Upload 11 files
Browse files- config.json +96 -0
- merges.txt +0 -0
- preprocessor_config.json +27 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +87 -0
- trainer_state.json +544 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/layoutlmv3-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LayoutLMv3ForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"coordinate_size": 128,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"has_relative_attention_bias": true,
|
| 12 |
+
"has_spatial_attention_bias": true,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0.1,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "Ignore",
|
| 18 |
+
"1": "Store_name_value",
|
| 19 |
+
"2": "Store_name_key",
|
| 20 |
+
"3": "Store_addr_value",
|
| 21 |
+
"4": "Store_addr_key",
|
| 22 |
+
"5": "Tel_value",
|
| 23 |
+
"6": "Tel_key",
|
| 24 |
+
"7": "Date_value",
|
| 25 |
+
"8": "Date_key",
|
| 26 |
+
"9": "Time_value",
|
| 27 |
+
"10": "Time_key",
|
| 28 |
+
"11": "Prod_item_value",
|
| 29 |
+
"12": "Prod_item_key",
|
| 30 |
+
"13": "Prod_quantity_value",
|
| 31 |
+
"14": "Prod_quantity_key",
|
| 32 |
+
"15": "Prod_price_value",
|
| 33 |
+
"16": "Prod_price_key",
|
| 34 |
+
"17": "Subtotal_value",
|
| 35 |
+
"18": "Subtotal_key",
|
| 36 |
+
"19": "Tax_value",
|
| 37 |
+
"20": "Tax_key",
|
| 38 |
+
"21": "Tips_value",
|
| 39 |
+
"22": "Tips_key",
|
| 40 |
+
"23": "Total_value",
|
| 41 |
+
"24": "Total_key",
|
| 42 |
+
"25": "Others"
|
| 43 |
+
},
|
| 44 |
+
"initializer_range": 0.02,
|
| 45 |
+
"input_size": 224,
|
| 46 |
+
"intermediate_size": 3072,
|
| 47 |
+
"label2id": {
|
| 48 |
+
"Date_key": 8,
|
| 49 |
+
"Date_value": 7,
|
| 50 |
+
"Ignore": 0,
|
| 51 |
+
"Others": 25,
|
| 52 |
+
"Prod_item_key": 12,
|
| 53 |
+
"Prod_item_value": 11,
|
| 54 |
+
"Prod_price_key": 16,
|
| 55 |
+
"Prod_price_value": 15,
|
| 56 |
+
"Prod_quantity_key": 14,
|
| 57 |
+
"Prod_quantity_value": 13,
|
| 58 |
+
"Store_addr_key": 4,
|
| 59 |
+
"Store_addr_value": 3,
|
| 60 |
+
"Store_name_key": 2,
|
| 61 |
+
"Store_name_value": 1,
|
| 62 |
+
"Subtotal_key": 18,
|
| 63 |
+
"Subtotal_value": 17,
|
| 64 |
+
"Tax_key": 20,
|
| 65 |
+
"Tax_value": 19,
|
| 66 |
+
"Tel_key": 6,
|
| 67 |
+
"Tel_value": 5,
|
| 68 |
+
"Time_key": 10,
|
| 69 |
+
"Time_value": 9,
|
| 70 |
+
"Tips_key": 22,
|
| 71 |
+
"Tips_value": 21,
|
| 72 |
+
"Total_key": 24,
|
| 73 |
+
"Total_value": 23
|
| 74 |
+
},
|
| 75 |
+
"layer_norm_eps": 1e-05,
|
| 76 |
+
"max_2d_position_embeddings": 1024,
|
| 77 |
+
"max_position_embeddings": 514,
|
| 78 |
+
"max_rel_2d_pos": 256,
|
| 79 |
+
"max_rel_pos": 128,
|
| 80 |
+
"model_type": "layoutlmv3",
|
| 81 |
+
"num_attention_heads": 12,
|
| 82 |
+
"num_channels": 3,
|
| 83 |
+
"num_hidden_layers": 12,
|
| 84 |
+
"pad_token_id": 1,
|
| 85 |
+
"patch_size": 16,
|
| 86 |
+
"rel_2d_pos_bins": 64,
|
| 87 |
+
"rel_pos_bins": 32,
|
| 88 |
+
"second_input_size": 112,
|
| 89 |
+
"shape_size": 128,
|
| 90 |
+
"text_embed": true,
|
| 91 |
+
"torch_dtype": "float32",
|
| 92 |
+
"transformers_version": "4.25.0.dev0",
|
| 93 |
+
"type_vocab_size": 1,
|
| 94 |
+
"visual_embed": true,
|
| 95 |
+
"vocab_size": 50265
|
