Commit
•
793a500
1
Parent(s):
0367d3c
Training in progress, epoch 2
Browse files- model.safetensors +1 -1
- run-6/checkpoint-268/config.json +25 -0
- run-6/checkpoint-268/model.safetensors +3 -0
- run-6/checkpoint-268/optimizer.pt +3 -0
- run-6/checkpoint-268/rng_state.pth +3 -0
- run-6/checkpoint-268/scheduler.pt +3 -0
- run-6/checkpoint-268/special_tokens_map.json +7 -0
- run-6/checkpoint-268/tokenizer.json +0 -0
- run-6/checkpoint-268/tokenizer_config.json +55 -0
- run-6/checkpoint-268/trainer_state.json +37 -0
- run-6/checkpoint-268/training_args.bin +3 -0
- run-6/checkpoint-268/vocab.txt +0 -0
- run-7/checkpoint-1069/config.json +25 -0
- run-7/checkpoint-1069/model.safetensors +3 -0
- run-7/checkpoint-1069/optimizer.pt +3 -0
- run-7/checkpoint-1069/rng_state.pth +3 -0
- run-7/checkpoint-1069/scheduler.pt +3 -0
- run-7/checkpoint-1069/special_tokens_map.json +7 -0
- run-7/checkpoint-1069/tokenizer.json +0 -0
- run-7/checkpoint-1069/tokenizer_config.json +55 -0
- run-7/checkpoint-1069/trainer_state.json +61 -0
- run-7/checkpoint-1069/training_args.bin +3 -0
- run-7/checkpoint-1069/vocab.txt +0 -0
- run-7/checkpoint-2138/config.json +25 -0
- run-7/checkpoint-2138/model.safetensors +3 -0
- run-7/checkpoint-2138/optimizer.pt +3 -0
- run-7/checkpoint-2138/rng_state.pth +3 -0
- run-7/checkpoint-2138/scheduler.pt +3 -0
- run-7/checkpoint-2138/special_tokens_map.json +7 -0
- run-7/checkpoint-2138/tokenizer.json +0 -0
- run-7/checkpoint-2138/tokenizer_config.json +55 -0
- run-7/checkpoint-2138/trainer_state.json +84 -0
- run-7/checkpoint-2138/training_args.bin +3 -0
- run-7/checkpoint-2138/vocab.txt +0 -0
- runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723864031.b5f02c58e851.301.8 +3 -0
- runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723864059.b5f02c58e851.301.9 +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ece9257eae5f80e7eefc99c741b9b50c7f0f5258508f7b5a30317f034a7ccee
|
3 |
size 267832560
|
run-6/checkpoint-268/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.44.0",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-6/checkpoint-268/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:013c04aa340ef41c9374e7905e567557b71d93e104694d7bb9c8216ce5d74693
|
3 |
+
size 267832560
|
run-6/checkpoint-268/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:566fec9aa93b473f70dd3d824a34d0d88d0c42ca5c75264e3ff4e27dcf1ef4fc
|
3 |
+
size 535727290
|
run-6/checkpoint-268/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e4d50d736a66a8af24800ffaff167e56b398ac8ed3a0915e799e4ba26ab902c
|
3 |
+
size 14244
|
run-6/checkpoint-268/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7086a641d21ec9508bd45a67bd7d87d14ff822e32be7c50619cc1c86d5be14b8
|
3 |
+
size 1064
|
run-6/checkpoint-268/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-6/checkpoint-268/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-6/checkpoint-268/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": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-6/checkpoint-268/trainer_state.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 268,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [],
|
11 |
+
"logging_steps": 500,
|
12 |
+
"max_steps": 268,
|
13 |
+
"num_input_tokens_seen": 0,
|
14 |
+
"num_train_epochs": 1,
|
15 |
+
"save_steps": 500,
|
16 |
+
"stateful_callbacks": {
|
17 |
+
"TrainerControl": {
|
18 |
+
"args": {
|
19 |
+
"should_epoch_stop": false,
|
20 |
+
"should_evaluate": false,
|
21 |
+
"should_log": false,
|
22 |
+
"should_save": true,
|
23 |
+
"should_training_stop": true
|
24 |
+
},
|
25 |
+
"attributes": {}
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"total_flos": 0,
|
29 |
+
"train_batch_size": 32,
|
30 |
+
"trial_name": null,
|
31 |
+
"trial_params": {
|
32 |
+
"learning_rate": 1.6346025152713588e-06,
