diff --git a/checkpoint-1000/config.json b/checkpoint-1000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..337642e18341c758364c32c6b6159a090615329b
--- /dev/null
+++ b/checkpoint-1000/config.json
@@ -0,0 +1,47 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
diff --git a/checkpoint-1000/generation_config.json b/checkpoint-1000/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec4263613bc098f8eb01034b73fbe16fb43eba5c
--- /dev/null
+++ b/checkpoint-1000/generation_config.json
@@ -0,0 +1,175 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      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": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.51.3"
+}
diff --git a/checkpoint-1000/model.safetensors b/checkpoint-1000/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3bf7018eff7ee73d95174d3f50fa5e8611ec227c
--- /dev/null
+++ b/checkpoint-1000/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:516965ba5e615b23964c74658dc69b0b20127cc5e33a7e0f0f60b45805c48dbe
+size 966995080
diff --git a/checkpoint-1000/optimizer.pt b/checkpoint-1000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..97b39d531225b7f623bf7e6b834be03223040d5d
--- /dev/null
+++ b/checkpoint-1000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8ffcdd2d3002c7325f6bda25881965d45a68acda6014188e5992798d2bedec
+size 1925064044
diff --git a/checkpoint-1000/preprocessor_config.json b/checkpoint-1000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-1000/preprocessor_config.json
@@ -0,0 +1,15 @@
+{
+  "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,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-1000/rng_state.pth b/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4a1715dfa66f2d28c3e48d56767ce87b05adb078
--- /dev/null
+++ b/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:834c781436b196ed932372aaa6ec6dbfb0ebf83a994d376adbdcf25c4778b05e
+size 14244
diff --git a/checkpoint-1000/scaler.pt b/checkpoint-1000/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d3149e29009f0136e6e64a3c98e986c171494999
--- /dev/null
+++ b/checkpoint-1000/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a694eb2d6a253a859eb936acdef0e4e6559cd78dd4e08463d9a6ca4f6f44b832
+size 988
diff --git a/checkpoint-1000/scheduler.pt b/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..255a2596e6c2b16795fd4096583db2c9ee848379
--- /dev/null
+++ b/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76adde150b7edfb3ae13f98b035fa2e0eea67ff8b9245b007f253d93a74b937c
+size 1064
diff --git a/checkpoint-1000/trainer_state.json b/checkpoint-1000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..898657c16284fc7eeb6667a31f08dd7dd85ff15b
--- /dev/null
+++ b/checkpoint-1000/trainer_state.json
@@ -0,0 +1,429 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 38.00771402098731,
+  "best_model_checkpoint": "./HAUSA_B/checkpoint-1000",
+  "epoch": 1.3534190927555856,
+  "eval_steps": 200,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027081922816519974,
+      "grad_norm": 106.59215545654297,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 6.1915,
+      "step": 20
+    },
+    {
+      "epoch": 0.05416384563303995,
+      "grad_norm": 30.563518524169922,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 4.5886,
+      "step": 40
+    },
+    {
+      "epoch": 0.08124576844955991,
+      "grad_norm": 16.528457641601562,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 3.0338,
+      "step": 60
+    },
+    {
+      "epoch": 0.1083276912660799,
+      "grad_norm": 13.852096557617188,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.13540961408259986,
+      "grad_norm": 13.284646987915039,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.9725,
+      "step": 100
+    },
+    {
+      "epoch": 0.16249153689911983,
+      "grad_norm": 13.212055206298828,
+      "learning_rate": 5.8e-06,
+      "loss": 1.7839,
+      "step": 120
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 12.006990432739258,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.5991,
+      "step": 140
+    },
+    {
+      "epoch": 0.2166553825321598,
+      "grad_norm": 12.490514755249023,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4411,
+      "step": 160
+    },
+    {
+      "epoch": 0.24373730534867977,
+      "grad_norm": 11.587646484375,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3487,
+      "step": 180
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "grad_norm": 11.574933052062988,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.2119,
+      "step": 200
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "eval_loss": 1.1157827377319336,
+      "eval_runtime": 1601.2991,
+      "eval_samples_per_second": 3.688,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 64.22461160550755,
+      "step": 200
+    },
+    {
+      "epoch": 0.2979011509817197,
+      "grad_norm": 8.368565559387207,
+      "learning_rate": 9.920556107249256e-06,
+      "loss": 0.9452,
+      "step": 220
+    },
+    {
+      "epoch": 0.32498307379823965,
+      "grad_norm": 7.2616682052612305,
+      "learning_rate": 9.821251241310825e-06,
+      "loss": 0.9298,
+      "step": 240
+    },
+    {
+      "epoch": 0.35206499661475965,
+      "grad_norm": 7.266394138336182,
+      "learning_rate": 9.721946375372395e-06,
+      "loss": 0.8567,
+      "step": 260
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 8.120067596435547,
+      "learning_rate": 9.622641509433963e-06,
+      "loss": 0.8251,
+      "step": 280
+    },
+    {
+      "epoch": 0.4062288422477996,
+      "grad_norm": 7.483547687530518,
+      "learning_rate": 9.523336643495532e-06,
+      "loss": 0.7774,
+      "step": 300
+    },
+    {
+      "epoch": 0.4333107650643196,
+      "grad_norm": 7.521896839141846,
+      "learning_rate": 9.4240317775571e-06,
+      "loss": 0.7266,
+      "step": 320
+    },
+    {
+      "epoch": 0.46039268788083954,
+      "grad_norm": 7.073266506195068,
+      "learning_rate": 9.32472691161867e-06,
+      "loss": 0.7248,
+      "step": 340
+    },
+    {
+      "epoch": 0.48747461069735953,
+      "grad_norm": 6.335423469543457,
+      "learning_rate": 9.22542204568024e-06,
+      "loss": 0.7151,
+      "step": 360
+    },
+    {
+      "epoch": 0.5145565335138795,
+      "grad_norm": 6.936922550201416,
+      "learning_rate": 9.126117179741808e-06,
+      "loss": 0.6881,
+      "step": 380
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "grad_norm": 7.596807479858398,
+      "learning_rate": 9.026812313803377e-06,
+      "loss": 0.6995,
+      "step": 400
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "eval_loss": 0.6352065801620483,
+      "eval_runtime": 1597.3635,
+      "eval_samples_per_second": 3.697,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 51.63653601672089,
+      "step": 400
+    },
+    {
+      "epoch": 0.5687203791469194,
+      "grad_norm": 6.981812477111816,
+      "learning_rate": 8.927507447864945e-06,
+      "loss": 0.6795,
+      "step": 420
+    },
+    {
+      "epoch": 0.5958023019634394,
+      "grad_norm": 6.481506824493408,
+      "learning_rate": 8.828202581926516e-06,
+      "loss": 0.6643,
+      "step": 440
+    },
+    {
+      "epoch": 0.6228842247799594,
+      "grad_norm": 6.537086009979248,
+      "learning_rate": 8.728897715988084e-06,
+      "loss": 0.6459,
+      "step": 460
+    },
+    {
+      "epoch": 0.6499661475964793,
+      "grad_norm": 6.739567756652832,
+      "learning_rate": 8.629592850049653e-06,
+      "loss": 0.6736,
+      "step": 480
+    },
+    {
+      "epoch": 0.6770480704129993,
+      "grad_norm": 7.422546863555908,
+      "learning_rate": 8.530287984111221e-06,
+      "loss": 0.6591,
+      "step": 500
+    },
+    {
+      "epoch": 0.7041299932295193,
+      "grad_norm": 5.7051215171813965,
+      "learning_rate": 8.430983118172792e-06,
+      "loss": 0.6442,
+      "step": 520
+    },
+    {
+      "epoch": 0.7312119160460393,
+      "grad_norm": 7.166143417358398,
+      "learning_rate": 8.33167825223436e-06,
+      "loss": 0.6326,
+      "step": 540
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "grad_norm": 7.759460926055908,
+      "learning_rate": 8.232373386295929e-06,
+      "loss": 0.6328,
+      "step": 560
+    },
+    {
+      "epoch": 0.7853757616790792,
+      "grad_norm": 5.876537799835205,
+      "learning_rate": 8.133068520357497e-06,
+      "loss": 0.5945,
+      "step": 580
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "grad_norm": 6.475106716156006,
+      "learning_rate": 8.033763654419066e-06,
+      "loss": 0.6038,
+      "step": 600
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "eval_loss": 0.5318673849105835,
+      "eval_runtime": 1614.0202,
+      "eval_samples_per_second": 3.659,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 44.61419121291129,
+      "step": 600
+    },
+    {
+      "epoch": 0.8395396073121192,
+      "grad_norm": 6.8348259925842285,
+      "learning_rate": 7.934458788480636e-06,
+      "loss": 0.6046,
+      "step": 620
+    },
+    {
+      "epoch": 0.8666215301286392,
+      "grad_norm": 6.060784339904785,
+      "learning_rate": 7.835153922542206e-06,
+      "loss": 0.6055,
+      "step": 640
+    },
+    {
+      "epoch": 0.8937034529451591,
+      "grad_norm": 6.01262903213501,
+      "learning_rate": 7.735849056603775e-06,
+      "loss": 0.6139,
+      "step": 660
+    },
+    {
+      "epoch": 0.9207853757616791,
+      "grad_norm": 6.706854820251465,
+      "learning_rate": 7.636544190665344e-06,
+      "loss": 0.5789,
+      "step": 680
+    },
+    {
+      "epoch": 0.9478672985781991,
+      "grad_norm": 6.464681625366211,
+      "learning_rate": 7.537239324726913e-06,
+      "loss": 0.5857,
+      "step": 700
+    },
+    {
+      "epoch": 0.9749492213947191,
+      "grad_norm": 7.8035478591918945,
+      "learning_rate": 7.437934458788482e-06,
+      "loss": 0.5739,
+      "step": 720
+    },
+    {
+      "epoch": 1.001354096140826,
+      "grad_norm": 5.574532985687256,
+      "learning_rate": 7.33862959285005e-06,
+      "loss": 0.5443,
+      "step": 740
+    },
+    {
+      "epoch": 1.028436018957346,
+      "grad_norm": 5.275153160095215,
+      "learning_rate": 7.23932472691162e-06,
+      "loss": 0.4705,
+      "step": 760
+    },
+    {
+      "epoch": 1.055517941773866,
+      "grad_norm": 5.722527027130127,
+      "learning_rate": 7.140019860973188e-06,
+      "loss": 0.4692,
+      "step": 780
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "grad_norm": 5.501762866973877,
+      "learning_rate": 7.040714995034758e-06,
+      "loss": 0.4791,
+      "step": 800
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "eval_loss": 0.46895861625671387,
+      "eval_runtime": 1599.6376,
+      "eval_samples_per_second": 3.691,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 40.9726561658299,
+      "step": 800
+    },
+    {
+      "epoch": 1.1096817874069058,
+      "grad_norm": 5.207645893096924,
+      "learning_rate": 6.941410129096326e-06,
+      "loss": 0.4569,
+      "step": 820
+    },
+    {
+      "epoch": 1.1367637102234258,
+      "grad_norm": 5.584475517272949,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.4262,
+      "step": 840
+    },
+    {
+      "epoch": 1.1638456330399458,
+      "grad_norm": 5.881894588470459,
+      "learning_rate": 6.742800397219464e-06,
+      "loss": 0.4533,
+      "step": 860
+    },
+    {
+      "epoch": 1.1909275558564658,
+      "grad_norm": 6.939334869384766,
+      "learning_rate": 6.643495531281034e-06,
+      "loss": 0.4675,
+      "step": 880
+    },
+    {
+      "epoch": 1.2180094786729858,
+      "grad_norm": 5.780360698699951,
+      "learning_rate": 6.544190665342602e-06,
+      "loss": 0.4238,
+      "step": 900
+    },
+    {
+      "epoch": 1.2450914014895058,
+      "grad_norm": 5.867160797119141,
+      "learning_rate": 6.444885799404172e-06,
+      "loss": 0.444,
+      "step": 920
+    },
+    {
+      "epoch": 1.2721733243060258,
+      "grad_norm": 6.121824741363525,
+      "learning_rate": 6.34558093346574e-06,
+      "loss": 0.4333,
+      "step": 940
+    },
+    {
+      "epoch": 1.2992552471225456,
+      "grad_norm": 5.132157802581787,
+      "learning_rate": 6.24627606752731e-06,
+      "loss": 0.4544,
+      "step": 960
+    },
+    {
+      "epoch": 1.3263371699390656,
+      "grad_norm": 6.384315013885498,
+      "learning_rate": 6.146971201588878e-06,
+      "loss": 0.4332,
+      "step": 980
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "grad_norm": 4.54695987701416,
+      "learning_rate": 6.047666335650447e-06,
+      "loss": 0.4416,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "eval_loss": 0.43043428659439087,
+      "eval_runtime": 1614.3899,
+      "eval_samples_per_second": 3.658,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 38.00771402098731,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.22665241903104e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1000/training_args.bin b/checkpoint-1000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2a3b1da275660c7c7439512aa770d076034c70c
--- /dev/null
+++ b/checkpoint-1000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d182356a12cee606170360f976946e1a56ce9d494fc1de269ffa184a80a19aa
+size 5432
diff --git a/checkpoint-1200/config.json b/checkpoint-1200/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..337642e18341c758364c32c6b6159a090615329b
--- /dev/null
+++ b/checkpoint-1200/config.json
@@ -0,0 +1,47 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
diff --git a/checkpoint-1200/generation_config.json b/checkpoint-1200/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec4263613bc098f8eb01034b73fbe16fb43eba5c
--- /dev/null
+++ b/checkpoint-1200/generation_config.json
@@ -0,0 +1,175 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      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": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.51.3"
+}
diff --git a/checkpoint-1200/model.safetensors b/checkpoint-1200/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2d1fbe96a916acb59578163d711ff2a204245770
--- /dev/null
+++ b/checkpoint-1200/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb14949829a92f21b5831610a3e1c5818517a70e7b78c91869165be3fa027220
+size 966995080
diff --git a/checkpoint-1200/optimizer.pt b/checkpoint-1200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..08f77da65d67be662db3a971473bead08c0ad15d
--- /dev/null
+++ b/checkpoint-1200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d3c742b7a9d7e3ae2729a416b557ee7782f301ef925dea88ee4c0b277e087b
+size 1925064044
diff --git a/checkpoint-1200/preprocessor_config.json b/checkpoint-1200/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-1200/preprocessor_config.json
@@ -0,0 +1,15 @@
+{
+  "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,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-1200/rng_state.pth b/checkpoint-1200/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ab2ff414d3828b55130cc84e32870dfe65a02f4c
--- /dev/null
+++ b/checkpoint-1200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ee6e7cb7371fbb90ac429f9ed02af5fb766eaadcd01bf63f86ad9dfa2abf6c6
+size 14244
diff --git a/checkpoint-1200/scaler.pt b/checkpoint-1200/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bae0563cad6a38c18675c829bb6eea0f67292314
--- /dev/null
+++ b/checkpoint-1200/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2bba2d3316c5a034cb242c96fb8e8d64a45bd5676f615fdf565b22b5760dea1
+size 988
diff --git a/checkpoint-1200/scheduler.pt b/checkpoint-1200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..69f0a2ce6a080e54b7dd55b429acbf391d62bd3c
--- /dev/null
+++ b/checkpoint-1200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a2a9f4d0fd0f57c0ac9e3087fe25fc38ac9090191d38f259c2fb5164d10dce8
+size 1064
diff --git a/checkpoint-1200/trainer_state.json b/checkpoint-1200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..17ae6d38545a0024af7c4ceda7e86164abd07da6
--- /dev/null
+++ b/checkpoint-1200/trainer_state.json
@@ -0,0 +1,508 @@
+{
+  "best_global_step": 1200,
+  "best_metric": 37.091943373052636,
+  "best_model_checkpoint": "./HAUSA_B/checkpoint-1200",
+  "epoch": 1.6242383209207854,
+  "eval_steps": 200,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027081922816519974,
+      "grad_norm": 106.59215545654297,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 6.1915,
+      "step": 20
+    },
+    {
+      "epoch": 0.05416384563303995,
+      "grad_norm": 30.563518524169922,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 4.5886,
+      "step": 40
+    },
+    {
+      "epoch": 0.08124576844955991,
+      "grad_norm": 16.528457641601562,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 3.0338,
+      "step": 60
+    },
+    {
+      "epoch": 0.1083276912660799,
+      "grad_norm": 13.852096557617188,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.13540961408259986,
+      "grad_norm": 13.284646987915039,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.9725,
+      "step": 100
+    },
+    {
+      "epoch": 0.16249153689911983,
+      "grad_norm": 13.212055206298828,
+      "learning_rate": 5.8e-06,
+      "loss": 1.7839,
+      "step": 120
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 12.006990432739258,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.5991,
+      "step": 140
+    },
+    {
+      "epoch": 0.2166553825321598,
+      "grad_norm": 12.490514755249023,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4411,
+      "step": 160
+    },
+    {
+      "epoch": 0.24373730534867977,
+      "grad_norm": 11.587646484375,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3487,
+      "step": 180
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "grad_norm": 11.574933052062988,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.2119,
+      "step": 200
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "eval_loss": 1.1157827377319336,
+      "eval_runtime": 1601.2991,
+      "eval_samples_per_second": 3.688,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 64.22461160550755,
+      "step": 200
+    },
+    {
+      "epoch": 0.2979011509817197,
+      "grad_norm": 8.368565559387207,
+      "learning_rate": 9.920556107249256e-06,
+      "loss": 0.9452,
+      "step": 220
+    },
+    {
+      "epoch": 0.32498307379823965,
+      "grad_norm": 7.2616682052612305,
+      "learning_rate": 9.821251241310825e-06,
+      "loss": 0.9298,
+      "step": 240
+    },
+    {
+      "epoch": 0.35206499661475965,
+      "grad_norm": 7.266394138336182,
+      "learning_rate": 9.721946375372395e-06,
+      "loss": 0.8567,
+      "step": 260
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 8.120067596435547,
+      "learning_rate": 9.622641509433963e-06,
+      "loss": 0.8251,
+      "step": 280
+    },
+    {
+      "epoch": 0.4062288422477996,
+      "grad_norm": 7.483547687530518,
+      "learning_rate": 9.523336643495532e-06,
+      "loss": 0.7774,
+      "step": 300
+    },
+    {
+      "epoch": 0.4333107650643196,
+      "grad_norm": 7.521896839141846,
+      "learning_rate": 9.4240317775571e-06,
+      "loss": 0.7266,
+      "step": 320
+    },
+    {
+      "epoch": 0.46039268788083954,
+      "grad_norm": 7.073266506195068,
+      "learning_rate": 9.32472691161867e-06,
+      "loss": 0.7248,
+      "step": 340
+    },
+    {
+      "epoch": 0.48747461069735953,
+      "grad_norm": 6.335423469543457,
+      "learning_rate": 9.22542204568024e-06,
+      "loss": 0.7151,
+      "step": 360
+    },
+    {
+      "epoch": 0.5145565335138795,
+      "grad_norm": 6.936922550201416,
+      "learning_rate": 9.126117179741808e-06,
+      "loss": 0.6881,
+      "step": 380
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "grad_norm": 7.596807479858398,
+      "learning_rate": 9.026812313803377e-06,
+      "loss": 0.6995,
+      "step": 400
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "eval_loss": 0.6352065801620483,
+      "eval_runtime": 1597.3635,
+      "eval_samples_per_second": 3.697,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 51.63653601672089,
+      "step": 400
+    },
+    {
+      "epoch": 0.5687203791469194,
+      "grad_norm": 6.981812477111816,
+      "learning_rate": 8.927507447864945e-06,
+      "loss": 0.6795,
+      "step": 420
+    },
+    {
+      "epoch": 0.5958023019634394,
+      "grad_norm": 6.481506824493408,
+      "learning_rate": 8.828202581926516e-06,
+      "loss": 0.6643,
+      "step": 440
+    },
+    {
+      "epoch": 0.6228842247799594,
+      "grad_norm": 6.537086009979248,
+      "learning_rate": 8.728897715988084e-06,
+      "loss": 0.6459,
+      "step": 460
+    },
+    {
+      "epoch": 0.6499661475964793,
+      "grad_norm": 6.739567756652832,
+      "learning_rate": 8.629592850049653e-06,
+      "loss": 0.6736,
+      "step": 480
+    },
+    {
+      "epoch": 0.6770480704129993,
+      "grad_norm": 7.422546863555908,
+      "learning_rate": 8.530287984111221e-06,
+      "loss": 0.6591,
+      "step": 500
+    },
+    {
+      "epoch": 0.7041299932295193,
+      "grad_norm": 5.7051215171813965,
+      "learning_rate": 8.430983118172792e-06,
+      "loss": 0.6442,
+      "step": 520
+    },
+    {
+      "epoch": 0.7312119160460393,
+      "grad_norm": 7.166143417358398,
+      "learning_rate": 8.33167825223436e-06,
+      "loss": 0.6326,
+      "step": 540
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "grad_norm": 7.759460926055908,
+      "learning_rate": 8.232373386295929e-06,
+      "loss": 0.6328,
+      "step": 560
+    },
+    {
+      "epoch": 0.7853757616790792,
+      "grad_norm": 5.876537799835205,
+      "learning_rate": 8.133068520357497e-06,
+      "loss": 0.5945,
+      "step": 580
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "grad_norm": 6.475106716156006,
+      "learning_rate": 8.033763654419066e-06,
+      "loss": 0.6038,
+      "step": 600
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "eval_loss": 0.5318673849105835,
+      "eval_runtime": 1614.0202,
+      "eval_samples_per_second": 3.659,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 44.61419121291129,
+      "step": 600
+    },
+    {
+      "epoch": 0.8395396073121192,
+      "grad_norm": 6.8348259925842285,
+      "learning_rate": 7.934458788480636e-06,
+      "loss": 0.6046,
+      "step": 620
+    },
+    {
+      "epoch": 0.8666215301286392,
+      "grad_norm": 6.060784339904785,
+      "learning_rate": 7.835153922542206e-06,
+      "loss": 0.6055,
+      "step": 640
+    },
+    {
+      "epoch": 0.8937034529451591,
+      "grad_norm": 6.01262903213501,
+      "learning_rate": 7.735849056603775e-06,
+      "loss": 0.6139,
+      "step": 660
+    },
+    {
+      "epoch": 0.9207853757616791,
+      "grad_norm": 6.706854820251465,
+      "learning_rate": 7.636544190665344e-06,
+      "loss": 0.5789,
+      "step": 680
+    },
+    {
+      "epoch": 0.9478672985781991,
+      "grad_norm": 6.464681625366211,
+      "learning_rate": 7.537239324726913e-06,
+      "loss": 0.5857,
+      "step": 700
+    },
+    {
+      "epoch": 0.9749492213947191,
+      "grad_norm": 7.8035478591918945,
+      "learning_rate": 7.437934458788482e-06,
+      "loss": 0.5739,
+      "step": 720
+    },
+    {
+      "epoch": 1.001354096140826,
+      "grad_norm": 5.574532985687256,
+      "learning_rate": 7.33862959285005e-06,
+      "loss": 0.5443,
+      "step": 740
+    },
+    {
+      "epoch": 1.028436018957346,
+      "grad_norm": 5.275153160095215,
+      "learning_rate": 7.23932472691162e-06,
+      "loss": 0.4705,
+      "step": 760
+    },
+    {
+      "epoch": 1.055517941773866,
+      "grad_norm": 5.722527027130127,
+      "learning_rate": 7.140019860973188e-06,
+      "loss": 0.4692,
+      "step": 780
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "grad_norm": 5.501762866973877,
+      "learning_rate": 7.040714995034758e-06,
+      "loss": 0.4791,
+      "step": 800
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "eval_loss": 0.46895861625671387,
+      "eval_runtime": 1599.6376,
+      "eval_samples_per_second": 3.691,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 40.9726561658299,
+      "step": 800
+    },
+    {
+      "epoch": 1.1096817874069058,
+      "grad_norm": 5.207645893096924,
+      "learning_rate": 6.941410129096326e-06,
+      "loss": 0.4569,
