SjardiWillems
commited on
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-3/checkpoint-108/config.json +25 -0
- run-3/checkpoint-108/model.safetensors +3 -0
- run-3/checkpoint-108/optimizer.pt +3 -0
- run-3/checkpoint-108/rng_state.pth +3 -0
- run-3/checkpoint-108/scheduler.pt +3 -0
- run-3/checkpoint-108/special_tokens_map.json +7 -0
- run-3/checkpoint-108/tokenizer.json +0 -0
- run-3/checkpoint-108/tokenizer_config.json +55 -0
- run-3/checkpoint-108/trainer_state.json +44 -0
- run-3/checkpoint-108/training_args.bin +3 -0
- run-3/checkpoint-108/vocab.txt +0 -0
- run-3/checkpoint-162/config.json +25 -0
- run-3/checkpoint-162/model.safetensors +3 -0
- run-3/checkpoint-162/optimizer.pt +3 -0
- run-3/checkpoint-162/rng_state.pth +3 -0
- run-3/checkpoint-162/scheduler.pt +3 -0
- run-3/checkpoint-162/special_tokens_map.json +7 -0
- run-3/checkpoint-162/tokenizer.json +0 -0
- run-3/checkpoint-162/tokenizer_config.json +55 -0
- run-3/checkpoint-162/trainer_state.json +53 -0
- run-3/checkpoint-162/training_args.bin +3 -0
- run-3/checkpoint-162/vocab.txt +0 -0
- run-3/checkpoint-216/config.json +25 -0
- run-3/checkpoint-216/model.safetensors +3 -0
- run-3/checkpoint-216/optimizer.pt +3 -0
- run-3/checkpoint-216/rng_state.pth +3 -0
- run-3/checkpoint-216/scheduler.pt +3 -0
- run-3/checkpoint-216/special_tokens_map.json +7 -0
- run-3/checkpoint-216/tokenizer.json +0 -0
- run-3/checkpoint-216/tokenizer_config.json +55 -0
- run-3/checkpoint-216/trainer_state.json +62 -0
- run-3/checkpoint-216/training_args.bin +3 -0
- run-3/checkpoint-216/vocab.txt +0 -0
- run-3/checkpoint-270/config.json +25 -0
- run-3/checkpoint-270/model.safetensors +3 -0
- run-3/checkpoint-270/optimizer.pt +3 -0
- run-3/checkpoint-270/rng_state.pth +3 -0
- run-3/checkpoint-270/scheduler.pt +3 -0
- run-3/checkpoint-270/special_tokens_map.json +7 -0
- run-3/checkpoint-270/tokenizer.json +0 -0
- run-3/checkpoint-270/tokenizer_config.json +55 -0
- run-3/checkpoint-270/trainer_state.json +71 -0
- run-3/checkpoint-270/training_args.bin +3 -0
- run-3/checkpoint-270/vocab.txt +0 -0
- run-4/checkpoint-54/config.json +25 -0
- run-4/checkpoint-54/model.safetensors +3 -0
- run-4/checkpoint-54/optimizer.pt +3 -0
- run-4/checkpoint-54/rng_state.pth +3 -0
- run-4/checkpoint-54/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 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02862714de993ef37f27e3368f59c2a27353cbade9b451ae7a7827c2a8b05f06
|
3 |
size 267832560
|
run-3/checkpoint-108/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": "4.38.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-3/checkpoint-108/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb37c0a0e0ca531963a4e7e0f692d8b7e91d5962cf94ce6df4b896e2b6f859b0
|
3 |
+
size 267832560
|
run-3/checkpoint-108/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53530a8d0bcf32d08f68be361fde14b0b9065efa33a5b666cb78c553b04e92e3
|
3 |
+
size 535727290
|
run-3/checkpoint-108/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6248ee263aa8124cd7bbd3e19df3a7d7ccfdcd13889d62964bda4e725adec1d0
|
3 |
+
size 14180
|
run-3/checkpoint-108/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4552d0fa488a4a6d4a8151b0d4cb2a32d86e6512fcf6660d877f7e497c57610e
|
3 |
+
size 1064
|
run-3/checkpoint-108/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-3/checkpoint-108/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-108/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-3/checkpoint-108/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-54",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 108,
|
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": 0.6160927414894104,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4953,
|
16 |
+
"eval_samples_per_second": 2105.607,
|
17 |
+
"eval_steps_per_second": 133.241,
|
18 |
+
"step": 54
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6087684035301208,
|
23 |
+
"eval_matthews_correlation": 0.0,
|
24 |
+
"eval_runtime": 0.5033,
|
25 |
+
"eval_samples_per_second": 2072.39,
|
26 |
+
"eval_steps_per_second": 131.139,
|
27 |
+
"step": 108
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 270,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 5,
|
34 |
+
"save_steps": 500,
|
35 |
+
"total_flos": 0,
|
36 |
+
"train_batch_size": 16,
|
37 |
+
"trial_name": null,
|
38 |
+
"trial_params": {
|
39 |
+
"learning_rate": 4.118328225546516e-06,
|
40 |
+
"num_train_epochs": 5,
|
41 |
+
"per_device_train_batch_size": 16,
|
42 |
+
"seed": 10
|
43 |
+
}
|
44 |
+
}
|
run-3/checkpoint-108/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98eb71cc2a425fe99533b8db21e393132228db26f27ca6e23b50c5fe39be3492
|
3 |
+
size 4984
|
