softened thermorossi
Browse files- config.json +136 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- preprocessor_config.json +27 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +86 -0
- trainer_state.json +148 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "DataIntelligenceTeam/PickupReq_combined_RNS_Dec23_EEB_v13",
|
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": "pick_up_date",
|
18 |
+
"1": "delivery_date",
|
19 |
+
"2": "client_reference",
|
20 |
+
"3": "weight_tot",
|
21 |
+
"4": "weight_measure_unit",
|
22 |
+
"5": "numpack_tot",
|
23 |
+
"6": "volumes_tot",
|
24 |
+
"7": "incoterms",
|
25 |
+
"8": "controlled_temp",
|
26 |
+
"9": "pickup_name",
|
27 |
+
"10": "pickup_department",
|
28 |
+
"11": "pickup_address",
|
29 |
+
"12": "pickup_city",
|
30 |
+
"13": "pickup_province",
|
31 |
+
"14": "pickup_zipcode",
|
32 |
+
"15": "pickup_state",
|
33 |
+
"16": "contact_email",
|
34 |
+
"17": "contact_phone",
|
35 |
+
"18": "delivery_name",
|
36 |
+
"19": "delivery_department",
|
37 |
+
"20": "delivery_address",
|
38 |
+
"21": "delivery_city",
|
39 |
+
"22": "delivery_province",
|
40 |
+
"23": "delivery_zipcode",
|
41 |
+
"24": "delivery_state",
|
42 |
+
"25": "item_numpack_body",
|
43 |
+
"26": "item_pack_type",
|
44 |
+
"27": "item_notes",
|
45 |
+
"28": "item_weight_body",
|
46 |
+
"29": "item_weight_body_measure_unit",
|
47 |
+
"30": "item_volume_body",
|
48 |
+
"31": "item_measures_body",
|
49 |
+
"32": "item_stackable",
|
50 |
+
"33": "goods_value",
|
51 |
+
"34": "others",
|
52 |
+
"35": "delivery_time",
|
53 |
+
"36": "delivery_booking_needed",
|
54 |
+
"37": "pick_up_time_window",
|
55 |
+
"38": "delivery_time_window",
|
56 |
+
"39": "hazardous_goods",
|
57 |
+
"40": "limited_quantity",
|
58 |
+
"41": "consignee_name",
|
59 |
+
"42": "consignee_address",
|
60 |
+
"43": "consignee_city",
|
61 |
+
"44": "consignee_state",
|
62 |
+
"45": "consignee_zipcode"
|
63 |
+
},
|
64 |
+
"initializer_range": 0.02,
|
65 |
+
"input_size": 224,
|
66 |
+
"intermediate_size": 3072,
|
67 |
+
"label2id": {
|
68 |
+
"client_reference": 2,
|
69 |
+
"consignee_address": 42,
|
70 |
+
"consignee_city": 43,
|
71 |
+
"consignee_name": 41,
|
72 |
+
"consignee_state": 44,
|
73 |
+
"consignee_zipcode": 45,
|
74 |
+
"contact_email": 16,
|
75 |
+
"contact_phone": 17,
|
76 |
+
"controlled_temp": 8,
|
77 |
+
"delivery_address": 20,
|
78 |
+
"delivery_booking_needed": 36,
|
79 |
+
"delivery_city": 21,
|
80 |
+
"delivery_date": 1,
|
81 |
+
"delivery_department": 19,
|
82 |
+
"delivery_name": 18,
|
83 |
+
"delivery_province": 22,
|
84 |
+
"delivery_state": 24,
|
85 |
+
"delivery_time": 35,
|
86 |
+
"delivery_time_window": 38,
|
87 |
+
"delivery_zipcode": 23,
|
88 |
+
"goods_value": 33,
|
89 |
+
"hazardous_goods": 39,
|
90 |
+
"incoterms": 7,
|
91 |
+
"item_measures_body": 31,
|
92 |
+
"item_notes": 27,
|
93 |
+
"item_numpack_body": 25,
|
94 |
+
"item_pack_type": 26,
|
95 |
+
"item_stackable": 32,
|
96 |
+
"item_volume_body": 30,
|
97 |
+
"item_weight_body": 28,
|
98 |
+
"item_weight_body_measure_unit": 29,
|
99 |
+
"limited_quantity": 40,
|
100 |
+
"numpack_tot": 5,
|
101 |
+
"others": 34,
|
102 |
+
"pick_up_date": 0,
|
103 |
+
"pick_up_time_window": 37,
|
104 |
+
"pickup_address": 11,
|
105 |
+
"pickup_city": 12,
|
106 |
+
"pickup_department": 10,
|
107 |
+
"pickup_name": 9,
|
108 |
+
"pickup_province": 13,
|
109 |
+
"pickup_state": 15,
|
110 |
+
"pickup_zipcode": 14,
|
111 |
+
"volumes_tot": 6,
|
112 |
+
"weight_measure_unit": 4,
|
113 |
+
"weight_tot": 3
|
114 |
+
},
|
115 |
+
"layer_norm_eps": 1e-05,
|
116 |
+
"max_2d_position_embeddings": 1024,
|
117 |
+
"max_position_embeddings": 514,
|
118 |
+
"max_rel_2d_pos": 256,
