diff --git a/checkpoint-100/config.json b/checkpoint-100/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ced4222cb643328043e5846a838f1b0d75d0d83b
--- /dev/null
+++ b/checkpoint-100/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": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 24,
+  "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": 24,
+  "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-100/generation_config.json b/checkpoint-100/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..035377aa01d1542153592ce34a9f47cdea4c4494
--- /dev/null
+++ b/checkpoint-100/generation_config.json
@@ -0,0 +1,159 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      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-100/model.safetensors b/checkpoint-100/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..10fa0cfa4ffa936fa854f5cf96bd65bd3ab40e2f
--- /dev/null
+++ b/checkpoint-100/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3ebee1bf3b577788f44086b6870c30708ea9f1ba2b0eff15ab61dd6f507f65c
+size 3055544304
diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..202c133f7eb32bed19a60c64ecc6b6ebd4c67b09
--- /dev/null
+++ b/checkpoint-100/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49465fa24f0262b8a7baa3b92f220091bb0737b6d58e7f3ea0b4be472eaaa1c0
+size 6099375168
diff --git a/checkpoint-100/preprocessor_config.json b/checkpoint-100/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-100/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-100/rng_state.pth b/checkpoint-100/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1b5da9e94bb690e2b3d657056ec31a38d8b459c8
--- /dev/null
+++ b/checkpoint-100/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206ef3b368b0d1bcf9682fc8a9634f453a8914feef8f3f6431f8b5a6d19ac754
+size 14244
diff --git a/checkpoint-100/scaler.pt b/checkpoint-100/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..68cbe07a0c1880c143cc57096d07ac81f4225bce
--- /dev/null
+++ b/checkpoint-100/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58025004ffe541fca138ed57adabef0bd5bed04e11b0203f3296606a56170727
+size 988
diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..203b414d8e8e23d686006756b7230eabd090b919
--- /dev/null
+++ b/checkpoint-100/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:343e706fe1b5301fef8ebce62d0e72a326ba6d161faefaad6659d8f462a7c19d
+size 1064
diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..55c40ec6f5e38ff1056e56b54f66495ac3dbf463
--- /dev/null
+++ b/checkpoint-100/trainer_state.json
@@ -0,0 +1,78 @@
+{
+  "best_global_step": 100,
+  "best_metric": 74.07821923770442,
+  "best_model_checkpoint": "./JUDICM/checkpoint-100",
+  "epoch": 1.1764705882352942,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 9.61864185333252,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 2.9117,
+      "step": 20
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 8.609731674194336,
+      "learning_rate": 3.7e-06,
+      "loss": 2.0419,
+      "step": 40
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 7.390444278717041,
+      "learning_rate": 5.7e-06,
+      "loss": 1.5565,
+      "step": 60
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 5.834730625152588,
+      "learning_rate": 7.7e-06,
+      "loss": 0.9792,
+      "step": 80
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 5.353567123413086,
+      "learning_rate": 9.7e-06,
+      "loss": 0.8465,
+      "step": 100
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "eval_loss": 0.681628942489624,
+      "eval_runtime": 544.1503,
+      "eval_samples_per_second": 1.251,
+      "eval_steps_per_second": 0.158,
+      "eval_wer": 74.07821923770442,
+      "step": 100
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.265935704064e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-100/training_args.bin b/checkpoint-100/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b990948ac695aca51324427d9fc6f4dd144df715
--- /dev/null
+++ b/checkpoint-100/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
+size 5432
diff --git a/checkpoint-200/config.json b/checkpoint-200/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ced4222cb643328043e5846a838f1b0d75d0d83b
--- /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": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 24,
+  "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": 24,
+  "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..035377aa01d1542153592ce34a9f47cdea4c4494
--- /dev/null
+++ b/checkpoint-200/generation_config.json
@@ -0,0 +1,159 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      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..dcd2358372ca6dac35f54d80b459205e4812e4df
--- /dev/null
+++ b/checkpoint-200/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb80cad6e6c0bd190bad04904e728e365d0cd82e74ca67db627395d7b7b9b6ed
+size 3055544304
diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2f76221b42ffec9a1bae18ca3b6919d81824784d
--- /dev/null
+++ b/checkpoint-200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e7dce3c10f367dc9b4b882c82f2048429b26057d19ba5b338942d84cf2723c
+size 6099375168
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..71a45a88efacb2266b0a1c4985971e2bc95ffcb7
--- /dev/null
+++ b/checkpoint-200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd0f8fdc4bb45d077a8e9acb5eb055f681544897e03e2d5a85f869738dfad064
+size 14244
diff --git a/checkpoint-200/scaler.pt b/checkpoint-200/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..248681be5965ad84a8960558630c817814f990f8
--- /dev/null
+++ b/checkpoint-200/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098a61a2b2f4e2e2958851a7c9c3c4c247f929913aa62a8e00cca76807496a30
+size 988
diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3052de27245494d518841af4073d5a6ddeb10b0b
--- /dev/null
+++ b/checkpoint-200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23427674df6bb33784b590ae4aa53899078e927f5e43e1c513019f2bf257b7de
+size 1064
diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..0e2be192bda62a53f00acf8b04e05aa71557bcfe
--- /dev/null
+++ b/checkpoint-200/trainer_state.json
@@ -0,0 +1,122 @@
+{
+  "best_global_step": 200,
+  "best_metric": 61.49350245600945,
+  "best_model_checkpoint": "./JUDICM/checkpoint-200",
+  "epoch": 2.3529411764705883,
+  "eval_steps": 100,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 9.61864185333252,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 2.9117,
+      "step": 20
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 8.609731674194336,
+      "learning_rate": 3.7e-06,
+      "loss": 2.0419,
+      "step": 40
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 7.390444278717041,
+      "learning_rate": 5.7e-06,
+      "loss": 1.5565,
+      "step": 60
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 5.834730625152588,
+      "learning_rate": 7.7e-06,
+      "loss": 0.9792,
+      "step": 80
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 5.353567123413086,
+      "learning_rate": 9.7e-06,
+      "loss": 0.8465,
+      "step": 100
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "eval_loss": 0.681628942489624,
+      "eval_runtime": 544.1503,
+      "eval_samples_per_second": 1.251,
+      "eval_steps_per_second": 0.158,
+      "eval_wer": 74.07821923770442,
+      "step": 100
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 4.50194787979126,
+      "learning_rate": 9.773333333333335e-06,
+      "loss": 0.6137,
+      "step": 120
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 4.959797382354736,
+      "learning_rate": 9.506666666666667e-06,
+      "loss": 0.6733,
+      "step": 140
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 5.115293502807617,
+      "learning_rate": 9.240000000000001e-06,
+      "loss": 0.7026,
+      "step": 160
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 3.1620101928710938,
+      "learning_rate": 8.973333333333334e-06,
+      "loss": 0.5185,
+      "step": 180
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 4.74745512008667,
+      "learning_rate": 8.706666666666667e-06,
+      "loss": 0.4669,
+      "step": 200
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "eval_loss": 0.47813770174980164,
+      "eval_runtime": 481.7363,
+      "eval_samples_per_second": 1.414,
+      "eval_steps_per_second": 0.179,
+      "eval_wer": 61.49350245600945,
+      "step": 200
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.531871408128e+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..b990948ac695aca51324427d9fc6f4dd144df715
--- /dev/null
+++ b/checkpoint-200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
+size 5432
diff --git a/checkpoint-300/config.json b/checkpoint-300/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ced4222cb643328043e5846a838f1b0d75d0d83b
--- /dev/null
+++ b/checkpoint-300/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": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 24,
+  "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": 24,
+  "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-300/generation_config.json b/checkpoint-300/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..035377aa01d1542153592ce34a9f47cdea4c4494
--- /dev/null
+++ b/checkpoint-300/generation_config.json