+      "step": 820
+    },
+    {
+      "epoch": 1.1367637102234258,
+      "grad_norm": 5.584475517272949,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.4262,
+      "step": 840
+    },
+    {
+      "epoch": 1.1638456330399458,
+      "grad_norm": 5.881894588470459,
+      "learning_rate": 6.742800397219464e-06,
+      "loss": 0.4533,
+      "step": 860
+    },
+    {
+      "epoch": 1.1909275558564658,
+      "grad_norm": 6.939334869384766,
+      "learning_rate": 6.643495531281034e-06,
+      "loss": 0.4675,
+      "step": 880
+    },
+    {
+      "epoch": 1.2180094786729858,
+      "grad_norm": 5.780360698699951,
+      "learning_rate": 6.544190665342602e-06,
+      "loss": 0.4238,
+      "step": 900
+    },
+    {
+      "epoch": 1.2450914014895058,
+      "grad_norm": 5.867160797119141,
+      "learning_rate": 6.444885799404172e-06,
+      "loss": 0.444,
+      "step": 920
+    },
+    {
+      "epoch": 1.2721733243060258,
+      "grad_norm": 6.121824741363525,
+      "learning_rate": 6.34558093346574e-06,
+      "loss": 0.4333,
+      "step": 940
+    },
+    {
+      "epoch": 1.2992552471225456,
+      "grad_norm": 5.132157802581787,
+      "learning_rate": 6.24627606752731e-06,
+      "loss": 0.4544,
+      "step": 960
+    },
+    {
+      "epoch": 1.3263371699390656,
+      "grad_norm": 6.384315013885498,
+      "learning_rate": 6.146971201588878e-06,
+      "loss": 0.4332,
+      "step": 980
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "grad_norm": 4.54695987701416,
+      "learning_rate": 6.047666335650447e-06,
+      "loss": 0.4416,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "eval_loss": 0.43043428659439087,
+      "eval_runtime": 1614.3899,
+      "eval_samples_per_second": 3.658,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 38.00771402098731,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3805010155721056,
+      "grad_norm": 4.973900318145752,
+      "learning_rate": 5.948361469712016e-06,
+      "loss": 0.4401,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4075829383886256,
+      "grad_norm": 5.952788352966309,
+      "learning_rate": 5.849056603773585e-06,
+      "loss": 0.4865,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4346648612051456,
+      "grad_norm": 6.601942539215088,
+      "learning_rate": 5.749751737835154e-06,
+      "loss": 0.4435,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4617467840216656,
+      "grad_norm": 6.17143440246582,
+      "learning_rate": 5.650446871896723e-06,
+      "loss": 0.451,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4888287068381856,
+      "grad_norm": 5.782886981964111,
+      "learning_rate": 5.551142005958292e-06,
+      "loss": 0.4311,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5159106296547056,
+      "grad_norm": 5.734127998352051,
+      "learning_rate": 5.451837140019861e-06,
+      "loss": 0.4632,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5429925524712256,
+      "grad_norm": 5.601761341094971,
+      "learning_rate": 5.35253227408143e-06,
+      "loss": 0.424,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5700744752877456,
+      "grad_norm": 5.866110801696777,
+      "learning_rate": 5.253227408142999e-06,
+      "loss": 0.4273,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5971563981042654,
+      "grad_norm": 5.120361328125,
+      "learning_rate": 5.153922542204568e-06,
+      "loss": 0.4297,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "grad_norm": 5.093082427978516,
+      "learning_rate": 5.054617676266137e-06,
+      "loss": 0.4321,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "eval_loss": 0.3993258476257324,
+      "eval_runtime": 1619.3754,
+      "eval_samples_per_second": 3.646,
+      "eval_steps_per_second": 0.456,
+      "eval_wer": 37.091943373052636,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.107359898107904e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1200/training_args.bin b/checkpoint-1200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2a3b1da275660c7c7439512aa770d076034c70c
--- /dev/null
+++ b/checkpoint-1200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d182356a12cee606170360f976946e1a56ce9d494fc1de269ffa184a80a19aa
+size 5432
diff --git a/checkpoint-1400/config.json b/checkpoint-1400/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..337642e18341c758364c32c6b6159a090615329b
--- /dev/null
+++ b/checkpoint-1400/config.json
@@ -0,0 +1,47 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
diff --git a/checkpoint-1400/generation_config.json b/checkpoint-1400/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec4263613bc098f8eb01034b73fbe16fb43eba5c
--- /dev/null
+++ b/checkpoint-1400/generation_config.json
@@ -0,0 +1,175 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      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": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.51.3"
+}
diff --git a/checkpoint-1400/model.safetensors b/checkpoint-1400/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8199c3a603cc3767e313b7c6d03901ec462cc39e
--- /dev/null
+++ b/checkpoint-1400/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f0ee7d8634de74415ef90e2882c7e96fdac9cee1dad2f36bd4a6036ee092f6
+size 966995080
diff --git a/checkpoint-1400/optimizer.pt b/checkpoint-1400/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6028ad1cf84b061146d55e730a40cde8522d6259
--- /dev/null
+++ b/checkpoint-1400/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b40e7c5f8642aef067896fd0c278e4503941bf01b49682e4d60e13cac862df5
+size 1925064044
diff --git a/checkpoint-1400/preprocessor_config.json b/checkpoint-1400/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-1400/preprocessor_config.json
@@ -0,0 +1,15 @@
+{
+  "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,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-1400/rng_state.pth b/checkpoint-1400/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0777a37dfbc3063d3399a6037a6f14721d828b57
--- /dev/null
+++ b/checkpoint-1400/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c06f045bd7c705582a3aca1aaddd4580344f768a5e94a2ef07e8740f5001422
+size 14244
diff --git a/checkpoint-1400/scaler.pt b/checkpoint-1400/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1b0b8cafa9515f90455e82de546dc3d77b9d380f
--- /dev/null
+++ b/checkpoint-1400/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685987cc5b0f2ee0b68c24f0a8db28864faad52607ac80c3a55717c0108676b8
+size 988
diff --git a/checkpoint-1400/scheduler.pt b/checkpoint-1400/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5112056f7f3c07ab17a1bddc078988c338a712f6
--- /dev/null
+++ b/checkpoint-1400/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d27f0a7e829c9c887f2fcf55a867e136d8c795c676853896d6b350d68cf9fe
+size 1064
diff --git a/checkpoint-1400/trainer_state.json b/checkpoint-1400/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..873db977a3c28701f819271ae97851b152f300c3
--- /dev/null
+++ b/checkpoint-1400/trainer_state.json
@@ -0,0 +1,587 @@
+{
+  "best_global_step": 1400,
+  "best_metric": 35.20006895214291,
+  "best_model_checkpoint": "./HAUSA_B/checkpoint-1400",
+  "epoch": 1.8950575490859851,
+  "eval_steps": 200,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027081922816519974,
+      "grad_norm": 106.59215545654297,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 6.1915,
+      "step": 20
+    },
+    {
+      "epoch": 0.05416384563303995,
+      "grad_norm": 30.563518524169922,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 4.5886,
+      "step": 40
+    },
+    {
+      "epoch": 0.08124576844955991,
+      "grad_norm": 16.528457641601562,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 3.0338,
+      "step": 60
+    },
+    {
+      "epoch": 0.1083276912660799,
+      "grad_norm": 13.852096557617188,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.13540961408259986,
+      "grad_norm": 13.284646987915039,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.9725,
+      "step": 100
+    },
+    {
+      "epoch": 0.16249153689911983,
+      "grad_norm": 13.212055206298828,
+      "learning_rate": 5.8e-06,
+      "loss": 1.7839,
+      "step": 120
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 12.006990432739258,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.5991,
+      "step": 140
+    },
+    {
+      "epoch": 0.2166553825321598,
+      "grad_norm": 12.490514755249023,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4411,
+      "step": 160
+    },
+    {
+      "epoch": 0.24373730534867977,
+      "grad_norm": 11.587646484375,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3487,
+      "step": 180
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "grad_norm": 11.574933052062988,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.2119,
+      "step": 200
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "eval_loss": 1.1157827377319336,
+      "eval_runtime": 1601.2991,
+      "eval_samples_per_second": 3.688,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 64.22461160550755,
+      "step": 200
+    },
+    {
+      "epoch": 0.2979011509817197,
+      "grad_norm": 8.368565559387207,
+      "learning_rate": 9.920556107249256e-06,
+      "loss": 0.9452,
+      "step": 220
+    },
+    {
+      "epoch": 0.32498307379823965,
+      "grad_norm": 7.2616682052612305,
+      "learning_rate": 9.821251241310825e-06,
+      "loss": 0.9298,
+      "step": 240
+    },
+    {
+      "epoch": 0.35206499661475965,
+      "grad_norm": 7.266394138336182,
+      "learning_rate": 9.721946375372395e-06,
+      "loss": 0.8567,
+      "step": 260
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 8.120067596435547,
+      "learning_rate": 9.622641509433963e-06,
+      "loss": 0.8251,
+      "step": 280
+    },
+    {
+      "epoch": 0.4062288422477996,
+      "grad_norm": 7.483547687530518,
+      "learning_rate": 9.523336643495532e-06,
+      "loss": 0.7774,
+      "step": 300
+    },
+    {
+      "epoch": 0.4333107650643196,
+      "grad_norm": 7.521896839141846,
+      "learning_rate": 9.4240317775571e-06,
+      "loss": 0.7266,
+      "step": 320
+    },
+    {
+      "epoch": 0.46039268788083954,
+      "grad_norm": 7.073266506195068,
+      "learning_rate": 9.32472691161867e-06,
+      "loss": 0.7248,
+      "step": 340
+    },
+    {
+      "epoch": 0.48747461069735953,
+      "grad_norm": 6.335423469543457,
+      "learning_rate": 9.22542204568024e-06,
+      "loss": 0.7151,
+      "step": 360
+    },
+    {
+      "epoch": 0.5145565335138795,
+      "grad_norm": 6.936922550201416,
+      "learning_rate": 9.126117179741808e-06,
+      "loss": 0.6881,
+      "step": 380
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "grad_norm": 7.596807479858398,
+      "learning_rate": 9.026812313803377e-06,
+      "loss": 0.6995,
+      "step": 400
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "eval_loss": 0.6352065801620483,
+      "eval_runtime": 1597.3635,
+      "eval_samples_per_second": 3.697,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 51.63653601672089,
+      "step": 400
+    },
+    {
+      "epoch": 0.5687203791469194,
+      "grad_norm": 6.981812477111816,
+      "learning_rate": 8.927507447864945e-06,
+      "loss": 0.6795,
+      "step": 420
+    },
+    {
+      "epoch": 0.5958023019634394,
+      "grad_norm": 6.481506824493408,
+      "learning_rate": 8.828202581926516e-06,
+      "loss": 0.6643,
+      "step": 440
+    },
+    {
+      "epoch": 0.6228842247799594,
+      "grad_norm": 6.537086009979248,
+      "learning_rate": 8.728897715988084e-06,
+      "loss": 0.6459,
+      "step": 460
+    },
+    {
+      "epoch": 0.6499661475964793,
+      "grad_norm": 6.739567756652832,
+      "learning_rate": 8.629592850049653e-06,
+      "loss": 0.6736,
+      "step": 480
+    },
+    {
+      "epoch": 0.6770480704129993,
+      "grad_norm": 7.422546863555908,
+      "learning_rate": 8.530287984111221e-06,
+      "loss": 0.6591,
+      "step": 500
+    },
+    {
+      "epoch": 0.7041299932295193,
+      "grad_norm": 5.7051215171813965,
+      "learning_rate": 8.430983118172792e-06,
+      "loss": 0.6442,
+      "step": 520
+    },
+    {
+      "epoch": 0.7312119160460393,
+      "grad_norm": 7.166143417358398,
+      "learning_rate": 8.33167825223436e-06,
+      "loss": 0.6326,
+      "step": 540
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "grad_norm": 7.759460926055908,
+      "learning_rate": 8.232373386295929e-06,
+      "loss": 0.6328,
+      "step": 560
+    },
+    {
+      "epoch": 0.7853757616790792,
+      "grad_norm": 5.876537799835205,
+      "learning_rate": 8.133068520357497e-06,
+      "loss": 0.5945,
+      "step": 580
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "grad_norm": 6.475106716156006,
+      "learning_rate": 8.033763654419066e-06,
+      "loss": 0.6038,
+      "step": 600
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "eval_loss": 0.5318673849105835,
+      "eval_runtime": 1614.0202,
+      "eval_samples_per_second": 3.659,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 44.61419121291129,
+      "step": 600
+    },
+    {
+      "epoch": 0.8395396073121192,
+      "grad_norm": 6.8348259925842285,
+      "learning_rate": 7.934458788480636e-06,
+      "loss": 0.6046,
+      "step": 620
+    },
+    {
+      "epoch": 0.8666215301286392,
+      "grad_norm": 6.060784339904785,
+      "learning_rate": 7.835153922542206e-06,
+      "loss": 0.6055,
+      "step": 640
+    },
+    {
+      "epoch": 0.8937034529451591,
+      "grad_norm": 6.01262903213501,
+      "learning_rate": 7.735849056603775e-06,
+      "loss": 0.6139,
+      "step": 660
+    },
+    {
+      "epoch": 0.9207853757616791,
+      "grad_norm": 6.706854820251465,
+      "learning_rate": 7.636544190665344e-06,
+      "loss": 0.5789,
+      "step": 680
+    },
+    {
+      "epoch": 0.9478672985781991,
+      "grad_norm": 6.464681625366211,
+      "learning_rate": 7.537239324726913e-06,
+      "loss": 0.5857,
+      "step": 700
+    },
+    {
+      "epoch": 0.9749492213947191,
+      "grad_norm": 7.8035478591918945,
+      "learning_rate": 7.437934458788482e-06,
+      "loss": 0.5739,
+      "step": 720
+    },
+    {
+      "epoch": 1.001354096140826,
+      "grad_norm": 5.574532985687256,
+      "learning_rate": 7.33862959285005e-06,
+      "loss": 0.5443,
+      "step": 740
+    },
+    {
+      "epoch": 1.028436018957346,
+      "grad_norm": 5.275153160095215,
+      "learning_rate": 7.23932472691162e-06,
+      "loss": 0.4705,
+      "step": 760
+    },
+    {
+      "epoch": 1.055517941773866,
+      "grad_norm": 5.722527027130127,
+      "learning_rate": 7.140019860973188e-06,
+      "loss": 0.4692,
+      "step": 780
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "grad_norm": 5.501762866973877,
+      "learning_rate": 7.040714995034758e-06,
+      "loss": 0.4791,
+      "step": 800
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "eval_loss": 0.46895861625671387,
+      "eval_runtime": 1599.6376,
+      "eval_samples_per_second": 3.691,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 40.9726561658299,
+      "step": 800
+    },
+    {
+      "epoch": 1.1096817874069058,
+      "grad_norm": 5.207645893096924,
+      "learning_rate": 6.941410129096326e-06,
+      "loss": 0.4569,
+      "step": 820
+    },
+    {
+      "epoch": 1.1367637102234258,
+      "grad_norm": 5.584475517272949,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.4262,
+      "step": 840
+    },
+    {
+      "epoch": 1.1638456330399458,
+      "grad_norm": 5.881894588470459,
+      "learning_rate": 6.742800397219464e-06,
+      "loss": 0.4533,
+      "step": 860
+    },
+    {
+      "epoch": 1.1909275558564658,
+      "grad_norm": 6.939334869384766,
+      "learning_rate": 6.643495531281034e-06,
+      "loss": 0.4675,
+      "step": 880
+    },
+    {
+      "epoch": 1.2180094786729858,
+      "grad_norm": 5.780360698699951,
+      "learning_rate": 6.544190665342602e-06,
+      "loss": 0.4238,
+      "step": 900
+    },
+    {
+      "epoch": 1.2450914014895058,
+      "grad_norm": 5.867160797119141,
+      "learning_rate": 6.444885799404172e-06,
+      "loss": 0.444,
+      "step": 920
+    },
+    {
+      "epoch": 1.2721733243060258,
+      "grad_norm": 6.121824741363525,
+      "learning_rate": 6.34558093346574e-06,
+      "loss": 0.4333,
+      "step": 940
+    },
+    {
+      "epoch": 1.2992552471225456,
+      "grad_norm": 5.132157802581787,
+      "learning_rate": 6.24627606752731e-06,
+      "loss": 0.4544,
+      "step": 960
+    },
+    {
+      "epoch": 1.3263371699390656,
+      "grad_norm": 6.384315013885498,
+      "learning_rate": 6.146971201588878e-06,
+      "loss": 0.4332,
+      "step": 980
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "grad_norm": 4.54695987701416,
+      "learning_rate": 6.047666335650447e-06,
+      "loss": 0.4416,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "eval_loss": 0.43043428659439087,
+      "eval_runtime": 1614.3899,
+      "eval_samples_per_second": 3.658,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 38.00771402098731,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3805010155721056,
+      "grad_norm": 4.973900318145752,
+      "learning_rate": 5.948361469712016e-06,
+      "loss": 0.4401,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4075829383886256,
+      "grad_norm": 5.952788352966309,
+      "learning_rate": 5.849056603773585e-06,
+      "loss": 0.4865,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4346648612051456,
+      "grad_norm": 6.601942539215088,
+      "learning_rate": 5.749751737835154e-06,
+      "loss": 0.4435,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4617467840216656,
+      "grad_norm": 6.17143440246582,
+      "learning_rate": 5.650446871896723e-06,
+      "loss": 0.451,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4888287068381856,
+      "grad_norm": 5.782886981964111,
+      "learning_rate": 5.551142005958292e-06,
+      "loss": 0.4311,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5159106296547056,
+      "grad_norm": 5.734127998352051,
+      "learning_rate": 5.451837140019861e-06,
+      "loss": 0.4632,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5429925524712256,
+      "grad_norm": 5.601761341094971,
+      "learning_rate": 5.35253227408143e-06,
+      "loss": 0.424,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5700744752877456,
+      "grad_norm": 5.866110801696777,
+      "learning_rate": 5.253227408142999e-06,
+      "loss": 0.4273,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5971563981042654,
+      "grad_norm": 5.120361328125,
+      "learning_rate": 5.153922542204568e-06,
+      "loss": 0.4297,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "grad_norm": 5.093082427978516,
+      "learning_rate": 5.054617676266137e-06,
+      "loss": 0.4321,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "eval_loss": 0.3993258476257324,
+      "eval_runtime": 1619.3754,
+      "eval_samples_per_second": 3.646,
+      "eval_steps_per_second": 0.456,
+      "eval_wer": 37.091943373052636,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6513202437373053,
+      "grad_norm": 5.076949119567871,
+      "learning_rate": 4.955312810327706e-06,
+      "loss": 0.4446,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6784021665538253,
+      "grad_norm": 5.729442596435547,
+      "learning_rate": 4.856007944389276e-06,
+      "loss": 0.4375,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7054840893703453,
+      "grad_norm": 5.660022258758545,
+      "learning_rate": 4.756703078450844e-06,
+      "loss": 0.4318,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7325660121868651,
+      "grad_norm": 5.320847511291504,
+      "learning_rate": 4.657398212512414e-06,
+      "loss": 0.4255,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7596479350033851,
+      "grad_norm": 4.652419567108154,
+      "learning_rate": 4.558093346573982e-06,
+      "loss": 0.4231,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7867298578199051,
+      "grad_norm": 6.301181793212891,
+      "learning_rate": 4.458788480635551e-06,
+      "loss": 0.4426,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8138117806364251,
+      "grad_norm": 5.540495872497559,
+      "learning_rate": 4.35948361469712e-06,
+      "loss": 0.4361,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8408937034529451,
+      "grad_norm": 5.618797302246094,
+      "learning_rate": 4.260178748758689e-06,
+      "loss": 0.4081,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8679756262694651,
+      "grad_norm": 5.519278526306152,
+      "learning_rate": 4.160873882820258e-06,
+      "loss": 0.4311,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950575490859851,
+      "grad_norm": 5.24718713760376,
+      "learning_rate": 4.061569016881828e-06,
+      "loss": 0.441,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8950575490859851,
+      "eval_loss": 0.37384942173957825,
+      "eval_runtime": 1616.0813,
+      "eval_samples_per_second": 3.654,
+      "eval_steps_per_second": 0.457,
+      "eval_wer": 35.20006895214291,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.292054554312704e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1400/training_args.bin b/checkpoint-1400/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2a3b1da275660c7c7439512aa770d076034c70c
--- /dev/null
+++ b/checkpoint-1400/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d182356a12cee606170360f976946e1a56ce9d494fc1de269ffa184a80a19aa
+size 5432
diff --git a/checkpoint-1600/config.json b/checkpoint-1600/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..337642e18341c758364c32c6b6159a090615329b
--- /dev/null
+++ b/checkpoint-1600/config.json
@@ -0,0 +1,47 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
diff --git a/checkpoint-1600/generation_config.json b/checkpoint-1600/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec4263613bc098f8eb01034b73fbe16fb43eba5c
--- /dev/null
+++ b/checkpoint-1600/generation_config.json
@@ -0,0 +1,175 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      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": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.51.3"
+}
diff --git a/checkpoint-1600/model.safetensors b/checkpoint-1600/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ecf9377658c2d98626944d37af2f3864caacbb15
--- /dev/null
+++ b/checkpoint-1600/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:195e815a216c95f9715350995a8ec27eb0a0e4dc4ab78fcc4854e60db7b43a2a
+size 966995080
diff --git a/checkpoint-1600/optimizer.pt b/checkpoint-1600/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2b8760617a09eef1bcfb4b633f056d2e07a1bb70
--- /dev/null
+++ b/checkpoint-1600/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e501476dad50a1fa900e1dc3dfb6488a6f96ba0591c8178cd9fc54e4b72520ba
+size 1925064044
diff --git a/checkpoint-1600/preprocessor_config.json b/checkpoint-1600/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-1600/preprocessor_config.json
@@ -0,0 +1,15 @@
+{
+  "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,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-1600/rng_state.pth b/checkpoint-1600/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1dc1ffa4c4af160c43cd7797f73cdf4be9d9cb08
--- /dev/null
+++ b/checkpoint-1600/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de6548641f28651640920c1bf324e1f8b9a6815899170d00a5e76bb82579d107
+size 14244
diff --git a/checkpoint-1600/scaler.pt b/checkpoint-1600/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e33a3fffa4acf5930a407ebc9b7d9c59e59cb148
--- /dev/null
+++ b/checkpoint-1600/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62209be68631fc121c2385c081411b86d2ac6a6c67d45683880f6163d554ca03
+size 988
diff --git a/checkpoint-1600/scheduler.pt b/checkpoint-1600/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a1a08a27d3ef980a84d82a781f2ce080682d20c4
--- /dev/null
+++ b/checkpoint-1600/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11c00ff382b63572e9d003a78ef65a7346daf9110b160d2871e9936d362aeecf
+size 1064
diff --git a/checkpoint-1600/trainer_state.json b/checkpoint-1600/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..eef56b390e8194d23958ac3e90138cec13901a21
--- /dev/null