| 96 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"apply_ocr": false,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"feature_extractor_type": "LayoutLMv3FeatureExtractor",
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "LayoutLMv3ImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"ocr_lang": null,
|
| 19 |
+
"processor_class": "LayoutLMv3Processor",
|
| 20 |
+
"resample": 2,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"height": 224,
|
| 24 |
+
"width": 224
|
| 25 |
+
},
|
| 26 |
+
"tesseract_config": ""
|
| 27 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:721afcf20a61ea96668180206e656c8a93e5ce45083b1a52f1a272b6f9d7371d
|
| 3 |
+
size 503827343
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:341cb197d0c21ba9b226275dfc1b048a77fbadb9faf7f2aa6485e88e97579dd4
|
| 3 |
+
size 14503
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"apply_ocr": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"cls_token": {
|
| 13 |
+
"__type": "AddedToken",
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"cls_token_box": [
|
| 21 |
+
0,
|
| 22 |
+
0,
|
| 23 |
+
0,
|
| 24 |
+
0
|
| 25 |
+
],
|
| 26 |
+
"eos_token": {
|
| 27 |
+
"__type": "AddedToken",
|
| 28 |
+
"content": "</s>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
},
|
| 34 |
+
"errors": "replace",
|
| 35 |
+
"mask_token": {
|
| 36 |
+
"__type": "AddedToken",
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false
|
| 42 |
+
},
|
| 43 |
+
"model_max_length": 512,
|
| 44 |
+
"name_or_path": "microsoft/layoutlmv3-base",
|
| 45 |
+
"only_label_first_subword": true,
|
| 46 |
+
"pad_token": {
|
| 47 |
+
"__type": "AddedToken",
|
| 48 |
+
"content": "<pad>",
|
| 49 |
+
"lstrip": false,
|
| 50 |
+
"normalized": true,
|
| 51 |
+
"rstrip": false,
|
| 52 |
+
"single_word": false
|
| 53 |
+
},
|
| 54 |
+
"pad_token_box": [
|
| 55 |
+
0,
|
| 56 |
+
0,
|
| 57 |
+
0,
|
| 58 |
+
0
|
| 59 |
+
],
|
| 60 |
+
"pad_token_label": -100,
|
| 61 |
+
"processor_class": "LayoutLMv3Processor",
|
| 62 |
+
"sep_token": {
|
| 63 |
+
"__type": "AddedToken",
|
| 64 |
+
"content": "</s>",
|
| 65 |
+
"lstrip": false,
|
| 66 |
+
"normalized": true,
|
| 67 |
+
"rstrip": false,
|
| 68 |
+
"single_word": false
|
| 69 |
+
},
|
| 70 |
+
"sep_token_box": [
|
| 71 |
+
0,
|
| 72 |
+
0,
|
| 73 |
+
0,
|
| 74 |
+
0
|
| 75 |
+
],
|
| 76 |
+
"special_tokens_map_file": null,
|
| 77 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
| 78 |
+
"trim_offsets": true,
|
| 79 |
+
"unk_token": {
|
| 80 |
+
"__type": "AddedToken",
|
| 81 |
+
"content": "<unk>",
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"normalized": true,
|
| 84 |
+
"rstrip": false,
|
| 85 |
+
"single_word": false
|
| 86 |
+
}
|
| 87 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,544 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8802370452039692,
|
| 3 |
+
"best_model_checkpoint": "test/checkpoint-3000",
|
| 4 |
+
"epoch": 12.539184952978056,
|
| 5 |
+
"global_step": 4000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.31,
|
| 12 |
+
"eval_accuracy": 0.6750517260154634,
|
| 13 |
+
"eval_f1": 0.38478707258280515,
|
| 14 |
+
"eval_loss": 1.2847243547439575,
|
| 15 |
+
"eval_precision": 0.5487649605296664,
|
