Upload 13 files
Browse files- checkpoint-2000/config.json +74 -0
- checkpoint-2000/merges.txt +0 -0
- checkpoint-2000/model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/preprocessor_config.json +43 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/special_tokens_map.json +51 -0
- checkpoint-2000/tokenizer.json +0 -0
- checkpoint-2000/tokenizer_config.json +79 -0
- checkpoint-2000/trainer_state.json +289 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2000/vocab.json +0 -0
checkpoint-2000/config.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "num_facture",
|
18 |
+
"1": "date_facture",
|
19 |
+
"2": "fournisseur",
|
20 |
+
"3": "client",
|
21 |
+
"4": "mat_client",
|
22 |
+
"5": "mat_fournisseur",
|
23 |
+
"6": "tva",
|
24 |
+
"7": "pourcentage_tva",
|
25 |
+
"8": "remise",
|
26 |
+
"9": "pourcentage_remise",
|
27 |
+
"10": "timbre",
|
28 |
+
"11": "fodec",
|
29 |
+
"12": "ttc",
|
30 |
+
"13": "devise",
|
31 |
+
"14": "net_ht"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"input_size": 224,
|
35 |
+
"intermediate_size": 3072,
|
36 |
+
"label2id": {
|
37 |
+
"client": 3,
|
38 |
+
"date_facture": 1,
|
39 |
+
"devise": 13,
|
40 |
+
"fodec": 11,
|
41 |
+
"fournisseur": 2,
|
42 |
+
"mat_client": 4,
|
43 |
+
"mat_fournisseur": 5,
|
44 |
+
"net_ht": 14,
|
45 |
+
"num_facture": 0,
|
46 |
+
"pourcentage_remise": 9,
|
47 |
+
"pourcentage_tva": 7,
|
48 |
+
"remise": 8,
|
49 |
+
"timbre": 10,
|
50 |
+
"ttc": 12,
|
51 |
+
"tva": 6
|
52 |
+
},
|
53 |
+
"layer_norm_eps": 1e-05,
|
54 |
+
"max_2d_position_embeddings": 1024,
|
55 |
+
"max_position_embeddings": 514,
|
56 |
+
"max_rel_2d_pos": 256,
|
57 |
+
"max_rel_pos": 128,
|
58 |
+
"model_type": "layoutlmv3",
|
59 |
+
"num_attention_heads": 12,
|
60 |
+
"num_channels": 3,
|
61 |
+
"num_hidden_layers": 12,
|
62 |
+
"pad_token_id": 1,
|
63 |
+
"patch_size": 16,
|
64 |
+
"rel_2d_pos_bins": 64,
|
65 |
+
"rel_pos_bins": 32,
|
66 |
+
"second_input_size": 112,
|
67 |
+
"shape_size": 128,
|
68 |
+
"text_embed": true,
|
69 |
+
"torch_dtype": "float32",
|
70 |
+
"transformers_version": "4.40.0.dev0",
|
71 |
+
"type_vocab_size": 1,
|
72 |
+
"visual_embed": true,
|
73 |
+
"vocab_size": 50265
|
74 |
+
}
|
checkpoint-2000/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc932bd951f4e8e1ebb1498efc3cf84c11268e7417a179cf9c882475cb3b21ef
|
3 |
+
size 503742740
|
checkpoint-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcf4773b875ee2559b9924c96d3dd81f347c0ad2e247b53a629ec921fc8766cf
|
3 |
+
size 1007607354
|
checkpoint-2000/preprocessor_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"apply_ocr",
|
13 |
+
"ocr_lang",
|
14 |
+
"tesseract_config",
|
15 |
+
"return_tensors",
|
16 |
+
"data_format",
|
17 |
+
"input_data_format"
|
18 |
+
],
|
19 |
+
"apply_ocr": false,
|
20 |
+
"do_normalize": true,
|
21 |
+
"do_rescale": true,
|
22 |
+
"do_resize": true,
|
23 |
+
"image_mean": [
|
24 |
+
0.5,
|
25 |
+
0.5,
|
26 |
+
0.5
|
27 |
+
],
|
28 |
+
"image_processor_type": "LayoutLMv3ImageProcessor",
|
29 |
+
"image_std": [
|
30 |
+
0.5,
|
31 |
+
0.5,
|
32 |
+
0.5
|
33 |
+
],
|
34 |
+
"ocr_lang": null,
|
35 |
+
"processor_class": "LayoutLMv3Processor",
|
36 |
+
"resample": 2,
|
37 |
+
"rescale_factor": 0.00392156862745098,
|
38 |
+
"size": {
|
39 |
+
"height": 224,
|
40 |
+
"width": 224
|
41 |
+
},
|
42 |
+
"tesseract_config": ""
|
43 |
+
}
|
checkpoint-2000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d64d5cd4a8be5c64f958c67cb945a81de3232bbfc4fcbf2e466c683b1032b4f
|
3 |
+
size 13990
|
