xuancoblab2023
commited on
Commit
•
c801e09
1
Parent(s):
54d2eda
Training in progress, epoch 1
Browse files- logs/events.out.tfevents.1721964285.98acc6742512.15262.14 +2 -2
- logs/events.out.tfevents.1721964404.98acc6742512.15262.15 +3 -0
- logs/events.out.tfevents.1721964435.98acc6742512.15262.16 +3 -0
- model.safetensors +1 -1
- run-13/checkpoint-516/config.json +34 -0
- run-13/checkpoint-516/model.safetensors +3 -0
- run-13/checkpoint-516/optimizer.pt +3 -0
- run-13/checkpoint-516/rng_state.pth +3 -0
- run-13/checkpoint-516/scheduler.pt +3 -0
- run-13/checkpoint-516/special_tokens_map.json +7 -0
- run-13/checkpoint-516/tokenizer.json +0 -0
- run-13/checkpoint-516/tokenizer_config.json +55 -0
- run-13/checkpoint-516/trainer_state.json +98 -0
- run-13/checkpoint-516/training_args.bin +3 -0
- run-13/checkpoint-516/vocab.txt +0 -0
- run-15/checkpoint-172/config.json +34 -0
- run-15/checkpoint-172/model.safetensors +3 -0
- run-15/checkpoint-172/optimizer.pt +3 -0
- run-15/checkpoint-172/rng_state.pth +3 -0
- run-15/checkpoint-172/scheduler.pt +3 -0
- run-15/checkpoint-172/special_tokens_map.json +7 -0
- run-15/checkpoint-172/tokenizer.json +0 -0
- run-15/checkpoint-172/tokenizer_config.json +55 -0
- run-15/checkpoint-172/trainer_state.json +58 -0
- run-15/checkpoint-172/training_args.bin +3 -0
- run-15/checkpoint-172/vocab.txt +0 -0
- training_args.bin +1 -1
logs/events.out.tfevents.1721964285.98acc6742512.15262.14
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:c93a8e54f86f7357143ef425988a04b78dd7814b201f585dcee489aa2021fc1e
|
3 |
+
size 7883
|
logs/events.out.tfevents.1721964404.98acc6742512.15262.15
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d25e144181be6f878d09c6134f87d6480f2889ab165995fffb4565aea3cb77d
|
3 |
+
size 5708
|
logs/events.out.tfevents.1721964435.98acc6742512.15262.16
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7118850ad9e8581ca17734dd2e41ad622b8ac2d5812f359e1e4cae6c782f7325
|
3 |
+
size 5707
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17549312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:082dd18b297783f6c88dba6b24cf88b62397f1f17aaa33beffa51038f0d9d1af
|
3 |
size 17549312
|
run-13/checkpoint-516/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 128,
|
11 |
+
"id2label": {
|
12 |
+
"0": "negative",
|
13 |
+
"1": "positive"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 512,
|
17 |
+
"label2id": {
|
18 |
+
"negative": "0",
|
19 |
+
"positive": "1"
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "bert",
|
24 |
+
"num_attention_heads": 2,
|
25 |
+
"num_hidden_layers": 2,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.43.2",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
run-13/checkpoint-516/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:044d880a2bd8ed2c2a2395669c829b02597fc783155ff03d1bd2077697279ff8
|
3 |
+
size 17549312
|
run-13/checkpoint-516/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53520d86670a7c932c4bce6355df8ffa627845bb2b0bcb179b400b8ee3e6faee
|
3 |
+
size 35123898
|
run-13/checkpoint-516/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e559bd010dfad806644ec9950fc1246348c344f69faad3d9fcd91973ca8dae1e
|
3 |
+
size 14308
|
run-13/checkpoint-516/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e1b63c3dbea41b52469d0b01d97b914f8c28cc7a60181fcb9f0971c6d7891d5
|
3 |
+
size 1064
|
run-13/checkpoint-516/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 |
