Hugging Face's logo

jbl2024
/
camembert_v2_ner

Token Classification
Safetensors
French
deberta-v2
Model card Files Community
jbl2024 commited on
Commit
82f9351
•
1 Parent(s): 88da5d4

Ajout du modèle et du tokenizer

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-1060/config.json +58 -0
  2. checkpoint-1060/model.safetensors +3 -0
  3. checkpoint-1060/optimizer.pt +3 -0
  4. checkpoint-1060/rng_state.pth +3 -0
  5. checkpoint-1060/scheduler.pt +3 -0
  6. checkpoint-1060/special_tokens_map.json +51 -0
  7. checkpoint-1060/tokenizer.json +0 -0
  8. checkpoint-1060/tokenizer_config.json +57 -0
  9. checkpoint-1060/trainer_state.json +143 -0
  10. checkpoint-1060/training_args.bin +3 -0
  11. checkpoint-1060/vocab.txt +0 -0
  12. checkpoint-212/config.json +58 -0
  13. checkpoint-212/model.safetensors +3 -0
  14. checkpoint-212/optimizer.pt +3 -0
  15. checkpoint-212/rng_state.pth +3 -0
  16. checkpoint-212/scheduler.pt +3 -0
  17. checkpoint-212/special_tokens_map.json +51 -0
  18. checkpoint-212/tokenizer.json +0 -0
  19. checkpoint-212/tokenizer_config.json +57 -0
  20. checkpoint-212/trainer_state.json +55 -0
  21. checkpoint-212/training_args.bin +3 -0
  22. checkpoint-212/vocab.txt +0 -0
  23. checkpoint-425/config.json +58 -0
  24. checkpoint-425/model.safetensors +3 -0
  25. checkpoint-425/optimizer.pt +3 -0
  26. checkpoint-425/rng_state.pth +3 -0
  27. checkpoint-425/scheduler.pt +3 -0
  28. checkpoint-425/special_tokens_map.json +51 -0
  29. checkpoint-425/tokenizer.json +0 -0
  30. checkpoint-425/tokenizer_config.json +57 -0
  31. checkpoint-425/trainer_state.json +77 -0
  32. checkpoint-425/training_args.bin +3 -0
  33. checkpoint-425/vocab.txt +0 -0
  34. checkpoint-637/config.json +58 -0
  35. checkpoint-637/model.safetensors +3 -0
  36. checkpoint-637/optimizer.pt +3 -0
  37. checkpoint-637/rng_state.pth +3 -0
  38. checkpoint-637/scheduler.pt +3 -0
  39. checkpoint-637/special_tokens_map.json +51 -0
  40. checkpoint-637/tokenizer.json +0 -0
  41. checkpoint-637/tokenizer_config.json +57 -0
  42. checkpoint-637/trainer_state.json +99 -0
  43. checkpoint-637/training_args.bin +3 -0
  44. checkpoint-637/vocab.txt +0 -0
  45. checkpoint-850/config.json +58 -0
  46. checkpoint-850/model.safetensors +3 -0
  47. checkpoint-850/optimizer.pt +3 -0
  48. checkpoint-850/rng_state.pth +3 -0
  49. checkpoint-850/scheduler.pt +3 -0
  50. checkpoint-850/special_tokens_map.json +51 -0
checkpoint-1060/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "almanach/camembertav2-base-ftb-ner",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 1,
8
+ "conv_act": "gelu",
9
+ "conv_kernel_size": 0,
10
+ "embedding_size": 768,
11
+ "eos_token_id": 2,
12
+ "finetuning_task": "ner",
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "O",
18
+ "1": "LOC",
19
+ "2": "PER",
20
+ "3": "MISC",
21
+ "4": "ORG",
22
+ "5": "DATE"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "DATE": 5,
28
+ "LOC": 1,
29
+ "MISC": 3,
30
+ "O": 0,
31
+ "ORG": 4,
32
+ "PER": 2
33
+ },
34
+ "layer_norm_eps": 1e-07,
35
+ "max_position_embeddings": 1024,
36
+ "max_relative_positions": -1,
37
+ "model_name": "camembertav2-base-bf16",
38
+ "model_type": "deberta-v2",
39
+ "norm_rel_ebd": "layer_norm",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "pooler_dropout": 0,