checkpoint-2000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b10f220c6245e03a350e1cc1a80f8ae24824dafeecdff977b1aa19497e2e087a
|
3 |
+
size 1064
|
checkpoint-2000/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 |
+
}
|
checkpoint-2000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2000/tokenizer_config.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"apply_ocr": false,
|
46 |
+
"bos_token": "<s>",
|
47 |
+
"clean_up_tokenization_spaces": true,
|
48 |
+
"cls_token": "<s>",
|
49 |
+
"cls_token_box": [
|
50 |
+
0,
|
51 |
+
0,
|
52 |
+
0,
|
53 |
+
0
|
54 |
+
],
|
55 |
+
"eos_token": "</s>",
|
56 |
+
"errors": "replace",
|
57 |
+
"mask_token": "<mask>",
|
58 |
+
"model_max_length": 512,
|
59 |
+
"only_label_first_subword": true,
|
60 |
+
"pad_token": "<pad>",
|
61 |
+
"pad_token_box": [
|
62 |
+
0,
|
63 |
+
0,
|
64 |
+
0,
|
65 |
+
0
|
66 |
+
],
|
67 |
+
"pad_token_label": -100,
|
68 |
+
"processor_class": "LayoutLMv3Processor",
|
69 |
+
"sep_token": "</s>",
|
70 |
+
"sep_token_box": [
|
71 |
+
0,
|
72 |
+
0,
|
73 |
+
0,
|
74 |
+
0
|
75 |
+
],
|
76 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
77 |
+
"trim_offsets": true,
|
78 |
+
"unk_token": "<unk>"
|
79 |
+
}
|
checkpoint-2000/trainer_state.json
ADDED
@@ -0,0 +1,289 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.55,
|
3 |
+
"best_model_checkpoint": "test\\checkpoint-1500",
|
4 |
+
"epoch": 1000.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 2000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 50.0,
|
13 |
+
"eval_accuracy": 0.6,
|
14 |
+
"eval_f1": 0.5365853658536585,
|
15 |
+
"eval_loss": 1.264135479927063,
|
16 |
+
"eval_precision": 0.5238095238095238,
|
17 |
+
"eval_recall": 0.55,
|
18 |
+
"eval_runtime": 4.6603,
|
19 |
+
"eval_samples_per_second": 0.429,
|
20 |
+
"eval_steps_per_second": 0.215,
|
21 |
+
"step": 100
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 100.0,
|
25 |
+
"eval_accuracy": 0.6,
|
26 |
+
"eval_f1": 0.5365853658536585,
|
27 |
+
"eval_loss": 1.3265936374664307,
|
28 |
+
"eval_precision": 0.5238095238095238,
|
29 |
+
"eval_recall": 0.55,
|
30 |
+
"eval_runtime": 4.6509,
|
31 |
+
"eval_samples_per_second": 0.43,
|
32 |
+
"eval_steps_per_second": 0.215,
|
33 |
+
"step": 200
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 150.0,
|
37 |
+
"eval_accuracy": 0.6,
|
38 |
+
"eval_f1": 0.5365853658536585,
|
39 |
+
"eval_loss": 1.4988499879837036,
|
40 |
+
"eval_precision": 0.5238095238095238,
|
41 |
+
"eval_recall": 0.55,
|
42 |
+
"eval_runtime": 4.6202,
|
43 |
+
"eval_samples_per_second": 0.433,
|
44 |
+
"eval_steps_per_second": 0.216,
|
45 |
+
"step": 300
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 200.0,
|
49 |
+
"eval_accuracy": 0.6,
|
50 |
+
"eval_f1": 0.5365853658536585,
|
51 |
+
"eval_loss": 1.6139302253723145,
|
52 |
+
"eval_precision": 0.5238095238095238,
|
53 |
+
"eval_recall": 0.55,
|
54 |
+
"eval_runtime": 4.7737,
|
55 |
+
"eval_samples_per_second": 0.419,
|
56 |
+
"eval_steps_per_second": 0.209,
|
57 |
+
"step": 400
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 250.0,
|
61 |
+
"grad_norm": 0.14490167796611786,
|
62 |
+
"learning_rate": 7.500000000000001e-06,
|
63 |
+
"loss": 0.3046,
|
64 |
+
"step": 500
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 250.0,
|
68 |
+
"eval_accuracy": 0.6,
|
69 |
+
"eval_f1": 0.5365853658536585,
|
70 |
+
"eval_loss": 1.6872639656066895,
|
71 |
+
"eval_precision": 0.5238095238095238,
|
72 |
+
"eval_recall": 0.55,
|
73 |
+
"eval_runtime": 4.6336,
|
74 |
+
"eval_samples_per_second": 0.432,
|
75 |
+
"eval_steps_per_second": 0.216,
|
76 |
+
"step": 500
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 300.0,
|
80 |
+
"eval_accuracy": 0.6,
|
81 |
+
"eval_f1": 0.5365853658536585,
|
82 |
+
"eval_loss": 1.7239123582839966,
|
83 |
+
"eval_precision": 0.5238095238095238,
|
84 |
+
"eval_recall": 0.55,
|
85 |
+
"eval_runtime": 4.5649,
|
86 |
+
"eval_samples_per_second": 0.438,
|
87 |
+
"eval_steps_per_second": 0.219,
|
88 |
+
"step": 600
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 350.0,
|
92 |
+
"eval_accuracy": 0.6,
|
93 |
+
"eval_f1": 0.5365853658536585,
|
94 |
+
"eval_loss": 1.7806979417800903,
|
95 |
+
"eval_precision": 0.5238095238095238,
|
96 |
+
"eval_recall": 0.55,
|
97 |
+
"eval_runtime": 4.4489,
|
98 |
+
"eval_samples_per_second": 0.45,
|
99 |
+
"eval_steps_per_second": 0.225,
|
100 |
+
"step": 700
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 400.0,
|
104 |
+
"eval_accuracy": 0.6,
|
105 |
+
"eval_f1": 0.5365853658536585,
|
106 |
+
"eval_loss": 1.8008891344070435,
|
107 |
+
"eval_precision": 0.5238095238095238,
|
108 |
+
"eval_recall": 0.55,
|
109 |
+
"eval_runtime": 4.4619,
|
110 |
+
"eval_samples_per_second": 0.448,
|
111 |
+
"eval_steps_per_second": 0.224,
|
112 |
+
"step": 800
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 450.0,
|
116 |
+
"eval_accuracy": 0.6,
|
117 |
+
"eval_f1": 0.5365853658536585,
|
118 |
+
"eval_loss": 1.8712844848632812,
|
119 |
+
"eval_precision": 0.5238095238095238,
|
120 |
+
"eval_recall": 0.55,
|
121 |
+
"eval_runtime": 4.4231,
|
122 |
+
"eval_samples_per_second": 0.452,
|
123 |
+
"eval_steps_per_second": 0.226,
|
124 |
+
"step": 900
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 500.0,
|
128 |
+
"grad_norm": 0.03944549337029457,
|
129 |
+
"learning_rate": 5e-06,
|
130 |
+
"loss": 0.0081,
|
131 |
+
"step": 1000
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 500.0,
|
135 |
+
"eval_accuracy": 0.6,
|
136 |
+
"eval_f1": 0.5365853658536585,
|
137 |
+
"eval_loss": 1.9119956493377686,
|
138 |
+
"eval_precision": 0.5238095238095238,
|
139 |
+
"eval_recall": 0.55,
|
140 |
+
"eval_runtime": 4.9883,
|
141 |
+
"eval_samples_per_second": 0.401,
|
142 |
+
"eval_steps_per_second": 0.2,
|
143 |
+
"step": 1000
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 550.0,
|
147 |
+
"eval_accuracy": 0.6333333333333333,
|
148 |
+
"eval_f1": 0.55,
|
149 |
+
"eval_loss": 1.947400450706482,
|
150 |
+
"eval_precision": 0.55,
|
151 |
+
"eval_recall": 0.55,
|
152 |
+
"eval_runtime": 4.9564,
|
153 |
+
"eval_samples_per_second": 0.404,
|
154 |
+
"eval_steps_per_second": 0.202,
|
155 |
+
"step": 1100
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 600.0,
|
159 |
+
"eval_accuracy": 0.6,
|
160 |
+
"eval_f1": 0.5365853658536585,
|
161 |
+
"eval_loss": 1.939751386642456,
|
162 |
+
"eval_precision": 0.5238095238095238,
|
163 |
+
"eval_recall": 0.55,
|
164 |
+
"eval_runtime": 4.9517,
|
165 |
+
"eval_samples_per_second": 0.404,
|
166 |
+
"eval_steps_per_second": 0.202,
|
167 |
+
"step": 1200
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 650.0,
|
171 |
+
"eval_accuracy": 0.6,
|
172 |
+
"eval_f1": 0.5365853658536585,
|
173 |
+
"eval_loss": 1.9685324430465698,
|
174 |
+
"eval_precision": 0.5238095238095238,
|
175 |
+
"eval_recall": 0.55,
|
176 |
+
"eval_runtime": 4.9434,
|
177 |
+
"eval_samples_per_second": 0.405,
|
178 |
+
"eval_steps_per_second": 0.202,
|
179 |
+
"step": 1300
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 700.0,
|
183 |
+
"eval_accuracy": 0.6,
|
184 |
+
