Upload folder using huggingface_hub
Browse files- README.md +26 -0
- checkpoint-360/config.json +38 -0
- checkpoint-360/model.safetensors +3 -0
- checkpoint-360/optimizer.pt +3 -0
- checkpoint-360/rng_state.pth +3 -0
- checkpoint-360/scheduler.pt +3 -0
- checkpoint-360/trainer_state.json +501 -0
- checkpoint-360/training_args.bin +3 -0
- config.json +38 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Sep05_14-27-13_r-jjonas313-autotrain-ecb-uncertainy-zjc3cpem-d400c-3ytpc/events.out.tfevents.1725546434.r-jjonas313-autotrain-ecb-uncertainy-zjc3cpem-d400c-3ytpc.173.0 +2 -2
- runs/Sep05_14-27-13_r-jjonas313-autotrain-ecb-uncertainy-zjc3cpem-d400c-3ytpc/events.out.tfevents.1725546462.r-jjonas313-autotrain-ecb-uncertainy-zjc3cpem-d400c-3ytpc.173.1 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +61 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
base_model: mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Text Classification
|
14 |
+
|
15 |
+
## Validation Metrics
|
16 |
+
loss: 0.5102422833442688
|
17 |
+
|
18 |
+
f1: 0.6812227074235808
|
19 |
+
|
20 |
+
precision: 0.7428571428571429
|
21 |
+
|
22 |
+
recall: 0.6290322580645161
|
23 |
+
|
24 |
+
auc: 0.8403134164222874
|
25 |
+
|
26 |
+
accuracy: 0.7566666666666667
|
checkpoint-360/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "certain",
|
17 |
+
"1": "uncertain"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"certain": 0,
|
23 |
+
"uncertain": 1
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-05,
|
26 |
+
"max_position_embeddings": 514,
|
27 |
+
"model_type": "roberta",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 6,
|
30 |
+
"pad_token_id": 1,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.44.2",
|
35 |
+
"type_vocab_size": 1,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 50265
|
38 |
+
}
|
checkpoint-360/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b5734d128607df3920742efde94ba3cade3bef8e2ff341916598130c9aebabf
|
3 |
+
size 328492280
|
checkpoint-360/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbfdace913d24ca62b71f8bb606fa7c3069f2860b3afa357f67715edb5d89117
|
3 |
+
size 657047610
|
checkpoint-360/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e820c65277cffce765ff84bde20d377e481f7c40812ee2a5fdca1812061ddb12
|
3 |
+
size 14244
|
checkpoint-360/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbc971bef006065ac0cab9b0c2e7a9e24df62917419cd720c3a0a049bae36498
|
3 |
+
size 1064
|
checkpoint-360/trainer_state.json
ADDED
@@ -0,0 +1,501 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5102422833442688,
|
3 |
+
"best_model_checkpoint": "autotrain-ecb-uncertainty-financial-news-sentiment/checkpoint-360",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 360,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.05,
|
13 |
+
"grad_norm": 5.164536952972412,
|
14 |
+
"learning_rate": 1.6666666666666667e-06,
|
15 |
+
"loss": 0.7216,
|
16 |
+
"step": 6
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.1,
|
20 |
+
"grad_norm": 5.856216907501221,
|
21 |
+
"learning_rate": 3.3333333333333333e-06,
|
22 |
+
"loss": 0.7277,
|
23 |
+
"step": 12
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.15,
|
27 |
+
"grad_norm": 5.976062297821045,
|
28 |
+
"learning_rate": 5e-06,
|
29 |
+
"loss": 0.6939,
|
30 |
+
"step": 18
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.2,
|
34 |
+
"grad_norm": 4.827513217926025,
|
35 |
+
"learning_rate": 6.666666666666667e-06,
|
36 |
+
"loss": 0.7034,
|
37 |
+
"step": 24
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.25,
|
41 |
+
"grad_norm": Infinity,
|
42 |
+
"learning_rate": 8.055555555555557e-06,
|
43 |
+
"loss": 0.7007,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3,
|
48 |
+
"grad_norm": 8.159554481506348,
|
49 |
+
"learning_rate": 9.722222222222223e-06,
|
50 |
+
"loss": 0.6476,
|
51 |
+
"step": 36
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.35,
|
55 |
+
"grad_norm": Infinity,
|
56 |
+
