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-0/checkpoint-18/config.json +31 -0
- run-0/checkpoint-18/model.safetensors +3 -0
- run-0/checkpoint-18/optimizer.pt +3 -0
- run-0/checkpoint-18/rng_state.pth +3 -0
- run-0/checkpoint-18/scheduler.pt +3 -0
- run-0/checkpoint-18/special_tokens_map.json +7 -0
- run-0/checkpoint-18/tokenizer.json +0 -0
- run-0/checkpoint-18/tokenizer_config.json +55 -0
- run-0/checkpoint-18/trainer_state.json +46 -0
- run-0/checkpoint-18/training_args.bin +3 -0
- run-0/checkpoint-18/vocab.txt +0 -0
- run-0/checkpoint-27/config.json +31 -0
- run-0/checkpoint-27/model.safetensors +3 -0
- run-0/checkpoint-27/optimizer.pt +3 -0
- run-0/checkpoint-27/rng_state.pth +3 -0
- run-0/checkpoint-27/scheduler.pt +3 -0
- run-0/checkpoint-27/special_tokens_map.json +7 -0
- run-0/checkpoint-27/tokenizer.json +0 -0
- run-0/checkpoint-27/tokenizer_config.json +55 -0
- run-0/checkpoint-27/trainer_state.json +56 -0
- run-0/checkpoint-27/training_args.bin +3 -0
- run-0/checkpoint-27/vocab.txt +0 -0
- run-0/checkpoint-36/config.json +31 -0
- run-0/checkpoint-36/model.safetensors +3 -0
- run-0/checkpoint-36/optimizer.pt +3 -0
- run-0/checkpoint-36/rng_state.pth +3 -0
- run-0/checkpoint-36/scheduler.pt +3 -0
- run-0/checkpoint-36/special_tokens_map.json +7 -0
- run-0/checkpoint-36/tokenizer.json +0 -0
- run-0/checkpoint-36/tokenizer_config.json +55 -0
- run-0/checkpoint-36/trainer_state.json +66 -0
- run-0/checkpoint-36/training_args.bin +3 -0
- run-0/checkpoint-36/vocab.txt +0 -0
- run-0/checkpoint-45/config.json +31 -0
- run-0/checkpoint-45/model.safetensors +3 -0
- run-0/checkpoint-45/optimizer.pt +3 -0
- run-0/checkpoint-45/rng_state.pth +3 -0
- run-0/checkpoint-45/scheduler.pt +3 -0
- run-0/checkpoint-45/special_tokens_map.json +7 -0
- run-0/checkpoint-45/tokenizer.json +0 -0
- run-0/checkpoint-45/tokenizer_config.json +55 -0
- run-0/checkpoint-45/trainer_state.json +76 -0
- run-0/checkpoint-45/training_args.bin +3 -0
- run-0/checkpoint-45/vocab.txt +0 -0
- run-1/checkpoint-72/model.safetensors +1 -1
- run-1/checkpoint-72/optimizer.pt +1 -1
- run-1/checkpoint-72/rng_state.pth +2 -2
- run-1/checkpoint-72/scheduler.pt +1 -1
- run-1/checkpoint-72/trainer_state.json +15 -45
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 sha256:252cb0fde84c771fe9f26cd1f149f0c098738ed7f935bde0df5cbd3694bf14b3
|
3 |
size 267829484
|
run-0/checkpoint-18/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-0/checkpoint-18/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baf1bc3b6031979712ae9a703e994639a838c6d1418547d3de4cd5d42fcc1987
|
3 |
+
size 267829484
|
run-0/checkpoint-18/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:678ee58ea945e14347259ddbee8c7087506c15ab3bb2d556a6d4952c8c3a495f
|
3 |
+
size 535721146
|
run-0/checkpoint-18/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e286b9bff8b53bef74ce22a2bb491418497057e71b61563237976997da7ac700
|
3 |
+
size 14244
|
run-0/checkpoint-18/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39cff69ca41eb8f894bf9831891f8d1750928f9531a056de16a4c4e7a269dc4a
|
3 |
+
size 1064
|
run-0/checkpoint-18/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-18/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-18/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-18/trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4951149744376661,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-18",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 18,
|
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": 2.302802324295044,
|
14 |
+
"eval_pearson": 0.11274566771797583,
|
15 |
+
"eval_runtime": 0.9178,
|
16 |
+
"eval_samples_per_second": 1634.281,
|
17 |
+