44
+ "pooler_hidden_act": "gelu",
45
+ "pooler_hidden_size": 768,
46
+ "pos_att_type": [
47
+ "p2c",
48
+ "c2p"
49
+ ],
50
+ "position_biased_input": false,
51
+ "position_buckets": 256,
52
+ "relative_attention": true,
53
+ "share_att_key": true,
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.46.3",
56
+ "type_vocab_size": 0,
57
+ "vocab_size": 32768
58
+ }
checkpoint-1060/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e319dca5b356e8d2da18d85a6cd5cf0bf10625e365250758c31ccf909f11cedc
3
+ size 442509128
checkpoint-1060/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea4ae7d34bd868748a7511448997a0926a8f4c5d89a71fc633a71586deb3d9e9
3
+ size 885136762
checkpoint-1060/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d398fbc869c4ab64d173f43ba9544a0b252925a7ed665a1b6646b8f0199058e3
3
+ size 14244
checkpoint-1060/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ff125de4eccf8be9e9feaba08477f46cda4da4a9ed755d7bcdc6426df5643ed
3
+ size 1064
checkpoint-1060/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-1060/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1060/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "eos_token": "[SEP]",
49
+ "errors": "replace",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "[UNK]"
57
+ }
checkpoint-1060/trainer_state.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.034093648195266724,
3
+ "best_model_checkpoint": "/content/drive/My Drive/camembert_v2_ner/checkpoint-637",
4
+ "epoch": 4.988235294117647,
5
+ "eval_steps": 500,
6
+ "global_step": 1060,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47058823529411764,
13
+ "grad_norm": 0.31596189737319946,
14
+ "learning_rate": 4.5330188679245284e-05,
15
+ "loss": 0.1695,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.9411764705882353,
20
+ "grad_norm": 0.2977713346481323,
21
+ "learning_rate": 4.061320754716981e-05,
22
+ "loss": 0.0468,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.9976470588235294,
27
+ "eval_loss": 0.04163844883441925,
28
+ "eval_runtime": 11.7779,
29
+ "eval_samples_per_second": 1024.714,
30
+ "eval_steps_per_second": 32.094,
31
+ "step": 212
32
+ },
33
+ {
34
+ "epoch": 1.4117647058823528,
35
+ "grad_norm": 0.23586325347423553,
36
+ "learning_rate": 3.589622641509434e-05,
37
+ "loss": 0.0363,
38
+ "step": 300
39
+ },
40
+ {
41
+ "epoch": 1.8823529411764706,
42
+ "grad_norm": 0.2934682369232178,
43
+ "learning_rate": 3.117924528301887e-05,
44
+ "loss": 0.0333,
45
+ "step": 400
46
+ },
47
+ {
48
+ "epoch": 2.0,
49
+ "eval_loss": 0.035711608827114105,
50
+ "eval_runtime": 11.375,
51
+ "eval_samples_per_second": 1061.007,
52
+ "eval_steps_per_second": 33.231,
53
+ "step": 425
54
+ },
55
+ {
56
+ "epoch": 2.3529411764705883,
57
+ "grad_norm": 0.2868112325668335,
58
+ "learning_rate": 2.64622641509434e-05,
59
+ "loss": 0.0294,
60
+ "step": 500
61
+ },
62
+ {
63
+ "epoch": 2.8235294117647056,
64
+ "grad_norm": 0.32611510157585144,
65
+ "learning_rate": 2.1745283018867927e-05,
66
+ "loss": 0.026,
67
+ "step": 600
68
+ },
69
+ {
70
+ "epoch": 2.9976470588235293,
71
+ "eval_loss": 0.034093648195266724,
72
+ "eval_runtime": 11.7246,
73
+ "eval_samples_per_second": 1029.376,
74
+ "eval_steps_per_second": 32.24,
75
+ "step": 637
76
+ },
77
+ {
78
+ "epoch": 3.2941176470588234,
79
+ "grad_norm": 0.2773193120956421,