"learning_rate": 9.876543209876543e-06,
|
57 |
+
"loss": 0.6142,
|
58 |
+
"step": 42
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.4,
|
62 |
+
"grad_norm": 6.176295757293701,
|
63 |
+
"learning_rate": 9.691358024691358e-06,
|
64 |
+
"loss": 0.6683,
|
65 |
+
"step": 48
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.45,
|
69 |
+
"grad_norm": 11.041110038757324,
|
70 |
+
"learning_rate": 9.506172839506174e-06,
|
71 |
+
"loss": 0.6681,
|
72 |
+
"step": 54
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.5,
|
76 |
+
"grad_norm": 17.113492965698242,
|
77 |
+
"learning_rate": 9.320987654320989e-06,
|
78 |
+
"loss": 0.6375,
|
79 |
+
"step": 60
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.55,
|
83 |
+
"grad_norm": 7.319600582122803,
|
84 |
+
"learning_rate": 9.135802469135803e-06,
|
85 |
+
"loss": 0.5779,
|
86 |
+
"step": 66
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.6,
|
90 |
+
"grad_norm": 5.999816417694092,
|
91 |
+
"learning_rate": 8.950617283950618e-06,
|
92 |
+
"loss": 0.719,
|
93 |
+
"step": 72
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.65,
|
97 |
+
"grad_norm": 4.986242294311523,
|
98 |
+
"learning_rate": 8.765432098765432e-06,
|
99 |
+
"loss": 0.5776,
|
100 |
+
"step": 78
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.7,
|
104 |
+
"grad_norm": 6.471978664398193,
|
105 |
+
"learning_rate": 8.580246913580249e-06,
|
106 |
+
"loss": 0.6491,
|
107 |
+
"step": 84
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.75,
|
111 |
+
"grad_norm": 11.35699462890625,
|
112 |
+
"learning_rate": 8.395061728395062e-06,
|
113 |
+
"loss": 0.6184,
|
114 |
+
"step": 90
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.8,
|
118 |
+
"grad_norm": 7.669732570648193,
|
119 |
+
"learning_rate": 8.209876543209876e-06,
|
120 |
+
"loss": 0.6171,
|
121 |
+
"step": 96
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.85,
|
125 |
+
"grad_norm": 10.464934349060059,
|
126 |
+
"learning_rate": 8.024691358024692e-06,
|
127 |
+
"loss": 0.6059,
|
128 |
+
"step": 102
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.9,
|
132 |
+
"grad_norm": 4.58441686630249,
|
133 |
+
"learning_rate": 7.839506172839507e-06,
|
134 |
+
"loss": 0.5623,
|
135 |
+
"step": 108
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.95,
|
139 |
+
"grad_norm": 14.604641914367676,
|
140 |
+
"learning_rate": 7.654320987654322e-06,
|
141 |
+
"loss": 0.5632,
|
142 |
+
"step": 114
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.0,
|
146 |
+
"grad_norm": 5.632209300994873,
|
147 |
+
"learning_rate": 7.469135802469136e-06,
|
148 |
+
"loss": 0.5354,
|
149 |
+
"step": 120
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.0,
|
153 |
+
"eval_accuracy": 0.7,
|
154 |
+
"eval_auc": 0.7775843108504399,
|
155 |
+
"eval_f1": 0.6370967741935484,
|
156 |
+
"eval_loss": 0.5604915618896484,
|
157 |
+
"eval_precision": 0.6370967741935484,
|
158 |
+
"eval_recall": 0.6370967741935484,
|
159 |
+
"eval_runtime": 0.4337,
|
160 |
+
"eval_samples_per_second": 691.658,
|
161 |
+
"eval_steps_per_second": 34.583,
|
162 |
+
"step": 120
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 1.05,
|
166 |
+
"grad_norm": 5.2904229164123535,
|
167 |
+
"learning_rate": 7.283950617283952e-06,
|
168 |
+
"loss": 0.5369,
|
169 |
+
"step": 126
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 1.1,
|
173 |
+
"grad_norm": 5.897068500518799,
|
174 |
+
"learning_rate": 7.098765432098766e-06,
|
175 |
+
"loss": 0.5229,
|
176 |
+
"step": 132
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.15,
|
180 |
+
"grad_norm": 12.380674362182617,
|
181 |
+
"learning_rate": 6.913580246913581e-06,
|
182 |
+
"loss": 0.5339,
|
183 |
+
"step": 138
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 1.2,
|
187 |
+
"grad_norm": 8.4592924118042,
|
188 |
+
"learning_rate": 6.728395061728395e-06,
|
189 |
+
"loss": 0.4996,
|
190 |
+
"step": 144
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 1.25,
|
194 |
+
"grad_norm": 21.180438995361328,
