carolynayamamoto
commited on
Commit
•
2c12315
1
Parent(s):
5954d74
trained biogpt ner classification on customized dataset
Browse files- checkpoint-1482/config.json +51 -0
- checkpoint-1482/merges.txt +0 -0
- checkpoint-1482/optimizer.pt +3 -0
- checkpoint-1482/pytorch_model.bin +3 -0
- checkpoint-1482/rng_state.pth +3 -0
- checkpoint-1482/scheduler.pt +3 -0
- checkpoint-1482/special_tokens_map.json +7 -0
- checkpoint-1482/tokenizer_config.json +10 -0
- checkpoint-1482/trainer_state.json +40 -0
- checkpoint-1482/training_args.bin +3 -0
- checkpoint-1482/vocab.json +0 -0
- checkpoint-2964/config.json +51 -0
- checkpoint-2964/merges.txt +0 -0
- checkpoint-2964/optimizer.pt +3 -0
- checkpoint-2964/pytorch_model.bin +3 -0
- checkpoint-2964/rng_state.pth +3 -0
- checkpoint-2964/scheduler.pt +3 -0
- checkpoint-2964/special_tokens_map.json +7 -0
- checkpoint-2964/tokenizer_config.json +10 -0
- checkpoint-2964/trainer_state.json +70 -0
- checkpoint-2964/training_args.bin +3 -0
- checkpoint-2964/vocab.json +0 -0
- checkpoint-4446/config.json +51 -0
- checkpoint-4446/merges.txt +0 -0
- checkpoint-4446/optimizer.pt +3 -0
- checkpoint-4446/pytorch_model.bin +3 -0
- checkpoint-4446/rng_state.pth +3 -0
- checkpoint-4446/scheduler.pt +3 -0
- checkpoint-4446/special_tokens_map.json +7 -0
- checkpoint-4446/tokenizer_config.json +10 -0
- checkpoint-4446/trainer_state.json +100 -0
- checkpoint-4446/training_args.bin +3 -0
- checkpoint-4446/vocab.json +0 -0
- config.json +51 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Apr14_17-54-41_Carolynas-MacBook-Pro.local/1713131686.545365/events.out.tfevents.1713131686.Carolynas-MacBook-Pro.local.68492.1 +3 -0
- runs/Apr14_17-54-41_Carolynas-MacBook-Pro.local/events.out.tfevents.1713131686.Carolynas-MacBook-Pro.local.68492.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +10 -0
- training_args.bin +3 -0
- vocab.json +0 -0
checkpoint-1482/config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "carolynayamamoto/biogpt-ner-classification",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2ForTokenClassification"
|
7 |
+
],
|
8 |
+
"attention_probs_dropout_prob": 0.1,
|
9 |
+
"attn_pdrop": 0.1,
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"embd_pdrop": 0.1,
|
12 |
+
"eos_token_id": 2,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"id2label": {
|
16 |
+
"0": "O",
|
17 |
+
"1": "B-ADR",
|
18 |
+
"2": "I-ADR"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 4096,
|
22 |
+
"label2id": {
|
23 |
+
"B-ADR": 1,
|
24 |
+
"I-ADR": 2,
|
25 |
+
"O": 0
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-12,
|
28 |
+
"layer_norm_epsilon": 1e-05,
|
29 |
+
"layerdrop": 0.0,
|
30 |
+
"model_type": "gpt2",
|
31 |
+
"n_embd": 1024,
|
32 |
+
"n_head": 16,
|
33 |
+
"n_inner": null,
|
34 |
+
"n_layer": 24,
|
35 |
+
"n_positions": 1024,
|
36 |
+
"pad_token_id": 1,
|
37 |
+
"reorder_and_upcast_attn": false,
|
38 |
+
"resid_pdrop": 0.1,
|
39 |
+
"scale_attn_by_inverse_layer_idx": false,
|
40 |
+
"scale_attn_weights": true,
|
41 |
+
"scale_embedding": true,
|
42 |
+
"summary_activation": null,
|
43 |
+
"summary_first_dropout": 0.1,
|
44 |
+
"summary_proj_to_labels": true,
|
45 |
+
"summary_type": "cls_index",
|
46 |
+
"summary_use_proj": true,
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.29.2",
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 42384
|
51 |
+
}
|
checkpoint-1482/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1482/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba5142800358c351a7d16d85cccec8706c0e9f640223b265625cb568c35d4e5d
|
3 |
+
size 2774278906
