Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-6/checkpoint-108/config.json +31 -0
- run-6/checkpoint-108/model.safetensors +3 -0
- run-6/checkpoint-108/optimizer.pt +3 -0
- run-6/checkpoint-108/rng_state.pth +3 -0
- run-6/checkpoint-108/scheduler.pt +3 -0
- run-6/checkpoint-108/special_tokens_map.json +7 -0
- run-6/checkpoint-108/tokenizer.json +0 -0
- run-6/checkpoint-108/tokenizer_config.json +55 -0
- run-6/checkpoint-108/trainer_state.json +56 -0
- run-6/checkpoint-108/training_args.bin +3 -0
- run-6/checkpoint-108/vocab.txt +0 -0
- run-6/checkpoint-72/config.json +31 -0
- run-6/checkpoint-72/model.safetensors +3 -0
- run-6/checkpoint-72/optimizer.pt +3 -0
- run-6/checkpoint-72/rng_state.pth +3 -0
- run-6/checkpoint-72/scheduler.pt +3 -0
- run-6/checkpoint-72/special_tokens_map.json +7 -0
- run-6/checkpoint-72/tokenizer.json +0 -0
- run-6/checkpoint-72/tokenizer_config.json +55 -0
- run-6/checkpoint-72/trainer_state.json +46 -0
- run-6/checkpoint-72/training_args.bin +3 -0
- run-6/checkpoint-72/vocab.txt +0 -0
- run-8/checkpoint-9/model.safetensors +1 -1
- run-8/checkpoint-9/optimizer.pt +1 -1
- run-8/checkpoint-9/rng_state.pth +1 -1
- run-8/checkpoint-9/scheduler.pt +1 -1
- run-8/checkpoint-9/trainer_state.json +12 -12
- run-8/checkpoint-9/training_args.bin +1 -1
- runs/Mar06_19-02-43_8a0d46b883ab/events.out.tfevents.1709752414.8a0d46b883ab.2624.9 +3 -0
- runs/Mar06_19-02-43_8a0d46b883ab/events.out.tfevents.1709752417.8a0d46b883ab.2624.10 +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:b3a65e67d8882c4ead6c4ebed668d3406b18a9242df07315f836fccdabd8afd4
|
3 |
size 267829484
|
run-6/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-6/checkpoint-108/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0de97f559838a236953cac0ad54de46010dc612230ebca9360c957e6d277cc0
|
3 |
+
size 267829484
|
run-6/checkpoint-108/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4574787ee65e63b641074b71f91626a998b3d07d039009eb1bfed21eca9e4ff9
|
3 |
+
size 535721146
|
run-6/checkpoint-108/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ac3631361464a32dfb973ca26650a3e858c3270c3048a8a77c4ebfed6ffa360
|
3 |
+
size 14244
|
run-6/checkpoint-108/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f354e3f84d4c3226e279d42e145bacb5f4d3f5c15fdba90ddae2bd78a6127d0
|
3 |
+
size 1064
|
run-6/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-6/checkpoint-108/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-6/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-6/checkpoint-108/trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8216396482083662,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-6/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": 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 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 0.9170708060264587,
|
24 |
+
"eval_pearson": 0.8095416463018199,
|
25 |
+
"eval_runtime": 0.7946,
|
26 |
+
"eval_samples_per_second": 1887.657,
|
27 |
+
"eval_spearmanr": 0.8070877388190617,
|
28 |
+
"eval_steps_per_second": 118.293,
|
29 |
+
"step": 72
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 0.7417043447494507,
|
34 |
+
"eval_pearson": 0.8216396482083662,
|
35 |
+
"eval_runtime": 0.8035,
|
36 |
+
"eval_samples_per_second": 1866.838,
|
37 |
+
"eval_spearmanr": 0.821914669684342,
|
38 |
+
"eval_steps_per_second": 116.989,
|
39 |
+
"step": 108
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 500,
|
43 |
+
"max_steps": 108,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 3,
|
46 |
+
"save_steps": 500,
|
47 |
+
"total_flos": 0,
|
48 |
+
"train_batch_size": 16,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": {
|
51 |
+
"learning_rate": 5.712636964604973e-05,
|
52 |
+
"num_train_epochs": 3,
|
53 |
+
"per_device_train_batch_size": 16,
|
54 |
+
"seed": 36
|
55 |
+
}
|
56 |
+
}
|
run-6/checkpoint-108/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-108/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-6/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-6/checkpoint-72/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fa395b74cbfabd9f76276882a438e98be6dc5f4ee557d510e8aeab377f22ff4
|
3 |
+
size 267829484
|
run-6/checkpoint-72/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63df5a9e564e7f321672d4ab901d32039e6ebb4ee7670c4464c1d27ff42c1c39
|
3 |
+
size 535721146
|
run-6/checkpoint-72/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14a2e9ddb43fbca9461f3f5ceb25a215921da657500e6bb75a3e868569890ac4
|
3 |
+
size 14244
|
