Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-8/checkpoint-214/config.json +1 -1
- run-8/checkpoint-214/model.safetensors +1 -1
- run-8/checkpoint-214/optimizer.pt +1 -1
- run-8/checkpoint-214/rng_state.pth +1 -1
- run-8/checkpoint-214/scheduler.pt +1 -1
- run-8/checkpoint-214/trainer_state.json +21 -12
- run-8/checkpoint-214/training_args.bin +2 -2
- run-8/checkpoint-321/config.json +25 -0
- run-8/checkpoint-321/model.safetensors +3 -0
- run-8/checkpoint-321/optimizer.pt +3 -0
- run-8/checkpoint-321/rng_state.pth +3 -0
- run-8/checkpoint-321/scheduler.pt +3 -0
- run-8/checkpoint-321/special_tokens_map.json +7 -0
- run-8/checkpoint-321/tokenizer.json +0 -0
- run-8/checkpoint-321/tokenizer_config.json +55 -0
- run-8/checkpoint-321/trainer_state.json +53 -0
- run-8/checkpoint-321/training_args.bin +3 -0
- run-8/checkpoint-321/vocab.txt +0 -0
- runs/Feb23_10-35-48_ec6659c07f12/events.out.tfevents.1708685352.ec6659c07f12.1051.11 +3 -0
- runs/Feb23_10-35-48_ec6659c07f12/events.out.tfevents.1708685454.ec6659c07f12.1051.12 +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 sha256:787954613f44e4663c42543d9fe668f4e267480a972d0f0b3e45c093793760ce
|
3 |
size 267832560
|
run-8/checkpoint-214/config.json
CHANGED
@@ -20,6 +20,6 @@
|
|
20 |
"sinusoidal_pos_embds": false,
|
21 |
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.
|
24 |
"vocab_size": 30522
|
25 |
}
|
|
|
20 |
"sinusoidal_pos_embds": false,
|
21 |
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.38.1",
|
24 |
"vocab_size": 30522
|
25 |
}
|
run-8/checkpoint-214/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 sha256:5ad6e07cb26f6237b7f0f602f04121b93cd358989897632cabb5aecc3095f305
|
3 |
size 267832560
|
run-8/checkpoint-214/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535727290
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3da3afa1ab6d34efa184c300c6ffd1d0cd9bd7caf6ed17f77f16d4f8d6d9d166
|
3 |
size 535727290
|
run-8/checkpoint-214/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78080671ef27bab4d8367805cfe7f616e0d0b385124e8726093ff3663b195c6e
|
3 |
size 14244
|
run-8/checkpoint-214/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f02ffc0dc95b6749b4f4b195194be8e0062236dd266f9bec939a604538d47bc
|
3 |
size 1064
|
run-8/checkpoint-214/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-214",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 214,
|
7 |
"is_hyper_param_search": true,
|
@@ -10,26 +10,35 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss": 0.
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
-
"eval_runtime": 0.