@@ -0,0 +1,159 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      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-300/model.safetensors b/checkpoint-300/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bb6d8044908cafa2e1bcec048c821687a2f70199
--- /dev/null
+++ b/checkpoint-300/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497c35a362547e9ba1900b0c03db786a40c943441435bf887d0bb98d248d5318
+size 3055544304
diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1c81ec4f097f3939bf9041c0c037dfc50b91e95e
--- /dev/null
+++ b/checkpoint-300/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf6cae18b948017cfeaef4190a0ba7646f69fbe7dad08d634e1a9dbfd937969a
+size 6099375168
diff --git a/checkpoint-300/preprocessor_config.json b/checkpoint-300/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-300/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-300/rng_state.pth b/checkpoint-300/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7782431774f7564b3d12ccce13f887201c82401d
--- /dev/null
+++ b/checkpoint-300/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a000fee4dd7a261704c082c4dab084235fdbbde3019d4960d7076ff17338940
+size 14244
diff --git a/checkpoint-300/scaler.pt b/checkpoint-300/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a40d0305231b45dc5275081bea5b41a6b5cf179e
--- /dev/null
+++ b/checkpoint-300/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f3e185550664b35057edb47f034e1766b2ebcedc050e4c0131c34e7d23a38aa
+size 988
diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b4271c1ae2d5236f56366876f5c950fd6e43b2c4
--- /dev/null
+++ b/checkpoint-300/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9122dc6585a724b33eebfaf95afd97b180142b91a30efe1fe1ddc84cb2148c14
+size 1064
diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..ee677230539c3bd0e29e5fd2ea77033d36d1beed
--- /dev/null
+++ b/checkpoint-300/trainer_state.json
@@ -0,0 +1,166 @@
+{
+  "best_global_step": 300,
+  "best_metric": 56.034321954859166,
+  "best_model_checkpoint": "./JUDICM/checkpoint-300",
+  "epoch": 3.5294117647058822,
+  "eval_steps": 100,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 9.61864185333252,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 2.9117,
+      "step": 20
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 8.609731674194336,
+      "learning_rate": 3.7e-06,
+      "loss": 2.0419,
+      "step": 40
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 7.390444278717041,
+      "learning_rate": 5.7e-06,
+      "loss": 1.5565,
+      "step": 60
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 5.834730625152588,
+      "learning_rate": 7.7e-06,
+      "loss": 0.9792,
+      "step": 80
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 5.353567123413086,
+      "learning_rate": 9.7e-06,
+      "loss": 0.8465,
+      "step": 100
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "eval_loss": 0.681628942489624,
+      "eval_runtime": 544.1503,
+      "eval_samples_per_second": 1.251,
+      "eval_steps_per_second": 0.158,
+      "eval_wer": 74.07821923770442,
+      "step": 100
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 4.50194787979126,
+      "learning_rate": 9.773333333333335e-06,
+      "loss": 0.6137,
+      "step": 120
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 4.959797382354736,
+      "learning_rate": 9.506666666666667e-06,
+      "loss": 0.6733,
+      "step": 140
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 5.115293502807617,
+      "learning_rate": 9.240000000000001e-06,
+      "loss": 0.7026,
+      "step": 160
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 3.1620101928710938,
+      "learning_rate": 8.973333333333334e-06,
+      "loss": 0.5185,
+      "step": 180
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 4.74745512008667,
+      "learning_rate": 8.706666666666667e-06,
+      "loss": 0.4669,
+      "step": 200
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "eval_loss": 0.47813770174980164,
+      "eval_runtime": 481.7363,
+      "eval_samples_per_second": 1.414,
+      "eval_steps_per_second": 0.179,
+      "eval_wer": 61.49350245600945,
+      "step": 200
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 3.0848231315612793,
+      "learning_rate": 8.44e-06,
+      "loss": 0.5316,
+      "step": 220
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 3.566438674926758,
+      "learning_rate": 8.173333333333334e-06,
+      "loss": 0.4629,
+      "step": 240
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 2.9106101989746094,
+      "learning_rate": 7.906666666666667e-06,
+      "loss": 0.4565,
+      "step": 260
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 3.077847957611084,
+      "learning_rate": 7.640000000000001e-06,
+      "loss": 0.345,
+      "step": 280
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 3.5237925052642822,
+      "learning_rate": 7.373333333333334e-06,
+      "loss": 0.3376,
+      "step": 300
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "eval_loss": 0.367522269487381,
+      "eval_runtime": 520.1482,
+      "eval_samples_per_second": 1.309,
+      "eval_steps_per_second": 0.165,
+      "eval_wer": 56.034321954859166,
+      "step": 300
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.797807112192e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b990948ac695aca51324427d9fc6f4dd144df715
--- /dev/null
+++ b/checkpoint-300/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
+size 5432
diff --git a/checkpoint-400/config.json b/checkpoint-400/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ced4222cb643328043e5846a838f1b0d75d0d83b
--- /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": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 24,
+  "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": 24,
+  "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..035377aa01d1542153592ce34a9f47cdea4c4494
--- /dev/null
+++ b/checkpoint-400/generation_config.json
@@ -0,0 +1,159 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      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..c0198c1e56b7b0db297b80ea158e0ee9deb0f061
--- /dev/null
+++ b/checkpoint-400/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1435db7ec114542dd0a7a7f41264db20faecb13e42bfde4dafbbc58909fdd332
+size 3055544304
diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3b10dca98dd40e23a90826b4e36675a25ba1c7df
--- /dev/null
+++ b/checkpoint-400/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b72a1be90d279a50cee3c99e5fd3d5a2b39107ea27dfc8fb72a3b793281ae3d
+size 6099375168
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..9fa7ecd7549c2028c6c5a43f51f5b67b8055d702
--- /dev/null
+++ b/checkpoint-400/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c93c0d763f2f48be1002eb5f8b1862aafe7a262f77f9e6372efd5930ed91ea
+size 14244
diff --git a/checkpoint-400/scaler.pt b/checkpoint-400/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6bb637de9092b5add69b1496c52f1d73e125e0a4
--- /dev/null
+++ b/checkpoint-400/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d411252348daa905c30280db2bbe3da9eb26fb7a099e6886c85784755a895b83
+size 988
diff --git a/checkpoint-400/scheduler.pt b/checkpoint-400/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a054329091489253bc3e2398ff9260c7da2103ec
--- /dev/null
+++ b/checkpoint-400/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d838619a5e73d7fb3ccfd45f48dd11a5b5251829dba401a7a2d6341f3b7f2d
+size 1064
diff --git a/checkpoint-400/trainer_state.json b/checkpoint-400/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..9d76f3262a0f87fb6b2b39aa728f4e07fdb2ffc0
--- /dev/null
+++ b/checkpoint-400/trainer_state.json
@@ -0,0 +1,210 @@
+{
+  "best_global_step": 300,
+  "best_metric": 56.034321954859166,
+  "best_model_checkpoint": "./JUDICM/checkpoint-300",
+  "epoch": 4.705882352941177,
+  "eval_steps": 100,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 9.61864185333252,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 2.9117,
+      "step": 20
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 8.609731674194336,
+      "learning_rate": 3.7e-06,
+      "loss": 2.0419,
+      "step": 40
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 7.390444278717041,
+      "learning_rate": 5.7e-06,
+      "loss": 1.5565,
+      "step": 60
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 5.834730625152588,
+      "learning_rate": 7.7e-06,
+      "loss": 0.9792,
+      "step": 80
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 5.353567123413086,
+      "learning_rate": 9.7e-06,
+      "loss": 0.8465,
+      "step": 100
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "eval_loss": 0.681628942489624,
+      "eval_runtime": 544.1503,
+      "eval_samples_per_second": 1.251,
+      "eval_steps_per_second": 0.158,
+      "eval_wer": 74.07821923770442,
+      "step": 100
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 4.50194787979126,
+      "learning_rate": 9.773333333333335e-06,
+      "loss": 0.6137,
+      "step": 120
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 4.959797382354736,
+      "learning_rate": 9.506666666666667e-06,
+      "loss": 0.6733,
+      "step": 140
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 5.115293502807617,