|
checkpoint-1482/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6f729b21c65932feaa1910e61ec48924c85433df48c43d79aebcaa0ec70b823
|
3 |
+
size 1412330082
|
checkpoint-1482/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a39acc980e6abdf04b3751d16151f8cc4d4cf01414af038e7a6136e6ff0d7cf
|
3 |
+
size 13990
|
checkpoint-1482/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ac1d3b27903d2648276dd4f9810a33e5845b6159438a95010f1fee7a1c5e699
|
3 |
+
size 1064
|
checkpoint-1482/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"sep_token": "</s>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
checkpoint-1482/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"tokenizer_class": "BioGptTokenizer",
|
9 |
+
"unk_token": "<unk>"
|
10 |
+
}
|
checkpoint-1482/trainer_state.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 1482,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.34,
|
12 |
+
"learning_rate": 1.7750787224471436e-05,
|
13 |
+
"loss": 0.2516,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.67,
|
18 |
+
"learning_rate": 1.550157444894287e-05,
|
19 |
+
"loss": 0.1893,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.0,
|
24 |
+
"eval_accuracy": 0.9572655742438461,
|
25 |
+
"eval_f1": 0.5739710789766408,
|
26 |
+
"eval_loss": 0.11261405795812607,
|
27 |
+
"eval_precision": 0.5113974231912785,
|
28 |
+
"eval_recall": 0.6539923954372624,
|
29 |
+
"eval_runtime": 94.9871,
|
30 |
+
"eval_samples_per_second": 12.486,
|
31 |
+
"eval_steps_per_second": 3.127,
|
32 |
+
"step": 1482
|
33 |
+
}
|
34 |
+
],
|
35 |
+
"max_steps": 4446,
|
36 |
+
"num_train_epochs": 3,
|
37 |
+
"total_flos": 643184375315466.0,
|
38 |
+
"trial_name": null,
|
39 |
+
"trial_params": null
|
40 |
+
}
|
checkpoint-1482/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c0927501e95d62d5975af8521e7048e232aa28233b6e402efef14dc4a82cada
|
3 |
+
size 4408
|
checkpoint-1482/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2964/config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "carolynayamamoto/biogpt-ner-classification",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2ForTokenClassification"
|
7 |
+
],
|
8 |
+
"attention_probs_dropout_prob": 0.1,
|
9 |
+
"attn_pdrop": 0.1,
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"embd_pdrop": 0.1,
|
12 |
+
"eos_token_id": 2,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"id2label": {
|
16 |
+
"0": "O",
|
17 |
+
"1": "B-ADR",
|
18 |
+
"2": "I-ADR"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 4096,
|
22 |
+
"label2id": {
|
23 |
+
"B-ADR": 1,
|
24 |
+
"I-ADR": 2,
|
25 |
+
"O": 0
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-12,
|
28 |
+
"layer_norm_epsilon": 1e-05,
|
29 |
+
"layerdrop": 0.0,
|
30 |
+
"model_type": "gpt2",
|
31 |
+
"n_embd": 1024,
|
32 |
+
"n_head": 16,
|
33 |
+
"n_inner": null,
|
34 |
+
"n_layer": 24,
|
35 |
+
"n_positions": 1024,
|
36 |
+
"pad_token_id": 1,
|
37 |
+
"reorder_and_upcast_attn": false,
|
38 |
+
"resid_pdrop": 0.1,
|
39 |
+
"scale_attn_by_inverse_layer_idx": false,
|
40 |
+
"scale_attn_weights": true,
|
41 |
+
"scale_embedding": true,
|
42 |
+
"summary_activation": null,
|
43 |
+
"summary_first_dropout": 0.1,
|
44 |
+
"summary_proj_to_labels": true,
|
45 |
+
"summary_type": "cls_index",
|
46 |
+
"summary_use_proj": true,
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.29.2",
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 42384
|
51 |
+
}
|
checkpoint-2964/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2964/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66aa8bd7fefc3047c96ae6200d90e73905975b5dab34738e3f1d4e8584746aad
|
3 |
+
size 2774278906
|
checkpoint-2964/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87a1b0e6e3535c9d4642021cefb98f831330fe9556ed7753b09fc8d1ed92b31e
|
3 |
+
size 1412330082
|
checkpoint-2964/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dee2a5e4b8a499a60988188230b9ce3530184dbe25ec498fe37b614d527b7c7c
|
3 |
+
size 13990
|
checkpoint-2964/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:084184e968bc2e2f1d258ada63f13200a5ea5f80bad8c8b1619ea6196ba93ae1
|
3 |
+
size 1064
|
checkpoint-2964/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"sep_token": "</s>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
checkpoint-2964/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"tokenizer_class": "BioGptTokenizer",
|
9 |
+
"unk_token": "<unk>"
|
10 |
+
}
|
checkpoint-2964/trainer_state.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 2964,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.34,
|
12 |
+
"learning_rate": 1.7750787224471436e-05,
|
13 |
+
"loss": 0.2516,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.67,
|
18 |
+
"learning_rate": 1.550157444894287e-05,
|
19 |
+
"loss": 0.1893,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.0,
|
24 |
+
"eval_accuracy": 0.9572655742438461,
|
25 |
+
"eval_f1": 0.5739710789766408,
|
26 |
+
"eval_loss": 0.11261405795812607,
|
27 |
+
"eval_precision": 0.5113974231912785,
|
28 |
+
"eval_recall": 0.6539923954372624,
|
29 |
+
"eval_runtime": 94.9871,
|
30 |
+
"eval_samples_per_second": 12.486,
|
31 |
+
"eval_steps_per_second": 3.127,
|
32 |
+
"step": 1482
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.01,
|
36 |
+
"learning_rate": 1.3252361673414307e-05,
|
37 |
+
"loss": 0.1719,
|
38 |
+
"step": 1500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.35,
|
42 |
+
"learning_rate": 1.100314889788574e-05,
|
43 |
+
"loss": 0.1202,
|
44 |
+
"step": 2000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.69,
|
48 |
+
"learning_rate": 8.753936122357177e-06,
|
49 |
+
"loss": 0.1117,
|
50 |
+
"step": 2500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 2.0,
|
54 |
+
"eval_accuracy": 0.9754806419788734,
|
55 |
+
"eval_f1": 0.725097218067604,
|
56 |
+
"eval_loss": 0.06848359107971191,
|
57 |
+
"eval_precision": 0.686685552407932,
|
58 |
+
"eval_recall": 0.7680608365019012,
|
59 |
+
"eval_runtime": 101.9581,
|
60 |
+
"eval_samples_per_second": 11.632,
|
61 |
+
"eval_steps_per_second": 2.913,
|
62 |
+
"step": 2964
|
63 |
+
}
|
64 |
+
],
|
65 |
+
"max_steps": 4446,
|
66 |
+
"num_train_epochs": 3,
|
67 |
+
"total_flos": 1287500616115188.0,
|
68 |
+
"trial_name": null,
|
69 |
+
"trial_params": null
|
70 |
+
}
|
checkpoint-2964/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c0927501e95d62d5975af8521e7048e232aa28233b6e402efef14dc4a82cada
|
3 |
+
size 4408
|
checkpoint-2964/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4446/config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "carolynayamamoto/biogpt-ner-classification",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2ForTokenClassification"
|
7 |
+
],
|
8 |
+
"attention_probs_dropout_prob": 0.1,
|
9 |
+
"attn_pdrop": 0.1,
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"embd_pdrop": 0.1,
|
12 |
+
"eos_token_id": 2,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"id2label": {
|
16 |
+
"0": "O",
|
17 |
+
"1": "B-ADR",
|
18 |
+
"2": "I-ADR"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 4096,
|
22 |
+
"label2id": {
|
23 |
+
"B-ADR": 1,
|
24 |
+
"I-ADR": 2,
|
25 |
+
"O": 0
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-12,
