msgfrom96/xlm_emo_multi
Browse files- README.md +15 -15
- config.json +5 -5
- model.safetensors +2 -2
- training_args.bin +1 -1
- xlm_multi_emo/config.json +5 -5
- xlm_multi_emo/model.safetensors +2 -2
- xlm_multi_emo/training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
license: mit
|
| 4 |
-
base_model: xlm-roberta-
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
|
@@ -14,11 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# emotion_model
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [xlm-roberta-
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
-
- Micro F1: 0.
|
| 21 |
-
- Macro F1: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Micro F1 | Macro F1 |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
license: mit
|
| 4 |
+
base_model: xlm-roberta-large
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
|
|
|
| 14 |
|
| 15 |
# emotion_model
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2936
|
| 20 |
+
- Micro F1: 0.7177
|
| 21 |
+
- Macro F1: 0.5792
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Micro F1 | Macro F1 |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
| 54 |
+
| 0.4725 | 1.0 | 143 | 0.3610 | 0.5857 | 0.3394 |
|
| 55 |
+
| 0.3219 | 2.0 | 286 | 0.3058 | 0.6957 | 0.5022 |
|
| 56 |
+
| 0.2892 | 3.0 | 429 | 0.3067 | 0.6814 | 0.4921 |
|
| 57 |
+
| 0.263 | 4.0 | 572 | 0.2915 | 0.7037 | 0.5397 |
|
| 58 |
+
| 0.2399 | 5.0 | 715 | 0.2911 | 0.7108 | 0.5625 |
|
| 59 |
+
| 0.2255 | 6.0 | 858 | 0.2922 | 0.7115 | 0.5833 |
|
| 60 |
+
| 0.2147 | 7.0 | 1001 | 0.2877 | 0.7115 | 0.5792 |
|
| 61 |
+
| 0.1989 | 8.0 | 1144 | 0.2922 | 0.7176 | 0.5882 |
|
| 62 |
+
| 0.1908 | 9.0 | 1287 | 0.2956 | 0.7162 | 0.5816 |
|
| 63 |
+
| 0.1851 | 10.0 | 1430 | 0.2970 | 0.7193 | 0.5984 |
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "xlm-roberta-
|
| 3 |
"architectures": [
|
| 4 |
"XLMRobertaForSequenceClassification"
|
| 5 |
],
|
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"eos_token_id": 2,
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
-
"hidden_size":
|
| 13 |
"id2label": {
|
| 14 |
"0": "anger",
|
| 15 |
"1": "anticipation",
|
|
@@ -24,7 +24,7 @@
|
|
| 24 |
"10": "pessimism"
|
| 25 |
},
|
| 26 |
"initializer_range": 0.02,
|
| 27 |
-
"intermediate_size":
|
| 28 |
"label2id": {
|
| 29 |
"anger": 0,
|
| 30 |
"anticipation": 1,
|
|
@@ -41,8 +41,8 @@
|
|
| 41 |
"layer_norm_eps": 1e-05,
|
| 42 |
"max_position_embeddings": 514,
|
| 43 |
"model_type": "xlm-roberta",
|
| 44 |
-
"num_attention_heads":
|
| 45 |
-
"num_hidden_layers":
|
| 46 |
"output_past": true,
|
| 47 |
"pad_token_id": 1,
|
| 48 |
"position_embedding_type": "absolute",
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "xlm-roberta-large",
|
| 3 |
"architectures": [
|
| 4 |
"XLMRobertaForSequenceClassification"
|
| 5 |
],
|
|
|
|
| 9 |
"eos_token_id": 2,
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
"id2label": {
|
| 14 |
"0": "anger",
|
| 15 |
"1": "anticipation",
|
|
|
|
| 24 |
"10": "pessimism"
|
| 25 |
},
|
| 26 |
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 4096,
|
| 28 |
"label2id": {
|
| 29 |
"anger": 0,
|
| 30 |
"anticipation": 1,
|
|
|
|
| 41 |
"layer_norm_eps": 1e-05,
|
| 42 |
"max_position_embeddings": 514,
|
| 43 |
"model_type": "xlm-roberta",
|
| 44 |
+
"num_attention_heads": 16,
|
| 45 |
+
"num_hidden_layers": 24,
|
| 46 |
"output_past": true,
|
| 47 |
"pad_token_id": 1,
|
| 48 |
"position_embedding_type": "absolute",
|
model.safetensors
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 sha256:91a64034f69d6333a6584e016aa189cf01372ef99c0d34c1ea8d05edb0cd8b4a
|
| 3 |
+
size 2239655572
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:848316f869eb3b1363d9052b1f9bfe54b5c795f4a47506ae95e4a324cb5266dc
|
| 3 |
size 5304
|
xlm_multi_emo/config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "xlm-roberta-
|
| 3 |
"architectures": [
|
| 4 |
"XLMRobertaForSequenceClassification"
|
| 5 |
],
|
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"eos_token_id": 2,
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
-
"hidden_size":
|
| 13 |
"id2label": {
|
| 14 |
"0": "anger",
|
| 15 |
"1": "anticipation",
|
|
@@ -24,7 +24,7 @@
|
|
| 24 |
"10": "pessimism"
|
| 25 |
},
|
| 26 |
"initializer_range": 0.02,
|
| 27 |
-
"intermediate_size":
|
| 28 |
"label2id": {
|
| 29 |
"anger": 0,
|
| 30 |
"anticipation": 1,
|
|
@@ -41,8 +41,8 @@
|
|
| 41 |
"layer_norm_eps": 1e-05,
|
| 42 |
"max_position_embeddings": 514,
|
| 43 |
"model_type": "xlm-roberta",
|
| 44 |
-
"num_attention_heads":
|
| 45 |
-
"num_hidden_layers":
|
| 46 |
"output_past": true,
|
| 47 |
"pad_token_id": 1,
|
| 48 |
"position_embedding_type": "absolute",
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "xlm-roberta-large",
|
| 3 |
"architectures": [
|
| 4 |
"XLMRobertaForSequenceClassification"
|
| 5 |
],
|
|
|
|
| 9 |
"eos_token_id": 2,
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
"id2label": {
|
| 14 |
"0": "anger",
|
| 15 |
"1": "anticipation",
|
|
|
|
| 24 |
"10": "pessimism"
|
| 25 |
},
|
| 26 |
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 4096,
|
| 28 |
"label2id": {
|
| 29 |
"anger": 0,
|
| 30 |
"anticipation": 1,
|
|
|
|
| 41 |
"layer_norm_eps": 1e-05,
|
| 42 |
"max_position_embeddings": 514,
|
| 43 |
"model_type": "xlm-roberta",
|
| 44 |
+
"num_attention_heads": 16,
|
| 45 |
+
"num_hidden_layers": 24,
|
| 46 |
"output_past": true,
|
| 47 |
"pad_token_id": 1,
|
| 48 |
"position_embedding_type": "absolute",
|
xlm_multi_emo/model.safetensors
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 sha256:91a64034f69d6333a6584e016aa189cf01372ef99c0d34c1ea8d05edb0cd8b4a
|
| 3 |
+
size 2239655572
|
xlm_multi_emo/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:848316f869eb3b1363d9052b1f9bfe54b5c795f4a47506ae95e4a324cb5266dc
|
| 3 |
size 5304
|