run-3/checkpoint-108/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-162/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": "4.38.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-3/checkpoint-162/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3be9b1103128393fe83f08a5b3e43fb1100909a19ecedf3e013bdbc01289d99d
|
3 |
+
size 267832560
|
run-3/checkpoint-162/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c868dd7ec3bc6e9a3e2fec13c6d6bf3af2aa6ed54788d032090a91ee946ac85
|
3 |
+
size 535727290
|
run-3/checkpoint-162/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68a9ce68cb050eacbdf583e0c527cd361b694283d9eb8c34aba0177144208765
|
3 |
+
size 14180
|
run-3/checkpoint-162/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce613ff5efb031c46a008a6e9112ed30ade6223a12677bcd67e819e55cf5e609
|
3 |
+
size 1064
|
run-3/checkpoint-162/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-3/checkpoint-162/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-162/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-3/checkpoint-162/trainer_state.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-54",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 162,
|
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": 0.6160927414894104,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4953,
|
16 |
+
"eval_samples_per_second": 2105.607,
|
17 |
+
"eval_steps_per_second": 133.241,
|
18 |
+
"step": 54
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6087684035301208,
|
23 |
+
"eval_matthews_correlation": 0.0,
|
24 |
+
"eval_runtime": 0.5033,
|
25 |
+
"eval_samples_per_second": 2072.39,
|
26 |
+
"eval_steps_per_second": 131.139,
|
27 |
+
"step": 108
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.6040787100791931,
|
32 |
+
"eval_matthews_correlation": 0.0,
|
33 |
+
"eval_runtime": 0.4985,
|
34 |
+
"eval_samples_per_second": 2092.254,
|
35 |
+
"eval_steps_per_second": 132.396,
|
36 |
+
"step": 162
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"logging_steps": 500,
|
40 |
+
"max_steps": 270,
|
41 |
+
"num_input_tokens_seen": 0,
|
42 |
+
"num_train_epochs": 5,
|
43 |
+
"save_steps": 500,
|
44 |
+
"total_flos": 0,
|
45 |
+
"train_batch_size": 16,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": {
|
48 |
+
"learning_rate": 4.118328225546516e-06,
|
49 |
+
"num_train_epochs": 5,
|
50 |
+
"per_device_train_batch_size": 16,
|
51 |
+
"seed": 10
|
52 |
+
}
|
53 |
+
}
|
run-3/checkpoint-162/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98eb71cc2a425fe99533b8db21e393132228db26f27ca6e23b50c5fe39be3492
|
3 |
+
size 4984
|
run-3/checkpoint-162/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-216/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": "4.38.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-3/checkpoint-216/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:800de9d202edd1830402add7f125e8d6f5db08f2dd1a62107f4927bfee50e6bc
|
3 |
+
size 267832560
|
run-3/checkpoint-216/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:821f26d098cf75233065f1800ed011140c405b4e32c393c75de9ab699ca78639
|
3 |
+
size 535727290
|
run-3/checkpoint-216/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffdddfb82c3b4963aa78aa8d28957a2bbb3e40a855a2b9ac45bec4d31ce00afc
|
3 |
+
size 14180
|
run-3/checkpoint-216/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9602eccc673b4ba7a13f63d9a551e782d489b37be0b11ac56839b6ade9c337af
|
3 |
+
size 1064
|
run-3/checkpoint-216/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-3/checkpoint-216/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-216/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-3/checkpoint-216/trainer_state.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-54",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 216,
|
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": 0.6160927414894104,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4953,
|
16 |
+
"eval_samples_per_second": 2105.607,
|
17 |
+
"eval_steps_per_second": 133.241,
|
18 |
+
"step": 54
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6087684035301208,
|
23 |
+
"eval_matthews_correlation": 0.0,
|
24 |
+
"eval_runtime": 0.5033,
|
25 |
+
"eval_samples_per_second": 2072.39,
|
26 |
+
"eval_steps_per_second": 131.139,
|
27 |
+
"step": 108
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.6040787100791931,
|
32 |
+
"eval_matthews_correlation": 0.0,
|
33 |
+
"eval_runtime": 0.4985,
|
34 |
+
"eval_samples_per_second": 2092.254,
|
35 |
+
"eval_steps_per_second": 132.396,
|
36 |
+
"step": 162
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_loss": 0.5997274518013,
|
41 |
+
"eval_matthews_correlation": 0.0,
|
42 |
+
"eval_runtime": 0.5179,
