bikashpatra commited on
Commit
9a0ac90
1 Parent(s): 9d14826

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: FacebookAI/roberta-large
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: 5.475988388061523
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 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/roberta-large",
3
+ "_num_labels": 37,
4
+ "architectures": [
5
+ "RobertaForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "B-Apparatus",
16
+ "1": "B-Chemical Compound",
17
+ "2": "I-Algorithm",
18
+ "3": "B-Product",
19
+ "4": "B-Composition of Matter",
20
+ "5": "B-Machine",
21
+ "6": "B-Algorithm",
22
+ "7": "B-Biotechnology",
23
+ "8": "B-Process",
24
+ "9": "I-Electrical Circuit",
25
+ "10": "I-Manufacture",
26
+ "11": "B-Electrical Circuit",
27
+ "12": "O",
28
+ "13": "I-Software",
29
+ "14": "I-Composition of Matter",
30
+ "15": "I-Pharmaceutical Formulation",
31
+ "16": "I-System",
32
+ "17": "I-Hardware",
33
+ "18": "I-Biotechnology",
34
+ "19": "B-Device",
35
+ "20": "B-Pharmaceutical Formulation",
36
+ "21": "I-Product",
37
+ "22": "I-Machine",
38
+ "23": "B-Hardware",
39
+ "24": "B-System",
40
+ "25": "B-Software",
41
+ "26": "I-Device",
42
+ "27": "B-Design",
43
+ "28": "I-Design",
44
+ "29": "I-Process",
45
+ "30": "I-Chemical Compound",
46
+ "31": "B-Method of Use",
47
+ "32": "I-Apparatus",
48
+ "33": "I-Method of Use",
49
+ "34": "B-Method",
50
+ "35": "B-Manufacture",
51
+ "36": "I-Method"
52
+ },
53
+ "initializer_range": 0.02,
54
+ "intermediate_size": 4096,
55
+ "label2id": {
56
+ "B-Algorithm": 6,
57
+ "B-Apparatus": 0,
58
+ "B-Biotechnology": 7,
59
+ "B-Chemical Compound": 1,
60
+ "B-Composition of Matter": 4,
61
+ "B-Design": 27,
62
+ "B-Device": 19,
63
+ "B-Electrical Circuit": 11,
64
+ "B-Hardware": 23,
65
+ "B-Machine": 5,
66
+ "B-Manufacture": 35,
67
+ "B-Method": 34,
68
+ "B-Method of Use": 31,
69
+ "B-Pharmaceutical Formulation": 20,
70
+ "B-Process": 8,
71
+ "B-Product": 3,
72
+ "B-Software": 25,
73
+ "B-System": 24,
74
+ "I-Algorithm": 2,
75
+ "I-Apparatus": 32,
76
+ "I-Biotechnology": 18,
77
+ "I-Chemical Compound": 30,
78
+ "I-Composition of Matter": 14,
79
+ "I-Design": 28,
80
+ "I-Device": 26,
81
+ "I-Electrical Circuit": 9,
82
+ "I-Hardware": 17,
83
+ "I-Machine": 22,
84
+ "I-Manufacture": 10,
85
+ "I-Method": 36,
86
+ "I-Method of Use": 33,
87
+ "I-Pharmaceutical Formulation": 15,
88
+ "I-Process": 29,
89
+ "I-Product": 21,
90
+ "I-Software": 13,
91
+ "I-System": 16,
92
+ "O": 12
93
+ },
94
+ "layer_norm_eps": 1e-05,
95
+ "max_position_embeddings": 514,
96
+ "model_type": "roberta",
97
+ "num_attention_heads": 16,
98
+ "num_hidden_layers": 24,
99
+ "pad_token_id": 1,
100
+ "position_embedding_type": "absolute",
101
+ "torch_dtype": "float32",
102
+ "transformers_version": "4.43.1",
103
+ "type_vocab_size": 1,
104
+ "use_cache": true,
105
+ "vocab_size": 50265
106
+ }
