bikashpatra commited on
Commit
3dbac81
1 Parent(s): 3c03772

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - token-classification
6
+ base_model: elastic/distilbert-base-uncased-finetuned-conll03-english
7
+ widget:
8
+ - text: "I love AutoTrain"
9
+ datasets:
10
+ - bikashpatra/claims_token_classification
11
+ ---
12
+
13
+ # Model Trained Using AutoTrain
14
+
15
+ - Problem type: Token Classification
16
+
17
+ ## Validation Metrics
18
+ loss: 5.248876094818115
19
+
20
+ precision: 0.0
21
+
22
+ recall: 0.0
23
+
24
+ f1: 0.0
25
+
26
+ accuracy: 0.0026870229007633587
checkpoint-64/config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "elastic/distilbert-base-uncased-finetuned-conll03-english",
3
+ "_num_labels": 37,
4
+ "activation": "gelu",
5
+ "architectures": [
6
+ "DistilBertForTokenClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "dim": 768,
10
+ "dropout": 0.1,
11
+ "finetuning_task": "ner",
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "B-Apparatus",
15
+ "1": "B-Chemical Compound",
16
+ "2": "I-Algorithm",
17
+ "3": "B-Product",
18
+ "4": "B-Composition of Matter",
19
+ "5": "B-Machine",
20
+ "6": "B-Algorithm",
21
+ "7": "B-Biotechnology",
22
+ "8": "B-Process",
23
+ "9": "I-Electrical Circuit",
24
+ "10": "I-Manufacture",
25
+ "11": "B-Electrical Circuit",
26
+ "12": "O",
27
+ "13": "I-Software",
28
+ "14": "I-Composition of Matter",
29
+ "15": "I-Pharmaceutical Formulation",
30
+ "16": "I-System",
31
+ "17": "I-Hardware",
32
+ "18": "I-Biotechnology",
33
+ "19": "B-Device",
34
+ "20": "B-Pharmaceutical Formulation",
35
+ "21": "I-Product",
36
+ "22": "I-Machine",
37
+ "23": "B-Hardware",
38
+ "24": "B-System",
39
+ "25": "B-Software",
40
+ "26": "I-Device",
41
+ "27": "B-Design",
42
+ "28": "I-Design",
43
+ "29": "I-Process",
44
+ "30": "I-Chemical Compound",
45
+ "31": "B-Method of Use",
46
+ "32": "I-Apparatus",
47
+ "33": "I-Method of Use",
48
+ "34": "B-Method",
49
+ "35": "B-Manufacture",
50
+ "36": "I-Method"
51
+ },
52
+ "initializer_range": 0.02,
53
+ "label2id": {
54
+ "B-Algorithm": 6,
55
+ "B-Apparatus": 0,
56
+ "B-Biotechnology": 7,
57
+ "B-Chemical Compound": 1,
58
+ "B-Composition of Matter": 4,
59
+ "B-Design": 27,
60
+ "B-Device": 19,
61
+ "B-Electrical Circuit": 11,
62
+ "B-Hardware": 23,
63
+ "B-Machine": 5,
64
+ "B-Manufacture": 35,
65
+ "B-Method": 34,
66
+ "B-Method of Use": 31,
67
+ "B-Pharmaceutical Formulation": 20,
68
+ "B-Process": 8,
69
+ "B-Product": 3,
70
+ "B-Software": 25,
71
+ "B-System": 24,
72
+ "I-Algorithm": 2,
73
+ "I-Apparatus": 32,
74
+ "I-Biotechnology": 18,
75
+ "I-Chemical Compound": 30,
76
+ "I-Composition of Matter": 14,
77
+ "I-Design": 28,
78
+ "I-Device": 26,
79
+ "I-Electrical Circuit": 9,
80
+ "I-Hardware": 17,
81
+ "I-Machine": 22,
82
+ "I-Manufacture": 10,
83
+ "I-Method": 36,
84
+ "I-Method of Use": 33,
85
+ "I-Pharmaceutical Formulation": 15,
86
+ "I-Process": 29,
87
+ "I-Product": 21,
88
+ "I-Software": 13,
89
+ "I-System": 16,
90
+ "O": 12
91
+ },
92
+ "max_position_embeddings": 512,
93
+ "model_type": "distilbert",
94
+ "n_heads": 12,
95
+ "n_layers": 6,
96
+ "pad_token_id": 0,
97
+ "qa_dropout": 0.1,
98
+ "seq_classif_dropout": 0.2,
99
+ "sinusoidal_pos_embds": false,
100
+ "tie_weights_": true,
101
+ "torch_dtype": "float32",
102
+ "transformers_version": "4.43.1",
103
+ "vocab_size": 30522
