Commit
•
8c836db
1
Parent(s):
0abad5a
Training in progress, step 4800
Browse files- checkpoint-4800/config.json +161 -0
- checkpoint-4800/optimizer.pt +3 -0
- checkpoint-4800/pytorch_model.bin +3 -0
- checkpoint-4800/rng_state.pth +3 -0
- checkpoint-4800/scaler.pt +3 -0
- checkpoint-4800/scheduler.pt +3 -0
- checkpoint-4800/sentencepiece.bpe.model +3 -0
- checkpoint-4800/special_tokens_map.json +15 -0
- checkpoint-4800/tokenizer_config.json +41 -0
- checkpoint-4800/trainer_state.json +262 -0
- checkpoint-4800/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- runs/Mar02_21-56-31_2c0f9ccb1a2a/1677795998.3346019/events.out.tfevents.1677795998.2c0f9ccb1a2a.299.1 +3 -0
- runs/Mar02_21-56-31_2c0f9ccb1a2a/events.out.tfevents.1677795998.2c0f9ccb1a2a.299.0 +3 -0
- training_args.bin +1 -1
checkpoint-4800/config.json
ADDED
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/layoutxlm-base",
|
3 |
+
"architectures": [
|
4 |
+
"LayoutLMv2ForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"convert_sync_batchnorm": true,
|
9 |
+
"coordinate_size": 128,
|
10 |
+
"detectron2_config_args": {
|
11 |
+
"MODEL.ANCHOR_GENERATOR.SIZES": [
|
12 |
+
[
|
13 |
+
32
|
14 |
+
],
|
15 |
+
[
|
16 |
+
64
|
17 |
+
],
|
18 |
+
[
|
19 |
+
128
|
20 |
+
],
|
21 |
+
[
|
22 |
+
256
|
23 |
+
],
|
24 |
+
[
|
25 |
+
512
|
26 |
+
]
|
27 |
+
],
|
28 |
+
"MODEL.BACKBONE.NAME": "build_resnet_fpn_backbone",
|
29 |
+
"MODEL.FPN.IN_FEATURES": [
|
30 |
+
"res2",
|
31 |
+
"res3",
|
32 |
+
"res4",
|
33 |
+
"res5"
|
34 |
+
],
|
35 |
+
"MODEL.MASK_ON": true,
|
36 |
+
"MODEL.PIXEL_STD": [
|
37 |
+
57.375,
|
38 |
+
57.12,
|
39 |
+
58.395
|
40 |
+
],
|
41 |
+
"MODEL.POST_NMS_TOPK_TEST": 1000,
|
42 |
+
"MODEL.RESNETS.ASPECT_RATIOS": [
|
43 |
+
[
|
44 |
+
0.5,
|
45 |
+
1.0,
|
46 |
+
2.0
|
47 |
+
]
|
48 |
+
],
|
49 |
+
"MODEL.RESNETS.DEPTH": 101,
|
50 |
+
"MODEL.RESNETS.NUM_GROUPS": 32,
|
51 |
+
"MODEL.RESNETS.OUT_FEATURES": [
|
52 |
+
"res2",
|
53 |
+
"res3",
|
54 |
+
"res4",
|
55 |
+
"res5"
|
56 |
+
],
|
57 |
+
"MODEL.RESNETS.SIZES": [
|
58 |
+
[
|
59 |
+
32
|
60 |
+
],
|
61 |
+
[
|
62 |
+
64
|
63 |
+
],
|
64 |
+
[
|
65 |
+
128
|
66 |
+
],
|
67 |
+
[
|
68 |
+
256
|
69 |
+
],
|
70 |
+
[
|
71 |
+
512
|
72 |
+
]
|
73 |
+
],
|
74 |
+
"MODEL.RESNETS.STRIDE_IN_1X1": false,
|
75 |
+
"MODEL.RESNETS.WIDTH_PER_GROUP": 8,
|
76 |
+
"MODEL.ROI_BOX_HEAD.NAME": "FastRCNNConvFCHead",
|
77 |
+
"MODEL.ROI_BOX_HEAD.NUM_FC": 2,
|
78 |
+
"MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION": 14,
|
79 |
+
"MODEL.ROI_HEADS.IN_FEATURES": [
|
80 |
+
"p2",
|
81 |
+
"p3",
|
82 |
+
"p4",
|
83 |
+
"p5"
|
84 |
+
],
|
85 |
+
"MODEL.ROI_HEADS.NAME": "StandardROIHeads",
|
86 |
+
"MODEL.ROI_HEADS.NUM_CLASSES": 5,
|
87 |
+
"MODEL.ROI_MASK_HEAD.NAME": "MaskRCNNConvUpsampleHead",
|
88 |
+
"MODEL.ROI_MASK_HEAD.NUM_CONV": 4,
|
89 |
+
"MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION": 7,
|
90 |
+
"MODEL.RPN.IN_FEATURES": [
|
91 |
+
"p2",
|
92 |
+
"p3",
|
93 |
+
"p4",
|
94 |
+
"p5",
|
95 |
+
"p6"
|
96 |
+
],
|
97 |
+
"MODEL.RPN.POST_NMS_TOPK_TRAIN": 1000,
|
98 |
+
"MODEL.RPN.PRE_NMS_TOPK_TEST": 1000,
|
99 |
+
"MODEL.RPN.PRE_NMS_TOPK_TRAIN": 2000
|
100 |
+
},
|
101 |
+
"eos_token_id": 2,
|
102 |
+
"fast_qkv": false,
|
103 |
+
"gradient_checkpointing": false,
|
104 |
+
"has_relative_attention_bias": false,
|