"eval_spearmanr": 0.12987920930990302,
|
18 |
+
"eval_steps_per_second": 102.415,
|
19 |
+
"step": 9
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 2.3637888431549072,
|
24 |
+
"eval_pearson": 0.4951149744376661,
|
25 |
+
"eval_runtime": 1.7789,
|
26 |
+
"eval_samples_per_second": 843.198,
|
27 |
+
"eval_spearmanr": 0.4849163929338027,
|
28 |
+
"eval_steps_per_second": 52.84,
|
29 |
+
"step": 18
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"logging_steps": 500,
|
33 |
+
"max_steps": 45,
|
34 |
+
"num_input_tokens_seen": 0,
|
35 |
+
"num_train_epochs": 5,
|
36 |
+
"save_steps": 500,
|
37 |
+
"total_flos": 0,
|
38 |
+
"train_batch_size": 64,
|
39 |
+
"trial_name": null,
|
40 |
+
"trial_params": {
|
41 |
+
"learning_rate": 4.481764265618048e-05,
|
42 |
+
"num_train_epochs": 5,
|
43 |
+
"per_device_train_batch_size": 64,
|
44 |
+
"seed": 34
|
45 |
+
}
|
46 |
+
}
|
run-0/checkpoint-18/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c09fba38efbfaed97000a3a94d8c55aa1cde1316bbda4831aa4e5e1bd7ee7a7
|
3 |
+
size 4920
|
run-0/checkpoint-18/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-27/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-0/checkpoint-27/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8be6f6fa0df4bfbbbfda08cce877b6e7e3b0283edbd2c7b75f7df9bb5286c0b1
|
3 |
+
size 267829484
|
run-0/checkpoint-27/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8b66082d319b2338bcfea10c929a0420129fc6863b06548d301048bdc23bd87
|
3 |
+
size 535721146
|
run-0/checkpoint-27/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8d52213f53e08ff3d1242d3153448b0b10804720396a2908b09ce5eb6baf816
|
3 |
+
size 14244
|
run-0/checkpoint-27/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5e15d089373332dccb9316de3e868ab812d210567758f27a5c51bef54f05aa9
|
3 |
+
size 1064
|
run-0/checkpoint-27/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-27/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-27/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-27/trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6914272738462158,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-27",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 27,
|
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": 2.302802324295044,
|
14 |
+
"eval_pearson": 0.11274566771797583,
|
15 |
+
"eval_runtime": 0.9178,
|
16 |
+
"eval_samples_per_second": 1634.281,
|
17 |
+
"eval_spearmanr": 0.12987920930990302,
|
18 |
+
"eval_steps_per_second": 102.415,
|
19 |
+
"step": 9
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 2.3637888431549072,
|
24 |
+
"eval_pearson": 0.4951149744376661,
|
25 |
+
"eval_runtime": 1.7789,
|
26 |
+
"eval_samples_per_second": 843.198,
|
27 |
+
"eval_spearmanr": 0.4849163929338027,
|
28 |
+
"eval_steps_per_second": 52.84,
|
29 |
+
"step": 18
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 1.796323537826538,
|
34 |
+
"eval_pearson": 0.6914272738462158,
|
35 |
+
"eval_runtime": 2.2193,
|
36 |
+
"eval_samples_per_second": 675.895,
|
37 |
+
"eval_spearmanr": 0.6818774421011495,
|
38 |
+
"eval_steps_per_second": 42.356,
|
39 |
+
"step": 27
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 500,
|
43 |
+
"max_steps": 45,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 5,
|
46 |
+
"save_steps": 500,
|
47 |
+
"total_flos": 0,
|
48 |
+
"train_batch_size": 64,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": {
|
51 |
+
"learning_rate": 4.481764265618048e-05,
|
52 |
+
"num_train_epochs": 5,
|
53 |
+
"per_device_train_batch_size": 64,
|
54 |
+
"seed": 34
|
55 |
+
}
|
56 |
+
}
|
run-0/checkpoint-27/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c09fba38efbfaed97000a3a94d8c55aa1cde1316bbda4831aa4e5e1bd7ee7a7
|
3 |
+
size 4920
|
run-0/checkpoint-27/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/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-0/checkpoint-36/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4970e9ff8f9a3040577b0049ae497296e6987a30fac9b1978c983f913df74fa5
|
3 |
+
size 267829484
|
run-0/checkpoint-36/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8139b1565518d5a05b7de8a7feebaf2491cddb1d6df45d777067b9c734fa147a
|
3 |
+
size 535721146
|
run-0/checkpoint-36/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bab4519567a43826cccf1e52a5b955644cdaddb11d27e410800b049731a6001b
|
3 |
+
size 14244
|
run-0/checkpoint-36/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b82dab0331e4c7b81b892b8fe9731b1b085524364be8bf73cf5a4d037bc735a6
|
3 |
+
size 1064
|
run-0/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-0/checkpoint-36/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/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-0/checkpoint-36/trainer_state.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7636700196702717,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-36",
|
4 |
+
"epoch": 4.0,
|
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": 2.302802324295044,
|
14 |
+
"eval_pearson": 0.11274566771797583,
|
15 |
+
"eval_runtime": 0.9178,
|
16 |
+
"eval_samples_per_second": 1634.281,
|
17 |
+
"eval_spearmanr": 0.12987920930990302,
|
18 |
+
"eval_steps_per_second": 102.415,
|
19 |
+
"step": 9
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 2.3637888431549072,
|
24 |
+
"eval_pearson": 0.4951149744376661,
|
25 |
+
"eval_runtime": 1.7789,
|
26 |
+
"eval_samples_per_second": 843.198,
|
27 |
+
"eval_spearmanr": 0.4849163929338027,
|
28 |
+
"eval_steps_per_second": 52.84,
|
29 |
+
"step": 18
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 1.796323537826538,
|
34 |
+
"eval_pearson": 0.6914272738462158,
|
35 |
+
"eval_runtime": 2.2193,
|
36 |
+
"eval_samples_per_second": 675.895,
|
37 |
+
"eval_spearmanr": 0.6818774421011495,
|
38 |
+
"eval_steps_per_second": 42.356,
|
39 |
+
"step": 27
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 4.0,
|
43 |
+
"eval_loss": 1.0367522239685059,
|
44 |
+
"eval_pearson": 0.7636700196702717,
|
45 |
+
"eval_runtime": 1.9263,
|
46 |
+
"eval_samples_per_second": 778.713,
|
47 |
+
"eval_spearmanr": 0.7608002745735356,
|
48 |
+
"eval_steps_per_second": 48.799,
|
49 |
+
"step": 36
|
50 |
+
}
|
51 |
+
],
|
52 |
+
"logging_steps": 500,
|
53 |
+
"max_steps": 45,
|
54 |
+
"num_input_tokens_seen": 0,
|
55 |
+
"num_train_epochs": 5,
|
56 |
+
"save_steps": 500,
|
57 |
+
"total_flos": 0,
|
58 |
+
"train_batch_size": 64,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": {
|
61 |
+
"learning_rate": 4.481764265618048e-05,
|
62 |
+
"num_train_epochs": 5,
|
63 |
+
"per_device_train_batch_size": 64,
|
64 |
+
"seed": 34
|
65 |
+
}
|
66 |
+
}
|
run-0/checkpoint-36/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c09fba38efbfaed97000a3a94d8c55aa1cde1316bbda4831aa4e5e1bd7ee7a7
|
3 |
+
size 4920
|
run-0/checkpoint-36/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-45/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-0/checkpoint-45/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a4722c63f648fc239d2d7575df701f7f042b0f1f2330e9322ec6da12374eeac
|
3 |
+
size 267829484
|
run-0/checkpoint-45/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:456c7dad06cf3ecce368d782ff76c0738e27ea2dac98e40a035b1e2d897f2ad1
|
3 |
+
size 535721146
|
run-0/checkpoint-45/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5db689fab0a3dc998ce051211556a4fde769c6ad5b5e6756d907fec36410b2aa
|
3 |
+
size 14244
|
run-0/checkpoint-45/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4eddd4325e87d0a81d76b96f2b101ad452ca3c8c920ff3e7f6732184e009808
|
3 |
+
size 1064
|
run-0/checkpoint-45/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-45/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-45/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-45/trainer_state.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7772615297087864,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-45",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 45,
|
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": 2.302802324295044,
|
14 |
+
"eval_pearson": 0.11274566771797583,
|
15 |
+
"eval_runtime": 0.9178,
|
16 |
+
"eval_samples_per_second": 1634.281,
|
17 |
+
"eval_spearmanr": 0.12987920930990302,
|
18 |
+
"eval_steps_per_second": 102.415,
|
19 |
+
"step": 9
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 2.3637888431549072,
|
24 |
+
"eval_pearson": 0.4951149744376661,
|
25 |
+
"eval_runtime": 1.7789,
|
26 |
+
"eval_samples_per_second": 843.198,
|
27 |
+
"eval_spearmanr": 0.4849163929338027,
|
28 |
+
"eval_steps_per_second": 52.84,
|
29 |
+
"step": 18
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 1.796323537826538,
|
34 |
+
"eval_pearson": 0.6914272738462158,
|
35 |
+
"eval_runtime": 2.2193,
|
36 |
+
"eval_samples_per_second": 675.895,
|
37 |
+
"eval_spearmanr": 0.6818774421011495,
|
38 |
+
"eval_steps_per_second": 42.356,
|
39 |
+
"step": 27
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 4.0,
|
43 |
+
"eval_loss": 1.0367522239685059,
|
44 |
+
"eval_pearson": 0.7636700196702717,
|
45 |
+
"eval_runtime": 1.9263,
|
46 |
+
"eval_samples_per_second": 778.713,
|
47 |
+
"eval_spearmanr": 0.7608002745735356,
|
48 |
+
"eval_steps_per_second": 48.799,
|
49 |
+
"step": 36
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 5.0,
|
53 |
+
"eval_loss": 1.022187352180481,
|
54 |
+
"eval_pearson": 0.7772615297087864,
|
55 |
+
"eval_runtime": 1.1629,
|
56 |
+
"eval_samples_per_second": 1289.882,
|
57 |
+
"eval_spearmanr": 0.7651538770048484,
|
58 |
+
"eval_steps_per_second": 80.833,
|
59 |
+
"step": 45
|
60 |
+
}
|
61 |
+
],
|
62 |
+
"logging_steps": 500,
|
63 |
+
"max_steps": 45,
|
64 |
+
"num_input_tokens_seen": 0,
|
65 |
+
"num_train_epochs": 5,
|
66 |
+
"save_steps": 500,
|
67 |
+
"total_flos": 0,
|
68 |
+
"train_batch_size": 64,
|
69 |
+
"trial_name": null,
|
70 |
+
"trial_params": {
|
71 |
+
"learning_rate": 4.481764265618048e-05,
|
72 |
+
"num_train_epochs": 5,
|
73 |
+
"per_device_train_batch_size": 64,
|
74 |
+
"seed": 34
|
75 |
+
}
|
76 |
+
}
|
run-0/checkpoint-45/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c09fba38efbfaed97000a3a94d8c55aa1cde1316bbda4831aa4e5e1bd7ee7a7
|
3 |
+
size 4920
|
run-0/checkpoint-45/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-72/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 sha256:252cb0fde84c771fe9f26cd1f149f0c098738ed7f935bde0df5cbd3694bf14b3
|
3 |
size 267829484
|
run-1/checkpoint-72/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 sha256:6be8502a6b70d61fd71071c3d7a0bb95d5488c14b6bb1282e4f401b255c57c85
|
3 |
size 535721146
|
run-1/checkpoint-72/rng_state.pth
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 sha256:0c9f2f274085426ce5f70a91b3b5b9148df7fb50b52222177f28f81034e3c481
|
3 |
+
size 14244
|
run-1/checkpoint-72/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:a8eb0b045faee1fcc8466dcf28c9f8cbe045f9fe6e8ffc851d18de161e691e00
|
3 |
size 1064
|
run-1/checkpoint-72/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-72",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 72,
|
7 |
"is_hyper_param_search": true,
|
@@ -10,57 +10,27 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss": 1.
|
14 |
-
"eval_pearson": 0.
|
15 |
-
"eval_runtime": 0.
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_spearmanr": 0.
|
18 |
-
"eval_steps_per_second":
|
19 |
-
"step": 18
|
20 |
-
},
|
21 |
-
{
|
22 |
-
"epoch": 2.0,
|
23 |
-
"eval_loss": 1.7851035594940186,
|
24 |
-
"eval_pearson": 0.6869651194383046,
|
25 |
-
"eval_runtime": 0.8033,
|
26 |
-
"eval_samples_per_second": 1867.276,
|
27 |
-
"eval_spearmanr": 0.619343622594654,
|
28 |
-
"eval_steps_per_second": 117.016,
|
29 |
-
"step": 36
|
30 |
-
},
|
31 |
-
{
|
32 |
-
"epoch": 3.0,
|
33 |
-
"eval_loss": 0.7565258741378784,
|
34 |
-
"eval_pearson": 0.8285257169035537,
|
35 |
-
"eval_runtime": 0.8057,
|
36 |
-
"eval_samples_per_second": 1861.771,
|
37 |
-
"eval_spearmanr": 0.8319559534455686,
|
38 |
-
"eval_steps_per_second": 116.671,
|
39 |
-
"step": 54
|
40 |
-
},
|
41 |
-
{
|
42 |
-
"epoch": 4.0,
|
43 |
-
"eval_loss": 0.7455037236213684,
|
44 |
-
"eval_pearson": 0.8337510188712361,
|
45 |
-
"eval_runtime": 0.7987,
|
46 |
-
"eval_samples_per_second": 1877.938,
|
47 |
-
"eval_spearmanr": 0.8313859769239171,
|
48 |
-
"eval_steps_per_second": 117.684,
|
49 |
"step": 72
|
50 |
}
|
51 |
],
|
52 |
"logging_steps": 500,
|
53 |
-
"max_steps":
|
54 |
"num_input_tokens_seen": 0,
|
55 |
-
"num_train_epochs":
|
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":
|
63 |
-
"per_device_train_batch_size":
|
64 |
-
"seed":
|
65 |
}
|
66 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7580884083785275,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-72",
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 72,
|
7 |
"is_hyper_param_search": true,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 1.1846531629562378,
|
14 |
+
"eval_pearson": 0.7580884083785275,
|
15 |
+
"eval_runtime": 0.9281,
|
16 |
+
"eval_samples_per_second": 1616.21,
|
17 |
+
"eval_spearmanr": 0.7189361728033606,
|
18 |
+
"eval_steps_per_second": 101.283,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
"step": 72
|
20 |
}
|
21 |
],
|
22 |
"logging_steps": 500,
|
23 |
+
"max_steps": 216,
|
24 |
"num_input_tokens_seen": 0,
|
25 |
+
"num_train_epochs": 3,
|
26 |
"save_steps": 500,
|
27 |
"total_flos": 0,
|
28 |
+
"train_batch_size": 8,
|
29 |
"trial_name": null,
|
30 |
"trial_params": {
|
31 |
+
"learning_rate": 3.662007760473047e-05,
|
32 |
+
"num_train_epochs": 3,
|
33 |
+
"per_device_train_batch_size": 8,
|
34 |
+
"seed": 7
|
35 |
}
|
36 |
}
|