Commit
•
a9979c8
1
Parent(s):
822c5ab
Upload folder using huggingface_hub
Browse files- README.md +69 -0
- all_results.json +20 -0
- config.json +41 -0
- eval_results.json +9 -0
- model.safetensors +3 -0
- pred_logit_eval.npy +3 -0
- pred_logit_test.npy +3 -0
- pred_logit_train.npy +3 -0
- runs/Apr27_03-43-38_clu/events.out.tfevents.1714189438.clu +3 -0
- runs/Apr27_03-43-38_clu/events.out.tfevents.1714190869.clu +3 -0
- special_tokens_map.json +7 -0
- test_results.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- train_results.json +9 -0
- trainer_state.json +169 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: ddi_42
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# ddi_42
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2085
|
21 |
+
- Accuracy: 0.9551
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 5e-05
|
41 |
+
- train_batch_size: 32
|
42 |
+
- eval_batch_size: 256
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 10
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| No log | 1.0 | 791 | 0.1986 | 0.9383 |
|
53 |
+
| 0.1723 | 2.0 | 1582 | 0.2700 | 0.9455 |
|
54 |
+
| 0.0772 | 3.0 | 2373 | 0.2085 | 0.9551 |
|
55 |
+
| 0.0516 | 4.0 | 3164 | 0.2970 | 0.9427 |
|
56 |
+
| 0.0516 | 5.0 | 3955 | 0.2620 | 0.9539 |
|
57 |
+
| 0.0341 | 6.0 | 4746 | 0.3973 | 0.9423 |
|
58 |
+
| 0.0203 | 7.0 | 5537 | 0.3637 | 0.9423 |
|
59 |
+
| 0.0146 | 8.0 | 6328 | 0.4154 | 0.9451 |
|
60 |
+
| 0.007 | 9.0 | 7119 | 0.4219 | 0.9463 |
|
61 |
+
| 0.007 | 10.0 | 7910 | 0.4098 | 0.9447 |
|
62 |
+
|
63 |
+
|
64 |
+
### Framework versions
|
65 |
+
|
66 |
+
- Transformers 4.39.3
|
67 |
+
- Pytorch 2.2.2+cu118
|
68 |
+
- Datasets 2.18.0
|
69 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.9551282051282052,
|
4 |
+
"eval_loss": 0.20845328271389008,
|
5 |
+
"eval_runtime": 4.9096,
|
6 |
+
"eval_samples": 25296,
|
7 |
+
"eval_samples_per_second": 508.388,
|
8 |
+
"eval_steps_per_second": 2.037,
|
9 |
+
"test_accuracy": 0.9391182645206438,
|
10 |
+
"test_loss": 0.3346391022205353,
|
11 |
+
"test_runtime": 9.9095,
|
12 |
+
"test_samples_per_second": 576.823,
|
13 |
+
"test_steps_per_second": 2.321,
|
14 |
+
"train_accuracy": 0.9922912713472486,
|
15 |
+
"train_loss": 0.03253408521413803,
|
16 |
+
"train_runtime": 40.6672,
|
17 |
+
"train_samples": 25296,
|
18 |
+
"train_samples_per_second": 622.025,
|
19 |
+
"train_steps_per_second": 2.434
|
20 |
+
}
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"finetuning_task": "text-classification",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"0": 0,
|
23 |
+
"1": 1,
|
24 |
+
"2": 2,
|
25 |
+
"3": 3,
|
26 |
+
"4": 4
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"max_position_embeddings": 512,
|
30 |
+
"model_type": "bert",
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"pad_token_id": 0,
|
34 |
+
"position_embedding_type": "absolute",
|
35 |
+
"problem_type": "single_label_classification",
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.39.3",
|
38 |
+
"type_vocab_size": 2,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 30522
|
41 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.9551282051282052,
|
4 |
+
"eval_loss": 0.20845328271389008,
|
5 |
+
"eval_runtime": 4.9096,
|
6 |
+
"eval_samples": 2496,
|
7 |
+
"eval_samples_per_second": 508.388,
|
8 |
+
"eval_steps_per_second": 2.037
|
9 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8057e2d26cccbc75703b20f2c650e0332ed275e6f805e991e284c0e4044a8905
