Training in progress, epoch 2, checkpoint

checkpoint-2500/config.json

@@ -0,0 +1,176 @@
+{
+  "_name_or_path": "kkatiz/thai-trocr-thaigov-v2",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
+    "add_cross_attention": true,
+    "architectures": [
+      "RobertaForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "camembert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_head": 12,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 39544
+  },
+  "decoder_start_token_id": 5,
+  "encoder": {
+    "_name_or_path": "encoder",
+    "add_cross_attention": false,
+    "architectures": [
+      "ViTModel"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "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,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "encoder_stride": 16,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 384,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "vit",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": false,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "eos_token_id": 6,
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.2",
+  "vocab_size": 39544
+}

checkpoint-2500/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "decoder_start_token_id": 5,
+  "early_stopping": true,
+  "eos_token_id": 6,
+  "length_penalty": 2.0,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.39.2",
+  "vocab_size": 39544
+}

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f85adb924d2edd7adca448d1971a1392c27dcc504d9870df2c6440e7e741645
+size 925948800

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d947bc8329e7a7a45d7de5f16208773fe3b0be8c86d10903387890056cab59
+size 1847454910

checkpoint-2500/preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 384
+  }
+}

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9ea095ef6611c36d7e5b3904a03e2e7be7d3ffc1039c725955caa78de66899
+size 14244

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de8b6835fe3754207894e756017dbd88f9b1a5590a114b7412804a86544d2b2b
+size 1064

checkpoint-2500/trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.201437473297119,
+      "learning_rate": 4.9e-05,
+      "loss": 2.6116,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.178571701049805,
+      "learning_rate": 4.8e-05,
+      "loss": 1.9634,
+      "step": 200
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.5103917121887207,
+      "learning_rate": 4.7e-05,
+      "loss": 1.6752,
+      "step": 300
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.7221550941467285,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.483,
+      "step": 400
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.4923272132873535,
+      "learning_rate": 4.5e-05,
+      "loss": 1.3296,
+      "step": 500
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 6.077773571014404,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.1978,
+      "step": 600
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.388939142227173,
+      "learning_rate": 4.3e-05,
+      "loss": 1.1306,
+      "step": 700
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.460210084915161,
+      "learning_rate": 4.201e-05,
+      "loss": 1.0513,
+      "step": 800
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.139218330383301,
+      "learning_rate": 4.101e-05,
+      "loss": 0.9612,
+      "step": 900
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.382781505584717,
+      "learning_rate": 4.0010000000000005e-05,
+      "loss": 0.8977,
+      "step": 1000
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 6.498015403747559,
+      "learning_rate": 3.902e-05,
+      "loss": 0.8653,
+      "step": 1100
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.856051445007324,
+      "learning_rate": 3.802e-05,
+      "loss": 0.8131,
+      "step": 1200
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 2.134838819503784,
+      "learning_rate": 3.702e-05,
+      "loss": 0.7421,
+      "step": 1300
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 2.3750529289245605,
+      "learning_rate": 3.6020000000000004e-05,
+      "loss": 0.6864,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.56854510307312,
+      "learning_rate": 3.502e-05,
+      "loss": 0.6453,
+      "step": 1500
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 2.0850515365600586,
+      "learning_rate": 3.402e-05,
+      "loss": 0.6245,
+      "step": 1600
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 2.8658158779144287,
+      "learning_rate": 3.302e-05,
+      "loss": 0.597,
+      "step": 1700
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 2.8391458988189697,
+      "learning_rate": 3.202e-05,
+      "loss": 0.5792,
+      "step": 1800
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.1407833099365234,
+      "learning_rate": 3.102e-05,
+      "loss": 0.5501,
+      "step": 1900
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 3.772876739501953,
+      "learning_rate": 3.0020000000000004e-05,
+      "loss": 0.5411,
+      "step": 2000
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 1.72440505027771,
+      "learning_rate": 2.9020000000000003e-05,
+      "loss": 0.5107,
+      "step": 2100
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 3.845543622970581,
+      "learning_rate": 2.8020000000000003e-05,
+      "loss": 0.4988,
+      "step": 2200
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.5010182857513428,
+      "learning_rate": 2.7020000000000002e-05,
+      "loss": 0.48,
+      "step": 2300
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.9300732612609863,
+      "learning_rate": 2.602e-05,
+      "loss": 0.4683,
+      "step": 2400
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.938793659210205,
+      "learning_rate": 2.5019999999999998e-05,
+      "loss": 0.4501,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 3.835588846288896e+20,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60849881d7de4a5d829e6552d876c4866e51fa690f19468483c79816a9cac15c
+size 5176