+
}
|
run-13/checkpoint-516/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-13/checkpoint-516/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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_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 |
+
}
|
run-13/checkpoint-516/trainer_state.json
ADDED
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.794,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-13/checkpoint-516",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 516,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"grad_norm": 1.6519217491149902,
|
14 |
+
"learning_rate": 0.0003489409909619128,
|
15 |
+
"loss": 0.6241,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.8201937777777778,
|
21 |
+
"eval_BAC": 0.738,
|
22 |
+
"eval_MCC": 0.4761528166708038,
|
23 |
+
"eval_PR_AUC": 0.7788333782261532,
|
24 |
+
"eval_accuracy": 0.738,
|
25 |
+
"eval_loss": 0.5376982688903809,
|
26 |
+
"eval_runtime": 6.2979,
|
27 |
+
"eval_samples_per_second": 238.174,
|
28 |
+
"eval_steps_per_second": 7.463,
|
29 |
+
"step": 172
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"grad_norm": 2.3186373710632324,
|
34 |
+
"learning_rate": 0.0003101697697439225,
|
35 |
+
"loss": 0.5634,
|
36 |
+
"step": 344
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.0,
|
40 |
+
"eval_AUC": 0.8520746666666666,
|
41 |
+
"eval_BAC": 0.7846666666666666,
|
42 |
+
"eval_MCC": 0.5843621161716221,
|
43 |
+
"eval_PR_AUC": 0.8014637687014566,
|
44 |
+
"eval_accuracy": 0.7846666666666666,
|
45 |
+
"eval_loss": 0.4982443153858185,
|
46 |
+
"eval_runtime": 6.2909,
|
47 |
+
"eval_samples_per_second": 238.439,
|
48 |
+
"eval_steps_per_second": 7.471,
|
49 |
+
"step": 344
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 3.0,
|
53 |
+
"grad_norm": 2.0677402019500732,
|
54 |
+
"learning_rate": 0.00027139854852593215,
|
55 |
+
"loss": 0.5357,
|
56 |
+
"step": 516
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.0,
|
60 |
+
"eval_AUC": 0.8606488888888889,
|
61 |
+
"eval_BAC": 0.794,
|
62 |
+
"eval_MCC": 0.5893641888341185,
|
63 |
+
"eval_PR_AUC": 0.8320856182757431,
|
64 |
+
"eval_accuracy": 0.794,
|
65 |
+
"eval_loss": 0.48504742980003357,
|
66 |
+
"eval_runtime": 6.1927,
|
67 |
+
"eval_samples_per_second": 242.22,
|
68 |
+
"eval_steps_per_second": 7.59,
|
69 |
+
"step": 516
|
70 |
+
}
|
71 |
+
],
|
72 |
+
"logging_steps": 500,
|
73 |
+
"max_steps": 1720,
|
74 |
+
"num_input_tokens_seen": 0,
|
75 |
+
"num_train_epochs": 10,
|
76 |
+
"save_steps": 500,
|
77 |
+
"stateful_callbacks": {
|
78 |
+
"TrainerControl": {
|
79 |
+
"args": {
|
80 |
+
"should_epoch_stop": false,
|
81 |
+
"should_evaluate": false,
|
82 |
+
"should_log": false,
|
83 |
+
"should_save": true,
|
84 |
+
"should_training_stop": false
|
85 |
+
},
|
86 |
+
"attributes": {}
|
87 |
+
}
|
88 |
+
},
|
89 |
+
"total_flos": 1351133190000.0,
|
90 |
+
"train_batch_size": 32,
|
91 |
+
"trial_name": null,
|
92 |
+
"trial_params": {
|
93 |
+
"alpha": 0.9793694957428477,
|
94 |
+
"learning_rate": 0.0003877122121799031,
|
95 |
+
"num_train_epochs": 10,
|
96 |
+
"temperature": 8
|
97 |
+
}
|
98 |
+
}
|
run-13/checkpoint-516/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5f5a036df1b03e4a4ba9a6e0ee0d631925c8ae6af2604af8ddb074e8926e2a8
|
3 |
+
size 5240
|
run-13/checkpoint-516/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-15/checkpoint-172/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 128,