104
+ }
checkpoint-64/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4857a393adef2bce26439838d6a4670a78da4705fd01ab4f483396354df94b43
3
+ size 265577684
checkpoint-64/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5db76f04880db5ba99dcd5a9a2d55bf94a320a5befc154cb1b9ffbdddb00cd5b
3
+ size 531216186
checkpoint-64/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2d0249207403224c7b99d38079bca3889406694e740f0bf771d1d935e8528f5
3
+ size 14244
checkpoint-64/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:babe1e1360803b9cfd2c3f6ddf50699039a80afc990dc2e2cda56aab8577fab2
3
+ size 1064
checkpoint-64/trainer_state.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 5.248876094818115,
3
+ "best_model_checkpoint": "autotrain-htyqd-ivazp/checkpoint-64",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 64,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.046875,
13
+ "grad_norm": 14.052762985229492,
14
+ "learning_rate": 1.5625e-06,
15
+ "loss": 3.6996,
16
+ "step": 3
17
+ },
18
+ {
19
+ "epoch": 0.09375,
20
+ "grad_norm": 14.165870666503906,
21
+ "learning_rate": 3.90625e-06,
22
+ "loss": 3.6546,
23
+ "step": 6
24
+ },
25
+ {
26
+ "epoch": 0.140625,
27
+ "grad_norm": 16.012378692626953,
28
+ "learning_rate": 6.25e-06,
29
+ "loss": 3.4308,
30
+ "step": 9
31
+ },
32
+ {
33
+ "epoch": 0.1875,
34
+ "grad_norm": 14.69151496887207,
35
+ "learning_rate": 8.59375e-06,
36
+ "loss": 2.9723,
37
+ "step": 12
38
+ },
39
+ {
40
+ "epoch": 0.234375,
41
+ "grad_norm": 14.49859619140625,
42
+ "learning_rate": 1.09375e-05,
43
+ "loss": 2.55,
44
+ "step": 15
45
+ },
46
+ {
47
+ "epoch": 0.28125,
48
+ "grad_norm": 9.837970733642578,
49
+ "learning_rate": 1.3281250000000001e-05,
50
+ "loss": 2.1128,
51
+ "step": 18
52
+ },
53
+ {
54
+ "epoch": 0.328125,
55
+ "grad_norm": 5.071118354797363,
56
+ "learning_rate": 1.5625e-05,
57
+ "loss": 1.6801,
58
+ "step": 21
59
+ },
60
+ {
61
+ "epoch": 0.375,
62
+ "grad_norm": 2.0291266441345215,
63
+ "learning_rate": 1.796875e-05,
64
+ "loss": 1.6157,
65
+ "step": 24
66
+ },
67
+ {
68
+ "epoch": 0.421875,
69
+ "grad_norm": 3.643156051635742,
70
+ "learning_rate": 2.0312500000000002e-05,
71
+ "loss": 1.4422,
72
+ "step": 27
73
+ },
74
+ {
75
+ "epoch": 0.46875,
76
+ "grad_norm": 2.610175609588623,
77
+ "learning_rate": 2.2656250000000002e-05,
78
+ "loss": 1.5487,
79
+ "step": 30
80
+ },
81
+ {
82
+ "epoch": 0.515625,
83
+ "grad_norm": 2.2735087871551514,
84
+ "learning_rate": 2.5e-05,
85
+ "loss": 1.5584,
86
+ "step": 33
87
+ },
88
+ {
89
+ "epoch": 0.5625,
90
+ "grad_norm": 3.6203994750976562,
91
+ "learning_rate": 2.734375e-05,
92
+ "loss": 1.4387,
93
+ "step": 36
94
+ },
95
+ {
96
+ "epoch": 0.609375,
97
+ "grad_norm": 1.6243354082107544,
98
+ "learning_rate": 2.96875e-05,
99
+ "loss": 1.4952,
100
+ "step": 39
101
+ },
102
+ {
103
+ "epoch": 0.65625,
104
+ "grad_norm": 1.4888181686401367,
105
+ "learning_rate": 3.203125e-05,
106
+ "loss": 1.3624,
107
+ "step": 42
108
+ },
109
+ {
110
+ "epoch": 0.703125,
111
+ "grad_norm": 2.144364595413208,
112
+ "learning_rate": 3.4375e-05,
113
+ "loss": 1.5163,
114
+ "step": 45
115
+ },
116
+ {
117
+ "epoch": 0.75,
118
+ "grad_norm": 1.7939876317977905,
119
+ "learning_rate": 3.671875e-05,
120
+ "loss": 1.2903,
121
+ "step": 48
122
+ },
123
+ {
124
+ "epoch": 0.796875,
125
+ "grad_norm": 1.5901564359664917,