+++ b/checkpoint-1600/trainer_state.json
@@ -0,0 +1,666 @@
+{
+  "best_global_step": 1600,
+  "best_metric": 34.23258419703075,
+  "best_model_checkpoint": "./HAUSA_B/checkpoint-1600",
+  "epoch": 2.1651997291807716,
+  "eval_steps": 200,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027081922816519974,
+      "grad_norm": 106.59215545654297,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 6.1915,
+      "step": 20
+    },
+    {
+      "epoch": 0.05416384563303995,
+      "grad_norm": 30.563518524169922,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 4.5886,
+      "step": 40
+    },
+    {
+      "epoch": 0.08124576844955991,
+      "grad_norm": 16.528457641601562,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 3.0338,
+      "step": 60
+    },
+    {
+      "epoch": 0.1083276912660799,
+      "grad_norm": 13.852096557617188,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.13540961408259986,
+      "grad_norm": 13.284646987915039,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.9725,
+      "step": 100
+    },
+    {
+      "epoch": 0.16249153689911983,
+      "grad_norm": 13.212055206298828,
+      "learning_rate": 5.8e-06,
+      "loss": 1.7839,
+      "step": 120
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 12.006990432739258,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.5991,
+      "step": 140
+    },
+    {
+      "epoch": 0.2166553825321598,
+      "grad_norm": 12.490514755249023,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4411,
+      "step": 160
+    },
+    {
+      "epoch": 0.24373730534867977,
+      "grad_norm": 11.587646484375,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3487,
+      "step": 180
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "grad_norm": 11.574933052062988,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.2119,
+      "step": 200
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "eval_loss": 1.1157827377319336,
+      "eval_runtime": 1601.2991,
+      "eval_samples_per_second": 3.688,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 64.22461160550755,
+      "step": 200
+    },
+    {
+      "epoch": 0.2979011509817197,
+      "grad_norm": 8.368565559387207,
+      "learning_rate": 9.920556107249256e-06,
+      "loss": 0.9452,
+      "step": 220
+    },
+    {
+      "epoch": 0.32498307379823965,
+      "grad_norm": 7.2616682052612305,
+      "learning_rate": 9.821251241310825e-06,
+      "loss": 0.9298,
+      "step": 240
+    },
+    {
+      "epoch": 0.35206499661475965,
+      "grad_norm": 7.266394138336182,
+      "learning_rate": 9.721946375372395e-06,
+      "loss": 0.8567,
+      "step": 260
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 8.120067596435547,
+      "learning_rate": 9.622641509433963e-06,
+      "loss": 0.8251,
+      "step": 280
+    },
+    {
+      "epoch": 0.4062288422477996,
+      "grad_norm": 7.483547687530518,
+      "learning_rate": 9.523336643495532e-06,
+      "loss": 0.7774,
+      "step": 300
+    },
+    {
+      "epoch": 0.4333107650643196,
+      "grad_norm": 7.521896839141846,
+      "learning_rate": 9.4240317775571e-06,
+      "loss": 0.7266,
+      "step": 320
+    },
+    {
+      "epoch": 0.46039268788083954,
+      "grad_norm": 7.073266506195068,
+      "learning_rate": 9.32472691161867e-06,
+      "loss": 0.7248,
+      "step": 340
+    },
+    {
+      "epoch": 0.48747461069735953,
+      "grad_norm": 6.335423469543457,
+      "learning_rate": 9.22542204568024e-06,
+      "loss": 0.7151,
+      "step": 360
+    },
+    {
+      "epoch": 0.5145565335138795,
+      "grad_norm": 6.936922550201416,
+      "learning_rate": 9.126117179741808e-06,
+      "loss": 0.6881,
+      "step": 380
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "grad_norm": 7.596807479858398,
+      "learning_rate": 9.026812313803377e-06,
+      "loss": 0.6995,
+      "step": 400
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "eval_loss": 0.6352065801620483,
+      "eval_runtime": 1597.3635,
+      "eval_samples_per_second": 3.697,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 51.63653601672089,
+      "step": 400
+    },
+    {
+      "epoch": 0.5687203791469194,
+      "grad_norm": 6.981812477111816,
+      "learning_rate": 8.927507447864945e-06,
+      "loss": 0.6795,
+      "step": 420
+    },
+    {
+      "epoch": 0.5958023019634394,
+      "grad_norm": 6.481506824493408,
+      "learning_rate": 8.828202581926516e-06,
+      "loss": 0.6643,
+      "step": 440
+    },
+    {
+      "epoch": 0.6228842247799594,
+      "grad_norm": 6.537086009979248,
+      "learning_rate": 8.728897715988084e-06,
+      "loss": 0.6459,
+      "step": 460
+    },
+    {
+      "epoch": 0.6499661475964793,
+      "grad_norm": 6.739567756652832,
+      "learning_rate": 8.629592850049653e-06,
+      "loss": 0.6736,
+      "step": 480
+    },
+    {
+      "epoch": 0.6770480704129993,
+      "grad_norm": 7.422546863555908,
+      "learning_rate": 8.530287984111221e-06,
+      "loss": 0.6591,
+      "step": 500
+    },
+    {
+      "epoch": 0.7041299932295193,
+      "grad_norm": 5.7051215171813965,
+      "learning_rate": 8.430983118172792e-06,
+      "loss": 0.6442,
+      "step": 520
+    },
+    {
+      "epoch": 0.7312119160460393,
+      "grad_norm": 7.166143417358398,
+      "learning_rate": 8.33167825223436e-06,
+      "loss": 0.6326,
+      "step": 540
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "grad_norm": 7.759460926055908,
+      "learning_rate": 8.232373386295929e-06,
+      "loss": 0.6328,
+      "step": 560
+    },
+    {
+      "epoch": 0.7853757616790792,
+      "grad_norm": 5.876537799835205,
+      "learning_rate": 8.133068520357497e-06,
+      "loss": 0.5945,
+      "step": 580
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "grad_norm": 6.475106716156006,
+      "learning_rate": 8.033763654419066e-06,
+      "loss": 0.6038,
+      "step": 600
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "eval_loss": 0.5318673849105835,
+      "eval_runtime": 1614.0202,
+      "eval_samples_per_second": 3.659,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 44.61419121291129,
+      "step": 600
+    },
+    {
+      "epoch": 0.8395396073121192,
+      "grad_norm": 6.8348259925842285,
+      "learning_rate": 7.934458788480636e-06,
+      "loss": 0.6046,
+      "step": 620
+    },
+    {
+      "epoch": 0.8666215301286392,
+      "grad_norm": 6.060784339904785,
+      "learning_rate": 7.835153922542206e-06,
+      "loss": 0.6055,
+      "step": 640
+    },
+    {
+      "epoch": 0.8937034529451591,
+      "grad_norm": 6.01262903213501,
+      "learning_rate": 7.735849056603775e-06,
+      "loss": 0.6139,
+      "step": 660
+    },
+    {
+      "epoch": 0.9207853757616791,
+      "grad_norm": 6.706854820251465,
+      "learning_rate": 7.636544190665344e-06,
+      "loss": 0.5789,
+      "step": 680
+    },
+    {
+      "epoch": 0.9478672985781991,
+      "grad_norm": 6.464681625366211,
+      "learning_rate": 7.537239324726913e-06,
+      "loss": 0.5857,
+      "step": 700
+    },
+    {
+      "epoch": 0.9749492213947191,
+      "grad_norm": 7.8035478591918945,
+      "learning_rate": 7.437934458788482e-06,
+      "loss": 0.5739,
+      "step": 720
+    },
+    {
+      "epoch": 1.001354096140826,
+      "grad_norm": 5.574532985687256,
+      "learning_rate": 7.33862959285005e-06,
+      "loss": 0.5443,
+      "step": 740
+    },
+    {
+      "epoch": 1.028436018957346,
+      "grad_norm": 5.275153160095215,
+      "learning_rate": 7.23932472691162e-06,
+      "loss": 0.4705,
+      "step": 760
+    },
+    {
+      "epoch": 1.055517941773866,
+      "grad_norm": 5.722527027130127,
+      "learning_rate": 7.140019860973188e-06,
+      "loss": 0.4692,
+      "step": 780
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "grad_norm": 5.501762866973877,
+      "learning_rate": 7.040714995034758e-06,
+      "loss": 0.4791,
+      "step": 800
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "eval_loss": 0.46895861625671387,
+      "eval_runtime": 1599.6376,
+      "eval_samples_per_second": 3.691,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 40.9726561658299,
+      "step": 800
+    },
+    {
+      "epoch": 1.1096817874069058,
+      "grad_norm": 5.207645893096924,
+      "learning_rate": 6.941410129096326e-06,
+      "loss": 0.4569,
+      "step": 820
+    },
+    {
+      "epoch": 1.1367637102234258,
+      "grad_norm": 5.584475517272949,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.4262,
+      "step": 840
+    },
+    {
+      "epoch": 1.1638456330399458,
+      "grad_norm": 5.881894588470459,
+      "learning_rate": 6.742800397219464e-06,
+      "loss": 0.4533,
+      "step": 860
+    },
+    {
+      "epoch": 1.1909275558564658,
+      "grad_norm": 6.939334869384766,
+      "learning_rate": 6.643495531281034e-06,
+      "loss": 0.4675,
+      "step": 880
+    },
+    {
+      "epoch": 1.2180094786729858,
+      "grad_norm": 5.780360698699951,
+      "learning_rate": 6.544190665342602e-06,
+      "loss": 0.4238,
+      "step": 900
+    },
+    {
+      "epoch": 1.2450914014895058,
+      "grad_norm": 5.867160797119141,
+      "learning_rate": 6.444885799404172e-06,
+      "loss": 0.444,
+      "step": 920
+    },
+    {
+      "epoch": 1.2721733243060258,
+      "grad_norm": 6.121824741363525,
+      "learning_rate": 6.34558093346574e-06,
+      "loss": 0.4333,
+      "step": 940
+    },
+    {
+      "epoch": 1.2992552471225456,
+      "grad_norm": 5.132157802581787,
+      "learning_rate": 6.24627606752731e-06,
+      "loss": 0.4544,
+      "step": 960
+    },
+    {
+      "epoch": 1.3263371699390656,
+      "grad_norm": 6.384315013885498,
+      "learning_rate": 6.146971201588878e-06,
+      "loss": 0.4332,
+      "step": 980
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "grad_norm": 4.54695987701416,
+      "learning_rate": 6.047666335650447e-06,
+      "loss": 0.4416,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "eval_loss": 0.43043428659439087,
+      "eval_runtime": 1614.3899,
+      "eval_samples_per_second": 3.658,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 38.00771402098731,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3805010155721056,
+      "grad_norm": 4.973900318145752,
+      "learning_rate": 5.948361469712016e-06,
+      "loss": 0.4401,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4075829383886256,
+      "grad_norm": 5.952788352966309,
+      "learning_rate": 5.849056603773585e-06,
+      "loss": 0.4865,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4346648612051456,
+      "grad_norm": 6.601942539215088,
+      "learning_rate": 5.749751737835154e-06,
+      "loss": 0.4435,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4617467840216656,
+      "grad_norm": 6.17143440246582,
+      "learning_rate": 5.650446871896723e-06,
+      "loss": 0.451,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4888287068381856,
+      "grad_norm": 5.782886981964111,
+      "learning_rate": 5.551142005958292e-06,
+      "loss": 0.4311,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5159106296547056,
+      "grad_norm": 5.734127998352051,
+      "learning_rate": 5.451837140019861e-06,
+      "loss": 0.4632,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5429925524712256,
+      "grad_norm": 5.601761341094971,
+      "learning_rate": 5.35253227408143e-06,
+      "loss": 0.424,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5700744752877456,
+      "grad_norm": 5.866110801696777,
+      "learning_rate": 5.253227408142999e-06,
+      "loss": 0.4273,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5971563981042654,
+      "grad_norm": 5.120361328125,
+      "learning_rate": 5.153922542204568e-06,
+      "loss": 0.4297,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "grad_norm": 5.093082427978516,
+      "learning_rate": 5.054617676266137e-06,
+      "loss": 0.4321,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "eval_loss": 0.3993258476257324,
+      "eval_runtime": 1619.3754,
+      "eval_samples_per_second": 3.646,
+      "eval_steps_per_second": 0.456,
+      "eval_wer": 37.091943373052636,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6513202437373053,
+      "grad_norm": 5.076949119567871,
+      "learning_rate": 4.955312810327706e-06,
+      "loss": 0.4446,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6784021665538253,
+      "grad_norm": 5.729442596435547,
+      "learning_rate": 4.856007944389276e-06,
+      "loss": 0.4375,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7054840893703453,
+      "grad_norm": 5.660022258758545,
+      "learning_rate": 4.756703078450844e-06,
+      "loss": 0.4318,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7325660121868651,
+      "grad_norm": 5.320847511291504,
+      "learning_rate": 4.657398212512414e-06,
+      "loss": 0.4255,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7596479350033851,
+      "grad_norm": 4.652419567108154,
+      "learning_rate": 4.558093346573982e-06,
+      "loss": 0.4231,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7867298578199051,
+      "grad_norm": 6.301181793212891,
+      "learning_rate": 4.458788480635551e-06,
+      "loss": 0.4426,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8138117806364251,
+      "grad_norm": 5.540495872497559,
+      "learning_rate": 4.35948361469712e-06,
+      "loss": 0.4361,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8408937034529451,
+      "grad_norm": 5.618797302246094,
+      "learning_rate": 4.260178748758689e-06,
+      "loss": 0.4081,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8679756262694651,
+      "grad_norm": 5.519278526306152,
+      "learning_rate": 4.160873882820258e-06,
+      "loss": 0.4311,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950575490859851,
+      "grad_norm": 5.24718713760376,
+      "learning_rate": 4.061569016881828e-06,
+      "loss": 0.441,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8950575490859851,
+      "eval_loss": 0.37384942173957825,
+      "eval_runtime": 1616.0813,
+      "eval_samples_per_second": 3.654,
+      "eval_steps_per_second": 0.457,
+      "eval_wer": 35.20006895214291,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9221394719025051,
+      "grad_norm": 5.9886884689331055,
+      "learning_rate": 3.962264150943396e-06,
+      "loss": 0.4125,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9492213947190251,
+      "grad_norm": 5.233187198638916,
+      "learning_rate": 3.862959285004966e-06,
+      "loss": 0.4179,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9763033175355451,
+      "grad_norm": 5.533965587615967,
+      "learning_rate": 3.763654419066535e-06,
+      "loss": 0.4272,
+      "step": 1460
+    },
+    {
+      "epoch": 2.002708192281652,
+      "grad_norm": 5.179864883422852,
+      "learning_rate": 3.664349553128104e-06,
+      "loss": 0.4082,
+      "step": 1480
+    },
+    {
+      "epoch": 2.029790115098172,
+      "grad_norm": 4.748936653137207,
+      "learning_rate": 3.565044687189673e-06,
+      "loss": 0.3085,
+      "step": 1500
+    },
+    {
+      "epoch": 2.056872037914692,
+      "grad_norm": 5.267838001251221,
+      "learning_rate": 3.4657398212512415e-06,
+      "loss": 0.312,
+      "step": 1520
+    },
+    {
+      "epoch": 2.083953960731212,
+      "grad_norm": 6.315608501434326,
+      "learning_rate": 3.3664349553128105e-06,
+      "loss": 0.3512,
+      "step": 1540
+    },
+    {
+      "epoch": 2.111035883547732,
+      "grad_norm": 5.232484340667725,
+      "learning_rate": 3.2671300893743795e-06,
+      "loss": 0.3184,
+      "step": 1560
+    },
+    {
+      "epoch": 2.138117806364252,
+      "grad_norm": 4.316751956939697,
+      "learning_rate": 3.1678252234359485e-06,
+      "loss": 0.3129,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1651997291807716,
+      "grad_norm": 4.040640354156494,
+      "learning_rate": 3.0685203574975175e-06,
+      "loss": 0.3073,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1651997291807716,
+      "eval_loss": 0.3516213595867157,
+      "eval_runtime": 1617.0984,
+      "eval_samples_per_second": 3.652,
+      "eval_steps_per_second": 0.457,
+      "eval_wer": 34.23258419703075,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.475941171396608e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1600/training_args.bin b/checkpoint-1600/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2a3b1da275660c7c7439512aa770d076034c70c
--- /dev/null
+++ b/checkpoint-1600/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d182356a12cee606170360f976946e1a56ce9d494fc1de269ffa184a80a19aa
+size 5432
diff --git a/checkpoint-1800/config.json b/checkpoint-1800/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..337642e18341c758364c32c6b6159a090615329b
--- /dev/null
+++ b/checkpoint-1800/config.json
@@ -0,0 +1,47 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
diff --git a/checkpoint-1800/generation_config.json b/checkpoint-1800/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec4263613bc098f8eb01034b73fbe16fb43eba5c
--- /dev/null
+++ b/checkpoint-1800/generation_config.json
@@ -0,0 +1,175 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      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": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.51.3"
+}
diff --git a/checkpoint-1800/model.safetensors b/checkpoint-1800/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3613c36171c761318a49bc89a8dc1a675537c8ac
--- /dev/null
+++ b/checkpoint-1800/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dc6dee26661153af82843dc98a2bf3c620d3eb96f9cccead9a0a30cc189e51e
+size 966995080
diff --git a/checkpoint-1800/optimizer.pt b/checkpoint-1800/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a9b025b42bb156479e51a094409df13cabdabd8a
--- /dev/null
+++ b/checkpoint-1800/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:477587882c393bea2cc1aefb308921ce1a0f3bba2d063d3ef09781c4d2c9903d
+size 1925064044
diff --git a/checkpoint-1800/preprocessor_config.json b/checkpoint-1800/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-1800/preprocessor_config.json
@@ -0,0 +1,15 @@
+{
+  "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,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-1800/rng_state.pth b/checkpoint-1800/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..716c877efff6620ca41c4642d0df6e1bf462a816
--- /dev/null
+++ b/checkpoint-1800/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c02f80a636544d120b715d6dca9e9c0e47f8b014a7a4861bdf4a0b8572e1441d
+size 14244
diff --git a/checkpoint-1800/scaler.pt b/checkpoint-1800/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fba40071182e6efa611de583ec8af198085839da
--- /dev/null
+++ b/checkpoint-1800/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83e85adb2cd8f94e8a73d4675c91bbf77e4ecf8433ddf2b612a7e29cbba96885
+size 988
diff --git a/checkpoint-1800/scheduler.pt b/checkpoint-1800/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..185cee0312b18637da6e713ef39a50f2d219acd7
--- /dev/null
+++ b/checkpoint-1800/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69d282d7d5684966027cd3da548aacffa1698b5f2194c7ffab99a06da17983f
+size 1064
diff --git a/checkpoint-1800/trainer_state.json b/checkpoint-1800/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..cb0fef1c6db4f575dff7634e55fc6dae7bc3a229
--- /dev/null
+++ b/checkpoint-1800/trainer_state.json
@@ -0,0 +1,745 @@
+{
+  "best_global_step": 1800,
+  "best_metric": 33.028076450688445,
+  "best_model_checkpoint": "./HAUSA_B/checkpoint-1800",
+  "epoch": 2.4360189573459716,
+  "eval_steps": 200,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027081922816519974,
+      "grad_norm": 106.59215545654297,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 6.1915,
+      "step": 20
+    },
+    {
+      "epoch": 0.05416384563303995,
+      "grad_norm": 30.563518524169922,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 4.5886,
+      "step": 40
+    },
+    {
+      "epoch": 0.08124576844955991,
+      "grad_norm": 16.528457641601562,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 3.0338,
+      "step": 60
+    },
+    {
+      "epoch": 0.1083276912660799,
+      "grad_norm": 13.852096557617188,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.13540961408259986,
+      "grad_norm": 13.284646987915039,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.9725,
+      "step": 100
+    },
+    {
+      "epoch": 0.16249153689911983,
+      "grad_norm": 13.212055206298828,
+      "learning_rate": 5.8e-06,
+      "loss": 1.7839,
+      "step": 120
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 12.006990432739258,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.5991,
+      "step": 140
+    },
+    {
+      "epoch": 0.2166553825321598,
+      "grad_norm": 12.490514755249023,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4411,
+      "step": 160
+    },
+    {
+      "epoch": 0.24373730534867977,
+      "grad_norm": 11.587646484375,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3487,
+      "step": 180
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "grad_norm": 11.574933052062988,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.2119,
+      "step": 200
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "eval_loss": 1.1157827377319336,
+      "eval_runtime": 1601.2991,
+      "eval_samples_per_second": 3.688,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 64.22461160550755,
+      "step": 200
+    },
+    {
+      "epoch": 0.2979011509817197,
+      "grad_norm": 8.368565559387207,
+      "learning_rate": 9.920556107249256e-06,
+      "loss": 0.9452,
+      "step": 220
+    },
+    {
+      "epoch": 0.32498307379823965,
+      "grad_norm": 7.2616682052612305,
+      "learning_rate": 9.821251241310825e-06,
+      "loss": 0.9298,
+      "step": 240
+    },
+    {
+      "epoch": 0.35206499661475965,
+      "grad_norm": 7.266394138336182,
+      "learning_rate": 9.721946375372395e-06,
+      "loss": 0.8567,
+      "step": 260
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 8.120067596435547,
+      "learning_rate": 9.622641509433963e-06,
+      "loss": 0.8251,
+      "step": 280
+    },
+    {
+      "epoch": 0.4062288422477996,
+      "grad_norm": 7.483547687530518,
+      "learning_rate": 9.523336643495532e-06,
+      "loss": 0.7774,
+      "step": 300
+    },
+    {
+      "epoch": 0.4333107650643196,
+      "grad_norm": 7.521896839141846,
+      "learning_rate": 9.4240317775571e-06,
+      "loss": 0.7266,
+      "step": 320
+    },
+    {
+      "epoch": 0.46039268788083954,
+      "grad_norm": 7.073266506195068,
+      "learning_rate": 9.32472691161867e-06,
+      "loss": 0.7248,
+      "step": 340
+    },
+    {
+      "epoch": 0.48747461069735953,
+      "grad_norm": 6.335423469543457,
+      "learning_rate": 9.22542204568024e-06,
+      "loss": 0.7151,
+      "step": 360
+    },
+    {
+      "epoch": 0.5145565335138795,
+      "grad_norm": 6.936922550201416,
+      "learning_rate": 9.126117179741808e-06,
+      "loss": 0.6881,
+      "step": 380
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "grad_norm": 7.596807479858398,
+      "learning_rate": 9.026812313803377e-06,
+      "loss": 0.6995,
+      "step": 400
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "eval_loss": 0.6352065801620483,
+      "eval_runtime": 1597.3635,
+      "eval_samples_per_second": 3.697,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 51.63653601672089,
+      "step": 400
+    },
+    {
+      "epoch": 0.5687203791469194,
+      "grad_norm": 6.981812477111816,
+      "learning_rate": 8.927507447864945e-06,
+      "loss": 0.6795,
+      "step": 420
+    },
+    {
+      "epoch": 0.5958023019634394,
+      "grad_norm": 6.481506824493408,
+      "learning_rate": 8.828202581926516e-06,
+      "loss": 0.6643,
+      "step": 440
+    },
+    {
+      "epoch": 0.6228842247799594,
+      "grad_norm": 6.537086009979248,
+      "learning_rate": 8.728897715988084e-06,
+      "loss": 0.6459,
+      "step": 460
+    },
+    {
+      "epoch": 0.6499661475964793,
+      "grad_norm": 6.739567756652832,
+      "learning_rate": 8.629592850049653e-06,
+      "loss": 0.6736,
+      "step": 480
+    },
+    {
+      "epoch": 0.6770480704129993,
