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-28/config.json +25 -0
- run-3/checkpoint-28/model.safetensors +3 -0
- run-3/checkpoint-28/optimizer.pt +3 -0
- run-3/checkpoint-28/rng_state.pth +3 -0
- run-3/checkpoint-28/scheduler.pt +3 -0
- run-3/checkpoint-28/special_tokens_map.json +7 -0
- run-3/checkpoint-28/tokenizer.json +0 -0
- run-3/checkpoint-28/tokenizer_config.json +55 -0
- run-3/checkpoint-28/trainer_state.json +44 -0
- run-3/checkpoint-28/training_args.bin +3 -0
- run-3/checkpoint-28/vocab.txt +0 -0
- run-3/checkpoint-42/config.json +25 -0
- run-3/checkpoint-42/model.safetensors +3 -0
- run-3/checkpoint-42/optimizer.pt +3 -0
- run-3/checkpoint-42/rng_state.pth +3 -0
- run-3/checkpoint-42/scheduler.pt +3 -0
- run-3/checkpoint-42/special_tokens_map.json +7 -0
- run-3/checkpoint-42/tokenizer.json +0 -0
- run-3/checkpoint-42/tokenizer_config.json +55 -0
- run-3/checkpoint-42/trainer_state.json +53 -0
- run-3/checkpoint-42/training_args.bin +3 -0
- run-3/checkpoint-42/vocab.txt +0 -0
- run-3/checkpoint-56/config.json +25 -0
- run-3/checkpoint-56/model.safetensors +3 -0
- run-3/checkpoint-56/optimizer.pt +3 -0
- run-3/checkpoint-56/rng_state.pth +3 -0
- run-3/checkpoint-56/scheduler.pt +3 -0
- run-3/checkpoint-56/special_tokens_map.json +7 -0
- run-3/checkpoint-56/tokenizer.json +0 -0
- run-3/checkpoint-56/tokenizer_config.json +55 -0
- run-3/checkpoint-56/trainer_state.json +62 -0
- run-3/checkpoint-56/training_args.bin +3 -0
- run-3/checkpoint-56/vocab.txt +0 -0
- run-3/checkpoint-70/config.json +25 -0
- run-3/checkpoint-70/model.safetensors +3 -0
- run-3/checkpoint-70/optimizer.pt +3 -0
- run-3/checkpoint-70/rng_state.pth +3 -0
- run-3/checkpoint-70/scheduler.pt +3 -0
- run-3/checkpoint-70/special_tokens_map.json +7 -0
- run-3/checkpoint-70/tokenizer.json +0 -0
- run-3/checkpoint-70/tokenizer_config.json +55 -0
- run-3/checkpoint-70/trainer_state.json +71 -0
- run-3/checkpoint-70/training_args.bin +3 -0
- run-3/checkpoint-70/vocab.txt +0 -0
- run-4/checkpoint-214/config.json +25 -0
- run-4/checkpoint-214/model.safetensors +3 -0
- run-4/checkpoint-214/optimizer.pt +3 -0
- run-4/checkpoint-214/rng_state.pth +3 -0
- run-4/checkpoint-214/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:accb1e5702c6bc6a53263a9f3a364707cd0f1c6ea92511e8fda89f46880770db
|
3 |
size 267832560
|
run-3/checkpoint-28/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-3/checkpoint-28/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca109eea28d5d80e352e547f6c9087f099348e1d1ea7e4232d0ebd4010ebd997
|
3 |
+
size 267832560
|
run-3/checkpoint-28/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28ebbc34ebdf1e1c106b30c9f0e7dc216b20ec55450b3e15b68d723b62014358
|
3 |
+
size 535727290
|
run-3/checkpoint-28/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb32f55c6d8ebbbf0a0546de2235e269199878366c6e524a55b735bd7a7aa4a1
|
3 |
+
size 14244
|
run-3/checkpoint-28/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d49159137c329deb57122124785470706b2c638efd30e2f60407c8b36614bfcd
|
3 |
+
size 1064
|
run-3/checkpoint-28/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-28/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-28/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-28/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.006558425391695436,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-14",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 28,
|
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": 0.7035912871360779,
|
14 |
+
"eval_matthews_correlation": 0.006558425391695436,
|
15 |
+
"eval_runtime": 0.7409,
|
16 |
+
"eval_samples_per_second": 1407.711,
|
17 |
+
"eval_steps_per_second": 89.079,
|
18 |
+
"step": 14
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6941744089126587,
|
23 |
+
"eval_matthews_correlation": -0.036114649977135045,
|
24 |
+
"eval_runtime": 0.8152,
|
25 |
+
"eval_samples_per_second": 1279.437,
|
26 |
+
"eval_steps_per_second": 80.962,
|
27 |
+
"step": 28
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 70,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 5,
|
34 |
+
"save_steps": 500,
|
35 |
+
"total_flos": 0,
|
36 |
+
"train_batch_size": 64,
|
37 |
+
"trial_name": null,
|
38 |
+
"trial_params": {
|
39 |
+
"learning_rate": 1.1291452758992565e-06,
|
40 |
+
"num_train_epochs": 5,
|
41 |
+
"per_device_train_batch_size": 64,
|
42 |
+
"seed": 34
|
43 |
+
}
|
44 |
+
}
|
run-3/checkpoint-28/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4a7612941dcfd74fb747ca12fdb515017d55fd7241a3def037f151934860a55
|
3 |
+
size 4984
|
