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-2/checkpoint-108/config.json +31 -0
- run-2/checkpoint-108/model.safetensors +3 -0
- run-2/checkpoint-108/optimizer.pt +3 -0
- run-2/checkpoint-108/rng_state.pth +3 -0
- run-2/checkpoint-108/scheduler.pt +3 -0
- run-2/checkpoint-108/special_tokens_map.json +7 -0
- run-2/checkpoint-108/tokenizer.json +0 -0
- run-2/checkpoint-108/tokenizer_config.json +55 -0
- run-2/checkpoint-108/trainer_state.json +56 -0
- run-2/checkpoint-108/training_args.bin +3 -0
- run-2/checkpoint-108/vocab.txt +0 -0
- run-2/checkpoint-144/config.json +31 -0
- run-2/checkpoint-144/model.safetensors +3 -0
- run-2/checkpoint-144/optimizer.pt +3 -0
- run-2/checkpoint-144/rng_state.pth +3 -0
- run-2/checkpoint-144/scheduler.pt +3 -0
- run-2/checkpoint-144/special_tokens_map.json +7 -0
- run-2/checkpoint-144/tokenizer.json +0 -0
- run-2/checkpoint-144/tokenizer_config.json +55 -0
- run-2/checkpoint-144/trainer_state.json +66 -0
- run-2/checkpoint-144/training_args.bin +3 -0
- run-2/checkpoint-144/vocab.txt +0 -0
- run-2/checkpoint-180/config.json +31 -0
- run-2/checkpoint-180/model.safetensors +3 -0
- run-2/checkpoint-180/optimizer.pt +3 -0
- run-2/checkpoint-180/rng_state.pth +3 -0
- run-2/checkpoint-180/scheduler.pt +3 -0
- run-2/checkpoint-180/special_tokens_map.json +7 -0
- run-2/checkpoint-180/tokenizer.json +0 -0
- run-2/checkpoint-180/tokenizer_config.json +55 -0
- run-2/checkpoint-180/trainer_state.json +76 -0
- run-2/checkpoint-180/training_args.bin +3 -0
- run-2/checkpoint-180/vocab.txt +0 -0
- run-2/checkpoint-72/config.json +31 -0
- run-2/checkpoint-72/model.safetensors +3 -0
- run-2/checkpoint-72/optimizer.pt +3 -0
- run-2/checkpoint-72/rng_state.pth +3 -0
- run-2/checkpoint-72/scheduler.pt +3 -0
- run-2/checkpoint-72/special_tokens_map.json +7 -0
- run-2/checkpoint-72/tokenizer.json +0 -0
- run-2/checkpoint-72/tokenizer_config.json +55 -0
- run-2/checkpoint-72/trainer_state.json +46 -0
- run-2/checkpoint-72/training_args.bin +3 -0
- run-2/checkpoint-72/vocab.txt +0 -0
- run-3/checkpoint-9/config.json +31 -0
- run-3/checkpoint-9/model.safetensors +3 -0
- run-3/checkpoint-9/optimizer.pt +3 -0
- run-3/checkpoint-9/rng_state.pth +3 -0
- run-3/checkpoint-9/scheduler.pt +3 -0
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 sha256:14f5762c371f130636e8407289379fd8a59813f886ded6dda1395d6d31a7f12c
|
3 |
size 267829484
|
run-2/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-2/checkpoint-108/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecdf1600d2c703207fc2445099fac21fd4fa874049cf275de35c72a6b81a8332
|
3 |
+
size 267829484
|
run-2/checkpoint-108/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ba1aa152298b5a89ccb2e20dcb2d6f6f3c32b4300a9fa9a542aa3c606c43748
|
3 |
+
size 535721146
|
run-2/checkpoint-108/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66be31c432556d1e4cd63f47c4fe9e83556b6dc838f90ac4025e897e6ae62376
|
3 |
+
size 14308
|
run-2/checkpoint-108/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e816737c323e3a2d45e5481e584f40808fa11f3d51c831a99b0dbbf80623d29
|
3 |
+
size 1064
|
run-2/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-2/checkpoint-108/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/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-2/checkpoint-108/trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8156384301074189,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/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": 2.4969136714935303,
|
14 |
+
"eval_pearson": 0.32223422122729983,
|
15 |
+
"eval_runtime": 0.9052,
|
16 |
+
"eval_samples_per_second": 1657.071,