+      "learning_rate": 9.240000000000001e-06,
+      "loss": 0.7026,
+      "step": 160
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 3.1620101928710938,
+      "learning_rate": 8.973333333333334e-06,
+      "loss": 0.5185,
+      "step": 180
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 4.74745512008667,
+      "learning_rate": 8.706666666666667e-06,
+      "loss": 0.4669,
+      "step": 200
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "eval_loss": 0.47813770174980164,
+      "eval_runtime": 481.7363,
+      "eval_samples_per_second": 1.414,
+      "eval_steps_per_second": 0.179,
+      "eval_wer": 61.49350245600945,
+      "step": 200
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 3.0848231315612793,
+      "learning_rate": 8.44e-06,
+      "loss": 0.5316,
+      "step": 220
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 3.566438674926758,
+      "learning_rate": 8.173333333333334e-06,
+      "loss": 0.4629,
+      "step": 240
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 2.9106101989746094,
+      "learning_rate": 7.906666666666667e-06,
+      "loss": 0.4565,
+      "step": 260
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 3.077847957611084,
+      "learning_rate": 7.640000000000001e-06,
+      "loss": 0.345,
+      "step": 280
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 3.5237925052642822,
+      "learning_rate": 7.373333333333334e-06,
+      "loss": 0.3376,
+      "step": 300
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "eval_loss": 0.367522269487381,
+      "eval_runtime": 520.1482,
+      "eval_samples_per_second": 1.309,
+      "eval_steps_per_second": 0.165,
+      "eval_wer": 56.034321954859166,
+      "step": 300
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 3.1221227645874023,
+      "learning_rate": 7.1066666666666675e-06,
+      "loss": 0.3879,
+      "step": 320
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.873680353164673,
+      "learning_rate": 6.8400000000000014e-06,
+      "loss": 0.3156,
+      "step": 340
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 5.0606160163879395,
+      "learning_rate": 6.573333333333334e-06,
+      "loss": 0.243,
+      "step": 360
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 2.9561641216278076,
+      "learning_rate": 6.3066666666666676e-06,
+      "loss": 0.2344,
+      "step": 380
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 3.9523017406463623,
+      "learning_rate": 6.040000000000001e-06,
+      "loss": 0.2195,
+      "step": 400
+    },
+    {
+      "epoch": 4.705882352941177,
+      "eval_loss": 0.2805194854736328,
+      "eval_runtime": 475.2131,
+      "eval_samples_per_second": 1.433,
+      "eval_steps_per_second": 0.181,
+      "eval_wer": 58.521420133059756,
+      "step": 400
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3063742816256e+19,
+  "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..b990948ac695aca51324427d9fc6f4dd144df715
--- /dev/null
+++ b/checkpoint-400/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
+size 5432
diff --git a/checkpoint-500/config.json b/checkpoint-500/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ced4222cb643328043e5846a838f1b0d75d0d83b
--- /dev/null
+++ b/checkpoint-500/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": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 24,
+  "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": 24,
+  "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-500/generation_config.json b/checkpoint-500/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..035377aa01d1542153592ce34a9f47cdea4c4494
--- /dev/null
+++ b/checkpoint-500/generation_config.json
@@ -0,0 +1,159 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      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-500/model.safetensors b/checkpoint-500/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9346b89425b28fe347d169a6d31eeced1afeab33
--- /dev/null
+++ b/checkpoint-500/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ffb1025b60d7771f0d45de3868862f7fa639d5b01995833309266409f45e7de
+size 3055544304
diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ddc295313644576cc65209c7639460177c515613
--- /dev/null
+++ b/checkpoint-500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff7763bb0d44779104cc405fe7784b084baf7d3d20107a73feb3b806fbe7cb2a
+size 6099375168
diff --git a/checkpoint-500/preprocessor_config.json b/checkpoint-500/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-500/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-500/rng_state.pth b/checkpoint-500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7b8df181b811d7ab5d98241789ef144ded0475d3
--- /dev/null
+++ b/checkpoint-500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a341708b6cf11886bf8cc26bc3c6f36ad48ca33355cdd25d71b56ab641b962d4
+size 14244
diff --git a/checkpoint-500/scaler.pt b/checkpoint-500/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4793476ff3767e9e6be4287395fbc53b43953425
--- /dev/null
+++ b/checkpoint-500/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd0f2027b6dff8c9abeb7ff05269dab276fdd046a75d4d2cde10cb2835f2470
+size 988
diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d132e36966d34b9978922358defe2e7e71af4665
--- /dev/null
+++ b/checkpoint-500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e37d0e3abe4f26a67104e2dc03695cbf6a36428ae4534496e8677a64b279559
+size 1064
diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..1b379de23d23cf26bf78130ce9c9ae03fd897a78
--- /dev/null
+++ b/checkpoint-500/trainer_state.json
@@ -0,0 +1,254 @@
+{
+  "best_global_step": 300,
+  "best_metric": 56.034321954859166,
+  "best_model_checkpoint": "./JUDICM/checkpoint-300",
+  "epoch": 5.882352941176471,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 9.61864185333252,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 2.9117,
+      "step": 20
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 8.609731674194336,
+      "learning_rate": 3.7e-06,
+      "loss": 2.0419,
+      "step": 40
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 7.390444278717041,
+      "learning_rate": 5.7e-06,
+      "loss": 1.5565,
+      "step": 60
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 5.834730625152588,
+      "learning_rate": 7.7e-06,
+      "loss": 0.9792,
+      "step": 80
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 5.353567123413086,
+      "learning_rate": 9.7e-06,
+      "loss": 0.8465,
+      "step": 100
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "eval_loss": 0.681628942489624,
+      "eval_runtime": 544.1503,
+      "eval_samples_per_second": 1.251,
+      "eval_steps_per_second": 0.158,
+      "eval_wer": 74.07821923770442,
+      "step": 100
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 4.50194787979126,
+      "learning_rate": 9.773333333333335e-06,
+      "loss": 0.6137,
+      "step": 120
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 4.959797382354736,
+      "learning_rate": 9.506666666666667e-06,
+      "loss": 0.6733,
+      "step": 140
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 5.115293502807617,
+      "learning_rate": 9.240000000000001e-06,
+      "loss": 0.7026,
+      "step": 160
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 3.1620101928710938,
+      "learning_rate": 8.973333333333334e-06,
+      "loss": 0.5185,
+      "step": 180
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 4.74745512008667,
+      "learning_rate": 8.706666666666667e-06,
+      "loss": 0.4669,
+      "step": 200
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "eval_loss": 0.47813770174980164,
+      "eval_runtime": 481.7363,
+      "eval_samples_per_second": 1.414,
+      "eval_steps_per_second": 0.179,
+      "eval_wer": 61.49350245600945,
+      "step": 200
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 3.0848231315612793,
+      "learning_rate": 8.44e-06,
+      "loss": 0.5316,
+      "step": 220
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 3.566438674926758,
+      "learning_rate": 8.173333333333334e-06,
+      "loss": 0.4629,
+      "step": 240
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 2.9106101989746094,
+      "learning_rate": 7.906666666666667e-06,
+      "loss": 0.4565,
+      "step": 260
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 3.077847957611084,
+      "learning_rate": 7.640000000000001e-06,
+      "loss": 0.345,
+      "step": 280
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 3.5237925052642822,
+      "learning_rate": 7.373333333333334e-06,
+      "loss": 0.3376,
+      "step": 300
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "eval_loss": 0.367522269487381,
+      "eval_runtime": 520.1482,
+      "eval_samples_per_second": 1.309,
+      "eval_steps_per_second": 0.165,
+      "eval_wer": 56.034321954859166,
+      "step": 300
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 3.1221227645874023,
+      "learning_rate": 7.1066666666666675e-06,
+      "loss": 0.3879,
+      "step": 320
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.873680353164673,
+      "learning_rate": 6.8400000000000014e-06,
+      "loss": 0.3156,
+      "step": 340
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 5.0606160163879395,
