Shresthadev403
commited on
Commit
•
5abe211
1
Parent(s):
dab44ff
End of training
Browse files- README.md +9 -13
- config.json +1 -1
- logs/events.out.tfevents.1705983189.70e47a1f5afe.42.12 +3 -0
- special_tokens_map.json +5 -35
- tokenizer_config.json +0 -7
- trainer_state.json +8 -73
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
model-index:
|
@@ -11,9 +13,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
11 |
|
12 |
# ner-bert-ingredients
|
13 |
|
14 |
-
This model
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
-
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -43,17 +50,6 @@ The following hyperparameters were used during training:
|
|
43 |
- num_epochs: 50
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
46 |
-
### Training results
|
47 |
-
|
48 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
| 0.3826 | 10.0 | 10 | 4.4464 |
|
51 |
-
| 0.207 | 20.0 | 20 | 4.5212 |
|
52 |
-
| 0.1171 | 30.0 | 30 | 4.5379 |
|
53 |
-
| 0.0764 | 40.0 | 40 | 4.6038 |
|
54 |
-
| 0.063 | 50.0 | 50 | 4.6987 |
|
55 |
-
|
56 |
-
|
57 |
### Framework versions
|
58 |
|
59 |
- Transformers 4.36.0
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
13 |
|
14 |
# ner-bert-ingredients
|
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 |
+
- eval_loss: 4.4464
|
19 |
+
- eval_runtime: 0.0184
|
20 |
+
- eval_samples_per_second: 54.288
|
21 |
+
- eval_steps_per_second: 54.288
|
22 |
+
- epoch: 10.0
|
23 |
+
- step: 10
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
50 |
- num_epochs: 50
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
### Framework versions
|
54 |
|
55 |
- Transformers 4.36.0
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertForTokenClassification"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
"architectures": [
|
4 |
"BertForTokenClassification"
|
5 |
],
|
logs/events.out.tfevents.1705983189.70e47a1f5afe.42.12
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f551b9e27c17ebfa551fc7d1e14ed51a482b4bc22699aa35a77795af53bf867
|
3 |
+
size 7028
|
special_tokens_map.json
CHANGED
@@ -1,37 +1,7 @@
|
|
1 |
{
|
2 |
-
"cls_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"mask_token": {
|
10 |
-
"content": "[MASK]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "[PAD]",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"sep_token": {
|
24 |
-
"content": "[SEP]",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"unk_token": {
|
31 |
-
"content": "[UNK]",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
}
|
37 |
}
|
|
|
1 |
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
tokenizer_config.json
CHANGED
@@ -45,18 +45,11 @@
|
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
-
"max_length": 512,
|
49 |
"model_max_length": 512,
|
50 |
-
"pad_to_multiple_of": null,
|
51 |
"pad_token": "[PAD]",
|
52 |
-
"pad_token_type_id": 0,
|
53 |
-
"padding_side": "right",
|
54 |
"sep_token": "[SEP]",
|
55 |
-
"stride": 0,
|
56 |
"strip_accents": null,
|
57 |
"tokenize_chinese_chars": true,
|
58 |
"tokenizer_class": "BertTokenizer",
|
59 |
-
"truncation_side": "right",
|
60 |
-
"truncation_strategy": "longest_first",
|
61 |
"unk_token": "[UNK]"
|
62 |
