anamelchor
commited on
Commit
•
cafd6ac
1
Parent(s):
6b02635
Training in progress, epoch 1
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- model.safetensors +1 -1
- run-0/checkpoint-28/config.json +27 -0
- run-0/checkpoint-28/model.safetensors +3 -0
- run-0/checkpoint-28/optimizer.pt +3 -0
- run-0/checkpoint-28/rng_state.pth +3 -0
- run-0/checkpoint-28/scheduler.pt +3 -0
- run-0/checkpoint-28/special_tokens_map.json +7 -0
- run-0/checkpoint-28/tokenizer.json +0 -0
- run-0/checkpoint-28/tokenizer_config.json +55 -0
- run-0/checkpoint-28/trainer_state.json +44 -0
- run-0/checkpoint-28/training_args.bin +3 -0
- run-0/checkpoint-28/vocab.txt +0 -0
- run-0/checkpoint-42/config.json +27 -0
- run-0/checkpoint-42/model.safetensors +3 -0
- run-0/checkpoint-42/optimizer.pt +3 -0
- run-0/checkpoint-42/rng_state.pth +3 -0
- run-0/checkpoint-42/scheduler.pt +3 -0
- run-0/checkpoint-42/special_tokens_map.json +7 -0
- run-0/checkpoint-42/tokenizer.json +0 -0
- run-0/checkpoint-42/tokenizer_config.json +55 -0
- run-0/checkpoint-42/trainer_state.json +53 -0
- run-0/checkpoint-42/training_args.bin +3 -0
- run-0/checkpoint-42/vocab.txt +0 -0
- run-0/checkpoint-56/config.json +27 -0
- run-0/checkpoint-56/model.safetensors +3 -0
- run-0/checkpoint-56/optimizer.pt +3 -0
- run-0/checkpoint-56/rng_state.pth +3 -0
- run-0/checkpoint-56/scheduler.pt +3 -0
- run-0/checkpoint-56/special_tokens_map.json +7 -0
- run-0/checkpoint-56/tokenizer.json +0 -0
- run-0/checkpoint-56/tokenizer_config.json +55 -0
- run-0/checkpoint-56/trainer_state.json +62 -0
- run-0/checkpoint-56/training_args.bin +3 -0
- run-0/checkpoint-56/vocab.txt +0 -0
- run-0/checkpoint-70/config.json +27 -0
- run-0/checkpoint-70/model.safetensors +3 -0
- run-0/checkpoint-70/optimizer.pt +3 -0
- run-0/checkpoint-70/rng_state.pth +3 -0
- run-0/checkpoint-70/scheduler.pt +3 -0
- run-0/checkpoint-70/special_tokens_map.json +7 -0
- run-0/checkpoint-70/tokenizer.json +0 -0
- run-0/checkpoint-70/tokenizer_config.json +55 -0
- run-0/checkpoint-70/trainer_state.json +71 -0
- run-0/checkpoint-70/training_args.bin +3 -0
- run-0/checkpoint-70/vocab.txt +0 -0
- run-1/checkpoint-27/config.json +27 -0
- run-1/checkpoint-27/model.safetensors +3 -0
- run-1/checkpoint-27/optimizer.pt +3 -0
- run-1/checkpoint-27/rng_state.pth +3 -0
- run-1/checkpoint-27/scheduler.pt +3 -0
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 sha256:5fcc181451301798b54be3d9e7a78f85d6907820dc4c74a9fd4726c1f118305a
|
3 |
size 437958648
|
run-0/checkpoint-28/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-0/checkpoint-28/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6377819e15ed83dd817b895768691af0622c98ef48096cd08d358b9dcf762b92
|
3 |
+
size 437958648
|
run-0/checkpoint-28/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:534d557d8ca1a78912bbc9816667253c71fb69168f99d2396f1de5e2a9f2bf07
|
3 |
+
size 876038394
|
run-0/checkpoint-28/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a646e0a4e1ae5513e0c62f07f6c3ee267a92a2277a8293ddf235f8e2f74e0331
|
3 |
+
size 14308
|
run-0/checkpoint-28/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e127a735df00ad010829fe70859cbcd291b7ae24214299de1a845742296b7744
|
3 |
+
size 1064
|
run-0/checkpoint-28/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-0/checkpoint-28/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-28/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-0/checkpoint-28/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6941514860977949,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-qnli/run-0/checkpoint-28",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 28,