|
119 |
+
"max_rel_pos": 128,
|
120 |
+
"model_type": "layoutlmv3",
|
121 |
+
"num_attention_heads": 12,
|
122 |
+
"num_channels": 3,
|
123 |
+
"num_hidden_layers": 12,
|
124 |
+
"pad_token_id": 1,
|
125 |
+
"patch_size": 16,
|
126 |
+
"rel_2d_pos_bins": 64,
|
127 |
+
"rel_pos_bins": 32,
|
128 |
+
"second_input_size": 112,
|
129 |
+
"shape_size": 128,
|
130 |
+
"text_embed": true,
|
131 |
+
"torch_dtype": "float32",
|
132 |
+
"transformers_version": "4.28.0",
|
133 |
+
"type_vocab_size": 1,
|
134 |
+
"visual_embed": true,
|
135 |
+
"vocab_size": 50265
|
136 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa85ffed7ae274415db6c1a6f587052fa5f01c31849238e8157d0df06990ef02
|
3 |
+
size 1007750650
|
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 sha256:3ba4d055d680fd5f8dbdec7625953cd3535faf211783e63d92f520eff5475e24
|
3 |
+
size 503891182
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16bbd6b69fece68f45bedf6263dd6b2640925eaf32384470ef53833a6ecd6974
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f042675461f8f610862c1509ea5fbd03199d20b5efce158faebeaf2b387e9b9
|
3 |
+
size 1064
|
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 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"cls_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"cls_token_box": [
|
22 |
+
0,
|
23 |
+
0,
|
24 |
+
0,
|
25 |
+
0
|
26 |
+
],
|
27 |
+
"eos_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "</s>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
},
|
35 |
+
"errors": "replace",
|
36 |
+
"mask_token": {
|
37 |
+
"__type": "AddedToken",
|
38 |
+
"content": "<mask>",
|
39 |
+
"lstrip": true,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"model_max_length": 512,
|
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 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
77 |
+
"trim_offsets": true,
|
78 |
+
"unk_token": {
|
79 |
+
"__type": "AddedToken",
|
80 |
+
"content": "<unk>",
|
81 |
+
"lstrip": false,
|
82 |
+
"normalized": true,
|
83 |
+
"rstrip": false,
|
84 |
+
"single_word": false
|
85 |
+
}
|
86 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9710806697108066,
|
3 |
+
"best_model_checkpoint": "/content/drive/Shareddrives/Data Science Team folder-open/Clients/Rhenus Documents/attachments_batch7_20231027_SELECTED/Thermorossi/pdf2img/processedimg/0-60 THERMOROSSI/model/PickupReq_combined_RNS_Jan24_TEEB_v14/checkpoint-1000",
|
4 |
+
"epoch": 15.625,
|
5 |
+
"global_step": 1000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.56,
|
12 |
+
"eval_accuracy": 0.9884072580645161,
|
13 |
+
"eval_f1": 0.9488939740655988,
|
14 |
+
"eval_loss": 0.057314518839120865,
|
15 |
+
"eval_precision": 0.9510703363914373,
|
16 |
+
"eval_recall": 0.9467275494672754,
|
17 |
+
"eval_runtime": 1.2555,
|
18 |
+
"eval_samples_per_second": 10.354,
|
19 |
+
"eval_steps_per_second": 5.575,
|
20 |
+
"step": 100
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 3.12,
|
24 |
+
"eval_accuracy": 0.9889112903225806,
|
25 |
+
"eval_f1": 0.945288753799392,
|
26 |
+
"eval_loss": 0.03306853398680687,
|
27 |
+
"eval_precision": 0.9438543247344461,
|
28 |
+
"eval_recall": 0.9467275494672754,
|
29 |
+
"eval_runtime": 1.2456,
|
30 |
+
"eval_samples_per_second": 10.436,
|
31 |
+
"eval_steps_per_second": 5.62,
|
32 |
+
"step": 200
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 4.69,
|
36 |
+
"eval_accuracy": 0.9924395161290323,
|
37 |
+
"eval_f1": 0.9627376425855514,
|
38 |
+
"eval_loss": 0.021277662366628647,
|
39 |
+
"eval_precision": 0.9620060790273556,
|
40 |
+
"eval_recall": 0.9634703196347032,
|
41 |
+
"eval_runtime": 1.2613,
|
42 |
+
"eval_samples_per_second": 10.307,
|
43 |
+
"eval_steps_per_second": 5.55,