|
33 |
+
"num_train_epochs": 1,
|
34 |
+
"per_device_train_batch_size": 32,
|
35 |
+
"seed": 25
|
36 |
+
}
|
37 |
+
}
|
run-6/checkpoint-268/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54ca454c86eaaa647c649f9d93dea6a429ad8e94c8c6adca1348aae7c4fc5f0b
|
3 |
+
size 5240
|
run-6/checkpoint-268/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-7/checkpoint-1069/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.44.0",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-7/checkpoint-1069/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf945a4cb72b7f07ea06c29c90ef2dc26fadb9cfd5008c8e15b5640f10cb4dff
|
3 |
+
size 267832560
|
run-7/checkpoint-1069/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:535a306ba7c3590d9d23342f62e0e86236d9597abc9c85c2f15626ded1e7ea98
|
3 |
+
size 535727290
|
run-7/checkpoint-1069/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:991df4aa76f24d91526e7e51a90de580470ee9ff4e3f5336667f187c26f0e6c4
|
3 |
+
size 14244
|
run-7/checkpoint-1069/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75cdd5628239fee0b56334346304f649325520a5cd5a761550cce211c947a457
|
3 |
+
size 1064
|
run-7/checkpoint-1069/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-7/checkpoint-1069/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-7/checkpoint-1069/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": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-7/checkpoint-1069/trainer_state.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.46472372045336796,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-1069",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1069,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.4677268475210477,
|
13 |
+
"grad_norm": 12.974456787109375,
|
14 |
+
"learning_rate": 1.1101348047567246e-05,
|
15 |
+
"loss": 0.5482,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.9354536950420954,
|
20 |
+
"grad_norm": 6.763242721557617,
|
21 |
+
"learning_rate": 9.955698094257931e-06,
|
22 |
+
"loss": 0.4949,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.0,
|
27 |
+
"eval_loss": 0.47264614701271057,
|
28 |
+
"eval_matthews_correlation": 0.46472372045336796,
|
29 |
+
"eval_runtime": 0.7997,
|
30 |
+
"eval_samples_per_second": 1304.217,
|
31 |
+
"eval_steps_per_second": 82.53,
|
32 |
+
"step": 1069
|
33 |
+
}
|
34 |
+
],
|
35 |
+
"logging_steps": 500,
|
36 |
+
"max_steps": 5345,
|
37 |
+
"num_input_tokens_seen": 0,
|
38 |
+
"num_train_epochs": 5,
|
39 |
+
"save_steps": 500,
|
40 |
+
"stateful_callbacks": {
|
41 |
+
"TrainerControl": {
|
42 |
+
"args": {
|
43 |
+
"should_epoch_stop": false,
|
44 |
+
"should_evaluate": false,
|
45 |
+
"should_log": false,
|
46 |
+
"should_save": true,
|
47 |
+
"should_training_stop": false
|
48 |
+
},
|
49 |
+
"attributes": {}
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"total_flos": 145295003393040.0,
|
53 |
+
"train_batch_size": 8,
|
54 |
+
"trial_name": null,
|
55 |
+
"trial_params": {
|
56 |
+
"learning_rate": 1.2246998000876558e-05,
|
57 |
+
"num_train_epochs": 5,
|
58 |
+
"per_device_train_batch_size": 8,
|
59 |
+
"seed": 6
|
60 |
+
}
|
61 |
+
}
|
run-7/checkpoint-1069/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fa913b6dd4193043ca75983cebb619f3f12421d16f3812039f1dd107acad34f
|
3 |
+
size 5240
|
run-7/checkpoint-1069/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-7/checkpoint-2138/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.44.0",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-7/checkpoint-2138/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ece9257eae5f80e7eefc99c741b9b50c7f0f5258508f7b5a30317f034a7ccee
|
3 |
+
size 267832560
|
run-7/checkpoint-2138/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a47526de69f653d290a76d28b0a7c4af7352364bfa71aad91c5b854dfff01fff
|
3 |
+
size 535727290
|
run-7/checkpoint-2138/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90df934dd18ebd7d91cb8acb41efb58fb7d921aa4d2cfcc4238089f367f711f7
|
3 |
+
size 14244
|
run-7/checkpoint-2138/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a07338759d3c36bc9346a7dde55e24b372b8253ea7bb3a52166d4bb3c8c3bc7a
|
3 |
+
size 1064
|
run-7/checkpoint-2138/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-7/checkpoint-2138/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-7/checkpoint-2138/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": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-7/checkpoint-2138/trainer_state.json
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5238946707778435,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-2138",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2138,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.4677268475210477,
|
13 |
+
"grad_norm": 12.974456787109375,
|
14 |
+
"learning_rate": 1.1101348047567246e-05,
|
15 |
+
"loss": 0.5482,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.9354536950420954,
|
20 |
+
"grad_norm": 6.763242721557617,
|
21 |
+
"learning_rate": 9.955698094257931e-06,
|
22 |
+
"loss": 0.4949,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.0,
|
27 |
+
"eval_loss": 0.47264614701271057,
|
28 |
+
"eval_matthews_correlation": 0.46472372045336796,
|
29 |
+
"eval_runtime": 0.7997,
|
30 |
+
"eval_samples_per_second": 1304.217,
|
31 |
+
"eval_steps_per_second": 82.53,
|
32 |
+
"step": 1069
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.4031805425631432,
|
36 |
+
"grad_norm": 21.93242835998535,
|
37 |
+
"learning_rate": 8.810048140948619e-06,
|
38 |
+
"loss": 0.3822,
|
39 |
+
"step": 1500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.8709073900841908,
|
43 |
+
"grad_norm": 23.08902359008789,
|
44 |
+
"learning_rate": 7.664398187639304e-06,
|
45 |
+
"loss": 0.3651,
|
46 |
+
"step": 2000
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 2.0,
|
50 |
+
"eval_loss": 0.5118151903152466,
|
51 |
+
"eval_matthews_correlation": 0.5238946707778435,
|
52 |
+
"eval_runtime": 0.7256,
|
53 |
+
"eval_samples_per_second": 1437.525,
|
54 |
+
"eval_steps_per_second": 90.965,
|
55 |
+
"step": 2138
|
56 |
+
}
|
57 |
+
],
|
58 |
+
"logging_steps": 500,
|
59 |
+
"max_steps": 5345,
|
60 |
+
"num_input_tokens_seen": 0,
|
61 |
+
"num_train_epochs": 5,
|
62 |
+
"save_steps": 500,
|
63 |
+
"stateful_callbacks": {
|
64 |
+
"TrainerControl": {
|
65 |
+
"args": {
|
66 |
+
"should_epoch_stop": false,
|
67 |
+
"should_evaluate": false,
|
68 |
+
"should_log": false,
|
69 |
+
"should_save": true,
|
70 |
+
"should_training_stop": false
|
71 |
+
},
|
72 |
+
"attributes": {}
|
73 |
+
}
|
74 |
+
},
|
75 |
+
"total_flos": 182960762828856.0,
|
76 |
+
"train_batch_size": 8,
|
77 |
+
"trial_name": null,
|
78 |
+
"trial_params": {
|
79 |
+
"learning_rate": 1.2246998000876558e-05,
|
80 |
+
"num_train_epochs": 5,
|
81 |
+
"per_device_train_batch_size": 8,
|
82 |
+
"seed": 6
|
83 |
+
}
|
84 |
+
}
|
run-7/checkpoint-2138/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fa913b6dd4193043ca75983cebb619f3f12421d16f3812039f1dd107acad34f
|
3 |
+
size 5240
|
run-7/checkpoint-2138/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723864031.b5f02c58e851.301.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:205f86dcece1c79246874c4238b329cbcd56b791c2fde0974a4a2412bb8cc178
|
3 |
+
size 5233
|
runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723864059.b5f02c58e851.301.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e79883f3175656d7cf17931867dfa4f0fcae30f462470ad878ec58cdf2995eb
|
3 |
+
size 7924
|
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 sha256:6fa913b6dd4193043ca75983cebb619f3f12421d16f3812039f1dd107acad34f
|
3 |
size 5240
|