+      "grad_norm": 7.422546863555908,
+      "learning_rate": 8.530287984111221e-06,
+      "loss": 0.6591,
+      "step": 500
+    },
+    {
+      "epoch": 0.7041299932295193,
+      "grad_norm": 5.7051215171813965,
+      "learning_rate": 8.430983118172792e-06,
+      "loss": 0.6442,
+      "step": 520
+    },
+    {
+      "epoch": 0.7312119160460393,
+      "grad_norm": 7.166143417358398,
+      "learning_rate": 8.33167825223436e-06,
+      "loss": 0.6326,
+      "step": 540
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "grad_norm": 7.759460926055908,
+      "learning_rate": 8.232373386295929e-06,
+      "loss": 0.6328,
+      "step": 560
+    },
+    {
+      "epoch": 0.7853757616790792,
+      "grad_norm": 5.876537799835205,
+      "learning_rate": 8.133068520357497e-06,
+      "loss": 0.5945,
+      "step": 580
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "grad_norm": 6.475106716156006,
+      "learning_rate": 8.033763654419066e-06,
+      "loss": 0.6038,
+      "step": 600
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "eval_loss": 0.5318673849105835,
+      "eval_runtime": 1614.0202,
+      "eval_samples_per_second": 3.659,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 44.61419121291129,
+      "step": 600
+    },
+    {
+      "epoch": 0.8395396073121192,
+      "grad_norm": 6.8348259925842285,
+      "learning_rate": 7.934458788480636e-06,
+      "loss": 0.6046,
+      "step": 620
+    },
+    {
+      "epoch": 0.8666215301286392,
+      "grad_norm": 6.060784339904785,
+      "learning_rate": 7.835153922542206e-06,
+      "loss": 0.6055,
+      "step": 640
+    },
+    {
+      "epoch": 0.8937034529451591,
+      "grad_norm": 6.01262903213501,
+      "learning_rate": 7.735849056603775e-06,
+      "loss": 0.6139,
+      "step": 660
+    },
+    {
+      "epoch": 0.9207853757616791,
+      "grad_norm": 6.706854820251465,
+      "learning_rate": 7.636544190665344e-06,
+      "loss": 0.5789,
+      "step": 680
+    },
+    {
+      "epoch": 0.9478672985781991,
+      "grad_norm": 6.464681625366211,
+      "learning_rate": 7.537239324726913e-06,
+      "loss": 0.5857,
+      "step": 700
+    },
+    {
+      "epoch": 0.9749492213947191,
+      "grad_norm": 7.8035478591918945,
+      "learning_rate": 7.437934458788482e-06,
+      "loss": 0.5739,
+      "step": 720
+    },
+    {
+      "epoch": 1.001354096140826,
+      "grad_norm": 5.574532985687256,
+      "learning_rate": 7.33862959285005e-06,
+      "loss": 0.5443,
+      "step": 740
+    },
+    {
+      "epoch": 1.028436018957346,
+      "grad_norm": 5.275153160095215,
+      "learning_rate": 7.23932472691162e-06,
+      "loss": 0.4705,
+      "step": 760
+    },
+    {
+      "epoch": 1.055517941773866,
+      "grad_norm": 5.722527027130127,
+      "learning_rate": 7.140019860973188e-06,
+      "loss": 0.4692,
+      "step": 780
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "grad_norm": 5.501762866973877,
+      "learning_rate": 7.040714995034758e-06,
+      "loss": 0.4791,
+      "step": 800
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "eval_loss": 0.46895861625671387,
+      "eval_runtime": 1599.6376,
+      "eval_samples_per_second": 3.691,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 40.9726561658299,
+      "step": 800
+    },
+    {
+      "epoch": 1.1096817874069058,
+      "grad_norm": 5.207645893096924,
+      "learning_rate": 6.941410129096326e-06,
+      "loss": 0.4569,
+      "step": 820
+    },
+    {
+      "epoch": 1.1367637102234258,
+      "grad_norm": 5.584475517272949,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.4262,
+      "step": 840
+    },
+    {
+      "epoch": 1.1638456330399458,
+      "grad_norm": 5.881894588470459,
+      "learning_rate": 6.742800397219464e-06,
+      "loss": 0.4533,
+      "step": 860
+    },
+    {
+      "epoch": 1.1909275558564658,
+      "grad_norm": 6.939334869384766,
+      "learning_rate": 6.643495531281034e-06,
+      "loss": 0.4675,
+      "step": 880
+    },
+    {
+      "epoch": 1.2180094786729858,
+      "grad_norm": 5.780360698699951,
+      "learning_rate": 6.544190665342602e-06,
+      "loss": 0.4238,
+      "step": 900
+    },
+    {
+      "epoch": 1.2450914014895058,
+      "grad_norm": 5.867160797119141,
+      "learning_rate": 6.444885799404172e-06,
+      "loss": 0.444,
+      "step": 920
+    },
+    {
+      "epoch": 1.2721733243060258,
+      "grad_norm": 6.121824741363525,
+      "learning_rate": 6.34558093346574e-06,
+      "loss": 0.4333,
+      "step": 940
+    },
+    {
+      "epoch": 1.2992552471225456,
+      "grad_norm": 5.132157802581787,
+      "learning_rate": 6.24627606752731e-06,
+      "loss": 0.4544,
+      "step": 960
+    },
+    {
+      "epoch": 1.3263371699390656,
+      "grad_norm": 6.384315013885498,
+      "learning_rate": 6.146971201588878e-06,
+      "loss": 0.4332,
+      "step": 980
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "grad_norm": 4.54695987701416,
+      "learning_rate": 6.047666335650447e-06,
+      "loss": 0.4416,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "eval_loss": 0.43043428659439087,
+      "eval_runtime": 1614.3899,
+      "eval_samples_per_second": 3.658,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 38.00771402098731,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3805010155721056,
+      "grad_norm": 4.973900318145752,
+      "learning_rate": 5.948361469712016e-06,
+      "loss": 0.4401,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4075829383886256,
+      "grad_norm": 5.952788352966309,
+      "learning_rate": 5.849056603773585e-06,
+      "loss": 0.4865,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4346648612051456,
+      "grad_norm": 6.601942539215088,
+      "learning_rate": 5.749751737835154e-06,
+      "loss": 0.4435,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4617467840216656,
+      "grad_norm": 6.17143440246582,
+      "learning_rate": 5.650446871896723e-06,
+      "loss": 0.451,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4888287068381856,
+      "grad_norm": 5.782886981964111,
+      "learning_rate": 5.551142005958292e-06,
+      "loss": 0.4311,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5159106296547056,
+      "grad_norm": 5.734127998352051,
+      "learning_rate": 5.451837140019861e-06,
+      "loss": 0.4632,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5429925524712256,
+      "grad_norm": 5.601761341094971,
+      "learning_rate": 5.35253227408143e-06,
+      "loss": 0.424,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5700744752877456,
+      "grad_norm": 5.866110801696777,
+      "learning_rate": 5.253227408142999e-06,
+      "loss": 0.4273,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5971563981042654,
+      "grad_norm": 5.120361328125,
+      "learning_rate": 5.153922542204568e-06,
+      "loss": 0.4297,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "grad_norm": 5.093082427978516,
+      "learning_rate": 5.054617676266137e-06,
+      "loss": 0.4321,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "eval_loss": 0.3993258476257324,
+      "eval_runtime": 1619.3754,
+      "eval_samples_per_second": 3.646,
+      "eval_steps_per_second": 0.456,
+      "eval_wer": 37.091943373052636,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6513202437373053,
+      "grad_norm": 5.076949119567871,
+      "learning_rate": 4.955312810327706e-06,
+      "loss": 0.4446,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6784021665538253,
+      "grad_norm": 5.729442596435547,
+      "learning_rate": 4.856007944389276e-06,
+      "loss": 0.4375,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7054840893703453,
+      "grad_norm": 5.660022258758545,
+      "learning_rate": 4.756703078450844e-06,
+      "loss": 0.4318,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7325660121868651,
+      "grad_norm": 5.320847511291504,
+      "learning_rate": 4.657398212512414e-06,
+      "loss": 0.4255,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7596479350033851,
+      "grad_norm": 4.652419567108154,
+      "learning_rate": 4.558093346573982e-06,
+      "loss": 0.4231,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7867298578199051,
+      "grad_norm": 6.301181793212891,
+      "learning_rate": 4.458788480635551e-06,
+      "loss": 0.4426,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8138117806364251,
+      "grad_norm": 5.540495872497559,
+      "learning_rate": 4.35948361469712e-06,
+      "loss": 0.4361,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8408937034529451,
+      "grad_norm": 5.618797302246094,
+      "learning_rate": 4.260178748758689e-06,
+      "loss": 0.4081,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8679756262694651,
+      "grad_norm": 5.519278526306152,
+      "learning_rate": 4.160873882820258e-06,
+      "loss": 0.4311,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950575490859851,
+      "grad_norm": 5.24718713760376,
+      "learning_rate": 4.061569016881828e-06,
+      "loss": 0.441,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8950575490859851,
+      "eval_loss": 0.37384942173957825,
+      "eval_runtime": 1616.0813,
+      "eval_samples_per_second": 3.654,
+      "eval_steps_per_second": 0.457,
+      "eval_wer": 35.20006895214291,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9221394719025051,
+      "grad_norm": 5.9886884689331055,
+      "learning_rate": 3.962264150943396e-06,
+      "loss": 0.4125,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9492213947190251,
+      "grad_norm": 5.233187198638916,
+      "learning_rate": 3.862959285004966e-06,
+      "loss": 0.4179,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9763033175355451,
+      "grad_norm": 5.533965587615967,
+      "learning_rate": 3.763654419066535e-06,
+      "loss": 0.4272,
+      "step": 1460
+    },
+    {
+      "epoch": 2.002708192281652,
+      "grad_norm": 5.179864883422852,
+      "learning_rate": 3.664349553128104e-06,
+      "loss": 0.4082,
+      "step": 1480
+    },
+    {
+      "epoch": 2.029790115098172,
+      "grad_norm": 4.748936653137207,
+      "learning_rate": 3.565044687189673e-06,
+      "loss": 0.3085,
+      "step": 1500
+    },
+    {
+      "epoch": 2.056872037914692,
+      "grad_norm": 5.267838001251221,
+      "learning_rate": 3.4657398212512415e-06,
+      "loss": 0.312,
+      "step": 1520
+    },
+    {
+      "epoch": 2.083953960731212,
+      "grad_norm": 6.315608501434326,
+      "learning_rate": 3.3664349553128105e-06,
+      "loss": 0.3512,
+      "step": 1540
+    },
+    {
+      "epoch": 2.111035883547732,
+      "grad_norm": 5.232484340667725,
+      "learning_rate": 3.2671300893743795e-06,
+      "loss": 0.3184,
+      "step": 1560
+    },
+    {
+      "epoch": 2.138117806364252,
+      "grad_norm": 4.316751956939697,
+      "learning_rate": 3.1678252234359485e-06,
+      "loss": 0.3129,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1651997291807716,
+      "grad_norm": 4.040640354156494,
+      "learning_rate": 3.0685203574975175e-06,
+      "loss": 0.3073,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1651997291807716,
+      "eval_loss": 0.3516213595867157,
+      "eval_runtime": 1617.0984,
+      "eval_samples_per_second": 3.652,
+      "eval_steps_per_second": 0.457,
+      "eval_wer": 34.23258419703075,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1922816519972916,
+      "grad_norm": 4.437410831451416,
+      "learning_rate": 2.9692154915590865e-06,
+      "loss": 0.3293,
+      "step": 1620
+    },
+    {
+      "epoch": 2.2193635748138116,
+      "grad_norm": 4.284883499145508,
+      "learning_rate": 2.8699106256206555e-06,
+      "loss": 0.3237,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2464454976303316,
+      "grad_norm": 4.959640979766846,
+      "learning_rate": 2.7706057596822245e-06,
+      "loss": 0.3374,
+      "step": 1660
+    },
+    {
+      "epoch": 2.2735274204468516,
+      "grad_norm": 5.366809368133545,
+      "learning_rate": 2.6713008937437935e-06,
+      "loss": 0.3086,
+      "step": 1680
+    },
+    {
+      "epoch": 2.3006093432633716,
+      "grad_norm": 4.363138198852539,
+      "learning_rate": 2.571996027805363e-06,
+      "loss": 0.331,
+      "step": 1700
+    },
+    {
+      "epoch": 2.3276912660798916,
+      "grad_norm": 4.7536468505859375,
+      "learning_rate": 2.4726911618669315e-06,
+      "loss": 0.317,
+      "step": 1720
+    },
+    {
+      "epoch": 2.3547731888964116,
+      "grad_norm": 4.352657794952393,
+      "learning_rate": 2.3733862959285005e-06,
+      "loss": 0.3008,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3818551117129316,
+      "grad_norm": 4.978397846221924,
+      "learning_rate": 2.2740814299900695e-06,
+      "loss": 0.3245,
+      "step": 1760
+    },
+    {
+      "epoch": 2.4089370345294516,
+      "grad_norm": 4.570504665374756,
+      "learning_rate": 2.174776564051639e-06,
+      "loss": 0.3147,
+      "step": 1780
+    },
+    {
+      "epoch": 2.4360189573459716,
+      "grad_norm": 5.904801845550537,
+      "learning_rate": 2.075471698113208e-06,
+      "loss": 0.3395,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4360189573459716,
+      "eval_loss": 0.3366335332393646,
+      "eval_runtime": 1614.6836,
+      "eval_samples_per_second": 3.657,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 33.028076450688445,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.660635827601408e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1800/training_args.bin b/checkpoint-1800/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2a3b1da275660c7c7439512aa770d076034c70c
--- /dev/null
+++ b/checkpoint-1800/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d182356a12cee606170360f976946e1a56ce9d494fc1de269ffa184a80a19aa
+size 5432
diff --git a/checkpoint-200/config.json b/checkpoint-200/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..337642e18341c758364c32c6b6159a090615329b
--- /dev/null
+++ b/checkpoint-200/config.json
@@ -0,0 +1,47 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
diff --git a/checkpoint-200/generation_config.json b/checkpoint-200/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec4263613bc098f8eb01034b73fbe16fb43eba5c
--- /dev/null
+++ b/checkpoint-200/generation_config.json
@@ -0,0 +1,175 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      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": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.51.3"
+}
diff --git a/checkpoint-200/model.safetensors b/checkpoint-200/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..021f787a76f81161d6d662e17b6d0b34e08e24fd
--- /dev/null
+++ b/checkpoint-200/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc159dbbb2204a002b5b86d37735b00b65e8f1275016f9d0fb847d11276be58
+size 966995080
diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d498cb1b609ad1b51580fea7972eebb379e9c32a
--- /dev/null
+++ b/checkpoint-200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58d8bb8c6f50e756538af9e3878da9c31a30dc0a88c3db9068a76d53d1b0d2fe
+size 1925064044
diff --git a/checkpoint-200/preprocessor_config.json b/checkpoint-200/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-200/preprocessor_config.json
@@ -0,0 +1,15 @@
+{
+  "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,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-200/rng_state.pth b/checkpoint-200/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5afecceece7428669edfa7b6bf3c4e2ff1f9bb31
--- /dev/null
+++ b/checkpoint-200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:754195ade1a9fba8e0250e2a761de2f39722175ebd64e81d651092d7346bb67c
+size 14244
diff --git a/checkpoint-200/scaler.pt b/checkpoint-200/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..301024517b9bd18cceaa75e0d050c891dc8e4f95
--- /dev/null
+++ b/checkpoint-200/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:204e7351292b4fdffdae64cb1ae46f8fcb473bd7203f6216c0f1d2c22875e855
+size 988
diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..635dafb37d95cb360b0283b33e79a1ee49a29ff7
--- /dev/null
+++ b/checkpoint-200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b551e44d36a93f06118444de4d46a48d68025b941ad3f20a21f7cd1e45875cd
+size 1064
diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..cc0787c2aa1ff434e6238de0256b6ebc2178c47f
--- /dev/null
+++ b/checkpoint-200/trainer_state.json
@@ -0,0 +1,113 @@
+{
+  "best_global_step": 200,
+  "best_metric": 64.22461160550755,
+  "best_model_checkpoint": "./HAUSA_B/checkpoint-200",
+  "epoch": 0.2708192281651997,
+  "eval_steps": 200,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027081922816519974,
+      "grad_norm": 106.59215545654297,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 6.1915,
+      "step": 20
+    },
+    {
+      "epoch": 0.05416384563303995,
+      "grad_norm": 30.563518524169922,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 4.5886,
+      "step": 40
+    },
+    {
+      "epoch": 0.08124576844955991,
+      "grad_norm": 16.528457641601562,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 3.0338,
+      "step": 60
+    },
+    {
+      "epoch": 0.1083276912660799,
+      "grad_norm": 13.852096557617188,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.13540961408259986,
+      "grad_norm": 13.284646987915039,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.9725,
+      "step": 100
+    },
+    {
+      "epoch": 0.16249153689911983,
+      "grad_norm": 13.212055206298828,
+      "learning_rate": 5.8e-06,
+      "loss": 1.7839,
+      "step": 120
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 12.006990432739258,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.5991,
+      "step": 140
+    },
+    {
+      "epoch": 0.2166553825321598,
+      "grad_norm": 12.490514755249023,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4411,
+      "step": 160
+    },
+    {
+      "epoch": 0.24373730534867977,
+      "grad_norm": 11.587646484375,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3487,
+      "step": 180
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "grad_norm": 11.574933052062988,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.2119,
+      "step": 200
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "eval_loss": 1.1157827377319336,
+      "eval_runtime": 1601.2991,
+      "eval_samples_per_second": 3.688,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 64.22461160550755,
+      "step": 200
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.846946562048e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2a3b1da275660c7c7439512aa770d076034c70c
--- /dev/null
+++ b/checkpoint-200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d182356a12cee606170360f976946e1a56ce9d494fc1de269ffa184a80a19aa
+size 5432
diff --git a/checkpoint-2000/config.json b/checkpoint-2000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..337642e18341c758364c32c6b6159a090615329b
--- /dev/null
+++ b/checkpoint-2000/config.json
@@ -0,0 +1,47 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
diff --git a/checkpoint-2000/generation_config.json b/checkpoint-2000/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec4263613bc098f8eb01034b73fbe16fb43eba5c
--- /dev/null
+++ b/checkpoint-2000/generation_config.json
@@ -0,0 +1,175 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      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": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.51.3"
+}
diff --git a/checkpoint-2000/model.safetensors b/checkpoint-2000/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7dc3076ef68aa0b27b02d14811146ace70f4b33e
--- /dev/null
+++ b/checkpoint-2000/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f8050989dd9d3ba60dddfe8082b5f3bb7ed4368a5c3460725416e61a9ebe3e
+size 966995080
diff --git a/checkpoint-2000/optimizer.pt b/checkpoint-2000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9ebc7d876feacd9a92afab1f9b3c2e19df98b2c9
--- /dev/null
+++ b/checkpoint-2000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:360aa6fb5834e15566e4eb4ce9632ca0654180c96a96da672f59689304aeb49f
+size 1925064044
diff --git a/checkpoint-2000/preprocessor_config.json b/checkpoint-2000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-2000/preprocessor_config.json
@@ -0,0 +1,15 @@
+{
+  "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,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-2000/rng_state.pth b/checkpoint-2000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1891c4400e7d42c2c7f3fde8aac6e462f80c73cf
--- /dev/null
+++ b/checkpoint-2000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1aff00c4f3279529262792fd261793d98da5d4568e48b4346f3fe69abccc5b6
+size 14244
diff --git a/checkpoint-2000/scaler.pt b/checkpoint-2000/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..61423d084d5c6b3e0d590142cabbf4c840ad316e
--- /dev/null
+++ b/checkpoint-2000/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f6abcb644665d1fd56bff09158e23082c1b1f12f08add6e0dd0cc949837621
+size 988
diff --git a/checkpoint-2000/scheduler.pt b/checkpoint-2000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f83e1c0b48fff7b706a354702bf290c6dd26acd2
--- /dev/null
+++ b/checkpoint-2000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d68c9945ce72f13ab5ad942ff530972e3d0789a27f2ac813dfab670f5f8eba9
+size 1064
diff --git a/checkpoint-2000/trainer_state.json b/checkpoint-2000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c325f08ecf708bd3505086def54221a9864df2d7
--- /dev/null
+++ b/checkpoint-2000/trainer_state.json
@@ -0,0 +1,824 @@
+{
+  "best_global_step": 2000,
+  "best_metric": 32.74580361567799,
+  "best_model_checkpoint": "./HAUSA_B/checkpoint-2000",
+  "epoch": 2.706838185511171,
+  "eval_steps": 200,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027081922816519974,
+      "grad_norm": 106.59215545654297,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 6.1915,
+      "step": 20
+    },
+    {
+      "epoch": 0.05416384563303995,
+      "grad_norm": 30.563518524169922,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 4.5886,
+      "step": 40
+    },
+    {
+      "epoch": 0.08124576844955991,
+      "grad_norm": 16.528457641601562,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 3.0338,
+      "step": 60
+    },
+    {
+      "epoch": 0.1083276912660799,
+      "grad_norm": 13.852096557617188,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.13540961408259986,
+      "grad_norm": 13.284646987915039,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.9725,
+      "step": 100
+    },
+    {
+      "epoch": 0.16249153689911983,
+      "grad_norm": 13.212055206298828,
+      "learning_rate": 5.8e-06,
+      "loss": 1.7839,
+      "step": 120
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 12.006990432739258,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.5991,
+      "step": 140
+    },
+    {
+      "epoch": 0.2166553825321598,
+      "grad_norm": 12.490514755249023,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4411,
+      "step": 160
+    },
+    {
+      "epoch": 0.24373730534867977,
+      "grad_norm": 11.587646484375,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3487,
+      "step": 180
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "grad_norm": 11.574933052062988,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.2119,
+      "step": 200
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "eval_loss": 1.1157827377319336,
+      "eval_runtime": 1601.2991,
+      "eval_samples_per_second": 3.688,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 64.22461160550755,
+      "step": 200
+    },
+    {
+      "epoch": 0.2979011509817197,
+      "grad_norm": 8.368565559387207,
+      "learning_rate": 9.920556107249256e-06,
+      "loss": 0.9452,
+      "step": 220
+    },
+    {
+      "epoch": 0.32498307379823965,
+      "grad_norm": 7.2616682052612305,
+      "learning_rate": 9.821251241310825e-06,
+      "loss": 0.9298,
+      "step": 240
+    },
+    {
+      "epoch": 0.35206499661475965,
+      "grad_norm": 7.266394138336182,
+      "learning_rate": 9.721946375372395e-06,
+      "loss": 0.8567,
+      "step": 260
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 8.120067596435547,
+      "learning_rate": 9.622641509433963e-06,
+      "loss": 0.8251,
+      "step": 280