run-3/checkpoint-28/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-42/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-3/checkpoint-42/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9afc2b7857ccc261fb14ad1948b053dbbcfe19d9390e2effaaaf808637801164
|
3 |
+
size 267832560
|
run-3/checkpoint-42/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a197d4d1d9a20fce0a152f493e6f41eb4b8925ecd3b754fa756b23f1a5c3fa6
|
3 |
+
size 535727290
|
run-3/checkpoint-42/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac454f25a59d65071854fdc2c3dbdaf2d58718da25b19a20fbababa87ce86cbf
|
3 |
+
size 14244
|
run-3/checkpoint-42/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:108d6ca86de76255a841174ec1078fef458c4f4368395a1b9ef253ada12a496e
|
3 |
+
size 1064
|
run-3/checkpoint-42/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-42/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-42/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-42/trainer_state.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.006558425391695436,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-14",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 42,
|
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": 0.7035912871360779,
|
14 |
+
"eval_matthews_correlation": 0.006558425391695436,
|
15 |
+
"eval_runtime": 0.7409,
|
16 |
+
"eval_samples_per_second": 1407.711,
|
17 |
+
"eval_steps_per_second": 89.079,
|
18 |
+
"step": 14
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6941744089126587,
|
23 |
+
"eval_matthews_correlation": -0.036114649977135045,
|
24 |
+
"eval_runtime": 0.8152,
|
25 |
+
"eval_samples_per_second": 1279.437,
|
26 |
+
"eval_steps_per_second": 80.962,
|
27 |
+
"step": 28
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.687230110168457,
|
32 |
+
"eval_matthews_correlation": -0.00313313961007992,
|
33 |
+
"eval_runtime": 0.8165,
|
34 |
+
"eval_samples_per_second": 1277.436,
|
35 |
+
"eval_steps_per_second": 80.835,
|
36 |
+
"step": 42
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"logging_steps": 500,
|
40 |
+
"max_steps": 70,
|
41 |
+
"num_input_tokens_seen": 0,
|
42 |
+
"num_train_epochs": 5,
|
43 |
+
"save_steps": 500,
|
44 |
+
"total_flos": 0,
|
45 |
+
"train_batch_size": 64,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": {
|
48 |
+
"learning_rate": 1.1291452758992565e-06,
|
49 |
+
"num_train_epochs": 5,
|
50 |
+
"per_device_train_batch_size": 64,
|
51 |
+
"seed": 34
|
52 |
+
}
|
53 |
+
}
|
run-3/checkpoint-42/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4a7612941dcfd74fb747ca12fdb515017d55fd7241a3def037f151934860a55
|
3 |
+
size 4984
|
run-3/checkpoint-42/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-56/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-3/checkpoint-56/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8783249ff2986c0d5f2c36f50117a891c6c63bc17bdaea5793c4ec48e0a77dd0
|
3 |
+
size 267832560
|
run-3/checkpoint-56/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fce1221145fe2e762a34dae25a68a4af82f42d954b264a986e5abaf26bf88286
|
3 |
+
size 535727290
|
run-3/checkpoint-56/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:953edee990dee3bba166164bae584289fdbee58052910ff5a22e6fc649724e95
|
3 |
+
size 14244
|
run-3/checkpoint-56/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9738f9b01e4ca0784aeeba0a90da55e29a301ed8002694c38ece97ee8712785e
|
3 |
+
size 1064
|
run-3/checkpoint-56/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-56/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-56/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-56/trainer_state.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.006558425391695436,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-14",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 56,
|
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": 0.7035912871360779,
|
14 |
+
"eval_matthews_correlation": 0.006558425391695436,
|
15 |
+
"eval_runtime": 0.7409,
|
16 |
+
"eval_samples_per_second": 1407.711,
|
17 |
+
"eval_steps_per_second": 89.079,
|
18 |
+
"step": 14
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6941744089126587,
|
23 |
+
"eval_matthews_correlation": -0.036114649977135045,
|
24 |
+
"eval_runtime": 0.8152,
|
25 |
+
"eval_samples_per_second": 1279.437,
|
26 |
+
"eval_steps_per_second": 80.962,
|
27 |
+
"step": 28
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.687230110168457,
|
32 |
+
"eval_matthews_correlation": -0.00313313961007992,
|
33 |
+
"eval_runtime": 0.8165,
|
34 |
+
"eval_samples_per_second": 1277.436,
|
35 |
+
"eval_steps_per_second": 80.835,
|
36 |
+
"step": 42
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_loss": 0.6829940676689148,
|
41 |
+
"eval_matthews_correlation": -0.023854095893688712,
|
42 |
+
"eval_runtime": 0.837,
|
43 |
+