80
+ "learning_rate": 1.7028301886792454e-05,
81
+ "loss": 0.0235,
82
+ "step": 700
83
+ },
84
+ {
85
+ "epoch": 3.764705882352941,
86
+ "grad_norm": 0.3388814330101013,
87
+ "learning_rate": 1.2311320754716981e-05,
88
+ "loss": 0.0219,
89
+ "step": 800
90
+ },
91
+ {
92
+ "epoch": 4.0,
93
+ "eval_loss": 0.034132931381464005,
94
+ "eval_runtime": 11.541,
95
+ "eval_samples_per_second": 1045.747,
96
+ "eval_steps_per_second": 32.753,
97
+ "step": 850
98
+ },
99
+ {
100
+ "epoch": 4.235294117647059,
101
+ "grad_norm": 0.211588054895401,
102
+ "learning_rate": 7.594339622641509e-06,
103
+ "loss": 0.0201,
104
+ "step": 900
105
+ },
106
+ {
107
+ "epoch": 4.705882352941177,
108
+ "grad_norm": 0.3314550220966339,
109
+ "learning_rate": 2.877358490566038e-06,
110
+ "loss": 0.0193,
111
+ "step": 1000
112
+ },
113
+ {
114
+ "epoch": 4.988235294117647,
115
+ "eval_loss": 0.034694816917181015,
116
+ "eval_runtime": 12.3787,
117
+ "eval_samples_per_second": 974.984,
118
+ "eval_steps_per_second": 30.536,
119
+ "step": 1060
120
+ }
121
+ ],
122
+ "logging_steps": 100,
123
+ "max_steps": 1060,
124
+ "num_input_tokens_seen": 0,
125
+ "num_train_epochs": 5,
126
+ "save_steps": 500,
127
+ "stateful_callbacks": {
128
+ "TrainerControl": {
129
+ "args": {
130
+ "should_epoch_stop": false,
131
+ "should_evaluate": false,
132
+ "should_log": false,
133
+ "should_save": true,
134
+ "should_training_stop": true
135
+ },
136
+ "attributes": {}
137
+ }
138
+ },
139
+ "total_flos": 3.54058011339264e+16,
140
+ "train_batch_size": 256,
141
+ "trial_name": null,
142
+ "trial_params": null
143
+ }
checkpoint-1060/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f48dedd3d48c42c036192fe12e665f9adf8f7252b564a9b49498df676e57a2
3
+ size 5368
checkpoint-1060/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-212/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "almanach/camembertav2-base-ftb-ner",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 1,
8
+ "conv_act": "gelu",
9
+ "conv_kernel_size": 0,
10
+ "embedding_size": 768,
11
+ "eos_token_id": 2,
12
+ "finetuning_task": "ner",
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "O",
18
+ "1": "LOC",
19
+ "2": "PER",
20
+ "3": "MISC",
21
+ "4": "ORG",
22
+ "5": "DATE"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "DATE": 5,
28
+ "LOC": 1,
29
+ "MISC": 3,
30
+ "O": 0,
31
+ "ORG": 4,
32
+ "PER": 2
33
+ },
34
+ "layer_norm_eps": 1e-07,
35
+ "max_position_embeddings": 1024,
36
+ "max_relative_positions": -1,
37
+ "model_name": "camembertav2-base-bf16",
38
+ "model_type": "deberta-v2",
39
+ "norm_rel_ebd": "layer_norm",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "pooler_dropout": 0,
44
+ "pooler_hidden_act": "gelu",
45
+ "pooler_hidden_size": 768,
46
+ "pos_att_type": [
47
+ "p2c",
48
+ "c2p"
49
+ ],
50
+ "position_biased_input": false,
51
+ "position_buckets": 256,
52
+ "relative_attention": true,
53
+ "share_att_key": true,
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.46.3",
56
+ "type_vocab_size": 0,
57
+ "vocab_size": 32768
58
+ }
checkpoint-212/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd74b7360c9f8ccce6b11ccacc01ec57842478c211af73f903204e4525da935
3
+ size 442509128
checkpoint-212/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a608dc8061fbb1d82be292403d457ce2ee81783cc7f4cad3e3cca1c5d95881e