|
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": 0.6912751677852349,
|
14 |
+
"eval_loss": 0.6039506196975708,
|
15 |
+
"eval_runtime": 1.3411,
|
16 |
+
"eval_samples_per_second": 777.73,
|
17 |
+
"eval_steps_per_second": 49.214,
|
18 |
+
"step": 14
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.6941514860977949,
|
23 |
+
"eval_loss": 0.5453055500984192,
|
24 |
+
"eval_runtime": 1.4385,
|
25 |
+
"eval_samples_per_second": 725.079,
|
26 |
+
"eval_steps_per_second": 45.882,
|
27 |
+
"step": 28
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 70,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 5,
|
34 |
+
"save_steps": 500,
|
35 |
+
"total_flos": 0,
|
36 |
+
"train_batch_size": 64,
|
37 |
+
"trial_name": null,
|
38 |
+
"trial_params": {
|
39 |
+
"learning_rate": 4.85616163033555e-05,
|
40 |
+
"num_train_epochs": 5,
|
41 |
+
"per_device_train_batch_size": 64,
|
42 |
+
"seed": 33
|
43 |
+
}
|
44 |
+
}
|
run-0/checkpoint-28/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0442d15116d6d6d98fb40bd2b1c446b3e1c87aa21e7274a8954d5b6a1ff24d7a
|
3 |
+
size 4920
|
run-0/checkpoint-28/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-42/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-0/checkpoint-42/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4624a9412d64c04ab7a8e68b3a9c0dc097fb8b407373164293e6ce317bfa2315
|
3 |
+
size 437958648
|
run-0/checkpoint-42/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b9919119147f91ab616ac345defc16c5971dcfe5206e6559b99d461db6cffb8
|
3 |
+
size 876038394
|
run-0/checkpoint-42/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abb841ebedde002effa8d5525ef18f685043dcd9ea764a557641f39f766f4358
|
3 |
+
size 14308
|
run-0/checkpoint-42/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8f947e99cd0dd30c894cc491636f3d99c045dd98cfdcc61423e330976361fac
|
3 |
+
size 1064
|
run-0/checkpoint-42/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-0/checkpoint-42/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-42/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-0/checkpoint-42/trainer_state.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7555129434324065,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-qnli/run-0/checkpoint-42",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 42,
|
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": 0.6912751677852349,
|
14 |
+
"eval_loss": 0.6039506196975708,
|
15 |
+
"eval_runtime": 1.3411,
|
16 |
+
"eval_samples_per_second": 777.73,
|
17 |
+
"eval_steps_per_second": 49.214,
|
18 |
+
"step": 14
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.6941514860977949,
|
23 |
+
"eval_loss": 0.5453055500984192,
|
24 |
+
"eval_runtime": 1.4385,
|
25 |
+
"eval_samples_per_second": 725.079,
|
26 |
+
"eval_steps_per_second": 45.882,
|
27 |
+
"step": 28
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_accuracy": 0.7555129434324065,
|
32 |
+
"eval_loss": 0.573279619216919,
|
33 |
+
"eval_runtime": 2.3373,
|
34 |
+
"eval_samples_per_second": 446.245,
|
35 |
+
"eval_steps_per_second": 28.238,
|
36 |
+
"step": 42
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"logging_steps": 500,
|
40 |
+
"max_steps": 70,
|
41 |
+
"num_input_tokens_seen": 0,
|
42 |
+
"num_train_epochs": 5,
|
43 |
+
"save_steps": 500,
|
44 |
+
"total_flos": 0,
|
45 |
+
"train_batch_size": 64,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": {
|
48 |
+
"learning_rate": 4.85616163033555e-05,