|
195 |
+
"learning_rate": 6.543209876543211e-06,
|
196 |
+
"loss": 0.5274,
|
197 |
+
"step": 150
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.3,
|
201 |
+
"grad_norm": 15.163029670715332,
|
202 |
+
"learning_rate": 6.358024691358025e-06,
|
203 |
+
"loss": 0.54,
|
204 |
+
"step": 156
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 1.35,
|
208 |
+
"grad_norm": 21.411739349365234,
|
209 |
+
"learning_rate": 6.17283950617284e-06,
|
210 |
+
"loss": 0.5242,
|
211 |
+
"step": 162
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 1.4,
|
215 |
+
"grad_norm": 12.492610931396484,
|
216 |
+
"learning_rate": 6.018518518518519e-06,
|
217 |
+
"loss": 0.4742,
|
218 |
+
"step": 168
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.45,
|
222 |
+
"grad_norm": 13.228275299072266,
|
223 |
+
"learning_rate": 5.833333333333334e-06,
|
224 |
+
"loss": 0.632,
|
225 |
+
"step": 174
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 1.5,
|
229 |
+
"grad_norm": 9.77871036529541,
|
230 |
+
"learning_rate": 5.6481481481481485e-06,
|
231 |
+
"loss": 0.4448,
|
232 |
+
"step": 180
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 1.55,
|
236 |
+
"grad_norm": 12.018665313720703,
|
237 |
+
"learning_rate": 5.462962962962963e-06,
|
238 |
+
"loss": 0.4488,
|
239 |
+
"step": 186
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.6,
|
243 |
+
"grad_norm": 6.660854339599609,
|
244 |
+
"learning_rate": 5.2777777777777785e-06,
|
245 |
+
"loss": 0.5037,
|
246 |
+
"step": 192
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 1.65,
|
250 |
+
"grad_norm": 16.42615509033203,
|
251 |
+
"learning_rate": 5.092592592592593e-06,
|
252 |
+
"loss": 0.4555,
|
253 |
+
"step": 198
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 1.7,
|
257 |
+
"grad_norm": 31.713699340820312,
|
258 |
+
"learning_rate": 4.907407407407408e-06,
|
259 |
+
"loss": 0.5626,
|
260 |
+
"step": 204
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.75,
|
264 |
+
"grad_norm": 10.685063362121582,
|
265 |
+
"learning_rate": 4.722222222222222e-06,
|
266 |
+
"loss": 0.4936,
|
267 |
+
"step": 210
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 1.8,
|
271 |
+
"grad_norm": 4.968717575073242,
|
272 |
+
"learning_rate": 4.537037037037038e-06,
|
273 |
+
"loss": 0.4902,
|
274 |
+
"step": 216
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 1.85,
|
278 |
+
"grad_norm": 9.011704444885254,
|
279 |
+
"learning_rate": 4.351851851851852e-06,
|
280 |
+
"loss": 0.4297,
|
281 |
+
"step": 222
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.9,
|
285 |
+
"grad_norm": 7.851383686065674,
|
286 |
+
"learning_rate": 4.166666666666667e-06,
|
287 |
+
"loss": 0.5542,
|
288 |
+
"step": 228
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 1.95,
|
292 |
+
"grad_norm": 26.625791549682617,
|
293 |
+
"learning_rate": 3.9814814814814814e-06,
|
294 |
+
"loss": 0.5122,
|
295 |
+
"step": 234
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 2.0,
|
299 |
+
"grad_norm": 12.834867477416992,
|
300 |
+
"learning_rate": 3.796296296296297e-06,
|
301 |
+
"loss": 0.4312,
|
302 |
+
"step": 240
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 2.0,
|
306 |
+
"eval_accuracy": 0.7433333333333333,
|
307 |
+
"eval_auc": 0.8314699413489737,
|
308 |
+
"eval_f1": 0.6280193236714976,
|
309 |
+
"eval_loss": 0.5365661382675171,
|
310 |
+
"eval_precision": 0.7831325301204819,
|
311 |
+
"eval_recall": 0.5241935483870968,
|
312 |
+
"eval_runtime": 0.4308,
|
313 |
+
"eval_samples_per_second": 696.341,
|
314 |
+
"eval_steps_per_second": 34.817,
|
315 |
+
"step": 240
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 2.05,
|
319 |
+
"grad_norm": 22.944910049438477,
|
320 |
+
"learning_rate": 3.6111111111111115e-06,
|
321 |
+
"loss": 0.3966,
|
322 |
+
"step": 246
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 2.1,
|
326 |
+
"grad_norm": 30.294570922851562,
|
327 |
+
"learning_rate": 3.4259259259259265e-06,
|
328 |
+
"loss": 0.4825,
|
329 |