3
+ size 885136762
checkpoint-212/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba1d775f02a0ddaa2c5f0bb97f3651b1a4512dc3391a40c597fd8759ff039e6d
3
+ size 14244
checkpoint-212/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de72e4aa9e3f6920414fc1961588d7451c495b85ccd994bca8987ba2548786d1
3
+ size 1064
checkpoint-212/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-212/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-212/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "eos_token": "[SEP]",
49
+ "errors": "replace",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "[UNK]"
57
+ }
checkpoint-212/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.04163844883441925,
3
+ "best_model_checkpoint": "/content/drive/My Drive/camembert_v2_ner/checkpoint-212",
4
+ "epoch": 0.9976470588235294,
5
+ "eval_steps": 500,
6
+ "global_step": 212,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47058823529411764,
13
+ "grad_norm": 0.31596189737319946,
14
+ "learning_rate": 4.5330188679245284e-05,
15
+ "loss": 0.1695,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.9411764705882353,
20
+ "grad_norm": 0.2977713346481323,
21
+ "learning_rate": 4.061320754716981e-05,
22
+ "loss": 0.0468,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.9976470588235294,
27
+ "eval_loss": 0.04163844883441925,
28
+ "eval_runtime": 11.7779,
29
+ "eval_samples_per_second": 1024.714,
30
+ "eval_steps_per_second": 32.094,
31
+ "step": 212
32
+ }
33
+ ],
34
+ "logging_steps": 100,
35
+ "max_steps": 1060,
36
+ "num_input_tokens_seen": 0,
37
+ "num_train_epochs": 5,
38
+ "save_steps": 500,
39
+ "stateful_callbacks": {
40
+ "TrainerControl": {
41
+ "args": {
42
+ "should_epoch_stop": false,
43
+ "should_evaluate": false,
44
+ "should_log": false,
45
+ "should_save": true,
46
+ "should_training_stop": false
47
+ },
48
+ "attributes": {}
49
+ }
50
+ },
51
+ "total_flos": 7095440868825600.0,
52
+ "train_batch_size": 256,
53
+ "trial_name": null,
54
+ "trial_params": null
55
+ }
checkpoint-212/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f48dedd3d48c42c036192fe12e665f9adf8f7252b564a9b49498df676e57a2
3
+ size 5368
checkpoint-212/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-425/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "almanach/camembertav2-base-ftb-ner",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 1,
8
+ "conv_act": "gelu",
9
+ "conv_kernel_size": 0,
10
+ "embedding_size": 768,
11
+ "eos_token_id": 2,
12
+ "finetuning_task": "ner",
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "O",
18
+ "1": "LOC",
19
+ "2": "PER",
20
+ "3": "MISC",
21
+ "4": "ORG",
22
+ "5": "DATE"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "DATE": 5,
28
+ "LOC": 1,
29
+ "MISC": 3,
30
+ "O": 0,
31
+ "ORG": 4,
32
+ "PER": 2
33
+ },
34
+ "layer_norm_eps": 1e-07,
35
+ "max_position_embeddings": 1024,
36
+ "max_relative_positions": -1,
37
+ "model_name": "camembertav2-base-bf16",
38
+ "model_type": "deberta-v2",
39
+ "norm_rel_ebd": "layer_norm",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "pooler_dropout": 0,
44
+ "pooler_hidden_act": "gelu",
45
+ "pooler_hidden_size": 768,
46
+ "pos_att_type": [
47
+ "p2c",
48
+ "c2p"
49
+ ],
50
+ "position_biased_input": false,
51
+ "position_buckets": 256,
52
+ "relative_attention": true,