|
11 |
+
"id2label": {
|
12 |
+
"0": "negative",
|
13 |
+
"1": "positive"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 512,
|
17 |
+
"label2id": {
|
18 |
+
"negative": "0",
|
19 |
+
"positive": "1"
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "bert",
|
24 |
+
"num_attention_heads": 2,
|
25 |
+
"num_hidden_layers": 2,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.43.2",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
run-15/checkpoint-172/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:082dd18b297783f6c88dba6b24cf88b62397f1f17aaa33beffa51038f0d9d1af
|
3 |
+
size 17549312
|
run-15/checkpoint-172/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ae200490e151cf4610694ae2bb70cb226e5437a2a5f4f1695c98906d9657cce
|
3 |
+
size 35123898
|
run-15/checkpoint-172/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b99cb6263c36c5c191e9bbbef2d3167790018df547076ed69608752e2b4353d4
|
3 |
+
size 14308
|
run-15/checkpoint-172/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08bcb961298561b790f63cccbd5d8983b8beec6481b13664e1b511e0024353ae
|
3 |
+
size 1064
|
run-15/checkpoint-172/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 |
+
}
|
run-15/checkpoint-172/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-15/checkpoint-172/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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_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 |
+
}
|
run-15/checkpoint-172/trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.738,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-15/checkpoint-172",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 172,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"grad_norm": 4.1632184982299805,
|
14 |
+
"learning_rate": 0.0008185158371058891,
|
15 |
+
"loss": 0.596,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.8105351111111112,
|
21 |
+
"eval_BAC": 0.738,
|
22 |
+
"eval_MCC": 0.47685912032201233,
|
23 |
+
"eval_PR_AUC": 0.7725723255076244,
|
24 |
+
"eval_accuracy": 0.738,
|
25 |
+
"eval_loss": 0.5038211345672607,
|
26 |
+
"eval_runtime": 6.2713,
|
27 |
+
"eval_samples_per_second": 239.187,
|
28 |
+
"eval_steps_per_second": 7.495,
|
29 |
+
"step": 172
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"logging_steps": 500,
|
33 |
+
"max_steps": 1376,
|
34 |
+
"num_input_tokens_seen": 0,
|
35 |
+
"num_train_epochs": 8,
|
36 |
+
"save_steps": 500,
|
37 |
+
"stateful_callbacks": {
|
38 |
+
"TrainerControl": {
|
39 |
+
"args": {
|
40 |
+
"should_epoch_stop": false,
|
41 |
+
"should_evaluate": false,
|
42 |
+
"should_log": false,
|
43 |
+
"should_save": true,
|
44 |
+
"should_training_stop": false
|
45 |
+
},
|
46 |
+
"attributes": {}
|
47 |
+
}
|
48 |
+
},
|
49 |
+
"total_flos": 450377730000.0,
|
50 |
+
"train_batch_size": 32,
|
51 |
+
"trial_name": null,
|
52 |
+
"trial_params": {
|
53 |
+
"alpha": 0.9064804959719234,
|
54 |
+
"learning_rate": 0.0009354466709781589,
|
55 |
+
"num_train_epochs": 8,
|
56 |
+
"temperature": 19
|
57 |
+
}
|
58 |
+
}
|
run-15/checkpoint-172/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d1461bddfc617a28fee1074dc029698599dfb9300cdfd81f3ac264a73049462
|
3 |
+
size 5240
|
run-15/checkpoint-172/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d1461bddfc617a28fee1074dc029698599dfb9300cdfd81f3ac264a73049462
|
3 |
size 5240
|