+      "learning_rate": 6.573333333333334e-06,
+      "loss": 0.243,
+      "step": 360
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 2.9561641216278076,
+      "learning_rate": 6.3066666666666676e-06,
+      "loss": 0.2344,
+      "step": 380
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 3.9523017406463623,
+      "learning_rate": 6.040000000000001e-06,
+      "loss": 0.2195,
+      "step": 400
+    },
+    {
+      "epoch": 4.705882352941177,
+      "eval_loss": 0.2805194854736328,
+      "eval_runtime": 475.2131,
+      "eval_samples_per_second": 1.433,
+      "eval_steps_per_second": 0.181,
+      "eval_wer": 58.521420133059756,
+      "step": 400
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 3.081202983856201,
+      "learning_rate": 5.7733333333333345e-06,
+      "loss": 0.2079,
+      "step": 420
+    },
+    {
+      "epoch": 5.176470588235294,
+      "grad_norm": 3.1263742446899414,
+      "learning_rate": 5.506666666666667e-06,
+      "loss": 0.1388,
+      "step": 440
+    },
+    {
+      "epoch": 5.411764705882353,
+      "grad_norm": 3.4922068119049072,
+      "learning_rate": 5.240000000000001e-06,
+      "loss": 0.1538,
+      "step": 460
+    },
+    {
+      "epoch": 5.647058823529412,
+      "grad_norm": 5.9641594886779785,
+      "learning_rate": 4.973333333333334e-06,
+      "loss": 0.1697,
+      "step": 480
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 4.860027313232422,
+      "learning_rate": 4.706666666666667e-06,
+      "loss": 0.1284,
+      "step": 500
+    },
+    {
+      "epoch": 5.882352941176471,
+      "eval_loss": 0.2389652281999588,
+      "eval_runtime": 524.8677,
+      "eval_samples_per_second": 1.297,
+      "eval_steps_per_second": 0.164,
+      "eval_wer": 59.46651744077598,
+      "step": 500
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.632967852032e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b990948ac695aca51324427d9fc6f4dd144df715
--- /dev/null
+++ b/checkpoint-500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
+size 5432
diff --git a/checkpoint-600/config.json b/checkpoint-600/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ced4222cb643328043e5846a838f1b0d75d0d83b
--- /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": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 24,
+  "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": 24,
+  "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..035377aa01d1542153592ce34a9f47cdea4c4494
--- /dev/null
+++ b/checkpoint-600/generation_config.json
@@ -0,0 +1,159 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      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..d386bb1c973e7ea94252b22da76b9950830b2cd5
--- /dev/null
+++ b/checkpoint-600/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c51b90035065c4209d6c91e423f639291e67a58bc003611e93cb08ea46e31b90
+size 3055544304
diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c5c1bc4b9d4b43ee2699d468a5f997916e90fa9e
--- /dev/null
+++ b/checkpoint-600/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7553e91945014ab678edc7a97f6c8a40ce03ac2b20f466a51400bfdbf3eaf0f4
+size 6099375168
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..1c3fc1b849cdedaa6ea767c1a1c7a10068ade2e7
--- /dev/null
+++ b/checkpoint-600/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c4e8c97c46dc536590f8315c680a3c7f8f05be481adc89258038b02f7b81fe
+size 14244
diff --git a/checkpoint-600/scaler.pt b/checkpoint-600/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bc2691ce7eee8887dbba6d41911b2dd0c6fee6d0
--- /dev/null
+++ b/checkpoint-600/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3e78251943449f229c7ce872250cb25655dc18fb291b061529bfaa8ab87ee9
+size 988
diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..395c6d70393eb7a102b378eb393edfd60a464fbf
--- /dev/null
+++ b/checkpoint-600/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d46dd22904aaf85d0644f49c10885b626ac117fc0ebc918d1c08bcd9bcaed9a
+size 1064
diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa35edb4a81d9780012465b77968abb1757bfa23
--- /dev/null
+++ b/checkpoint-600/trainer_state.json
@@ -0,0 +1,298 @@
+{
+  "best_global_step": 300,
+  "best_metric": 56.034321954859166,
+  "best_model_checkpoint": "./JUDICM/checkpoint-300",
+  "epoch": 7.0588235294117645,
+  "eval_steps": 100,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 9.61864185333252,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 2.9117,
+      "step": 20
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 8.609731674194336,
+      "learning_rate": 3.7e-06,
+      "loss": 2.0419,
+      "step": 40
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 7.390444278717041,
+      "learning_rate": 5.7e-06,
+      "loss": 1.5565,
+      "step": 60
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 5.834730625152588,
+      "learning_rate": 7.7e-06,
+      "loss": 0.9792,
+      "step": 80
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 5.353567123413086,
+      "learning_rate": 9.7e-06,
+      "loss": 0.8465,
+      "step": 100
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "eval_loss": 0.681628942489624,
+      "eval_runtime": 544.1503,
+      "eval_samples_per_second": 1.251,
+      "eval_steps_per_second": 0.158,
+      "eval_wer": 74.07821923770442,
+      "step": 100
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 4.50194787979126,
+      "learning_rate": 9.773333333333335e-06,
+      "loss": 0.6137,
+      "step": 120
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 4.959797382354736,
+      "learning_rate": 9.506666666666667e-06,
+      "loss": 0.6733,
+      "step": 140
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 5.115293502807617,
+      "learning_rate": 9.240000000000001e-06,
+      "loss": 0.7026,
+      "step": 160
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 3.1620101928710938,
+      "learning_rate": 8.973333333333334e-06,
+      "loss": 0.5185,
+      "step": 180
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 4.74745512008667,
+      "learning_rate": 8.706666666666667e-06,
+      "loss": 0.4669,
+      "step": 200
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "eval_loss": 0.47813770174980164,
+      "eval_runtime": 481.7363,
+      "eval_samples_per_second": 1.414,
+      "eval_steps_per_second": 0.179,
+      "eval_wer": 61.49350245600945,
+      "step": 200
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 3.0848231315612793,
+      "learning_rate": 8.44e-06,
+      "loss": 0.5316,
+      "step": 220
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 3.566438674926758,
+      "learning_rate": 8.173333333333334e-06,
+      "loss": 0.4629,
+      "step": 240
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 2.9106101989746094,
+      "learning_rate": 7.906666666666667e-06,
+      "loss": 0.4565,
+      "step": 260
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 3.077847957611084,
+      "learning_rate": 7.640000000000001e-06,
+      "loss": 0.345,
+      "step": 280
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 3.5237925052642822,
+      "learning_rate": 7.373333333333334e-06,
+      "loss": 0.3376,
+      "step": 300
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "eval_loss": 0.367522269487381,
+      "eval_runtime": 520.1482,
+      "eval_samples_per_second": 1.309,
+      "eval_steps_per_second": 0.165,
+      "eval_wer": 56.034321954859166,
+      "step": 300
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 3.1221227645874023,
+      "learning_rate": 7.1066666666666675e-06,
+      "loss": 0.3879,
+      "step": 320
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.873680353164673,
+      "learning_rate": 6.8400000000000014e-06,
+      "loss": 0.3156,
+      "step": 340
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 5.0606160163879395,
+      "learning_rate": 6.573333333333334e-06,
+      "loss": 0.243,
+      "step": 360
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 2.9561641216278076,
+      "learning_rate": 6.3066666666666676e-06,
+      "loss": 0.2344,
+      "step": 380
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 3.9523017406463623,
+      "learning_rate": 6.040000000000001e-06,
+      "loss": 0.2195,
+      "step": 400
+    },
+    {
+      "epoch": 4.705882352941177,
+      "eval_loss": 0.2805194854736328,
+      "eval_runtime": 475.2131,
+      "eval_samples_per_second": 1.433,
+      "eval_steps_per_second": 0.181,
+      "eval_wer": 58.521420133059756,
+      "step": 400
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 3.081202983856201,
+      "learning_rate": 5.7733333333333345e-06,
+      "loss": 0.2079,
+      "step": 420
+    },
+    {
+      "epoch": 5.176470588235294,
+      "grad_norm": 3.1263742446899414,
+      "learning_rate": 5.506666666666667e-06,
+      "loss": 0.1388,
+      "step": 440
+    },
+    {
+      "epoch": 5.411764705882353,
+      "grad_norm": 3.4922068119049072,
+      "learning_rate": 5.240000000000001e-06,
+      "loss": 0.1538,
+      "step": 460
+    },
+    {
+      "epoch": 5.647058823529412,
+      "grad_norm": 5.9641594886779785,
+      "learning_rate": 4.973333333333334e-06,
+      "loss": 0.1697,
+      "step": 480
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 4.860027313232422,
