wy3106714391
commited on
Training in progress, epoch 3
Browse files- model.safetensors +1 -1
- 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 +63 -0
- run-1/checkpoint-536/training_args.bin +3 -0
- run-1/checkpoint-536/vocab.txt +0 -0
- run-1/checkpoint-804/config.json +25 -0
- run-1/checkpoint-804/model.safetensors +3 -0
- run-1/checkpoint-804/optimizer.pt +3 -0
- run-1/checkpoint-804/rng_state.pth +3 -0
- run-1/checkpoint-804/scheduler.pt +3 -0
- run-1/checkpoint-804/special_tokens_map.json +7 -0
- run-1/checkpoint-804/tokenizer.json +0 -0
- run-1/checkpoint-804/tokenizer_config.json +55 -0
- run-1/checkpoint-804/trainer_state.json +72 -0
- run-1/checkpoint-804/training_args.bin +3 -0
- run-1/checkpoint-804/vocab.txt +0 -0
- runs/Jun05_17-06-49_52616c5e4acb/events.out.tfevents.1717607834.52616c5e4acb.227.3 +2 -2
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 sha256:037dea29367f0e5b58aefe0f78fbf7735fa28073eecc199122e615b488b8ca8a
|
3 |
size 267832560
|
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": "4.41.2",
|
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 sha256:2440af37a7e4f1e1eb029e23688a44d782e3be8776972d1c7eb32766a3e5245e
|
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 sha256:6331a666ccdb1436b720728e29310cbc95605efdf745d48028ef379fcb6ef6bf
|
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 sha256:0f71bb389dd6e249f188f9858b426db87b81a0ce7b04ded9224105129c561ced
|
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 sha256:562e1b468fe660ffe3f75e92d0dfde40bcb6b38cfea191d29757fd8fbb6a2f13
|
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 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4748831613141367,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-536",
|
4 |
+
"epoch": 2.0,
|
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": 0.4888503849506378,
|
14 |
+
"eval_matthews_correlation": 0.4329275215299443,
|
15 |
+
"eval_runtime": 0.935,
|
16 |
+
"eval_samples_per_second": 1115.543,
|
17 |
+
"eval_steps_per_second": 70.59,
|
18 |
+
"step": 268
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.8656716417910446,
|
22 |
+
"grad_norm": 9.826521873474121,
|
23 |
+
"learning_rate": 7.500401646747706e-06,
|
24 |
+
"loss": 0.4534,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_loss": 0.5052120685577393,
|
30 |
+
"eval_matthews_correlation": 0.4748831613141367,
|
31 |
+
"eval_runtime": 0.816,
|
32 |
+
"eval_samples_per_second": 1278.206,
|
33 |
+
"eval_steps_per_second": 80.884,
|
34 |
+
"step": 536
|
35 |
+
}
|
36 |
+
],
|
37 |
+
"logging_steps": 500,
|
38 |
+
"max_steps": 804,
|
39 |
+
"num_input_tokens_seen": 0,
|
40 |
+
"num_train_epochs": 3,
|
41 |
+
"save_steps": 500,
|
42 |
+
"stateful_callbacks": {
|
43 |
+
"TrainerControl": {
|
44 |
+
"args": {
|
45 |
+
"should_epoch_stop": false,
|
46 |
+
"should_evaluate": false,
|
47 |
+
"should_log": false,
|
48 |
+
"should_save": true,
|
49 |
+
"should_training_stop": false
|
50 |
+
},
|
51 |
+
"attributes": {}
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"total_flos": 95845337435376.0,
|
55 |
+
"train_batch_size": 32,
|
56 |
+
"trial_name": null,
|
57 |
+
"trial_params": {
|
58 |
+
"learning_rate": 1.9836588565740644e-05,
|
59 |
+
"num_train_epochs": 3,
|
60 |
+
"per_device_train_batch_size": 32,
|
61 |
+
"seed": 24
|
62 |
+
}
|
63 |
+
}
|
run-1/checkpoint-536/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27ec5f3a2774ea48d134bd5512100b8daf0012e26efe2ac00fefd3440c874afb
|
3 |
+
size 5176
|