|
28 |
+
"layer_norm_epsilon": 1e-05,
|
29 |
+
"layerdrop": 0.0,
|
30 |
+
"model_type": "gpt2",
|
31 |
+
"n_embd": 1024,
|
32 |
+
"n_head": 16,
|
33 |
+
"n_inner": null,
|
34 |
+
"n_layer": 24,
|
35 |
+
"n_positions": 1024,
|
36 |
+
"pad_token_id": 1,
|
37 |
+
"reorder_and_upcast_attn": false,
|
38 |
+
"resid_pdrop": 0.1,
|
39 |
+
"scale_attn_by_inverse_layer_idx": false,
|
40 |
+
"scale_attn_weights": true,
|
41 |
+
"scale_embedding": true,
|
42 |
+
"summary_activation": null,
|
43 |
+
"summary_first_dropout": 0.1,
|
44 |
+
"summary_proj_to_labels": true,
|
45 |
+
"summary_type": "cls_index",
|
46 |
+
"summary_use_proj": true,
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.29.2",
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 42384
|
51 |
+
}
|
checkpoint-4446/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4446/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:085c09cc30222f100fc3849cff570092c5c821f48f1093c8ee30e59b911246bf
|
3 |
+
size 2774278906
|
checkpoint-4446/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f49776bc5b87cd626b9c53dbaedc6d8780ab48dadcd18484cf0f3d4557e1a07
|
3 |
+
size 1412330082
|
checkpoint-4446/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aad866a0125d0a4cac6333cfc57bd6fefd41acb9a4efecaa1e4dd6e87b2c4e68
|
3 |
+
size 13990
|
checkpoint-4446/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:322d397750c588f036a552da0fd6709d2fc5a2f7a47efa7e2f7e525fb42d4d8d
|
3 |
+
size 1064
|
checkpoint-4446/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"sep_token": "</s>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
checkpoint-4446/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"tokenizer_class": "BioGptTokenizer",
|
9 |
+
"unk_token": "<unk>"
|
10 |
+
}
|
checkpoint-4446/trainer_state.json
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 4446,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.34,
|
12 |
+
"learning_rate": 1.7750787224471436e-05,
|
13 |
+
"loss": 0.2516,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.67,
|
18 |
+
"learning_rate": 1.550157444894287e-05,
|
19 |
+
"loss": 0.1893,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.0,
|
24 |
+
"eval_accuracy": 0.9572655742438461,
|
25 |
+
"eval_f1": 0.5739710789766408,
|
26 |
+
"eval_loss": 0.11261405795812607,
|
27 |
+
"eval_precision": 0.5113974231912785,
|
28 |
+
"eval_recall": 0.6539923954372624,
|
29 |
+
"eval_runtime": 94.9871,
|
30 |
+
"eval_samples_per_second": 12.486,
|
31 |
+
"eval_steps_per_second": 3.127,
|
32 |
+
"step": 1482
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.01,
|
36 |
+
"learning_rate": 1.3252361673414307e-05,
|
37 |
+
"loss": 0.1719,
|
38 |
+
"step": 1500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.35,
|
42 |
+
"learning_rate": 1.100314889788574e-05,
|
43 |
+
"loss": 0.1202,
|
44 |
+
"step": 2000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.69,
|
48 |
+
"learning_rate": 8.753936122357177e-06,
|
49 |
+
"loss": 0.1117,
|
50 |
+
"step": 2500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 2.0,
|
54 |
+
"eval_accuracy": 0.9754806419788734,
|
55 |
+
"eval_f1": 0.725097218067604,
|
56 |
+
"eval_loss": 0.06848359107971191,
|
57 |
+
"eval_precision": 0.686685552407932,
|
58 |
+
"eval_recall": 0.7680608365019012,
|
59 |
+
"eval_runtime": 101.9581,
|
60 |
+
"eval_samples_per_second": 11.632,
|
61 |
+
"eval_steps_per_second": 2.913,
|
62 |
+
"step": 2964
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 2.02,
|
66 |
+
"learning_rate": 6.504723346828611e-06,
|
67 |
+
"loss": 0.1075,
|
68 |
+