105 |
+
"has_spatial_attention_bias": false,
|
106 |
+
"has_visual_segment_embedding": true,
|
107 |
+
"hidden_act": "gelu",
|
108 |
+
"hidden_dropout_prob": 0.1,
|
109 |
+
"hidden_size": 768,
|
110 |
+
"id2label": {
|
111 |
+
"0": "Caption",
|
112 |
+
"1": "Footnote",
|
113 |
+
"2": "Formula",
|
114 |
+
"3": "List-item",
|
115 |
+
"4": "Page-footer",
|
116 |
+
"5": "Page-header",
|
117 |
+
"6": "Picture",
|
118 |
+
"7": "Section-header",
|
119 |
+
"8": "Table",
|
120 |
+
"9": "Text",
|
121 |
+
"10": "Title"
|
122 |
+
},
|
123 |
+
"image_feature_pool_shape": [
|
124 |
+
7,
|
125 |
+
7,
|
126 |
+
256
|
127 |
+
],
|
128 |
+
"initializer_range": 0.02,
|
129 |
+
"intermediate_size": 3072,
|
130 |
+
"label2id": {
|
131 |
+
"Caption": 0,
|
132 |
+
"Footnote": 1,
|
133 |
+
"Formula": 2,
|
134 |
+
"List-item": 3,
|
135 |
+
"Page-footer": 4,
|
136 |
+
"Page-header": 5,
|
137 |
+
"Picture": 6,
|
138 |
+
"Section-header": 7,
|
139 |
+
"Table": 8,
|
140 |
+
"Text": 9,
|
141 |
+
"Title": 10
|
142 |
+
},
|
143 |
+
"layer_norm_eps": 1e-05,
|
144 |
+
"max_2d_position_embeddings": 1024,
|
145 |
+
"max_position_embeddings": 514,
|
146 |
+
"max_rel_2d_pos": 256,
|
147 |
+
"max_rel_pos": 128,
|
148 |
+
"model_type": "layoutlmv2",
|
149 |
+
"num_attention_heads": 12,
|
150 |
+
"num_hidden_layers": 12,
|
151 |
+
"output_past": true,
|
152 |
+
"pad_token_id": 1,
|
153 |
+
"rel_2d_pos_bins": 64,
|
154 |
+
"rel_pos_bins": 32,
|
155 |
+
"shape_size": 128,
|
156 |
+
"tokenizer_class": "LayoutXLMTokenizer",
|
157 |
+
"torch_dtype": "float32",
|
158 |
+
"transformers_version": "4.26.1",
|
159 |
+
"type_vocab_size": 1,
|
160 |
+
"vocab_size": 250002
|
161 |
+
}
|
checkpoint-4800/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3629e5a7a1cb9907dd717417bf26632b8b0dc654b751d867bff0a92624a97613
|
3 |
+
size 2927175013
|
checkpoint-4800/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8eadfa9997d1faa34349dfa531c88cf8b5dd425c80a137295d5efc012e1dcb7
|
3 |
+
size 1476527911
|
checkpoint-4800/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fad59e12d865a642628baf6b88088c022ba772dc94c32ca55d8f00f9fccb09d4
|
3 |
+
size 14503
|
checkpoint-4800/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:064328dd445c9b5136a50edc9b3ac2c311975a6d0b34181f5745e3f6b8a2496a
|
3 |
+
size 559
|
checkpoint-4800/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53912adbeffe40727d9d0f7d438ed85a0962c947ce564936813158ab2de1e6a6
|
3 |
+
size 623
|
checkpoint-4800/sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
checkpoint-4800/special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
checkpoint-4800/tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"cls_token_box": [
|
5 |
+
0,
|
6 |
+
0,
|
7 |
+
0,
|
8 |
+
0
|
9 |
+
],
|
10 |
+
"eos_token": "</s>",
|
11 |
+
"mask_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "<mask>",
|
14 |
+
"lstrip": true,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"model_max_length": 1000000000000000019884624838656,
|
20 |
+
"name_or_path": "microsoft/layoutxlm-base",
|
21 |
+
"only_label_first_subword": true,
|
22 |
+
"pad_token": "<pad>",
|
23 |
+
"pad_token_box": [
|
24 |
+
0,
|
25 |
+
0,
|
26 |
+
0,
|
27 |
+
0
|
28 |
+
],
|
29 |
+
"pad_token_label": -100,
|
30 |
+
"sep_token": "</s>",
|
31 |
+
"sep_token_box": [
|
32 |
+
1000,
|
