Training in progress, epoch 1
Browse files
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Pix2StructForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"decoder_start_token_id": 50378,
|
| 6 |
+
"dtype": "float32",
|
| 7 |
+
"eos_token_id": 1,
|
| 8 |
+
"initializer_factor": 1.0,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"is_encoder_decoder": true,
|
| 11 |
+
"is_vqa": false,
|
| 12 |
+
"model_type": "pix2struct",
|
| 13 |
+
"pad_token_id": 0,
|
| 14 |
+
"text_config": {
|
| 15 |
+
"d_ff": 2048,
|
| 16 |
+
"d_kv": 64,
|
| 17 |
+
"dense_act_fn": "gelu_new",
|
| 18 |
+
"dropout_rate": 0.2,
|
| 19 |
+
"dtype": "float32",
|
| 20 |
+
"encoder_hidden_size": 768,
|
| 21 |
+
"hidden_size": 768,
|
| 22 |
+
"initializer_factor": 1.0,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"is_encoder_decoder": true,
|
| 25 |
+
"layer_norm_epsilon": 1e-06,
|
| 26 |
+
"model_type": "pix2struct_text_model",
|
| 27 |
+
"num_heads": 12,
|
| 28 |
+
"num_layers": 12,
|
| 29 |
+
"relative_attention_max_distance": 128,
|
| 30 |
+
"relative_attention_num_buckets": 32,
|
| 31 |
+
"use_cache": false,
|
| 32 |
+
"vocab_size": 50432
|
| 33 |
+
},
|
| 34 |
+
"tie_word_embeddings": false,
|
| 35 |
+
"transformers_version": "4.57.3",
|
| 36 |
+
"vision_config": {
|
| 37 |
+
"attention_dropout": 0.2,
|
| 38 |
+
"d_ff": 2048,
|
| 39 |
+
"d_kv": 64,
|
| 40 |
+
"dense_act_fn": "gelu_new",
|
| 41 |
+
"dropout_rate": 0.2,
|
| 42 |
+
"dtype": "float32",
|
| 43 |
+
"hidden_dropout_prob": 0.2,
|
| 44 |
+
"hidden_size": 768,
|
| 45 |
+
"initializer_factor": 1.0,
|
| 46 |
+
"initializer_range": 0.02,
|
| 47 |
+
"layer_norm_bias": false,
|
| 48 |
+
"layer_norm_eps": 1e-06,
|
| 49 |
+
"model_type": "pix2struct_vision_model",
|
| 50 |
+
"num_attention_heads": 12,
|
| 51 |
+
"num_channels": 3,
|
| 52 |
+
"num_hidden_layers": 12,
|
| 53 |
+
"patch_embed_hidden_size": 768,
|
| 54 |
+
"patch_size": 16,
|
| 55 |
+
"projection_dim": 768,
|
| 56 |
+
"relative_attention_max_distance": 128,
|
| 57 |
+
"relative_attention_num_buckets": 32,
|
| 58 |
+
"seq_len": 4096
|
| 59 |
+
}
|
| 60 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.57.3",
|
| 7 |
+
"use_cache": false
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a80a48495a25e33874ef76a68e6cdccd87b7f047a17917e96c57ee55ff656150
|
| 3 |
+
size 1130333048
|
runs/Dec29_20-07-00_2e8f3bb6a9b3/events.out.tfevents.1767038821.2e8f3bb6a9b3.786.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50130bc4d38339f476ef353b4c7ff694cc6d3569671190e6edcd718d0b2a4ab5
|
| 3 |
+
size 7274
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c04a7c67fc06fb7f2815d99d0efa90508f7562847a0a7dcee330805e346779bd
|
| 3 |
+
size 6033
|