+    },
+    {
+      "epoch": 0.4062288422477996,
+      "grad_norm": 7.483547687530518,
+      "learning_rate": 9.523336643495532e-06,
+      "loss": 0.7774,
+      "step": 300
+    },
+    {
+      "epoch": 0.4333107650643196,
+      "grad_norm": 7.521896839141846,
+      "learning_rate": 9.4240317775571e-06,
+      "loss": 0.7266,
+      "step": 320
+    },
+    {
+      "epoch": 0.46039268788083954,
+      "grad_norm": 7.073266506195068,
+      "learning_rate": 9.32472691161867e-06,
+      "loss": 0.7248,
+      "step": 340
+    },
+    {
+      "epoch": 0.48747461069735953,
+      "grad_norm": 6.335423469543457,
+      "learning_rate": 9.22542204568024e-06,
+      "loss": 0.7151,
+      "step": 360
+    },
+    {
+      "epoch": 0.5145565335138795,
+      "grad_norm": 6.936922550201416,
+      "learning_rate": 9.126117179741808e-06,
+      "loss": 0.6881,
+      "step": 380
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "grad_norm": 7.596807479858398,
+      "learning_rate": 9.026812313803377e-06,
+      "loss": 0.6995,
+      "step": 400
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "eval_loss": 0.6352065801620483,
+      "eval_runtime": 1597.3635,
+      "eval_samples_per_second": 3.697,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 51.63653601672089,
+      "step": 400
+    },
+    {
+      "epoch": 0.5687203791469194,
+      "grad_norm": 6.981812477111816,
+      "learning_rate": 8.927507447864945e-06,
+      "loss": 0.6795,
+      "step": 420
+    },
+    {
+      "epoch": 0.5958023019634394,
+      "grad_norm": 6.481506824493408,
+      "learning_rate": 8.828202581926516e-06,
+      "loss": 0.6643,
+      "step": 440
+    },
+    {
+      "epoch": 0.6228842247799594,
+      "grad_norm": 6.537086009979248,
+      "learning_rate": 8.728897715988084e-06,
+      "loss": 0.6459,
+      "step": 460
+    },
+    {
+      "epoch": 0.6499661475964793,
+      "grad_norm": 6.739567756652832,
+      "learning_rate": 8.629592850049653e-06,
+      "loss": 0.6736,
+      "step": 480
+    },
+    {
+      "epoch": 0.6770480704129993,
+      "grad_norm": 7.422546863555908,
+      "learning_rate": 8.530287984111221e-06,
+      "loss": 0.6591,
+      "step": 500
+    },
+    {
+      "epoch": 0.7041299932295193,
+      "grad_norm": 5.7051215171813965,
+      "learning_rate": 8.430983118172792e-06,
+      "loss": 0.6442,
+      "step": 520
+    },
+    {
+      "epoch": 0.7312119160460393,
+      "grad_norm": 7.166143417358398,
+      "learning_rate": 8.33167825223436e-06,
+      "loss": 0.6326,
+      "step": 540
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "grad_norm": 7.759460926055908,
+      "learning_rate": 8.232373386295929e-06,
+      "loss": 0.6328,
+      "step": 560
+    },
+    {
+      "epoch": 0.7853757616790792,
+      "grad_norm": 5.876537799835205,
+      "learning_rate": 8.133068520357497e-06,
+      "loss": 0.5945,
+      "step": 580
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "grad_norm": 6.475106716156006,
+      "learning_rate": 8.033763654419066e-06,
+      "loss": 0.6038,
+      "step": 600
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "eval_loss": 0.5318673849105835,
+      "eval_runtime": 1614.0202,
+      "eval_samples_per_second": 3.659,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 44.61419121291129,
+      "step": 600
+    },
+    {
+      "epoch": 0.8395396073121192,
+      "grad_norm": 6.8348259925842285,
+      "learning_rate": 7.934458788480636e-06,
+      "loss": 0.6046,
+      "step": 620
+    },
+    {
+      "epoch": 0.8666215301286392,
+      "grad_norm": 6.060784339904785,
+      "learning_rate": 7.835153922542206e-06,
+      "loss": 0.6055,
+      "step": 640
+    },
+    {
+      "epoch": 0.8937034529451591,
+      "grad_norm": 6.01262903213501,
+      "learning_rate": 7.735849056603775e-06,
+      "loss": 0.6139,
+      "step": 660
+    },
+    {
+      "epoch": 0.9207853757616791,
+      "grad_norm": 6.706854820251465,
+      "learning_rate": 7.636544190665344e-06,
+      "loss": 0.5789,
+      "step": 680
+    },
+    {
+      "epoch": 0.9478672985781991,
+      "grad_norm": 6.464681625366211,
+      "learning_rate": 7.537239324726913e-06,
+      "loss": 0.5857,
+      "step": 700
+    },
+    {
+      "epoch": 0.9749492213947191,
+      "grad_norm": 7.8035478591918945,
+      "learning_rate": 7.437934458788482e-06,
+      "loss": 0.5739,
+      "step": 720
+    },
+    {
+      "epoch": 1.001354096140826,
+      "grad_norm": 5.574532985687256,
+      "learning_rate": 7.33862959285005e-06,
+      "loss": 0.5443,
+      "step": 740
+    },
+    {
+      "epoch": 1.028436018957346,
+      "grad_norm": 5.275153160095215,
+      "learning_rate": 7.23932472691162e-06,
+      "loss": 0.4705,
+      "step": 760
+    },
+    {
+      "epoch": 1.055517941773866,
+      "grad_norm": 5.722527027130127,
+      "learning_rate": 7.140019860973188e-06,
+      "loss": 0.4692,
+      "step": 780
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "grad_norm": 5.501762866973877,
+      "learning_rate": 7.040714995034758e-06,
+      "loss": 0.4791,
+      "step": 800
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "eval_loss": 0.46895861625671387,
+      "eval_runtime": 1599.6376,
+      "eval_samples_per_second": 3.691,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 40.9726561658299,
+      "step": 800
+    },
+    {
+      "epoch": 1.1096817874069058,
+      "grad_norm": 5.207645893096924,
+      "learning_rate": 6.941410129096326e-06,
+      "loss": 0.4569,
+      "step": 820
+    },
+    {
+      "epoch": 1.1367637102234258,
+      "grad_norm": 5.584475517272949,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.4262,
+      "step": 840
+    },
+    {
+      "epoch": 1.1638456330399458,
+      "grad_norm": 5.881894588470459,
+      "learning_rate": 6.742800397219464e-06,
+      "loss": 0.4533,
+      "step": 860
+    },
+    {
+      "epoch": 1.1909275558564658,
+      "grad_norm": 6.939334869384766,
+      "learning_rate": 6.643495531281034e-06,
+      "loss": 0.4675,
+      "step": 880
+    },
+    {
+      "epoch": 1.2180094786729858,
+      "grad_norm": 5.780360698699951,
+      "learning_rate": 6.544190665342602e-06,
+      "loss": 0.4238,
+      "step": 900
+    },
+    {
+      "epoch": 1.2450914014895058,
+      "grad_norm": 5.867160797119141,
+      "learning_rate": 6.444885799404172e-06,
+      "loss": 0.444,
+      "step": 920
+    },
+    {
+      "epoch": 1.2721733243060258,
+      "grad_norm": 6.121824741363525,
+      "learning_rate": 6.34558093346574e-06,
+      "loss": 0.4333,
+      "step": 940
+    },
+    {
+      "epoch": 1.2992552471225456,
+      "grad_norm": 5.132157802581787,
+      "learning_rate": 6.24627606752731e-06,
+      "loss": 0.4544,
+      "step": 960
+    },
+    {
+      "epoch": 1.3263371699390656,
+      "grad_norm": 6.384315013885498,
+      "learning_rate": 6.146971201588878e-06,
+      "loss": 0.4332,
+      "step": 980
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "grad_norm": 4.54695987701416,
+      "learning_rate": 6.047666335650447e-06,
+      "loss": 0.4416,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "eval_loss": 0.43043428659439087,
+      "eval_runtime": 1614.3899,
+      "eval_samples_per_second": 3.658,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 38.00771402098731,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3805010155721056,
+      "grad_norm": 4.973900318145752,
+      "learning_rate": 5.948361469712016e-06,
+      "loss": 0.4401,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4075829383886256,
+      "grad_norm": 5.952788352966309,
+      "learning_rate": 5.849056603773585e-06,
+      "loss": 0.4865,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4346648612051456,
+      "grad_norm": 6.601942539215088,
+      "learning_rate": 5.749751737835154e-06,
+      "loss": 0.4435,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4617467840216656,
+      "grad_norm": 6.17143440246582,
+      "learning_rate": 5.650446871896723e-06,
+      "loss": 0.451,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4888287068381856,
+      "grad_norm": 5.782886981964111,
+      "learning_rate": 5.551142005958292e-06,
+      "loss": 0.4311,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5159106296547056,
+      "grad_norm": 5.734127998352051,
+      "learning_rate": 5.451837140019861e-06,
+      "loss": 0.4632,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5429925524712256,
+      "grad_norm": 5.601761341094971,
+      "learning_rate": 5.35253227408143e-06,
+      "loss": 0.424,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5700744752877456,
+      "grad_norm": 5.866110801696777,
+      "learning_rate": 5.253227408142999e-06,
+      "loss": 0.4273,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5971563981042654,
+      "grad_norm": 5.120361328125,
+      "learning_rate": 5.153922542204568e-06,
+      "loss": 0.4297,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "grad_norm": 5.093082427978516,
+      "learning_rate": 5.054617676266137e-06,
+      "loss": 0.4321,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "eval_loss": 0.3993258476257324,
+      "eval_runtime": 1619.3754,
+      "eval_samples_per_second": 3.646,
+      "eval_steps_per_second": 0.456,
+      "eval_wer": 37.091943373052636,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6513202437373053,
+      "grad_norm": 5.076949119567871,
+      "learning_rate": 4.955312810327706e-06,
+      "loss": 0.4446,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6784021665538253,
+      "grad_norm": 5.729442596435547,
+      "learning_rate": 4.856007944389276e-06,
+      "loss": 0.4375,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7054840893703453,
+      "grad_norm": 5.660022258758545,
+      "learning_rate": 4.756703078450844e-06,
+      "loss": 0.4318,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7325660121868651,
+      "grad_norm": 5.320847511291504,
+      "learning_rate": 4.657398212512414e-06,
+      "loss": 0.4255,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7596479350033851,
+      "grad_norm": 4.652419567108154,
+      "learning_rate": 4.558093346573982e-06,
+      "loss": 0.4231,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7867298578199051,
+      "grad_norm": 6.301181793212891,
+      "learning_rate": 4.458788480635551e-06,
+      "loss": 0.4426,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8138117806364251,
+      "grad_norm": 5.540495872497559,
+      "learning_rate": 4.35948361469712e-06,
+      "loss": 0.4361,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8408937034529451,
+      "grad_norm": 5.618797302246094,
+      "learning_rate": 4.260178748758689e-06,
+      "loss": 0.4081,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8679756262694651,
+      "grad_norm": 5.519278526306152,
+      "learning_rate": 4.160873882820258e-06,
+      "loss": 0.4311,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950575490859851,
+      "grad_norm": 5.24718713760376,
+      "learning_rate": 4.061569016881828e-06,
+      "loss": 0.441,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8950575490859851,
+      "eval_loss": 0.37384942173957825,
+      "eval_runtime": 1616.0813,
+      "eval_samples_per_second": 3.654,
+      "eval_steps_per_second": 0.457,
+      "eval_wer": 35.20006895214291,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9221394719025051,
+      "grad_norm": 5.9886884689331055,
+      "learning_rate": 3.962264150943396e-06,
+      "loss": 0.4125,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9492213947190251,
+      "grad_norm": 5.233187198638916,
+      "learning_rate": 3.862959285004966e-06,
+      "loss": 0.4179,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9763033175355451,
+      "grad_norm": 5.533965587615967,
+      "learning_rate": 3.763654419066535e-06,
+      "loss": 0.4272,
+      "step": 1460
+    },
+    {
+      "epoch": 2.002708192281652,
+      "grad_norm": 5.179864883422852,
+      "learning_rate": 3.664349553128104e-06,
+      "loss": 0.4082,
+      "step": 1480
+    },
+    {
+      "epoch": 2.029790115098172,
+      "grad_norm": 4.748936653137207,
+      "learning_rate": 3.565044687189673e-06,
+      "loss": 0.3085,
+      "step": 1500
+    },
+    {
+      "epoch": 2.056872037914692,
+      "grad_norm": 5.267838001251221,
+      "learning_rate": 3.4657398212512415e-06,
+      "loss": 0.312,
+      "step": 1520
+    },
+    {
+      "epoch": 2.083953960731212,
+      "grad_norm": 6.315608501434326,
+      "learning_rate": 3.3664349553128105e-06,
+      "loss": 0.3512,
+      "step": 1540
+    },
+    {
+      "epoch": 2.111035883547732,
+      "grad_norm": 5.232484340667725,
+      "learning_rate": 3.2671300893743795e-06,
+      "loss": 0.3184,
+      "step": 1560
+    },
+    {
+      "epoch": 2.138117806364252,
+      "grad_norm": 4.316751956939697,
+      "learning_rate": 3.1678252234359485e-06,
+      "loss": 0.3129,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1651997291807716,
+      "grad_norm": 4.040640354156494,
+      "learning_rate": 3.0685203574975175e-06,
+      "loss": 0.3073,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1651997291807716,
+      "eval_loss": 0.3516213595867157,
+      "eval_runtime": 1617.0984,
+      "eval_samples_per_second": 3.652,
+      "eval_steps_per_second": 0.457,
+      "eval_wer": 34.23258419703075,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1922816519972916,
+      "grad_norm": 4.437410831451416,
+      "learning_rate": 2.9692154915590865e-06,
+      "loss": 0.3293,
+      "step": 1620
+    },
+    {
+      "epoch": 2.2193635748138116,
+      "grad_norm": 4.284883499145508,
+      "learning_rate": 2.8699106256206555e-06,
+      "loss": 0.3237,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2464454976303316,
+      "grad_norm": 4.959640979766846,
+      "learning_rate": 2.7706057596822245e-06,
+      "loss": 0.3374,
+      "step": 1660
+    },
+    {
+      "epoch": 2.2735274204468516,
+      "grad_norm": 5.366809368133545,
+      "learning_rate": 2.6713008937437935e-06,
+      "loss": 0.3086,
+      "step": 1680
+    },
+    {
+      "epoch": 2.3006093432633716,
+      "grad_norm": 4.363138198852539,
+      "learning_rate": 2.571996027805363e-06,
+      "loss": 0.331,
+      "step": 1700
+    },
+    {
+      "epoch": 2.3276912660798916,
+      "grad_norm": 4.7536468505859375,
+      "learning_rate": 2.4726911618669315e-06,
+      "loss": 0.317,
+      "step": 1720
+    },
+    {
+      "epoch": 2.3547731888964116,
+      "grad_norm": 4.352657794952393,
+      "learning_rate": 2.3733862959285005e-06,
+      "loss": 0.3008,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3818551117129316,
+      "grad_norm": 4.978397846221924,
+      "learning_rate": 2.2740814299900695e-06,
+      "loss": 0.3245,
+      "step": 1760
+    },
+    {
+      "epoch": 2.4089370345294516,
+      "grad_norm": 4.570504665374756,
+      "learning_rate": 2.174776564051639e-06,
+      "loss": 0.3147,
+      "step": 1780
+    },
+    {
+      "epoch": 2.4360189573459716,
+      "grad_norm": 5.904801845550537,
+      "learning_rate": 2.075471698113208e-06,
+      "loss": 0.3395,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4360189573459716,
+      "eval_loss": 0.3366335332393646,
+      "eval_runtime": 1614.6836,
+      "eval_samples_per_second": 3.657,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 33.028076450688445,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4631008801624916,
+      "grad_norm": 5.771766185760498,
+      "learning_rate": 1.976166832174777e-06,
+      "loss": 0.3064,
+      "step": 1820
+    },
+    {
+      "epoch": 2.4901828029790116,
+      "grad_norm": 5.262455463409424,
+      "learning_rate": 1.8768619662363458e-06,
+      "loss": 0.2961,
+      "step": 1840
+    },
+    {
+      "epoch": 2.5172647257955316,
+      "grad_norm": 5.288928031921387,
+      "learning_rate": 1.7775571002979148e-06,
+      "loss": 0.3285,
+      "step": 1860
+    },
+    {
+      "epoch": 2.5443466486120516,
+      "grad_norm": 5.816193580627441,
+      "learning_rate": 1.6782522343594838e-06,
+      "loss": 0.3254,
+      "step": 1880
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 5.249015808105469,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.3279,
+      "step": 1900
+    },
+    {
+      "epoch": 2.598510494245091,
+      "grad_norm": 4.509056568145752,
+      "learning_rate": 1.4796425024826216e-06,
+      "loss": 0.317,
+      "step": 1920
+    },
+    {
+      "epoch": 2.625592417061611,
+      "grad_norm": 4.113898754119873,
+      "learning_rate": 1.3803376365441908e-06,
+      "loss": 0.3135,
+      "step": 1940
+    },
+    {
+      "epoch": 2.652674339878131,
+      "grad_norm": 5.507041931152344,
+      "learning_rate": 1.2810327706057598e-06,
+      "loss": 0.3302,
+      "step": 1960
+    },
+    {
+      "epoch": 2.679756262694651,
+      "grad_norm": 4.8485846519470215,
+      "learning_rate": 1.1817279046673288e-06,
+      "loss": 0.3106,
+      "step": 1980
+    },
+    {
+      "epoch": 2.706838185511171,
+      "grad_norm": 5.389250755310059,
+      "learning_rate": 1.0824230387288978e-06,
+      "loss": 0.3347,
+      "step": 2000
+    },
+    {
+      "epoch": 2.706838185511171,
+      "eval_loss": 0.3267146348953247,
+      "eval_runtime": 1650.7646,
+      "eval_samples_per_second": 3.577,
+      "eval_steps_per_second": 0.448,
+      "eval_wer": 32.74580361567799,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.845330483806208e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2000/training_args.bin b/checkpoint-2000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2a3b1da275660c7c7439512aa770d076034c70c
--- /dev/null
+++ b/checkpoint-2000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d182356a12cee606170360f976946e1a56ce9d494fc1de269ffa184a80a19aa
+size 5432
diff --git a/checkpoint-2200/config.json b/checkpoint-2200/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..337642e18341c758364c32c6b6159a090615329b
--- /dev/null
+++ b/checkpoint-2200/config.json
@@ -0,0 +1,47 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
diff --git a/checkpoint-2200/generation_config.json b/checkpoint-2200/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec4263613bc098f8eb01034b73fbe16fb43eba5c
--- /dev/null
+++ b/checkpoint-2200/generation_config.json
@@ -0,0 +1,175 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      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": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.51.3"
+}
diff --git a/checkpoint-2200/model.safetensors b/checkpoint-2200/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6fc41fb2a263f58e06e1c8628cf0104945105836
--- /dev/null
+++ b/checkpoint-2200/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dee1ad34a5b830cd61cfa84d69221af6901c37be090f3ebf7dc73af805879162
+size 966995080
diff --git a/checkpoint-2200/optimizer.pt b/checkpoint-2200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4f64b8b8c31e0d5c347315cc14aa63921d0c266a
--- /dev/null
+++ b/checkpoint-2200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0abca534d2a0566079dcd0c065f74b653f128f9ee081a831d1763806e2da370
+size 1925064044
diff --git a/checkpoint-2200/preprocessor_config.json b/checkpoint-2200/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-2200/preprocessor_config.json
@@ -0,0 +1,15 @@
+{
+  "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,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-2200/rng_state.pth b/checkpoint-2200/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ae867b6a7c590fa559d6002bcb2f2a9e0ae2f04d
--- /dev/null
+++ b/checkpoint-2200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344c371ec2620dae2f1ad1bae8430f06939cdf192fdc2eecbff808e88b0fe4ad
+size 14244
diff --git a/checkpoint-2200/scaler.pt b/checkpoint-2200/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..949ebef601154dfd2551d8fa05592d84be015e3f
--- /dev/null
+++ b/checkpoint-2200/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d06488fb6d49291655217385de047a66f999fefe8f57591bb657809b32efc79e
+size 988
diff --git a/checkpoint-2200/scheduler.pt b/checkpoint-2200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e3a68c95a74d3d1287307b9cae2eb4124d083146
--- /dev/null
+++ b/checkpoint-2200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e90d606e610a778d87ab2f8037ce5078f9b3c1ea190e900b208b86465cf8efb
+size 1064
diff --git a/checkpoint-2200/trainer_state.json b/checkpoint-2200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..506cb1a93476d1c97f8faf7334c1ec6efc6a08fe
--- /dev/null
+++ b/checkpoint-2200/trainer_state.json
@@ -0,0 +1,903 @@
+{
+  "best_global_step": 2000,
+  "best_metric": 32.74580361567799,
+  "best_model_checkpoint": "./HAUSA_B/checkpoint-2000",
+  "epoch": 2.977657413676371,
+  "eval_steps": 200,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027081922816519974,
+      "grad_norm": 106.59215545654297,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 6.1915,
+      "step": 20
+    },
+    {
+      "epoch": 0.05416384563303995,
+      "grad_norm": 30.563518524169922,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 4.5886,
+      "step": 40
+    },
+    {
+      "epoch": 0.08124576844955991,
+      "grad_norm": 16.528457641601562,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 3.0338,
+      "step": 60
+    },
+    {
+      "epoch": 0.1083276912660799,
+      "grad_norm": 13.852096557617188,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.13540961408259986,
+      "grad_norm": 13.284646987915039,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.9725,
+      "step": 100
+    },
+    {
+      "epoch": 0.16249153689911983,
+      "grad_norm": 13.212055206298828,
+      "learning_rate": 5.8e-06,
+      "loss": 1.7839,
+      "step": 120
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 12.006990432739258,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.5991,
+      "step": 140
+    },
+    {
+      "epoch": 0.2166553825321598,
+      "grad_norm": 12.490514755249023,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4411,
+      "step": 160
+    },
+    {
+      "epoch": 0.24373730534867977,
+      "grad_norm": 11.587646484375,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3487,
+      "step": 180
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "grad_norm": 11.574933052062988,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.2119,
+      "step": 200
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "eval_loss": 1.1157827377319336,
+      "eval_runtime": 1601.2991,
+      "eval_samples_per_second": 3.688,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 64.22461160550755,
+      "step": 200
+    },
+    {
+      "epoch": 0.2979011509817197,
+      "grad_norm": 8.368565559387207,
+      "learning_rate": 9.920556107249256e-06,
+      "loss": 0.9452,
+      "step": 220
+    },
+    {
+      "epoch": 0.32498307379823965,
+      "grad_norm": 7.2616682052612305,
+      "learning_rate": 9.821251241310825e-06,
+      "loss": 0.9298,
+      "step": 240
+    },
+    {
+      "epoch": 0.35206499661475965,
+      "grad_norm": 7.266394138336182,
+      "learning_rate": 9.721946375372395e-06,
+      "loss": 0.8567,
+      "step": 260
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 8.120067596435547,
+      "learning_rate": 9.622641509433963e-06,
+      "loss": 0.8251,
+      "step": 280
+    },
+    {
+      "epoch": 0.4062288422477996,
+      "grad_norm": 7.483547687530518,
+      "learning_rate": 9.523336643495532e-06,
+      "loss": 0.7774,
+      "step": 300
+    },
+    {
+      "epoch": 0.4333107650643196,
+      "grad_norm": 7.521896839141846,
+      "learning_rate": 9.4240317775571e-06,
+      "loss": 0.7266,
+      "step": 320
+    },
+    {
+      "epoch": 0.46039268788083954,
+      "grad_norm": 7.073266506195068,
+      "learning_rate": 9.32472691161867e-06,
+      "loss": 0.7248,
+      "step": 340
+    },
+    {
+      "epoch": 0.48747461069735953,
+      "grad_norm": 6.335423469543457,
+      "learning_rate": 9.22542204568024e-06,
+      "loss": 0.7151,
+      "step": 360
+    },
+    {
+      "epoch": 0.5145565335138795,
+      "grad_norm": 6.936922550201416,
+      "learning_rate": 9.126117179741808e-06,
