Commit
•
7ed23c0
1
Parent(s):
8570a1d
Upload folder using huggingface_hub
Browse files- added_tokens.json +15 -0
- checkpoint-2679/config.json +192 -0
- checkpoint-2679/generation_config.json +8 -0
- checkpoint-2679/model.safetensors +3 -0
- checkpoint-2679/optimizer.pt +3 -0
- checkpoint-2679/rng_state.pth +3 -0
- checkpoint-2679/scheduler.pt +3 -0
- checkpoint-2679/trainer_state.json +203 -0
- checkpoint-2679/training_args.bin +3 -0
- checkpoint-2820/config.json +192 -0
- checkpoint-2820/generation_config.json +8 -0
- checkpoint-2820/model.safetensors +3 -0
- checkpoint-2820/optimizer.pt +3 -0
- checkpoint-2820/rng_state.pth +3 -0
- checkpoint-2820/scheduler.pt +3 -0
- checkpoint-2820/trainer_state.json +217 -0
- checkpoint-2820/training_args.bin +3 -0
- config.json +192 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +26 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +137 -0
- tokenizer.json +0 -0
- tokenizer_config.json +174 -0
- trainer_state.json +217 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s_invoice_date>": 57534,
|
| 3 |
+
"</s_invoice_num>": 57532,
|
| 4 |
+
"</s_tax>": 57530,
|
| 5 |
+
"</s_total_price>": 57528,
|
| 6 |
+
"</s_untaxed_price>": 57526,
|
| 7 |
+
"<s_iitcdip>": 57523,
|
| 8 |
+
"<s_invoice_date>": 57533,
|
| 9 |
+
"<s_invoice_num>": 57531,
|
| 10 |
+
"<s_synthdog>": 57524,
|
| 11 |
+
"<s_tax>": 57529,
|
| 12 |
+
"<s_total_price>": 57527,
|
| 13 |
+
"<s_untaxed_price>": 57525,
|
| 14 |
+
"<sep/>": 57522
|
| 15 |
+
}
|
checkpoint-2679/config.json
ADDED
|
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "naver-clova-ix/donut-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"VisionEncoderDecoderModel"
|
| 5 |
+
],
|
| 6 |
+
"decoder": {
|
| 7 |
+
"_name_or_path": "",
|
| 8 |
+
"activation_dropout": 0.0,
|
| 9 |
+
"activation_function": "gelu",
|
| 10 |
+
"add_cross_attention": true,
|
| 11 |
+
"add_final_layer_norm": true,
|
| 12 |
+
"architectures": null,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"bad_words_ids": null,
|
| 15 |
+
"begin_suppress_tokens": null,
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"chunk_size_feed_forward": 0,
|
| 18 |
+
"classifier_dropout": 0.0,
|
| 19 |
+
"cross_attention_hidden_size": null,
|
| 20 |
+
"d_model": 1024,
|
| 21 |
+
"decoder_attention_heads": 16,
|
| 22 |
+
"decoder_ffn_dim": 4096,
|
| 23 |
+
"decoder_layerdrop": 0.0,
|
| 24 |
+
"decoder_layers": 4,
|
| 25 |
+
"decoder_start_token_id": null,
|
| 26 |
+
"diversity_penalty": 0.0,
|
| 27 |
+
"do_sample": false,
|
| 28 |
+
"dropout": 0.1,
|
| 29 |
+
"early_stopping": false,
|
| 30 |
+
"encoder_attention_heads": 16,
|
| 31 |
+
"encoder_ffn_dim": 4096,
|
| 32 |
+
"encoder_layerdrop": 0.0,
|
| 33 |
+
"encoder_layers": 12,
|
| 34 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 35 |
+
"eos_token_id": 2,
|
| 36 |
+
"exponential_decay_length_penalty": null,
|
| 37 |
+
"finetuning_task": null,
|
| 38 |
+
"forced_bos_token_id": null,
|
| 39 |
+
"forced_eos_token_id": 2,
|
| 40 |
+
"id2label": {
|
| 41 |
+
"0": "LABEL_0",
|
| 42 |
+
"1": "LABEL_1"
|
| 43 |
+
},
|
| 44 |
+
"init_std": 0.02,
|
| 45 |
+
"is_decoder": true,
|
| 46 |
+
"is_encoder_decoder": false,
|
| 47 |
+
"label2id": {
|
| 48 |
+
"LABEL_0": 0,
|
| 49 |
+
"LABEL_1": 1
|
| 50 |
+
},
|
| 51 |
+
"length_penalty": 1.0,
|
| 52 |
+
"max_length": 512,
|
| 53 |
+
"max_position_embeddings": 1536,
|
| 54 |
+
"min_length": 0,
|
| 55 |
+
"model_type": "mbart",
|
| 56 |
+
"no_repeat_ngram_size": 0,
|
| 57 |
+
"num_beam_groups": 1,
|
| 58 |
+
"num_beams": 1,
|
| 59 |
+
"num_hidden_layers": 12,
|
| 60 |
+
"num_return_sequences": 1,
|
| 61 |
+
"output_attentions": false,
|
| 62 |
+
"output_hidden_states": false,
|
| 63 |
+
"output_scores": false,
|
| 64 |
+
"pad_token_id": 1,
|
| 65 |
+
"prefix": null,
|
| 66 |
+
"problem_type": null,
|
| 67 |
+
"pruned_heads": {},
|
| 68 |
+
"remove_invalid_values": false,
|
| 69 |
+
"repetition_penalty": 1.0,
|
| 70 |
+
"return_dict": true,
|
| 71 |
+
"return_dict_in_generate": false,
|
| 72 |
+
"scale_embedding": true,
|
| 73 |
+
"sep_token_id": null,
|
| 74 |
+
"suppress_tokens": null,
|
| 75 |
+
"task_specific_params": null,
|
| 76 |
+
"temperature": 1.0,
|
| 77 |
+
"tf_legacy_loss": false,
|
| 78 |
+
"tie_encoder_decoder": false,
|
| 79 |
+
"tie_word_embeddings": true,
|
| 80 |
+
"tokenizer_class": null,
|
| 81 |
+
"top_k": 50,
|
| 82 |
+
"top_p": 1.0,
|
| 83 |
+
"torch_dtype": null,
|
| 84 |
+
"torchscript": false,
|
| 85 |
+
"typical_p": 1.0,
|
| 86 |
+
"use_bfloat16": false,
|
| 87 |
+
"use_cache": true,
|
| 88 |
+
"vocab_size": 57535
|
| 89 |
+
},
|
| 90 |
+
"decoder_start_token_id": 0,
|
| 91 |
+
"encoder": {
|
| 92 |
+
"_name_or_path": "",
|
| 93 |
+
"add_cross_attention": false,
|
| 94 |
+
"architectures": null,
|
| 95 |
+
"attention_probs_dropout_prob": 0.0,
|
| 96 |
+
"bad_words_ids": null,
|
| 97 |
+
"begin_suppress_tokens": null,
|
| 98 |
+
"bos_token_id": null,
|
| 99 |
+
"chunk_size_feed_forward": 0,
|
| 100 |
+
"cross_attention_hidden_size": null,
|
| 101 |
+
"decoder_start_token_id": null,
|
| 102 |
+
"depths": [
|
| 103 |
+
2,
|
| 104 |
+
2,
|
| 105 |
+
14,
|
| 106 |
+
2
|
| 107 |
+
],
|
| 108 |
+
"diversity_penalty": 0.0,
|
| 109 |
+
"do_sample": false,
|
| 110 |
+
"drop_path_rate": 0.1,
|
| 111 |
+
"early_stopping": false,
|
| 112 |
+
"embed_dim": 128,
|
| 113 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 114 |
+
"eos_token_id": null,
|
| 115 |
+
"exponential_decay_length_penalty": null,
|
| 116 |
+
"finetuning_task": null,
|
| 117 |
+
"forced_bos_token_id": null,
|
| 118 |
+
"forced_eos_token_id": null,
|
| 119 |
+
"hidden_act": "gelu",
|
| 120 |
+
"hidden_dropout_prob": 0.0,
|
| 121 |