| 16 |
+
"eval_recall": 0.29626065438548255,
|
| 17 |
+
"eval_runtime": 48.6236,
|
| 18 |
+
"eval_samples_per_second": 9.728,
|
| 19 |
+
"eval_steps_per_second": 2.447,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.63,
|
| 24 |
+
"eval_accuracy": 0.7829140803658935,
|
| 25 |
+
"eval_f1": 0.589244320815948,
|
| 26 |
+
"eval_loss": 0.8382514119148254,
|
| 27 |
+
"eval_precision": 0.6727240649258998,
|
| 28 |
+
"eval_recall": 0.5241957657409954,
|
| 29 |
+
"eval_runtime": 47.451,
|
| 30 |
+
"eval_samples_per_second": 9.968,
|
| 31 |
+
"eval_steps_per_second": 2.508,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.94,
|
| 36 |
+
"eval_accuracy": 0.8379070020690407,
|
| 37 |
+
"eval_f1": 0.7082447783070723,
|
| 38 |
+
"eval_loss": 0.6504582166671753,
|
| 39 |
+
"eval_precision": 0.7584366661434626,
|
| 40 |
+
"eval_recall": 0.6642837503436898,
|
| 41 |
+
"eval_runtime": 47.1785,
|
| 42 |
+
"eval_samples_per_second": 10.026,
|
| 43 |
+
"eval_steps_per_second": 2.522,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.25,
|
| 48 |
+
"eval_accuracy": 0.8560383316998802,
|
| 49 |
+
"eval_f1": 0.74649361523969,
|
| 50 |
+
"eval_loss": 0.5616394877433777,
|
| 51 |
+
"eval_precision": 0.7579708091256908,
|
| 52 |
+
"eval_recall": 0.7353588122078636,
|
| 53 |
+
"eval_runtime": 47.4319,
|
| 54 |
+
"eval_samples_per_second": 9.972,
|
| 55 |
+
"eval_steps_per_second": 2.509,
|
| 56 |
+
"step": 400
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.57,
|
| 60 |
+
"learning_rate": 8.750000000000001e-06,
|
| 61 |
+
"loss": 1.0044,
|
| 62 |
+
"step": 500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.57,
|
| 66 |
+
"eval_accuracy": 0.8640967004246978,
|
| 67 |
+
"eval_f1": 0.7635898529098273,
|
| 68 |
+
"eval_loss": 0.48347049951553345,
|
| 69 |
+
"eval_precision": 0.7902632740108839,
|
| 70 |
+
"eval_recall": 0.7386582348089085,
|
| 71 |
+
"eval_runtime": 47.4677,
|
| 72 |
+
"eval_samples_per_second": 9.965,
|
| 73 |
+
"eval_steps_per_second": 2.507,
|
| 74 |
+
"step": 500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.88,
|
| 78 |
+
"eval_accuracy": 0.8795600566263748,
|
| 79 |
+
"eval_f1": 0.7909914858555341,
|
| 80 |
+
"eval_loss": 0.4531821012496948,
|
| 81 |
+
"eval_precision": 0.7901234567901234,
|
| 82 |
+
"eval_recall": 0.7918614242507561,
|
| 83 |
+
"eval_runtime": 48.4837,
|
| 84 |
+
"eval_samples_per_second": 9.756,
|
| 85 |
+
"eval_steps_per_second": 2.454,
|
| 86 |
+
"step": 600
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.19,
|
| 90 |
+
"eval_accuracy": 0.8883262550364804,
|
| 91 |
+
"eval_f1": 0.8112951398316589,
|
| 92 |
+
"eval_loss": 0.4272719919681549,
|
| 93 |
+
"eval_precision": 0.8012872083668544,
|
| 94 |
+
"eval_recall": 0.8215562276601595,
|
| 95 |
+
"eval_runtime": 47.6145,
|
| 96 |
+
"eval_samples_per_second": 9.934,
|
| 97 |
+
"eval_steps_per_second": 2.499,
|
| 98 |
+
"step": 700
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.51,
|
| 102 |
+
"eval_accuracy": 0.8954590003266907,
|
| 103 |
+
"eval_f1": 0.8212751449028298,
|
| 104 |
+
"eval_loss": 0.3849042057991028,
|
| 105 |
+
"eval_precision": 0.8147747260181302,
|
| 106 |
+
"eval_recall": 0.8278801209788287,
|
| 107 |
