Upload TR OCR custom model checkpoint

config.json

@@ -0,0 +1,177 @@
+{
+  "_name_or_path": "microsoft/trocr-large-handwritten",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": 1024,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 12,
+    "decoder_start_token_id": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "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,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layernorm_embedding": true,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "trocr",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": 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,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": false,
+    "use_learned_position_embeddings": true,
+    "vocab_size": 50265
+  },
+  "decoder_start_token_id": 0,
+  "early_stopping": null,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "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": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 384,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "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": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "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": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "eos_token_id": 2,
+  "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,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 128,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.45.2",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:101871dae29db9057f9c7752597ab36edc51c180db8a0374be175d2a9bc8c47e
+size 2232985336

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97533d60e6f1c861b07c5eca03e2c9921056e7791a19ef3004558b6675d450da
+size 2947809280

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "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
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd82af33de6afdd38c126837a6cef1796d39e1c508be57950b45f6628c47ecb
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c7dac7fa99e6b47e321738efd3b54f56245b52ba9442a9555dedeadefa6bdec
+size 1064

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-large", "tokenizer_class": "RobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": 0.8729119896888733,
+  "best_model_checkpoint": "seq2seq_model_handwritten/checkpoint-1656",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 2070,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 91.65796661376953,
+      "learning_rate": 4.512077294685991e-05,
+      "loss": 2.3731,
+      "step": 207
+    },
+    {
+      "epoch": 1.0,
+      "eval_cer": 0.5382716049382716,
+      "eval_loss": 1.7942910194396973,
+      "eval_runtime": 7.573,
+      "eval_samples_per_second": 3.961,
+      "eval_steps_per_second": 1.056,
+      "step": 207
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 28.777713775634766,
+      "learning_rate": 4.012077294685991e-05,
+      "loss": 1.5318,
+      "step": 414
+    },
+    {
+      "epoch": 2.0,
+      "eval_cer": 1.9481481481481482,
+      "eval_loss": 2.347219944000244,
+      "eval_runtime": 10.932,
+      "eval_samples_per_second": 2.744,
+      "eval_steps_per_second": 0.732,
+      "step": 414
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.893929481506348,
+      "learning_rate": 3.51207729468599e-05,
+      "loss": 1.1272,
+      "step": 621
+    },
+    {
+      "epoch": 3.0,
+      "eval_cer": 0.3925925925925926,
+      "eval_loss": 1.6664316654205322,
+      "eval_runtime": 5.6669,
+      "eval_samples_per_second": 5.294,
+      "eval_steps_per_second": 1.412,
+      "step": 621
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 12.895403861999512,
+      "learning_rate": 3.0120772946859905e-05,
+      "loss": 0.8353,
+      "step": 828
+    },
+    {
+      "epoch": 4.0,
+      "eval_cer": 0.35555555555555557,
+      "eval_loss": 1.744159460067749,
+      "eval_runtime": 5.9067,
+      "eval_samples_per_second": 5.079,
+      "eval_steps_per_second": 1.354,
+      "step": 828
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 10.83328914642334,
+      "learning_rate": 2.5120772946859905e-05,
+      "loss": 0.6815,
+      "step": 1035
+    },
+    {
+      "epoch": 5.0,
+      "eval_cer": 0.2617283950617284,
+      "eval_loss": 1.6649540662765503,
+      "eval_runtime": 6.0195,
+      "eval_samples_per_second": 4.984,
+      "eval_steps_per_second": 1.329,
+      "step": 1035
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 39.549861907958984,
+      "learning_rate": 2.0120772946859902e-05,
+      "loss": 0.4102,
+      "step": 1242
+    },
+    {
+      "epoch": 6.0,
+      "eval_cer": 0.2419753086419753,
+      "eval_loss": 1.126643180847168,
+      "eval_runtime": 5.5303,
+      "eval_samples_per_second": 5.425,
+      "eval_steps_per_second": 1.447,
+      "step": 1242
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 33.302223205566406,
+      "learning_rate": 1.5120772946859905e-05,
+      "loss": 0.3097,
+      "step": 1449
+    },
+    {
+      "epoch": 7.0,
+      "eval_cer": 0.2617283950617284,
+      "eval_loss": 1.1228829622268677,
+      "eval_runtime": 5.9786,
+      "eval_samples_per_second": 5.018,
+      "eval_steps_per_second": 1.338,
+      "step": 1449
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.6234323382377625,
+      "learning_rate": 1.0120772946859903e-05,
+      "loss": 0.2095,
+      "step": 1656
+    },
+    {
+      "epoch": 8.0,
+      "eval_cer": 0.2074074074074074,
+      "eval_loss": 0.8729119896888733,
+      "eval_runtime": 6.0046,
+      "eval_samples_per_second": 4.996,
+      "eval_steps_per_second": 1.332,
+      "step": 1656
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 3.2294392585754395,
+      "learning_rate": 5.120772946859904e-06,
+      "loss": 0.1344,
+      "step": 1863
+    },
+    {
+      "epoch": 9.0,
+      "eval_cer": 0.1580246913580247,
+      "eval_loss": 0.9647266268730164,
+      "eval_runtime": 6.0304,
+      "eval_samples_per_second": 4.975,
+      "eval_steps_per_second": 1.327,
+      "step": 1863
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.18482227623462677,
+      "learning_rate": 1.2077294685990338e-07,
+      "loss": 0.0616,
+      "step": 2070
+    },
+    {
+      "epoch": 10.0,
+      "eval_cer": 0.1308641975308642,
+      "eval_loss": 0.9429413080215454,
+      "eval_runtime": 6.0359,
+      "eval_samples_per_second": 4.97,
+      "eval_steps_per_second": 1.325,
+      "step": 2070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1125309068426609e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:572ae67ea2ee2ef6f4f9fd5ba514f8e8d37878eb7779d562260b4a9cf0d5e827
+size 5368