run-6/checkpoint-72/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ba73909db342f50fe1719cba2bc98a74cc86f647ea7eeaf161b98693f724820
|
3 |
+
size 1064
|
run-6/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-6/checkpoint-72/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-6/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-6/checkpoint-72/trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8095416463018199,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-6/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": 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 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 0.9170708060264587,
|
24 |
+
"eval_pearson": 0.8095416463018199,
|
25 |
+
"eval_runtime": 0.7946,
|
26 |
+
"eval_samples_per_second": 1887.657,
|
27 |
+
"eval_spearmanr": 0.8070877388190617,
|
28 |
+
"eval_steps_per_second": 118.293,
|
29 |
+
"step": 72
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"logging_steps": 500,
|
33 |
+
"max_steps": 108,
|
34 |
+
"num_input_tokens_seen": 0,
|
35 |
+
"num_train_epochs": 3,
|
36 |
+
"save_steps": 500,
|
37 |
+
"total_flos": 0,
|
38 |
+
"train_batch_size": 16,
|
39 |
+
"trial_name": null,
|
40 |
+
"trial_params": {
|
41 |
+
"learning_rate": 5.712636964604973e-05,
|
42 |
+
"num_train_epochs": 3,
|
43 |
+
"per_device_train_batch_size": 16,
|
44 |
+
"seed": 36
|
45 |
+
}
|
46 |
+
}
|
run-6/checkpoint-72/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-72/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-8/checkpoint-9/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:b3a65e67d8882c4ead6c4ebed668d3406b18a9242df07315f836fccdabd8afd4
|
3 |
size 267829484
|
run-8/checkpoint-9/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 sha256:6ed4a40fc62a6fed076f3e9d9ff48230548bcdc34c94bf0ddb0f1e583a6319cd
|
3 |
size 535721146
|
run-8/checkpoint-9/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 sha256:848005be7fae1c9430d2b52adb4bc0e0c1093f49aa0ff65b41b862ac61822d6c
|
3 |
size 14244
|
run-8/checkpoint-9/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 sha256:899b4ecfc14f32bb346d6b7a622be95e2b37d8fa91cbd41d527068709c272f4e
|
3 |
size 1064
|
run-8/checkpoint-9/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-8/checkpoint-9",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
@@ -10,27 +10,27 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss": 6.
|
14 |
-
"eval_pearson": 0.
|
15 |
-
"eval_runtime": 0.
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_spearmanr": 0.
|
18 |
-
"eval_steps_per_second":
|
19 |
"step": 9
|
20 |
}
|
21 |
],
|
22 |
"logging_steps": 500,
|
23 |
-
"max_steps":
|
24 |
"num_input_tokens_seen": 0,
|
25 |
-
"num_train_epochs":
|
26 |
"save_steps": 500,
|
27 |
"total_flos": 0,
|
28 |
"train_batch_size": 64,
|
29 |
"trial_name": null,
|
30 |
"trial_params": {
|
31 |
-
"learning_rate":
|
32 |
-
"num_train_epochs":
|
33 |
"per_device_train_batch_size": 64,
|
34 |
-
"seed":
|
35 |
}
|
36 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.12656826722415604,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-8/checkpoint-9",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 6.634343147277832,
|
14 |
+
"eval_pearson": 0.12656826722415604,
|
15 |
+
"eval_runtime": 0.8007,
|
16 |
+
"eval_samples_per_second": 1873.357,
|
17 |
+
"eval_spearmanr": 0.12889343747604146,
|
18 |
+
"eval_steps_per_second": 117.397,
|
19 |
"step": 9
|
20 |
}
|
21 |
],
|
22 |
"logging_steps": 500,
|
23 |
+
"max_steps": 9,
|
24 |
"num_input_tokens_seen": 0,
|
25 |
+
"num_train_epochs": 1,
|
26 |
"save_steps": 500,
|
27 |
"total_flos": 0,
|
28 |
"train_batch_size": 64,
|
29 |
"trial_name": null,
|
30 |
"trial_params": {
|
31 |
+
"learning_rate": 6.912229381195154e-06,
|
32 |
+
"num_train_epochs": 1,
|
33 |
"per_device_train_batch_size": 64,
|
34 |
+
"seed": 25
|
35 |
}
|
36 |
}
|
run-8/checkpoint-9/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 sha256:22d3560b1d2c56e0a0f05db268ba7e93f82bd568facac781459b8ddc8656e252
|
3 |
size 4920
|
runs/Mar06_19-02-43_8a0d46b883ab/events.out.tfevents.1709752414.8a0d46b883ab.2624.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a5189fa9d5c7653c75824590a275f5a22a40dc90d9985c1ae9e5189566e3f8e
|
3 |
+
size 4976
|
runs/Mar06_19-02-43_8a0d46b883ab/events.out.tfevents.1709752417.8a0d46b883ab.2624.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a19c45ac52e393cc078646cedd7af2924f908007b8f772d68ac9a9f8689faecd
|
3 |
+
size 5323
|
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 sha256:22d3560b1d2c56e0a0f05db268ba7e93f82bd568facac781459b8ddc8656e252
|
3 |
size 4920
|