checkpoint-64/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2999897b68b4283640d2b12972ef9a3769c18b37d945eb006b115ec3bb6f161
3
+ size 1417440300
checkpoint-64/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f9ef2ff26e0e0ba4af38a93f2c4a110684fe2d6019a65e85b06b1e741d19d2e
3
+ size 2835111719
checkpoint-64/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b63b5ac2d0af70d8e4802996fee5151faa35a74e5f6c6f13db05945a2c154a0d
3
+ size 14244
checkpoint-64/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f652a94aafc900788fa1911a5495f00aa5cf7737ca6e1ed230b247ee0dc78bba
3
+ size 1064
checkpoint-64/trainer_state.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 5.475988388061523,
3
+ "best_model_checkpoint": "autotrain-g10wr-ryb7t/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": Infinity,
14
+ "learning_rate": 0.0,
15
+ "loss": 3.8675,
16
+ "step": 3
17
+ },
18
+ {
19
+ "epoch": 0.09375,
20
+ "grad_norm": 26.64595603942871,
21
+ "learning_rate": 7.8125e-07,
22
+ "loss": 3.8727,
23
+ "step": 6
24
+ },
25
+ {
26
+ "epoch": 0.140625,
27
+ "grad_norm": 28.351032257080078,
28
+ "learning_rate": 3.125e-06,
29
+ "loss": 3.8738,
30
+ "step": 9
31
+ },
32
+ {
33
+ "epoch": 0.1875,
34
+ "grad_norm": 30.790821075439453,
35
+ "learning_rate": 5.46875e-06,
36
+ "loss": 3.6174,
37
+ "step": 12
38
+ },
39
+ {
40
+ "epoch": 0.234375,
41
+ "grad_norm": 30.02513885498047,
42
+ "learning_rate": 7.8125e-06,
43
+ "loss": 2.5911,
44
+ "step": 15
45
+ },
46
+ {
47
+ "epoch": 0.28125,
48
+ "grad_norm": 16.17921257019043,
49
+ "learning_rate": 1.0156250000000001e-05,
50
+ "loss": 1.8417,
51
+ "step": 18
52
+ },
53
+ {
54
+ "epoch": 0.328125,
55
+ "grad_norm": 20.254079818725586,
56
+ "learning_rate": 1.25e-05,
57
+ "loss": 1.5405,
58
+ "step": 21
59
+ },
60
+ {
61
+ "epoch": 0.375,
62
+ "grad_norm": 6.887765884399414,
63
+ "learning_rate": 1.484375e-05,
64
+ "loss": 1.5088,
65
+ "step": 24
66
+ },
67
+ {
68
+ "epoch": 0.421875,
69
+ "grad_norm": 10.511013984680176,
70
+ "learning_rate": 1.71875e-05,
71
+ "loss": 1.3341,
72
+ "step": 27
73
+ },
74
+ {
75
+ "epoch": 0.46875,
76
+ "grad_norm": 12.581910133361816,
77
+ "learning_rate": 1.953125e-05,
78
+ "loss": 1.4883,
79
+ "step": 30
80
+ },
81
+ {
82
+ "epoch": 0.515625,
83
+ "grad_norm": 5.822439670562744,
84
+ "learning_rate": 2.1875e-05,
85
+ "loss": 1.5237,
86
+ "step": 33
87
+ },
88
+ {
89
+ "epoch": 0.5625,
90
+ "grad_norm": 9.540604591369629,
91
+ "learning_rate": 2.4218750000000003e-05,
92
+ "loss": 1.4182,
93
+ "step": 36
94
+ },
95
+ {
96
+ "epoch": 0.609375,
97
+ "grad_norm": 3.624293804168701,
98
+ "learning_rate": 2.6562500000000002e-05,
99
+ "loss": 1.5184,
100
+ "step": 39
101
+ },
102
+ {
103
+ "epoch": 0.65625,
104
+ "grad_norm": 6.4345221519470215,
105
+ "learning_rate": 2.890625e-05,
106
+ "loss": 1.3708,
107
+ "step": 42
108
+ },
109
+ {
110
+ "epoch": 0.703125,
111