|
44 |
+
"step": 300
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 6.25,
|
48 |
+
"eval_accuracy": 0.9949596774193549,
|
49 |
+
"eval_f1": 0.9710806697108066,
|
50 |
+
"eval_loss": 0.01480509340763092,
|
51 |
+
"eval_precision": 0.9710806697108066,
|
52 |
+
"eval_recall": 0.9710806697108066,
|
53 |
+
"eval_runtime": 1.1856,
|
54 |
+
"eval_samples_per_second": 10.965,
|
55 |
+
"eval_steps_per_second": 5.904,
|
56 |
+
"step": 400
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 7.81,
|
60 |
+
"learning_rate": 9e-06,
|
61 |
+
"loss": 0.0701,
|
62 |
+
"step": 500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 7.81,
|
66 |
+
"eval_accuracy": 0.9924395161290323,
|
67 |
+
"eval_f1": 0.9695121951219512,
|
68 |
+
"eval_loss": 0.026869984343647957,
|
69 |
+
"eval_precision": 0.9709923664122138,
|
70 |
+
"eval_recall": 0.9680365296803652,
|
71 |
+
"eval_runtime": 1.1983,
|
72 |
+
"eval_samples_per_second": 10.849,
|
73 |
+
"eval_steps_per_second": 5.842,
|
74 |
+
"step": 500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 9.38,
|
78 |
+
"eval_accuracy": 0.9929435483870968,
|
79 |
+
"eval_f1": 0.9665144596651446,
|
80 |
+
"eval_loss": 0.01921714097261429,
|
81 |
+
"eval_precision": 0.9665144596651446,
|
82 |
+
"eval_recall": 0.9665144596651446,
|
83 |
+
"eval_runtime": 1.1917,
|
84 |
+
"eval_samples_per_second": 10.909,
|
85 |
+
"eval_steps_per_second": 5.874,
|
86 |
+
"step": 600
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 10.94,
|
90 |
+
"eval_accuracy": 0.9969758064516129,
|
91 |
+
"eval_f1": 0.9817351598173516,
|
92 |
+
"eval_loss": 0.012911161407828331,
|
93 |
+
"eval_precision": 0.9817351598173516,
|
94 |
+
"eval_recall": 0.9817351598173516,
|
95 |
+
"eval_runtime": 1.1856,
|
96 |
+
"eval_samples_per_second": 10.965,
|
97 |
+
"eval_steps_per_second": 5.904,
|
98 |
+
"step": 700
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 12.5,
|
102 |
+
"eval_accuracy": 0.9919354838709677,
|
103 |
+
"eval_f1": 0.9650455927051671,
|
104 |
+
"eval_loss": 0.022616565227508545,
|
105 |
+
"eval_precision": 0.9635811836115327,
|
106 |
+
"eval_recall": 0.9665144596651446,
|
107 |
+
"eval_runtime": 1.2697,
|
108 |
+
"eval_samples_per_second": 10.239,
|
109 |
+
"eval_steps_per_second": 5.513,
|
110 |
+
"step": 800
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 14.06,
|
114 |
+
"eval_accuracy": 0.9964717741935484,
|
115 |
+
"eval_f1": 0.9786910197869102,
|
116 |
+
"eval_loss": 0.01615973375737667,
|
117 |
+
"eval_precision": 0.9786910197869102,
|
118 |
+
"eval_recall": 0.9786910197869102,
|
119 |
+
"eval_runtime": 1.2432,
|
120 |
+
"eval_samples_per_second": 10.457,
|
121 |
+
"eval_steps_per_second": 5.631,
|
122 |
+
"step": 900
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 15.62,
|
126 |
+
"learning_rate": 8.000000000000001e-06,
|
127 |
+
"loss": 0.005,
|
128 |
+
"step": 1000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 15.62,
|
132 |
+
"eval_accuracy": 0.9944556451612904,
|
133 |
+
"eval_f1": 0.9710806697108066,
|
134 |
+
"eval_loss": 0.01734299212694168,
|
135 |
+
"eval_precision": 0.9710806697108066,
|
136 |
+
"eval_recall": 0.9710806697108066,
|
137 |
+
"eval_runtime": 1.2549,
|
138 |
+
"eval_samples_per_second": 10.359,
|
139 |
+
"eval_steps_per_second": 5.578,
|
140 |
+
"step": 1000
|
141 |
+
}
|
142 |
+
],
|
143 |
+
"max_steps": 5000,
|
144 |
+
"num_train_epochs": 79,
|
145 |
+
"total_flos": 527040871802880.0,
|
146 |
+
"trial_name": null,
|
147 |
+
"trial_params": null
|
148 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e2d16b150619e30681439fdc28ece9702d3628dfec5abf66feccada895a8c4c
|
3 |
+
size 4408
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|