Training in progress, step 500
Browse files- config.json +79 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"VisionEncoderDecoderModel"
|
| 4 |
+
],
|
| 5 |
+
"decoder": {
|
| 6 |
+
"_attn_implementation_autoset": true,
|
| 7 |
+
"activation_dropout": 0.0,
|
| 8 |
+
"activation_function": "gelu",
|
| 9 |
+
"add_cross_attention": true,
|
| 10 |
+
"add_final_layer_norm": true,
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"classifier_dropout": 0.0,
|
| 13 |
+
"d_model": 1024,
|
| 14 |
+
"decoder_attention_heads": 16,
|
| 15 |
+
"decoder_ffn_dim": 4096,
|
| 16 |
+
"decoder_layerdrop": 0.0,
|
| 17 |
+
"decoder_layers": 10,
|
| 18 |
+
"dropout": 0.1,
|
| 19 |
+
"encoder_attention_heads": 16,
|
| 20 |
+
"encoder_ffn_dim": 4096,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 12,
|
| 23 |
+
"init_std": 0.02,
|
| 24 |
+
"is_decoder": true,
|
| 25 |
+
"is_encoder_decoder": false,
|
| 26 |
+
"max_length": 2048,
|
| 27 |
+
"max_position_embeddings": 4096,
|
| 28 |
+
"model_type": "mbart",
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"scale_embedding": true,
|
| 31 |
+
"tie_word_embeddings": false,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 73921
|
| 35 |
+
},
|
| 36 |
+
"decoder_start_token_id": 0,
|
| 37 |
+
"encoder": {
|
| 38 |
+
"_attn_implementation_autoset": true,
|
| 39 |
+
"attention_probs_dropout_prob": 0.0,
|
| 40 |
+
"depths": [
|
| 41 |
+
2,
|
| 42 |
+
2,
|
| 43 |
+
14,
|
| 44 |
+
2
|
| 45 |
+
],
|
| 46 |
+
"drop_path_rate": 0.1,
|
| 47 |
+
"embed_dim": 128,
|
| 48 |
+
"hidden_act": "gelu",
|
| 49 |
+
"hidden_dropout_prob": 0.0,
|
| 50 |
+
"hidden_size": 1024,
|
| 51 |
+
"image_size": [
|
| 52 |
+
896,
|
| 53 |
+
896
|
| 54 |
+
],
|
| 55 |
+
"initializer_range": 0.02,
|
| 56 |
+
"layer_norm_eps": 1e-05,
|
| 57 |
+
"mlp_ratio": 4.0,
|
| 58 |
+
"model_type": "donut-swin",
|
| 59 |
+
"num_channels": 3,
|
| 60 |
+
"num_heads": [
|
| 61 |
+
4,
|
| 62 |
+
8,
|
| 63 |
+
16,
|
| 64 |
+
32
|
| 65 |
+
],
|
| 66 |
+
"num_layers": 4,
|
| 67 |
+
"patch_size": 4,
|
| 68 |
+
"qkv_bias": true,
|
| 69 |
+
"torch_dtype": "float32",
|
| 70 |
+
"use_absolute_embeddings": false,
|
| 71 |
+
"window_size": 7
|
| 72 |
+
},
|
| 73 |
+
"is_encoder_decoder": true,
|
| 74 |
+
"model_type": "vision-encoder-decoder",
|
| 75 |
+
"pad_token_id": 1,
|
| 76 |
+
"tie_word_embeddings": false,
|
| 77 |
+
"torch_dtype": "float32",
|
| 78 |
+
"transformers_version": "4.56.0.dev0"
|
| 79 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be425295ec97ad7ad675707e98661150d2cf8ce0c70c88937c1ee50b9591fbed
|
| 3 |
+
size 1591180248
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dd6f68df441a5bb0a8684b825a879f75fa368bd7ea6fe2c899a74a9b4108c63
|
| 3 |
+
size 6033
|