Training in progress epoch 0
Browse files- README.md +6 -15
- config.json +19 -38
- generation_config.json +1 -2
- tf_model.h5 +2 -2
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# node-py/my_awesome_eli5_clm-model
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss:
|
19 |
-
- Validation Loss:
|
20 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -43,16 +43,7 @@ The following hyperparameters were used during training:
|
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
-
| 7.
|
47 |
-
| 6.0733 | 5.8991 | 1 |
|
48 |
-
| 5.9048 | 5.7918 | 2 |
|
49 |
-
| 5.7975 | 5.6991 | 3 |
|
50 |
-
| 5.7077 | 5.6058 | 4 |
|
51 |
-
| 5.6085 | 5.5014 | 5 |
|
52 |
-
| 5.5086 | 5.4011 | 6 |
|
53 |
-
| 5.4100 | 5.3107 | 7 |
|
54 |
-
| 5.3142 | 5.2220 | 8 |
|
55 |
-
| 5.2212 | 5.1350 | 9 |
|
56 |
|
57 |
|
58 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
|
|
13 |
|
14 |
# node-py/my_awesome_eli5_clm-model
|
15 |
|
16 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 7.4278
|
19 |
+
- Validation Loss: 6.1153
|
20 |
+
- Epoch: 0
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
+
| 7.4278 | 6.1153 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
config.json
CHANGED
@@ -1,45 +1,26 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"_num_labels": 1,
|
4 |
-
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
6 |
-
"
|
7 |
],
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
|
14 |
-
},
|
15 |
"initializer_range": 0.02,
|
16 |
-
"
|
17 |
-
|
18 |
-
|
19 |
-
"
|
20 |
-
"model_type": "
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"n_layer": 6,
|
26 |
-
"n_positions": 1024,
|
27 |
-
"reorder_and_upcast_attn": false,
|
28 |
-
"resid_pdrop": 0.1,
|
29 |
-
"scale_attn_by_inverse_layer_idx": false,
|
30 |
-
"scale_attn_weights": true,
|
31 |
-
"summary_activation": null,
|
32 |
-
"summary_first_dropout": 0.1,
|
33 |
-
"summary_proj_to_labels": true,
|
34 |
-
"summary_type": "cls_index",
|
35 |
-
"summary_use_proj": true,
|
36 |
-
"task_specific_params": {
|
37 |
-
"text-generation": {
|
38 |
-
"do_sample": true,
|
39 |
-
"max_length": 50
|
40 |
-
}
|
41 |
-
},
|
42 |
"transformers_version": "4.44.0",
|
|
|
43 |
"use_cache": true,
|
44 |
-
"vocab_size":
|
45 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
|
|
|
|
3 |
"architectures": [
|
4 |
+
"BertLMHeadModel"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"is_decoder": true,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "bert",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
"transformers_version": "4.44.0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
}
|
generation_config.json
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"
|
4 |
-
"eos_token_id": 50256,
|
5 |
"transformers_version": "4.44.0"
|
6 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"pad_token_id": 0,
|
|
|
4 |
"transformers_version": "4.44.0"
|
5 |
}
|
tf_model.h5
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:d12e8534ea4b65b4e1ab43d991fdad385ca0338fbd005b1c5160af0a650d4c4f
|
3 |
+
size 533687616
|