53
+ "share_att_key": true,
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.46.3",
56
+ "type_vocab_size": 0,
57
+ "vocab_size": 32768
58
+ }
checkpoint-425/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9597cc88592ca242e5a0d10378dd578748cb09b649ef1739ecfa832d30eb0ed1
3
+ size 442509128
checkpoint-425/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb6050fb8116dc0ce725a82a43e7525a1c925013a5da582741eb92514af56cbb
3
+ size 885136762
checkpoint-425/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd528beea8e4cf430475413011db66b8377b30a9f6ad93f506d9b9d20c133742
3
+ size 14244
checkpoint-425/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86443c2a7858df60efecf33cdbc88c2201b5ef0f439a28251dc2baed758b989d
3
+ size 1064
checkpoint-425/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-425/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-425/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "eos_token": "[SEP]",
49
+ "errors": "replace",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "[UNK]"
57
+ }
checkpoint-425/trainer_state.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.035711608827114105,
3
+ "best_model_checkpoint": "/content/drive/My Drive/camembert_v2_ner/checkpoint-425",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 425,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47058823529411764,
13
+ "grad_norm": 0.31596189737319946,
14
+ "learning_rate": 4.5330188679245284e-05,
15
+ "loss": 0.1695,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.9411764705882353,
20
+ "grad_norm": 0.2977713346481323,
21
+ "learning_rate": 4.061320754716981e-05,
22
+ "loss": 0.0468,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.9976470588235294,
27
+ "eval_loss": 0.04163844883441925,
28
+ "eval_runtime": 11.7779,
29
+ "eval_samples_per_second": 1024.714,
30
+ "eval_steps_per_second": 32.094,
31
+ "step": 212
32
+ },
33
+ {
34
+ "epoch": 1.4117647058823528,
35
+ "grad_norm": 0.23586325347423553,
36
+ "learning_rate": 3.589622641509434e-05,
37
+ "loss": 0.0363,
38
+ "step": 300
39
+ },
40
+ {
41
+ "epoch": 1.8823529411764706,
42
+ "grad_norm": 0.2934682369232178,
43
+ "learning_rate": 3.117924528301887e-05,
44
+ "loss": 0.0333,
45
+ "step": 400
46
+ },
47
+ {
48
+ "epoch": 2.0,
49
+ "eval_loss": 0.035711608827114105,
50
+ "eval_runtime": 11.375,
51
+ "eval_samples_per_second": 1061.007,
52
+ "eval_steps_per_second": 33.231,
53
+ "step": 425
54
+ }
55
+ ],
56
+ "logging_steps": 100,
57
+ "max_steps": 1060,
58
+ "num_input_tokens_seen": 0,
59
+ "num_train_epochs": 5,
60
+ "save_steps": 500,
61
+ "stateful_callbacks": {
62
+ "TrainerControl": {
63
+ "args": {
64
+ "should_epoch_stop": false,
65
+ "should_evaluate": false,
66
+ "should_log": false,
67
+ "should_save": true,
68
+ "should_training_stop": false
69
+ },
70
+ "attributes": {}
71
+ }
72
+ },
73
+ "total_flos": 1.41908817376512e+16,
74
+ "train_batch_size": 256,
75
+ "trial_name": null,
76
+ "trial_params": null
77
+ }
checkpoint-425/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f48dedd3d48c42c036192fe12e665f9adf8f7252b564a9b49498df676e57a2
3
+ size 5368
checkpoint-425/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-637/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "almanach/camembertav2-base-ftb-ner",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 1,