+
"eval_runtime": 47.9087,
|
| 108 |
+
"eval_samples_per_second": 9.873,
|
| 109 |
+
"eval_steps_per_second": 2.484,
|
| 110 |
+
"step": 800
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.82,
|
| 114 |
+
"eval_accuracy": 0.8950234128280519,
|
| 115 |
+
"eval_f1": 0.8168306752629793,
|
| 116 |
+
"eval_loss": 0.3808012306690216,
|
| 117 |
+
"eval_precision": 0.8065942903096099,
|
| 118 |
+
"eval_recall": 0.8273302172119879,
|
| 119 |
+
"eval_runtime": 47.5595,
|
| 120 |
+
"eval_samples_per_second": 9.945,
|
| 121 |
+
"eval_steps_per_second": 2.502,
|
| 122 |
+
"step": 900
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.13,
|
| 126 |
+
"learning_rate": 7.500000000000001e-06,
|
| 127 |
+
"loss": 0.4068,
|
| 128 |
+
"step": 1000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.13,
|
| 132 |
+
"eval_accuracy": 0.9042796471741261,
|
| 133 |
+
"eval_f1": 0.838237306692213,
|
| 134 |
+
"eval_loss": 0.35156166553497314,
|
| 135 |
+
"eval_precision": 0.8344686648501363,
|
| 136 |
+
"eval_recall": 0.8420401429749794,
|
| 137 |
+
"eval_runtime": 48.1704,
|
| 138 |
+
"eval_samples_per_second": 9.819,
|
| 139 |
+
"eval_steps_per_second": 2.47,
|
| 140 |
+
"step": 1000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 3.45,
|
| 144 |
+
"eval_accuracy": 0.9095066971577915,
|
| 145 |
+
"eval_f1": 0.8464466126911634,
|
| 146 |
+
"eval_loss": 0.33900508284568787,
|
| 147 |
+
"eval_precision": 0.8521666434443361,
|
| 148 |
+
"eval_recall": 0.8408028594995876,
|
| 149 |
+
"eval_runtime": 48.0055,
|
| 150 |
+
"eval_samples_per_second": 9.853,
|
| 151 |
+
"eval_steps_per_second": 2.479,
|
| 152 |
+
"step": 1100
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.76,
|
| 156 |
+
"eval_accuracy": 0.9087444190351737,
|
| 157 |
+
"eval_f1": 0.8463414634146341,
|
| 158 |
+
"eval_loss": 0.32527512311935425,
|
| 159 |
+
"eval_precision": 0.8343574672722415,
|
| 160 |
+
"eval_recall": 0.8586747319219137,
|
| 161 |
+
"eval_runtime": 48.0035,
|
| 162 |
+
"eval_samples_per_second": 9.853,
|
| 163 |
+
"eval_steps_per_second": 2.479,
|
| 164 |
+
"step": 1200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.08,
|
| 168 |
+
"eval_accuracy": 0.9081999346618752,
|
| 169 |
+
"eval_f1": 0.8466865833785986,
|
| 170 |
+
"eval_loss": 0.33180123567581177,
|
| 171 |
+
"eval_precision": 0.8364636436812449,
|
| 172 |
+
"eval_recall": 0.8571624965631015,
|
| 173 |
+
"eval_runtime": 47.8611,
|
| 174 |
+
"eval_samples_per_second": 9.883,
|
| 175 |
+
"eval_steps_per_second": 2.486,
|
| 176 |
+
"step": 1300
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.39,
|
| 180 |
+
"eval_accuracy": 0.9187629315038658,
|
| 181 |
+
"eval_f1": 0.8616123499142367,
|
| 182 |
+
"eval_loss": 0.3064488470554352,
|
| 183 |
+
"eval_precision": 0.8600191754554171,
|
| 184 |
+
"eval_recall": 0.8632114379983503,
|
| 185 |
+
"eval_runtime": 47.6825,
|
| 186 |
+
"eval_samples_per_second": 9.92,
|
| 187 |
+
"eval_steps_per_second": 2.496,
|
| 188 |
+
"step": 1400
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.7,
|
| 192 |
+
"learning_rate": 6.25e-06,
|
| 193 |
+
"loss": 0.2678,
|
| 194 |
+
"step": 1500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.7,
