sejalv/Fine_Tuned_LP_TROCR

README.md

@@ -0,0 +1,92 @@
+---
+base_model: microsoft/trocr-small-printed
+tags:
+- generated_from_trainer
+model-index:
+- name: seq2seq_model_printed
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# seq2seq_model_printed
+
+This model is a fine-tuned version of [microsoft/trocr-small-printed](https://huggingface.co/microsoft/trocr-small-printed) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5578
+- Cer: 0.2138
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 35
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Cer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 4.6751        | 1.0   | 244  | 3.5585          | 1.0652 |
+| 3.3624        | 2.0   | 488  | 2.7206          | 0.7373 |
+| 2.9125        | 3.0   | 732  | 1.9523          | 0.5418 |
+| 2.5734        | 4.0   | 976  | 2.0470          | 0.7149 |
+| 2.4143        | 5.0   | 1220 | 1.4577          | 0.3585 |
+| 2.2459        | 6.0   | 1464 | 1.5741          | 0.4501 |
+| 2.1514        | 7.0   | 1708 | 1.2625          | 0.3218 |
+| 2.0268        | 8.0   | 1952 | 1.4816          | 0.3625 |
+| 1.9513        | 9.0   | 2196 | 1.6085          | 0.3259 |
+| 1.7768        | 10.0  | 2440 | 1.4458          | 0.4033 |
+| 1.7156        | 11.0  | 2684 | 1.4845          | 0.3055 |
+| 1.5976        | 12.0  | 2928 | 1.6491          | 0.3503 |
+| 1.4664        | 13.0  | 3172 | 1.3220          | 0.3381 |
+| 1.3276        | 14.0  | 3416 | 1.4486          | 0.3503 |
+| 1.2354        | 15.0  | 3660 | 1.6394          | 0.3177 |
+| 1.1072        | 16.0  | 3904 | 1.5189          | 0.3035 |
+| 0.9209        | 17.0  | 4148 | 1.3820          | 0.2485 |
+| 0.7356        | 18.0  | 4392 | 1.4799          | 0.2607 |
+| 0.6336        | 19.0  | 4636 | 1.5075          | 0.2220 |
+| 0.5035        | 20.0  | 4880 | 1.5413          | 0.2179 |
+| 0.406         | 21.0  | 5124 | 1.5602          | 0.2464 |
+| 0.3294        | 22.0  | 5368 | 1.4495          | 0.2159 |
+| 0.2515        | 23.0  | 5612 | 1.5809          | 0.2240 |
+| 0.2207        | 24.0  | 5856 | 1.5188          | 0.2281 |
+| 0.1689        | 25.0  | 6100 | 1.5153          | 0.2118 |
+| 0.1426        | 26.0  | 6344 | 1.5616          | 0.2118 |
+| 0.1142        | 27.0  | 6588 | 1.7044          | 0.2179 |
+| 0.0785        | 28.0  | 6832 | 1.6267          | 0.2281 |
+| 0.0751        | 29.0  | 7076 | 1.6769          | 0.2159 |
+| 0.0507        | 30.0  | 7320 | 1.7316          | 0.2342 |
+| 0.0388        | 31.0  | 7564 | 1.5750          | 0.2220 |
+| 0.0264        | 32.0  | 7808 | 1.7028          | 0.2159 |
+| 0.021         | 33.0  | 8052 | 1.6861          | 0.2322 |
+| 0.0195        | 34.0  | 8296 | 1.7154          | 0.2077 |
+| 0.0167        | 35.0  | 8540 | 1.5578          | 0.2138 |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.1.0a0+b5021ba
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,177 @@
+{
+  "_name_or_path": "microsoft/trocr-small-printed",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "relu",
+    "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": 384,
+    "d_model": 256,
+    "decoder_attention_heads": 8,
+    "decoder_ffn_dim": 1024,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "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": true,
+    "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": false,
+    "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": 64044
+  },
+  "decoder_start_token_id": 0,
+  "early_stopping": true,
+  "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": 384,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 384,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "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": "deit",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 6,
+    "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": true,
+    "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": 2.0,
+  "max_length": 64,
+  "model_type": "vision-encoder-decoder",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "vocab_size": 64044
+}

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": 64,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.4",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28e2c89518b7b682e1aa1975f08597e0c9c25a3336c6aba88ed5a52606954c3
+size 246430696

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": false,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "DeiTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 384
+  }
+}

runs/Jul19_08-25-04_c7563290c136/events.out.tfevents.1721377505.c7563290c136.2155.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce4ea4f05647936ffabd1744258f6b9c5c46067936b9d3d443af081b937ecf5
+size 27911

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f44ea64464682100be27021a5049098da6857c411809b89599a189ea4cc4bc8
+size 5240