Training in progress, epoch 1

config.json

@@ -4,117 +4,126 @@
   ],
   "decoder": {
     "_attn_implementation_autoset": true,
-    "_name_or_path": "vinai/bartpho-syllable",
-    "activation_dropout": 0.0,
-    "activation_function": "gelu",
+    "_name_or_path": "NlpHUST/gpt2-vietnamese",
+    "activation_function": "gelu_new",
     "add_cross_attention": true,
     "architectures": [
-      "MBartModel"
+      "GPT2LMHeadModel"
     ],
-    "attention_dropout": 0.0,
+    "attn_pdrop": 0.0,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
-    "bos_token_id": 0,
+    "bos_token_id": 50256,
     "chunk_size_feed_forward": 0,
-    "classifier_dropout": 0.0,
     "cross_attention_hidden_size": null,
-    "d_model": 1024,
-    "decoder_attention_heads": 16,
-    "decoder_ffn_dim": 4096,
-    "decoder_layerdrop": 0.0,
-    "decoder_layers": 12,
-    "decoder_start_token_id": 0,
+    "decoder_start_token_id": 50257,
     "diversity_penalty": 0.0,
     "do_sample": false,
-    "dropout": 0.1,
     "early_stopping": true,
-    "encoder_attention_heads": 16,
-    "encoder_ffn_dim": 4096,
-    "encoder_layerdrop": 0.0,
-    "encoder_layers": 12,
+    "embd_pdrop": 0.0,
     "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 2,
+    "eos_token_id": 50257,
     "exponential_decay_length_penalty": null,
     "finetuning_task": null,
     "forced_bos_token_id": null,
-    "forced_eos_token_id": 2,
-    "gradient_checkpointing": false,
+    "forced_eos_token_id": null,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
-    "init_std": 0.02,
+    "initializer_range": 0.02,
     "is_decoder": true,
     "is_encoder_decoder": false,
     "label2id": {
       "LABEL_0": 0,
       "LABEL_1": 1
     },
+    "layer_norm_epsilon": 1e-05,
     "length_penalty": 2.0,
     "max_length": 29,
-    "max_position_embeddings": 1024,
     "min_length": 0,
-    "model_type": "mbart",
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 12,
+    "n_positions": 1024,
     "no_repeat_ngram_size": 3,
     "num_beam_groups": 1,
     "num_beams": 4,
-    "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 1,
+    "pad_token_id": 50258,
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
     "remove_invalid_values": false,
+    "reorder_and_upcast_attn": false,
     "repetition_penalty": 1.0,
+    "resid_pdrop": 0.0,
     "return_dict": true,
     "return_dict_in_generate": false,
-    "scale_embedding": false,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
     "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
     "suppress_tokens": null,
-    "task_specific_params": null,
+    "task_specific_params": {
+      "text-generation": {
+        "do_sample": true,
+        "max_length": 50
+      }
+    },
     "temperature": 1.0,
     "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
-    "tokenizer_class": "BartphoTokenizer",
+    "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": "float32",
+    "torch_dtype": null,
     "torchscript": false,
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 40030
+    "vocab_size": 50259
   },
-  "decoder_start_token_id": 0,
+  "decoder_start_token_id": 50257,
   "early_stopping": null,
   "encoder": {
     "_attn_implementation_autoset": true,
-    "_name_or_path": "microsoft/beit-large-patch16-224-pt22k-ft22k",
+    "_name_or_path": "microsoft/swin-large-patch4-window12-384-in22k",
     "add_cross_attention": false,
-    "add_fpn": false,
     "architectures": [
-      "BeitForImageClassification"
+      "SwinForImageClassification"
     ],
     "attention_probs_dropout_prob": 0.0,
-    "auxiliary_channels": 256,
-    "auxiliary_concat_input": false,
-    "auxiliary_loss_weight": 0.4,
-    "auxiliary_num_convs": 1,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
     "bos_token_id": null,
     "chunk_size_feed_forward": 0,
     "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
+    "depths": [
+      2,
+      2,
+      18,
+      2
+    ],
     "diversity_penalty": 0.0,
     "do_sample": false,
     "drop_path_rate": 0.1,
     "early_stopping": false,
+    "embed_dim": 192,
     "encoder_no_repeat_ngram_size": 0,
+    "encoder_stride": 32,
     "eos_token_id": null,
     "exponential_decay_length_penalty": null,
     "finetuning_task": null,
@@ -122,7 +131,7 @@
     "forced_eos_token_id": null,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.0,
-    "hidden_size": 1024,
+    "hidden_size": 1536,
     "id2label": {
       "0": "organism, being",
       "1": "benthos",
@@ -21966,9 +21975,8 @@
       "21841": "chipboard, hardboard",
       "21842": "knothole"
     },
-    "image_size": 224,
+    "image_size": 384,
     "initializer_range": 0.02,
-    "intermediate_size": 4096,
     "is_decoder": false,
     "is_encoder_decoder": false,
     "label2id": {
@@ -43211,72 +43219,51 @@
       "zwieback, rusk, Brussels_biscuit, twice-baked_bread": 12729,
       "zygospore": 21630
     },
-    "layer_norm_eps": 1e-12,
-    "layer_scale_init_value": 0.1,
+    "layer_norm_eps": 1e-05,
     "length_penalty": 1.0,
     "max_length": 20,
     "min_length": 0,
-    "model_type": "beit",
+    "mlp_ratio": 4.0,
+    "model_type": "swin",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 16,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_channels": 3,
-    "num_hidden_layers": 24,
+    "num_heads": [
+      6,
+      12,
+      24,
+      48
+    ],
+    "num_layers": 4,
     "num_return_sequences": 1,
     "out_features": [
-      "stage24"
+      "stage4"
     ],
     "out_indices": [
-      24
+      4
     ],
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
     "pad_token_id": null,
-    "patch_size": 16,
-    "pool_scales": [
-      1,
-      2,
-      3,
-      6
-    ],
+    "patch_size": 4,
+    "path_norm": true,
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
+    "qkv_bias": true,
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
-    "reshape_hidden_states": true,
     "return_dict": true,
     "return_dict_in_generate": false,
-    "semantic_loss_ignore_index": 255,
     "sep_token_id": null,
     "stage_names": [
       "stem",
       "stage1",
       "stage2",
       "stage3",
-      "stage4",
-      "stage5",
-      "stage6",
-      "stage7",
-      "stage8",
-      "stage9",
-      "stage10",
-      "stage11",
-      "stage12",
-      "stage13",
-      "stage14",
-      "stage15",
-      "stage16",
-      "stage17",
-      "stage18",
-      "stage19",
-      "stage20",
-      "stage21",
-      "stage22",
-      "stage23",
-      "stage24"
+      "stage4"
     ],
     "suppress_tokens": null,
     "task_specific_params": null,
@@ -43290,26 +43277,21 @@
     "torch_dtype": "float32",
     "torchscript": false,
     "typical_p": 1.0,
-    "use_absolute_position_embeddings": false,
-    "use_auxiliary_head": true,
+    "use_absolute_embeddings": false,
     "use_bfloat16": false,
-    "use_mask_token": false,
-    "use_mean_pooling": true,
-    "use_relative_position_bias": true,
-    "use_shared_relative_position_bias": false,
-    "vocab_size": 8192
+    "window_size": 12
   },
-  "eos_token_id": 2,
+  "eos_token_id": 50257,
   "is_encoder_decoder": true,
   "length_penalty": null,
   "max_length": null,
   "model_type": "vision-encoder-decoder",
   "no_repeat_ngram_size": null,
   "num_beams": null,
-  "pad_token_id": 1,
+  "pad_token_id": 50258,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.46.2",
   "use_cache": false,
-  "vocab_size": 40030
+  "vocab_size": 50257
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f067af818fdaf6489b2d41b308e363ce3c01d12cc18654b5a70aab1ea4ec0e15
-size 2188139048
+oid sha256:ca33e1051c71c8ea69c5164c539dd6e008f63e75c9bd2621b784e310bcfce3aa
+size 1400816568