"eval_f1": 0.5365853658536585,
|
185 |
+
"eval_loss": 1.9726978540420532,
|
186 |
+
"eval_precision": 0.5238095238095238,
|
187 |
+
"eval_recall": 0.55,
|
188 |
+
"eval_runtime": 5.0891,
|
189 |
+
"eval_samples_per_second": 0.393,
|
190 |
+
"eval_steps_per_second": 0.196,
|
191 |
+
"step": 1400
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 750.0,
|
195 |
+
"grad_norm": 0.0346556194126606,
|
196 |
+
"learning_rate": 2.5e-06,
|
197 |
+
"loss": 0.0044,
|
198 |
+
"step": 1500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 750.0,
|
202 |
+
"eval_accuracy": 0.6333333333333333,
|
203 |
+
"eval_f1": 0.55,
|
204 |
+
"eval_loss": 1.9932883977890015,
|
205 |
+
"eval_precision": 0.55,
|
206 |
+
"eval_recall": 0.55,
|
207 |
+
"eval_runtime": 5.166,
|
208 |
+
"eval_samples_per_second": 0.387,
|
209 |
+
"eval_steps_per_second": 0.194,
|
210 |
+
"step": 1500
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 800.0,
|
214 |
+
"eval_accuracy": 0.6333333333333333,
|
215 |
+
"eval_f1": 0.55,
|
216 |
+
"eval_loss": 2.012096643447876,
|
217 |
+
"eval_precision": 0.55,
|
218 |
+
"eval_recall": 0.55,
|
219 |
+
"eval_runtime": 5.144,
|
220 |
+
"eval_samples_per_second": 0.389,
|
221 |
+
"eval_steps_per_second": 0.194,
|
222 |
+
"step": 1600
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 850.0,
|
226 |
+
"eval_accuracy": 0.6333333333333333,
|
227 |
+
"eval_f1": 0.55,
|
228 |
+
"eval_loss": 2.0032660961151123,
|
229 |
+
"eval_precision": 0.55,
|
230 |
+
"eval_recall": 0.55,
|
231 |
+
"eval_runtime": 5.175,
|
232 |
+
"eval_samples_per_second": 0.386,
|
233 |
+
"eval_steps_per_second": 0.193,
|
234 |
+
"step": 1700
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 900.0,
|
238 |
+
"eval_accuracy": 0.6333333333333333,
|
239 |
+
"eval_f1": 0.55,
|
240 |
+
"eval_loss": 2.017909288406372,
|
241 |
+
"eval_precision": 0.55,
|
242 |
+
"eval_recall": 0.55,
|
243 |
+
"eval_runtime": 4.7769,
|
244 |
+
"eval_samples_per_second": 0.419,
|
245 |
+
"eval_steps_per_second": 0.209,
|
246 |
+
"step": 1800
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 950.0,
|
250 |
+
"eval_accuracy": 0.6333333333333333,
|
251 |
+
"eval_f1": 0.55,
|
252 |
+
"eval_loss": 2.016812324523926,
|
253 |
+
"eval_precision": 0.55,
|
254 |
+
"eval_recall": 0.55,
|
255 |
+
"eval_runtime": 4.6461,
|
256 |
+
"eval_samples_per_second": 0.43,
|
257 |
+
"eval_steps_per_second": 0.215,
|
258 |
+
"step": 1900
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 1000.0,
|
262 |
+
"grad_norm": 0.030378883704543114,
|
263 |
+
"learning_rate": 0.0,
|
264 |
+
"loss": 0.0034,
|
265 |
+
"step": 2000
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1000.0,
|
269 |
+
"eval_accuracy": 0.6333333333333333,
|
270 |
+
"eval_f1": 0.55,
|
271 |
+
"eval_loss": 2.0183417797088623,
|
272 |
+
"eval_precision": 0.55,
|
273 |
+
"eval_recall": 0.55,
|
274 |
+
"eval_runtime": 4.7632,
|
275 |
+
"eval_samples_per_second": 0.42,
|
276 |
+
"eval_steps_per_second": 0.21,
|
277 |
+
"step": 2000
|
278 |
+
}
|
279 |
+
],
|
280 |
+
"logging_steps": 500,
|
281 |
+
"max_steps": 2000,
|
282 |
+
"num_input_tokens_seen": 0,
|
283 |
+
"num_train_epochs": 1000,
|
284 |
+
"save_steps": 500,
|
285 |
+
"total_flos": 796315622400000.0,
|
286 |
+
"train_batch_size": 2,
|
287 |
+
"trial_name": null,
|
288 |
+
"trial_params": null
|
289 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d728b567e0023c8282187ce7c3d7cee0bfd33f8df96b33496aba47eed4b471e6
|
3 |
+
size 4856
|
checkpoint-2000/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|