}
|
|
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
|
|
48 |
"model_max_length": 512,
|
|
|
49 |
"pad_token": "[PAD]",
|
|
|
|
|
50 |
"sep_token": "[SEP]",
|
|
|
51 |
"strip_accents": null,
|
52 |
"tokenize_chinese_chars": true,
|
53 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
54 |
"unk_token": "[UNK]"
|
55 |
}
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint":
|
4 |
-
"epoch":
|
5 |
"eval_steps": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -17,75 +17,10 @@
|
|
17 |
{
|
18 |
"epoch": 10.0,
|
19 |
"eval_loss": 4.4464287757873535,
|
20 |
-
"eval_runtime": 0.0176,
|
21 |
-
"eval_samples_per_second": 56.724,
|
22 |
-
"eval_steps_per_second": 56.724,
|
23 |
-
"step": 10
|
24 |
-
},
|
25 |
-
{
|
26 |
-
"epoch": 20.0,
|
27 |
-
"learning_rate": 3e-05,
|
28 |
-
"loss": 0.207,
|
29 |
-
"step": 20
|
30 |
-
},
|
31 |
-
{
|
32 |
-
"epoch": 20.0,
|
33 |
-
"eval_loss": 4.521205425262451,
|
34 |
-
"eval_runtime": 0.018,
|
35 |
-
"eval_samples_per_second": 55.513,
|
36 |
-
"eval_steps_per_second": 55.513,
|
37 |
-
"step": 20
|
38 |
-
},
|
39 |
-
{
|
40 |
-
"epoch": 30.0,
|
41 |
-
"learning_rate": 2e-05,
|
42 |
-
"loss": 0.1171,
|
43 |
-
"step": 30
|
44 |
-
},
|
45 |
-
{
|
46 |
-
"epoch": 30.0,
|
47 |
-
"eval_loss": 4.5379462242126465,
|
48 |
-
"eval_runtime": 0.0188,
|
49 |
-
"eval_samples_per_second": 53.052,
|
50 |
-
"eval_steps_per_second": 53.052,
|
51 |
-
"step": 30
|
52 |
-
},
|
53 |
-
{
|
54 |
-
"epoch": 40.0,
|
55 |
-
"learning_rate": 1e-05,
|
56 |
-
"loss": 0.0764,
|
57 |
-
"step": 40
|
58 |
-
},
|
59 |
-
{
|
60 |
-
"epoch": 40.0,
|
61 |
-
"eval_loss": 4.603794574737549,
|
62 |
-
"eval_runtime": 0.0208,
|
63 |
-
"eval_samples_per_second": 48.022,
|
64 |
-
"eval_steps_per_second": 48.022,
|
65 |
-
"step": 40
|
66 |
-
},
|
67 |
-
{
|
68 |
-
"epoch": 50.0,
|
69 |
-
"learning_rate": 4e-05,
|
70 |
-
"loss": 0.063,
|
71 |
-
"step": 50
|
72 |
-
},
|
73 |
-
{
|
74 |
-
"epoch": 50.0,
|
75 |
-
"eval_loss": 4.698660850524902,
|
76 |
"eval_runtime": 0.0184,
|
77 |
-
"eval_samples_per_second": 54.
|
78 |
-
"eval_steps_per_second": 54.
|
79 |
-
"step":
|
80 |
-
},
|
81 |
-
{
|
82 |
-
"epoch": 50.0,
|
83 |
-
"step": 50,
|
84 |
-
"total_flos": 32856154788600.0,
|
85 |
-
"train_loss": 0.012607929706573486,
|
86 |
-
"train_runtime": 24.4386,
|
87 |
-
"train_samples_per_second": 18.413,
|
88 |
-
"train_steps_per_second": 2.046
|
89 |
}
|
90 |
],
|
91 |
"logging_steps": 10,
|
@@ -93,7 +28,7 @@
|
|
93 |
"num_input_tokens_seen": 0,
|
94 |
"num_train_epochs": 50,
|
95 |
"save_steps": 10,
|
96 |
-
"total_flos":
|
97 |
"train_batch_size": 16,
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
17 |
{
|
18 |
"epoch": 10.0,
|
19 |
"eval_loss": 4.4464287757873535,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"eval_runtime": 0.0184,
|
21 |
+
"eval_samples_per_second": 54.288,
|
22 |
+
"eval_steps_per_second": 54.288,
|
23 |
+
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 10,
|
|
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 50,
|
30 |
"save_steps": 10,
|
31 |
+
"total_flos": 6571230957720.0,
|
32 |
"train_batch_size": 16,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|