|
| 198 |
+
"eval_accuracy": 0.9184906893172166,
|
| 199 |
+
"eval_f1": 0.8611149536588739,
|
| 200 |
+
"eval_loss": 0.30125683546066284,
|
| 201 |
+
"eval_precision": 0.8665089086859689,
|
| 202 |
+
"eval_recall": 0.8557877371459994,
|
| 203 |
+
"eval_runtime": 47.6577,
|
| 204 |
+
"eval_samples_per_second": 9.925,
|
| 205 |
+
"eval_steps_per_second": 2.497,
|
| 206 |
+
"step": 1500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 5.02,
|
| 210 |
+
"eval_accuracy": 0.9157138190133943,
|
| 211 |
+
"eval_f1": 0.8587268993839836,
|
| 212 |
+
"eval_loss": 0.30989399552345276,
|
| 213 |
+
"eval_precision": 0.8550981461286805,
|
| 214 |
+
"eval_recall": 0.8623865823480891,
|
| 215 |
+
"eval_runtime": 47.7978,
|
| 216 |
+
"eval_samples_per_second": 9.896,
|
| 217 |
+
"eval_steps_per_second": 2.49,
|
| 218 |
+
"step": 1600
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 5.33,
|
| 222 |
+
"eval_accuracy": 0.9191440705651748,
|
| 223 |
+
"eval_f1": 0.8643950889777902,
|
| 224 |
+
"eval_loss": 0.3114277124404907,
|
| 225 |
+
"eval_precision": 0.8673864894795127,
|
| 226 |
+
"eval_recall": 0.8614242507561177,
|
| 227 |
+
"eval_runtime": 47.8331,
|
| 228 |
+
"eval_samples_per_second": 9.889,
|
| 229 |
+
"eval_steps_per_second": 2.488,
|
| 230 |
+
"step": 1700
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.64,
|
| 234 |
+
"eval_accuracy": 0.9207230752477404,
|
| 235 |
+
"eval_f1": 0.8651245795867938,
|
| 236 |
+
"eval_loss": 0.3051866888999939,
|
| 237 |
+
"eval_precision": 0.8638793694311172,
|
| 238 |
+
"eval_recall": 0.8663733846576849,
|
| 239 |
+
"eval_runtime": 47.7044,
|
| 240 |
+
"eval_samples_per_second": 9.915,
|
| 241 |
+
"eval_steps_per_second": 2.495,
|
| 242 |
+
"step": 1800
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 5.96,
|
| 246 |
+
"eval_accuracy": 0.9236088424262223,
|
| 247 |
+
"eval_f1": 0.8706572930175415,
|
| 248 |
+
"eval_loss": 0.2927141785621643,
|
| 249 |
+
"eval_precision": 0.8645790971939813,
|
| 250 |
+
"eval_recall": 0.8768215562276601,
|
| 251 |
+
"eval_runtime": 47.4403,
|
| 252 |
+
"eval_samples_per_second": 9.97,
|
| 253 |
+
"eval_steps_per_second": 2.508,
|
| 254 |
+
"step": 1900
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 6.27,
|
| 258 |
+
"learning_rate": 5e-06,
|
| 259 |
+
"loss": 0.2068,
|
| 260 |
+
"step": 2000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 6.27,
|
| 264 |
+
"eval_accuracy": 0.9194707611891538,
|
| 265 |
+
"eval_f1": 0.8640943047083819,
|
| 266 |
+
"eval_loss": 0.30293476581573486,
|
| 267 |
+
"eval_precision": 0.8615552822194888,
|
| 268 |
+
"eval_recall": 0.8666483365411053,
|
| 269 |
+
"eval_runtime": 47.7322,
|
| 270 |
+
"eval_samples_per_second": 9.909,
|
| 271 |
+
"eval_steps_per_second": 2.493,
|
| 272 |
+
"step": 2000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 6.58,
|
| 276 |
+
"eval_accuracy": 0.9211042143090493,
|
| 277 |
+
"eval_f1": 0.8684515293957353,
|
| 278 |
+
"eval_loss": 0.3005865216255188,
|
| 279 |
+
"eval_precision": 0.8607697501688049,
|
| 280 |
+
"eval_recall": 0.8762716524608194,
|
| 281 |
+
"eval_runtime": 47.8357,
|
| 282 |
+
"eval_samples_per_second": 9.888,
|
| 283 |
+
"eval_steps_per_second": 2.488,