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_steps_per_second":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
"step": 214
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
22 |
-
"max_steps":
|
23 |
"num_input_tokens_seen": 0,
|
24 |
-
"num_train_epochs":
|
25 |
"save_steps": 500,
|
26 |
"total_flos": 0,
|
27 |
-
"train_batch_size":
|
28 |
"trial_name": null,
|
29 |
"trial_params": {
|
30 |
-
"learning_rate":
|
31 |
-
"num_train_epochs":
|
32 |
-
"per_device_train_batch_size":
|
33 |
"seed": 36
|
34 |
}
|
35 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.30246066235214725,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-214",
|
4 |
+
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 214,
|
7 |
"is_hyper_param_search": true,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.5813318490982056,
|
14 |
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4888,
|
16 |
+
"eval_samples_per_second": 2133.724,
|
17 |
+
"eval_steps_per_second": 135.02,
|
18 |
+
"step": 107
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6579855680465698,
|
23 |
+
"eval_matthews_correlation": 0.30246066235214725,
|
24 |
+
"eval_runtime": 0.4813,
|
25 |
+
"eval_samples_per_second": 2167.13,
|
26 |
+
"eval_steps_per_second": 137.134,
|
27 |
"step": 214
|
28 |
}
|
29 |
],
|
30 |
"logging_steps": 500,
|
31 |
+
"max_steps": 321,
|
32 |
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 3,
|
34 |
"save_steps": 500,
|
35 |
"total_flos": 0,
|
36 |
+
"train_batch_size": 8,
|
37 |
"trial_name": null,
|
38 |
"trial_params": {
|
39 |
+
"learning_rate": 3.438273396233882e-05,
|
40 |
+
"num_train_epochs": 3,
|
41 |
+
"per_device_train_batch_size": 8,
|
42 |
"seed": 36
|
43 |
}
|
44 |
}
|
run-8/checkpoint-214/training_args.bin
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 sha256:8238f446d69fcc6cc9010ead2f33f328df1196aac5b15d9bdce1a4f9bead8e06
|
3 |
+
size 4984
|
run-8/checkpoint-321/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": "4.38.1",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-8/checkpoint-321/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbd3890c650c755a4f54ba6ad3c18669e4e24c46dc5c8d77fe2d55ec2d988eec
|
3 |
+
size 267832560
|
run-8/checkpoint-321/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07a995e7cdd339f94b9e4acbf2f4f6bd3accbf0e101b58854127b25ad7daed52
|
3 |
+
size 535727290
|
run-8/checkpoint-321/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec477d87fb3b0852f22ff98a5c737823705734f907275aca32e5016f0654e4ce
|
3 |
+
size 14244
|
run-8/checkpoint-321/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6a8b6771c68dc52b08a13d75125c76260a0e75d3b8c974f5fdd28893ffff912
|
3 |
+
size 1064
|
run-8/checkpoint-321/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-8/checkpoint-321/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-8/checkpoint-321/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-8/checkpoint-321/trainer_state.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3051965941207153,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-321",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 321,
|
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": 0.5813318490982056,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4888,
|
16 |
+
"eval_samples_per_second": 2133.724,
|
17 |
+
"eval_steps_per_second": 135.02,
|
18 |
+
"step": 107
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6579855680465698,
|
23 |
+
"eval_matthews_correlation": 0.30246066235214725,
|
24 |
+
"eval_runtime": 0.4813,
|
25 |
+
"eval_samples_per_second": 2167.13,
|
26 |
+
"eval_steps_per_second": 137.134,
|
27 |
+
"step": 214
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.8824570775032043,
|
32 |
+
"eval_matthews_correlation": 0.3051965941207153,
|
33 |
+
"eval_runtime": 0.4826,
|
34 |
+
"eval_samples_per_second": 2161.247,
|
35 |
+
"eval_steps_per_second": 136.762,
|
36 |
+
"step": 321
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"logging_steps": 500,
|
40 |
+
"max_steps": 321,
|
41 |
+
"num_input_tokens_seen": 0,
|
42 |
+
"num_train_epochs": 3,
|
43 |
+
"save_steps": 500,
|
44 |
+
"total_flos": 0,
|
45 |
+
"train_batch_size": 8,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": {
|
48 |
+
"learning_rate": 3.438273396233882e-05,
|
49 |
+
"num_train_epochs": 3,
|
50 |
+
"per_device_train_batch_size": 8,
|
51 |
+
"seed": 36
|
52 |
+
}
|
53 |
+
}
|
run-8/checkpoint-321/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8238f446d69fcc6cc9010ead2f33f328df1196aac5b15d9bdce1a4f9bead8e06
|
3 |
+
size 4984
|
run-8/checkpoint-321/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Feb23_10-35-48_ec6659c07f12/events.out.tfevents.1708685352.ec6659c07f12.1051.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a11b70863a5f0ffc991f5d54ca4b6d065f05c1ed5290bdf53230d9748f53c66
|
3 |
+
size 4877
|
runs/Feb23_10-35-48_ec6659c07f12/events.out.tfevents.1708685454.ec6659c07f12.1051.12
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cd13299c3c08ba268b653021df730f92972501d974cf4be6c1ed810bed13145
|
3 |
+
size 6535
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c8a2f53a405f321cf90788b9039982bb31601b72430591127a453fbb500d00a
|
3 |
size 4984
|