33 |
+
1000,
|
34 |
+
1000,
|
35 |
+
1000
|
36 |
+
],
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"special_tokens_map_file": null,
|
39 |
+
"tokenizer_class": "LayoutXLMTokenizer",
|
40 |
+
"unk_token": "<unk>"
|
41 |
+
}
|
checkpoint-4800/trainer_state.json
ADDED
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7223092684102689,
|
3 |
+
"best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_lines_ml384-v1/checkpoint-4200",
|
4 |
+
"epoch": 1.9941836310760284,
|
5 |
+
"global_step": 4800,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.12,
|
12 |
+
"eval_accuracy": 0.8412902144953226,
|
13 |
+
"eval_f1": 0.13109765966400155,
|
14 |
+
"eval_loss": 0.5185014605522156,
|
15 |
+
"eval_precision": 0.14371894960965223,
|
16 |
+
"eval_recall": 0.1205141938939475,
|
17 |
+
"eval_runtime": 363.2958,
|
18 |
+
"eval_samples_per_second": 5.648,
|
19 |
+
"eval_steps_per_second": 0.355,
|
20 |
+
"step": 300
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.21,
|
24 |
+
"learning_rate": 1.372060857538036e-05,
|
25 |
+
"loss": 0.9231,
|
26 |
+
"step": 500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.25,
|
30 |
+
"eval_accuracy": 0.8751371332529899,
|
31 |
+
"eval_f1": 0.5030902012034086,
|
32 |
+
"eval_loss": 0.4107707738876343,
|
33 |
+
"eval_precision": 0.4636655625815517,
|
34 |
+
"eval_recall": 0.5498422900672499,
|
35 |
+
"eval_runtime": 366.1838,
|
36 |
+
"eval_samples_per_second": 5.604,
|
37 |
+
"eval_steps_per_second": 0.352,
|
38 |
+
"step": 600
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.37,
|
42 |
+
"eval_accuracy": 0.8887072454995973,
|
43 |
+
"eval_f1": 0.520614670919107,
|
44 |
+
"eval_loss": 0.3911038935184479,
|
45 |
+
"eval_precision": 0.5076044552496184,
|
46 |
+
"eval_recall": 0.5343093495209189,
|
47 |
+
"eval_runtime": 358.5079,
|
48 |
+
"eval_samples_per_second": 5.724,
|
49 |
+
"eval_steps_per_second": 0.36,
|
50 |
+
"step": 900
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.42,
|
54 |
+
"learning_rate": 1.9159741458910434e-05,
|
55 |
+
"loss": 0.369,
|
56 |
+
"step": 1000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.5,
|
60 |
+
"eval_accuracy": 0.8723944681931917,
|
61 |
+
"eval_f1": 0.5365372697053354,
|
62 |
+
"eval_loss": 0.41175082325935364,
|
63 |
+
"eval_precision": 0.5093875367745386,
|
64 |
+
"eval_recall": 0.5667440338034875,
|
65 |
+
"eval_runtime": 370.2231,
|
66 |
+
"eval_samples_per_second": 5.543,
|
67 |
+
"eval_steps_per_second": 0.348,
|
68 |
+
"step": 1200
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.62,
|
72 |
+
"learning_rate": 1.7620806401969838e-05,
|
73 |
+
"loss": 0.2737,
|
74 |
+
"step": 1500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.62,
|
78 |
+
"eval_accuracy": 0.8960354303687331,
|
79 |
+
"eval_f1": 0.6032919847328244,
|
80 |
+
"eval_loss": 0.33280590176582336,
|
81 |
+
"eval_precision": 0.6045538755752107,
|
82 |
+
"eval_recall": 0.6020353508302089,
|
83 |
+
"eval_runtime": 369.9685,
|
84 |
+
"eval_samples_per_second": 5.546,
|
85 |
+
"eval_steps_per_second": 0.349,
|
86 |
+
"step": 1500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.75,
|
90 |
+
"eval_accuracy": 0.9185901350526106,
|
91 |
+
"eval_f1": 0.640386343216532,
|
92 |
+
"eval_loss": 0.2983764410018921,
|
93 |
+
"eval_precision": 0.6061765800244512,
|
94 |
+