|
49 |
+
"num_train_epochs": 5,
|
50 |
+
"per_device_train_batch_size": 64,
|
51 |
+
"seed": 33
|
52 |
+
}
|
53 |
+
}
|
run-0/checkpoint-42/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0442d15116d6d6d98fb40bd2b1c446b3e1c87aa21e7274a8954d5b6a1ff24d7a
|
3 |
+
size 4920
|
run-0/checkpoint-42/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-56/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-0/checkpoint-56/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc3b4cdfbd4bbfd6a0083360516ef84d2c4244615a936e47c98e0f2a0270c1cf
|
3 |
+
size 437958648
|
run-0/checkpoint-56/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:830ee9f78e7f02f4555ce8abe2d12a02d64d3828585b53c75208f9ab8a7acaf1
|
3 |
+
size 876038394
|
run-0/checkpoint-56/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5c465bbe5e77275d1bee0bf2905b792f24b272174f5c364bd2503ed3dfc3012
|
3 |
+
size 14308
|
run-0/checkpoint-56/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58d9c450e62fa6f212f1ca2c5f127177d481cc4ceb0ae583424f9dded33b591f
|
3 |
+
size 1064
|
run-0/checkpoint-56/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-0/checkpoint-56/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-56/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-0/checkpoint-56/trainer_state.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.775647171620326,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-qnli/run-0/checkpoint-56",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 56,
|
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": 0.6912751677852349,
|
14 |
+
"eval_loss": 0.6039506196975708,
|
15 |
+
"eval_runtime": 1.3411,
|
16 |
+
"eval_samples_per_second": 777.73,
|
17 |
+
"eval_steps_per_second": 49.214,
|
18 |
+
"step": 14
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.6941514860977949,
|
23 |
+
"eval_loss": 0.5453055500984192,
|
24 |
+
"eval_runtime": 1.4385,
|
25 |
+
"eval_samples_per_second": 725.079,
|
26 |
+
"eval_steps_per_second": 45.882,
|
27 |
+
"step": 28
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_accuracy": 0.7555129434324065,
|
32 |
+
"eval_loss": 0.573279619216919,
|
33 |
+
"eval_runtime": 2.3373,
|
34 |
+
"eval_samples_per_second": 446.245,
|
35 |
+
"eval_steps_per_second": 28.238,
|
36 |
+
"step": 42
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_accuracy": 0.775647171620326,
|
41 |
+
"eval_loss": 0.5979775190353394,
|
42 |
+
"eval_runtime": 1.7938,
|
43 |
+
"eval_samples_per_second": 581.441,
|
44 |
+
"eval_steps_per_second": 36.793,
|
45 |
+
"step": 56
|
46 |
+
}
|
47 |
+
],
|
48 |
+
"logging_steps": 500,
|
49 |
+
"max_steps": 70,
|
50 |
+
"num_input_tokens_seen": 0,
|
51 |
+
"num_train_epochs": 5,
|
52 |
+
"save_steps": 500,
|
53 |
+
"total_flos": 0,
|
54 |
+
"train_batch_size": 64,
|
55 |
+
"trial_name": null,
|
56 |
+
"trial_params": {
|
57 |
+
"learning_rate": 4.85616163033555e-05,
|
58 |
+
"num_train_epochs": 5,
|
59 |
+
"per_device_train_batch_size": 64,
|
60 |
+
"seed": 33
|
61 |
+
}
|
62 |
+
}
|
run-0/checkpoint-56/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0442d15116d6d6d98fb40bd2b1c446b3e1c87aa21e7274a8954d5b6a1ff24d7a
|
3 |
+
size 4920
|
run-0/checkpoint-56/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-70/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-0/checkpoint-70/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04ed467294f494ae5cb904d0327aff0fe18f47d08ec093d6096f2c69f5926809
|
3 |
+
size 437958648
|
run-0/checkpoint-70/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c1acc3e1ea7fce04cb0db6e6dbc41249aa594f33390f80eabd6d911ec9634d9