run-1/checkpoint-536/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-804/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": "4.41.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-1/checkpoint-804/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:037dea29367f0e5b58aefe0f78fbf7735fa28073eecc199122e615b488b8ca8a
|
3 |
+
size 267832560
|
run-1/checkpoint-804/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0212e881bdf9a0c690ca78e050199321f889b147097c72a39ae5ac54e637ae9e
|
3 |
+
size 535727290
|
run-1/checkpoint-804/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b685297a7767eda06ff43a38a7d96f3e5e6fa3a36215c2f1800eaded35ddc3d
|
3 |
+
size 14308
|
run-1/checkpoint-804/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0df5776799039712cebaba1e05abef822b132ab2358f80c6b41c56df301aeaf9
|
3 |
+
size 1064
|
run-1/checkpoint-804/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-804/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-804/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-804/trainer_state.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.49285731840923963,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-804",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 804,
|
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": 0.4888503849506378,
|
14 |
+
"eval_matthews_correlation": 0.4329275215299443,
|
15 |
+
"eval_runtime": 0.935,
|
16 |
+
"eval_samples_per_second": 1115.543,
|
17 |
+
"eval_steps_per_second": 70.59,
|
18 |
+
"step": 268
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.8656716417910446,
|
22 |
+
"grad_norm": 9.826521873474121,
|
23 |
+
"learning_rate": 7.500401646747706e-06,
|
24 |
+
"loss": 0.4534,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_loss": 0.5052120685577393,
|
30 |
+
"eval_matthews_correlation": 0.4748831613141367,
|
31 |
+
"eval_runtime": 0.816,
|
32 |
+
"eval_samples_per_second": 1278.206,
|
33 |
+
"eval_steps_per_second": 80.884,
|
34 |
+
"step": 536
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 3.0,
|
38 |
+
"eval_loss": 0.5398480892181396,
|
39 |
+
"eval_matthews_correlation": 0.49285731840923963,
|
40 |
+
"eval_runtime": 0.7667,
|
41 |
+
"eval_samples_per_second": 1360.427,
|
42 |
+
"eval_steps_per_second": 86.086,
|
43 |
+
"step": 804
|
44 |
+
}
|
45 |
+
],
|
46 |
+
"logging_steps": 500,
|
47 |
+
"max_steps": 804,
|
48 |
+
"num_input_tokens_seen": 0,
|
49 |
+
"num_train_epochs": 3,
|
50 |
+
"save_steps": 500,
|
51 |
+
"stateful_callbacks": {
|
52 |
+
"TrainerControl": {
|
53 |
+
"args": {
|
54 |
+
"should_epoch_stop": false,
|
55 |
+
"should_evaluate": false,
|
56 |
+
"should_log": false,
|
57 |
+
"should_save": true,
|
58 |
+
"should_training_stop": true
|
59 |
+
},
|
60 |
+
"attributes": {}
|
61 |
+
}
|
62 |
+
},
|
63 |
+
"total_flos": 95845337435376.0,
|
64 |
+
"train_batch_size": 32,
|
65 |
+
"trial_name": null,
|
66 |
+
"trial_params": {
|
67 |
+
"learning_rate": 1.9836588565740644e-05,
|
68 |
+
"num_train_epochs": 3,
|
69 |
+
"per_device_train_batch_size": 32,
|
70 |
+
"seed": 24
|
71 |
+
}
|
72 |
+
}
|
run-1/checkpoint-804/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27ec5f3a2774ea48d134bd5512100b8daf0012e26efe2ac00fefd3440c874afb
|
3 |
+
size 5176
|
run-1/checkpoint-804/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Jun05_17-06-49_52616c5e4acb/events.out.tfevents.1717607834.52616c5e4acb.227.3
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:f602e0f4ffe615ae8ff1b917aecc983736862656ad24ae097ca11c38f13dbc77
|
3 |
+
size 6359
|