"eval_recall": 0.6786883294649765,
|
95 |
+
"eval_runtime": 366.7561,
|
96 |
+
"eval_samples_per_second": 5.595,
|
97 |
+
"eval_steps_per_second": 0.352,
|
98 |
+
"step": 1800
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.83,
|
102 |
+
"learning_rate": 1.6084949215143123e-05,
|
103 |
+
"loss": 0.2542,
|
104 |
+
"step": 2000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.87,
|
108 |
+
"eval_accuracy": 0.9162879176822183,
|
109 |
+
"eval_f1": 0.6593356503902912,
|
110 |
+
"eval_loss": 0.3114674985408783,
|
111 |
+
"eval_precision": 0.6323842832941691,
|
112 |
+
"eval_recall": 0.6886865440695114,
|
113 |
+
"eval_runtime": 356.8285,
|
114 |
+
"eval_samples_per_second": 5.751,
|
115 |
+
"eval_steps_per_second": 0.362,
|
116 |
+
"step": 2100
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.0,
|
120 |
+
"eval_accuracy": 0.919752052270062,
|
121 |
+
"eval_f1": 0.6536656236030397,
|
122 |
+
"eval_loss": 0.2877778708934784,
|
123 |
+
"eval_precision": 0.6160408657643899,
|
124 |
+
"eval_recall": 0.6961852050229126,
|
125 |
+
"eval_runtime": 352.6194,
|
126 |
+
"eval_samples_per_second": 5.819,
|
127 |
+
"eval_steps_per_second": 0.366,
|
128 |
+
"step": 2400
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.04,
|
132 |
+
"learning_rate": 1.4546014158202526e-05,
|
133 |
+
"loss": 0.1938,
|
134 |
+
"step": 2500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.12,
|
138 |
+
"eval_accuracy": 0.9165257053918363,
|
139 |
+
"eval_f1": 0.6752131725962951,
|
140 |
+
"eval_loss": 0.34137091040611267,
|
141 |
+
"eval_precision": 0.6672865694194223,
|
142 |
+
"eval_recall": 0.6833303576742248,
|
143 |
+
"eval_runtime": 349.7664,
|
144 |
+
"eval_samples_per_second": 5.867,
|
145 |
+
"eval_steps_per_second": 0.369,
|
146 |
+
"step": 2700
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.25,
|
150 |
+
"learning_rate": 1.3007079101261929e-05,
|
151 |
+
"loss": 0.1581,
|
152 |
+
"step": 3000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.25,
|
156 |
+
"eval_accuracy": 0.9193251152459752,
|
157 |
+
"eval_f1": 0.6871282417320962,
|
158 |
+
"eval_loss": 0.3610578179359436,
|
159 |
+
"eval_precision": 0.6867605968729564,
|
160 |
+
"eval_recall": 0.6874962804261144,
|
161 |
+
"eval_runtime": 346.075,
|
162 |
+
"eval_samples_per_second": 5.929,
|
163 |
+
"eval_steps_per_second": 0.373,
|
164 |
+
"step": 3000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.37,
|
168 |
+
"eval_accuracy": 0.9256291916839153,
|
169 |
+
"eval_f1": 0.6821629855293222,
|
170 |
+
"eval_loss": 0.2762657403945923,
|
171 |
+
"eval_precision": 0.6987891648982649,
|
172 |
+
"eval_recall": 0.6663095875736476,
|
173 |
+
"eval_runtime": 342.8929,
|
174 |
+
"eval_samples_per_second": 5.984,
|
175 |
+
"eval_steps_per_second": 0.376,
|
176 |
+
"step": 3300
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.45,
|
180 |
+
"learning_rate": 1.1471221914435212e-05,
|
181 |
+
"loss": 0.1428,
|
182 |
+
"step": 3500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 1.5,
|
186 |
+
"eval_accuracy": 0.9287285383081404,
|
187 |
+
"eval_f1": 0.7083662914511712,
|
188 |
+
"eval_loss": 0.306523859500885,
|
189 |
+
"eval_precision": 0.7245907761249767,
|
190 |
+
"eval_recall": 0.6928524668214009,
|
191 |
+
"eval_runtime": 342.9768,
|
192 |
+
"eval_samples_per_second": 5.983,
