Hugging Face's logo

SushantGautam
/
KG-LLM-roberta-base-single_stage

Text Classification
Transformers
Safetensors
roberta
Inference Endpoints
Model card Files Community
SushantGautam commited on
Commit
3cc1736
•
1 Parent(s): e5847d8

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +28 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +216 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.41.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aac80ed6c74c84ca05b9ddac1caf8758f1284bfa8a2f18ebe675d1e134c2678d
3
+ size 498612824
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d536302016ae761d0976e85cdbff94ebd022c57b644de4555bd9fffe5df4b5ef
3
+ size 997345530
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6ec344beebd3f72596ac1cac307e4af951e151964e2c2ed5c0c0d3e22762db
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5914f60cf2d686482bfa02d3deefa784e933d1f165f7d2c4559485cf8b26e86b
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6626126766204834,
3
+ "best_model_checkpoint": "./results/roberta-base/checkpoint-8097",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 16194,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 2.618255853652954,
14
+ "learning_rate": 4.672437244961049e-05,
15
+ "loss": 0.3464,
16
+ "step": 2699
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7697120458314488,
21
+ "eval_conf_mat": [
22
+ [
23
+ 6318,
24
+ 522
25
+ ],
26
+ [
27
+ 2533,
28
+ 3893
29
+ ]
30
+ ],
31
+ "eval_f1": 0.7181994280970391,
32
+ "eval_loss": 0.7109997272491455,
33
+ "eval_precision": 0.8817667044167611,
34
+ "eval_recall": 0.6058201058201058,
35
+ "eval_runtime": 31.5248,
36
+ "eval_samples_per_second": 420.812,
37
+ "eval_steps_per_second": 13.164,
38
+ "step": 2699
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "grad_norm": 30.145366668701172,
43
+ "learning_rate": 4.338691727463831e-05,
44
+ "loss": 0.1889,
45
+ "step": 5398
46
+ },
47
+ {
48
+ "epoch": 2.0,
49
+ "eval_accuracy": 0.8014473089099955,
50
+ "eval_conf_mat": [
51
+ [
52
+ 6207,
53
+ 633
54
+ ],
55
+ [
56
+ 2001,
57
+ 4425
58
+ ]
59
+ ],
60
+ "eval_f1": 0.7706374085684431,
61
+ "eval_loss": 0.8169035911560059,
62
+ "eval_precision": 0.8748517200474496,
63
+ "eval_recall": 0.688608776844071,
64
+ "eval_runtime": 31.2094,
65
+ "eval_samples_per_second": 425.065,
66
+ "eval_steps_per_second": 13.297,
67
+ "step": 5398
68
+ },
69
+ {
70
+ "epoch": 3.0,
71
+ "grad_norm": 11.833324432373047,
72
+ "learning_rate": 4.004946209966614e-05,
73
+ "loss": 0.1456,
74
+ "step": 8097
75
+ },
76
+ {
77
+ "epoch": 3.0,
78
+ "eval_accuracy": 0.818407960199005,
79
+ "eval_conf_mat": [
80
+ [
81
+ 6207,
82
+ 633
83
+ ],
84
+ [
85
+ 1776,
86
+ 4650
87
+ ]
88
+ ],
89
+ "eval_f1": 0.7942608250064054,
90
+ "eval_loss": 0.6626126766204834,
91
+ "eval_precision": 0.8801817149346962,
92
+ "eval_recall": 0.7236227824463118,
93
+ "eval_runtime": 31.2622,
94
+ "eval_samples_per_second": 424.346,
95
+ "eval_steps_per_second": 13.275,
96
+ "step": 8097
97
+ },
98
+ {
99
+ "epoch": 4.0,
100
+ "grad_norm": 16.268821716308594,
101
+ "learning_rate": 3.6712006924693956e-05,
102
+ "loss": 0.1181,
103
+ "step": 10796
104
+ },
105
+ {
106
+ "epoch": 4.0,
107
+ "eval_accuracy": 0.7795115332428765,
108
+ "eval_conf_mat": [
109
+ [
110
+ 6320,
111
+ 520
112
+ ],
113
+ [
114
+ 2405,
115
+ 4021
116
+ ]
117
+ ],
118
+ "eval_f1": 0.7332907814352148,
119
+ "eval_loss": 1.1288779973983765,
120
+ "eval_precision": 0.885487778022462,
121
+ "eval_recall": 0.6257391845627139,
122
+ "eval_runtime": 31.3467,
123
+ "eval_samples_per_second": 423.202,
124
+ "eval_steps_per_second": 13.239,
125
+ "step": 10796
126
+ },
127
+ {
128
+ "epoch": 5.0,
129
+ "grad_norm": 152.2488555908203,
130
+ "learning_rate": 3.337455174972178e-05,
131
+ "loss": 0.0985,
132
+ "step": 13495
133
+ },
134
+ {
135
+ "epoch": 5.0,
136
+ "eval_accuracy": 0.7281772953414745,
137
+ "eval_conf_mat": [
138
+ [
139
+ 6390,
140
+ 450
141
+ ],
142
+ [
143
+ 3156,
144
+ 3270
145
+ ]
146
+ ],
147
+ "eval_f1": 0.644589000591366,
148
+ "eval_loss": 1.4766658544540405,
149
+ "eval_precision": 0.8790322580645161,
150
+ "eval_recall": 0.5088702147525677,
151
+ "eval_runtime": 31.2848,
152
+ "eval_samples_per_second": 424.039,
153
+ "eval_steps_per_second": 13.265,
154
+ "step": 13495
155
+ },
156
+ {
157
+ "epoch": 6.0,
158
+ "grad_norm": 0.3119850754737854,
159
+ "learning_rate": 3.0037096574749602e-05,
160
+ "loss": 0.0771,
161
+ "step": 16194
162
+ },
163
+ {
164
+ "epoch": 6.0,
165
+ "eval_accuracy": 0.7473239861299563,
166
+ "eval_conf_mat": [
167
+ [
168
+ 6387,
169
+ 453
170
+ ],
171
+ [
172
+ 2899,
173
+ 3527
174
+ ]
175
+ ],
176
+ "eval_f1": 0.6778781472227561,
177
+ "eval_loss": 1.5410542488098145,
178
+ "eval_precision": 0.8861809045226131,
179
+ "eval_recall": 0.5488639900404606,
180
+ "eval_runtime": 31.3637,
181
+ "eval_samples_per_second": 422.973,
182
+ "eval_steps_per_second": 13.232,
183
+ "step": 16194
184
+ }
185
+ ],
186
+ "logging_steps": 500,
187
+ "max_steps": 40485,
188
+ "num_input_tokens_seen": 0,
189
+ "num_train_epochs": 15,
190
+ "save_steps": 500,
191
+ "stateful_callbacks": {
192
+ "EarlyStoppingCallback": {
193
+ "args": {
194
+ "early_stopping_patience": 3,
195
+ "early_stopping_threshold": 0.0
196
+ },
197
+ "attributes": {
198
+ "early_stopping_patience_counter": 0
199
+ }
200
+ },
201
+ "TrainerControl": {
202
+ "args": {
203
+ "should_epoch_stop": false,
204
+ "should_evaluate": false,
205
+ "should_log": false,
206
+ "should_save": true,
207
+ "should_training_stop": true
208
+ },
209
+ "attributes": {}
210
+ }
211
+ },
212
+ "total_flos": 4.229063080284522e+16,
213
+ "train_batch_size": 32,
214
+ "trial_name": null,
215
+ "trial_params": null
216
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14e8df44da40a7895b92693123aa030c4f1819f7dc4c7dad27e89fda37eee16f
3
+ size 5048