+      "loss": 0.6881,
+      "step": 380
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "grad_norm": 7.596807479858398,
+      "learning_rate": 9.026812313803377e-06,
+      "loss": 0.6995,
+      "step": 400
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "eval_loss": 0.6352065801620483,
+      "eval_runtime": 1597.3635,
+      "eval_samples_per_second": 3.697,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 51.63653601672089,
+      "step": 400
+    },
+    {
+      "epoch": 0.5687203791469194,
+      "grad_norm": 6.981812477111816,
+      "learning_rate": 8.927507447864945e-06,
+      "loss": 0.6795,
+      "step": 420
+    },
+    {
+      "epoch": 0.5958023019634394,
+      "grad_norm": 6.481506824493408,
+      "learning_rate": 8.828202581926516e-06,
+      "loss": 0.6643,
+      "step": 440
+    },
+    {
+      "epoch": 0.6228842247799594,
+      "grad_norm": 6.537086009979248,
+      "learning_rate": 8.728897715988084e-06,
+      "loss": 0.6459,
+      "step": 460
+    },
+    {
+      "epoch": 0.6499661475964793,
+      "grad_norm": 6.739567756652832,
+      "learning_rate": 8.629592850049653e-06,
+      "loss": 0.6736,
+      "step": 480
+    },
+    {
+      "epoch": 0.6770480704129993,
+      "grad_norm": 7.422546863555908,
+      "learning_rate": 8.530287984111221e-06,
+      "loss": 0.6591,
+      "step": 500
+    },
+    {
+      "epoch": 0.7041299932295193,
+      "grad_norm": 5.7051215171813965,
+      "learning_rate": 8.430983118172792e-06,
+      "loss": 0.6442,
+      "step": 520
+    },
+    {
+      "epoch": 0.7312119160460393,
+      "grad_norm": 7.166143417358398,
+      "learning_rate": 8.33167825223436e-06,
+      "loss": 0.6326,
+      "step": 540
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "grad_norm": 7.759460926055908,
+      "learning_rate": 8.232373386295929e-06,
+      "loss": 0.6328,
+      "step": 560
+    },
+    {
+      "epoch": 0.7853757616790792,
+      "grad_norm": 5.876537799835205,
+      "learning_rate": 8.133068520357497e-06,
+      "loss": 0.5945,
+      "step": 580
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "grad_norm": 6.475106716156006,
+      "learning_rate": 8.033763654419066e-06,
+      "loss": 0.6038,
+      "step": 600
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "eval_loss": 0.5318673849105835,
+      "eval_runtime": 1614.0202,
+      "eval_samples_per_second": 3.659,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 44.61419121291129,
+      "step": 600
+    },
+    {
+      "epoch": 0.8395396073121192,
+      "grad_norm": 6.8348259925842285,
+      "learning_rate": 7.934458788480636e-06,
+      "loss": 0.6046,
+      "step": 620
+    },
+    {
+      "epoch": 0.8666215301286392,
+      "grad_norm": 6.060784339904785,
+      "learning_rate": 7.835153922542206e-06,
+      "loss": 0.6055,
+      "step": 640
+    },
+    {
+      "epoch": 0.8937034529451591,
+      "grad_norm": 6.01262903213501,
+      "learning_rate": 7.735849056603775e-06,
+      "loss": 0.6139,
+      "step": 660
+    },
+    {
+      "epoch": 0.9207853757616791,
+      "grad_norm": 6.706854820251465,
+      "learning_rate": 7.636544190665344e-06,
+      "loss": 0.5789,
+      "step": 680
+    },
+    {
+      "epoch": 0.9478672985781991,
+      "grad_norm": 6.464681625366211,
+      "learning_rate": 7.537239324726913e-06,
+      "loss": 0.5857,
+      "step": 700
+    },
+    {
+      "epoch": 0.9749492213947191,
+      "grad_norm": 7.8035478591918945,
+      "learning_rate": 7.437934458788482e-06,
+      "loss": 0.5739,
+      "step": 720
+    },
+    {
+      "epoch": 1.001354096140826,
+      "grad_norm": 5.574532985687256,
+      "learning_rate": 7.33862959285005e-06,
+      "loss": 0.5443,
+      "step": 740
+    },
+    {
+      "epoch": 1.028436018957346,
+      "grad_norm": 5.275153160095215,
+      "learning_rate": 7.23932472691162e-06,
+      "loss": 0.4705,
+      "step": 760
+    },
+    {
+      "epoch": 1.055517941773866,
+      "grad_norm": 5.722527027130127,
+      "learning_rate": 7.140019860973188e-06,
+      "loss": 0.4692,
+      "step": 780
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "grad_norm": 5.501762866973877,
+      "learning_rate": 7.040714995034758e-06,
+      "loss": 0.4791,
+      "step": 800
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "eval_loss": 0.46895861625671387,
+      "eval_runtime": 1599.6376,
+      "eval_samples_per_second": 3.691,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 40.9726561658299,
+      "step": 800
+    },
+    {
+      "epoch": 1.1096817874069058,
+      "grad_norm": 5.207645893096924,
+      "learning_rate": 6.941410129096326e-06,
+      "loss": 0.4569,
+      "step": 820
+    },
+    {
+      "epoch": 1.1367637102234258,
+      "grad_norm": 5.584475517272949,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.4262,
+      "step": 840
+    },
+    {
+      "epoch": 1.1638456330399458,
+      "grad_norm": 5.881894588470459,
+      "learning_rate": 6.742800397219464e-06,
+      "loss": 0.4533,
+      "step": 860
+    },
+    {
+      "epoch": 1.1909275558564658,
+      "grad_norm": 6.939334869384766,
+      "learning_rate": 6.643495531281034e-06,
+      "loss": 0.4675,
+      "step": 880
+    },
+    {
+      "epoch": 1.2180094786729858,
+      "grad_norm": 5.780360698699951,
+      "learning_rate": 6.544190665342602e-06,
+      "loss": 0.4238,
+      "step": 900
+    },
+    {
+      "epoch": 1.2450914014895058,
+      "grad_norm": 5.867160797119141,
+      "learning_rate": 6.444885799404172e-06,
+      "loss": 0.444,
+      "step": 920
+    },
+    {
+      "epoch": 1.2721733243060258,
+      "grad_norm": 6.121824741363525,
+      "learning_rate": 6.34558093346574e-06,
+      "loss": 0.4333,
+      "step": 940
+    },
+    {
+      "epoch": 1.2992552471225456,
+      "grad_norm": 5.132157802581787,
+      "learning_rate": 6.24627606752731e-06,
+      "loss": 0.4544,
+      "step": 960
+    },
+    {
+      "epoch": 1.3263371699390656,
+      "grad_norm": 6.384315013885498,
+      "learning_rate": 6.146971201588878e-06,
+      "loss": 0.4332,
+      "step": 980
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "grad_norm": 4.54695987701416,
+      "learning_rate": 6.047666335650447e-06,
+      "loss": 0.4416,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "eval_loss": 0.43043428659439087,
+      "eval_runtime": 1614.3899,
+      "eval_samples_per_second": 3.658,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 38.00771402098731,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3805010155721056,
+      "grad_norm": 4.973900318145752,
+      "learning_rate": 5.948361469712016e-06,
+      "loss": 0.4401,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4075829383886256,
+      "grad_norm": 5.952788352966309,
+      "learning_rate": 5.849056603773585e-06,
+      "loss": 0.4865,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4346648612051456,
+      "grad_norm": 6.601942539215088,
+      "learning_rate": 5.749751737835154e-06,
+      "loss": 0.4435,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4617467840216656,
+      "grad_norm": 6.17143440246582,
+      "learning_rate": 5.650446871896723e-06,
+      "loss": 0.451,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4888287068381856,
+      "grad_norm": 5.782886981964111,
+      "learning_rate": 5.551142005958292e-06,
+      "loss": 0.4311,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5159106296547056,
+      "grad_norm": 5.734127998352051,
+      "learning_rate": 5.451837140019861e-06,
+      "loss": 0.4632,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5429925524712256,
+      "grad_norm": 5.601761341094971,
+      "learning_rate": 5.35253227408143e-06,
+      "loss": 0.424,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5700744752877456,
+      "grad_norm": 5.866110801696777,
+      "learning_rate": 5.253227408142999e-06,
+      "loss": 0.4273,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5971563981042654,
+      "grad_norm": 5.120361328125,
+      "learning_rate": 5.153922542204568e-06,
+      "loss": 0.4297,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "grad_norm": 5.093082427978516,
+      "learning_rate": 5.054617676266137e-06,
+      "loss": 0.4321,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "eval_loss": 0.3993258476257324,
+      "eval_runtime": 1619.3754,
+      "eval_samples_per_second": 3.646,
+      "eval_steps_per_second": 0.456,
+      "eval_wer": 37.091943373052636,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6513202437373053,
+      "grad_norm": 5.076949119567871,
+      "learning_rate": 4.955312810327706e-06,
+      "loss": 0.4446,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6784021665538253,
+      "grad_norm": 5.729442596435547,
+      "learning_rate": 4.856007944389276e-06,
+      "loss": 0.4375,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7054840893703453,
+      "grad_norm": 5.660022258758545,
+      "learning_rate": 4.756703078450844e-06,
+      "loss": 0.4318,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7325660121868651,
+      "grad_norm": 5.320847511291504,
+      "learning_rate": 4.657398212512414e-06,
+      "loss": 0.4255,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7596479350033851,
+      "grad_norm": 4.652419567108154,
+      "learning_rate": 4.558093346573982e-06,
+      "loss": 0.4231,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7867298578199051,
+      "grad_norm": 6.301181793212891,
+      "learning_rate": 4.458788480635551e-06,
+      "loss": 0.4426,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8138117806364251,
+      "grad_norm": 5.540495872497559,
+      "learning_rate": 4.35948361469712e-06,
+      "loss": 0.4361,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8408937034529451,
+      "grad_norm": 5.618797302246094,
+      "learning_rate": 4.260178748758689e-06,
+      "loss": 0.4081,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8679756262694651,
+      "grad_norm": 5.519278526306152,
+      "learning_rate": 4.160873882820258e-06,
+      "loss": 0.4311,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950575490859851,
+      "grad_norm": 5.24718713760376,
+      "learning_rate": 4.061569016881828e-06,
+      "loss": 0.441,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8950575490859851,
+      "eval_loss": 0.37384942173957825,
+      "eval_runtime": 1616.0813,
+      "eval_samples_per_second": 3.654,
+      "eval_steps_per_second": 0.457,
+      "eval_wer": 35.20006895214291,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9221394719025051,
+      "grad_norm": 5.9886884689331055,
+      "learning_rate": 3.962264150943396e-06,
+      "loss": 0.4125,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9492213947190251,
+      "grad_norm": 5.233187198638916,
+      "learning_rate": 3.862959285004966e-06,
+      "loss": 0.4179,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9763033175355451,
+      "grad_norm": 5.533965587615967,
+      "learning_rate": 3.763654419066535e-06,
+      "loss": 0.4272,
+      "step": 1460
+    },
+    {
+      "epoch": 2.002708192281652,
+      "grad_norm": 5.179864883422852,
+      "learning_rate": 3.664349553128104e-06,
+      "loss": 0.4082,
+      "step": 1480
+    },
+    {
+      "epoch": 2.029790115098172,
+      "grad_norm": 4.748936653137207,
+      "learning_rate": 3.565044687189673e-06,
+      "loss": 0.3085,
+      "step": 1500
+    },
+    {
+      "epoch": 2.056872037914692,
+      "grad_norm": 5.267838001251221,
+      "learning_rate": 3.4657398212512415e-06,
+      "loss": 0.312,
+      "step": 1520
+    },
+    {
+      "epoch": 2.083953960731212,
+      "grad_norm": 6.315608501434326,
+      "learning_rate": 3.3664349553128105e-06,
+      "loss": 0.3512,
+      "step": 1540
+    },
+    {
+      "epoch": 2.111035883547732,
+      "grad_norm": 5.232484340667725,
+      "learning_rate": 3.2671300893743795e-06,
+      "loss": 0.3184,
+      "step": 1560
+    },
+    {
+      "epoch": 2.138117806364252,
+      "grad_norm": 4.316751956939697,
+      "learning_rate": 3.1678252234359485e-06,
+      "loss": 0.3129,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1651997291807716,
+      "grad_norm": 4.040640354156494,
+      "learning_rate": 3.0685203574975175e-06,
+      "loss": 0.3073,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1651997291807716,
+      "eval_loss": 0.3516213595867157,
+      "eval_runtime": 1617.0984,
+      "eval_samples_per_second": 3.652,
+      "eval_steps_per_second": 0.457,
+      "eval_wer": 34.23258419703075,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1922816519972916,
+      "grad_norm": 4.437410831451416,
+      "learning_rate": 2.9692154915590865e-06,
+      "loss": 0.3293,
+      "step": 1620
+    },
+    {
+      "epoch": 2.2193635748138116,
+      "grad_norm": 4.284883499145508,
+      "learning_rate": 2.8699106256206555e-06,
+      "loss": 0.3237,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2464454976303316,
+      "grad_norm": 4.959640979766846,
+      "learning_rate": 2.7706057596822245e-06,
+      "loss": 0.3374,
+      "step": 1660
+    },
+    {
+      "epoch": 2.2735274204468516,
+      "grad_norm": 5.366809368133545,
+      "learning_rate": 2.6713008937437935e-06,
+      "loss": 0.3086,
+      "step": 1680
+    },
+    {
+      "epoch": 2.3006093432633716,
+      "grad_norm": 4.363138198852539,
+      "learning_rate": 2.571996027805363e-06,
+      "loss": 0.331,
+      "step": 1700
+    },
+    {
+      "epoch": 2.3276912660798916,
+      "grad_norm": 4.7536468505859375,
+      "learning_rate": 2.4726911618669315e-06,
+      "loss": 0.317,
+      "step": 1720
+    },
+    {
+      "epoch": 2.3547731888964116,
+      "grad_norm": 4.352657794952393,
+      "learning_rate": 2.3733862959285005e-06,
+      "loss": 0.3008,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3818551117129316,
+      "grad_norm": 4.978397846221924,
+      "learning_rate": 2.2740814299900695e-06,
+      "loss": 0.3245,
+      "step": 1760
+    },
+    {
+      "epoch": 2.4089370345294516,
+      "grad_norm": 4.570504665374756,
+      "learning_rate": 2.174776564051639e-06,
+      "loss": 0.3147,
+      "step": 1780
+    },
+    {
+      "epoch": 2.4360189573459716,
+      "grad_norm": 5.904801845550537,
+      "learning_rate": 2.075471698113208e-06,
+      "loss": 0.3395,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4360189573459716,
+      "eval_loss": 0.3366335332393646,
+      "eval_runtime": 1614.6836,
+      "eval_samples_per_second": 3.657,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 33.028076450688445,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4631008801624916,
+      "grad_norm": 5.771766185760498,
+      "learning_rate": 1.976166832174777e-06,
+      "loss": 0.3064,
+      "step": 1820
+    },
+    {
+      "epoch": 2.4901828029790116,
+      "grad_norm": 5.262455463409424,
+      "learning_rate": 1.8768619662363458e-06,
+      "loss": 0.2961,
+      "step": 1840
+    },
+    {
+      "epoch": 2.5172647257955316,
+      "grad_norm": 5.288928031921387,
+      "learning_rate": 1.7775571002979148e-06,
+      "loss": 0.3285,
+      "step": 1860
+    },
+    {
+      "epoch": 2.5443466486120516,
+      "grad_norm": 5.816193580627441,
+      "learning_rate": 1.6782522343594838e-06,
+      "loss": 0.3254,
+      "step": 1880
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 5.249015808105469,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.3279,
+      "step": 1900
+    },
+    {
+      "epoch": 2.598510494245091,
+      "grad_norm": 4.509056568145752,
+      "learning_rate": 1.4796425024826216e-06,
+      "loss": 0.317,
+      "step": 1920
+    },
+    {
+      "epoch": 2.625592417061611,
+      "grad_norm": 4.113898754119873,
+      "learning_rate": 1.3803376365441908e-06,
+      "loss": 0.3135,
+      "step": 1940
+    },
+    {
+      "epoch": 2.652674339878131,
+      "grad_norm": 5.507041931152344,
+      "learning_rate": 1.2810327706057598e-06,
+      "loss": 0.3302,
+      "step": 1960
+    },
+    {
+      "epoch": 2.679756262694651,
+      "grad_norm": 4.8485846519470215,
+      "learning_rate": 1.1817279046673288e-06,
+      "loss": 0.3106,
+      "step": 1980
+    },
+    {
+      "epoch": 2.706838185511171,
+      "grad_norm": 5.389250755310059,
+      "learning_rate": 1.0824230387288978e-06,
+      "loss": 0.3347,
+      "step": 2000
+    },
+    {
+      "epoch": 2.706838185511171,
+      "eval_loss": 0.3267146348953247,
+      "eval_runtime": 1650.7646,
+      "eval_samples_per_second": 3.577,
+      "eval_steps_per_second": 0.448,
+      "eval_wer": 32.74580361567799,
+      "step": 2000
+    },
+    {
+      "epoch": 2.733920108327691,
+      "grad_norm": 4.579651832580566,
+      "learning_rate": 9.831181727904668e-07,
+      "loss": 0.3348,
+      "step": 2020
+    },
+    {
+      "epoch": 2.761002031144211,
+      "grad_norm": 5.236474514007568,
+      "learning_rate": 8.838133068520357e-07,
+      "loss": 0.3183,
+      "step": 2040
+    },
+    {
+      "epoch": 2.788083953960731,
+      "grad_norm": 5.183202743530273,
+      "learning_rate": 7.845084409136048e-07,
+      "loss": 0.3158,
+      "step": 2060
+    },
+    {
+      "epoch": 2.815165876777251,
+      "grad_norm": 4.969793796539307,
+      "learning_rate": 6.852035749751739e-07,
+      "loss": 0.3372,
+      "step": 2080
+    },
+    {
+      "epoch": 2.842247799593771,
+      "grad_norm": 4.525297164916992,
+      "learning_rate": 5.858987090367429e-07,
+      "loss": 0.2949,
+      "step": 2100
+    },
+    {
+      "epoch": 2.869329722410291,
+      "grad_norm": 5.897444725036621,
+      "learning_rate": 4.865938430983119e-07,
+      "loss": 0.3109,
+      "step": 2120
+    },
+    {
+      "epoch": 2.896411645226811,
+      "grad_norm": 5.232760906219482,
+      "learning_rate": 3.872889771598809e-07,
+      "loss": 0.2958,
+      "step": 2140
+    },
+    {
+      "epoch": 2.923493568043331,
+      "grad_norm": 4.443195819854736,
+      "learning_rate": 2.879841112214499e-07,
+      "loss": 0.3239,
+      "step": 2160
+    },
+    {
+      "epoch": 2.950575490859851,
+      "grad_norm": 4.811395168304443,
+      "learning_rate": 1.886792452830189e-07,
+      "loss": 0.3104,
+      "step": 2180
+    },
+    {
+      "epoch": 2.977657413676371,
+      "grad_norm": 4.447694778442383,
+      "learning_rate": 8.93743793445879e-08,
+      "loss": 0.3103,
+      "step": 2200
+    },
+    {
+      "epoch": 2.977657413676371,
+      "eval_loss": 0.321925550699234,
+      "eval_runtime": 1631.903,
+      "eval_samples_per_second": 3.618,
+      "eval_steps_per_second": 0.453,
+      "eval_wer": 32.812601004115585,
+      "step": 2200
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.030025140011008e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2200/training_args.bin b/checkpoint-2200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2a3b1da275660c7c7439512aa770d076034c70c
--- /dev/null
+++ b/checkpoint-2200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d182356a12cee606170360f976946e1a56ce9d494fc1de269ffa184a80a19aa
+size 5432
diff --git a/checkpoint-2214/config.json b/checkpoint-2214/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..337642e18341c758364c32c6b6159a090615329b
--- /dev/null
+++ b/checkpoint-2214/config.json
@@ -0,0 +1,47 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
diff --git a/checkpoint-2214/generation_config.json b/checkpoint-2214/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec4263613bc098f8eb01034b73fbe16fb43eba5c
--- /dev/null
+++ b/checkpoint-2214/generation_config.json
@@ -0,0 +1,175 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      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": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.51.3"
+}
diff --git a/checkpoint-2214/model.safetensors b/checkpoint-2214/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1a815774b847c3309598e94206e0b4862aed31c1
--- /dev/null
+++ b/checkpoint-2214/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f016bce67a5be17d0b4a4b6ec22c9f33bd78214e1cb15cfd8949639b1e41089
+size 966995080
diff --git a/checkpoint-2214/optimizer.pt b/checkpoint-2214/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c6ff06a73f30e0b7dc7e71f34f7822b422ab568a
--- /dev/null
+++ b/checkpoint-2214/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2d3d5862520c496859b1a385d157d0be503da1bbed50f5a9521b5d859eabbf9
+size 1925064044
diff --git a/checkpoint-2214/preprocessor_config.json b/checkpoint-2214/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-2214/preprocessor_config.json
@@ -0,0 +1,15 @@
+{
+  "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,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-2214/rng_state.pth b/checkpoint-2214/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ece682502ab33f1eaed619643dc3404747237c48
--- /dev/null
+++ b/checkpoint-2214/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9126da64d50ccf3858016f6809a65a04d0f40d24fc95e8c439c828c47ddcb2ac
+size 14244
diff --git a/checkpoint-2214/scaler.pt b/checkpoint-2214/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3db6b6c4d3f4bbfdcae15474231467724eaf1e69
--- /dev/null
+++ b/checkpoint-2214/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6dd0548a5ff4d33bdee197bfb173859d8c950ff4af20c10d229dca7652491e
+size 988
diff --git a/checkpoint-2214/scheduler.pt b/checkpoint-2214/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..801be25a1d2ebec2d943b6ece5e35382d3afee22
--- /dev/null
+++ b/checkpoint-2214/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893f6a58d2ab1b61603e2d0c3514de84d56f503ce9c87000217dfe1075f2298e
+size 1064
diff --git a/checkpoint-2214/trainer_state.json b/checkpoint-2214/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..31dd1b6d1b681fe6fd7c8dbd385b9abff5755a0a
--- /dev/null
+++ b/checkpoint-2214/trainer_state.json
@@ -0,0 +1,903 @@
+{
+  "best_global_step": 2000,
+  "best_metric": 32.74580361567799,
+  "best_model_checkpoint": "./HAUSA_B/checkpoint-2000",
+  "epoch": 2.996614759647935,
+  "eval_steps": 200,
+  "global_step": 2214,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027081922816519974,
+      "grad_norm": 106.59215545654297,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 6.1915,
+      "step": 20
+    },
+    {
+      "epoch": 0.05416384563303995,
+      "grad_norm": 30.563518524169922,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 4.5886,
+      "step": 40
+    },
+    {
+      "epoch": 0.08124576844955991,
+      "grad_norm": 16.528457641601562,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 3.0338,
+      "step": 60
+    },
+    {
+      "epoch": 0.1083276912660799,
+      "grad_norm": 13.852096557617188,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.13540961408259986,
+      "grad_norm": 13.284646987915039,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.9725,
+      "step": 100
+    },
+    {
+      "epoch": 0.16249153689911983,
+      "grad_norm": 13.212055206298828,
+      "learning_rate": 5.8e-06,
+      "loss": 1.7839,
+      "step": 120
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 12.006990432739258,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.5991,
+      "step": 140
+    },
+    {
+      "epoch": 0.2166553825321598,
+      "grad_norm": 12.490514755249023,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4411,
+      "step": 160
+    },
+    {
+      "epoch": 0.24373730534867977,
+      "grad_norm": 11.587646484375,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3487,
+      "step": 180
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "grad_norm": 11.574933052062988,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.2119,
+      "step": 200
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "eval_loss": 1.1157827377319336,
+      "eval_runtime": 1601.2991,
+      "eval_samples_per_second": 3.688,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 64.22461160550755,
+      "step": 200
+    },
+    {
+      "epoch": 0.2979011509817197,
+      "grad_norm": 8.368565559387207,
+      "learning_rate": 9.920556107249256e-06,
+      "loss": 0.9452,
+      "step": 220
+    },
+    {
+      "epoch": 0.32498307379823965,
+      "grad_norm": 7.2616682052612305,