|
193 |
+
"eval_steps_per_second": 0.376,
|
194 |
+
"step": 3600
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 1.62,
|
198 |
+
"eval_accuracy": 0.9193764557741881,
|
199 |
+
"eval_f1": 0.6812402542881132,
|
200 |
+
"eval_loss": 0.29422909021377563,
|
201 |
+
"eval_precision": 0.6865518283469326,
|
202 |
+
"eval_recall": 0.6760102362673333,
|
203 |
+
"eval_runtime": 340.2288,
|
204 |
+
"eval_samples_per_second": 6.031,
|
205 |
+
"eval_steps_per_second": 0.379,
|
206 |
+
"step": 3900
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.66,
|
210 |
+
"learning_rate": 9.932286857494614e-06,
|
211 |
+
"loss": 0.1025,
|
212 |
+
"step": 4000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.74,
|
216 |
+
"eval_accuracy": 0.9346597203832706,
|
217 |
+
"eval_f1": 0.7223092684102689,
|
218 |
+
"eval_loss": 0.2989632189273834,
|
219 |
+
"eval_precision": 0.7315227342081172,
|
220 |
+
"eval_recall": 0.7133250014878295,
|
221 |
+
"eval_runtime": 368.8508,
|
222 |
+
"eval_samples_per_second": 5.563,
|
223 |
+
"eval_steps_per_second": 0.35,
|
224 |
+
"step": 4200
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.87,
|
228 |
+
"learning_rate": 8.393351800554018e-06,
|
229 |
+
"loss": 0.1225,
|
230 |
+
"step": 4500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.87,
|
234 |
+
"eval_accuracy": 0.9360324039797016,
|
235 |
+
"eval_f1": 0.7047921954799842,
|
236 |
+
"eval_loss": 0.2729274332523346,
|
237 |
+
"eval_precision": 0.7248993457473578,
|
238 |
+
"eval_recall": 0.6857703981431887,
|
239 |
+
"eval_runtime": 366.3118,
|
240 |
+
"eval_samples_per_second": 5.602,
|
241 |
+
"eval_steps_per_second": 0.352,
|
242 |
+
"step": 4500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.99,
|
246 |
+
"eval_accuracy": 0.9395776025594604,
|
247 |
+
"eval_f1": 0.7221742349457059,
|
248 |
+
"eval_loss": 0.2825567126274109,
|
249 |
+
"eval_precision": 0.7496957663485557,
|
250 |
+
"eval_recall": 0.6966017972981016,
|
251 |
+
"eval_runtime": 379.1173,
|
252 |
+
"eval_samples_per_second": 5.413,
|
253 |
+
"eval_steps_per_second": 0.34,
|
254 |
+
"step": 4800
|
255 |
+
}
|
256 |
+
],
|
257 |
+
"max_steps": 7221,
|
258 |
+
"num_train_epochs": 3,
|
259 |
+
"total_flos": 1.5545389723552512e+16,
|
260 |
+
"trial_name": null,
|
261 |
+
"trial_params": null
|
262 |
+
}
|
checkpoint-4800/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64fe5cba1b7f9d3bec562632694d0a69501b8cea02c7e57f6ebc355e549d19b9
|
3 |
+
size 3631
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1476527911
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8eadfa9997d1faa34349dfa531c88cf8b5dd425c80a137295d5efc012e1dcb7
|
3 |
size 1476527911
|
runs/Mar02_21-56-31_2c0f9ccb1a2a/1677795998.3346019/events.out.tfevents.1677795998.2c0f9ccb1a2a.299.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc8866a0768c088edf43e3147573a601951f2276421b2355e96e71ab8e306c93
|
3 |
+
size 5889
|
runs/Mar02_21-56-31_2c0f9ccb1a2a/events.out.tfevents.1677795998.2c0f9ccb1a2a.299.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb6e40479c126fb62bec8a54d0fc50eaa8fcf588ac874b7d31679ea501273c0b
|
3 |
+
size 7079
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3631
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64fe5cba1b7f9d3bec562632694d0a69501b8cea02c7e57f6ebc355e549d19b9
|
3 |
size 3631
|