|
3 |
+
size 876038394
|
run-0/checkpoint-70/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c630cee81f18143146235db6503c944621a4dfa0830d74e7e22cdde5d6d410ed
|
3 |
+
size 14308
|
run-0/checkpoint-70/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ac2161aae87daaf1f2b020f78fcdc46bd9c6b516ccdb967bb6c3dfca1012a45
|
3 |
+
size 1064
|
run-0/checkpoint-70/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-0/checkpoint-70/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-70/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-0/checkpoint-70/trainer_state.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.775647171620326,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-qnli/run-0/checkpoint-56",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 70,
|
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": 0.6912751677852349,
|
14 |
+
"eval_loss": 0.6039506196975708,
|
15 |
+
"eval_runtime": 1.3411,
|
16 |
+
"eval_samples_per_second": 777.73,
|
17 |
+
"eval_steps_per_second": 49.214,
|
18 |
+
"step": 14
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.6941514860977949,
|
23 |
+
"eval_loss": 0.5453055500984192,
|
24 |
+
"eval_runtime": 1.4385,
|
25 |
+
"eval_samples_per_second": 725.079,
|
26 |
+
"eval_steps_per_second": 45.882,
|
27 |
+
"step": 28
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_accuracy": 0.7555129434324065,
|
32 |
+
"eval_loss": 0.573279619216919,
|
33 |
+
"eval_runtime": 2.3373,
|
34 |
+
"eval_samples_per_second": 446.245,
|
35 |
+
"eval_steps_per_second": 28.238,
|
36 |
+
"step": 42
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_accuracy": 0.775647171620326,
|
41 |
+
"eval_loss": 0.5979775190353394,
|
42 |
+
"eval_runtime": 1.7938,
|
43 |
+
"eval_samples_per_second": 581.441,
|
44 |
+
"eval_steps_per_second": 36.793,
|
45 |
+
"step": 56
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 5.0,
|
49 |
+
"eval_accuracy": 0.7708533077660594,
|
50 |
+
"eval_loss": 0.6849012970924377,
|
51 |
+
"eval_runtime": 1.6211,
|
52 |
+
"eval_samples_per_second": 643.392,
|
53 |
+
"eval_steps_per_second": 40.713,
|
54 |
+
"step": 70
|
55 |
+
}
|
56 |
+
],
|
57 |
+
"logging_steps": 500,
|
58 |
+
"max_steps": 70,
|
59 |
+
"num_input_tokens_seen": 0,
|
60 |
+
"num_train_epochs": 5,
|
61 |
+
"save_steps": 500,
|
62 |
+
"total_flos": 0,
|
63 |
+
"train_batch_size": 64,
|
64 |
+
"trial_name": null,
|
65 |
+
"trial_params": {
|
66 |
+
"learning_rate": 4.85616163033555e-05,
|
67 |
+
"num_train_epochs": 5,
|
68 |
+
"per_device_train_batch_size": 64,
|
69 |
+
"seed": 33
|
70 |
+
}
|
71 |
+
}
|
run-0/checkpoint-70/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0442d15116d6d6d98fb40bd2b1c446b3e1c87aa21e7274a8954d5b6a1ff24d7a
|
3 |
+
size 4920
|
run-0/checkpoint-70/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-27/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-27/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fcc181451301798b54be3d9e7a78f85d6907820dc4c74a9fd4726c1f118305a
|
3 |
+
size 437958648
|
run-1/checkpoint-27/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a24d9b9ba50bb0dbf0c72ab8a5a38aeb6415c7853fd0da8e69cc16607c8685b3
|
3 |
+
size 876038394
|
run-1/checkpoint-27/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30bc2234ab8c220ef2038bc7f82f6f788affb7b90d7b6db371d4187babceb94f
|
3 |
+
size 14244
|
run-1/checkpoint-27/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:200f1219191b0ecfe5ae4e1a6659c774fa1382e7ae7895a6a10774de69c2abf5
|
3 |
+
size 1064
|