preprocessor_config.json

@@ -1,24 +1,22 @@
 {
-  "crop_size": 224,
-  "do_center_crop": false,
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.5,
-    0.5,
-    0.5
+    0.485,
+    0.456,
+    0.406
   ],
   "image_processor_type": "ViTImageProcessor",
   "image_std": [
-    0.5,
-    0.5,
-    0.5
+    0.229,
+    0.224,
+    0.225
   ],
-  "resample": 2,
+  "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "height": 224,
-    "width": 224
+    "height": 384,
+    "width": 384
   }
 }

runs/Nov30_13-17-05_3a55e4dea1ac/events.out.tfevents.1732972630.3a55e4dea1ac.847.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ecbcadf998c153e97334047eae0ceb3d4a5162b8b24b9d1e244e7f543dd6d9f
+size 1761368

runs/Nov30_13-18-52_3a55e4dea1ac/events.out.tfevents.1732972733.3a55e4dea1ac.4166.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe16f6d7ed2097b0ee9fbb458e3312e11e89661f1d967f708dc2d15df38631d
+size 1762242

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:debf02df871fc5dfa6dae15f563b696c84d8ee9b3e8b3212d735c908c3aa8cbc
+oid sha256:2fa015fb227493245f67922f6a49ea97cc1ef194da74222fb821d691980f64bd
 size 5432