|
17 |
+
"eval_spearmanr": 0.32647520010278785,
|
18 |
+
"eval_steps_per_second": 103.843,
|
19 |
+
"step": 36
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 1.1902464628219604,
|
24 |
+
"eval_pearson": 0.774068032504475,
|
25 |
+
"eval_runtime": 0.9073,
|
26 |
+
"eval_samples_per_second": 1653.256,
|
27 |
+
"eval_spearmanr": 0.7685396079860547,
|
28 |
+
"eval_steps_per_second": 103.604,
|
29 |
+
"step": 72
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 0.845661461353302,
|
34 |
+
"eval_pearson": 0.8156384301074189,
|
35 |
+
"eval_runtime": 0.9602,
|
36 |
+
"eval_samples_per_second": 1562.214,
|
37 |
+
"eval_spearmanr": 0.8142363416044488,
|
38 |
+
"eval_steps_per_second": 97.899,
|
39 |
+
"step": 108
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 500,
|
43 |
+
"max_steps": 180,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 5,
|
46 |
+
"save_steps": 500,
|
47 |
+
"total_flos": 0,
|
48 |
+
"train_batch_size": 16,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": {
|
51 |
+
"learning_rate": 2.5099285971844188e-05,
|
52 |
+
"num_train_epochs": 5,
|
53 |
+
"per_device_train_batch_size": 16,
|
54 |
+
"seed": 8
|
55 |
+
}
|
56 |
+
}
|
run-2/checkpoint-108/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12643df0525ba3f2bf5dee245df6a74c3697e1dda56998a9dd617f86119470b4
|
3 |
+
size 4920
|
run-2/checkpoint-108/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/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-2/checkpoint-144/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21f6582acf44517f58c26e691eb63d014825714aededbd69adac4d339c081105
|
3 |
+
size 267829484
|
run-2/checkpoint-144/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edbf6367e389ba399c49e51c1ee81b1addeb8c1c51c7cda327cee13a75fdfe1b
|
3 |
+
size 535721146
|
run-2/checkpoint-144/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83c69057d9a8716b83a57fd1bf30575ccb392f8cc39a8f0e55a46c81c9b5b431
|
3 |
+
size 14308
|
run-2/checkpoint-144/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaa559c16a11b6cfd5298e6bf6f570bf1e2be2e1785629c53d3a81a22fefc34d
|
3 |
+
size 1064
|
run-2/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-2/checkpoint-144/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/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-2/checkpoint-144/trainer_state.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.820309116112808,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/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": 2.4969136714935303,
|
14 |
+
"eval_pearson": 0.32223422122729983,
|
15 |
+
"eval_runtime": 0.9052,
|
16 |
+
"eval_samples_per_second": 1657.071,
|
17 |
+
"eval_spearmanr": 0.32647520010278785,
|
18 |
+
"eval_steps_per_second": 103.843,
|
19 |
+
"step": 36
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 1.1902464628219604,
|
24 |
+
"eval_pearson": 0.774068032504475,
|
25 |
+
"eval_runtime": 0.9073,
|
26 |
+
"eval_samples_per_second": 1653.256,
|
27 |
+
"eval_spearmanr": 0.7685396079860547,
|
28 |
+
"eval_steps_per_second": 103.604,
|
29 |
+
"step": 72
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 0.845661461353302,
|
34 |
+
"eval_pearson": 0.8156384301074189,
|
35 |
+
"eval_runtime": 0.9602,
|
36 |
+
"eval_samples_per_second": 1562.214,
|
37 |
+
"eval_spearmanr": 0.8142363416044488,
|
38 |
+
"eval_steps_per_second": 97.899,
|
39 |
+
"step": 108
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 4.0,
|
43 |
+
"eval_loss": 0.7359773516654968,
|
44 |
+
"eval_pearson": 0.820309116112808,
|
45 |
+
"eval_runtime": 0.9488,
|
46 |
+
"eval_samples_per_second": 1580.967,
|
47 |
+