+ "grad_norm": 4.039494514465332,
112
+ "learning_rate": 3.125e-05,
113
+ "loss": 1.5398,
114
+ "step": 45
115
+ },
116
+ {
117
+ "epoch": 0.75,
118
+ "grad_norm": 8.686318397521973,
119
+ "learning_rate": 3.359375e-05,
120
+ "loss": 1.3794,
121
+ "step": 48
122
+ },
123
+ {
124
+ "epoch": 0.796875,
125
+ "grad_norm": 5.242523193359375,
126
+ "learning_rate": 3.59375e-05,
127
+ "loss": 1.3477,
128
+ "step": 51
129
+ },
130
+ {
131
+ "epoch": 0.84375,
132
+ "grad_norm": 2.8347246646881104,
133
+ "learning_rate": 3.828125e-05,
134
+ "loss": 1.4509,
135
+ "step": 54
136
+ },
137
+ {
138
+ "epoch": 0.890625,
139
+ "grad_norm": 3.3037731647491455,
140
+ "learning_rate": 4.0625000000000005e-05,
141
+ "loss": 1.4429,
142
+ "step": 57
143
+ },
144
+ {
145
+ "epoch": 0.9375,
146
+ "grad_norm": 3.0450754165649414,
147
+ "learning_rate": 4.2968750000000004e-05,
148
+ "loss": 1.5172,
149
+ "step": 60
150
+ },
151
+ {
152
+ "epoch": 0.984375,
153
+ "grad_norm": 3.5716280937194824,
154
+ "learning_rate": 4.5312500000000004e-05,
155
+ "loss": 1.3965,
156
+ "step": 63
157
+ },
158
+ {
159
+ "epoch": 1.0,
160
+ "eval_accuracy": 0.0026870229007633587,
161
+ "eval_f1": 0.0,
162
+ "eval_loss": 5.475988388061523,
163
+ "eval_precision": 0.0,
164
+ "eval_recall": 0.0,
165
+ "eval_runtime": 0.7114,
166
+ "eval_samples_per_second": 195.393,
167
+ "eval_steps_per_second": 12.651,
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": 118191988716288.0,
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:fa8bfec92782685207af4b6824eac055a4cb35f3ea39b7b06aaf3db1cee238e7
3
+ size 5240
config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/roberta-large",
3
+ "_num_labels": 37,
4
+ "architectures": [
5
+ "RobertaForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "B-Apparatus",
16
+ "1": "B-Chemical Compound",
17
+ "2": "I-Algorithm",
18
+ "3": "B-Product",
19
+ "4": "B-Composition of Matter",
20
+ "5": "B-Machine",
21
+ "6": "B-Algorithm",
22
+ "7": "B-Biotechnology",
23
+ "8": "B-Process",
24
+ "9": "I-Electrical Circuit",
25
+ "10": "I-Manufacture",
26
+ "11": "B-Electrical Circuit",
27
+ "12": "O",
28
+ "13": "I-Software",
29
+ "14": "I-Composition of Matter",
30
+ "15": "I-Pharmaceutical Formulation",
31
+ "16": "I-System",
32
+ "17": "I-Hardware",
33
+ "18": "I-Biotechnology",
34
+ "19": "B-Device",
35
+ "20": "B-Pharmaceutical Formulation",
36
+ "21": "I-Product",
37
+ "22": "I-Machine",
38
+ "23": "B-Hardware",
39
+ "24": "B-System",
40
+ "25": "B-Software",
41
+ "26": "I-Device",
42
+ "27": "B-Design",
43
+ "28": "I-Design",
44
+ "29": "I-Process",
45
+ "30": "I-Chemical Compound",
46
+ "31": "B-Method of Use",
47
+ "32": "I-Apparatus",
48
+ "33": "I-Method of Use",
49
+ "34": "B-Method",
50
+ "35": "B-Manufacture",
51
+ "36": "I-Method"
52
+ },
53
+ "initializer_range": 0.02,
54
+ "intermediate_size": 4096,
55
+ "label2id": {
56
+ "B-Algorithm": 6,
57