"step": 3000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 2.36,
|
72 |
+
"learning_rate": 4.255510571300046e-06,
|
73 |
+
"loss": 0.0829,
|
74 |
+
"step": 3500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.7,
|
78 |
+
"learning_rate": 2.00629779577148e-06,
|
79 |
+
"loss": 0.0889,
|
80 |
+
"step": 4000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 3.0,
|
84 |
+
"eval_accuracy": 0.9814961861449987,
|
85 |
+
"eval_f1": 0.777242624924744,
|
86 |
+
"eval_loss": 0.054215945303440094,
|
87 |
+
"eval_precision": 0.7402522935779816,
|
88 |
+
"eval_recall": 0.8181242078580482,
|
89 |
+
"eval_runtime": 95.5514,
|
90 |
+
"eval_samples_per_second": 12.412,
|
91 |
+
"eval_steps_per_second": 3.108,
|
92 |
+
"step": 4446
|
93 |
+
}
|
94 |
+
],
|
95 |
+
"max_steps": 4446,
|
96 |
+
"num_train_epochs": 3,
|
97 |
+
"total_flos": 1931548401639798.0,
|
98 |
+
"trial_name": null,
|
99 |
+
"trial_params": null
|
100 |
+
}
|
checkpoint-4446/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c0927501e95d62d5975af8521e7048e232aa28233b6e402efef14dc4a82cada
|
3 |
+
size 4408
|
checkpoint-4446/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "carolynayamamoto/biogpt-ner-classification",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2ForTokenClassification"
|
7 |
+
],
|
8 |
+
"attention_probs_dropout_prob": 0.1,
|
9 |
+
"attn_pdrop": 0.1,
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"embd_pdrop": 0.1,
|
12 |
+
"eos_token_id": 2,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"id2label": {
|
16 |
+
"0": "O",
|
17 |
+
"1": "B-ADR",
|
18 |
+
"2": "I-ADR"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 4096,
|
22 |
+
"label2id": {
|
23 |
+
"B-ADR": 1,
|
24 |
+
"I-ADR": 2,
|
25 |
+
"O": 0
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-12,
|
28 |
+
"layer_norm_epsilon": 1e-05,
|
29 |
+
"layerdrop": 0.0,
|
30 |
+
"model_type": "gpt2",
|
31 |
+
"n_embd": 1024,
|
32 |
+
"n_head": 16,
|
33 |
+
"n_inner": null,
|
34 |
+
"n_layer": 24,
|
35 |
+
"n_positions": 1024,
|
36 |
+
"pad_token_id": 1,
|
37 |
+
"reorder_and_upcast_attn": false,
|
38 |
+
"resid_pdrop": 0.1,
|
39 |
+
"scale_attn_by_inverse_layer_idx": false,
|
40 |
+
"scale_attn_weights": true,
|
41 |
+
"scale_embedding": true,
|
42 |
+
"summary_activation": null,
|
43 |
+
"summary_first_dropout": 0.1,
|
44 |
+
"summary_proj_to_labels": true,
|
45 |
+
"summary_type": "cls_index",
|
46 |
+
"summary_use_proj": true,
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.29.2",
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 42384
|
51 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f49776bc5b87cd626b9c53dbaedc6d8780ab48dadcd18484cf0f3d4557e1a07
|
3 |
+
size 1412330082
|
runs/Apr14_17-54-41_Carolynas-MacBook-Pro.local/1713131686.545365/events.out.tfevents.1713131686.Carolynas-MacBook-Pro.local.68492.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce9a69bc84f7b884a3168e66f1321b69ca4f767be7c89180f7541ec87bc04fc2
|
3 |
+
size 5955
|
runs/Apr14_17-54-41_Carolynas-MacBook-Pro.local/events.out.tfevents.1713131686.Carolynas-MacBook-Pro.local.68492.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02839c744b2192232c42d4eac54197c899f236f4e8bb86f192f3e0c3071c41cb
|
3 |
+
size 7640
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"sep_token": "</s>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"tokenizer_class": "BioGptTokenizer",
|
9 |
+
"unk_token": "<unk>"
|
10 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c0927501e95d62d5975af8521e7048e232aa28233b6e402efef14dc4a82cada
|
3 |
+
size 4408
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|