|
| 284 |
+
"step": 2100
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 6.9,
|
| 288 |
+
"eval_accuracy": 0.923391048676903,
|
| 289 |
+
"eval_f1": 0.8718300205620287,
|
| 290 |
+
"eval_loss": 0.2952803373336792,
|
| 291 |
+
"eval_precision": 0.8693275013668671,
|
| 292 |
+
"eval_recall": 0.8743469892768766,
|
| 293 |
+
"eval_runtime": 47.6233,
|
| 294 |
+
"eval_samples_per_second": 9.932,
|
| 295 |
+
"eval_steps_per_second": 2.499,
|
| 296 |
+
"step": 2200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.21,
|
| 300 |
+
"eval_accuracy": 0.9212675596210389,
|
| 301 |
+
"eval_f1": 0.8683849739511927,
|
| 302 |
+
"eval_loss": 0.3120380938053131,
|
| 303 |
+
"eval_precision": 0.8660103910308996,
|
| 304 |
+
"eval_recall": 0.8707726147924113,
|
| 305 |
+
"eval_runtime": 48.4779,
|
| 306 |
+
"eval_samples_per_second": 9.757,
|
| 307 |
+
"eval_steps_per_second": 2.455,
|
| 308 |
+
"step": 2300
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 7.52,
|
| 312 |
+
"eval_accuracy": 0.9225198736796254,
|
| 313 |
+
"eval_f1": 0.8689645739296951,
|
| 314 |
+
"eval_loss": 0.3099469840526581,
|
| 315 |
+
"eval_precision": 0.8645890038105607,
|
| 316 |
+
"eval_recall": 0.8733846576849051,
|
| 317 |
+
"eval_runtime": 47.5215,
|
| 318 |
+
"eval_samples_per_second": 9.953,
|
| 319 |
+
"eval_steps_per_second": 2.504,
|
| 320 |
+
"step": 2400
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 7.84,
|
| 324 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 325 |
+
"loss": 0.16,
|
| 326 |
+
"step": 2500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 7.84,
|
| 330 |
+
"eval_accuracy": 0.9236088424262223,
|
| 331 |
+
"eval_f1": 0.8730713844887883,
|
| 332 |
+
"eval_loss": 0.299545019865036,
|
| 333 |
+
"eval_precision": 0.8709809823505268,
|
| 334 |
+
"eval_recall": 0.8751718449271377,
|
| 335 |
+
"eval_runtime": 47.9228,
|
| 336 |
+
"eval_samples_per_second": 9.87,
|
| 337 |
+
"eval_steps_per_second": 2.483,
|
| 338 |
+
"step": 2500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 8.15,
|
| 342 |
+
"eval_accuracy": 0.9233366002395731,
|
| 343 |
+
"eval_f1": 0.8713222745579903,
|
| 344 |
+
"eval_loss": 0.3018472492694855,
|
| 345 |
+
"eval_precision": 0.8653559322033898,
|
| 346 |
+
"eval_recall": 0.877371459994501,
|
| 347 |
+
"eval_runtime": 47.7011,
|
| 348 |
+
"eval_samples_per_second": 9.916,
|
| 349 |
+
"eval_steps_per_second": 2.495,
|
| 350 |
+
"step": 2600
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 8.46,
|
| 354 |
+
"eval_accuracy": 0.9234999455515627,
|
| 355 |
+
"eval_f1": 0.8743416102332581,
|
| 356 |
+
"eval_loss": 0.305177241563797,
|
| 357 |
+
"eval_precision": 0.8701157249829816,
|
| 358 |
+
"eval_recall": 0.8786087434698928,
|
| 359 |
+
"eval_runtime": 48.329,
|
| 360 |
+
"eval_samples_per_second": 9.787,
|
| 361 |
+
"eval_steps_per_second": 2.462,
|
| 362 |
+
"step": 2700
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 8.78,
|
| 366 |
+
"eval_accuracy": 0.9252967439834476,
|
| 367 |
+
"eval_f1": 0.8783895960154953,
|
| 368 |
+
"eval_loss": 0.2957703769207001,
|
| 369 |
+
"eval_precision": 0.8840155945419104,
|
| 370 |
+
"eval_recall": 0.8728347539180643,
|
| 371 |
+