+ "B-Apparatus": 0,
58
+ "B-Biotechnology": 7,
59
+ "B-Chemical Compound": 1,
60
+ "B-Composition of Matter": 4,
61
+ "B-Design": 27,
62
+ "B-Device": 19,
63
+ "B-Electrical Circuit": 11,
64
+ "B-Hardware": 23,
65
+ "B-Machine": 5,
66
+ "B-Manufacture": 35,
67
+ "B-Method": 34,
68
+ "B-Method of Use": 31,
69
+ "B-Pharmaceutical Formulation": 20,
70
+ "B-Process": 8,
71
+ "B-Product": 3,
72
+ "B-Software": 25,
73
+ "B-System": 24,
74
+ "I-Algorithm": 2,
75
+ "I-Apparatus": 32,
76
+ "I-Biotechnology": 18,
77
+ "I-Chemical Compound": 30,
78
+ "I-Composition of Matter": 14,
79
+ "I-Design": 28,
80
+ "I-Device": 26,
81
+ "I-Electrical Circuit": 9,
82
+ "I-Hardware": 17,
83
+ "I-Machine": 22,
84
+ "I-Manufacture": 10,
85
+ "I-Method": 36,
86
+ "I-Method of Use": 33,
87
+ "I-Pharmaceutical Formulation": 15,
88
+ "I-Process": 29,
89
+ "I-Product": 21,
90
+ "I-Software": 13,
91
+ "I-System": 16,
92
+ "O": 12
93
+ },
94
+ "layer_norm_eps": 1e-05,
95
+ "max_position_embeddings": 514,
96
+ "model_type": "roberta",
97
+ "num_attention_heads": 16,
98
+ "num_hidden_layers": 24,
99
+ "pad_token_id": 1,
100
+ "position_embedding_type": "absolute",
101
+ "torch_dtype": "float32",
102
+ "transformers_version": "4.43.1",
103
+ "type_vocab_size": 1,
104
+ "use_cache": true,
105
+ "vocab_size": 50265
106
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2999897b68b4283640d2b12972ef9a3769c18b37d945eb006b115ec3bb6f161
3
+ size 1417440300
runs/Jul25_06-13-13_r-bikashpatra-argilla-ds-train-9yweanj5-9f6a6-ri0c1/events.out.tfevents.1721887993.r-bikashpatra-argilla-ds-train-9yweanj5-9f6a6-ri0c1.78.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a457914027326d7b246edc4194cd481e02dfbaed448105cfee83457fcd53f84
3
- size 6907
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2b25cf7b2c15ec97d0465637dcde5f3cc408ffccb3a7ca29dd809f6ad9cd38e
3
+ size 36924
runs/Jul25_06-13-13_r-bikashpatra-argilla-ds-train-9yweanj5-9f6a6-ri0c1/events.out.tfevents.1721888137.r-bikashpatra-argilla-ds-train-9yweanj5-9f6a6-ri0c1.78.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e1b05cfe492d3906769b6f77b2f9e13edcd35ba9da3abde7ea3a295e90e55b9
3
+ size 560
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": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
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
+ "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": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
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:fa8bfec92782685207af4b6824eac055a4cb35f3ea39b7b06aaf3db1cee238e7
3
+ size 5240
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "bikashpatra/claims_token_classification",
3
+ "model": "FacebookAI/roberta-large",
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-g10wr-ryb7t",
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.json ADDED
The diff for this file is too large to render. See raw diff