+
"hidden_size": 1024,
|
| 122 |
+
"id2label": {
|
| 123 |
+
"0": "LABEL_0",
|
| 124 |
+
"1": "LABEL_1"
|
| 125 |
+
},
|
| 126 |
+
"image_size": [
|
| 127 |
+
550,
|
| 128 |
+
960
|
| 129 |
+
],
|
| 130 |
+
"initializer_range": 0.02,
|
| 131 |
+
"is_decoder": false,
|
| 132 |
+
"is_encoder_decoder": false,
|
| 133 |
+
"label2id": {
|
| 134 |
+
"LABEL_0": 0,
|
| 135 |
+
"LABEL_1": 1
|
| 136 |
+
},
|
| 137 |
+
"layer_norm_eps": 1e-05,
|
| 138 |
+
"length_penalty": 1.0,
|
| 139 |
+
"max_length": 20,
|
| 140 |
+
"min_length": 0,
|
| 141 |
+
"mlp_ratio": 4.0,
|
| 142 |
+
"model_type": "donut-swin",
|
| 143 |
+
"no_repeat_ngram_size": 0,
|
| 144 |
+
"num_beam_groups": 1,
|
| 145 |
+
"num_beams": 1,
|
| 146 |
+
"num_channels": 3,
|
| 147 |
+
"num_heads": [
|
| 148 |
+
4,
|
| 149 |
+
8,
|
| 150 |
+
16,
|
| 151 |
+
32
|
| 152 |
+
],
|
| 153 |
+
"num_layers": 4,
|
| 154 |
+
"num_return_sequences": 1,
|
| 155 |
+
"output_attentions": false,
|
| 156 |
+
"output_hidden_states": false,
|
| 157 |
+
"output_scores": false,
|
| 158 |
+
"pad_token_id": null,
|
| 159 |
+
"patch_size": 4,
|
| 160 |
+
"path_norm": true,
|
| 161 |
+
"prefix": null,
|
| 162 |
+
"problem_type": null,
|
| 163 |
+
"pruned_heads": {},
|
| 164 |
+
"qkv_bias": true,
|
| 165 |
+
"remove_invalid_values": false,
|
| 166 |
+
"repetition_penalty": 1.0,
|
| 167 |
+
"return_dict": true,
|
| 168 |
+
"return_dict_in_generate": false,
|
| 169 |
+
"sep_token_id": null,
|
| 170 |
+
"suppress_tokens": null,
|
| 171 |
+
"task_specific_params": null,
|
| 172 |
+
"temperature": 1.0,
|
| 173 |
+
"tf_legacy_loss": false,
|
| 174 |
+
"tie_encoder_decoder": false,
|
| 175 |
+
"tie_word_embeddings": true,
|
| 176 |
+
"tokenizer_class": null,
|
| 177 |
+
"top_k": 50,
|
| 178 |
+
"top_p": 1.0,
|
| 179 |
+
"torch_dtype": null,
|
| 180 |
+
"torchscript": false,
|
| 181 |
+
"typical_p": 1.0,
|
| 182 |
+
"use_absolute_embeddings": false,
|
| 183 |
+
"use_bfloat16": false,
|
| 184 |
+
"window_size": 10
|
| 185 |
+
},
|
| 186 |
+
"is_encoder_decoder": true,
|
| 187 |
+
"model_type": "vision-encoder-decoder",
|
| 188 |
+
"pad_token_id": 1,
|
| 189 |
+
"tie_word_embeddings": false,
|
| 190 |
+
"torch_dtype": "float32",
|
| 191 |
+
"transformers_version": "4.38.2"
|
| 192 |
+
}
|
checkpoint-2679/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"forced_eos_token_id": 2,
|
| 6 |
+
"pad_token_id": 1,
|
| 7 |
+
"transformers_version": "4.38.2"
|
| 8 |
+
}
|
checkpoint-2679/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0f7b7ea34f82c23ef845898690a240ad211c36710071fbf9b3f8a1d7a5a7dbc
|
| 3 |
+
size 809111704
|
checkpoint-2679/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75b31f3982fe4f70b72d137648542e34c7156abf66b73e1e02927abcc1ae9e2c
|
| 3 |
+
size 1615285631
|
checkpoint-2679/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36b971ceb71d8f63e88169c2c3920ffb19687d23468d666d2d761851cb40672d
|
| 3 |
+
size 14244
|
checkpoint-2679/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:462a9272587176079547d41ee691bf8190c3c10bee147183419fd9b480dd8f42
|
| 3 |
+
size 1064
|
checkpoint-2679/trainer_state.json
ADDED
|
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2679,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.71,
|
| 13 |
+
"grad_norm": 42.0918083190918,
|
| 14 |
+
"learning_rate": 1.929078014184397e-06,
|
| 15 |
+
"loss": 10.0975,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.42,
|
| 20 |
+
"grad_norm": 54.439884185791016,
|
| 21 |
+
"learning_rate": 1.8581560283687943e-06,
|
| 22 |
+
"loss": 5.8147,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.13,
|
| 27 |
+
"grad_norm": 60.155399322509766,
|
| 28 |
+
"learning_rate": 1.7872340425531913e-06,
|
| 29 |
+
"loss": 4.1279,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.84,
|
| 34 |
+
"grad_norm": 49.89198684692383,
|
| 35 |
+
"learning_rate": 1.7163120567375885e-06,
|
| 36 |
+
"loss": 2.8192,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 3.55,
|
| 41 |
+
"grad_norm": 24.662052154541016,
|
| 42 |
+
"learning_rate": 1.6453900709219858e-06,
|
| 43 |
+
"loss": 2.3071,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.26,
|
| 48 |
+
"grad_norm": 46.319374084472656,
|
| 49 |
+
"learning_rate": 1.574468085106383e-06,
|
| 50 |
+
"loss": 1.788,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.96,
|
| 55 |
+
"grad_norm": 19.011852264404297,
|
| 56 |
+
"learning_rate": 1.50354609929078e-06,
|
| 57 |
+
"loss": 1.6626,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 5.67,
|
| 62 |
+
"grad_norm": 24.53301239013672,
|
| 63 |
+
"learning_rate": 1.4326241134751774e-06,
|
| 64 |
+
"loss": 1.5502,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 6.38,
|
| 69 |
+
"grad_norm": 29.92524528503418,
|
| 70 |
+
"learning_rate": 1.3617021276595744e-06,
|
| 71 |
+
"loss": 1.4522,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 7.09,
|
| 76 |
+
"grad_norm": 49.022037506103516,
|
| 77 |
+
"learning_rate": 1.2907801418439716e-06,
|
| 78 |
+
"loss": 1.3627,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 7.8,
|
| 83 |
+
"grad_norm": 15.343302726745605,
|
| 84 |
+
"learning_rate": 1.2198581560283688e-06,
|
| 85 |
+
"loss": 1.2928,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 8.51,
|
| 90 |
+
"grad_norm": 20.46482276916504,
|
| 91 |
+
"learning_rate": 1.148936170212766e-06,
|
| 92 |
+
"loss": 1.2246,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 9.22,
|
| 97 |
+
"grad_norm": 26.57284927368164,
|
| 98 |
+
"learning_rate": 1.078014184397163e-06,
|
| 99 |
+
"loss": 1.153,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 9.93,
|
| 104 |
+
"grad_norm": 15.145112991333008,
|
| 105 |
+
"learning_rate": 1.00709219858156e-06,
|