"eval_runtime": 47.6638,
|
| 372 |
+
"eval_samples_per_second": 9.924,
|
| 373 |
+
"eval_steps_per_second": 2.497,
|
| 374 |
+
"step": 2800
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 9.09,
|
| 378 |
+
"eval_accuracy": 0.9270935424153327,
|
| 379 |
+
"eval_f1": 0.8792522850663185,
|
| 380 |
+
"eval_loss": 0.2976396679878235,
|
| 381 |
+
"eval_precision": 0.8790710457606157,
|
| 382 |
+
"eval_recall": 0.879433599120154,
|
| 383 |
+
"eval_runtime": 48.2883,
|
| 384 |
+
"eval_samples_per_second": 9.795,
|
| 385 |
+
"eval_steps_per_second": 2.464,
|
| 386 |
+
"step": 2900
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 9.4,
|
| 390 |
+
"learning_rate": 2.5e-06,
|
| 391 |
+
"loss": 0.1364,
|
| 392 |
+
"step": 3000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 9.4,
|
| 396 |
+
"eval_accuracy": 0.9288358924098878,
|
| 397 |
+
"eval_f1": 0.8802370452039692,
|
| 398 |
+
"eval_loss": 0.30077481269836426,
|
| 399 |
+
"eval_precision": 0.8824260845537442,
|
| 400 |
+
"eval_recall": 0.878058839703052,
|
| 401 |
+
"eval_runtime": 47.4506,
|
| 402 |
+
"eval_samples_per_second": 9.968,
|
| 403 |
+
"eval_steps_per_second": 2.508,
|
| 404 |
+
"step": 3000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 9.72,
|
| 408 |
+
"eval_accuracy": 0.9276380267886312,
|
| 409 |
+
"eval_f1": 0.8794581144594968,
|
| 410 |
+
"eval_loss": 0.295279324054718,
|
| 411 |
+
"eval_precision": 0.8843480678343064,
|
| 412 |
+
"eval_recall": 0.8746219411602969,
|
| 413 |
+
"eval_runtime": 48.0211,
|
| 414 |
+
"eval_samples_per_second": 9.85,
|
| 415 |
+
"eval_steps_per_second": 2.478,
|
| 416 |
+
"step": 3100
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 10.03,
|
| 420 |
+
"eval_accuracy": 0.9261134705433954,
|
| 421 |
+
"eval_f1": 0.8766407807023572,
|
| 422 |
+
"eval_loss": 0.30134841799736023,
|
| 423 |
+
"eval_precision": 0.8764600797031744,
|
| 424 |
+
"eval_recall": 0.8768215562276601,
|
| 425 |
+
"eval_runtime": 47.9205,
|
| 426 |
+
"eval_samples_per_second": 9.871,
|
| 427 |
+
"eval_steps_per_second": 2.483,
|
| 428 |
+
"step": 3200
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 10.34,
|
| 432 |
+
"eval_accuracy": 0.9256234346074268,
|
| 433 |
+
"eval_f1": 0.876704818038517,
|
| 434 |
+
"eval_loss": 0.306386798620224,
|
| 435 |
+
"eval_precision": 0.8741287412874129,
|
| 436 |
+
"eval_recall": 0.8792961231784437,
|
| 437 |
+
"eval_runtime": 47.48,
|
| 438 |
+
"eval_samples_per_second": 9.962,
|
| 439 |
+
"eval_steps_per_second": 2.506,
|
| 440 |
+
"step": 3300
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 10.66,
|
| 444 |
+
"eval_accuracy": 0.9298159642818251,
|
| 445 |
+
"eval_f1": 0.8808639427706698,
|
| 446 |
+
"eval_loss": 0.2949816882610321,
|
| 447 |
+
"eval_precision": 0.8814702643171806,
|
| 448 |
+
"eval_recall": 0.8802584547704152,
|
| 449 |
+
"eval_runtime": 47.5486,
|
| 450 |
+
"eval_samples_per_second": 9.948,
|
| 451 |
+
"eval_steps_per_second": 2.503,
|
| 452 |
+
"step": 3400
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 10.97,
|
| 456 |
+
"learning_rate": 1.25e-06,
|
| 457 |
+
"loss": 0.1192,
|
| 458 |
+
"step": 3500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 10.97,