126
+ "learning_rate": 3.90625e-05,
127
+ "loss": 1.2762,
128
+ "step": 51
129
+ },
130
+ {
131
+ "epoch": 0.84375,
132
+ "grad_norm": 1.5492233037948608,
133
+ "learning_rate": 4.140625e-05,
134
+ "loss": 1.3743,
135
+ "step": 54
136
+ },
137
+ {
138
+ "epoch": 0.890625,
139
+ "grad_norm": 1.4556649923324585,
140
+ "learning_rate": 4.375e-05,
141
+ "loss": 1.4039,
142
+ "step": 57
143
+ },
144
+ {
145
+ "epoch": 0.9375,
146
+ "grad_norm": 2.0221164226531982,
147
+ "learning_rate": 4.609375e-05,
148
+ "loss": 1.464,
149
+ "step": 60
150
+ },
151
+ {
152
+ "epoch": 0.984375,
153
+ "grad_norm": 1.9775513410568237,
154
+ "learning_rate": 4.8437500000000005e-05,
155
+ "loss": 1.385,
156
+ "step": 63
157
+ },
158
+ {
159
+ "epoch": 1.0,
160
+ "eval_accuracy": 0.0026870229007633587,
161
+ "eval_f1": 0.0,
162
+ "eval_loss": 5.248876094818115,
163
+ "eval_precision": 0.0,
164
+ "eval_recall": 0.0,
165
+ "eval_runtime": 0.4245,
166
+ "eval_samples_per_second": 327.45,
167
+ "eval_steps_per_second": 21.202,
168
+ "step": 64
169
+ }
170
+ ],
171
+ "logging_steps": 3,
172
+ "max_steps": 640,
173
+ "num_input_tokens_seen": 0,
174
+ "num_train_epochs": 10,
175
+ "save_steps": 500,
176
+ "stateful_callbacks": {
177
+ "EarlyStoppingCallback": {
178
+ "args": {
179
+ "early_stopping_patience": 5,
180
+ "early_stopping_threshold": 0.01
181
+ },
182
+ "attributes": {
183
+ "early_stopping_patience_counter": 0
184
+ }
185
+ },
186
+ "TrainerControl": {
187
+ "args": {
188
+ "should_epoch_stop": false,
189
+ "should_evaluate": false,
190
+ "should_log": false,
191
+ "should_save": true,
192
+ "should_training_stop": false
193
+ },
194
+ "attributes": {}
195
+ }
196
+ },
197
+ "total_flos": 16636128375552.0,
198
+ "train_batch_size": 8,
199
+ "trial_name": null,
200
+ "trial_params": null
201
+ }
checkpoint-64/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd376d5ea1a441ba0ffcf806601771ebe76ffc7d05b2db10990fb6072796567
3
+ size 5240
config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "elastic/distilbert-base-uncased-finetuned-conll03-english",
3
+ "_num_labels": 37,
4
+ "activation": "gelu",
5
+ "architectures": [
6
+ "DistilBertForTokenClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "dim": 768,
10
+ "dropout": 0.1,
11
+ "finetuning_task": "ner",
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "B-Apparatus",
15
+ "1": "B-Chemical Compound",
16
+ "2": "I-Algorithm",
17
+ "3": "B-Product",
18
+ "4": "B-Composition of Matter",
19
+ "5": "B-Machine",
20
+ "6": "B-Algorithm",
21
+ "7": "B-Biotechnology",
22
+ "8": "B-Process",
23
+ "9": "I-Electrical Circuit",
24
+ "10": "I-Manufacture",
25
+ "11": "B-Electrical Circuit",
26
+ "12": "O",
27
+ "13": "I-Software",
28
+ "14": "I-Composition of Matter",
29
+ "15": "I-Pharmaceutical Formulation",
30
+ "16": "I-System",
31
+ "17": "I-Hardware",
32
+ "18": "I-Biotechnology",
33
+ "19": "B-Device",
34
+ "20": "B-Pharmaceutical Formulation",
35
+ "21": "I-Product",
36
+ "22": "I-Machine",
37
+ "23": "B-Hardware",
38
+ "24": "B-System",
39
+ "25": "B-Software",
40
+ "26": "I-Device",
41
+ "27": "B-Design",
42
+ "28": "I-Design",
43
+ "29": "I-Process",
44
+ "30": "I-Chemical Compound",
45
+ "31": "B-Method of Use",
46
+ "32": "I-Apparatus",
47
+ "33": "I-Method of Use",
48
+ "34": "B-Method",
49
+ "35": "B-Manufacture",
50