+      "learning_rate": 4.706666666666667e-06,
+      "loss": 0.1284,
+      "step": 500
+    },
+    {
+      "epoch": 5.882352941176471,
+      "eval_loss": 0.2389652281999588,
+      "eval_runtime": 524.8677,
+      "eval_samples_per_second": 1.297,
+      "eval_steps_per_second": 0.164,
+      "eval_wer": 59.46651744077598,
+      "step": 500
+    },
+    {
+      "epoch": 6.117647058823529,
+      "grad_norm": 4.114612102508545,
+      "learning_rate": 4.440000000000001e-06,
+      "loss": 0.1121,
+      "step": 520
+    },
+    {
+      "epoch": 6.352941176470588,
+      "grad_norm": 2.893221855163574,
+      "learning_rate": 4.173333333333334e-06,
+      "loss": 0.1032,
+      "step": 540
+    },
+    {
+      "epoch": 6.588235294117647,
+      "grad_norm": 5.563397407531738,
+      "learning_rate": 3.906666666666667e-06,
+      "loss": 0.0902,
+      "step": 560
+    },
+    {
+      "epoch": 6.823529411764706,
+      "grad_norm": 3.545964002609253,
+      "learning_rate": 3.6400000000000003e-06,
+      "loss": 0.0801,
+      "step": 580
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "grad_norm": 0.6986887454986572,
+      "learning_rate": 3.3733333333333334e-06,
+      "loss": 0.0558,
+      "step": 600
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "eval_loss": 0.2277635931968689,
+      "eval_runtime": 501.1892,
+      "eval_samples_per_second": 1.359,
+      "eval_steps_per_second": 0.172,
+      "eval_wer": 59.578436858795,
+      "step": 600
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9595614224384e+19,
+  "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..b990948ac695aca51324427d9fc6f4dd144df715
--- /dev/null
+++ b/checkpoint-600/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
+size 5432
diff --git a/checkpoint-700/config.json b/checkpoint-700/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ced4222cb643328043e5846a838f1b0d75d0d83b
--- /dev/null
+++ b/checkpoint-700/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": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 24,
+  "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": 24,
+  "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-700/generation_config.json b/checkpoint-700/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..035377aa01d1542153592ce34a9f47cdea4c4494
--- /dev/null
+++ b/checkpoint-700/generation_config.json
@@ -0,0 +1,159 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      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-700/model.safetensors b/checkpoint-700/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7c699ba3d9c808938a0f083b80bdfa7c94672c15
--- /dev/null
+++ b/checkpoint-700/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faaa759e3ade1d2967fb5233a50c5d6845dcc9420e6a5d5dc9dc5c36e445590a
+size 3055544304
diff --git a/checkpoint-700/optimizer.pt b/checkpoint-700/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2955830c18373cd599066a5bce51a02776b53649
--- /dev/null
+++ b/checkpoint-700/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07cbb40df51129dc5bc22cb229aff396736fd2832dd017b3a5670bca0ec8ff6e
+size 6099375168
diff --git a/checkpoint-700/preprocessor_config.json b/checkpoint-700/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-700/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-700/rng_state.pth b/checkpoint-700/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d1a65d0138d9fbfe1760b507ab0f6d3003dd7348
--- /dev/null
+++ b/checkpoint-700/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d12d1b40d6ed415c35679a12634848e042ed3ae9ac31e649cc6d3ea286cf811
+size 14244
diff --git a/checkpoint-700/scaler.pt b/checkpoint-700/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..856ff4a64a5b0443eba559746242d54057c3be99
--- /dev/null
+++ b/checkpoint-700/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfec630398982b8f17c5c835db05f6537e84df77a436204e10fb5de9a5987d8c
+size 988
diff --git a/checkpoint-700/scheduler.pt b/checkpoint-700/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..eee9cb4347b24203e07e21ba7c4d4c3cfad52aa1
--- /dev/null
+++ b/checkpoint-700/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb16e99178a46012c67a4b4d91c2b43733a8bdecab272535bb9ee8ffb1aa83b
+size 1064
diff --git a/checkpoint-700/trainer_state.json b/checkpoint-700/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..7ebca45cf5ed8c9d9f57a4bf3d4f239554eab3e4
--- /dev/null
+++ b/checkpoint-700/trainer_state.json
@@ -0,0 +1,342 @@
+{
+  "best_global_step": 300,
+  "best_metric": 56.034321954859166,
+  "best_model_checkpoint": "./JUDICM/checkpoint-300",
+  "epoch": 8.235294117647058,
+  "eval_steps": 100,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 9.61864185333252,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 2.9117,
+      "step": 20
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 8.609731674194336,
+      "learning_rate": 3.7e-06,
+      "loss": 2.0419,
+      "step": 40
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 7.390444278717041,
+      "learning_rate": 5.7e-06,
+      "loss": 1.5565,
+      "step": 60
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 5.834730625152588,
+      "learning_rate": 7.7e-06,
+      "loss": 0.9792,
+      "step": 80
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 5.353567123413086,
+      "learning_rate": 9.7e-06,
+      "loss": 0.8465,
+      "step": 100
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "eval_loss": 0.681628942489624,
+      "eval_runtime": 544.1503,
+      "eval_samples_per_second": 1.251,
+      "eval_steps_per_second": 0.158,
+      "eval_wer": 74.07821923770442,
+      "step": 100
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 4.50194787979126,
+      "learning_rate": 9.773333333333335e-06,
+      "loss": 0.6137,
+      "step": 120
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 4.959797382354736,
+      "learning_rate": 9.506666666666667e-06,
+      "loss": 0.6733,
+      "step": 140
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 5.115293502807617,
+      "learning_rate": 9.240000000000001e-06,
+      "loss": 0.7026,
+      "step": 160
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 3.1620101928710938,
+      "learning_rate": 8.973333333333334e-06,
+      "loss": 0.5185,
+      "step": 180
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 4.74745512008667,
+      "learning_rate": 8.706666666666667e-06,
+      "loss": 0.4669,
+      "step": 200
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "eval_loss": 0.47813770174980164,
+      "eval_runtime": 481.7363,
+      "eval_samples_per_second": 1.414,
+      "eval_steps_per_second": 0.179,
+      "eval_wer": 61.49350245600945,
+      "step": 200
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 3.0848231315612793,
+      "learning_rate": 8.44e-06,
+      "loss": 0.5316,
+      "step": 220
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 3.566438674926758,
+      "learning_rate": 8.173333333333334e-06,
+      "loss": 0.4629,
+      "step": 240
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 2.9106101989746094,
+      "learning_rate": 7.906666666666667e-06,
+      "loss": 0.4565,
+      "step": 260
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 3.077847957611084,
+      "learning_rate": 7.640000000000001e-06,
+      "loss": 0.345,
+      "step": 280
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 3.5237925052642822,
+      "learning_rate": 7.373333333333334e-06,
+      "loss": 0.3376,
+      "step": 300
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "eval_loss": 0.367522269487381,
+      "eval_runtime": 520.1482,
+      "eval_samples_per_second": 1.309,
+      "eval_steps_per_second": 0.165,
+      "eval_wer": 56.034321954859166,
+      "step": 300
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 3.1221227645874023,
+      "learning_rate": 7.1066666666666675e-06,
+      "loss": 0.3879,
+      "step": 320
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.873680353164673,
+      "learning_rate": 6.8400000000000014e-06,
+      "loss": 0.3156,
+      "step": 340
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 5.0606160163879395,
+      "learning_rate": 6.573333333333334e-06,
+      "loss": 0.243,
+      "step": 360
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 2.9561641216278076,
+      "learning_rate": 6.3066666666666676e-06,
+      "loss": 0.2344,
+      "step": 380
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 3.9523017406463623,
+      "learning_rate": 6.040000000000001e-06,
+      "loss": 0.2195,
+      "step": 400
+    },
+    {
+      "epoch": 4.705882352941177,
+      "eval_loss": 0.2805194854736328,
+      "eval_runtime": 475.2131,
+      "eval_samples_per_second": 1.433,
+      "eval_steps_per_second": 0.181,
+      "eval_wer": 58.521420133059756,
+      "step": 400
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 3.081202983856201,
+      "learning_rate": 5.7733333333333345e-06,
+      "loss": 0.2079,
+      "step": 420
+    },
+    {
+      "epoch": 5.176470588235294,
+      "grad_norm": 3.1263742446899414,
+      "learning_rate": 5.506666666666667e-06,
+      "loss": 0.1388,
+      "step": 440
+    },
+    {
+      "epoch": 5.411764705882353,
+      "grad_norm": 3.4922068119049072,
+      "learning_rate": 5.240000000000001e-06,
+      "loss": 0.1538,
+      "step": 460
+    },
+    {
+      "epoch": 5.647058823529412,
+      "grad_norm": 5.9641594886779785,
+      "learning_rate": 4.973333333333334e-06,
+      "loss": 0.1697,
+      "step": 480
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 4.860027313232422,
+      "learning_rate": 4.706666666666667e-06,
+      "loss": 0.1284,
+      "step": 500
+    },
+    {
+      "epoch": 5.882352941176471,
+      "eval_loss": 0.2389652281999588,
+      "eval_runtime": 524.8677,
+      "eval_samples_per_second": 1.297,
+      "eval_steps_per_second": 0.164,
+      "eval_wer": 59.46651744077598,
+      "step": 500
+    },
+    {
+      "epoch": 6.117647058823529,
+      "grad_norm": 4.114612102508545,
+      "learning_rate": 4.440000000000001e-06,
+      "loss": 0.1121,
+      "step": 520
+    },
+    {
+      "epoch": 6.352941176470588,
+      "grad_norm": 2.893221855163574,
+      "learning_rate": 4.173333333333334e-06,
+      "loss": 0.1032,
+      "step": 540
+    },
+    {
+      "epoch": 6.588235294117647,
+      "grad_norm": 5.563397407531738,
+      "learning_rate": 3.906666666666667e-06,
+      "loss": 0.0902,
+      "step": 560
+    },
+    {
+      "epoch": 6.823529411764706,
+      "grad_norm": 3.545964002609253,
+      "learning_rate": 3.6400000000000003e-06,
+      "loss": 0.0801,
+      "step": 580
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "grad_norm": 0.6986887454986572,
+      "learning_rate": 3.3733333333333334e-06,
+      "loss": 0.0558,
+      "step": 600
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "eval_loss": 0.2277635931968689,
+      "eval_runtime": 501.1892,
+      "eval_samples_per_second": 1.359,
+      "eval_steps_per_second": 0.172,
+      "eval_wer": 59.578436858795,
+      "step": 600
+    },
+    {
+      "epoch": 7.294117647058823,
+      "grad_norm": 5.380858421325684,
+      "learning_rate": 3.106666666666667e-06,
+      "loss": 0.0519,
+      "step": 620
+    },
+    {
+      "epoch": 7.529411764705882,
+      "grad_norm": 0.6195468902587891,
+      "learning_rate": 2.84e-06,
+      "loss": 0.0408,
+      "step": 640
+    },
+    {
+      "epoch": 7.764705882352941,
+      "grad_norm": 0.9261361956596375,
+      "learning_rate": 2.573333333333334e-06,
+      "loss": 0.0507,
+      "step": 660
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.9102230668067932,
+      "learning_rate": 2.306666666666667e-06,
+      "loss": 0.0557,
+      "step": 680
+    },
+    {
+      "epoch": 8.235294117647058,
+      "grad_norm": 0.5318379402160645,
+      "learning_rate": 2.04e-06,
+      "loss": 0.0296,
+      "step": 700
+    },
+    {
+      "epoch": 8.235294117647058,
+      "eval_loss": 0.22038468718528748,
+      "eval_runtime": 502.7125,
+      "eval_samples_per_second": 1.355,
+      "eval_steps_per_second": 0.171,
+      "eval_wer": 59.329727040974944,
+      "step": 700
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2861549928448e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-700/training_args.bin b/checkpoint-700/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b990948ac695aca51324427d9fc6f4dd144df715
--- /dev/null
+++ b/checkpoint-700/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
+size 5432
diff --git a/checkpoint-800/config.json b/checkpoint-800/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ced4222cb643328043e5846a838f1b0d75d0d83b
--- /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": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 24,
+  "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": 24,
+  "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..035377aa01d1542153592ce34a9f47cdea4c4494
--- /dev/null
+++ b/checkpoint-800/generation_config.json
@@ -0,0 +1,159 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      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..2eb6b3d6e1e708b6a2ad8ae7328fd1b274b22028
--- /dev/null
+++ b/checkpoint-800/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78d4a1f45b1f8f9f2c001aba19b65c8a5aea1570aed690a72f31140e6aa5a74
+size 3055544304
diff --git a/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..99c968c96879e5b7e89f4d04146e9858b8e0f900
--- /dev/null
+++ b/checkpoint-800/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:688541091c21a3c7cecd3f07b02cc7b4b7bb71e4ad4cf416ac837a330950396c
+size 6099375168
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..e519cf300477e62a79c51b7098d39e6161dc8d1c
--- /dev/null
+++ b/checkpoint-800/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:103955276e91fb5534d93e871dde1da03cce037f848ba7a236b1c19db2d24967
+size 14244
diff --git a/checkpoint-800/scaler.pt b/checkpoint-800/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..648e0cb0129e31f94d784a407bf89506d59a8c5a
--- /dev/null
+++ b/checkpoint-800/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568558b38467e295768eced4a6789460a687fbc2f595e0a8756549e1878d70b7
+size 988
diff --git a/checkpoint-800/scheduler.pt b/checkpoint-800/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3594db3c39cd7c2a49b5f9aa70c06c35caf02cf6
--- /dev/null
+++ b/checkpoint-800/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:180ba15249ffbfeafef27a842c80652611e6770d582ad4bd65efde638c7011e3
+size 1064
diff --git a/checkpoint-800/trainer_state.json b/checkpoint-800/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..44640880d03cee5a8aff6a13757157d5be5fefe4
--- /dev/null
+++ b/checkpoint-800/trainer_state.json
@@ -0,0 +1,386 @@
+{
+  "best_global_step": 300,
+  "best_metric": 56.034321954859166,
+  "best_model_checkpoint": "./JUDICM/checkpoint-300",
+  "epoch": 9.411764705882353,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 9.61864185333252,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 2.9117,
+      "step": 20
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 8.609731674194336,
+      "learning_rate": 3.7e-06,
+      "loss": 2.0419,
+      "step": 40
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 7.390444278717041,
+      "learning_rate": 5.7e-06,
+      "loss": 1.5565,
+      "step": 60
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 5.834730625152588,
+      "learning_rate": 7.7e-06,
+      "loss": 0.9792,
+      "step": 80
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 5.353567123413086,
+      "learning_rate": 9.7e-06,
+      "loss": 0.8465,
+      "step": 100
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "eval_loss": 0.681628942489624,
+      "eval_runtime": 544.1503,
+      "eval_samples_per_second": 1.251,
+      "eval_steps_per_second": 0.158,
+      "eval_wer": 74.07821923770442,
+      "step": 100
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 4.50194787979126,
+      "learning_rate": 9.773333333333335e-06,
+      "loss": 0.6137,
+      "step": 120
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 4.959797382354736,
+      "learning_rate": 9.506666666666667e-06,
+      "loss": 0.6733,
+      "step": 140
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 5.115293502807617,
+      "learning_rate": 9.240000000000001e-06,
+      "loss": 0.7026,
+      "step": 160
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 3.1620101928710938,
+      "learning_rate": 8.973333333333334e-06,
+      "loss": 0.5185,
+      "step": 180
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 4.74745512008667,
+      "learning_rate": 8.706666666666667e-06,
+      "loss": 0.4669,
+      "step": 200
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "eval_loss": 0.47813770174980164,
+      "eval_runtime": 481.7363,
+      "eval_samples_per_second": 1.414,
+      "eval_steps_per_second": 0.179,
+      "eval_wer": 61.49350245600945,
+      "step": 200
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 3.0848231315612793,
+      "learning_rate": 8.44e-06,
+      "loss": 0.5316,
+      "step": 220
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 3.566438674926758,
+      "learning_rate": 8.173333333333334e-06,
+      "loss": 0.4629,
+      "step": 240
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 2.9106101989746094,
+      "learning_rate": 7.906666666666667e-06,
+      "loss": 0.4565,
+      "step": 260
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 3.077847957611084,
+      "learning_rate": 7.640000000000001e-06,
+      "loss": 0.345,
+      "step": 280
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 3.5237925052642822,
+      "learning_rate": 7.373333333333334e-06,
+      "loss": 0.3376,
+      "step": 300
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "eval_loss": 0.367522269487381,
+      "eval_runtime": 520.1482,
+      "eval_samples_per_second": 1.309,
+      "eval_steps_per_second": 0.165,
+      "eval_wer": 56.034321954859166,
+      "step": 300
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 3.1221227645874023,
+      "learning_rate": 7.1066666666666675e-06,
+      "loss": 0.3879,
+      "step": 320
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.873680353164673,
+      "learning_rate": 6.8400000000000014e-06,
+      "loss": 0.3156,
+      "step": 340
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 5.0606160163879395,
+      "learning_rate": 6.573333333333334e-06,
