Training in progress, step 50

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "GiorgiSekhniashvili/whisper-tiny-ka-02",
+  "_name_or_path": "GiorgiSekhniashvili/whisper-tiny-ka-01",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -7,10 +7,7 @@
     "WhisperForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
-  "begin_suppress_tokens": [
-    220,
-    50257
-  ],
+  "begin_suppress_tokens": null,
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
   "d_model": 384,
@@ -25,7 +22,20 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 4,
   "eos_token_id": 50257,
-  "forced_decoder_ids": null,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
@@ -34,7 +44,7 @@
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
-  "max_length": 448,
+  "max_length": null,
   "max_source_positions": 1500,
   "max_target_positions": 448,
   "median_filter_width": 7,
@@ -43,10 +53,9 @@
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
-  "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
-  "use_cache": false,
+  "transformers_version": "4.48.0",
+  "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64c5d6688ba739d2518ba266e893b7aa83bb05e90cc6e83ac148709ef063e039
+oid sha256:b62a2a8c47d2d50c6c5e7a3529055a26fd0b6ea5ab1f37e2f8d2df66e3687630
 size 151061672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93a7c03a7c36fe242b4cc2cdfb181c3a3d1e7e197702083e84c7ba45e5c3f612
-size 4667
+oid sha256:3fb2efe0aa0d7f2e985b32649ce41573d3d1eff30130f73bb6547c64a7ffa838
+size 5496