+      "learning_rate": 9.821251241310825e-06,
+      "loss": 0.9298,
+      "step": 240
+    },
+    {
+      "epoch": 0.35206499661475965,
+      "grad_norm": 7.266394138336182,
+      "learning_rate": 9.721946375372395e-06,
+      "loss": 0.8567,
+      "step": 260
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 8.120067596435547,
+      "learning_rate": 9.622641509433963e-06,
+      "loss": 0.8251,
+      "step": 280
+    },
+    {
+      "epoch": 0.4062288422477996,
+      "grad_norm": 7.483547687530518,
+      "learning_rate": 9.523336643495532e-06,
+      "loss": 0.7774,
+      "step": 300
+    },
+    {
+      "epoch": 0.4333107650643196,
+      "grad_norm": 7.521896839141846,
+      "learning_rate": 9.4240317775571e-06,
+      "loss": 0.7266,
+      "step": 320
+    },
+    {
+      "epoch": 0.46039268788083954,
+      "grad_norm": 7.073266506195068,
+      "learning_rate": 9.32472691161867e-06,
+      "loss": 0.7248,
+      "step": 340
+    },
+    {
+      "epoch": 0.48747461069735953,
+      "grad_norm": 6.335423469543457,
+      "learning_rate": 9.22542204568024e-06,
+      "loss": 0.7151,
+      "step": 360
+    },
+    {
+      "epoch": 0.5145565335138795,
+      "grad_norm": 6.936922550201416,
+      "learning_rate": 9.126117179741808e-06,
+      "loss": 0.6881,
+      "step": 380
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "grad_norm": 7.596807479858398,
+      "learning_rate": 9.026812313803377e-06,
+      "loss": 0.6995,
+      "step": 400
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "eval_loss": 0.6352065801620483,
+      "eval_runtime": 1597.3635,
+      "eval_samples_per_second": 3.697,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 51.63653601672089,
+      "step": 400
+    },
+    {
+      "epoch": 0.5687203791469194,
+      "grad_norm": 6.981812477111816,
+      "learning_rate": 8.927507447864945e-06,
+      "loss": 0.6795,
+      "step": 420
+    },
+    {
+      "epoch": 0.5958023019634394,
+      "grad_norm": 6.481506824493408,
+      "learning_rate": 8.828202581926516e-06,
+      "loss": 0.6643,
+      "step": 440
+    },
+    {
+      "epoch": 0.6228842247799594,
+      "grad_norm": 6.537086009979248,
+      "learning_rate": 8.728897715988084e-06,
+      "loss": 0.6459,
+      "step": 460
+    },
+    {
+      "epoch": 0.6499661475964793,
+      "grad_norm": 6.739567756652832,
+      "learning_rate": 8.629592850049653e-06,
+      "loss": 0.6736,
+      "step": 480
+    },
+    {
+      "epoch": 0.6770480704129993,
+      "grad_norm": 7.422546863555908,
+      "learning_rate": 8.530287984111221e-06,
+      "loss": 0.6591,
+      "step": 500
+    },
+    {
+      "epoch": 0.7041299932295193,
+      "grad_norm": 5.7051215171813965,
+      "learning_rate": 8.430983118172792e-06,
+      "loss": 0.6442,
+      "step": 520
+    },
+    {
+      "epoch": 0.7312119160460393,
+      "grad_norm": 7.166143417358398,
+      "learning_rate": 8.33167825223436e-06,
+      "loss": 0.6326,
+      "step": 540
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "grad_norm": 7.759460926055908,
+      "learning_rate": 8.232373386295929e-06,
+      "loss": 0.6328,
+      "step": 560
+    },
+    {
+      "epoch": 0.7853757616790792,
+      "grad_norm": 5.876537799835205,
+      "learning_rate": 8.133068520357497e-06,
+      "loss": 0.5945,
+      "step": 580
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "grad_norm": 6.475106716156006,
+      "learning_rate": 8.033763654419066e-06,
+      "loss": 0.6038,
+      "step": 600
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "eval_loss": 0.5318673849105835,
+      "eval_runtime": 1614.0202,
+      "eval_samples_per_second": 3.659,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 44.61419121291129,
+      "step": 600
+    },
+    {
+      "epoch": 0.8395396073121192,
+      "grad_norm": 6.8348259925842285,
+      "learning_rate": 7.934458788480636e-06,
+      "loss": 0.6046,
+      "step": 620
+    },
+    {
+      "epoch": 0.8666215301286392,
+      "grad_norm": 6.060784339904785,
+      "learning_rate": 7.835153922542206e-06,
+      "loss": 0.6055,
+      "step": 640
+    },
+    {
+      "epoch": 0.8937034529451591,
+      "grad_norm": 6.01262903213501,
+      "learning_rate": 7.735849056603775e-06,
+      "loss": 0.6139,
+      "step": 660
+    },
+    {
+      "epoch": 0.9207853757616791,
+      "grad_norm": 6.706854820251465,
+      "learning_rate": 7.636544190665344e-06,
+      "loss": 0.5789,
+      "step": 680
+    },
+    {
+      "epoch": 0.9478672985781991,
+      "grad_norm": 6.464681625366211,
+      "learning_rate": 7.537239324726913e-06,
+      "loss": 0.5857,
+      "step": 700
+    },
+    {
+      "epoch": 0.9749492213947191,
+      "grad_norm": 7.8035478591918945,
+      "learning_rate": 7.437934458788482e-06,
+      "loss": 0.5739,
+      "step": 720
+    },
+    {
+      "epoch": 1.001354096140826,
+      "grad_norm": 5.574532985687256,
+      "learning_rate": 7.33862959285005e-06,
+      "loss": 0.5443,
+      "step": 740
+    },
+    {
+      "epoch": 1.028436018957346,
+      "grad_norm": 5.275153160095215,
+      "learning_rate": 7.23932472691162e-06,
+      "loss": 0.4705,
+      "step": 760
+    },
+    {
+      "epoch": 1.055517941773866,
+      "grad_norm": 5.722527027130127,
+      "learning_rate": 7.140019860973188e-06,
+      "loss": 0.4692,
+      "step": 780
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "grad_norm": 5.501762866973877,
+      "learning_rate": 7.040714995034758e-06,
+      "loss": 0.4791,
+      "step": 800
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "eval_loss": 0.46895861625671387,
+      "eval_runtime": 1599.6376,
+      "eval_samples_per_second": 3.691,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 40.9726561658299,
+      "step": 800
+    },
+    {
+      "epoch": 1.1096817874069058,
+      "grad_norm": 5.207645893096924,
+      "learning_rate": 6.941410129096326e-06,
+      "loss": 0.4569,
+      "step": 820
+    },
+    {
+      "epoch": 1.1367637102234258,
+      "grad_norm": 5.584475517272949,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.4262,
+      "step": 840
+    },
+    {
+      "epoch": 1.1638456330399458,
+      "grad_norm": 5.881894588470459,
+      "learning_rate": 6.742800397219464e-06,
+      "loss": 0.4533,
+      "step": 860
+    },
+    {
+      "epoch": 1.1909275558564658,
+      "grad_norm": 6.939334869384766,
+      "learning_rate": 6.643495531281034e-06,
+      "loss": 0.4675,
+      "step": 880
+    },
+    {
+      "epoch": 1.2180094786729858,
+      "grad_norm": 5.780360698699951,
+      "learning_rate": 6.544190665342602e-06,
+      "loss": 0.4238,
+      "step": 900
+    },
+    {
+      "epoch": 1.2450914014895058,
+      "grad_norm": 5.867160797119141,
+      "learning_rate": 6.444885799404172e-06,
+      "loss": 0.444,
+      "step": 920
+    },
+    {
+      "epoch": 1.2721733243060258,
+      "grad_norm": 6.121824741363525,
+      "learning_rate": 6.34558093346574e-06,
+      "loss": 0.4333,
+      "step": 940
+    },
+    {
+      "epoch": 1.2992552471225456,
+      "grad_norm": 5.132157802581787,
+      "learning_rate": 6.24627606752731e-06,
+      "loss": 0.4544,
+      "step": 960
+    },
+    {
+      "epoch": 1.3263371699390656,
+      "grad_norm": 6.384315013885498,
+      "learning_rate": 6.146971201588878e-06,
+      "loss": 0.4332,
+      "step": 980
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "grad_norm": 4.54695987701416,
+      "learning_rate": 6.047666335650447e-06,
+      "loss": 0.4416,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3534190927555856,
+      "eval_loss": 0.43043428659439087,
+      "eval_runtime": 1614.3899,
+      "eval_samples_per_second": 3.658,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 38.00771402098731,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3805010155721056,
+      "grad_norm": 4.973900318145752,
+      "learning_rate": 5.948361469712016e-06,
+      "loss": 0.4401,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4075829383886256,
+      "grad_norm": 5.952788352966309,
+      "learning_rate": 5.849056603773585e-06,
+      "loss": 0.4865,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4346648612051456,
+      "grad_norm": 6.601942539215088,
+      "learning_rate": 5.749751737835154e-06,
+      "loss": 0.4435,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4617467840216656,
+      "grad_norm": 6.17143440246582,
+      "learning_rate": 5.650446871896723e-06,
+      "loss": 0.451,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4888287068381856,
+      "grad_norm": 5.782886981964111,
+      "learning_rate": 5.551142005958292e-06,
+      "loss": 0.4311,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5159106296547056,
+      "grad_norm": 5.734127998352051,
+      "learning_rate": 5.451837140019861e-06,
+      "loss": 0.4632,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5429925524712256,
+      "grad_norm": 5.601761341094971,
+      "learning_rate": 5.35253227408143e-06,
+      "loss": 0.424,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5700744752877456,
+      "grad_norm": 5.866110801696777,
+      "learning_rate": 5.253227408142999e-06,
+      "loss": 0.4273,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5971563981042654,
+      "grad_norm": 5.120361328125,
+      "learning_rate": 5.153922542204568e-06,
+      "loss": 0.4297,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "grad_norm": 5.093082427978516,
+      "learning_rate": 5.054617676266137e-06,
+      "loss": 0.4321,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6242383209207854,
+      "eval_loss": 0.3993258476257324,
+      "eval_runtime": 1619.3754,
+      "eval_samples_per_second": 3.646,
+      "eval_steps_per_second": 0.456,
+      "eval_wer": 37.091943373052636,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6513202437373053,
+      "grad_norm": 5.076949119567871,
+      "learning_rate": 4.955312810327706e-06,
+      "loss": 0.4446,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6784021665538253,
+      "grad_norm": 5.729442596435547,
+      "learning_rate": 4.856007944389276e-06,
+      "loss": 0.4375,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7054840893703453,
+      "grad_norm": 5.660022258758545,
+      "learning_rate": 4.756703078450844e-06,
+      "loss": 0.4318,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7325660121868651,
+      "grad_norm": 5.320847511291504,
+      "learning_rate": 4.657398212512414e-06,
+      "loss": 0.4255,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7596479350033851,
+      "grad_norm": 4.652419567108154,
+      "learning_rate": 4.558093346573982e-06,
+      "loss": 0.4231,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7867298578199051,
+      "grad_norm": 6.301181793212891,
+      "learning_rate": 4.458788480635551e-06,
+      "loss": 0.4426,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8138117806364251,
+      "grad_norm": 5.540495872497559,
+      "learning_rate": 4.35948361469712e-06,
+      "loss": 0.4361,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8408937034529451,
+      "grad_norm": 5.618797302246094,
+      "learning_rate": 4.260178748758689e-06,
+      "loss": 0.4081,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8679756262694651,
+      "grad_norm": 5.519278526306152,
+      "learning_rate": 4.160873882820258e-06,
+      "loss": 0.4311,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950575490859851,
+      "grad_norm": 5.24718713760376,
+      "learning_rate": 4.061569016881828e-06,
+      "loss": 0.441,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8950575490859851,
+      "eval_loss": 0.37384942173957825,
+      "eval_runtime": 1616.0813,
+      "eval_samples_per_second": 3.654,
+      "eval_steps_per_second": 0.457,
+      "eval_wer": 35.20006895214291,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9221394719025051,
+      "grad_norm": 5.9886884689331055,
+      "learning_rate": 3.962264150943396e-06,
+      "loss": 0.4125,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9492213947190251,
+      "grad_norm": 5.233187198638916,
+      "learning_rate": 3.862959285004966e-06,
+      "loss": 0.4179,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9763033175355451,
+      "grad_norm": 5.533965587615967,
+      "learning_rate": 3.763654419066535e-06,
+      "loss": 0.4272,
+      "step": 1460
+    },
+    {
+      "epoch": 2.002708192281652,
+      "grad_norm": 5.179864883422852,
+      "learning_rate": 3.664349553128104e-06,
+      "loss": 0.4082,
+      "step": 1480
+    },
+    {
+      "epoch": 2.029790115098172,
+      "grad_norm": 4.748936653137207,
+      "learning_rate": 3.565044687189673e-06,
+      "loss": 0.3085,
+      "step": 1500
+    },
+    {
+      "epoch": 2.056872037914692,
+      "grad_norm": 5.267838001251221,
+      "learning_rate": 3.4657398212512415e-06,
+      "loss": 0.312,
+      "step": 1520
+    },
+    {
+      "epoch": 2.083953960731212,
+      "grad_norm": 6.315608501434326,
+      "learning_rate": 3.3664349553128105e-06,
+      "loss": 0.3512,
+      "step": 1540
+    },
+    {
+      "epoch": 2.111035883547732,
+      "grad_norm": 5.232484340667725,
+      "learning_rate": 3.2671300893743795e-06,
+      "loss": 0.3184,
+      "step": 1560
+    },
+    {
+      "epoch": 2.138117806364252,
+      "grad_norm": 4.316751956939697,
+      "learning_rate": 3.1678252234359485e-06,
+      "loss": 0.3129,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1651997291807716,
+      "grad_norm": 4.040640354156494,
+      "learning_rate": 3.0685203574975175e-06,
+      "loss": 0.3073,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1651997291807716,
+      "eval_loss": 0.3516213595867157,
+      "eval_runtime": 1617.0984,
+      "eval_samples_per_second": 3.652,
+      "eval_steps_per_second": 0.457,
+      "eval_wer": 34.23258419703075,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1922816519972916,
+      "grad_norm": 4.437410831451416,
+      "learning_rate": 2.9692154915590865e-06,
+      "loss": 0.3293,
+      "step": 1620
+    },
+    {
+      "epoch": 2.2193635748138116,
+      "grad_norm": 4.284883499145508,
+      "learning_rate": 2.8699106256206555e-06,
+      "loss": 0.3237,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2464454976303316,
+      "grad_norm": 4.959640979766846,
+      "learning_rate": 2.7706057596822245e-06,
+      "loss": 0.3374,
+      "step": 1660
+    },
+    {
+      "epoch": 2.2735274204468516,
+      "grad_norm": 5.366809368133545,
+      "learning_rate": 2.6713008937437935e-06,
+      "loss": 0.3086,
+      "step": 1680
+    },
+    {
+      "epoch": 2.3006093432633716,
+      "grad_norm": 4.363138198852539,
+      "learning_rate": 2.571996027805363e-06,
+      "loss": 0.331,
+      "step": 1700
+    },
+    {
+      "epoch": 2.3276912660798916,
+      "grad_norm": 4.7536468505859375,
+      "learning_rate": 2.4726911618669315e-06,
+      "loss": 0.317,
+      "step": 1720
+    },
+    {
+      "epoch": 2.3547731888964116,
+      "grad_norm": 4.352657794952393,
+      "learning_rate": 2.3733862959285005e-06,
+      "loss": 0.3008,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3818551117129316,
+      "grad_norm": 4.978397846221924,
+      "learning_rate": 2.2740814299900695e-06,
+      "loss": 0.3245,
+      "step": 1760
+    },
+    {
+      "epoch": 2.4089370345294516,
+      "grad_norm": 4.570504665374756,
+      "learning_rate": 2.174776564051639e-06,
+      "loss": 0.3147,
+      "step": 1780
+    },
+    {
+      "epoch": 2.4360189573459716,
+      "grad_norm": 5.904801845550537,
+      "learning_rate": 2.075471698113208e-06,
+      "loss": 0.3395,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4360189573459716,
+      "eval_loss": 0.3366335332393646,
+      "eval_runtime": 1614.6836,
+      "eval_samples_per_second": 3.657,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 33.028076450688445,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4631008801624916,
+      "grad_norm": 5.771766185760498,
+      "learning_rate": 1.976166832174777e-06,
+      "loss": 0.3064,
+      "step": 1820
+    },
+    {
+      "epoch": 2.4901828029790116,
+      "grad_norm": 5.262455463409424,
+      "learning_rate": 1.8768619662363458e-06,
+      "loss": 0.2961,
+      "step": 1840
+    },
+    {
+      "epoch": 2.5172647257955316,
+      "grad_norm": 5.288928031921387,
+      "learning_rate": 1.7775571002979148e-06,
+      "loss": 0.3285,
+      "step": 1860
+    },
+    {
+      "epoch": 2.5443466486120516,
+      "grad_norm": 5.816193580627441,
+      "learning_rate": 1.6782522343594838e-06,
+      "loss": 0.3254,
+      "step": 1880
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 5.249015808105469,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.3279,
+      "step": 1900
+    },
+    {
+      "epoch": 2.598510494245091,
+      "grad_norm": 4.509056568145752,
+      "learning_rate": 1.4796425024826216e-06,
+      "loss": 0.317,
+      "step": 1920
+    },
+    {
+      "epoch": 2.625592417061611,
+      "grad_norm": 4.113898754119873,
+      "learning_rate": 1.3803376365441908e-06,
+      "loss": 0.3135,
+      "step": 1940
+    },
+    {
+      "epoch": 2.652674339878131,
+      "grad_norm": 5.507041931152344,
+      "learning_rate": 1.2810327706057598e-06,
+      "loss": 0.3302,
+      "step": 1960
+    },
+    {
+      "epoch": 2.679756262694651,
+      "grad_norm": 4.8485846519470215,
+      "learning_rate": 1.1817279046673288e-06,
+      "loss": 0.3106,
+      "step": 1980
+    },
+    {
+      "epoch": 2.706838185511171,
+      "grad_norm": 5.389250755310059,
+      "learning_rate": 1.0824230387288978e-06,
+      "loss": 0.3347,
+      "step": 2000
+    },
+    {
+      "epoch": 2.706838185511171,
+      "eval_loss": 0.3267146348953247,
+      "eval_runtime": 1650.7646,
+      "eval_samples_per_second": 3.577,
+      "eval_steps_per_second": 0.448,
+      "eval_wer": 32.74580361567799,
+      "step": 2000
+    },
+    {
+      "epoch": 2.733920108327691,
+      "grad_norm": 4.579651832580566,
+      "learning_rate": 9.831181727904668e-07,
+      "loss": 0.3348,
+      "step": 2020
+    },
+    {
+      "epoch": 2.761002031144211,
+      "grad_norm": 5.236474514007568,
+      "learning_rate": 8.838133068520357e-07,
+      "loss": 0.3183,
+      "step": 2040
+    },
+    {
+      "epoch": 2.788083953960731,
+      "grad_norm": 5.183202743530273,
+      "learning_rate": 7.845084409136048e-07,
+      "loss": 0.3158,
+      "step": 2060
+    },
+    {
+      "epoch": 2.815165876777251,
+      "grad_norm": 4.969793796539307,
+      "learning_rate": 6.852035749751739e-07,
+      "loss": 0.3372,
+      "step": 2080
+    },
+    {
+      "epoch": 2.842247799593771,
+      "grad_norm": 4.525297164916992,
+      "learning_rate": 5.858987090367429e-07,
+      "loss": 0.2949,
+      "step": 2100
+    },
+    {
+      "epoch": 2.869329722410291,
+      "grad_norm": 5.897444725036621,
+      "learning_rate": 4.865938430983119e-07,
+      "loss": 0.3109,
+      "step": 2120
+    },
+    {
+      "epoch": 2.896411645226811,
+      "grad_norm": 5.232760906219482,
+      "learning_rate": 3.872889771598809e-07,
+      "loss": 0.2958,
+      "step": 2140
+    },
+    {
+      "epoch": 2.923493568043331,
+      "grad_norm": 4.443195819854736,
+      "learning_rate": 2.879841112214499e-07,
+      "loss": 0.3239,
+      "step": 2160
+    },
+    {
+      "epoch": 2.950575490859851,
+      "grad_norm": 4.811395168304443,
+      "learning_rate": 1.886792452830189e-07,
+      "loss": 0.3104,
+      "step": 2180
+    },
+    {
+      "epoch": 2.977657413676371,
+      "grad_norm": 4.447694778442383,
+      "learning_rate": 8.93743793445879e-08,
+      "loss": 0.3103,
+      "step": 2200
+    },
+    {
+      "epoch": 2.977657413676371,
+      "eval_loss": 0.321925550699234,
+      "eval_runtime": 1631.903,
+      "eval_samples_per_second": 3.618,
+      "eval_steps_per_second": 0.453,
+      "eval_wer": 32.812601004115585,
+      "step": 2200
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.042953765945344e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2214/training_args.bin b/checkpoint-2214/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2a3b1da275660c7c7439512aa770d076034c70c
--- /dev/null
+++ b/checkpoint-2214/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d182356a12cee606170360f976946e1a56ce9d494fc1de269ffa184a80a19aa
+size 5432
diff --git a/checkpoint-400/config.json b/checkpoint-400/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..337642e18341c758364c32c6b6159a090615329b
--- /dev/null
+++ b/checkpoint-400/config.json
@@ -0,0 +1,47 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
diff --git a/checkpoint-400/generation_config.json b/checkpoint-400/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec4263613bc098f8eb01034b73fbe16fb43eba5c
--- /dev/null
+++ b/checkpoint-400/generation_config.json
@@ -0,0 +1,175 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      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": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.51.3"
+}
diff --git a/checkpoint-400/model.safetensors b/checkpoint-400/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a233ceadcd3702a66dd2b3193056016966ec2d70
--- /dev/null
+++ b/checkpoint-400/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cfcb7554def8c698de1930b3b33fd67ae92dcfc4829d4edcd928868830f0b75
+size 966995080
diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..526c9490fc4171054be1dd90ca07cead0453b366
--- /dev/null
+++ b/checkpoint-400/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d874f4b07a67f2ec157df8994a1f94be290db3cce6bc20cfe3d9b1f8611b2c85
+size 1925064044
diff --git a/checkpoint-400/preprocessor_config.json b/checkpoint-400/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-400/preprocessor_config.json
@@ -0,0 +1,15 @@
+{
+  "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,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-400/rng_state.pth b/checkpoint-400/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c4a4846f23b0114a7e6dffbb2570f038270c803c
--- /dev/null
+++ b/checkpoint-400/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e083c2714494131f831e7de87e7eb1e8d45ceb79273b4cc4541a589644bf042a
+size 14244
diff --git a/checkpoint-400/scaler.pt b/checkpoint-400/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6320d020e8a84c9ecaf817e706d34bec9660adcb
--- /dev/null
+++ b/checkpoint-400/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55bd04dcda5749d47b2210eb8786c3946a11c6f865c33206bfb65f22052d8c0d
+size 988
diff --git a/checkpoint-400/scheduler.pt b/checkpoint-400/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b8016fbe009680708da254e6608c843b0ac5beb1
--- /dev/null
+++ b/checkpoint-400/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3afcf5812e480023ee14c7496749c5e9cb331b95d8f28dfff8808f57241b21ad
+size 1064
diff --git a/checkpoint-400/trainer_state.json b/checkpoint-400/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..ea6565da8426f96d607ea1c867fcfa6685332683
--- /dev/null
+++ b/checkpoint-400/trainer_state.json
@@ -0,0 +1,192 @@
+{
+  "best_global_step": 400,
+  "best_metric": 51.63653601672089,
+  "best_model_checkpoint": "./HAUSA_B/checkpoint-400",
+  "epoch": 0.5416384563303994,
+  "eval_steps": 200,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027081922816519974,
+      "grad_norm": 106.59215545654297,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 6.1915,
+      "step": 20
+    },
+    {
+      "epoch": 0.05416384563303995,
+      "grad_norm": 30.563518524169922,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 4.5886,
+      "step": 40
+    },
+    {
+      "epoch": 0.08124576844955991,
+      "grad_norm": 16.528457641601562,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 3.0338,
+      "step": 60
+    },
+    {
+      "epoch": 0.1083276912660799,
+      "grad_norm": 13.852096557617188,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.13540961408259986,
+      "grad_norm": 13.284646987915039,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.9725,
+      "step": 100
+    },
+    {
+      "epoch": 0.16249153689911983,
+      "grad_norm": 13.212055206298828,
+      "learning_rate": 5.8e-06,