|
| 462 |
+
"eval_accuracy": 0.9262223674180551,
|
| 463 |
+
"eval_f1": 0.8796156485929993,
|
| 464 |
+
"eval_loss": 0.3046295940876007,
|
| 465 |
+
"eval_precision": 0.8782894736842105,
|
| 466 |
+
"eval_recall": 0.8809458344789661,
|
| 467 |
+
"eval_runtime": 47.8942,
|
| 468 |
+
"eval_samples_per_second": 9.876,
|
| 469 |
+
"eval_steps_per_second": 2.485,
|
| 470 |
+
"step": 3500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 11.29,
|
| 474 |
+
"eval_accuracy": 0.9261134705433954,
|
| 475 |
+
"eval_f1": 0.8789643126241523,
|
| 476 |
+
"eval_loss": 0.30884549021720886,
|
| 477 |
+
"eval_precision": 0.8759044368600682,
|
| 478 |
+
"eval_recall": 0.8820456420126478,
|
| 479 |
+
"eval_runtime": 48.0682,
|
| 480 |
+
"eval_samples_per_second": 9.84,
|
| 481 |
+
"eval_steps_per_second": 2.476,
|
| 482 |
+
"step": 3600
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 11.6,
|
| 486 |
+
"eval_accuracy": 0.9268757486660133,
|
| 487 |
+
"eval_f1": 0.8796163069544365,
|
| 488 |
+
"eval_loss": 0.30328136682510376,
|
| 489 |
+
"eval_precision": 0.8767927878705095,
|
| 490 |
+
"eval_recall": 0.8824580698377784,
|
| 491 |
+
"eval_runtime": 47.6224,
|
| 492 |
+
"eval_samples_per_second": 9.932,
|
| 493 |
+
"eval_steps_per_second": 2.499,
|
| 494 |
+
"step": 3700
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 11.91,
|
| 498 |
+
"eval_accuracy": 0.9269301971033431,
|
| 499 |
+
"eval_f1": 0.8791058081327573,
|
| 500 |
+
"eval_loss": 0.30441808700561523,
|
| 501 |
+
"eval_precision": 0.8770009577233547,
|
| 502 |
+
"eval_recall": 0.8812207863623865,
|
| 503 |
+
"eval_runtime": 47.6174,
|
| 504 |
+
"eval_samples_per_second": 9.933,
|
| 505 |
+
"eval_steps_per_second": 2.499,
|
| 506 |
+
"step": 3800
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 12.23,
|
| 510 |
+
"eval_accuracy": 0.9272568877273222,
|
| 511 |
+
"eval_f1": 0.8795933786661172,
|
| 512 |
+
"eval_loss": 0.3058357238769531,
|
| 513 |
+
"eval_precision": 0.8789293067947838,
|
| 514 |
+
"eval_recall": 0.8802584547704152,
|
| 515 |
+
"eval_runtime": 47.5523,
|
| 516 |
+
"eval_samples_per_second": 9.947,
|
| 517 |
+
"eval_steps_per_second": 2.503,
|
| 518 |
+
"step": 3900
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 12.54,
|
| 522 |
+
"learning_rate": 0.0,
|
| 523 |
+
"loss": 0.1044,
|
| 524 |
+
"step": 4000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 12.54,
|
| 528 |
+
"eval_accuracy": 0.9272024392899924,
|
| 529 |
+
"eval_f1": 0.8791826659352715,
|
| 530 |
+
"eval_loss": 0.3065986931324005,
|
| 531 |
+
"eval_precision": 0.8770177838577291,
|
| 532 |
+
"eval_recall": 0.8813582623040968,
|
| 533 |
+
"eval_runtime": 47.8877,
|
| 534 |
+
"eval_samples_per_second": 9.877,
|
| 535 |
+
"eval_steps_per_second": 2.485,
|
| 536 |
+
"step": 4000
|
| 537 |
+
}
|
| 538 |
+
],
|
| 539 |
+
"max_steps": 4000,
|
| 540 |
+
"num_train_epochs": 13,
|
| 541 |
+
"total_flos": 4247432429568000.0,
|
| 542 |
+
"trial_name": null,
|
| 543 |
+
"trial_params": null
|
| 544 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbc92f1b4cffe4e9feedf5d78521d0d8178c4147b02e2255294af38531b75863
|
| 3 |
+
size 3375
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|