+
"step": 252
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 2.15,
|
333 |
+
"grad_norm": 9.981026649475098,
|
334 |
+
"learning_rate": 3.240740740740741e-06,
|
335 |
+
"loss": 0.3736,
|
336 |
+
"step": 258
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 2.2,
|
340 |
+
"grad_norm": 7.664780616760254,
|
341 |
+
"learning_rate": 3.055555555555556e-06,
|
342 |
+
"loss": 0.4053,
|
343 |
+
"step": 264
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 2.25,
|
347 |
+
"grad_norm": 13.810154914855957,
|
348 |
+
"learning_rate": 2.8703703703703706e-06,
|
349 |
+
"loss": 0.4773,
|
350 |
+
"step": 270
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 2.3,
|
354 |
+
"grad_norm": 13.744608879089355,
|
355 |
+
"learning_rate": 2.6851851851851856e-06,
|
356 |
+
"loss": 0.4968,
|
357 |
+
"step": 276
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 2.35,
|
361 |
+
"grad_norm": 31.586156845092773,
|
362 |
+
"learning_rate": 2.5e-06,
|
363 |
+
"loss": 0.4273,
|
364 |
+
"step": 282
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 2.4,
|
368 |
+
"grad_norm": 13.05024242401123,
|
369 |
+
"learning_rate": 2.314814814814815e-06,
|
370 |
+
"loss": 0.4525,
|
371 |
+
"step": 288
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 2.45,
|
375 |
+
"grad_norm": 29.851980209350586,
|
376 |
+
"learning_rate": 2.1296296296296298e-06,
|
377 |
+
"loss": 0.3998,
|
378 |
+
"step": 294
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 2.5,
|
382 |
+
"grad_norm": 19.604598999023438,
|
383 |
+
"learning_rate": 1.944444444444445e-06,
|
384 |
+
"loss": 0.4503,
|
385 |
+
"step": 300
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 2.55,
|
389 |
+
"grad_norm": 20.182512283325195,
|
390 |
+
"learning_rate": 1.7592592592592594e-06,
|
391 |
+
"loss": 0.4324,
|
392 |
+
"step": 306
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 2.6,
|
396 |
+
"grad_norm": 14.632848739624023,
|
397 |
+
"learning_rate": 1.5740740740740742e-06,
|
398 |
+
"loss": 0.4608,
|
399 |
+
"step": 312
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 2.65,
|
403 |
+
"grad_norm": 20.7685489654541,
|
404 |
+
"learning_rate": 1.3888888888888892e-06,
|
405 |
+
"loss": 0.49,
|
406 |
+
"step": 318
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 2.7,
|
410 |
+
"grad_norm": 10.122600555419922,
|
411 |
+
"learning_rate": 1.2037037037037037e-06,
|
412 |
+
"loss": 0.4825,
|
413 |
+
"step": 324
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 2.75,
|
417 |
+
"grad_norm": 14.672435760498047,
|
418 |
+
"learning_rate": 1.0185185185185185e-06,
|
419 |
+
"loss": 0.5361,
|
420 |
+
"step": 330
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 2.8,
|
424 |
+
"grad_norm": 16.504741668701172,
|
425 |
+
"learning_rate": 8.333333333333333e-07,
|
426 |
+
"loss": 0.3532,
|
427 |
+
"step": 336
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 2.85,
|
431 |
+
"grad_norm": 13.80346393585205,
|
432 |
+
"learning_rate": 6.481481481481481e-07,
|
433 |
+
"loss": 0.4261,
|
434 |
+
"step": 342
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 2.9,
|
438 |
+
"grad_norm": 4.231124401092529,
|
439 |
+
"learning_rate": 4.6296296296296297e-07,
|
440 |
+
"loss": 0.3972,
|
441 |
+
"step": 348
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 2.95,
|
445 |
+
"grad_norm": 18.095500946044922,
|
446 |
+
"learning_rate": 2.7777777777777776e-07,
|
447 |
+
"loss": 0.4544,
|
448 |
+
"step": 354
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 3.0,
|
452 |
+
"grad_norm": 14.508122444152832,
|
453 |
+
"learning_rate": 9.259259259259259e-08,
|
454 |
+
"loss": 0.4752,
|
455 |
+
"step": 360
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 3.0,
|
459 |
+
"eval_accuracy": 0.7566666666666667,
|
460 |
+
"eval_auc": 0.8403134164222874,
|
461 |
+
"eval_f1": 0.6812227074235808,
|
462 |
+
"eval_loss": 0.5102422833442688,
|
463 |
+
"eval_precision": 0.7428571428571429,
|
464 |
+
"eval_recall": 0.6290322580645161,
|
465 |
+
