ana-grassmann
commited on
Commit
•
c8f482b
1
Parent(s):
bf32ecb
Training in progress, epoch 3
Browse files- model.safetensors +1 -1
- run-1/checkpoint-1254/config.json +27 -0
- run-1/checkpoint-1254/model.safetensors +3 -0
- run-1/checkpoint-1254/optimizer.pt +3 -0
- run-1/checkpoint-1254/rng_state.pth +3 -0
- run-1/checkpoint-1254/scheduler.pt +3 -0
- run-1/checkpoint-1254/special_tokens_map.json +7 -0
- run-1/checkpoint-1254/tokenizer.json +0 -0
- run-1/checkpoint-1254/tokenizer_config.json +55 -0
- run-1/checkpoint-1254/trainer_state.json +67 -0
- run-1/checkpoint-1254/training_args.bin +3 -0
- run-1/checkpoint-1254/vocab.txt +0 -0
- run-1/checkpoint-836/config.json +27 -0
- run-1/checkpoint-836/model.safetensors +3 -0
- run-1/checkpoint-836/optimizer.pt +3 -0
- run-1/checkpoint-836/rng_state.pth +3 -0
- run-1/checkpoint-836/scheduler.pt +3 -0
- run-1/checkpoint-836/special_tokens_map.json +7 -0
- run-1/checkpoint-836/tokenizer.json +0 -0
- run-1/checkpoint-836/tokenizer_config.json +55 -0
- run-1/checkpoint-836/trainer_state.json +51 -0
- run-1/checkpoint-836/training_args.bin +3 -0
- run-1/checkpoint-836/vocab.txt +0 -0
- runs/Mar21_16-50-03_43ee8d6b3d53/events.out.tfevents.1711041077.43ee8d6b3d53.2090.1 +2 -2
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437958648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7dcbeda55097af57b723f3c572c73a4ac0273f536f4983f245d3a89e00cc812
|
3 |
size 437958648
|
run-1/checkpoint-1254/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
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 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
run-1/checkpoint-1254/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7dcbeda55097af57b723f3c572c73a4ac0273f536f4983f245d3a89e00cc812
|
3 |
+
size 437958648
|
run-1/checkpoint-1254/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:630dc0288a30e165cfcb5a0b61316d0f904e9b137a7a8b1f657d4166dfb82633
|
3 |
+
size 876038394
|
run-1/checkpoint-1254/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d16934ddb65a0cdde96ecdc5a40c32200e35b587e85a8aee6af23fd1ff50d843
|
3 |
+
size 14308
|
run-1/checkpoint-1254/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6ee60a7dbe0f6d8c5d94d17ba554afc467ce5d5fcb91b2f48697f8fe19f5ef6
|
3 |
+
size 1064
|
run-1/checkpoint-1254/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-1/checkpoint-1254/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-1254/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-1/checkpoint-1254/trainer_state.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9800479328939484,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-1/checkpoint-1254",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1254,
|
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 |
+
"eval_accuracy": 0.954104254044338,
|
14 |
+
"eval_loss": 0.19407691061496735,
|
15 |
+
"eval_runtime": 591.9344,
|
16 |
+
"eval_samples_per_second": 28.196,
|
17 |
+
"eval_steps_per_second": 1.764,
|
18 |
+
"step": 418
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.2,
|
22 |
+
"grad_norm": 2.8940045833587646,
|
23 |
+
"learning_rate": 5.932776707197725e-05,
|
24 |
+
"loss": 0.2105,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.9713600958657879,
|
30 |
+
"eval_loss": 0.1521669328212738,
|
31 |
+
"eval_runtime": 587.4301,
|
32 |
+
"eval_samples_per_second": 28.412,
|
33 |
+
"eval_steps_per_second": 1.777,
|
34 |
+
"step": 836
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.39,
|
38 |
+
"grad_norm": 0.07928234338760376,
|
39 |
+
"learning_rate": 1.9985746467217804e-05,
|
40 |
+
"loss": 0.0822,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.9800479328939484,
|
46 |
+
"eval_loss": 0.10306233912706375,
|
47 |
+