8
+ "conv_act": "gelu",
9
+ "conv_kernel_size": 0,
10
+ "embedding_size": 768,
11
+ "eos_token_id": 2,
12
+ "finetuning_task": "ner",
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "O",
18
+ "1": "LOC",
19
+ "2": "PER",
20
+ "3": "MISC",
21
+ "4": "ORG",
22
+ "5": "DATE"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "DATE": 5,
28
+ "LOC": 1,
29
+ "MISC": 3,
30
+ "O": 0,
31
+ "ORG": 4,
32
+ "PER": 2
33
+ },
34
+ "layer_norm_eps": 1e-07,
35
+ "max_position_embeddings": 1024,
36
+ "max_relative_positions": -1,
37
+ "model_name": "camembertav2-base-bf16",
38
+ "model_type": "deberta-v2",
39
+ "norm_rel_ebd": "layer_norm",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "pooler_dropout": 0,
44
+ "pooler_hidden_act": "gelu",
45
+ "pooler_hidden_size": 768,
46
+ "pos_att_type": [
47
+ "p2c",
48
+ "c2p"
49
+ ],
50
+ "position_biased_input": false,
51
+ "position_buckets": 256,
52
+ "relative_attention": true,
53
+ "share_att_key": true,
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.46.3",
56
+ "type_vocab_size": 0,
57
+ "vocab_size": 32768
58
+ }
checkpoint-637/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6a3121f9604489799189d78e66fac5cf98bb33ab5395751c9e708435ad3b8d2
3
+ size 442509128
checkpoint-637/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad33d1fd6c9acb745f1919b552bee17e9e47ca0b49fe8c9f8d31cb1e3c36511b
3
+ size 885136762
checkpoint-637/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e27f2c29b6abc8525dfc13c49e5c25e7b3ff7e7113bdb4d6aa62b026310dbf9e
3
+ size 14244
checkpoint-637/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f16daaa3c41f2d678e0c22876ccf183cc3c8cb9eefaea9be7d9f63223d4036ae
3
+ size 1064
checkpoint-637/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-637/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-637/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "eos_token": "[SEP]",
49
+ "errors": "replace",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "[UNK]"
57
+ }
checkpoint-637/trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.034093648195266724,
3
+ "best_model_checkpoint": "/content/drive/My Drive/camembert_v2_ner/checkpoint-637",
4
+ "epoch": 2.9976470588235293,
5
+ "eval_steps": 500,
6
+ "global_step": 637,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47058823529411764,
13
+ "grad_norm": 0.31596189737319946,
14
+ "learning_rate": 4.5330188679245284e-05,
15
+ "loss": 0.1695,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.9411764705882353,
20
+ "grad_norm": 0.2977713346481323,
21
+ "learning_rate": 4.061320754716981e-05,
22
+ "loss": 0.0468,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.9976470588235294,
27
+ "eval_loss": 0.04163844883441925,
28
+ "eval_runtime": 11.7779,
29
+ "eval_samples_per_second": 1024.714,
30
+ "eval_steps_per_second": 32.094,
31
+ "step": 212
32
+ },
33
+ {
34
+ "epoch": 1.4117647058823528,
35
+ "grad_norm": 0.23586325347423553,
36
+ "learning_rate": 3.589622641509434e-05,
37
+ "loss": 0.0363,
38
+ "step": 300
39
+ },
40
+ {
41
+ "epoch": 1.8823529411764706,
42
+ "grad_norm": 0.2934682369232178,
43
+ "learning_rate": 3.117924528301887e-05,
44
+ "loss": 0.0333,
45
+ "step": 400
46
+ },
47
+ {
48
+ "epoch": 2.0,
49
+ "eval_loss": 0.035711608827114105,
50
+ "eval_runtime": 11.375,