"eval_spearmanr": 0.8207010328870485,
|
48 |
+
"eval_steps_per_second": 99.074,
|
49 |
+
"step": 144
|
50 |
+
}
|
51 |
+
],
|
52 |
+
"logging_steps": 500,
|
53 |
+
"max_steps": 180,
|
54 |
+
"num_input_tokens_seen": 0,
|
55 |
+
"num_train_epochs": 5,
|
56 |
+
"save_steps": 500,
|
57 |
+
"total_flos": 0,
|
58 |
+
"train_batch_size": 16,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": {
|
61 |
+
"learning_rate": 2.5099285971844188e-05,
|
62 |
+
"num_train_epochs": 5,
|
63 |
+
"per_device_train_batch_size": 16,
|
64 |
+
"seed": 8
|
65 |
+
}
|
66 |
+
}
|
run-2/checkpoint-144/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12643df0525ba3f2bf5dee245df6a74c3697e1dda56998a9dd617f86119470b4
|
3 |
+
size 4920
|
run-2/checkpoint-144/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-180/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-2/checkpoint-180/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5b7f2025a8d01e16baaf0c56e91991bd3fd2226c1e323a2c5372b694df927ae
|
3 |
+
size 267829484
|
run-2/checkpoint-180/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02621271fc9fcebe1cf4b01b6f890c052ca90fd951b20507f9c3a120ca2bd142
|
3 |
+
size 535721146
|
run-2/checkpoint-180/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b985c4d07829b462d67d43e81a1329a8f2890d9c00496cf43889b6d5a40cd8d5
|
3 |
+
size 14308
|
run-2/checkpoint-180/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40e8f8c803d1f4cbb6bbf08444fe39507f528857226dd87c6b8ed525e8765cf5
|
3 |
+
size 1064
|
run-2/checkpoint-180/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-2/checkpoint-180/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-180/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-2/checkpoint-180/trainer_state.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8215994541006149,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-180",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 180,
|
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": 2.4969136714935303,
|
14 |
+
"eval_pearson": 0.32223422122729983,
|
15 |
+
"eval_runtime": 0.9052,
|
16 |
+
"eval_samples_per_second": 1657.071,
|
17 |
+
"eval_spearmanr": 0.32647520010278785,
|
18 |
+
"eval_steps_per_second": 103.843,
|
19 |
+
"step": 36
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 1.1902464628219604,
|
24 |
+
"eval_pearson": 0.774068032504475,
|
25 |
+
"eval_runtime": 0.9073,
|
26 |
+
"eval_samples_per_second": 1653.256,
|
27 |
+
"eval_spearmanr": 0.7685396079860547,
|
28 |
+
"eval_steps_per_second": 103.604,
|
29 |
+
"step": 72
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 0.845661461353302,
|
34 |
+
"eval_pearson": 0.8156384301074189,
|
35 |
+
"eval_runtime": 0.9602,
|
36 |
+
"eval_samples_per_second": 1562.214,
|
37 |
+
"eval_spearmanr": 0.8142363416044488,
|
38 |
+
"eval_steps_per_second": 97.899,
|
39 |
+
"step": 108
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 4.0,
|
43 |
+
"eval_loss": 0.7359773516654968,
|
44 |
+
"eval_pearson": 0.820309116112808,
|
45 |
+
"eval_runtime": 0.9488,
|
46 |
+
"eval_samples_per_second": 1580.967,
|
47 |
+
"eval_spearmanr": 0.8207010328870485,
|
48 |
+
"eval_steps_per_second": 99.074,
|
49 |
+
"step": 144
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 5.0,
|
53 |
+
"eval_loss": 0.7456313371658325,
|
54 |
+
"eval_pearson": 0.8215994541006149,
|
55 |
+
"eval_runtime": 0.9399,
|
56 |
+
"eval_samples_per_second": 1595.857,
|
57 |
+
"eval_spearmanr": 0.8210025491088271,
|
58 |
+
"eval_steps_per_second": 100.007,
|
59 |
+
"step": 180
|
60 |
+
}
|
61 |
+
],
|
62 |
+
"logging_steps": 500,
|
63 |
+
"max_steps": 180,
|
64 |
+
"num_input_tokens_seen": 0,
