": 29.245283018867923,
+      "grad_norm": 0.33853980898857117,
+      "learning_rate": 4.4015625e-06,
+      "loss": 0.003,
+      "step": 1550
+    },
+    {
+      "epoch": 30.18867924528302,
+      "grad_norm": 0.7224472761154175,
+      "learning_rate": 4.375520833333334e-06,
+      "loss": 0.0034,
+      "step": 1600
+    },
+    {
+      "epoch": 31.132075471698112,
+      "grad_norm": 0.3685856759548187,
+      "learning_rate": 4.349479166666667e-06,
+      "loss": 0.0039,
+      "step": 1650
+    },
+    {
+      "epoch": 32.075471698113205,
+      "grad_norm": 0.12565827369689941,
+      "learning_rate": 4.323437500000001e-06,
+      "loss": 0.0053,
+      "step": 1700
+    },
+    {
+      "epoch": 33.0188679245283,
+      "grad_norm": 0.08283157646656036,
+      "learning_rate": 4.297395833333334e-06,
+      "loss": 0.004,
+      "step": 1750
+    },
+    {
+      "epoch": 33.9622641509434,
+      "grad_norm": 0.5767920613288879,
+      "learning_rate": 4.271354166666667e-06,
+      "loss": 0.0037,
+      "step": 1800
+    },
+    {
+      "epoch": 34.905660377358494,
+      "grad_norm": 0.04113687574863434,
+      "learning_rate": 4.245312500000001e-06,
+      "loss": 0.0024,
+      "step": 1850
+    },
+    {
+      "epoch": 35.84905660377358,
+      "grad_norm": 3.3687660694122314,
+      "learning_rate": 4.219270833333334e-06,
+      "loss": 0.0024,
+      "step": 1900
+    },
+    {
+      "epoch": 36.79245283018868,
+      "grad_norm": 0.05653538182377815,
+      "learning_rate": 4.193229166666667e-06,
+      "loss": 0.0019,
+      "step": 1950
+    },
+    {
+      "epoch": 37.735849056603776,
+      "grad_norm": 0.3379884362220764,
+      "learning_rate": 4.1671875000000005e-06,
+      "loss": 0.0016,
+      "step": 2000
+    },
+    {
+      "epoch": 37.735849056603776,
+      "eval_loss": 0.9562090635299683,
+      "eval_runtime": 34.7163,
+      "eval_samples_per_second": 6.279,
+      "eval_steps_per_second": 0.202,
+      "eval_wer": 17.593140153755176,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 189,
+  "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": 1.0728746118217728e+20,
+  "train_batch_size": 32,
+  "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:d638ca1122be1f997d7d290393818f1059d955ba8e44c5b8e19028875a4418aa
+size 5688

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a56e81ab23069fbc84195cd9cd9762105457218ac981b3737121e7de157135d
+size 3235581408

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d638ca1122be1f997d7d290393818f1059d955ba8e44c5b8e19028875a4418aa
+size 5688