|
43 |
+
"eval_samples_per_second": 2013.994,
|
44 |
+
"eval_steps_per_second": 127.444,
|
45 |
+
"step": 216
|
46 |
+
}
|
47 |
+
],
|
48 |
+
"logging_steps": 500,
|
49 |
+
"max_steps": 270,
|
50 |
+
"num_input_tokens_seen": 0,
|
51 |
+
"num_train_epochs": 5,
|
52 |
+
"save_steps": 500,
|
53 |
+
"total_flos": 0,
|
54 |
+
"train_batch_size": 16,
|
55 |
+
"trial_name": null,
|
56 |
+
"trial_params": {
|
57 |
+
"learning_rate": 4.118328225546516e-06,
|
58 |
+
"num_train_epochs": 5,
|
59 |
+
"per_device_train_batch_size": 16,
|
60 |
+
"seed": 10
|
61 |
+
}
|
62 |
+
}
|
run-3/checkpoint-216/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98eb71cc2a425fe99533b8db21e393132228db26f27ca6e23b50c5fe39be3492
|
3 |
+
size 4984
|
run-3/checkpoint-216/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-270/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": "4.38.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-3/checkpoint-270/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:891c9400c800e7a4e0cf4a66b75234a81ec48e269afdee30008b594281577267
|
3 |
+
size 267832560
|
run-3/checkpoint-270/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2848ef7caf597c1c8e7fd46397ea348ff4387b8f6e01aad0f77969aa0245ce6c
|
3 |
+
size 535727290
|
run-3/checkpoint-270/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0c091714099710d340535bbcb3659c356e65310b79179b187ea7dae4af20a34
|
3 |
+
size 14180
|
run-3/checkpoint-270/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a41caa36f61731e1a1c86dd5347a8b5c0eb6db1b347a7fa2845f42e83c0c646
|
3 |
+
size 1064
|
run-3/checkpoint-270/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-3/checkpoint-270/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-270/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-3/checkpoint-270/trainer_state.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-54",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 270,
|
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": 0.6160927414894104,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4953,
|
16 |
+
"eval_samples_per_second": 2105.607,
|
17 |
+
"eval_steps_per_second": 133.241,
|
18 |
+
"step": 54
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6087684035301208,
|
23 |
+
"eval_matthews_correlation": 0.0,
|
24 |
+
"eval_runtime": 0.5033,
|
25 |
+
"eval_samples_per_second": 2072.39,
|
26 |
+
"eval_steps_per_second": 131.139,
|
27 |
+
"step": 108
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.6040787100791931,
|
32 |
+
"eval_matthews_correlation": 0.0,
|
33 |
+
"eval_runtime": 0.4985,
|
34 |
+
"eval_samples_per_second": 2092.254,
|
35 |
+
"eval_steps_per_second": 132.396,
|
36 |
+
"step": 162
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_loss": 0.5997274518013,
|
41 |
+
"eval_matthews_correlation": 0.0,
|
42 |
+
"eval_runtime": 0.5179,
|
43 |
+
"eval_samples_per_second": 2013.994,
|
44 |
+
"eval_steps_per_second": 127.444,
|
45 |
+
"step": 216
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 5.0,
|
49 |
+
"eval_loss": 0.5987327694892883,
|
50 |
+
"eval_matthews_correlation": 0.0,
|
51 |
+
"eval_runtime": 0.4912,
|
52 |
+
"eval_samples_per_second": 2123.423,
|
53 |
+
"eval_steps_per_second": 134.368,
|
54 |
+
"step": 270
|
55 |
+
}
|
56 |
+
],
|
57 |
+
"logging_steps": 500,
|
58 |
+
"max_steps": 270,
|
59 |
+
"num_input_tokens_seen": 0,
|
60 |
+
"num_train_epochs": 5,
|
61 |
+
"save_steps": 500,
|
62 |
+
"total_flos": 0,
|
63 |
+
"train_batch_size": 16,
|
64 |
+
"trial_name": null,
|
65 |
+
"trial_params": {
|
66 |
+
"learning_rate": 4.118328225546516e-06,
|
67 |
+
"num_train_epochs": 5,
|
68 |
+
"per_device_train_batch_size": 16,
|
69 |
+
"seed": 10
|
70 |
+
}
|
71 |
+
}
|
run-3/checkpoint-270/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98eb71cc2a425fe99533b8db21e393132228db26f27ca6e23b50c5fe39be3492
|
3 |
+
size 4984
|
run-3/checkpoint-270/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-54/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": "4.38.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-4/checkpoint-54/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02862714de993ef37f27e3368f59c2a27353cbade9b451ae7a7827c2a8b05f06
|
3 |
+
size 267832560
|
run-4/checkpoint-54/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dea78c6e466a6e28a060acb25b05ae9c3daf1a6c808ce0f60f0fa88bcad3acce
|
3 |
+
size 535727290
|
run-4/checkpoint-54/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db6c018004c8341f62d292cd0e83aea5f442dbd6d99c159bb74281a986c0410b
|
3 |
+
size 14244
|
run-4/checkpoint-54/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1ce217590d9de8b73c6b7064631cd0f4f72df156ea469ee6367953b0fd95b15
|
3 |
+
size 1064
|