Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-7/checkpoint-108/config.json +31 -0
- run-7/checkpoint-108/model.safetensors +3 -0
- run-7/checkpoint-108/optimizer.pt +3 -0
- run-7/checkpoint-108/rng_state.pth +3 -0
- run-7/checkpoint-108/scheduler.pt +3 -0
- run-7/checkpoint-108/special_tokens_map.json +7 -0
- run-7/checkpoint-108/tokenizer.json +0 -0
- run-7/checkpoint-108/tokenizer_config.json +55 -0
- run-7/checkpoint-108/trainer_state.json +56 -0
- run-7/checkpoint-108/training_args.bin +3 -0
- run-7/checkpoint-108/vocab.txt +0 -0
- run-7/checkpoint-144/config.json +31 -0
- run-7/checkpoint-144/model.safetensors +3 -0
- run-7/checkpoint-144/optimizer.pt +3 -0
- run-7/checkpoint-144/rng_state.pth +3 -0
- run-7/checkpoint-144/scheduler.pt +3 -0
- run-7/checkpoint-144/special_tokens_map.json +7 -0
- run-7/checkpoint-144/tokenizer.json +0 -0
- run-7/checkpoint-144/tokenizer_config.json +55 -0
- run-7/checkpoint-144/trainer_state.json +66 -0
- run-7/checkpoint-144/training_args.bin +3 -0
- run-7/checkpoint-144/vocab.txt +0 -0
- run-7/checkpoint-72/config.json +31 -0
- run-7/checkpoint-72/model.safetensors +3 -0
- run-7/checkpoint-72/optimizer.pt +3 -0
- run-7/checkpoint-72/rng_state.pth +3 -0
- run-7/checkpoint-72/scheduler.pt +3 -0
- run-7/checkpoint-72/special_tokens_map.json +7 -0
- run-7/checkpoint-72/tokenizer.json +0 -0
- run-7/checkpoint-72/tokenizer_config.json +55 -0
- run-7/checkpoint-72/trainer_state.json +46 -0
- run-7/checkpoint-72/training_args.bin +3 -0
- run-7/checkpoint-72/vocab.txt +0 -0
- run-8/checkpoint-9/config.json +31 -0
- run-8/checkpoint-9/model.safetensors +3 -0
- run-8/checkpoint-9/optimizer.pt +3 -0
- run-8/checkpoint-9/rng_state.pth +3 -0
- run-8/checkpoint-9/scheduler.pt +3 -0
- run-8/checkpoint-9/special_tokens_map.json +7 -0
- run-8/checkpoint-9/tokenizer.json +0 -0
- run-8/checkpoint-9/tokenizer_config.json +55 -0
- run-8/checkpoint-9/trainer_state.json +36 -0
- run-8/checkpoint-9/training_args.bin +3 -0
- run-8/checkpoint-9/vocab.txt +0 -0
- runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709676487.fe13c9557656.828.10 +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 sha256:296a06adfbeff62ca91477d5e82f5670afdbfbc521fd3ce94daa5fb3bdff38d6
|
3 |
size 267829484
|
run-7/checkpoint-108/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-7/checkpoint-108/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:071ff7e497b6d08663367bb4ecd40abe75ce57a85f945ccb684ab74b5356fe64
|
3 |
+
size 267829484
|
run-7/checkpoint-108/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f639f74f8af428176cf6b9c1f5bf256d32aaba167f10b09729853bffb522b96e
|
3 |
+
size 535721146
|
run-7/checkpoint-108/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0aecf885568284746410b2b3a2d0f171bcb339f83b133f1afd3c4d55f0c6ade4
|
3 |
+
size 14244
|
run-7/checkpoint-108/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29f65ce6c2b05666c3bee7b58ae87f6fdc22b8d17d4a4f11d8ffc5899ad68500
|
3 |
+
size 1064
|
run-7/checkpoint-108/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-7/checkpoint-108/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-7/checkpoint-108/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-7/checkpoint-108/trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7983928342038554,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-7/checkpoint-108",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 108,
|
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": 2.1181581020355225,
|
14 |
+
"eval_pearson": 0.457192832227161,
|
15 |
+
"eval_runtime": 0.8791,
|
16 |
+
"eval_samples_per_second": 1706.218,
|
17 |
+
"eval_spearmanr": 0.44927428651795276,
|
18 |
+
"eval_steps_per_second": 106.923,
|
19 |
+
"step": 36
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 1.0036637783050537,
|
24 |
+
"eval_pearson": 0.7920428854372943,
|
25 |
+
"eval_runtime": 0.9239,
|
26 |
+
"eval_samples_per_second": 1623.531,
|
27 |
+
"eval_spearmanr": 0.7786283028593889,
|
28 |
+
"eval_steps_per_second": 101.741,
|
29 |
+
"step": 72
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 0.9715855121612549,
|
34 |
+
"eval_pearson": 0.7983928342038554,
|
35 |
+
"eval_runtime": 0.9626,
|
36 |
+
"eval_samples_per_second": 1558.354,
|
37 |
+
"eval_spearmanr": 0.7966315465683397,
|
38 |
+
"eval_steps_per_second": 97.657,
|
39 |
+
"step": 108