| 106 |
+
"loss": 1.1536,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 10.64,
|
| 111 |
+
"grad_norm": 19.93513298034668,
|
| 112 |
+
"learning_rate": 9.361702127659575e-07,
|
| 113 |
+
"loss": 1.0598,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 11.35,
|
| 118 |
+
"grad_norm": 27.3331298828125,
|
| 119 |
+
"learning_rate": 8.652482269503546e-07,
|
| 120 |
+
"loss": 1.047,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 12.06,
|
| 125 |
+
"grad_norm": 43.462093353271484,
|
| 126 |
+
"learning_rate": 7.943262411347518e-07,
|
| 127 |
+
"loss": 1.0587,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 12.77,
|
| 132 |
+
"grad_norm": 36.50919723510742,
|
| 133 |
+
"learning_rate": 7.23404255319149e-07,
|
| 134 |
+
"loss": 1.0709,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 13.48,
|
| 139 |
+
"grad_norm": 19.904586791992188,
|
| 140 |
+
"learning_rate": 6.524822695035461e-07,
|
| 141 |
+
"loss": 0.972,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 14.18,
|
| 146 |
+
"grad_norm": 19.49388313293457,
|
| 147 |
+
"learning_rate": 5.815602836879432e-07,
|
| 148 |
+
"loss": 1.0102,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 14.89,
|
| 153 |
+
"grad_norm": 16.17923927307129,
|
| 154 |
+
"learning_rate": 5.106382978723403e-07,
|
| 155 |
+
"loss": 0.9229,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 15.6,
|
| 160 |
+
"grad_norm": 20.12999153137207,
|
| 161 |
+
"learning_rate": 4.397163120567376e-07,
|
| 162 |
+
"loss": 0.9488,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 16.31,
|
| 167 |
+
"grad_norm": 26.802228927612305,
|
| 168 |
+
"learning_rate": 3.687943262411347e-07,
|
| 169 |
+
"loss": 0.9173,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 17.02,
|
| 174 |
+
"grad_norm": 30.8055419921875,
|
| 175 |
+
"learning_rate": 2.978723404255319e-07,
|
| 176 |
+
"loss": 0.9306,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 17.73,
|
| 181 |
+
"grad_norm": 15.404391288757324,
|
| 182 |
+
"learning_rate": 2.2695035460992907e-07,
|
| 183 |
+
"loss": 0.898,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 18.44,
|
| 188 |
+
"grad_norm": 11.279256820678711,
|
| 189 |
+
"learning_rate": 1.5602836879432623e-07,
|
| 190 |
+
"loss": 0.9177,
|
| 191 |
+
"step": 2600
|
| 192 |
+
}
|
| 193 |
+
],
|
| 194 |
+
"logging_steps": 100,
|
| 195 |
+
"max_steps": 2820,
|
| 196 |
+
"num_input_tokens_seen": 0,
|
| 197 |
+
"num_train_epochs": 20,
|
| 198 |
+
"save_steps": 500,
|
| 199 |
+
"total_flos": 7.173452904406272e+18,
|
| 200 |
+
"train_batch_size": 2,
|
| 201 |
+
"trial_name": null,
|
| 202 |
+
"trial_params": null
|
| 203 |
+
}
|
checkpoint-2679/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08f398330d641864000e86a0d95e15e57481b8d831a40d683c790c0a3adcd7d1
|
| 3 |
+
size 5048
|
checkpoint-2820/config.json
ADDED
|
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "naver-clova-ix/donut-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"VisionEncoderDecoderModel"
|
| 5 |
+
],
|
| 6 |
+
"decoder": {
|
| 7 |
+
"_name_or_path": "",
|
| 8 |
+
"activation_dropout": 0.0,
|
| 9 |
+
"activation_function": "gelu",
|
| 10 |
+
"add_cross_attention": true,
|
| 11 |
+
"add_final_layer_norm": true,
|
| 12 |
+
"architectures": null,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"bad_words_ids": null,
|
| 15 |
+
"begin_suppress_tokens": null,
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"chunk_size_feed_forward": 0,
|
| 18 |
+
"classifier_dropout": 0.0,
|
| 19 |
+
"cross_attention_hidden_size": null,
|
| 20 |
+
"d_model": 1024,
|
| 21 |
+
"decoder_attention_heads": 16,
|
| 22 |
+
"decoder_ffn_dim": 4096,
|
| 23 |
+
"decoder_layerdrop": 0.0,
|
| 24 |
+
"decoder_layers": 4,
|
| 25 |
+
"decoder_start_token_id": null,
|
| 26 |
+
"diversity_penalty": 0.0,
|
| 27 |
+
"do_sample": false,
|
| 28 |
+
"dropout": 0.1,
|
| 29 |
+
"early_stopping": false,
|
| 30 |
+
"encoder_attention_heads": 16,
|
| 31 |
+
"encoder_ffn_dim": 4096,
|
| 32 |
+
"encoder_layerdrop": 0.0,
|
| 33 |
+
"encoder_layers": 12,
|
| 34 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 35 |
+
"eos_token_id": 2,
|
| 36 |
+
"exponential_decay_length_penalty": null,
|
| 37 |
+
"finetuning_task": null,
|
| 38 |
+
"forced_bos_token_id": null,
|
| 39 |
+
"forced_eos_token_id": 2,
|
| 40 |
+
"id2label": {
|
| 41 |
+
"0": "LABEL_0",
|
| 42 |
+
"1": "LABEL_1"
|
| 43 |
+
},
|
| 44 |
+
"init_std": 0.02,
|
| 45 |
+
"is_decoder": true,
|
| 46 |
+
"is_encoder_decoder": false,
|
| 47 |
+
"label2id": {
|
| 48 |
+
"LABEL_0": 0,
|
| 49 |
+
"LABEL_1": 1
|
| 50 |
+
},
|
| 51 |
+
"length_penalty": 1.0,
|
| 52 |
+
"max_length": 512,
|
| 53 |
+
"max_position_embeddings": 1536,
|
| 54 |
+
"min_length": 0,
|
| 55 |
+
"model_type": "mbart",
|
| 56 |
+
"no_repeat_ngram_size": 0,
|
| 57 |
+
"num_beam_groups": 1,
|
| 58 |
+
"num_beams": 1,
|
| 59 |
+
"num_hidden_layers": 12,
|
| 60 |
+
"num_return_sequences": 1,
|
| 61 |
+
"output_attentions": false,
|
| 62 |
+
"output_hidden_states": false,
|
| 63 |
+
"output_scores": false,
|
| 64 |
+
"pad_token_id": 1,
|
| 65 |
+
"prefix": null,
|
| 66 |
+
"problem_type": null,
|
| 67 |
+
"pruned_heads": {},
|
| 68 |
+
"remove_invalid_values": false,
|
| 69 |
+
"repetition_penalty": 1.0,
|
| 70 |
+
"return_dict": true,
|
| 71 |
+
"return_dict_in_generate": false,
|
| 72 |
+
"scale_embedding": true,
|
| 73 |
+
"sep_token_id": null,
|
| 74 |
+
"suppress_tokens": null,
|
| 75 |
+
"task_specific_params": null,
|
| 76 |
+
"temperature": 1.0,
|
| 77 |
+
"tf_legacy_loss": false,
|
| 78 |
+
"tie_encoder_decoder": false,
|
| 79 |
+
"tie_word_embeddings": true,
|
| 80 |
+
"tokenizer_class": null,
|
| 81 |
+
"top_k": 50,
|
| 82 |
+
"top_p": 1.0,
|
| 83 |
+
"torch_dtype": null,
|
| 84 |
+
"torchscript": false,
|
| 85 |
+
"typical_p": 1.0,
|
| 86 |
+
"use_bfloat16": false,
|
| 87 |
+
"use_cache": true,
|
| 88 |
+
"vocab_size": 57535
|
| 89 |
+
},
|
| 90 |
+
"decoder_start_token_id": 0,
|
| 91 |
+
"encoder": {
|
| 92 |
+
"_name_or_path": "",
|
| 93 |
+
"add_cross_attention": false,
|
| 94 |
+
"architectures": null,
|
| 95 |
+
"attention_probs_dropout_prob": 0.0,
|
| 96 |
+
"bad_words_ids": null,
|
| 97 |
+
"begin_suppress_tokens": null,
|
| 98 |
+
"bos_token_id": null,
|
| 99 |
+
"chunk_size_feed_forward": 0,
|
| 100 |
+
"cross_attention_hidden_size": null,
|
| 101 |
+
"decoder_start_token_id": null,
|
| 102 |
+
"depths": [
|
| 103 |
+
2,
|
| 104 |
+
2,
|
| 105 |
+
14,
|
| 106 |
+
2
|
| 107 |
+
],
|
| 108 |
+
"diversity_penalty": 0.0,
|
| 109 |
+
"do_sample": false,
|
| 110 |
+
"drop_path_rate": 0.1,
|
| 111 |
+
"early_stopping": false,
|
| 112 |
+
"embed_dim": 128,
|
| 113 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 114 |
+
"eos_token_id": null,
|
| 115 |
+
"exponential_decay_length_penalty": null,
|
| 116 |
+
"finetuning_task": null,
|
| 117 |
+
"forced_bos_token_id": null,
|
| 118 |
+
"forced_eos_token_id": null,
|
| 119 |
+
"hidden_act": "gelu",
|
| 120 |
+
"hidden_dropout_prob": 0.0,
|
| 121 |
+
"hidden_size": 1024,
|
| 122 |
+
"id2label": {
|
| 123 |
+
"0": "LABEL_0",
|
| 124 |
+
"1": "LABEL_1"
|
| 125 |
+
},
|
| 126 |
+
"image_size": [
|
| 127 |
+
550,
|
| 128 |
+
960
|
| 129 |
+
],
|
| 130 |
+
"initializer_range": 0.02,
|
| 131 |
+
"is_decoder": false,
|
| 132 |
+
"is_encoder_decoder": false,
|
| 133 |
+
"label2id": {
|
| 134 |
+
"LABEL_0": 0,
|
| 135 |
+
"LABEL_1": 1
|
| 136 |
+
},
|
| 137 |
+
"layer_norm_eps": 1e-05,
|
| 138 |
+
"length_penalty": 1.0,
|
| 139 |
+
"max_length": 20,
|
| 140 |
+
"min_length": 0,
|
| 141 |
+
"mlp_ratio": 4.0,
|
| 142 |
+
"model_type": "donut-swin",
|
| 143 |
+
"no_repeat_ngram_size": 0,
|
| 144 |
+
"num_beam_groups": 1,
|
| 145 |
+
"num_beams": 1,
|
| 146 |
+
"num_channels": 3,
|
| 147 |
+
"num_heads": [
|
| 148 |
+
4,
|
| 149 |
+
8,
|
| 150 |
+
16,
|
| 151 |
+
32
|
| 152 |
+
],
|
| 153 |
+
"num_layers": 4,
|
| 154 |
+
"num_return_sequences": 1,
|
| 155 |
+
"output_attentions": false,
|
| 156 |
+
"output_hidden_states": false,
|
| 157 |
+
"output_scores": false,
|
| 158 |
+
"pad_token_id": null,
|
| 159 |
+
"patch_size": 4,
|
| 160 |
+
"path_norm": true,
|
| 161 |
+
"prefix": null,
|
| 162 |
+
"problem_type": null,
|
| 163 |
+
"pruned_heads": {},
|
| 164 |
+
"qkv_bias": true,
|
| 165 |
+
"remove_invalid_values": false,
|
| 166 |
+
"repetition_penalty": 1.0,
|
| 167 |
+
"return_dict": true,
|
| 168 |
+
"return_dict_in_generate": false,
|
| 169 |
+
"sep_token_id": null,
|
| 170 |
+
"suppress_tokens": null,
|
| 171 |
+
"task_specific_params": null,
|
| 172 |
+
"temperature": 1.0,
|
| 173 |
+
"tf_legacy_loss": false,
|
| 174 |
+
"tie_encoder_decoder": false,
|
| 175 |
+
"tie_word_embeddings": true,
|
| 176 |
+
"tokenizer_class": null,
|
| 177 |
+
"top_k": 50,
|
| 178 |
+
"top_p": 1.0,
|
| 179 |
+
"torch_dtype": null,
|
| 180 |
+
"torchscript": false,
|
| 181 |
+
"typical_p": 1.0,
|
| 182 |
+
"use_absolute_embeddings": false,
|
| 183 |
+
"use_bfloat16": false,
|
| 184 |
+
"window_size": 10
|
| 185 |
+
},
|
| 186 |
+
"is_encoder_decoder": true,
|
| 187 |
+
"model_type": "vision-encoder-decoder",
|
| 188 |
+
"pad_token_id": 1,
|
| 189 |
+
"tie_word_embeddings": false,
|
| 190 |
+
"torch_dtype": "float32",
|
| 191 |
+
"transformers_version": "4.38.2"
|
| 192 |
+
}
|
checkpoint-2820/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"forced_eos_token_id": 2,
|
| 6 |
+
"pad_token_id": 1,
|
| 7 |
+
"transformers_version": "4.38.2"
|
| 8 |
+
}
|
checkpoint-2820/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4bc5fee2fcb2023bd9a33d708bf5f0b087950254a3ec1f8771e4804d18b089c
|
| 3 |
+
size 809111704
|
checkpoint-2820/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59bc7dbf73e8a8675eb73e04ea3706ffaaa61cf8c28dbc354a3c7593f04a95c6
|
| 3 |
+
size 1615285631
|
checkpoint-2820/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a449d045338a8380f32ee2c2c1e59988f272eba53067874fb88278de36c58fbd
|
| 3 |
+
size 14244
|
checkpoint-2820/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41d2b331930c8e09578a23a086b436a0ab0e343daf44f3b6ece96a8fbf0ade03
|
| 3 |
+
size 1064
|
checkpoint-2820/trainer_state.json
ADDED
|
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2820,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.71,
|
| 13 |
+
"grad_norm": 42.0918083190918,
|
| 14 |
+
"learning_rate": 1.929078014184397e-06,
|
| 15 |
+
"loss": 10.0975,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.42,
|
| 20 |
+
"grad_norm": 54.439884185791016,
|
| 21 |
+
"learning_rate": 1.8581560283687943e-06,
|
| 22 |
+
"loss": 5.8147,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.13,
|
| 27 |
+
"grad_norm": 60.155399322509766,
|
| 28 |
+
"learning_rate": 1.7872340425531913e-06,
|
| 29 |
+
"loss": 4.1279,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.84,
|
| 34 |
+
"grad_norm": 49.89198684692383,
|
| 35 |
+
"learning_rate": 1.7163120567375885e-06,
|
| 36 |
+
"loss": 2.8192,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 3.55,
|
| 41 |
+
"grad_norm": 24.662052154541016,
|
| 42 |
+
"learning_rate": 1.6453900709219858e-06,
|
| 43 |
+
"loss": 2.3071,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.26,
|
| 48 |
+
"grad_norm": 46.319374084472656,
|
| 49 |
+
"learning_rate": 1.574468085106383e-06,
|
| 50 |
+
"loss": 1.788,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.96,
|
| 55 |
+
"grad_norm": 19.011852264404297,
|
| 56 |
+