+ "36": "I-Method"
51
+ },
52
+ "initializer_range": 0.02,
53
+ "label2id": {
54
+ "B-Algorithm": 6,
55
+ "B-Apparatus": 0,
56
+ "B-Biotechnology": 7,
57
+ "B-Chemical Compound": 1,
58
+ "B-Composition of Matter": 4,
59
+ "B-Design": 27,
60
+ "B-Device": 19,
61
+ "B-Electrical Circuit": 11,
62
+ "B-Hardware": 23,
63
+ "B-Machine": 5,
64
+ "B-Manufacture": 35,
65
+ "B-Method": 34,
66
+ "B-Method of Use": 31,
67
+ "B-Pharmaceutical Formulation": 20,
68
+ "B-Process": 8,
69
+ "B-Product": 3,
70
+ "B-Software": 25,
71
+ "B-System": 24,
72
+ "I-Algorithm": 2,
73
+ "I-Apparatus": 32,
74
+ "I-Biotechnology": 18,
75
+ "I-Chemical Compound": 30,
76
+ "I-Composition of Matter": 14,
77
+ "I-Design": 28,
78
+ "I-Device": 26,
79
+ "I-Electrical Circuit": 9,
80
+ "I-Hardware": 17,
81
+ "I-Machine": 22,
82
+ "I-Manufacture": 10,
83
+ "I-Method": 36,
84
+ "I-Method of Use": 33,
85
+ "I-Pharmaceutical Formulation": 15,
86
+ "I-Process": 29,
87
+ "I-Product": 21,
88
+ "I-Software": 13,
89
+ "I-System": 16,
90
+ "O": 12
91
+ },
92
+ "max_position_embeddings": 512,
93
+ "model_type": "distilbert",
94
+ "n_heads": 12,
95
+ "n_layers": 6,
96
+ "pad_token_id": 0,
97
+ "qa_dropout": 0.1,
98
+ "seq_classif_dropout": 0.2,
99
+ "sinusoidal_pos_embds": false,
100
+ "tie_weights_": true,
101
+ "torch_dtype": "float32",
102
+ "transformers_version": "4.43.1",
103
+ "vocab_size": 30522
104
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4857a393adef2bce26439838d6a4670a78da4705fd01ab4f483396354df94b43
3
+ size 265577684
runs/Jul25_06-39-01_r-bikashpatra-argilla-ds-train-mpij26va-36565-x6bgo/events.out.tfevents.1721889541.r-bikashpatra-argilla-ds-train-mpij26va-36565-x6bgo.66.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7c074b50a4c1b3a6d7e19855ddf3cc96a104e0bee727487d85e33e9538e07c1
3
- size 6847
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e22546c5dc303e94fefa15fd0f02bdb6990c7abdab7b3fdd2fefc01b5bde83a7
3
+ size 36864
runs/Jul25_06-39-01_r-bikashpatra-argilla-ds-train-mpij26va-36565-x6bgo/events.out.tfevents.1721889567.r-bikashpatra-argilla-ds-train-mpij26va-36565-x6bgo.66.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16fc822f54e9b992286ebf1fe3c3d2ac357d2319eb581c12f468fbcb79279dcb
3
+ size 560
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd376d5ea1a441ba0ffcf806601771ebe76ffc7d05b2db10990fb6072796567
3
+ size 5240
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "bikashpatra/claims_token_classification",
3
+ "model": "elastic/distilbert-base-uncased-finetuned-conll03-english",
4
+ "lr": 5e-05,
5
+ "epochs": 10,
6
+ "max_seq_length": 128,
7
+ "batch_size": 8,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 1,
10
+ "optimizer": "adamw_torch",
11
+ "scheduler": "linear",
12
+ "weight_decay": 0.0,
13
+ "max_grad_norm": 1.0,
14
+ "seed": 42,
15
+ "train_split": "train",
16
+ "valid_split": "validation",
17
+ "tokens_column": "tokens",
18
+ "tags_column": "ner_tags",
19
+ "logging_steps": -1,
20
+ "project_name": "autotrain-htyqd-ivazp",
21
+ "auto_find_batch_size": false,
22
+ "mixed_precision": "fp16",
23
+ "save_total_limit": 1,
24
+ "push_to_hub": true,
25
+ "eval_strategy": "epoch",
26
+ "username": "bikashpatra",
27
+ "log": "tensorboard",
28
+ "early_stopping_patience": 5,
29
+ "early_stopping_threshold": 0.01
30
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff