Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-4/checkpoint-144/model.safetensors +1 -1
- run-4/checkpoint-144/optimizer.pt +1 -1
- run-4/checkpoint-144/rng_state.pth +1 -1
- run-4/checkpoint-144/scheduler.pt +1 -1
- run-4/checkpoint-144/trainer_state.json +20 -40
- run-4/checkpoint-144/training_args.bin +1 -1
- run-4/checkpoint-216/config.json +31 -0
- run-4/checkpoint-216/model.safetensors +3 -0
- run-4/checkpoint-216/optimizer.pt +3 -0
- run-4/checkpoint-216/rng_state.pth +3 -0
- run-4/checkpoint-216/scheduler.pt +3 -0
- run-4/checkpoint-216/special_tokens_map.json +7 -0
- run-4/checkpoint-216/tokenizer.json +0 -0
- run-4/checkpoint-216/tokenizer_config.json +55 -0
- run-4/checkpoint-216/trainer_state.json +56 -0
- run-4/checkpoint-216/training_args.bin +3 -0
- run-4/checkpoint-216/vocab.txt +0 -0
- run-4/checkpoint-288/config.json +31 -0
- run-4/checkpoint-288/model.safetensors +3 -0
- run-4/checkpoint-288/optimizer.pt +3 -0
- run-4/checkpoint-288/rng_state.pth +3 -0
- run-4/checkpoint-288/scheduler.pt +3 -0
- run-4/checkpoint-288/special_tokens_map.json +7 -0
- run-4/checkpoint-288/tokenizer.json +0 -0
- run-4/checkpoint-288/tokenizer_config.json +55 -0
- run-4/checkpoint-288/trainer_state.json +66 -0
- run-4/checkpoint-288/training_args.bin +3 -0
- run-4/checkpoint-288/vocab.txt +0 -0
- run-6/checkpoint-36/config.json +31 -0
- run-6/checkpoint-36/model.safetensors +3 -0
- run-6/checkpoint-36/optimizer.pt +3 -0
- run-6/checkpoint-36/rng_state.pth +3 -0
- run-6/checkpoint-36/scheduler.pt +3 -0
- run-6/checkpoint-36/special_tokens_map.json +7 -0
- run-6/checkpoint-36/tokenizer.json +0 -0
- run-6/checkpoint-36/tokenizer_config.json +55 -0
- run-6/checkpoint-36/trainer_state.json +36 -0
- run-6/checkpoint-36/training_args.bin +3 -0
- run-6/checkpoint-36/vocab.txt +0 -0
- runs/Mar06_19-02-43_8a0d46b883ab/events.out.tfevents.1709752299.8a0d46b883ab.2624.7 +3 -0
- runs/Mar06_19-02-43_8a0d46b883ab/events.out.tfevents.1709752304.8a0d46b883ab.2624.8 +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 267829484
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:682075003b57e601a8439ef50dd57a6fc26442079b6fc6e7b62c08b98b8f1a23
|
3 |
size 267829484
|
run-4/checkpoint-144/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267829484
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67b96031aac114c6e35186c47bedb6093c9b1d8d7a35080d4af0e5427b7c0e7a
|
3 |
size 267829484
|
run-4/checkpoint-144/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535721146
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb35cac1bb27bfb5fff6849dd603b20c0df6498f36f3c3399382e82c90dbfd99
|
3 |
size 535721146
|
run-4/checkpoint-144/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:ba4ef1c5e753a9401f18db6dd0e9badc9fb4e3e4956aafa5bbed209ec8cba9e0
|
3 |
size 14244
|
run-4/checkpoint-144/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:a78e4fab71e71f8cfdac39d3ebd41054aafb6de39f3ccc727afec93c8a6994f8
|
3 |
size 1064
|
run-4/checkpoint-144/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-144",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 144,
|
7 |
"is_hyper_param_search": true,
|
@@ -10,57 +10,37 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss":
|
14 |
-
"eval_pearson": 0.
|
15 |
-
"eval_runtime": 0.
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_spearmanr": 0.
|
18 |
-
"eval_steps_per_second":
|
19 |
-
"step": 36
|
20 |
-
},
|
21 |
-
{
|
22 |
-
"epoch": 2.0,
|
23 |
-
"eval_loss": 2.214840888977051,
|
24 |
-
"eval_pearson": 0.22452541125699038,
|
25 |
-
"eval_runtime": 0.9301,
|
26 |
-
"eval_samples_per_second": 1612.779,
|
27 |
-
"eval_spearmanr": 0.24754498733937647,
|
28 |
-
"eval_steps_per_second": 101.067,
|
29 |
"step": 72
|
30 |
},
|
31 |
{
|
32 |
-
"epoch":
|
33 |
-
"eval_loss":
|
34 |
-
"eval_pearson": 0.
|
35 |
-
"eval_runtime": 0.
|
36 |
-
"eval_samples_per_second":
|
37 |
-
"eval_spearmanr": 0.
|
38 |
-
"eval_steps_per_second":
|
39 |
-
"step": 108
|
40 |
-
},
|
41 |
-
{
|
42 |
-
"epoch": 4.0,
|
43 |
-
"eval_loss": 2.1628456115722656,
|
44 |
-
"eval_pearson": 0.5270714523203409,
|
45 |
-
"eval_runtime": 0.9378,
|
46 |
-
"eval_samples_per_second": 1599.452,
|
47 |
-
"eval_spearmanr": 0.5570093927998047,
|
48 |
-
"eval_steps_per_second": 100.232,
|
49 |
"step": 144
|
50 |
}
|
51 |
],
|
52 |
"logging_steps": 500,
|
53 |
-
"max_steps":
|
54 |
"num_input_tokens_seen": 0,
|
55 |
"num_train_epochs": 4,
|
56 |
"save_steps": 500,
|
57 |
"total_flos": 0,
|
58 |
-
"train_batch_size":
|
59 |
"trial_name": null,
|
60 |
"trial_params": {
|
61 |
-
"learning_rate":
|
62 |
"num_train_epochs": 4,
|
63 |
-
"per_device_train_batch_size":
|
64 |
-
"seed":
|
65 |
}
|
66 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8072119226154155,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-144",
|
4 |
+
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 144,
|
7 |
"is_hyper_param_search": true,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 1.9030543565750122,
|
14 |
+
"eval_pearson": 0.6173001362903047,
|
15 |
+
"eval_runtime": 0.7967,
|
16 |
+
"eval_samples_per_second": 1882.655,
|
17 |
+
"eval_spearmanr": 0.6065460603935124,
|
18 |
+
"eval_steps_per_second": 117.98,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
"step": 72
|
20 |
},
|
21 |
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 1.0358508825302124,
|
24 |
+
"eval_pearson": 0.8072119226154155,
|
25 |
+
"eval_runtime": 0.8084,
|
26 |
+
"eval_samples_per_second": 1855.522,
|
27 |
+
"eval_spearmanr": 0.8100114657508573,
|
28 |
+
"eval_steps_per_second": 116.279,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
"step": 144
|
30 |
}
|
31 |
],
|
32 |
"logging_steps": 500,
|
33 |
+
"max_steps": 288,
|
34 |
"num_input_tokens_seen": 0,
|
35 |
"num_train_epochs": 4,
|
36 |
"save_steps": 500,
|
37 |
"total_flos": 0,
|
38 |
+
"train_batch_size": 8,
|
39 |
"trial_name": null,
|
40 |
"trial_params": {
|
41 |
+
"learning_rate": 2.5574276250903696e-05,
|
42 |
"num_train_epochs": 4,
|
43 |
+
"per_device_train_batch_size": 8,
|
44 |
+
"seed": 40
|
45 |
}
|
46 |
}
|
run-4/checkpoint-144/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feadc6806513ec4d8a685f2034114bf8544eb719bcbc361b5282de434aef445a
|
3 |
size 4920
|
run-4/checkpoint-216/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "distilbert",
|
20 |
+
"n_heads": 12,
|
21 |
+
"n_layers": 6,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"problem_type": "regression",
|
24 |
+
"qa_dropout": 0.1,
|
25 |
+
"seq_classif_dropout": 0.2,
|
26 |
+
"sinusoidal_pos_embds": false,
|
27 |
+
"tie_weights_": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.38.2",
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
run-4/checkpoint-216/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98e7ed4567edaf8cafd3b04aab5b2c4357198ecc55e0a732fb05e92389af23be
|
3 |
+
size 267829484
|
run-4/checkpoint-216/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:445fbf7678428da33cc6ef3dab5c6183654679f7828b6489a42b3512166af7e3
|
3 |
+
size 535721146
|
run-4/checkpoint-216/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:038e71594f5547a63cb7e467f33b50c0377a188cf2dc5dbbab756833f58c85c4
|
3 |
+
size 14244
|
run-4/checkpoint-216/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a286dc983477a9eeb41942ec56313b71758475c64c11b6678337da3196238271
|
3 |
+
size 1064
|
run-4/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-4/checkpoint-216/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/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-4/checkpoint-216/trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.811708722217708,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-216",
|
4 |
+
"epoch": 3.0,
|
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": 1.9030543565750122,
|
14 |
+
"eval_pearson": 0.6173001362903047,
|
15 |
+
"eval_runtime": 0.7967,
|
16 |
+
"eval_samples_per_second": 1882.655,
|
17 |
+
"eval_spearmanr": 0.6065460603935124,
|
18 |
+
"eval_steps_per_second": 117.98,
|
19 |
+
"step": 72
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 1.0358508825302124,
|
24 |
+
"eval_pearson": 0.8072119226154155,
|
25 |
+
"eval_runtime": 0.8084,
|
26 |
+
"eval_samples_per_second": 1855.522,
|
27 |
+
"eval_spearmanr": 0.8100114657508573,
|
28 |
+
"eval_steps_per_second": 116.279,
|
29 |
+
"step": 144
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 0.8175650238990784,
|
34 |
+
"eval_pearson": 0.811708722217708,
|
35 |
+
"eval_runtime": 0.7965,
|
36 |
+
"eval_samples_per_second": 1883.148,
|
37 |
+
"eval_spearmanr": 0.81090938379838,
|
38 |
+
"eval_steps_per_second": 118.011,
|
39 |
+
"step": 216
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 500,
|
43 |
+
"max_steps": 288,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 4,
|
46 |
+
"save_steps": 500,
|
47 |
+
"total_flos": 0,
|
48 |
+
"train_batch_size": 8,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": {
|
51 |
+
"learning_rate": 2.5574276250903696e-05,
|
52 |
+
"num_train_epochs": 4,
|
53 |
+
"per_device_train_batch_size": 8,
|
54 |
+
"seed": 40
|
55 |
+
}
|
56 |
+
}
|
run-4/checkpoint-216/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feadc6806513ec4d8a685f2034114bf8544eb719bcbc361b5282de434aef445a
|
3 |
+
size 4920
|
run-4/checkpoint-216/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-288/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "distilbert",
|
20 |
+
"n_heads": 12,
|
21 |
+
"n_layers": 6,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"problem_type": "regression",
|
24 |
+
"qa_dropout": 0.1,
|
25 |
+
"seq_classif_dropout": 0.2,
|
26 |
+
"sinusoidal_pos_embds": false,
|
27 |
+
"tie_weights_": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.38.2",
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
run-4/checkpoint-288/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6125377ff48a62c6d03a21d9fb4b335d9f21de4693c8cb1a630ff4548111d41e
|
3 |
+
size 267829484
|
run-4/checkpoint-288/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5aabc147b2850bcbb51f8aa3dae263c5d15dc8141718fe77ade4c5df57146576
|
3 |
+
size 535721146
|
run-4/checkpoint-288/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f626927ff09c9fc535421ec8dad43c9dbeb3494a6f853f65416b0df7692c7c0
|
3 |
+
size 14244
|
run-4/checkpoint-288/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cde1ecae63baaddae85f5be9fd342ed6778060c6fd18855f3528ca3e88271967
|
3 |
+
size 1064
|
run-4/checkpoint-288/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-4/checkpoint-288/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-288/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-4/checkpoint-288/trainer_state.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8210299726217956,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-288",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 288,
|
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": 1.9030543565750122,
|
14 |
+
"eval_pearson": 0.6173001362903047,
|
15 |
+
"eval_runtime": 0.7967,
|
16 |
+
"eval_samples_per_second": 1882.655,
|
17 |
+
"eval_spearmanr": 0.6065460603935124,
|
18 |
+
"eval_steps_per_second": 117.98,
|
19 |
+
"step": 72
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 1.0358508825302124,
|
24 |
+
"eval_pearson": 0.8072119226154155,
|
25 |
+
"eval_runtime": 0.8084,
|
26 |
+
"eval_samples_per_second": 1855.522,
|
27 |
+
"eval_spearmanr": 0.8100114657508573,
|
28 |
+
"eval_steps_per_second": 116.279,
|
29 |
+
"step": 144
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 0.8175650238990784,
|
34 |
+
"eval_pearson": 0.811708722217708,
|
35 |
+
"eval_runtime": 0.7965,
|
36 |
+
"eval_samples_per_second": 1883.148,
|
37 |
+
"eval_spearmanr": 0.81090938379838,
|
38 |