"eval_samples_per_second": 1246.158,
|
44 |
+
"eval_steps_per_second": 78.856,
|
45 |
+
"step": 56
|
46 |
+
}
|
47 |
+
],
|
48 |
+
"logging_steps": 500,
|
49 |
+
"max_steps": 70,
|
50 |
+
"num_input_tokens_seen": 0,
|
51 |
+
"num_train_epochs": 5,
|
52 |
+
"save_steps": 500,
|
53 |
+
"total_flos": 0,
|
54 |
+
"train_batch_size": 64,
|
55 |
+
"trial_name": null,
|
56 |
+
"trial_params": {
|
57 |
+
"learning_rate": 1.1291452758992565e-06,
|
58 |
+
"num_train_epochs": 5,
|
59 |
+
"per_device_train_batch_size": 64,
|
60 |
+
"seed": 34
|
61 |
+
}
|
62 |
+
}
|
run-3/checkpoint-56/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4a7612941dcfd74fb747ca12fdb515017d55fd7241a3def037f151934860a55
|
3 |
+
size 4984
|
run-3/checkpoint-56/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-70/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-3/checkpoint-70/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d53f7e14e503a3aff3d85a96f30630c1bd949cab6f6fda81d19ee872553b3e7
|
3 |
+
size 267832560
|
run-3/checkpoint-70/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:720cd26e0e1723eb0431e7e633dd7e8098f580db0b55e302a6c283aa47c9eed6
|
3 |
+
size 535727290
|
run-3/checkpoint-70/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb7416224507bb831ce8086d8366c4aefb5c714066d10921e96714f19ffa2e01
|
3 |
+
size 14244
|
run-3/checkpoint-70/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:729118ee0d914efc68f434f0a5a55f1e3668fcad7d72419c0235ac47be12d7fa
|
3 |
+
size 1064
|
run-3/checkpoint-70/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-70/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-70/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-70/trainer_state.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.006558425391695436,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-14",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 70,
|
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": 0.7035912871360779,
|
14 |
+
"eval_matthews_correlation": 0.006558425391695436,
|
15 |
+
"eval_runtime": 0.7409,
|
16 |
+
"eval_samples_per_second": 1407.711,
|
17 |
+
"eval_steps_per_second": 89.079,
|
18 |
+
"step": 14
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6941744089126587,
|
23 |
+
"eval_matthews_correlation": -0.036114649977135045,
|
24 |
+
"eval_runtime": 0.8152,
|
25 |
+
"eval_samples_per_second": 1279.437,
|
26 |
+
"eval_steps_per_second": 80.962,
|
27 |
+
"step": 28
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.687230110168457,
|
32 |
+
"eval_matthews_correlation": -0.00313313961007992,
|
33 |
+
"eval_runtime": 0.8165,
|
34 |
+
"eval_samples_per_second": 1277.436,
|
35 |
+
"eval_steps_per_second": 80.835,
|
36 |
+
"step": 42
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_loss": 0.6829940676689148,
|
41 |
+
"eval_matthews_correlation": -0.023854095893688712,
|
42 |
+
"eval_runtime": 0.837,
|
43 |
+
"eval_samples_per_second": 1246.158,
|
44 |
+
"eval_steps_per_second": 78.856,
|
45 |
+
"step": 56
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 5.0,
|
49 |
+
"eval_loss": 0.6815392971038818,
|
50 |
+
"eval_matthews_correlation": -0.03338203486315733,
|
51 |
+
"eval_runtime": 0.8181,
|
52 |
+
"eval_samples_per_second": 1274.892,
|
53 |
+
"eval_steps_per_second": 80.674,
|
54 |
+
"step": 70
|
55 |
+
}
|
56 |
+
],
|
57 |
+
"logging_steps": 500,
|
58 |
+
"max_steps": 70,
|
59 |
+
"num_input_tokens_seen": 0,
|
60 |
+
"num_train_epochs": 5,
|
61 |
+
"save_steps": 500,
|
62 |
+
"total_flos": 0,
|
63 |
+
"train_batch_size": 64,
|
64 |
+
"trial_name": null,
|
65 |
+
"trial_params": {
|
66 |
+
"learning_rate": 1.1291452758992565e-06,
|
67 |
+
"num_train_epochs": 5,
|
68 |
+
"per_device_train_batch_size": 64,
|
69 |
+
"seed": 34
|
70 |
+
}
|
71 |
+
}
|
run-3/checkpoint-70/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4a7612941dcfd74fb747ca12fdb515017d55fd7241a3def037f151934860a55
|
3 |
+
size 4984
|
run-3/checkpoint-70/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-214/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-4/checkpoint-214/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f812605938282d2a0aeaa81d951560fed7ee0a435f9197c937045e614d6a0329
|
3 |
+
size 267832560
|
run-4/checkpoint-214/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c95675f2c83ae6c0da42cbcf71d73b78f7ef6859ff384ae8505126959d230379
|
3 |
+
size 535727290
|
run-4/checkpoint-214/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d766942d878e1142348a31f1803be38ad188c8b4aa1b1487f4e9afdda2b7625
|
3 |
+
size 14308
|
run-4/checkpoint-214/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:876c19713dd65bb808dd422730f86fc3157316e9f3705fd74c0c4e1b26ab682a
|
3 |
+
size 1064
|