Training in progress, step 2000

config.json

@@ -2,7 +2,7 @@
   "architectures": [
     "SpeechEncoderDecoderModel"
   ],
-  "bos_token_id": 0,
+  "bos_token_id": 50000,
   "decoder": {
     "_attn_implementation_autoset": false,
     "_name_or_path": "fav-kky/gpt2-small-cs",
@@ -14,11 +14,11 @@
     "attn_pdrop": 0.1,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
-    "bos_token_id": 0,
+    "bos_token_id": 50000,
     "chunk_size_feed_forward": 0,
     "cross_attention_hidden_size": null,
-    "decoder_start_token_id": 0,
-    "decoder_vocab_size": 50000,
+    "decoder_start_token_id": 50000,
+    "decoder_vocab_size": 50002,
     "diversity_penalty": 0.0,
     "do_sample": false,
     "early_stopping": false,
@@ -26,8 +26,8 @@
     "encoder_ctc_loss_reduction": "mean",
     "encoder_layerdrop": 0.0,
     "encoder_no_repeat_ngram_size": 0,
-    "encoder_pad_token_id": 0,
-    "encoder_vocab_size": 50000,
+    "encoder_pad_token_id": 50001,
+    "encoder_vocab_size": 50002,
     "eos_token_id": 0,
     "exponential_decay_length_penalty": null,
     "finetuning_task": null,
@@ -47,7 +47,6 @@
     },
     "layer_norm_epsilon": 1e-05,
     "length_penalty": 1.0,
-    "mask_token_id": null,
     "max_length": 20,
     "min_length": 0,
     "model_type": "gpt2",
@@ -64,7 +63,7 @@
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 0,
+    "pad_token_id": 50001,
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
@@ -101,9 +100,9 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 50000
+    "vocab_size": 50002
   },
-  "decoder_start_token_id": 0,
+  "decoder_start_token_id": 50000,
   "encoder": {
     "_attn_implementation_autoset": false,
     "_name_or_path": "fav-kky/wav2vec2-base-cs-80k-ClTRUS",
@@ -120,7 +119,7 @@
     "attention_dropout": 0.1,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
-    "bos_token_id": 0,
+    "bos_token_id": 50000,
     "chunk_size_feed_forward": 0,
     "classifier_proj_size": 256,
     "codevector_dim": 256,
@@ -156,8 +155,8 @@
     "cross_attention_hidden_size": null,
     "ctc_loss_reduction": "sum",
     "ctc_zero_infinity": false,
-    "decoder_start_token_id": null,
-    "decoder_vocab_size": 50000,
+    "decoder_start_token_id": 50000,
+    "decoder_vocab_size": 50002,
     "diversity_loss_weight": 0.1,
     "diversity_penalty": 0.0,
     "do_sample": false,
@@ -166,8 +165,8 @@
     "encoder_ctc_loss_reduction": "mean",
     "encoder_layerdrop": 0.0,
     "encoder_no_repeat_ngram_size": 0,
-    "encoder_pad_token_id": 0,
-    "encoder_vocab_size": 50000,
+    "encoder_pad_token_id": 50001,
+    "encoder_vocab_size": 50002,
     "eos_token_id": 0,
     "exponential_decay_length_penalty": null,
     "feat_extract_activation": "gelu",
@@ -202,7 +201,6 @@
     "mask_time_length": 10,
     "mask_time_min_masks": 2,
     "mask_time_prob": 0.05,
-    "mask_token_id": null,
     "max_length": 20,
     "min_length": 0,
     "model_type": "wav2vec2",
@@ -223,7 +221,7 @@
     "output_hidden_size": 768,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 0,
+    "pad_token_id": 50001,
     "prefix": null,
     "problem_type": null,
     "proj_codevector_dim": 256,
@@ -274,7 +272,7 @@
   "eos_token_id": 0,
   "is_encoder_decoder": true,
   "model_type": "speech-encoder-decoder",
-  "pad_token_id": 0,
+  "pad_token_id": 50001,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.49.0"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bbfd1fb052347e73354c43b34b1bd6d3169a552e75a529e636b5c4449cba80b
-size 550862672
+oid sha256:a6c11deb910a326616126aebcc1e8e2afa1dbb2f0eb892c3da257f2ae759d7cb
+size 550866768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2424ec6d2f7b258ccbd71da6253ef1133bb223b4d24ea4e546834750eebba3d
-size 7800
+oid sha256:11fa44b3b8da62cb0d948e4fe6159afce332e4a75a1f94e121b8483ac5e2e1fd
+size 5624