+
"eval_steps_per_second": 118.011,
|
39 |
+
"step": 216
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 4.0,
|
43 |
+
"eval_loss": 0.7593460083007812,
|
44 |
+
"eval_pearson": 0.8210299726217956,
|
45 |
+
"eval_runtime": 0.8059,
|
46 |
+
"eval_samples_per_second": 1861.168,
|
47 |
+
"eval_spearmanr": 0.8175945414249048,
|
48 |
+
"eval_steps_per_second": 116.633,
|
49 |
+
"step": 288
|
50 |
+
}
|
51 |
+
],
|
52 |
+
"logging_steps": 500,
|
53 |
+
"max_steps": 288,
|
54 |
+
"num_input_tokens_seen": 0,
|
55 |
+
"num_train_epochs": 4,
|
56 |
+
"save_steps": 500,
|
57 |
+
"total_flos": 0,
|
58 |
+
"train_batch_size": 8,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": {
|
61 |
+
"learning_rate": 2.5574276250903696e-05,
|
62 |
+
"num_train_epochs": 4,
|
63 |
+
"per_device_train_batch_size": 8,
|
64 |
+
"seed": 40
|
65 |
+
}
|
66 |
+
}
|
run-4/checkpoint-288/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feadc6806513ec4d8a685f2034114bf8544eb719bcbc361b5282de434aef445a
|
3 |
+
size 4920
|
run-4/checkpoint-288/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-6/checkpoint-36/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "distilbert",
|
20 |
+
"n_heads": 12,
|
21 |
+
"n_layers": 6,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"problem_type": "regression",
|
24 |
+
"qa_dropout": 0.1,
|
25 |
+
"seq_classif_dropout": 0.2,
|
26 |
+
"sinusoidal_pos_embds": false,
|
27 |
+
"tie_weights_": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.38.2",
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
run-6/checkpoint-36/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:682075003b57e601a8439ef50dd57a6fc26442079b6fc6e7b62c08b98b8f1a23
|
3 |
+
size 267829484
|
run-6/checkpoint-36/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acb967429e79d5994e9bbee53ee756e4bd485fb25770e317eb5d665d5624aa4a
|
3 |
+
size 535721146
|
run-6/checkpoint-36/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1759e9e584a8dfdbc46ee44ac9cb0fa528dc393f134f4baed8bc200cff4e9da6
|
3 |
+
size 14244
|
run-6/checkpoint-36/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40ed83d51e7a677680096eee72a2f302a4690ed8aa59b8b755d6677d26162cda
|
3 |
+
size 1064
|
run-6/checkpoint-36/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-6/checkpoint-36/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-6/checkpoint-36/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-6/checkpoint-36/trainer_state.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5682043731058958,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-6/checkpoint-36",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 36,
|
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": 1.9094555377960205,
|
14 |
+
"eval_pearson": 0.5682043731058958,
|
15 |
+
"eval_runtime": 0.8058,
|
16 |
+
"eval_samples_per_second": 1861.603,
|
17 |
+
"eval_spearmanr": 0.5712894898305707,
|
18 |
+
"eval_steps_per_second": 116.66,
|
19 |
+
"step": 36
|
20 |
+
}
|
21 |
+
],
|
22 |
+
"logging_steps": 500,
|
23 |
+
"max_steps": 108,
|
24 |
+
"num_input_tokens_seen": 0,
|
25 |
+
"num_train_epochs": 3,
|
26 |
+
"save_steps": 500,
|
27 |
+
"total_flos": 0,
|
28 |
+
"train_batch_size": 16,
|
29 |
+
"trial_name": null,
|
30 |
+
"trial_params": {
|
31 |
+
"learning_rate": 5.712636964604973e-05,
|
32 |
+
"num_train_epochs": 3,
|
33 |
+
"per_device_train_batch_size": 16,
|
34 |
+
"seed": 36
|
35 |
+
}
|
36 |
+
}
|
run-6/checkpoint-36/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09f7a49d428cc1a74ed02b4fda35aa90bed1b7778219bce664edeb44d1f7e361
|
3 |
+
size 4920
|
run-6/checkpoint-36/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar06_19-02-43_8a0d46b883ab/events.out.tfevents.1709752299.8a0d46b883ab.2624.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ad5eed2f3c046092c5a21823082b1a7d17ca1c705ab721131332ce3b1154ebd
|
3 |
+
size 4981
|
runs/Mar06_19-02-43_8a0d46b883ab/events.out.tfevents.1709752304.8a0d46b883ab.2624.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88225183ae7ed111b0b79d8272c60931d239d29f05a81698b112152de0aab9bf
|
3 |
+
size 6059
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09f7a49d428cc1a74ed02b4fda35aa90bed1b7778219bce664edeb44d1f7e361
|
3 |
size 4920
|