Hugging Face's logo

hadrakey
/
alphapen_trocr_large_45000

Safetensors
vision-encoder-decoder
Model card Files Community
hadrakey commited on
Commit
9a845d0
•
1 Parent(s): 3b97f06

Training in progress, step 1000

Browse files
Files changed (6) hide show
  1. adapter_config.json +3 -3
  2. adapter_model.safetensors +1 -1
  3. config.json +1 -2
  4. model.safetensors +1 -1
  5. trainer_lora.py +3 -3
  6. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -24,10 +24,10 @@
24
  "revision": null,
25
  "target_modules": [
26
  "intermediate.dense",
27
- "key",
28
  "output.dense",
29
- "value",
30
- "query"
 
31
  ],
32
  "task_type": null,
33
  "use_dora": false,
 
24
  "revision": null,
25
  "target_modules": [
26
  "intermediate.dense",
 
27
  "output.dense",
28
+ "query",
29
+ "key",
30
+ "value"
31
  ],
32
  "task_type": null,
33
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c90013bbcf117465415008cd1e9209c2ab679f465f4a1afa524ba9fc186e7a3
3
  size 1811016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88c5081af754f2692d708a8bfb91ad6b11e06c9c30b341c16bf6e037e0a19a00
3
  size 1811016
config.json CHANGED
@@ -173,6 +173,5 @@
173
  "processor_class": "TrOCRProcessor",
174
  "tie_word_embeddings": false,
175
  "torch_dtype": "float32",
176
- "transformers_version": "4.42.3",
177
- "vocab_size": 50265
178
  }
 
173
  "processor_class": "TrOCRProcessor",
174
  "tie_word_embeddings": false,
175
  "torch_dtype": "float32",
176
+ "transformers_version": "4.44.2"
 
177
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b5c9a57267f9760bd4a7647d8ba830dc2631f0d0cd17ce843b0c314a00d5e79
3
  size 1335747032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14472ca382e9d96ea7efd3c778cbf0b73a412e31bc41cfec8d97e8988e6063d
3
  size 1335747032
trainer_lora.py CHANGED
@@ -57,10 +57,10 @@ root_dir = "/mnt/data1/Datasets/OCR/Alphapen/clean_data/final_cropped_rotated_"
57
  root_dir_b2 = "/mnt/data1/Datasets/OCR/Alphapen/DataBatch2/clean_data/cropped_data/cropped_"
58
  processor = TrOCRProcessor.from_pretrained(model_name)
59
 
60
- train_dataset_b1 = AphaPenDataset(root_dir=root_dir, df=train_df.iloc[:100,:], processor=processor)
61
- eval_dataset_b1 = AphaPenDataset(root_dir=root_dir, df=test_df.iloc[:100,:], processor=processor)
62
 
63
- eval_dataset_b2 = AphaPenDataset(root_dir=root_dir_b2, df=test_df_b2.iloc[:100,:], processor=processor)
64
 
65
  # train_dataset = ConcatDataset([train_dataset_b1, train_dataset_b2])
66
  eval_dataset = ConcatDataset([eval_dataset_b1, eval_dataset_b2])
 
57
  root_dir_b2 = "/mnt/data1/Datasets/OCR/Alphapen/DataBatch2/clean_data/cropped_data/cropped_"
58
  processor = TrOCRProcessor.from_pretrained(model_name)
59
 
60
+ train_dataset_b1 = AphaPenDataset(root_dir=root_dir, df=train_df, processor=processor)
61
+ eval_dataset_b1 = AphaPenDataset(root_dir=root_dir, df=test_df, processor=processor)
62
 
63
+ eval_dataset_b2 = AphaPenDataset(root_dir=root_dir_b2, df=test_df_b2, processor=processor)
64
 
65
  # train_dataset = ConcatDataset([train_dataset_b1, train_dataset_b2])
66
  eval_dataset = ConcatDataset([eval_dataset_b1, eval_dataset_b2])
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4194f08dc71e0a28f3b2e45e3d8295d81460016ced31554a21c6a58a78648e24
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26785aa9184a34e48ffa5ecd2b8318d40cfd69409fb16b3c5c47878a258dd031
3
  size 5368