"eval_runtime": 588.0912,
|
48 |
+
"eval_samples_per_second": 28.38,
|
49 |
+
"eval_steps_per_second": 1.775,
|
50 |
+
"step": 1254
|
51 |
+
}
|
52 |
+
],
|
53 |
+
"logging_steps": 500,
|
54 |
+
"max_steps": 1254,
|
55 |
+
"num_input_tokens_seen": 0,
|
56 |
+
"num_train_epochs": 3,
|
57 |
+
"save_steps": 500,
|
58 |
+
"total_flos": 4182298224915840.0,
|
59 |
+
"train_batch_size": 16,
|
60 |
+
"trial_name": null,
|
61 |
+
"trial_params": {
|
62 |
+
"learning_rate": 9.86697876767367e-05,
|
63 |
+
"num_train_epochs": 3,
|
64 |
+
"per_device_train_batch_size": 16,
|
65 |
+
"seed": 14
|
66 |
+
}
|
67 |
+
}
|
run-1/checkpoint-1254/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a1bc2ca1486d4354691d2859ca88c677e08f3269d34ab4a0a8373406db2ace6
|
3 |
+
size 4920
|
run-1/checkpoint-1254/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-836/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
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 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
run-1/checkpoint-836/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:754b1f12d2941c2a4b7c82a04cd180fa1e21d612210cc0e5b26615124d22d073
|
3 |
+
size 437958648
|
run-1/checkpoint-836/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4753cc331725be14961819c14a47d2d74975bd4008094bd86556c3a67d24ce48
|
3 |
+
size 876038394
|
run-1/checkpoint-836/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52e52d2f106a39352fe52613827135083798cde68853ad724f7d272acdf12e9d
|
3 |
+
size 14308
|
run-1/checkpoint-836/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f21d9f88cb55bb00ed8f28278606f452481cff66c77e80694f9fbee7391b9fd8
|
3 |
+
size 1064
|
run-1/checkpoint-836/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-1/checkpoint-836/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-836/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-1/checkpoint-836/trainer_state.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9713600958657879,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-1/checkpoint-836",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 836,
|
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 |
+
"eval_accuracy": 0.954104254044338,
|
14 |
+
"eval_loss": 0.19407691061496735,
|
15 |
+
"eval_runtime": 591.9344,
|
16 |
+
"eval_samples_per_second": 28.196,
|
17 |
+
"eval_steps_per_second": 1.764,
|
18 |
+
"step": 418
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.2,
|
22 |
+
"grad_norm": 2.8940045833587646,
|
23 |
+
"learning_rate": 5.932776707197725e-05,
|
24 |
+
"loss": 0.2105,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.9713600958657879,
|
30 |
+
"eval_loss": 0.1521669328212738,
|
31 |
+
"eval_runtime": 587.4301,
|
32 |
+
"eval_samples_per_second": 28.412,
|
33 |
+
"eval_steps_per_second": 1.777,
|
34 |
+
"step": 836
|
35 |
+
}
|
36 |
+
],
|
37 |
+
"logging_steps": 500,
|
38 |
+
"max_steps": 1254,
|
39 |
+
"num_input_tokens_seen": 0,
|
40 |
+
"num_train_epochs": 3,
|
41 |
+
"save_steps": 500,
|
42 |
+
"total_flos": 2092966223184000.0,
|
43 |
+
"train_batch_size": 16,
|
44 |
+
"trial_name": null,
|
45 |
+
"trial_params": {
|
46 |
+
"learning_rate": 9.86697876767367e-05,
|
47 |
+
"num_train_epochs": 3,
|
48 |
+
"per_device_train_batch_size": 16,
|
49 |
+
"seed": 14
|
50 |
+
}
|
51 |
+
}
|
run-1/checkpoint-836/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a1bc2ca1486d4354691d2859ca88c677e08f3269d34ab4a0a8373406db2ace6
|
3 |
+
size 4920
|
run-1/checkpoint-836/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar21_16-50-03_43ee8d6b3d53/events.out.tfevents.1711041077.43ee8d6b3d53.2090.1
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:ba45c38794d2fe122a395e147686e54dd890fba431221e8bbdf1163bd5c576a8
|
3 |
+
size 6383
|