|
65 |
+
"num_train_epochs": 5,
|
66 |
+
"save_steps": 500,
|
67 |
+
"total_flos": 0,
|
68 |
+
"train_batch_size": 16,
|
69 |
+
"trial_name": null,
|
70 |
+
"trial_params": {
|
71 |
+
"learning_rate": 2.5099285971844188e-05,
|
72 |
+
"num_train_epochs": 5,
|
73 |
+
"per_device_train_batch_size": 16,
|
74 |
+
"seed": 8
|
75 |
+
}
|
76 |
+
}
|
run-2/checkpoint-180/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12643df0525ba3f2bf5dee245df6a74c3697e1dda56998a9dd617f86119470b4
|
3 |
+
size 4920
|
run-2/checkpoint-180/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/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-2/checkpoint-72/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:249941c828507120d54adf6c5c3e3fcb54092c15aabd84dbcf3cb5310dc37911
|
3 |
+
size 267829484
|
run-2/checkpoint-72/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77633fbec22f842c94d0497b7fc329bd24ed1768be551c33e31789f8f18c0dc3
|
3 |
+
size 535721146
|
run-2/checkpoint-72/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c47b999f373d02779993f31b8f70bc6d254ebaa78c7cb6aceff9aa39b2c0fd53
|
3 |
+
size 14308
|
run-2/checkpoint-72/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:deab0b4d6a1efc5852cfd2b718d2f3d57a531cfe61c04096b0c43021400997ea
|
3 |
+
size 1064
|
run-2/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-2/checkpoint-72/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/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-2/checkpoint-72/trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.774068032504475,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/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": 2.4969136714935303,
|
14 |
+
"eval_pearson": 0.32223422122729983,
|
15 |
+
"eval_runtime": 0.9052,
|
16 |
+
"eval_samples_per_second": 1657.071,
|
17 |
+
"eval_spearmanr": 0.32647520010278785,
|
18 |
+
"eval_steps_per_second": 103.843,
|
19 |
+
"step": 36
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 1.1902464628219604,
|
24 |
+
"eval_pearson": 0.774068032504475,
|
25 |
+
"eval_runtime": 0.9073,
|
26 |
+
"eval_samples_per_second": 1653.256,
|
27 |
+
"eval_spearmanr": 0.7685396079860547,
|
28 |
+
"eval_steps_per_second": 103.604,
|
29 |
+
"step": 72
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"logging_steps": 500,
|
33 |
+
"max_steps": 180,
|
34 |
+
"num_input_tokens_seen": 0,
|
35 |
+
"num_train_epochs": 5,
|
36 |
+
"save_steps": 500,
|
37 |
+
"total_flos": 0,
|
38 |
+
"train_batch_size": 16,
|
39 |
+
"trial_name": null,
|
40 |
+
"trial_params": {
|
41 |
+
"learning_rate": 2.5099285971844188e-05,
|
42 |
+
"num_train_epochs": 5,
|
43 |
+
"per_device_train_batch_size": 16,
|
44 |
+
"seed": 8
|
45 |
+
}
|
46 |
+
}
|
run-2/checkpoint-72/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12643df0525ba3f2bf5dee245df6a74c3697e1dda56998a9dd617f86119470b4
|
3 |
+
size 4920
|
run-2/checkpoint-72/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/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-3/checkpoint-9/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14f5762c371f130636e8407289379fd8a59813f886ded6dda1395d6d31a7f12c
|
3 |
+
size 267829484
|
run-3/checkpoint-9/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9dcd68c867bc7e66d09d00cd6972fb094c4307e4caf066972f81431f276b6868
|
3 |
+
size 535721146
|
run-3/checkpoint-9/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48b127592b1841e69ad559ad38563940b6d1bfd53a4fd2f85e1c970834cc7ebe
|
3 |
+
size 14180
|
run-3/checkpoint-9/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44fdc4e9dd06a3de129eb66445c8274e22814d846d188dbc2e8fbe7cbbc70b19
|
3 |
+
size 1064
|