"eval_runtime": 0.432,
|
466 |
+
"eval_samples_per_second": 694.481,
|
467 |
+
"eval_steps_per_second": 34.724,
|
468 |
+
"step": 360
|
469 |
+
}
|
470 |
+
],
|
471 |
+
"logging_steps": 6,
|
472 |
+
"max_steps": 360,
|
473 |
+
"num_input_tokens_seen": 0,
|
474 |
+
"num_train_epochs": 3,
|
475 |
+
"save_steps": 500,
|
476 |
+
"stateful_callbacks": {
|
477 |
+
"EarlyStoppingCallback": {
|
478 |
+
"args": {
|
479 |
+
"early_stopping_patience": 5,
|
480 |
+
"early_stopping_threshold": 0.01
|
481 |
+
},
|
482 |
+
"attributes": {
|
483 |
+
"early_stopping_patience_counter": 0
|
484 |
+
}
|
485 |
+
},
|
486 |
+
"TrainerControl": {
|
487 |
+
"args": {
|
488 |
+
"should_epoch_stop": false,
|
489 |
+
"should_evaluate": false,
|
490 |
+
"should_log": false,
|
491 |
+
"should_save": true,
|
492 |
+
"should_training_stop": true
|
493 |
+
},
|
494 |
+
"attributes": {}
|
495 |
+
}
|
496 |
+
},
|
497 |
+
"total_flos": 238441317580800.0,
|
498 |
+
"train_batch_size": 10,
|
499 |
+
"trial_name": null,
|
500 |
+
"trial_params": null
|
501 |
+
}
|
checkpoint-360/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5dd2639eccefd0bc69c78213810646a7189500435d295c46fc9baeaadd5cd71
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "certain",
|
17 |
+
"1": "uncertain"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"certain": 0,
|
23 |
+
"uncertain": 1
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-05,
|
26 |
+
"max_position_embeddings": 514,
|
27 |
+
"model_type": "roberta",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 6,
|
30 |
+
"pad_token_id": 1,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.44.2",
|
35 |
+
"type_vocab_size": 1,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 50265
|
38 |
+
}
|
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 sha256:2b5734d128607df3920742efde94ba3cade3bef8e2ff341916598130c9aebabf
|
3 |
+
size 328492280
|
runs/Sep05_14-27-13_r-jjonas313-autotrain-ecb-uncertainy-zjc3cpem-d400c-3ytpc/events.out.tfevents.1725546434.r-jjonas313-autotrain-ecb-uncertainy-zjc3cpem-d400c-3ytpc.173.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fcbb962ba0f17330de403c11b68dabf598c1eb532c6af658d3cfe5b7b97315b
|
3 |
+
size 19841
|
runs/Sep05_14-27-13_r-jjonas313-autotrain-ecb-uncertainy-zjc3cpem-d400c-3ytpc/events.out.tfevents.1725546462.r-jjonas313-autotrain-ecb-uncertainy-zjc3cpem-d400c-3ytpc.173.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c30e6b83f0306234876e79b03c5ba3145446856ec461eed55f725e81b0bc297
|
3 |
+
size 607
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
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": "</s>",
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
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 |
+
"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 |
+
"max_length": 512,
|
52 |
+
"model_max_length": 512,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"stride": 0,
|
56 |
+
"tokenizer_class": "RobertaTokenizer",
|
57 |
+
"trim_offsets": true,
|
58 |
+
"truncation_side": "right",
|
59 |
+
"truncation_strategy": "longest_first",
|
60 |
+
"unk_token": "<unk>"
|
61 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5dd2639eccefd0bc69c78213810646a7189500435d295c46fc9baeaadd5cd71
|
3 |
+
size 5304
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-ecb-uncertainty-financial-news-sentiment/autotrain-data",
|
3 |
+
"model": "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis",
|
4 |
+
"lr": 1e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 256,
|
7 |
+
"batch_size": 10,
|
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": 333,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"text_column": "autotrain_text",
|
18 |
+
"target_column": "autotrain_label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "autotrain-ecb-uncertainty-financial-news-sentiment",
|
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": "jjonas313",
|
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
|
|