51
+ "eval_samples_per_second": 1061.007,
52
+ "eval_steps_per_second": 33.231,
53
+ "step": 425
54
+ },
55
+ {
56
+ "epoch": 2.3529411764705883,
57
+ "grad_norm": 0.2868112325668335,
58
+ "learning_rate": 2.64622641509434e-05,
59
+ "loss": 0.0294,
60
+ "step": 500
61
+ },
62
+ {
63
+ "epoch": 2.8235294117647056,
64
+ "grad_norm": 0.32611510157585144,
65
+ "learning_rate": 2.1745283018867927e-05,
66
+ "loss": 0.026,
67
+ "step": 600
68
+ },
69
+ {
70
+ "epoch": 2.9976470588235293,
71
+ "eval_loss": 0.034093648195266724,
72
+ "eval_runtime": 11.7246,
73
+ "eval_samples_per_second": 1029.376,
74
+ "eval_steps_per_second": 32.24,
75
+ "step": 637
76
+ }
77
+ ],
78
+ "logging_steps": 100,
79
+ "max_steps": 1060,
80
+ "num_input_tokens_seen": 0,
81
+ "num_train_epochs": 5,
82
+ "save_steps": 500,
83
+ "stateful_callbacks": {
84
+ "TrainerControl": {
85
+ "args": {
86
+ "should_epoch_stop": false,
87
+ "should_evaluate": false,
88
+ "should_log": false,
89
+ "should_save": true,
90
+ "should_training_stop": false
91
+ },
92
+ "attributes": {}
93
+ }
94
+ },
95
+ "total_flos": 2.12863226064768e+16,
96
+ "train_batch_size": 256,
97
+ "trial_name": null,
98
+ "trial_params": null
99
+ }
checkpoint-637/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f48dedd3d48c42c036192fe12e665f9adf8f7252b564a9b49498df676e57a2
3
+ size 5368
checkpoint-637/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-850/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "almanach/camembertav2-base-ftb-ner",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 1,
8
+ "conv_act": "gelu",
9
+ "conv_kernel_size": 0,
10
+ "embedding_size": 768,
11
+ "eos_token_id": 2,
12
+ "finetuning_task": "ner",
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "O",
18
+ "1": "LOC",
19
+ "2": "PER",
20
+ "3": "MISC",
21
+ "4": "ORG",
22
+ "5": "DATE"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "DATE": 5,
28
+ "LOC": 1,
29
+ "MISC": 3,
30
+ "O": 0,
31
+ "ORG": 4,
32
+ "PER": 2
33
+ },
34
+ "layer_norm_eps": 1e-07,
35
+ "max_position_embeddings": 1024,
36
+ "max_relative_positions": -1,
37
+ "model_name": "camembertav2-base-bf16",
38
+ "model_type": "deberta-v2",
39
+ "norm_rel_ebd": "layer_norm",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "pooler_dropout": 0,
44
+ "pooler_hidden_act": "gelu",
45
+ "pooler_hidden_size": 768,
46
+ "pos_att_type": [
47
+ "p2c",
48
+ "c2p"
49
+ ],
50
+ "position_biased_input": false,
51
+ "position_buckets": 256,
52
+ "relative_attention": true,
53
+ "share_att_key": true,
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.46.3",
56
+ "type_vocab_size": 0,
57
+ "vocab_size": 32768
58
+ }
checkpoint-850/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a199ee075a92f2afba56716cbe014b93c5b2cd80dccfed367ebbc4eaf481eaf0
3
+ size 442509128
checkpoint-850/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0390e4706aab994c0edcec12ca7ff213340f62f13011d3ee7f31ddcf56ef48f
3
+ size 885136762
checkpoint-850/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4b2c7d9d2390d4e9b15f0a51f5dc8118c8269467c789e995430e02a6b2add48
3
+ size 14244
checkpoint-850/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55694e2452ceb09645ac8e8bb510e480de7ca20e5bddf232e55c8935f0a8a111
3
+ size 1064
checkpoint-850/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }