wennycooper
commited on
Commit
•
255aaf4
1
Parent(s):
6b7ac07
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-1/checkpoint-268/config.json +25 -0
- run-1/checkpoint-268/model.safetensors +3 -0
- run-1/checkpoint-268/optimizer.pt +3 -0
- run-1/checkpoint-268/rng_state.pth +3 -0
- run-1/checkpoint-268/scheduler.pt +3 -0
- run-1/checkpoint-268/special_tokens_map.json +7 -0
- run-1/checkpoint-268/tokenizer.json +0 -0
- run-1/checkpoint-268/tokenizer_config.json +55 -0
- run-1/checkpoint-268/trainer_state.json +56 -0
- run-1/checkpoint-268/training_args.bin +3 -0
- run-1/checkpoint-268/vocab.txt +0 -0
- run-1/checkpoint-402/config.json +25 -0
- run-1/checkpoint-402/model.safetensors +3 -0
- run-1/checkpoint-402/optimizer.pt +3 -0
- run-1/checkpoint-402/rng_state.pth +3 -0
- run-1/checkpoint-402/scheduler.pt +3 -0
- run-1/checkpoint-402/special_tokens_map.json +7 -0
- run-1/checkpoint-402/tokenizer.json +0 -0
- run-1/checkpoint-402/tokenizer_config.json +55 -0
- run-1/checkpoint-402/trainer_state.json +65 -0
- run-1/checkpoint-402/training_args.bin +3 -0
- run-1/checkpoint-402/vocab.txt +0 -0
- run-1/checkpoint-536/config.json +25 -0
- run-1/checkpoint-536/model.safetensors +3 -0
- run-1/checkpoint-536/optimizer.pt +3 -0
- run-1/checkpoint-536/rng_state.pth +3 -0
- run-1/checkpoint-536/scheduler.pt +3 -0
- run-1/checkpoint-536/special_tokens_map.json +7 -0
- run-1/checkpoint-536/tokenizer.json +0 -0
- run-1/checkpoint-536/tokenizer_config.json +55 -0
- run-1/checkpoint-536/trainer_state.json +81 -0
- run-1/checkpoint-536/training_args.bin +3 -0
- run-1/checkpoint-536/vocab.txt +0 -0
- run-2/checkpoint-268/config.json +25 -0
- run-2/checkpoint-268/model.safetensors +3 -0
- run-2/checkpoint-268/optimizer.pt +3 -0
- run-2/checkpoint-268/rng_state.pth +3 -0
- run-2/checkpoint-268/scheduler.pt +3 -0
- run-2/checkpoint-268/special_tokens_map.json +7 -0
- run-2/checkpoint-268/tokenizer.json +0 -0
- run-2/checkpoint-268/tokenizer_config.json +55 -0
- run-2/checkpoint-268/trainer_state.json +47 -0
- run-2/checkpoint-268/training_args.bin +3 -0
- run-2/checkpoint-268/vocab.txt +0 -0
- runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723862972.b5f02c58e851.301.3 +2 -2
- runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723863099.b5f02c58e851.301.4 +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 sha256:7877dbd402fd4c7c5ad15f79ca5e7c947037e9f10a80b1e27a5b4acf0002a216
|
3 |
size 267832560
|
run-1/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-1/checkpoint-268/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a33ce56e6f155f65f2b72ea9a64cb2e3f2a1fd2e8ab00c3e9982535856c9cfc
|
3 |
+
size 267832560
|
run-1/checkpoint-268/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b854364d2509ae745ae1287b23e73d54bcdd58ff77f24a992eae9d516c9c920
|
3 |
+
size 535727290
|
run-1/checkpoint-268/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67c7825404bfca8251e3494c1620a72bb2e77173338c20795f9bf4ce6c487968
|
3 |
+
size 14308
|
run-1/checkpoint-268/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c263bc87248cd527af5249dee5bbc801af464336129b12d7bba82e097aecbab1
|
3 |
+
size 1064
|
run-1/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-1/checkpoint-268/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/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-1/checkpoint-268/trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4550840399220741,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-268",
|
4 |
+
"epoch": 2.0,
|
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 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.49098527431488037,
|
14 |
+
"eval_matthews_correlation": 0.41038483457442687,
|
15 |
+
"eval_runtime": 0.7284,
|
16 |
+
"eval_samples_per_second": 1431.833,
|
17 |
+
"eval_steps_per_second": 90.605,
|
18 |
+
"step": 134
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.5078911185264587,
|
23 |
+
"eval_matthews_correlation": 0.4550840399220741,
|
24 |
+
"eval_runtime": 1.0357,
|
25 |
+
"eval_samples_per_second": 1007.09,
|
26 |
+
"eval_steps_per_second": 63.728,
|
27 |
+
"step": 268
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 536,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 4,
|
34 |
+
"save_steps": 500,
|
35 |
+
"stateful_callbacks": {
|
36 |
+
"TrainerControl": {
|
37 |
+
"args": {
|
38 |
+
"should_epoch_stop": false,
|
39 |
+
"should_evaluate": false,
|
40 |
+
"should_log": false,
|
41 |
+
"should_save": true,
|
42 |
+
"should_training_stop": false
|
43 |
+
},
|
44 |
+
"attributes": {}
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"total_flos": 0,
|
48 |
+
"train_batch_size": 64,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": {
|
51 |
+
"learning_rate": 8.177363502382625e-05,
|
52 |
+
"num_train_epochs": 4,
|
53 |
+
"per_device_train_batch_size": 64,
|
54 |
+
"seed": 17
|
55 |
+
}
|
56 |
+
}
|
run-1/checkpoint-268/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5421fa1053c0128f22a4daab188c4af9bc8bf9a37722e6659e71c91a49f1d4a9
|
3 |
+
size 5240
|
run-1/checkpoint-268/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-402/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-1/checkpoint-402/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c91e0ebbe05a9755377600ae2ef504b1d3d8557584a1f21dd5a03776b1b6e677
|
3 |
+
size 267832560
|
run-1/checkpoint-402/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6576a1eaad87593323b67778c7eefe2d8de0701c58216a043c96ba92d6a536ad
|
3 |
+
size 535727290
|
run-1/checkpoint-402/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77f86e680d310b7f1ea8d4b95f066e8ea8ff54d02f70ac8a4841624bdafe1676
|
3 |
+
size 14308
|
run-1/checkpoint-402/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5e7ef3c9aec9bfcd03ee578f53998ec2b9777cc66da20e582453278b1a959b2
|
3 |
+
size 1064
|
run-1/checkpoint-402/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-402/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-402/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-1/checkpoint-402/trainer_state.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4863630663948402,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-402",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 402,
|
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_loss": 0.49098527431488037,
|
14 |
+
"eval_matthews_correlation": 0.41038483457442687,
|
15 |
+
"eval_runtime": 0.7284,
|
16 |
+
"eval_samples_per_second": 1431.833,
|
17 |
+
"eval_steps_per_second": 90.605,
|
18 |
+
"step": 134
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.5078911185264587,
|
23 |
+
"eval_matthews_correlation": 0.4550840399220741,
|
24 |
+
"eval_runtime": 1.0357,
|
25 |
+
"eval_samples_per_second": 1007.09,
|
26 |
+
"eval_steps_per_second": 63.728,
|
27 |
+
"step": 268
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.6435816287994385,
|
32 |
+
"eval_matthews_correlation": 0.4863630663948402,
|
33 |
+
"eval_runtime": 0.7155,
|
34 |
+
"eval_samples_per_second": 1457.781,
|
35 |
+
"eval_steps_per_second": 92.247,
|
36 |
+
"step": 402
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"logging_steps": 500,
|
40 |
+
"max_steps": 536,
|
41 |
+
"num_input_tokens_seen": 0,
|
42 |
+
"num_train_epochs": 4,
|
43 |
+
"save_steps": 500,
|
44 |
+
"stateful_callbacks": {
|
45 |
+
"TrainerControl": {
|
46 |
+
"args": {
|
47 |
+
"should_epoch_stop": false,
|
48 |
+
"should_evaluate": false,
|
49 |
+
"should_log": false,
|
50 |
+
"should_save": true,
|
51 |
+
"should_training_stop": false
|
52 |
+
},
|
53 |
+
"attributes": {}
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"total_flos": 0,
|
57 |
+
"train_batch_size": 64,
|
58 |
+
"trial_name": null,
|
59 |
+
"trial_params": {
|
60 |
+
"learning_rate": 8.177363502382625e-05,
|
61 |
+
"num_train_epochs": 4,
|
62 |
+
"per_device_train_batch_size": 64,
|
63 |
+
"seed": 17
|
64 |
+
}
|
65 |
+
}
|
run-1/checkpoint-402/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5421fa1053c0128f22a4daab188c4af9bc8bf9a37722e6659e71c91a49f1d4a9
|
3 |
+
size 5240
|
run-1/checkpoint-402/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-536/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-1/checkpoint-536/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05f684b2ad79c54c33547cf103f10069614ba485a6a42d1629046410127f8ba9
|
3 |
+
size 267832560
|
run-1/checkpoint-536/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5ec29c6343c8a924610fa3af27d8b107fb6b8bde18af31e4b89b85ca1787ff0
|
3 |
+
size 535727290
|
run-1/checkpoint-536/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b111baddcc4c2f565278017c8a868a22616f171cee66c80898318c26365f8a1
|
3 |
+
size 14308
|
run-1/checkpoint-536/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c476ec186a262870a4180b7f3df75ea005abdb37e5bafb7fd872fc4e8c129bcf
|
3 |
+
size 1064
|
run-1/checkpoint-536/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-536/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-536/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-1/checkpoint-536/trainer_state.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4863630663948402,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-402",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 536,
|
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_loss": 0.49098527431488037,
|
14 |
+
"eval_matthews_correlation": 0.41038483457442687,
|
15 |
+
"eval_runtime": 0.7284,
|
16 |
+
"eval_samples_per_second": 1431.833,
|
17 |
+
"eval_steps_per_second": 90.605,
|
18 |
+
"step": 134
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.5078911185264587,
|
23 |
+
"eval_matthews_correlation": 0.4550840399220741,
|
24 |
+
"eval_runtime": 1.0357,
|
25 |
+
"eval_samples_per_second": 1007.09,
|
26 |
+
"eval_steps_per_second": 63.728,
|
27 |
+
"step": 268
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.6435816287994385,
|
32 |
+
"eval_matthews_correlation": 0.4863630663948402,
|
33 |
+
"eval_runtime": 0.7155,
|
34 |
+
"eval_samples_per_second": 1457.781,
|
35 |
+
"eval_steps_per_second": 92.247,
|
36 |
+
"step": 402
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.7313432835820897,
|
40 |
+
"grad_norm": 3.6653482913970947,
|
41 |
+
"learning_rate": 5.49225906876445e-06,
|
42 |
+
"loss": 0.2839,
|
43 |
+
"step": 500
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 4.0,
|
47 |
+
"eval_loss": 0.739212691783905,
|
48 |
+
"eval_matthews_correlation": 0.4809785029448826,
|
49 |
+
"eval_runtime": 0.8504,
|
50 |
+
"eval_samples_per_second": 1226.417,
|
51 |
+
"eval_steps_per_second": 77.606,
|
52 |
+
"step": 536
|
53 |
+
}
|
54 |
+
],
|
55 |
+
"logging_steps": 500,
|
56 |
+
"max_steps": 536,
|
57 |
+
"num_input_tokens_seen": 0,
|
58 |
+
"num_train_epochs": 4,
|
59 |
+
"save_steps": 500,
|
60 |
+
"stateful_callbacks": {
|
61 |
+
"TrainerControl": {
|
62 |
+
"args": {
|
63 |
+
"should_epoch_stop": false,
|
64 |
+
"should_evaluate": false,
|
65 |
+
"should_log": false,
|
66 |
+
"should_save": true,
|
67 |
+
"should_training_stop": true
|
68 |
+
},
|
69 |
+
"attributes": {}
|
70 |
+
}
|
71 |
+
},
|
72 |
+
"total_flos": 210467669904852.0,
|
73 |
+
"train_batch_size": 64,
|
74 |
+
"trial_name": null,
|
75 |
+
"trial_params": {
|
76 |
+
"learning_rate": 8.177363502382625e-05,
|
77 |
+
"num_train_epochs": 4,
|
78 |
+
"per_device_train_batch_size": 64,
|
79 |
+
"seed": 17
|
80 |
+
}
|
81 |
+
}
|
run-1/checkpoint-536/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5421fa1053c0128f22a4daab188c4af9bc8bf9a37722e6659e71c91a49f1d4a9
|
3 |
+
size 5240
|
run-1/checkpoint-536/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/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-2/checkpoint-268/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7877dbd402fd4c7c5ad15f79ca5e7c947037e9f10a80b1e27a5b4acf0002a216
|
3 |
+
size 267832560
|
run-2/checkpoint-268/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90dc4cb827f116c5046cedcd87980d5ed6dff50f2b85b48295147c8d7416cf43
|
3 |
+
size 535727290
|
run-2/checkpoint-268/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25de9062e39b437f33e259486d14e9d697997bfd1a94e2133406605b55f12ae1
|
3 |
+
size 14244
|
run-2/checkpoint-268/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87f7f9af9cd286d2297df6ac824e130afa781f7c225e5c1e4c14013f93f14f84
|
3 |
+
size 1064
|
run-2/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-2/checkpoint-268/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/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-2/checkpoint-268/trainer_state.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-268",
|
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 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.602029025554657,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.7285,
|
16 |
+
"eval_samples_per_second": 1431.715,
|
17 |
+
"eval_steps_per_second": 90.598,
|
18 |
+
"step": 268
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 1340,
|
23 |
+
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 5,
|
25 |
+
"save_steps": 500,
|
26 |
+
"stateful_callbacks": {
|
27 |
+
"TrainerControl": {
|
28 |
+
"args": {
|
29 |
+
"should_epoch_stop": false,
|
30 |
+
"should_evaluate": false,
|
31 |
+
"should_log": false,
|
32 |
+
"should_save": true,
|
33 |
+
"should_training_stop": false
|
34 |
+
},
|
35 |
+
"attributes": {}
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"total_flos": 0,
|
39 |
+
"train_batch_size": 32,
|
40 |
+
"trial_name": null,
|
41 |
+
"trial_params": {
|
42 |
+
"learning_rate": 1.4488901076980227e-06,
|
43 |
+
"num_train_epochs": 5,
|
44 |
+
"per_device_train_batch_size": 32,
|
45 |
+
"seed": 3
|
46 |
+
}
|
47 |
+
}
|
run-2/checkpoint-268/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af4e47fab4bdf5c020fd9bae4771a8cf62c8b1f615f2e7b84ba1d5d152fb998d
|
3 |
+
size 5240
|
run-2/checkpoint-268/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.1723862972.b5f02c58e851.301.3
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:afc7a1426101a420f5afebced7378928a5e42fc7a9316e38eb26efd6ac7bdb50
|
3 |
+
size 6802
|
runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723863099.b5f02c58e851.301.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2fab615100e51a3e5550ad42bb03016c4404941df7a5b45ad89e63f2aac254e
|
3 |
+
size 5778
|
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:af4e47fab4bdf5c020fd9bae4771a8cf62c8b1f615f2e7b84ba1d5d152fb998d
|
3 |
size 5240
|