|
3 |
+
size 437967876
|
pred_logit_eval.npy
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f136441d59211f3ef7c46ece76cfa43f72aff95f9bf89f08a9e498b737ae4c71
|
3 |
+
size 50048
|
pred_logit_test.npy
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3e9f84d3a6af45c1dfaac187bf20245f80c41373b5675cebf69840e21313f0c
|
3 |
+
size 114448
|
pred_logit_train.npy
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c30b00c8ac7b65f9f249b5e68a343ea18ecde68212fdc139dd330614ac84a4be
|
3 |
+
size 506048
|
runs/Apr27_03-43-38_clu/events.out.tfevents.1714189438.clu
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33d109447de018595ea36c85d6ab8cdd9dab21ca67f60970ef956be8adb680fd
|
3 |
+
size 10021
|
runs/Apr27_03-43-38_clu/events.out.tfevents.1714190869.clu
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b72bb2cea2e520b69634cc82e12d77526e29bceab32a827e3b09402a5f403e2
|
3 |
+
size 1044
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
test_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_samples": 5716,
|
4 |
+
"test_accuracy": 0.9391182645206438,
|
5 |
+
"test_loss": 0.3346391022205353,
|
6 |
+
"test_runtime": 9.9095,
|
7 |
+
"test_samples_per_second": 576.823,
|
8 |
+
"test_steps_per_second": 2.321
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_samples": 25296,
|
4 |
+
"train_accuracy": 0.9922912713472486,
|
5 |
+
"train_loss": 0.03253408521413803,
|
6 |
+
"train_runtime": 40.6672,
|
7 |
+
"train_samples_per_second": 622.025,
|
8 |
+
"train_steps_per_second": 2.434
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9551282051282052,
|
3 |
+
"best_model_checkpoint": "text/train/checkpoint/pubmedbert-abstract/ddi_42/checkpoint-2373",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 7910,
|
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 |
+
"eval_accuracy": 0.938301282051282,
|
14 |
+
"eval_loss": 0.19862917065620422,
|
15 |
+
"eval_runtime": 5.4522,
|
16 |
+
"eval_samples_per_second": 457.799,
|
17 |
+
"eval_steps_per_second": 1.834,
|
18 |
+
"step": 791
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.26,
|
22 |
+
"grad_norm": 1.910953402519226,
|
23 |
+
"learning_rate": 4.367888748419722e-05,
|
24 |
+
"loss": 0.1723,
|
25 |
+
"step": 1000
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.9455128205128205,
|
30 |
+
"eval_loss": 0.2700441777706146,
|
31 |
+
"eval_runtime": 5.0135,
|
32 |
+
"eval_samples_per_second": 497.859,
|
33 |
+
"eval_steps_per_second": 1.995,
|
34 |
+
"step": 1582
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.53,
|
38 |
+
"grad_norm": 19.194658279418945,
|
39 |
+
"learning_rate": 3.735777496839444e-05,
|
40 |
+
"loss": 0.0772,
|
41 |
+
"step": 2000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.9551282051282052,
|
46 |
+
"eval_loss": 0.20845328271389008,
|
47 |
+
"eval_runtime": 4.8197,
|
48 |
+
"eval_samples_per_second": 517.874,
|
49 |
+
"eval_steps_per_second": 2.075,
|
50 |
+
"step": 2373
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 3.79,
|
54 |
+
"grad_norm": 0.3629066050052643,
|
55 |
+
"learning_rate": 3.1036662452591655e-05,
|
56 |
+
"loss": 0.0516,
|
57 |
+
"step": 3000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 4.0,
|
61 |
+
"eval_accuracy": 0.9427083333333334,
|
62 |
+
"eval_loss": 0.2969796061515808,
|
63 |
+
"eval_runtime": 4.7872,
|
64 |
+
"eval_samples_per_second": 521.395,
|
65 |
+
"eval_steps_per_second": 2.089,
|
66 |
+
"step": 3164
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 5.0,
|
70 |
+
"eval_accuracy": 0.953926282051282,
|
71 |
+
"eval_loss": 0.2620067596435547,
|
72 |
+
"eval_runtime": 4.7806,
|
73 |
+
"eval_samples_per_second": 522.107,
|
74 |
+
"eval_steps_per_second": 2.092,
|
75 |
+
"step": 3955
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.06,
|
79 |
+
"grad_norm": 0.0031597923953086138,
|
80 |
+
"learning_rate": 2.4715549936788876e-05,
|
81 |
+
"loss": 0.0341,
|
82 |
+
"step": 4000
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 6.0,
|
86 |
+
"eval_accuracy": 0.9423076923076923,
|
87 |
+
"eval_loss": 0.39730244874954224,
|
88 |
+
"eval_runtime": 4.7836,
|
89 |
+
"eval_samples_per_second": 521.783,
|
90 |
+
"eval_steps_per_second": 2.09,
|
91 |
+
"step": 4746
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 6.32,
|
95 |
+
"grad_norm": 0.006749527528882027,
|
96 |
+
"learning_rate": 1.8394437420986094e-05,
|
97 |
+
"loss": 0.0203,
|
98 |
+
"step": 5000
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_accuracy": 0.9423076923076923,
|
103 |
+
"eval_loss": 0.3636617958545685,
|
104 |
+
"eval_runtime": 4.7835,
|
105 |
+
"eval_samples_per_second": 521.797,
|
106 |
+
"eval_steps_per_second": 2.091,
|
107 |
+
"step": 5537
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 7.59,
|
111 |
+
"grad_norm": 0.012521493248641491,
|
112 |
+
"learning_rate": 1.2073324905183313e-05,
|
113 |
+
"loss": 0.0146,
|
114 |
+
"step": 6000
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 8.0,
|
118 |
+
"eval_accuracy": 0.9451121794871795,
|
119 |
+
"eval_loss": 0.4154008626937866,
|
120 |
+
"eval_runtime": 4.7634,
|
121 |
+
"eval_samples_per_second": 523.998,
|
122 |
+
"eval_steps_per_second": 2.099,
|
123 |
+
"step": 6328
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 8.85,
|
127 |
+
"grad_norm": 0.005341885611414909,
|
128 |
+
"learning_rate": 5.752212389380531e-06,
|
129 |
+
"loss": 0.007,
|
130 |
+
"step": 7000
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 9.0,
|
134 |
+
"eval_accuracy": 0.9463141025641025,
|
135 |
+
"eval_loss": 0.4218637943267822,
|
136 |
+
"eval_runtime": 4.8145,
|
137 |
+
"eval_samples_per_second": 518.431,
|
138 |
+
"eval_steps_per_second": 2.077,
|
139 |
+
"step": 7119
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 10.0,
|
143 |
+
"eval_accuracy": 0.9447115384615384,
|
144 |
+
"eval_loss": 0.4098478853702545,
|
145 |
+
"eval_runtime": 4.8332,
|
146 |
+
"eval_samples_per_second": 516.428,
|
147 |
+
"eval_steps_per_second": 2.069,
|
148 |
+
"step": 7910
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 10.0,
|
152 |
+
"step": 7910,
|
153 |
+
"total_flos": 1.663959132942336e+16,
|
154 |
+
"train_loss": 0.048086456131241864,
|
155 |
+
"train_runtime": 1425.5671,
|
156 |
+
"train_samples_per_second": 177.445,
|
157 |
+
"train_steps_per_second": 5.549
|
158 |
+
}
|
159 |
+
],
|
160 |
+
"logging_steps": 1000,
|
161 |
+
"max_steps": 7910,
|
162 |
+
"num_input_tokens_seen": 0,
|
163 |
+
"num_train_epochs": 10,
|
164 |
+
"save_steps": 500,
|
165 |
+
"total_flos": 1.663959132942336e+16,
|
166 |
+
"train_batch_size": 32,
|
167 |
+
"trial_name": null,
|
168 |
+
"trial_params": null
|
169 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4de6cbc7180e01d7bbaac6d209405970b8c1932b419ce007ab9190aeb3348435
|
3 |
+
size 5048
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|