Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-0/checkpoint-1070/config.json +25 -0
- run-0/checkpoint-1070/model.safetensors +3 -0
- run-0/checkpoint-1070/optimizer.pt +3 -0
- run-0/checkpoint-1070/rng_state.pth +3 -0
- run-0/checkpoint-1070/scheduler.pt +3 -0
- run-0/checkpoint-1070/special_tokens_map.json +7 -0
- run-0/checkpoint-1070/tokenizer.json +0 -0
- run-0/checkpoint-1070/tokenizer_config.json +55 -0
- run-0/checkpoint-1070/trainer_state.json +58 -0
- run-0/checkpoint-1070/training_args.bin +3 -0
- run-0/checkpoint-1070/vocab.txt +0 -0
- run-1/checkpoint-2138/config.json +25 -0
- run-1/checkpoint-2138/model.safetensors +3 -0
- run-1/checkpoint-2138/optimizer.pt +3 -0
- run-1/checkpoint-2138/rng_state.pth +3 -0
- run-1/checkpoint-2138/scheduler.pt +3 -0
- run-1/checkpoint-2138/special_tokens_map.json +7 -0
- run-1/checkpoint-2138/tokenizer.json +0 -0
- run-1/checkpoint-2138/tokenizer_config.json +55 -0
- run-1/checkpoint-2138/trainer_state.json +63 -0
- run-1/checkpoint-2138/training_args.bin +3 -0
- run-1/checkpoint-2138/vocab.txt +0 -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:a18197220f1d245217268bda9cd698d9538ec28fc25861e503fbdbdf35b87be6
|
3 |
size 267832560
|
run-0/checkpoint-1070/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-0/checkpoint-1070/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40198f66570b266dc213e6042b1c19489c79fdc63f197df65022b8242dc1db93
|
3 |
+
size 267832560
|
run-0/checkpoint-1070/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df5020e9014dd60975aba381f20a1562300adcf54949a0eb8d6447b1bf4693d4
|
3 |
+
size 535727290
|
run-0/checkpoint-1070/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88b65c6d33e127534f91722adc3effd26be85d2d9b2857d53ce97942bbc2d7b3
|
3 |
+
size 14244
|
run-0/checkpoint-1070/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01d4b0155fd7db410969940999dd8282c0af7ddcaaf4b4c2d3289631e2ebf232
|
3 |
+
size 1064
|
run-0/checkpoint-1070/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-0/checkpoint-1070/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-1070/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-0/checkpoint-1070/trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4809059900216985,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1070",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1070,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.93,
|
13 |
+
"grad_norm": 3.8641507625579834,
|
14 |
+
"learning_rate": 3.8123782979849475e-05,
|
15 |
+
"loss": 0.553,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_loss": 0.48692557215690613,
|
21 |
+
"eval_matthews_correlation": 0.40760885904937505,
|
22 |
+
"eval_runtime": 0.3431,
|
23 |
+
"eval_samples_per_second": 3040.316,
|
24 |
+
"eval_steps_per_second": 192.388,
|
25 |
+
"step": 535
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.87,
|
29 |
+
"grad_norm": 10.785917282104492,
|
30 |
+
"learning_rate": 4.6818680852446724e-06,
|
31 |
+
"loss": 0.3085,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_loss": 0.5644384026527405,
|
37 |
+
"eval_matthews_correlation": 0.4809059900216985,
|
38 |
+
"eval_runtime": 0.392,
|
39 |
+
"eval_samples_per_second": 2660.922,
|
40 |
+
"eval_steps_per_second": 168.38,
|
41 |
+
"step": 1070
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"logging_steps": 500,
|
45 |
+
"max_steps": 1070,
|
46 |
+
"num_input_tokens_seen": 0,
|
47 |
+
"num_train_epochs": 2,
|
48 |
+
"save_steps": 500,
|
49 |
+
"total_flos": 85536683075904.0,
|
50 |
+
"train_batch_size": 16,
|
51 |
+
"trial_name": null,
|
52 |
+
"trial_params": {
|
53 |
+
"learning_rate": 7.156569787445428e-05,
|
54 |
+
"num_train_epochs": 2,
|
55 |
+
"per_device_train_batch_size": 16,
|
56 |
+
"seed": 15
|
57 |
+
}
|
58 |
+
}
|
run-0/checkpoint-1070/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7db6bf6817bccd2005511528ed19af7abcd039666b6ad32830f38a36242c1637
|
3 |
+
size 4984
|
run-0/checkpoint-1070/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-2138/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-1/checkpoint-2138/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a18197220f1d245217268bda9cd698d9538ec28fc25861e503fbdbdf35b87be6
|
3 |
+
size 267832560
|
run-1/checkpoint-2138/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52cb7024d118e13800fdc704ca281a739b7bb13a0bb746bf3c83f86e4685ad65
|
3 |
+
size 535727290
|
run-1/checkpoint-2138/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a37affeb8a20a89cfc3df3c7f96a864f89eac4cdbf41b91eb89f20342f1012c
|
3 |
+
size 14244
|
run-1/checkpoint-2138/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2fbcb52720d748c59a596e7eb1ab29f8cdce25039f888c85e364a2f21dc1247
|
3 |
+
size 1064
|
run-1/checkpoint-2138/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-2138/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-2138/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-2138/trainer_state.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.40976281740188225,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-2138",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2138,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.23,
|
13 |
+
"grad_norm": 21.092390060424805,
|
14 |
+
"learning_rate": 1.2650690583673927e-05,
|
15 |
+
"loss": 0.5742,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.47,
|
20 |
+
"grad_norm": 14.845769882202148,
|
21 |
+
"learning_rate": 1.0975546173759478e-05,
|
22 |
+
"loss": 0.5397,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.7,
|
27 |
+
"grad_norm": 13.874490737915039,
|
28 |
+
"learning_rate": 9.300401763845028e-06,
|
29 |
+
"loss": 0.5327,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.94,
|
34 |
+
"grad_norm": 22.50566864013672,
|
35 |
+
"learning_rate": 7.625257353930576e-06,
|
36 |
+
"loss": 0.5138,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.0,
|
41 |
+
"eval_loss": 0.6036589741706848,
|
42 |
+
"eval_matthews_correlation": 0.40976281740188225,
|
43 |
+
"eval_runtime": 0.3434,
|
44 |
+
"eval_samples_per_second": 3036.988,
|
45 |
+
"eval_steps_per_second": 192.178,
|
46 |
+
"step": 2138
|
47 |
+
}
|
48 |
+
],
|
49 |
+
"logging_steps": 500,
|
50 |
+
"max_steps": 4276,
|
51 |
+
"num_input_tokens_seen": 0,
|
52 |
+
"num_train_epochs": 2,
|
53 |
+
"save_steps": 500,
|
54 |
+
"total_flos": 32518676566944.0,
|
55 |
+
"train_batch_size": 4,
|
56 |
+
"trial_name": null,
|
57 |
+
"trial_params": {
|
58 |
+
"learning_rate": 1.4325834993588377e-05,
|
59 |
+
"num_train_epochs": 2,
|
60 |
+
"per_device_train_batch_size": 4,
|
61 |
+
"seed": 4
|
62 |
+
}
|
63 |
+
}
|
run-1/checkpoint-2138/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a3e14306d3219fca061bb971b2957968ed8c21f8f1a0abd2b0cce499c151b2a
|
3 |
+
size 4984
|
run-1/checkpoint-2138/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 sha256:0a3e14306d3219fca061bb971b2957968ed8c21f8f1a0abd2b0cce499c151b2a
|
3 |
size 4984
|