Upload 17 files
Browse files- checkpoint-30000/config.json +184 -0
- checkpoint-30000/generation_config.json +13 -0
- checkpoint-30000/model.safetensors +3 -0
- checkpoint-30000/optimizer.pt +3 -0
- checkpoint-30000/rng_state.pth +3 -0
- checkpoint-30000/scheduler.pt +3 -0
- checkpoint-30000/trainer_state.json +0 -0
- checkpoint-30000/training_args.bin +3 -0
- model.safetensors +1 -1
checkpoint-30000/config.json
ADDED
|
@@ -0,0 +1,184 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "tirthadagr8/CustomOCR",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"VisionEncoderDecoderModel"
|
| 5 |
+
],
|
| 6 |
+
"decoder": {
|
| 7 |
+
"_attn_implementation_autoset": false,
|
| 8 |
+
"_name_or_path": "",
|
| 9 |
+
"activation_function": "gelu_new",
|
| 10 |
+
"add_cross_attention": true,
|
| 11 |
+
"architectures": null,
|
| 12 |
+
"attn_pdrop": 0.1,
|
| 13 |
+
"bad_words_ids": null,
|
| 14 |
+
"begin_suppress_tokens": null,
|
| 15 |
+
"bos_token_id": 12561,
|
| 16 |
+
"chunk_size_feed_forward": 0,
|
| 17 |
+
"cross_attention_hidden_size": null,
|
| 18 |
+
"decoder_start_token_id": null,
|
| 19 |
+
"diversity_penalty": 0.0,
|
| 20 |
+
"do_sample": false,
|
| 21 |
+
"early_stopping": false,
|
| 22 |
+
"embd_pdrop": 0.1,
|
| 23 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 24 |
+
"eos_token_id": 12562,
|
| 25 |
+
"exponential_decay_length_penalty": null,
|
| 26 |
+
"finetuning_task": null,
|
| 27 |
+
"forced_bos_token_id": null,
|
| 28 |
+
"forced_eos_token_id": null,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1"
|
| 32 |
+
},
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"is_decoder": true,
|
| 35 |
+
"is_encoder_decoder": false,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1
|
| 39 |
+
},
|
| 40 |
+
"layer_norm_epsilon": 1e-05,
|
| 41 |
+
"length_penalty": 1.0,
|
| 42 |
+
"max_length": 20,
|
| 43 |
+
"min_length": 0,
|
| 44 |
+
"model_type": "gpt2",
|
| 45 |
+
"n_embd": 768,
|
| 46 |
+
"n_head": 12,
|
| 47 |
+
"n_inner": 2048,
|
| 48 |
+
"n_layer": 12,
|
| 49 |
+
"n_positions": 512,
|
| 50 |
+
"no_repeat_ngram_size": 0,
|
| 51 |
+
"num_beam_groups": 1,
|
| 52 |
+
"num_beams": 1,
|
| 53 |
+
"num_return_sequences": 1,
|
| 54 |
+
"output_attentions": false,
|
| 55 |
+
"output_hidden_states": false,
|
| 56 |
+
"output_scores": false,
|
| 57 |
+
"pad_token_id": 12563,
|
| 58 |
+
"prefix": null,
|
| 59 |
+
"problem_type": null,
|
| 60 |
+
"pruned_heads": {},
|
| 61 |
+
"remove_invalid_values": false,
|
| 62 |
+
"reorder_and_upcast_attn": false,
|
| 63 |
+
"repetition_penalty": 1.0,
|
| 64 |
+
"resid_pdrop": 0.1,
|
| 65 |
+
"return_dict": true,
|
| 66 |
+
"return_dict_in_generate": false,
|
| 67 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 68 |
+
"scale_attn_weights": true,
|
| 69 |
+
"sep_token_id": null,
|
| 70 |
+
"summary_activation": null,
|
| 71 |
+
"summary_first_dropout": 0.1,
|
| 72 |
+
"summary_proj_to_labels": true,
|
| 73 |
+
"summary_type": "cls_index",
|
| 74 |
+
"summary_use_proj": true,
|
| 75 |
+
"suppress_tokens": null,
|
| 76 |
+
"task_specific_params": null,
|
| 77 |
+
"temperature": 1.0,
|
| 78 |
+
"tf_legacy_loss": false,
|
| 79 |
+
"tie_encoder_decoder": false,
|
| 80 |
+
"tie_word_embeddings": true,
|
| 81 |
+
"tokenizer_class": null,
|
| 82 |
+
"top_k": 50,
|
| 83 |
+
"top_p": 1.0,
|
| 84 |
+
"torch_dtype": null,
|
| 85 |
+
"torchscript": false,
|
| 86 |
+
"typical_p": 1.0,
|
| 87 |
+
"use_bfloat16": false,
|
| 88 |
+
"use_cache": false,
|
| 89 |
+
"vocab_size": 12564
|
| 90 |
+
},
|
| 91 |
+
"decoder_start_token_id": 12561,
|
| 92 |
+
"early_stopping": null,
|
| 93 |
+
"encoder": {
|
| 94 |
+
"_attn_implementation_autoset": false,
|
| 95 |
+
"_name_or_path": "",
|
| 96 |
+
"add_cross_attention": false,
|
| 97 |
+
"architectures": null,
|
| 98 |
+
"attention_probs_dropout_prob": 0.1,
|
| 99 |
+
"bad_words_ids": null,
|
| 100 |
+
"begin_suppress_tokens": null,
|
| 101 |
+
"bos_token_id": null,
|
| 102 |
+
"chunk_size_feed_forward": 0,
|
| 103 |
+
"cross_attention_hidden_size": null,
|
| 104 |
+
"decoder_start_token_id": null,
|
| 105 |
+
"diversity_penalty": 0.0,
|
| 106 |
+
"do_sample": false,
|
| 107 |