"learning_rate": 1.50354609929078e-06,
|
| 57 |
+
"loss": 1.6626,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 5.67,
|
| 62 |
+
"grad_norm": 24.53301239013672,
|
| 63 |
+
"learning_rate": 1.4326241134751774e-06,
|
| 64 |
+
"loss": 1.5502,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 6.38,
|
| 69 |
+
"grad_norm": 29.92524528503418,
|
| 70 |
+
"learning_rate": 1.3617021276595744e-06,
|
| 71 |
+
"loss": 1.4522,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 7.09,
|
| 76 |
+
"grad_norm": 49.022037506103516,
|
| 77 |
+
"learning_rate": 1.2907801418439716e-06,
|
| 78 |
+
"loss": 1.3627,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 7.8,
|
| 83 |
+
"grad_norm": 15.343302726745605,
|
| 84 |
+
"learning_rate": 1.2198581560283688e-06,
|
| 85 |
+
"loss": 1.2928,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 8.51,
|
| 90 |
+
"grad_norm": 20.46482276916504,
|
| 91 |
+
"learning_rate": 1.148936170212766e-06,
|
| 92 |
+
"loss": 1.2246,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 9.22,
|
| 97 |
+
"grad_norm": 26.57284927368164,
|
| 98 |
+
"learning_rate": 1.078014184397163e-06,
|
| 99 |
+
"loss": 1.153,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 9.93,
|
| 104 |
+
"grad_norm": 15.145112991333008,
|
| 105 |
+
"learning_rate": 1.00709219858156e-06,
|
| 106 |
+
"loss": 1.1536,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 10.64,
|
| 111 |
+
"grad_norm": 19.93513298034668,
|
| 112 |
+
"learning_rate": 9.361702127659575e-07,
|
| 113 |
+
"loss": 1.0598,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 11.35,
|
| 118 |
+
"grad_norm": 27.3331298828125,
|
| 119 |
+
"learning_rate": 8.652482269503546e-07,
|
| 120 |
+
"loss": 1.047,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 12.06,
|
| 125 |
+
"grad_norm": 43.462093353271484,
|
| 126 |
+
"learning_rate": 7.943262411347518e-07,
|
| 127 |
+
"loss": 1.0587,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 12.77,
|
| 132 |
+
"grad_norm": 36.50919723510742,
|
| 133 |
+
"learning_rate": 7.23404255319149e-07,
|
| 134 |
+
"loss": 1.0709,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 13.48,
|
| 139 |
+
"grad_norm": 19.904586791992188,
|
| 140 |
+
"learning_rate": 6.524822695035461e-07,
|
| 141 |
+
"loss": 0.972,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 14.18,
|
| 146 |
+
"grad_norm": 19.49388313293457,
|
| 147 |
+
"learning_rate": 5.815602836879432e-07,
|
| 148 |
+
"loss": 1.0102,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 14.89,
|
| 153 |
+
"grad_norm": 16.17923927307129,
|
| 154 |
+
"learning_rate": 5.106382978723403e-07,
|
| 155 |
+
"loss": 0.9229,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 15.6,
|
| 160 |
+
"grad_norm": 20.12999153137207,
|
| 161 |
+
"learning_rate": 4.397163120567376e-07,
|
| 162 |
+
"loss": 0.9488,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 16.31,
|
| 167 |
+
"grad_norm": 26.802228927612305,
|
| 168 |
+
"learning_rate": 3.687943262411347e-07,
|
| 169 |
+
"loss": 0.9173,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 17.02,
|
| 174 |
+
"grad_norm": 30.8055419921875,
|
| 175 |
+
"learning_rate": 2.978723404255319e-07,
|
| 176 |
+
"loss": 0.9306,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 17.73,
|
| 181 |
+
"grad_norm": 15.404391288757324,
|
| 182 |
+
"learning_rate": 2.2695035460992907e-07,
|
| 183 |
+
"loss": 0.898,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 18.44,
|
| 188 |
+
"grad_norm": 11.279256820678711,
|
| 189 |
+
"learning_rate": 1.5602836879432623e-07,
|
| 190 |
+
"loss": 0.9177,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 19.15,
|
| 195 |
+
"grad_norm": 20.938844680786133,
|
| 196 |
+
"learning_rate": 8.51063829787234e-08,
|
| 197 |
+
"loss": 0.8923,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 19.86,
|
| 202 |
+
"grad_norm": 48.48252868652344,
|
| 203 |
+
"learning_rate": 1.4184397163120567e-08,
|
| 204 |
+
"loss": 0.9238,
|
| 205 |
+
"step": 2800
|
| 206 |
+
}
|
| 207 |
+
],
|
| 208 |
+
"logging_steps": 100,
|
| 209 |
+
"max_steps": 2820,
|
| 210 |
+
"num_input_tokens_seen": 0,
|
| 211 |
+
"num_train_epochs": 20,
|
| 212 |
+
"save_steps": 500,
|
| 213 |
+
"total_flos": 7.55100305726976e+18,
|
| 214 |
+
"train_batch_size": 2,
|
| 215 |
+
"trial_name": null,
|
| 216 |
+
"trial_params": null
|
| 217 |
+
}
|
checkpoint-2820/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08f398330d641864000e86a0d95e15e57481b8d831a40d683c790c0a3adcd7d1
|
| 3 |
+
size 5048
|
config.json
ADDED
|
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "naver-clova-ix/donut-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"VisionEncoderDecoderModel"
|
| 5 |
+
],
|
| 6 |
+
"decoder": {
|
| 7 |
+
"_name_or_path": "",
|
| 8 |
+
"activation_dropout": 0.0,
|
| 9 |
+
"activation_function": "gelu",
|
| 10 |
+
"add_cross_attention": true,
|
| 11 |
+
"add_final_layer_norm": true,
|
| 12 |
+
"architectures": null,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"bad_words_ids": null,
|
| 15 |
+
"begin_suppress_tokens": null,
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"chunk_size_feed_forward": 0,
|
| 18 |
+
"classifier_dropout": 0.0,
|
| 19 |
+
"cross_attention_hidden_size": null,
|
| 20 |
+
"d_model": 1024,
|
| 21 |
+
"decoder_attention_heads": 16,
|
| 22 |
+
"decoder_ffn_dim": 4096,
|
| 23 |
+
"decoder_layerdrop": 0.0,
|
| 24 |
+
"decoder_layers": 4,
|
| 25 |
+
"decoder_start_token_id": null,
|
| 26 |
+
"diversity_penalty": 0.0,
|
| 27 |
+
"do_sample": false,
|
| 28 |
+
"dropout": 0.1,
|
| 29 |
+
"early_stopping": false,
|
| 30 |
+
"encoder_attention_heads": 16,
|
| 31 |
+
"encoder_ffn_dim": 4096,
|
| 32 |
+
"encoder_layerdrop": 0.0,
|
| 33 |
+
"encoder_layers": 12,
|
| 34 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 35 |
+
"eos_token_id": 2,
|
| 36 |
+
"exponential_decay_length_penalty": null,
|
| 37 |
+
"finetuning_task": null,
|
| 38 |
+
"forced_bos_token_id": null,
|
| 39 |
+
"forced_eos_token_id": 2,
|
| 40 |
+
"id2label": {
|
| 41 |
+
"0": "LABEL_0",
|
| 42 |
+
"1": "LABEL_1"
|
| 43 |
+
},
|
| 44 |
+
"init_std": 0.02,
|
| 45 |
+
"is_decoder": true,
|
| 46 |
+
"is_encoder_decoder": false,
|
| 47 |
+
"label2id": {
|
| 48 |
+
"LABEL_0": 0,
|
| 49 |
+
"LABEL_1": 1
|
| 50 |
+
},
|
| 51 |
+
"length_penalty": 1.0,
|
| 52 |
+
"max_length": 512,
|
| 53 |
+
"max_position_embeddings": 1536,
|
| 54 |
+
"min_length": 0,
|
| 55 |
+
"model_type": "mbart",
|
| 56 |
+
"no_repeat_ngram_size": 0,
|
| 57 |
+
"num_beam_groups": 1,
|
| 58 |
+
"num_beams": 1,
|
| 59 |
+
"num_hidden_layers": 12,
|
| 60 |
+
"num_return_sequences": 1,
|
| 61 |
+
"output_attentions": false,
|
| 62 |
+
"output_hidden_states": false,
|
| 63 |
+
"output_scores": false,
|
| 64 |
+
"pad_token_id": 1,
|
| 65 |
+
"prefix": null,
|
| 66 |
+
"problem_type": null,
|
| 67 |
+
"pruned_heads": {},
|
| 68 |
+
"remove_invalid_values": false,
|
| 69 |
+
"repetition_penalty": 1.0,
|
| 70 |
+
"return_dict": true,
|
| 71 |
+
"return_dict_in_generate": false,
|
| 72 |
+
"scale_embedding": true,
|
| 73 |
+
"sep_token_id": null,
|
| 74 |
+
"suppress_tokens": null,
|
| 75 |
+
"task_specific_params": null,
|
| 76 |
+
"temperature": 1.0,
|
| 77 |
+
"tf_legacy_loss": false,
|
| 78 |
+
"tie_encoder_decoder": false,
|
| 79 |
+
"tie_word_embeddings": true,
|
| 80 |
+
"tokenizer_class": null,
|
| 81 |
+
"top_k": 50,
|
| 82 |
+
"top_p": 1.0,
|
| 83 |
+
"torch_dtype": null,
|
| 84 |
+
"torchscript": false,
|
| 85 |
+
"typical_p": 1.0,
|
| 86 |
+
"use_bfloat16": false,
|
| 87 |
+
"use_cache": true,
|
| 88 |
+
"vocab_size": 57535
|
| 89 |
+
},
|
| 90 |
+
"decoder_start_token_id": 0,
|
| 91 |
+
"encoder": {
|
| 92 |
+
"_name_or_path": "",
|
| 93 |
+
"add_cross_attention": false,
|
| 94 |
+
"architectures": null,
|
| 95 |
+
"attention_probs_dropout_prob": 0.0,
|
| 96 |
+
"bad_words_ids": null,
|
| 97 |
+
"begin_suppress_tokens": null,
|
| 98 |
+
"bos_token_id": null,
|
| 99 |
+
"chunk_size_feed_forward": 0,
|
| 100 |
+
"cross_attention_hidden_size": null,
|
| 101 |
+
"decoder_start_token_id": null,
|
| 102 |
+
"depths": [
|
| 103 |
+
2,
|
| 104 |
+
2,
|
| 105 |
+
14,
|
| 106 |
+
2
|
| 107 |
+
],
|
| 108 |
+
"diversity_penalty": 0.0,
|
| 109 |
+
"do_sample": false,
|
| 110 |
+
"drop_path_rate": 0.1,
|
| 111 |
+
"early_stopping": false,
|
| 112 |
+
"embed_dim": 128,
|
| 113 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 114 |
+
"eos_token_id": null,
|
| 115 |
+
"exponential_decay_length_penalty": null,
|
| 116 |
+
"finetuning_task": null,
|
| 117 |
+
"forced_bos_token_id": null,
|
| 118 |
+
"forced_eos_token_id": null,
|
| 119 |
+
"hidden_act": "gelu",
|
| 120 |
+
"hidden_dropout_prob": 0.0,
|
| 121 |
+
"hidden_size": 1024,
|
| 122 |
+
"id2label": {
|
| 123 |
+
"0": "LABEL_0",
|
| 124 |
+
"1": "LABEL_1"
|
| 125 |
+
},
|
| 126 |
+
"image_size": [
|
| 127 |
+
550,
|
| 128 |
+
960
|
| 129 |
+
],
|
| 130 |
+
"initializer_range": 0.02,
|
| 131 |
+
"is_decoder": false,
|
| 132 |
+
"is_encoder_decoder": false,
|
| 133 |
+
"label2id": {
|
| 134 |
+
"LABEL_0": 0,
|
| 135 |
+
"LABEL_1": 1
|
| 136 |
+
},
|
| 137 |
+
"layer_norm_eps": 1e-05,
|
| 138 |
+
"length_penalty": 1.0,
|
| 139 |
+
"max_length": 20,
|
| 140 |
+
"min_length": 0,
|
| 141 |
+
"mlp_ratio": 4.0,
|
| 142 |
+
"model_type": "donut-swin",
|
| 143 |
+
"no_repeat_ngram_size": 0,
|
| 144 |
+
"num_beam_groups": 1,
|
| 145 |
+
"num_beams": 1,
|
| 146 |
+
"num_channels": 3,
|
| 147 |
+
"num_heads": [
|
| 148 |
+
4,
|
| 149 |
+
8,
|
| 150 |
+
16,
|
| 151 |
+
32
|
| 152 |
+
],
|
| 153 |
+
"num_layers": 4,
|
| 154 |
+
"num_return_sequences": 1,
|
| 155 |
+
"output_attentions": false,
|
| 156 |
+
"output_hidden_states": false,
|
| 157 |
+
"output_scores": false,
|
| 158 |
+
"pad_token_id": null,
|
| 159 |
+
"patch_size": 4,
|
| 160 |
+
"path_norm": true,
|
| 161 |
+
"prefix": null,
|
| 162 |
+
"problem_type": null,
|
| 163 |
+
"pruned_heads": {},
|
| 164 |
+
"qkv_bias": true,
|
| 165 |
+
"remove_invalid_values": false,
|
| 166 |
+
"repetition_penalty": 1.0,
|
| 167 |
+
"return_dict": true,
|
| 168 |
+
"return_dict_in_generate": false,
|
| 169 |
+
"sep_token_id": null,
|
| 170 |
+
"suppress_tokens": null,
|
| 171 |
+
"task_specific_params": null,
|
| 172 |
+
"temperature": 1.0,
|
| 173 |
+
"tf_legacy_loss": false,
|
| 174 |
+
"tie_encoder_decoder": false,
|
| 175 |
+
"tie_word_embeddings": true,
|
| 176 |
+
"tokenizer_class": null,
|
| 177 |
+
"top_k": 50,
|
| 178 |
+
"top_p": 1.0,
|
| 179 |
+
"torch_dtype": null,
|
| 180 |
+
"torchscript": false,
|
| 181 |
+
"typical_p": 1.0,
|
| 182 |
+
"use_absolute_embeddings": false,
|
| 183 |
+
"use_bfloat16": false,
|
| 184 |
+
"window_size": 10
|
| 185 |
+
},
|
| 186 |
+
"is_encoder_decoder": true,
|
| 187 |
+
"model_type": "vision-encoder-decoder",
|
| 188 |
+
"pad_token_id": 1,
|
| 189 |
+
"tie_word_embeddings": false,
|
| 190 |
+
"torch_dtype": "float32",
|
| 191 |
+
"transformers_version": "4.38.2"
|
| 192 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"forced_eos_token_id": 2,
|
| 6 |
+
"pad_token_id": 1,
|
| 7 |
+
"transformers_version": "4.38.2"
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4bc5fee2fcb2023bd9a33d708bf5f0b087950254a3ec1f8771e4804d18b089c
|
| 3 |
+
size 809111704
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59bc7dbf73e8a8675eb73e04ea3706ffaaa61cf8c28dbc354a3c7593f04a95c6
|
| 3 |
+
size 1615285631
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_align_long_axis": false,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pad": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"do_thumbnail": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "DonutImageProcessor",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "DonutProcessor",
|
| 20 |
+
"resample": 2,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": [
|
| 23 |
+
960,
|
| 24 |
+
550
|
| 25 |
+
]
|
| 26 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a449d045338a8380f32ee2c2c1e59988f272eba53067874fb88278de36c58fbd
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41d2b331930c8e09578a23a086b436a0ab0e343daf44f3b6ece96a8fbf0ade03
|
| 3 |
+
size 1064
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
|
| 3 |
+
size 1296245
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<s_untaxed_price>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "</s_untaxed_price>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<s_total_price>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "</s_total_price>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"content": "<s_tax>",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"content": "</s_tax>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"content": "<s_invoice_num>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"content": "</s_invoice_num>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"content": "<s_invoice_date>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"content": "</s_invoice_date>",
|
| 68 |
+
"lstrip": false,
|
| 69 |
+
"normalized": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"single_word": false
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"content": "<s>",
|
| 75 |
+
"lstrip": false,
|
| 76 |
+
"normalized": false,
|
| 77 |
+
"rstrip": false,
|
| 78 |
+
"single_word": false
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"content": "</s>",
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"normalized": false,
|
| 84 |
+
"rstrip": false,
|
| 85 |
+
"single_word": false
|
| 86 |
+
}
|
| 87 |
+
],
|
| 88 |
+
"bos_token": {
|
| 89 |
+
"content": "<s>",
|
| 90 |
+
"lstrip": false,
|
| 91 |
+
"normalized": false,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"single_word": false
|
| 94 |
+
},
|
| 95 |
+
"cls_token": {
|
| 96 |
+
"content": "<s>",
|
| 97 |
+
"lstrip": false,
|
| 98 |
+
"normalized": false,
|
| 99 |
+
"rstrip": false,
|
| 100 |
+
"single_word": false
|
| 101 |
+
},
|
| 102 |
+
"eos_token": {
|
| 103 |
+
"content": "</s>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false
|
| 108 |
+
},
|
| 109 |
+
"mask_token": {
|
| 110 |
+
"content": "<mask>",
|
| 111 |
+
"lstrip": true,
|
| 112 |
+
"normalized": true,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false
|
| 115 |
+
},
|
| 116 |
+
"pad_token": {
|
| 117 |
+
"content": "<pad>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false
|
| 122 |
+
},
|
| 123 |
+
"sep_token": {
|
| 124 |
+
"content": "</s>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false
|
| 129 |
+
},
|
| 130 |
+
"unk_token": {
|
| 131 |
+
"content": "<unk>",
|
| 132 |
+
"lstrip": false,
|
| 133 |
+
"normalized": false,
|
| 134 |
+
"rstrip": false,
|
| 135 |
+
"single_word": false
|
| 136 |
+
}
|
| 137 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,174 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"57521": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"57522": {
|
| 44 |
+
"content": "<sep/>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"57523": {
|
| 52 |
+
"content": "<s_iitcdip>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"57524": {
|
| 60 |
+
"content": "<s_synthdog>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"57525": {
|
| 68 |
+
"content": "<s_untaxed_price>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"57526": {
|
| 76 |
+
"content": "</s_untaxed_price>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"57527": {
|
| 84 |
+
"content": "<s_total_price>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"57528": {
|
| 92 |
+
"content": "</s_total_price>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"57529": {
|
| 100 |
+
"content": "<s_tax>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"57530": {
|
| 108 |
+
"content": "</s_tax>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"57531": {
|
| 116 |
+
"content": "<s_invoice_num>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"57532": {
|
| 124 |
+
"content": "</s_invoice_num>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"57533": {
|
| 132 |
+
"content": "<s_invoice_date>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"57534": {
|
| 140 |
+
"content": "</s_invoice_date>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
}
|
| 147 |
+
},
|
| 148 |
+
"additional_special_tokens": [
|
| 149 |
+
"<s_untaxed_price>",
|
| 150 |
+
"</s_untaxed_price>",
|
| 151 |
+
"<s_total_price>",
|
| 152 |
+
"</s_total_price>",
|
| 153 |
+
"<s_tax>",
|
| 154 |
+
"</s_tax>",
|
| 155 |
+
"<s_invoice_num>",
|
| 156 |
+
"</s_invoice_num>",
|
| 157 |
+
"<s_invoice_date>",
|
| 158 |
+
"</s_invoice_date>",
|
| 159 |
+
"<s>",
|
| 160 |
+
"</s>"
|
| 161 |
+
],
|
| 162 |
+
"bos_token": "<s>",
|
| 163 |
+
"clean_up_tokenization_spaces": true,
|
| 164 |
+
"cls_token": "<s>",
|
| 165 |
+
"eos_token": "</s>",
|
| 166 |
+
"mask_token": "<mask>",
|
| 167 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 168 |
+
"pad_token": "<pad>",
|
| 169 |
+
"processor_class": "DonutProcessor",
|
| 170 |
+
"sep_token": "</s>",
|
| 171 |
+
"sp_model_kwargs": {},
|
| 172 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 173 |
+
"unk_token": "<unk>"
|
| 174 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2820,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.71,
|
| 13 |
+
"grad_norm": 42.0918083190918,
|
| 14 |
+
"learning_rate": 1.929078014184397e-06,
|
| 15 |
+
"loss": 10.0975,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.42,
|
| 20 |
+
"grad_norm": 54.439884185791016,
|
| 21 |
+
"learning_rate": 1.8581560283687943e-06,
|
| 22 |
+
"loss": 5.8147,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.13,
|
| 27 |
+
"grad_norm": 60.155399322509766,
|
| 28 |
+
"learning_rate": 1.7872340425531913e-06,
|
| 29 |
+
"loss": 4.1279,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.84,
|
| 34 |
+
"grad_norm": 49.89198684692383,
|
| 35 |
+
"learning_rate": 1.7163120567375885e-06,
|
| 36 |
+
"loss": 2.8192,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 3.55,
|
| 41 |
+
"grad_norm": 24.662052154541016,
|
| 42 |
+
"learning_rate": 1.6453900709219858e-06,
|
| 43 |
+
"loss": 2.3071,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.26,
|
| 48 |
+
"grad_norm": 46.319374084472656,
|
| 49 |
+
"learning_rate": 1.574468085106383e-06,
|
| 50 |
+
"loss": 1.788,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.96,
|
| 55 |
+
"grad_norm": 19.011852264404297,
|
| 56 |
+
"learning_rate": 1.50354609929078e-06,
|
| 57 |
+
"loss": 1.6626,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 5.67,
|
| 62 |
+
"grad_norm": 24.53301239013672,
|
| 63 |
+
"learning_rate": 1.4326241134751774e-06,
|
| 64 |
+
"loss": 1.5502,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 6.38,
|
| 69 |
+
"grad_norm": 29.92524528503418,
|
| 70 |
+
"learning_rate": 1.3617021276595744e-06,
|
| 71 |
+
"loss": 1.4522,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 7.09,
|
| 76 |
+
"grad_norm": 49.022037506103516,
|
| 77 |
+
"learning_rate": 1.2907801418439716e-06,
|
| 78 |
+
"loss": 1.3627,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 7.8,
|
| 83 |
+
"grad_norm": 15.343302726745605,
|
| 84 |
+
"learning_rate": 1.2198581560283688e-06,
|
| 85 |
+
"loss": 1.2928,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 8.51,
|
| 90 |
+
"grad_norm": 20.46482276916504,
|
| 91 |
+
"learning_rate": 1.148936170212766e-06,
|
| 92 |
+
"loss": 1.2246,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 9.22,
|
| 97 |
+
"grad_norm": 26.57284927368164,
|
| 98 |
+
"learning_rate": 1.078014184397163e-06,
|
| 99 |
+
"loss": 1.153,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 9.93,
|
| 104 |
+
"grad_norm": 15.145112991333008,
|
| 105 |
+
"learning_rate": 1.00709219858156e-06,
|
| 106 |
+
"loss": 1.1536,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 10.64,
|
| 111 |
+
"grad_norm": 19.93513298034668,
|
| 112 |
+
"learning_rate": 9.361702127659575e-07,
|
| 113 |
+
"loss": 1.0598,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 11.35,
|
| 118 |
+
"grad_norm": 27.3331298828125,
|
| 119 |
+
"learning_rate": 8.652482269503546e-07,
|
| 120 |
+
"loss": 1.047,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 12.06,
|
| 125 |
+
"grad_norm": 43.462093353271484,
|
| 126 |
+
"learning_rate": 7.943262411347518e-07,
|
| 127 |
+
"loss": 1.0587,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 12.77,
|
| 132 |
+
"grad_norm": 36.50919723510742,
|
| 133 |
+
"learning_rate": 7.23404255319149e-07,
|
| 134 |
+
"loss": 1.0709,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 13.48,
|
| 139 |
+
"grad_norm": 19.904586791992188,
|
| 140 |
+
"learning_rate": 6.524822695035461e-07,
|
| 141 |
+
"loss": 0.972,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 14.18,
|
| 146 |
+
"grad_norm": 19.49388313293457,
|
| 147 |
+
"learning_rate": 5.815602836879432e-07,
|
| 148 |
+
"loss": 1.0102,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 14.89,
|
| 153 |
+
"grad_norm": 16.17923927307129,
|
| 154 |
+
"learning_rate": 5.106382978723403e-07,
|
| 155 |
+
"loss": 0.9229,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 15.6,
|
| 160 |
+
"grad_norm": 20.12999153137207,
|
| 161 |
+
"learning_rate": 4.397163120567376e-07,
|
| 162 |
+
"loss": 0.9488,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 16.31,
|
| 167 |
+
"grad_norm": 26.802228927612305,
|
| 168 |
+
"learning_rate": 3.687943262411347e-07,
|
| 169 |
+
"loss": 0.9173,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 17.02,
|
| 174 |
+
"grad_norm": 30.8055419921875,
|
| 175 |
+
"learning_rate": 2.978723404255319e-07,
|
| 176 |
+
"loss": 0.9306,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 17.73,
|
| 181 |
+
"grad_norm": 15.404391288757324,
|
| 182 |
+
"learning_rate": 2.2695035460992907e-07,
|
| 183 |
+
"loss": 0.898,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 18.44,
|
| 188 |
+
"grad_norm": 11.279256820678711,
|
| 189 |
+
"learning_rate": 1.5602836879432623e-07,
|
| 190 |
+
"loss": 0.9177,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 19.15,
|
| 195 |
+
"grad_norm": 20.938844680786133,
|
| 196 |
+
"learning_rate": 8.51063829787234e-08,
|
| 197 |
+
"loss": 0.8923,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 19.86,
|
| 202 |
+
"grad_norm": 48.48252868652344,
|
| 203 |
+
"learning_rate": 1.4184397163120567e-08,
|
| 204 |
+
"loss": 0.9238,
|
| 205 |
+
"step": 2800
|
| 206 |
+
}
|
| 207 |
+
],
|
| 208 |
+
"logging_steps": 100,
|
| 209 |
+
"max_steps": 2820,
|
| 210 |
+
"num_input_tokens_seen": 0,
|
| 211 |
+
"num_train_epochs": 20,
|
| 212 |
+
"save_steps": 500,
|
| 213 |
+
"total_flos": 7.55100305726976e+18,
|
| 214 |
+
"train_batch_size": 2,
|
| 215 |
+
"trial_name": null,
|
| 216 |
+
"trial_params": null
|
| 217 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08f398330d641864000e86a0d95e15e57481b8d831a40d683c790c0a3adcd7d1
|
| 3 |
+
size 5048
|