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 500,
|
43 |
+
"max_steps": 144,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 4,
|
46 |
+
"save_steps": 500,
|
47 |
+
"total_flos": 0,
|
48 |
+
"train_batch_size": 16,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": {
|
51 |
+
"learning_rate": 2.2613535003508284e-05,
|
52 |
+
"num_train_epochs": 4,
|
53 |
+
"per_device_train_batch_size": 16,
|
54 |
+
"seed": 19
|
55 |
+
}
|
56 |
+
}
|
run-7/checkpoint-108/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8d651dfeb39fbfdee53e1bd84f374650de80a6c4a3ae4617d7d4651e3cf08bd
|
3 |
+
size 4920
|
run-7/checkpoint-108/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-7/checkpoint-144/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-7/checkpoint-144/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdac1a2fad9635e8ac64216126e9488baaeef5d6419fe1eba3a42b5187caed41
|
3 |
+
size 267829484
|
run-7/checkpoint-144/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72ddf478422395e367427f6ef32f4a886613710c0d39b0b0049cb00456e9f70b
|
3 |
+
size 535721146
|
run-7/checkpoint-144/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d576a454a16bcb0bee7672c93705cc130e1969116aae04c751b2336bf08df3b8
|
3 |
+
size 14244
|
run-7/checkpoint-144/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77665bc6d88adcc4aeaf1dc3b66600ac359f58e6f406d3c8991bc774b4c0a1a7
|
3 |
+
size 1064
|
run-7/checkpoint-144/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-7/checkpoint-144/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-7/checkpoint-144/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-7/checkpoint-144/trainer_state.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8187561753672836,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-7/checkpoint-144",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 144,
|
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": 2.1181581020355225,
|
14 |
+
"eval_pearson": 0.457192832227161,
|
15 |
+
"eval_runtime": 0.8791,
|
16 |
+
"eval_samples_per_second": 1706.218,
|
17 |
+
"eval_spearmanr": 0.44927428651795276,
|
18 |
+
"eval_steps_per_second": 106.923,
|
19 |
+
"step": 36
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 1.0036637783050537,
|
24 |
+
"eval_pearson": 0.7920428854372943,
|
25 |
+
"eval_runtime": 0.9239,
|
26 |
+
"eval_samples_per_second": 1623.531,
|
27 |
+
"eval_spearmanr": 0.7786283028593889,
|
28 |
+
"eval_steps_per_second": 101.741,
|
29 |
+
"step": 72
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 0.9715855121612549,
|
34 |
+
"eval_pearson": 0.7983928342038554,
|
35 |
+
"eval_runtime": 0.9626,
|
36 |
+
"eval_samples_per_second": 1558.354,
|
37 |
+
"eval_spearmanr": 0.7966315465683397,
|
38 |
+
"eval_steps_per_second": 97.657,
|
39 |
+
"step": 108
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 4.0,
|
43 |
+
"eval_loss": 0.7629258632659912,
|
44 |
+
"eval_pearson": 0.8187561753672836,
|
45 |
+
"eval_runtime": 0.9245,
|
46 |
+
"eval_samples_per_second": 1622.579,
|
47 |
+
"eval_spearmanr": 0.8221472278326901,
|
48 |
+
"eval_steps_per_second": 101.682,
|
49 |
+
"step": 144
|
50 |
+
}
|
51 |
+
],
|
52 |
+
"logging_steps": 500,
|
53 |
+
"max_steps": 144,
|
54 |
+
"num_input_tokens_seen": 0,
|
55 |
+
"num_train_epochs": 4,
|
56 |
+
"save_steps": 500,
|
57 |
+
"total_flos": 0,
|
58 |
+
"train_batch_size": 16,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": {
|
61 |
+
"learning_rate": 2.2613535003508284e-05,
|
62 |
+
"num_train_epochs": 4,
|
63 |
+
"per_device_train_batch_size": 16,
|
64 |
+
"seed": 19
|
65 |
+
}
|
66 |
+
}
|
run-7/checkpoint-144/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8d651dfeb39fbfdee53e1bd84f374650de80a6c4a3ae4617d7d4651e3cf08bd
|
3 |
+
size 4920
|
run-7/checkpoint-144/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-7/checkpoint-72/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-7/checkpoint-72/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b947631eafce86fd9c8c48abadc852f0a5efdcd12fbc699761f4df1f95fb6838
|
3 |
+
size 267829484
|
run-7/checkpoint-72/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79205b93f4f71592becd1c291fc95787f55fa28579e21c152290732ee006561a
|
3 |
+
size 535721146
|
run-7/checkpoint-72/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dbfa4efd26f3ca372b3001f81d8806631763125304f0bd6056c458b7487a996
|
3 |
+
size 14244
|