+      "loss": 1.7839,
+      "step": 120
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 12.006990432739258,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.5991,
+      "step": 140
+    },
+    {
+      "epoch": 0.2166553825321598,
+      "grad_norm": 12.490514755249023,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4411,
+      "step": 160
+    },
+    {
+      "epoch": 0.24373730534867977,
+      "grad_norm": 11.587646484375,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3487,
+      "step": 180
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "grad_norm": 11.574933052062988,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.2119,
+      "step": 200
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "eval_loss": 1.1157827377319336,
+      "eval_runtime": 1601.2991,
+      "eval_samples_per_second": 3.688,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 64.22461160550755,
+      "step": 200
+    },
+    {
+      "epoch": 0.2979011509817197,
+      "grad_norm": 8.368565559387207,
+      "learning_rate": 9.920556107249256e-06,
+      "loss": 0.9452,
+      "step": 220
+    },
+    {
+      "epoch": 0.32498307379823965,
+      "grad_norm": 7.2616682052612305,
+      "learning_rate": 9.821251241310825e-06,
+      "loss": 0.9298,
+      "step": 240
+    },
+    {
+      "epoch": 0.35206499661475965,
+      "grad_norm": 7.266394138336182,
+      "learning_rate": 9.721946375372395e-06,
+      "loss": 0.8567,
+      "step": 260
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 8.120067596435547,
+      "learning_rate": 9.622641509433963e-06,
+      "loss": 0.8251,
+      "step": 280
+    },
+    {
+      "epoch": 0.4062288422477996,
+      "grad_norm": 7.483547687530518,
+      "learning_rate": 9.523336643495532e-06,
+      "loss": 0.7774,
+      "step": 300
+    },
+    {
+      "epoch": 0.4333107650643196,
+      "grad_norm": 7.521896839141846,
+      "learning_rate": 9.4240317775571e-06,
+      "loss": 0.7266,
+      "step": 320
+    },
+    {
+      "epoch": 0.46039268788083954,
+      "grad_norm": 7.073266506195068,
+      "learning_rate": 9.32472691161867e-06,
+      "loss": 0.7248,
+      "step": 340
+    },
+    {
+      "epoch": 0.48747461069735953,
+      "grad_norm": 6.335423469543457,
+      "learning_rate": 9.22542204568024e-06,
+      "loss": 0.7151,
+      "step": 360
+    },
+    {
+      "epoch": 0.5145565335138795,
+      "grad_norm": 6.936922550201416,
+      "learning_rate": 9.126117179741808e-06,
+      "loss": 0.6881,
+      "step": 380
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "grad_norm": 7.596807479858398,
+      "learning_rate": 9.026812313803377e-06,
+      "loss": 0.6995,
+      "step": 400
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "eval_loss": 0.6352065801620483,
+      "eval_runtime": 1597.3635,
+      "eval_samples_per_second": 3.697,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 51.63653601672089,
+      "step": 400
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.693893124096e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-400/training_args.bin b/checkpoint-400/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2a3b1da275660c7c7439512aa770d076034c70c
--- /dev/null
+++ b/checkpoint-400/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d182356a12cee606170360f976946e1a56ce9d494fc1de269ffa184a80a19aa
+size 5432
diff --git a/checkpoint-600/config.json b/checkpoint-600/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..337642e18341c758364c32c6b6159a090615329b
--- /dev/null
+++ b/checkpoint-600/config.json
@@ -0,0 +1,47 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
diff --git a/checkpoint-600/generation_config.json b/checkpoint-600/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec4263613bc098f8eb01034b73fbe16fb43eba5c
--- /dev/null
+++ b/checkpoint-600/generation_config.json
@@ -0,0 +1,175 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      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": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.51.3"
+}
diff --git a/checkpoint-600/model.safetensors b/checkpoint-600/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..075e5993b52e3605d29845326027ed28e009a813
--- /dev/null
+++ b/checkpoint-600/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87dd8d5bd45c2cde0ddba14fc6676a1bb1274e6ee74ea4e278738f2e3ca7aa3e
+size 966995080
diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..43cdddf4cbbaaa674d0ebc36f6cdc93f32847018
--- /dev/null
+++ b/checkpoint-600/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:740b395888e5b886eea6320a50af66b3f6766ebac6c5cd621fa1df6765dbd2f6
+size 1925064044
diff --git a/checkpoint-600/preprocessor_config.json b/checkpoint-600/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-600/preprocessor_config.json
@@ -0,0 +1,15 @@
+{
+  "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,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..dfaaf2de5b959871a53ec4a6b346c4ad2d89fa7c
--- /dev/null
+++ b/checkpoint-600/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d1bb2ddcee08903691b8b0f2318892008fe1624cc4dcddbaf3b8c17e2f04cc
+size 14244
diff --git a/checkpoint-600/scaler.pt b/checkpoint-600/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5cc0bd9de49eacad6c8eff1d0f2f15d07ac94a86
--- /dev/null
+++ b/checkpoint-600/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:232b088791c535c834b03ccb2b81d05edbc20dfa7a1b5973228c2f936657baa2
+size 988
diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..63b8323fa168e24b5e5fd8a6c9c636f9fdb986a2
--- /dev/null
+++ b/checkpoint-600/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d27e868beb27fd937118a59353f20c3d8b3ee1942e8783b04b5e81267ec6b3c
+size 1064
diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..13796ef32bbe25f2d5c88fd90e81daf88f135fb4
--- /dev/null
+++ b/checkpoint-600/trainer_state.json
@@ -0,0 +1,271 @@
+{
+  "best_global_step": 600,
+  "best_metric": 44.61419121291129,
+  "best_model_checkpoint": "./HAUSA_B/checkpoint-600",
+  "epoch": 0.8124576844955992,
+  "eval_steps": 200,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027081922816519974,
+      "grad_norm": 106.59215545654297,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 6.1915,
+      "step": 20
+    },
+    {
+      "epoch": 0.05416384563303995,
+      "grad_norm": 30.563518524169922,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 4.5886,
+      "step": 40
+    },
+    {
+      "epoch": 0.08124576844955991,
+      "grad_norm": 16.528457641601562,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 3.0338,
+      "step": 60
+    },
+    {
+      "epoch": 0.1083276912660799,
+      "grad_norm": 13.852096557617188,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.13540961408259986,
+      "grad_norm": 13.284646987915039,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.9725,
+      "step": 100
+    },
+    {
+      "epoch": 0.16249153689911983,
+      "grad_norm": 13.212055206298828,
+      "learning_rate": 5.8e-06,
+      "loss": 1.7839,
+      "step": 120
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 12.006990432739258,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.5991,
+      "step": 140
+    },
+    {
+      "epoch": 0.2166553825321598,
+      "grad_norm": 12.490514755249023,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4411,
+      "step": 160
+    },
+    {
+      "epoch": 0.24373730534867977,
+      "grad_norm": 11.587646484375,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3487,
+      "step": 180
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "grad_norm": 11.574933052062988,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.2119,
+      "step": 200
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "eval_loss": 1.1157827377319336,
+      "eval_runtime": 1601.2991,
+      "eval_samples_per_second": 3.688,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 64.22461160550755,
+      "step": 200
+    },
+    {
+      "epoch": 0.2979011509817197,
+      "grad_norm": 8.368565559387207,
+      "learning_rate": 9.920556107249256e-06,
+      "loss": 0.9452,
+      "step": 220
+    },
+    {
+      "epoch": 0.32498307379823965,
+      "grad_norm": 7.2616682052612305,
+      "learning_rate": 9.821251241310825e-06,
+      "loss": 0.9298,
+      "step": 240
+    },
+    {
+      "epoch": 0.35206499661475965,
+      "grad_norm": 7.266394138336182,
+      "learning_rate": 9.721946375372395e-06,
+      "loss": 0.8567,
+      "step": 260
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 8.120067596435547,
+      "learning_rate": 9.622641509433963e-06,
+      "loss": 0.8251,
+      "step": 280
+    },
+    {
+      "epoch": 0.4062288422477996,
+      "grad_norm": 7.483547687530518,
+      "learning_rate": 9.523336643495532e-06,
+      "loss": 0.7774,
+      "step": 300
+    },
+    {
+      "epoch": 0.4333107650643196,
+      "grad_norm": 7.521896839141846,
+      "learning_rate": 9.4240317775571e-06,
+      "loss": 0.7266,
+      "step": 320
+    },
+    {
+      "epoch": 0.46039268788083954,
+      "grad_norm": 7.073266506195068,
+      "learning_rate": 9.32472691161867e-06,
+      "loss": 0.7248,
+      "step": 340
+    },
+    {
+      "epoch": 0.48747461069735953,
+      "grad_norm": 6.335423469543457,
+      "learning_rate": 9.22542204568024e-06,
+      "loss": 0.7151,
+      "step": 360
+    },
+    {
+      "epoch": 0.5145565335138795,
+      "grad_norm": 6.936922550201416,
+      "learning_rate": 9.126117179741808e-06,
+      "loss": 0.6881,
+      "step": 380
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "grad_norm": 7.596807479858398,
+      "learning_rate": 9.026812313803377e-06,
+      "loss": 0.6995,
+      "step": 400
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "eval_loss": 0.6352065801620483,
+      "eval_runtime": 1597.3635,
+      "eval_samples_per_second": 3.697,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 51.63653601672089,
+      "step": 400
+    },
+    {
+      "epoch": 0.5687203791469194,
+      "grad_norm": 6.981812477111816,
+      "learning_rate": 8.927507447864945e-06,
+      "loss": 0.6795,
+      "step": 420
+    },
+    {
+      "epoch": 0.5958023019634394,
+      "grad_norm": 6.481506824493408,
+      "learning_rate": 8.828202581926516e-06,
+      "loss": 0.6643,
+      "step": 440
+    },
+    {
+      "epoch": 0.6228842247799594,
+      "grad_norm": 6.537086009979248,
+      "learning_rate": 8.728897715988084e-06,
+      "loss": 0.6459,
+      "step": 460
+    },
+    {
+      "epoch": 0.6499661475964793,
+      "grad_norm": 6.739567756652832,
+      "learning_rate": 8.629592850049653e-06,
+      "loss": 0.6736,
+      "step": 480
+    },
+    {
+      "epoch": 0.6770480704129993,
+      "grad_norm": 7.422546863555908,
+      "learning_rate": 8.530287984111221e-06,
+      "loss": 0.6591,
+      "step": 500
+    },
+    {
+      "epoch": 0.7041299932295193,
+      "grad_norm": 5.7051215171813965,
+      "learning_rate": 8.430983118172792e-06,
+      "loss": 0.6442,
+      "step": 520
+    },
+    {
+      "epoch": 0.7312119160460393,
+      "grad_norm": 7.166143417358398,
+      "learning_rate": 8.33167825223436e-06,
+      "loss": 0.6326,
+      "step": 540
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "grad_norm": 7.759460926055908,
+      "learning_rate": 8.232373386295929e-06,
+      "loss": 0.6328,
+      "step": 560
+    },
+    {
+      "epoch": 0.7853757616790792,
+      "grad_norm": 5.876537799835205,
+      "learning_rate": 8.133068520357497e-06,
+      "loss": 0.5945,
+      "step": 580
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "grad_norm": 6.475106716156006,
+      "learning_rate": 8.033763654419066e-06,
+      "loss": 0.6038,
+      "step": 600
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "eval_loss": 0.5318673849105835,
+      "eval_runtime": 1614.0202,
+      "eval_samples_per_second": 3.659,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 44.61419121291129,
+      "step": 600
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.540839686144e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2a3b1da275660c7c7439512aa770d076034c70c
--- /dev/null
+++ b/checkpoint-600/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d182356a12cee606170360f976946e1a56ce9d494fc1de269ffa184a80a19aa
+size 5432
diff --git a/checkpoint-800/config.json b/checkpoint-800/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..337642e18341c758364c32c6b6159a090615329b
--- /dev/null
+++ b/checkpoint-800/config.json
@@ -0,0 +1,47 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}
diff --git a/checkpoint-800/generation_config.json b/checkpoint-800/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec4263613bc098f8eb01034b73fbe16fb43eba5c
--- /dev/null
+++ b/checkpoint-800/generation_config.json
@@ -0,0 +1,175 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      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": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.51.3"
+}
diff --git a/checkpoint-800/model.safetensors b/checkpoint-800/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..23069b7aa6cbb0af24259735f8bc41a6a6064dcf
--- /dev/null
+++ b/checkpoint-800/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac49ffd99c4b01393445f3549ef8aca144dd5c8ec8112a03cb909555030833d2
+size 966995080
diff --git a/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..84640784798a63e654628811be54afdcd9d8c049
--- /dev/null
+++ b/checkpoint-800/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8205b2c01d72fc202e921b87caa2c9ea4c1a6859ac451b364d68a29b5a38351b
+size 1925064044
diff --git a/checkpoint-800/preprocessor_config.json b/checkpoint-800/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-800/preprocessor_config.json
@@ -0,0 +1,15 @@
+{
+  "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,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-800/rng_state.pth b/checkpoint-800/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..affa6ed126e411edc8ce42130044a5f630323bed
--- /dev/null
+++ b/checkpoint-800/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3597314765590ce34031001167e56c4aab4991e579a37a769afe4d4329beeb
+size 14244
diff --git a/checkpoint-800/scaler.pt b/checkpoint-800/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a56ea5c3e0f135deaf75b019a178792d730ef4aa
--- /dev/null
+++ b/checkpoint-800/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a477cd0cf5611f86f98ac976e71f31f9917b1890b4e8e993d095337d29945b33
+size 988
diff --git a/checkpoint-800/scheduler.pt b/checkpoint-800/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..50d06187e2a423245c8214cfa24a5910864c3937
--- /dev/null
+++ b/checkpoint-800/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c943efa03574374d15493433d15a5d39b6ae1ff38a04b80f73b08e75867040d9
+size 1064
diff --git a/checkpoint-800/trainer_state.json b/checkpoint-800/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e598f6a3672c42f360072b85974cc176c1d5f1d3
--- /dev/null
+++ b/checkpoint-800/trainer_state.json
@@ -0,0 +1,350 @@
+{
+  "best_global_step": 800,
+  "best_metric": 40.9726561658299,
+  "best_model_checkpoint": "./HAUSA_B/checkpoint-800",
+  "epoch": 1.0825998645903858,
+  "eval_steps": 200,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027081922816519974,
+      "grad_norm": 106.59215545654297,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 6.1915,
+      "step": 20
+    },
+    {
+      "epoch": 0.05416384563303995,
+      "grad_norm": 30.563518524169922,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 4.5886,
+      "step": 40
+    },
+    {
+      "epoch": 0.08124576844955991,
+      "grad_norm": 16.528457641601562,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 3.0338,
+      "step": 60
+    },
+    {
+      "epoch": 0.1083276912660799,
+      "grad_norm": 13.852096557617188,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.3188,
+      "step": 80
+    },
+    {
+      "epoch": 0.13540961408259986,
+      "grad_norm": 13.284646987915039,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.9725,
+      "step": 100
+    },
+    {
+      "epoch": 0.16249153689911983,
+      "grad_norm": 13.212055206298828,
+      "learning_rate": 5.8e-06,
+      "loss": 1.7839,
+      "step": 120
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 12.006990432739258,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.5991,
+      "step": 140
+    },
+    {
+      "epoch": 0.2166553825321598,
+      "grad_norm": 12.490514755249023,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4411,
+      "step": 160
+    },
+    {
+      "epoch": 0.24373730534867977,
+      "grad_norm": 11.587646484375,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3487,
+      "step": 180
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "grad_norm": 11.574933052062988,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.2119,
+      "step": 200
+    },
+    {
+      "epoch": 0.2708192281651997,
+      "eval_loss": 1.1157827377319336,
+      "eval_runtime": 1601.2991,
+      "eval_samples_per_second": 3.688,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 64.22461160550755,
+      "step": 200
+    },
+    {
+      "epoch": 0.2979011509817197,
+      "grad_norm": 8.368565559387207,
+      "learning_rate": 9.920556107249256e-06,
+      "loss": 0.9452,
+      "step": 220
+    },
+    {
+      "epoch": 0.32498307379823965,
+      "grad_norm": 7.2616682052612305,
+      "learning_rate": 9.821251241310825e-06,
+      "loss": 0.9298,
+      "step": 240
+    },
+    {
+      "epoch": 0.35206499661475965,
+      "grad_norm": 7.266394138336182,
+      "learning_rate": 9.721946375372395e-06,
+      "loss": 0.8567,
+      "step": 260
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 8.120067596435547,
+      "learning_rate": 9.622641509433963e-06,
+      "loss": 0.8251,
+      "step": 280
+    },
+    {
+      "epoch": 0.4062288422477996,
+      "grad_norm": 7.483547687530518,
+      "learning_rate": 9.523336643495532e-06,
+      "loss": 0.7774,
+      "step": 300
+    },
+    {
+      "epoch": 0.4333107650643196,
+      "grad_norm": 7.521896839141846,
+      "learning_rate": 9.4240317775571e-06,
+      "loss": 0.7266,
+      "step": 320
+    },
+    {
+      "epoch": 0.46039268788083954,
+      "grad_norm": 7.073266506195068,
+      "learning_rate": 9.32472691161867e-06,
+      "loss": 0.7248,
+      "step": 340
+    },
+    {
+      "epoch": 0.48747461069735953,
+      "grad_norm": 6.335423469543457,
+      "learning_rate": 9.22542204568024e-06,
+      "loss": 0.7151,
+      "step": 360
+    },
+    {
+      "epoch": 0.5145565335138795,
+      "grad_norm": 6.936922550201416,
+      "learning_rate": 9.126117179741808e-06,
+      "loss": 0.6881,
+      "step": 380
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "grad_norm": 7.596807479858398,
+      "learning_rate": 9.026812313803377e-06,
+      "loss": 0.6995,
+      "step": 400
+    },
+    {
+      "epoch": 0.5416384563303994,
+      "eval_loss": 0.6352065801620483,
+      "eval_runtime": 1597.3635,
+      "eval_samples_per_second": 3.697,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 51.63653601672089,
+      "step": 400
+    },
+    {
+      "epoch": 0.5687203791469194,
+      "grad_norm": 6.981812477111816,
+      "learning_rate": 8.927507447864945e-06,
+      "loss": 0.6795,
+      "step": 420
+    },
+    {
+      "epoch": 0.5958023019634394,
+      "grad_norm": 6.481506824493408,
+      "learning_rate": 8.828202581926516e-06,
+      "loss": 0.6643,
+      "step": 440
+    },
+    {
+      "epoch": 0.6228842247799594,
+      "grad_norm": 6.537086009979248,
+      "learning_rate": 8.728897715988084e-06,
+      "loss": 0.6459,
+      "step": 460
+    },
+    {
+      "epoch": 0.6499661475964793,
+      "grad_norm": 6.739567756652832,
+      "learning_rate": 8.629592850049653e-06,
+      "loss": 0.6736,
+      "step": 480
+    },
+    {
+      "epoch": 0.6770480704129993,
+      "grad_norm": 7.422546863555908,
+      "learning_rate": 8.530287984111221e-06,
+      "loss": 0.6591,
+      "step": 500
+    },
+    {
+      "epoch": 0.7041299932295193,
+      "grad_norm": 5.7051215171813965,
+      "learning_rate": 8.430983118172792e-06,
+      "loss": 0.6442,
+      "step": 520
+    },
+    {
+      "epoch": 0.7312119160460393,
+      "grad_norm": 7.166143417358398,
+      "learning_rate": 8.33167825223436e-06,
+      "loss": 0.6326,
+      "step": 540
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "grad_norm": 7.759460926055908,
+      "learning_rate": 8.232373386295929e-06,
+      "loss": 0.6328,
+      "step": 560
+    },
+    {
+      "epoch": 0.7853757616790792,
+      "grad_norm": 5.876537799835205,
+      "learning_rate": 8.133068520357497e-06,
+      "loss": 0.5945,
+      "step": 580
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "grad_norm": 6.475106716156006,
+      "learning_rate": 8.033763654419066e-06,
+      "loss": 0.6038,
+      "step": 600
+    },
+    {
+      "epoch": 0.8124576844955992,
+      "eval_loss": 0.5318673849105835,
+      "eval_runtime": 1614.0202,
+      "eval_samples_per_second": 3.659,
+      "eval_steps_per_second": 0.458,
+      "eval_wer": 44.61419121291129,
+      "step": 600
+    },
+    {
+      "epoch": 0.8395396073121192,
+      "grad_norm": 6.8348259925842285,
+      "learning_rate": 7.934458788480636e-06,
+      "loss": 0.6046,
+      "step": 620
+    },
+    {
+      "epoch": 0.8666215301286392,
+      "grad_norm": 6.060784339904785,
+      "learning_rate": 7.835153922542206e-06,
+      "loss": 0.6055,
+      "step": 640
+    },
+    {
+      "epoch": 0.8937034529451591,
+      "grad_norm": 6.01262903213501,
+      "learning_rate": 7.735849056603775e-06,
+      "loss": 0.6139,
+      "step": 660
+    },
+    {
+      "epoch": 0.9207853757616791,
+      "grad_norm": 6.706854820251465,
+      "learning_rate": 7.636544190665344e-06,
+      "loss": 0.5789,
+      "step": 680
+    },
+    {
+      "epoch": 0.9478672985781991,
+      "grad_norm": 6.464681625366211,
+      "learning_rate": 7.537239324726913e-06,
+      "loss": 0.5857,
+      "step": 700
+    },
+    {
+      "epoch": 0.9749492213947191,
+      "grad_norm": 7.8035478591918945,
+      "learning_rate": 7.437934458788482e-06,
+      "loss": 0.5739,
+      "step": 720
+    },
+    {
+      "epoch": 1.001354096140826,
+      "grad_norm": 5.574532985687256,
+      "learning_rate": 7.33862959285005e-06,
+      "loss": 0.5443,
+      "step": 740
+    },
+    {
+      "epoch": 1.028436018957346,
+      "grad_norm": 5.275153160095215,
+      "learning_rate": 7.23932472691162e-06,
+      "loss": 0.4705,
+      "step": 760
+    },
+    {
+      "epoch": 1.055517941773866,
+      "grad_norm": 5.722527027130127,
+      "learning_rate": 7.140019860973188e-06,
+      "loss": 0.4692,
+      "step": 780
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "grad_norm": 5.501762866973877,
+      "learning_rate": 7.040714995034758e-06,
+      "loss": 0.4791,
+      "step": 800
+    },
+    {
+      "epoch": 1.0825998645903858,
+      "eval_loss": 0.46895861625671387,
+      "eval_runtime": 1599.6376,
+      "eval_samples_per_second": 3.691,
+      "eval_steps_per_second": 0.462,
+      "eval_wer": 40.9726561658299,
+      "step": 800
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.37970585698304e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-800/training_args.bin b/checkpoint-800/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2a3b1da275660c7c7439512aa770d076034c70c
--- /dev/null
+++ b/checkpoint-800/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d182356a12cee606170360f976946e1a56ce9d494fc1de269ffa184a80a19aa
+size 5432
diff --git a/runs/May01_13-39-42_acb56da0a579/events.out.tfevents.1746106844.acb56da0a579.820.0 b/runs/May01_13-39-42_acb56da0a579/events.out.tfevents.1746106844.acb56da0a579.820.0
index 41d8b7ec1b9a791af0ccd9c9501772d6db8a4a5d..b3684a557d2504a8737b681cde423fc885a3af7f 100644
--- a/runs/May01_13-39-42_acb56da0a579/events.out.tfevents.1746106844.acb56da0a579.820.0
+++ b/runs/May01_13-39-42_acb56da0a579/events.out.tfevents.1746106844.acb56da0a579.820.0
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6dd2f824700e3cfa92906aaae454080d39798ed78d4f8231982c1529f4c610
-size 32431
+oid sha256:73a520f59eca140c5bb729f978109d41ea6ed816044c2718cbd830af689490cc
+size 32785