+      "loss": 0.243,
+      "step": 360
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 2.9561641216278076,
+      "learning_rate": 6.3066666666666676e-06,
+      "loss": 0.2344,
+      "step": 380
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 3.9523017406463623,
+      "learning_rate": 6.040000000000001e-06,
+      "loss": 0.2195,
+      "step": 400
+    },
+    {
+      "epoch": 4.705882352941177,
+      "eval_loss": 0.2805194854736328,
+      "eval_runtime": 475.2131,
+      "eval_samples_per_second": 1.433,
+      "eval_steps_per_second": 0.181,
+      "eval_wer": 58.521420133059756,
+      "step": 400
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 3.081202983856201,
+      "learning_rate": 5.7733333333333345e-06,
+      "loss": 0.2079,
+      "step": 420
+    },
+    {
+      "epoch": 5.176470588235294,
+      "grad_norm": 3.1263742446899414,
+      "learning_rate": 5.506666666666667e-06,
+      "loss": 0.1388,
+      "step": 440
+    },
+    {
+      "epoch": 5.411764705882353,
+      "grad_norm": 3.4922068119049072,
+      "learning_rate": 5.240000000000001e-06,
+      "loss": 0.1538,
+      "step": 460
+    },
+    {
+      "epoch": 5.647058823529412,
+      "grad_norm": 5.9641594886779785,
+      "learning_rate": 4.973333333333334e-06,
+      "loss": 0.1697,
+      "step": 480
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 4.860027313232422,
+      "learning_rate": 4.706666666666667e-06,
+      "loss": 0.1284,
+      "step": 500
+    },
+    {
+      "epoch": 5.882352941176471,
+      "eval_loss": 0.2389652281999588,
+      "eval_runtime": 524.8677,
+      "eval_samples_per_second": 1.297,
+      "eval_steps_per_second": 0.164,
+      "eval_wer": 59.46651744077598,
+      "step": 500
+    },
+    {
+      "epoch": 6.117647058823529,
+      "grad_norm": 4.114612102508545,
+      "learning_rate": 4.440000000000001e-06,
+      "loss": 0.1121,
+      "step": 520
+    },
+    {
+      "epoch": 6.352941176470588,
+      "grad_norm": 2.893221855163574,
+      "learning_rate": 4.173333333333334e-06,
+      "loss": 0.1032,
+      "step": 540
+    },
+    {
+      "epoch": 6.588235294117647,
+      "grad_norm": 5.563397407531738,
+      "learning_rate": 3.906666666666667e-06,
+      "loss": 0.0902,
+      "step": 560
+    },
+    {
+      "epoch": 6.823529411764706,
+      "grad_norm": 3.545964002609253,
+      "learning_rate": 3.6400000000000003e-06,
+      "loss": 0.0801,
+      "step": 580
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "grad_norm": 0.6986887454986572,
+      "learning_rate": 3.3733333333333334e-06,
+      "loss": 0.0558,
+      "step": 600
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "eval_loss": 0.2277635931968689,
+      "eval_runtime": 501.1892,
+      "eval_samples_per_second": 1.359,
+      "eval_steps_per_second": 0.172,
+      "eval_wer": 59.578436858795,
+      "step": 600
+    },
+    {
+      "epoch": 7.294117647058823,
+      "grad_norm": 5.380858421325684,
+      "learning_rate": 3.106666666666667e-06,
+      "loss": 0.0519,
+      "step": 620
+    },
+    {
+      "epoch": 7.529411764705882,
+      "grad_norm": 0.6195468902587891,
+      "learning_rate": 2.84e-06,
+      "loss": 0.0408,
+      "step": 640
+    },
+    {
+      "epoch": 7.764705882352941,
+      "grad_norm": 0.9261361956596375,
+      "learning_rate": 2.573333333333334e-06,
+      "loss": 0.0507,
+      "step": 660
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.9102230668067932,
+      "learning_rate": 2.306666666666667e-06,
+      "loss": 0.0557,
+      "step": 680
+    },
+    {
+      "epoch": 8.235294117647058,
+      "grad_norm": 0.5318379402160645,
+      "learning_rate": 2.04e-06,
+      "loss": 0.0296,
+      "step": 700
+    },
+    {
+      "epoch": 8.235294117647058,
+      "eval_loss": 0.22038468718528748,
+      "eval_runtime": 502.7125,
+      "eval_samples_per_second": 1.355,
+      "eval_steps_per_second": 0.171,
+      "eval_wer": 59.329727040974944,
+      "step": 700
+    },
+    {
+      "epoch": 8.470588235294118,
+      "grad_norm": 1.5851385593414307,
+      "learning_rate": 1.7733333333333336e-06,
+      "loss": 0.0313,
+      "step": 720
+    },
+    {
+      "epoch": 8.705882352941176,
+      "grad_norm": 0.4058867394924164,
+      "learning_rate": 1.506666666666667e-06,
+      "loss": 0.0353,
+      "step": 740
+    },
+    {
+      "epoch": 8.941176470588236,
+      "grad_norm": 0.6031798720359802,
+      "learning_rate": 1.2400000000000002e-06,
+      "loss": 0.0254,
+      "step": 760
+    },
+    {
+      "epoch": 9.176470588235293,
+      "grad_norm": 1.5348103046417236,
+      "learning_rate": 9.733333333333333e-07,
+      "loss": 0.0191,
+      "step": 780
+    },
+    {
+      "epoch": 9.411764705882353,
+      "grad_norm": 0.9447113275527954,
+      "learning_rate": 7.066666666666667e-07,
+      "loss": 0.0234,
+      "step": 800
+    },
+    {
+      "epoch": 9.411764705882353,
+      "eval_loss": 0.22373367846012115,
+      "eval_runtime": 497.079,
+      "eval_samples_per_second": 1.37,
+      "eval_steps_per_second": 0.173,
+      "eval_wer": 56.401168936143755,
+      "step": 800
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6127485632512e+19,
+  "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..b990948ac695aca51324427d9fc6f4dd144df715
--- /dev/null
+++ b/checkpoint-800/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
+size 5432
diff --git a/checkpoint-850/config.json b/checkpoint-850/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ced4222cb643328043e5846a838f1b0d75d0d83b
--- /dev/null
+++ b/checkpoint-850/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": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 24,
+  "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": 24,
+  "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-850/generation_config.json b/checkpoint-850/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..035377aa01d1542153592ce34a9f47cdea4c4494
--- /dev/null
+++ b/checkpoint-850/generation_config.json
@@ -0,0 +1,159 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      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-850/model.safetensors b/checkpoint-850/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7df47b960af8e367c96f7b2baa05802423ab8637
--- /dev/null
+++ b/checkpoint-850/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8203d6a7f5589333c285a8bf1584e29ecd6fda7615c679f6f095c15939197b
+size 3055544304
diff --git a/checkpoint-850/optimizer.pt b/checkpoint-850/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2bdbf05a73bd39bf96561416b87f0c8f507a0b98
--- /dev/null
+++ b/checkpoint-850/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714c168d715f0be8d720190dfdae2c5b491f25e65d189a012a9eb1fb5e7af700
+size 6099375168
diff --git a/checkpoint-850/preprocessor_config.json b/checkpoint-850/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d7c5b1dfd466c815664b16139e8f605620d22e4e
--- /dev/null
+++ b/checkpoint-850/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-850/rng_state.pth b/checkpoint-850/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0f1c00bf57ae1c7443b7bab72f2c33e359cc7a2c
--- /dev/null
+++ b/checkpoint-850/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:028cad0091abe783b0d31b0bc32f23aae7f0e52a793b3581c871ae65d02698d0
+size 14244
diff --git a/checkpoint-850/scaler.pt b/checkpoint-850/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ec8b3f7ba8c18f63d2d168e89f828b37c81bd084
--- /dev/null
+++ b/checkpoint-850/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601e164b841dd7303cc9b6e6d1246ccfe602ff2cecd422a6535e439df77c0962
+size 988
diff --git a/checkpoint-850/scheduler.pt b/checkpoint-850/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6273d20759a7e9cfaa41cb90c916f25ffb5ed6e6
--- /dev/null
+++ b/checkpoint-850/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:addb94f000bf4ff6afcfd865969db46b21c56041e9a4a9baef556c46b1c07096
+size 1064
diff --git a/checkpoint-850/trainer_state.json b/checkpoint-850/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..81581bcfc7d63339b1122d029f9fc47e66c6bfe4
--- /dev/null
+++ b/checkpoint-850/trainer_state.json
@@ -0,0 +1,400 @@
+{
+  "best_global_step": 300,
+  "best_metric": 56.034321954859166,
+  "best_model_checkpoint": "./JUDICM/checkpoint-300",
+  "epoch": 10.0,
+  "eval_steps": 100,
+  "global_step": 850,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 9.61864185333252,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 2.9117,
+      "step": 20
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 8.609731674194336,
+      "learning_rate": 3.7e-06,
+      "loss": 2.0419,
+      "step": 40
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 7.390444278717041,
+      "learning_rate": 5.7e-06,
+      "loss": 1.5565,
+      "step": 60
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 5.834730625152588,
+      "learning_rate": 7.7e-06,
+      "loss": 0.9792,
+      "step": 80
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 5.353567123413086,
+      "learning_rate": 9.7e-06,
+      "loss": 0.8465,
+      "step": 100
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "eval_loss": 0.681628942489624,