run-7/checkpoint-72/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de53b250c238602f2b802d3d1f8da3d5bbbd8382f453b5f83e232b529194087b
|
3 |
+
size 1064
|
run-7/checkpoint-72/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-7/checkpoint-72/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-7/checkpoint-72/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-7/checkpoint-72/trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7920428854372943,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-7/checkpoint-72",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 72,
|
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": 2.1181581020355225,
|
14 |
+
"eval_pearson": 0.457192832227161,
|
15 |
+
"eval_runtime": 0.8791,
|
16 |
+
"eval_samples_per_second": 1706.218,
|
17 |
+
"eval_spearmanr": 0.44927428651795276,
|
18 |
+
"eval_steps_per_second": 106.923,
|
19 |
+
"step": 36
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 1.0036637783050537,
|
24 |
+
"eval_pearson": 0.7920428854372943,
|
25 |
+
"eval_runtime": 0.9239,
|
26 |
+
"eval_samples_per_second": 1623.531,
|
27 |
+
"eval_spearmanr": 0.7786283028593889,
|
28 |
+
"eval_steps_per_second": 101.741,
|
29 |
+
"step": 72
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"logging_steps": 500,
|
33 |
+
"max_steps": 144,
|
34 |
+
"num_input_tokens_seen": 0,
|
35 |
+
"num_train_epochs": 4,
|
36 |
+
"save_steps": 500,
|
37 |
+
"total_flos": 0,
|
38 |
+
"train_batch_size": 16,
|
39 |
+
"trial_name": null,
|
40 |
+
"trial_params": {
|
41 |
+
"learning_rate": 2.2613535003508284e-05,
|
42 |
+
"num_train_epochs": 4,
|
43 |
+
"per_device_train_batch_size": 16,
|
44 |
+
"seed": 19
|
45 |
+
}
|
46 |
+
}
|
run-7/checkpoint-72/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8d651dfeb39fbfdee53e1bd84f374650de80a6c4a3ae4617d7d4651e3cf08bd
|
3 |
+
size 4920
|
run-7/checkpoint-72/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-8/checkpoint-9/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-8/checkpoint-9/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:296a06adfbeff62ca91477d5e82f5670afdbfbc521fd3ce94daa5fb3bdff38d6
|
3 |
+
size 267829484
|
run-8/checkpoint-9/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d888523efc454684e412c017ddc47f04b0e824407fb021ab4a7c93aa1fc6a252
|
3 |
+
size 535721146
|
run-8/checkpoint-9/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:804fa2b14c6a6edc25f8164c7c010dd98430421db38920dff796264f7886b63a
|
3 |
+
size 14244
|
run-8/checkpoint-9/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1189da5544d12989bfc07c1ccbe15e220a8e4e06e020ef2871212b5eea1b678
|
3 |
+
size 1064
|
run-8/checkpoint-9/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-8/checkpoint-9/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-8/checkpoint-9/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-8/checkpoint-9/trainer_state.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.043905414119680714,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-8/checkpoint-9",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 9,
|
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": 6.956941604614258,
|
14 |
+
"eval_pearson": 0.043905414119680714,
|
15 |
+
"eval_runtime": 0.912,
|
16 |
+
"eval_samples_per_second": 1644.683,
|
17 |
+
"eval_spearmanr": 0.05781131915286331,
|
18 |
+
"eval_steps_per_second": 103.067,
|
19 |
+
"step": 9
|
20 |
+
}
|
21 |
+
],
|
22 |
+
"logging_steps": 500,
|
23 |
+
"max_steps": 36,
|
24 |
+
"num_input_tokens_seen": 0,
|
25 |
+
"num_train_epochs": 4,
|
26 |
+
"save_steps": 500,
|
27 |
+
"total_flos": 0,
|
28 |
+
"train_batch_size": 64,
|
29 |
+
"trial_name": null,
|
30 |
+
"trial_params": {
|
31 |
+
"learning_rate": 3.543705482037019e-06,
|
32 |
+
"num_train_epochs": 4,
|
33 |
+
"per_device_train_batch_size": 64,
|
34 |
+
"seed": 12
|
35 |
+
}
|
36 |
+
}
|
run-8/checkpoint-9/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:215c51bd8415e34d1209cd0434b8760d71d6b1aedfdef2b5d9b927dd41885e68
|
3 |
+
size 4920
|
run-8/checkpoint-9/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709676487.fe13c9557656.828.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c46545bfbc1d4bbfae2c3509864a249e7951c3f2ff24b24e160619689543b86
|
3 |
+
size 6079
|
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 sha256:215c51bd8415e34d1209cd0434b8760d71d6b1aedfdef2b5d9b927dd41885e68
|
3 |
size 4920
|