+
"early_stopping": false,
|
| 108 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 109 |
+
"encoder_stride": 16,
|
| 110 |
+
"eos_token_id": null,
|
| 111 |
+
"exponential_decay_length_penalty": null,
|
| 112 |
+
"finetuning_task": null,
|
| 113 |
+
"forced_bos_token_id": null,
|
| 114 |
+
"forced_eos_token_id": null,
|
| 115 |
+
"hidden_act": "gelu",
|
| 116 |
+
"hidden_dropout_prob": 0.1,
|
| 117 |
+
"hidden_size": 768,
|
| 118 |
+
"id2label": {
|
| 119 |
+
"0": "LABEL_0",
|
| 120 |
+
"1": "LABEL_1"
|
| 121 |
+
},
|
| 122 |
+
"image_size": 224,
|
| 123 |
+
"initializer_range": 0.02,
|
| 124 |
+
"intermediate_size": 3072,
|
| 125 |
+
"is_decoder": false,
|
| 126 |
+
"is_encoder_decoder": false,
|
| 127 |
+
"is_training": true,
|
| 128 |
+
"label2id": {
|
| 129 |
+
"LABEL_0": 0,
|
| 130 |
+
"LABEL_1": 1
|
| 131 |
+
},
|
| 132 |
+
"layer_norm_eps": 1e-06,
|
| 133 |
+
"length_penalty": 1.0,
|
| 134 |
+
"max_length": 20,
|
| 135 |
+
"min_length": 0,
|
| 136 |
+
"model_type": "vit",
|
| 137 |
+
"no_repeat_ngram_size": 0,
|
| 138 |
+
"num_attention_heads": 12,
|
| 139 |
+
"num_beam_groups": 1,
|
| 140 |
+
"num_beams": 1,
|
| 141 |
+
"num_channels": 3,
|
| 142 |
+
"num_hidden_layers": 12,
|
| 143 |
+
"num_return_sequences": 1,
|
| 144 |
+
"output_attentions": false,
|
| 145 |
+
"output_hidden_states": false,
|
| 146 |
+
"output_scores": false,
|
| 147 |
+
"pad_token_id": null,
|
| 148 |
+
"patch_attention": true,
|
| 149 |
+
"patch_size": 16,
|
| 150 |
+
"prefix": null,
|
| 151 |
+
"problem_type": null,
|
| 152 |
+
"pruned_heads": {},
|
| 153 |
+
"qkv_bias": true,
|
| 154 |
+
"remove_invalid_values": false,
|
| 155 |
+
"repetition_penalty": 1.0,
|
| 156 |
+
"return_dict": true,
|
| 157 |
+
"return_dict_in_generate": false,
|
| 158 |
+
"sep_token_id": null,
|
| 159 |
+
"suppress_tokens": null,
|
| 160 |
+
"task_specific_params": null,
|
| 161 |
+
"temperature": 1.0,
|
| 162 |
+
"tf_legacy_loss": false,
|
| 163 |
+
"tie_encoder_decoder": false,
|
| 164 |
+
"tie_word_embeddings": true,
|
| 165 |
+
"tokenizer_class": null,
|
| 166 |
+
"top_k": 50,
|
| 167 |
+
"top_p": 1.0,
|
| 168 |
+
"torch_dtype": null,
|
| 169 |
+
"torchscript": false,
|
| 170 |
+
"typical_p": 1.0,
|
| 171 |
+
"use_bfloat16": false
|
| 172 |
+
},
|
| 173 |
+
"eos_token_id": 12562,
|
| 174 |
+
"is_encoder_decoder": true,
|
| 175 |
+
"length_penalty": null,
|
| 176 |
+
"max_length": null,
|
| 177 |
+
"model_type": "vision-encoder-decoder",
|
| 178 |
+
"no_repeat_ngram_size": null,
|
| 179 |
+
"num_beams": null,
|
| 180 |
+
"pad_token_id": 12563,
|
| 181 |
+
"tie_word_embeddings": false,
|
| 182 |
+
"torch_dtype": "float32",
|
| 183 |
+
"transformers_version": "4.47.0"
|
| 184 |
+
}
|
checkpoint-30000/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 12561,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 12562,
|
| 6 |
+
"length_penalty": 2.0,
|
| 7 |
+
"max_length": 64,
|
| 8 |
+
"no_repeat_ngram_size": 3,
|
| 9 |
+
"num_beams": 5,
|
| 10 |
+
"pad_token_id": 12563,
|
| 11 |
+
"transformers_version": "4.47.0",
|
| 12 |
+
"use_cache": false
|
| 13 |
+
}
|
checkpoint-30000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:341d3e5f4db3422a1cd0a64b08c6a3928cf99d8a58d183e8181a0337b48ddbb3
|
| 3 |
+
size 763923128
|
checkpoint-30000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8108abdd65481fb1a298c5212a4c7696e76ef9d3995773d44f5fca2af0560a5
|
| 3 |
+
size 1523387840
|
checkpoint-30000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24fa26d9606661b38e384cbbc22746beeee83fe7ce98768b8a2f552a1ae4bf05
|
| 3 |
+
size 14244
|
checkpoint-30000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f07c4c6e516da31982016693a569d482d4382c9834e50a8c5bab185a3dd96bc3
|
| 3 |
+
size 1064
|
checkpoint-30000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-30000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbe6c752c38185156408a423c6d7800b92658b79c11d11cf1982155bdeb01bbb
|
| 3 |
+
size 5368
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 763923128
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:341d3e5f4db3422a1cd0a64b08c6a3928cf99d8a58d183e8181a0337b48ddbb3
|
| 3 |
size 763923128
|