+      "eval_runtime": 544.1503,
+      "eval_samples_per_second": 1.251,
+      "eval_steps_per_second": 0.158,
+      "eval_wer": 74.07821923770442,
+      "step": 100
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 4.50194787979126,
+      "learning_rate": 9.773333333333335e-06,
+      "loss": 0.6137,
+      "step": 120
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 4.959797382354736,
+      "learning_rate": 9.506666666666667e-06,
+      "loss": 0.6733,
+      "step": 140
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 5.115293502807617,
+      "learning_rate": 9.240000000000001e-06,
+      "loss": 0.7026,
+      "step": 160
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 3.1620101928710938,
+      "learning_rate": 8.973333333333334e-06,
+      "loss": 0.5185,
+      "step": 180
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 4.74745512008667,
+      "learning_rate": 8.706666666666667e-06,
+      "loss": 0.4669,
+      "step": 200
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "eval_loss": 0.47813770174980164,
+      "eval_runtime": 481.7363,
+      "eval_samples_per_second": 1.414,
+      "eval_steps_per_second": 0.179,
+      "eval_wer": 61.49350245600945,
+      "step": 200
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 3.0848231315612793,
+      "learning_rate": 8.44e-06,
+      "loss": 0.5316,
+      "step": 220
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 3.566438674926758,
+      "learning_rate": 8.173333333333334e-06,
+      "loss": 0.4629,
+      "step": 240
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 2.9106101989746094,
+      "learning_rate": 7.906666666666667e-06,
+      "loss": 0.4565,
+      "step": 260
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 3.077847957611084,
+      "learning_rate": 7.640000000000001e-06,
+      "loss": 0.345,
+      "step": 280
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 3.5237925052642822,
+      "learning_rate": 7.373333333333334e-06,
+      "loss": 0.3376,
+      "step": 300
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "eval_loss": 0.367522269487381,
+      "eval_runtime": 520.1482,
+      "eval_samples_per_second": 1.309,
+      "eval_steps_per_second": 0.165,
+      "eval_wer": 56.034321954859166,
+      "step": 300
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 3.1221227645874023,
+      "learning_rate": 7.1066666666666675e-06,
+      "loss": 0.3879,
+      "step": 320
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.873680353164673,
+      "learning_rate": 6.8400000000000014e-06,
+      "loss": 0.3156,
+      "step": 340
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 5.0606160163879395,
+      "learning_rate": 6.573333333333334e-06,
+      "loss": 0.243,
+      "step": 360
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 2.9561641216278076,
+      "learning_rate": 6.3066666666666676e-06,
+      "loss": 0.2344,
+      "step": 380
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 3.9523017406463623,
+      "learning_rate": 6.040000000000001e-06,
+      "loss": 0.2195,
+      "step": 400
+    },
+    {
+      "epoch": 4.705882352941177,
+      "eval_loss": 0.2805194854736328,
+      "eval_runtime": 475.2131,
+      "eval_samples_per_second": 1.433,
+      "eval_steps_per_second": 0.181,
+      "eval_wer": 58.521420133059756,
+      "step": 400
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 3.081202983856201,
+      "learning_rate": 5.7733333333333345e-06,
+      "loss": 0.2079,
+      "step": 420
+    },
+    {
+      "epoch": 5.176470588235294,
+      "grad_norm": 3.1263742446899414,
+      "learning_rate": 5.506666666666667e-06,
+      "loss": 0.1388,
+      "step": 440
+    },
+    {
+      "epoch": 5.411764705882353,
+      "grad_norm": 3.4922068119049072,
+      "learning_rate": 5.240000000000001e-06,
+      "loss": 0.1538,
+      "step": 460
+    },
+    {
+      "epoch": 5.647058823529412,
+      "grad_norm": 5.9641594886779785,
+      "learning_rate": 4.973333333333334e-06,
+      "loss": 0.1697,
+      "step": 480
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 4.860027313232422,
+      "learning_rate": 4.706666666666667e-06,
+      "loss": 0.1284,
+      "step": 500
+    },
+    {
+      "epoch": 5.882352941176471,
+      "eval_loss": 0.2389652281999588,
+      "eval_runtime": 524.8677,
+      "eval_samples_per_second": 1.297,
+      "eval_steps_per_second": 0.164,
+      "eval_wer": 59.46651744077598,
+      "step": 500
+    },
+    {
+      "epoch": 6.117647058823529,
+      "grad_norm": 4.114612102508545,
+      "learning_rate": 4.440000000000001e-06,
+      "loss": 0.1121,
+      "step": 520
+    },
+    {
+      "epoch": 6.352941176470588,
+      "grad_norm": 2.893221855163574,
+      "learning_rate": 4.173333333333334e-06,
+      "loss": 0.1032,
+      "step": 540
+    },
+    {
+      "epoch": 6.588235294117647,
+      "grad_norm": 5.563397407531738,
+      "learning_rate": 3.906666666666667e-06,
+      "loss": 0.0902,
+      "step": 560
+    },
+    {
+      "epoch": 6.823529411764706,
+      "grad_norm": 3.545964002609253,
+      "learning_rate": 3.6400000000000003e-06,
+      "loss": 0.0801,
+      "step": 580
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "grad_norm": 0.6986887454986572,
+      "learning_rate": 3.3733333333333334e-06,
+      "loss": 0.0558,
+      "step": 600
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "eval_loss": 0.2277635931968689,
+      "eval_runtime": 501.1892,
+      "eval_samples_per_second": 1.359,
+      "eval_steps_per_second": 0.172,
+      "eval_wer": 59.578436858795,
+      "step": 600
+    },
+    {
+      "epoch": 7.294117647058823,
+      "grad_norm": 5.380858421325684,
+      "learning_rate": 3.106666666666667e-06,
+      "loss": 0.0519,
+      "step": 620
+    },
+    {
+      "epoch": 7.529411764705882,
+      "grad_norm": 0.6195468902587891,
+      "learning_rate": 2.84e-06,
+      "loss": 0.0408,
+      "step": 640
+    },
+    {
+      "epoch": 7.764705882352941,
+      "grad_norm": 0.9261361956596375,
+      "learning_rate": 2.573333333333334e-06,
+      "loss": 0.0507,
+      "step": 660
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.9102230668067932,
+      "learning_rate": 2.306666666666667e-06,
+      "loss": 0.0557,
+      "step": 680
+    },
+    {
+      "epoch": 8.235294117647058,
+      "grad_norm": 0.5318379402160645,
+      "learning_rate": 2.04e-06,
+      "loss": 0.0296,
+      "step": 700
+    },
+    {
+      "epoch": 8.235294117647058,
+      "eval_loss": 0.22038468718528748,
+      "eval_runtime": 502.7125,
+      "eval_samples_per_second": 1.355,
+      "eval_steps_per_second": 0.171,
+      "eval_wer": 59.329727040974944,
+      "step": 700
+    },
+    {
+      "epoch": 8.470588235294118,
+      "grad_norm": 1.5851385593414307,
+      "learning_rate": 1.7733333333333336e-06,
+      "loss": 0.0313,
+      "step": 720
+    },
+    {
+      "epoch": 8.705882352941176,
+      "grad_norm": 0.4058867394924164,
+      "learning_rate": 1.506666666666667e-06,
+      "loss": 0.0353,
+      "step": 740
+    },
+    {
+      "epoch": 8.941176470588236,
+      "grad_norm": 0.6031798720359802,
+      "learning_rate": 1.2400000000000002e-06,
+      "loss": 0.0254,
+      "step": 760
+    },
+    {
+      "epoch": 9.176470588235293,
+      "grad_norm": 1.5348103046417236,
+      "learning_rate": 9.733333333333333e-07,
+      "loss": 0.0191,
+      "step": 780
+    },
+    {
+      "epoch": 9.411764705882353,
+      "grad_norm": 0.9447113275527954,
+      "learning_rate": 7.066666666666667e-07,
+      "loss": 0.0234,
+      "step": 800
+    },
+    {
+      "epoch": 9.411764705882353,
+      "eval_loss": 0.22373367846012115,
+      "eval_runtime": 497.079,
+      "eval_samples_per_second": 1.37,
+      "eval_steps_per_second": 0.173,
+      "eval_wer": 56.401168936143755,
+      "step": 800
+    },
+    {
+      "epoch": 9.647058823529411,
+      "grad_norm": 0.2331121265888214,
+      "learning_rate": 4.4e-07,
+      "loss": 0.0084,
+      "step": 820
+    },
+    {
+      "epoch": 9.882352941176471,
+      "grad_norm": 0.7352120280265808,
+      "learning_rate": 1.7333333333333335e-07,
+      "loss": 0.0157,
+      "step": 840
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.7760453484544e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-850/training_args.bin b/checkpoint-850/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b990948ac695aca51324427d9fc6f4dd144df715
--- /dev/null
+++ b/checkpoint-850/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
+size 5432
diff --git a/runs/May01_16-17-06_cffb3ce9e37b/events.out.tfevents.1746116229.cffb3ce9e37b.5237.3 b/runs/May01_16-17-06_cffb3ce9e37b/events.out.tfevents.1746116229.cffb3ce9e37b.5237.3
index 35acaeb200cce4606b0be6e88d63c832f8472f9b..fa705ff4157011de3429f920088e71787dbe9f9c 100644
--- a/runs/May01_16-17-06_cffb3ce9e37b/events.out.tfevents.1746116229.cffb3ce9e37b.5237.3
+++ b/runs/May01_16-17-06_cffb3ce9e37b/events.out.tfevents.1746116229.cffb3ce9e37b.5237.3
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c859249f21cf261a107fac97ce19834b083b2165c46b4e0a4d51ff7be934ab
-size 17122
+oid sha256:805a06e33eaf542168f60a94eea0b37e6d7287b32dee2fbc2ae740a1aa182c6f
+size 17476