Training in progress, step 500
Browse files
config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"VisionEncoderDecoderModel"
|
| 4 |
+
],
|
| 5 |
+
"decoder": {
|
| 6 |
+
"activation_dropout": 0.0,
|
| 7 |
+
"activation_function": "gelu",
|
| 8 |
+
"add_cross_attention": true,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"cross_attention_hidden_size": 768,
|
| 12 |
+
"d_model": 1024,
|
| 13 |
+
"decoder_attention_heads": 16,
|
| 14 |
+
"decoder_ffn_dim": 4096,
|
| 15 |
+
"decoder_layerdrop": 0.0,
|
| 16 |
+
"decoder_layers": 12,
|
| 17 |
+
"dropout": 0.1,
|
| 18 |
+
"init_std": 0.02,
|
| 19 |
+
"is_decoder": true,
|
| 20 |
+
"layernorm_embedding": true,
|
| 21 |
+
"max_position_embeddings": 512,
|
| 22 |
+
"model_type": "trocr",
|
| 23 |
+
"scale_embedding": false,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"use_learned_position_embeddings": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
},
|
| 29 |
+
"decoder_start_token_id": 0,
|
| 30 |
+
"encoder": {
|
| 31 |
+
"attention_probs_dropout_prob": 0.0,
|
| 32 |
+
"encoder_stride": 16,
|
| 33 |
+
"hidden_act": "gelu",
|
| 34 |
+
"hidden_dropout_prob": 0.0,
|
| 35 |
+
"hidden_size": 768,
|
| 36 |
+
"image_size": 384,
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"intermediate_size": 3072,
|
| 39 |
+
"layer_norm_eps": 1e-12,
|
| 40 |
+
"model_type": "vit",
|
| 41 |
+
"num_attention_heads": 12,
|
| 42 |
+
"num_channels": 3,
|
| 43 |
+
"num_hidden_layers": 12,
|
| 44 |
+
"patch_size": 16,
|
| 45 |
+
"pooler_act": "tanh",
|
| 46 |
+
"pooler_output_size": 768,
|
| 47 |
+
"qkv_bias": false,
|
| 48 |
+
"torch_dtype": "float32"
|
| 49 |
+
},
|
| 50 |
+
"is_encoder_decoder": true,
|
| 51 |
+
"model_type": "vision-encoder-decoder",
|
| 52 |
+
"pad_token_id": 1,
|
| 53 |
+
"processor_class": "TrOCRProcessor",
|
| 54 |
+
"tie_word_embeddings": false,
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.53.2"
|
| 57 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71ddc2107c38ba7f826e6d82275f41d82c65585f4c04951311bc82ca11c96a89
|
| 3 |
+
size 1335747032
|
runs/Jul21_00-32-26_e089e18c7bc3/events.out.tfevents.1753057953.e089e18c7bc3.437.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b546f10d2a75fd582e7dc34498733ae7d21cbb5c012012aa69fe79327c4ca543
|
| 3 |
+
size 6321
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91efc0c57db0335d673030d4bfb1a4dee4841819b0ee29635add0ddd13822eb8
|
| 3 |
+
size 5905
|