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-8/checkpoint-1070/config.json +25 -0
- run-8/checkpoint-1070/model.safetensors +3 -0
- run-8/checkpoint-1070/optimizer.pt +3 -0
- run-8/checkpoint-1070/rng_state.pth +3 -0
- run-8/checkpoint-1070/scheduler.pt +3 -0
- run-8/checkpoint-1070/special_tokens_map.json +7 -0
- run-8/checkpoint-1070/tokenizer.json +0 -0
- run-8/checkpoint-1070/tokenizer_config.json +55 -0
- run-8/checkpoint-1070/trainer_state.json +85 -0
- run-8/checkpoint-1070/training_args.bin +3 -0
- run-8/checkpoint-1070/vocab.txt +0 -0
- run-8/checkpoint-428/config.json +25 -0
- run-8/checkpoint-428/model.safetensors +3 -0
- run-8/checkpoint-428/optimizer.pt +3 -0
- run-8/checkpoint-428/rng_state.pth +3 -0
- run-8/checkpoint-428/scheduler.pt +3 -0
- run-8/checkpoint-428/special_tokens_map.json +7 -0
- run-8/checkpoint-428/tokenizer.json +0 -0
- run-8/checkpoint-428/tokenizer_config.json +55 -0
- run-8/checkpoint-428/trainer_state.json +44 -0
- run-8/checkpoint-428/training_args.bin +3 -0
- run-8/checkpoint-428/vocab.txt +0 -0
- run-8/checkpoint-642/config.json +25 -0
- run-8/checkpoint-642/model.safetensors +3 -0
- run-8/checkpoint-642/optimizer.pt +3 -0
- run-8/checkpoint-642/rng_state.pth +3 -0
- run-8/checkpoint-642/scheduler.pt +3 -0
- run-8/checkpoint-642/special_tokens_map.json +7 -0
- run-8/checkpoint-642/tokenizer.json +0 -0
- run-8/checkpoint-642/tokenizer_config.json +55 -0
- run-8/checkpoint-642/trainer_state.json +60 -0
- run-8/checkpoint-642/training_args.bin +3 -0
- run-8/checkpoint-642/vocab.txt +0 -0
- run-8/checkpoint-856/config.json +25 -0
- run-8/checkpoint-856/model.safetensors +3 -0
- run-8/checkpoint-856/optimizer.pt +3 -0
- run-8/checkpoint-856/rng_state.pth +3 -0
- run-8/checkpoint-856/scheduler.pt +3 -0
- run-8/checkpoint-856/special_tokens_map.json +7 -0
- run-8/checkpoint-856/tokenizer.json +0 -0
- run-8/checkpoint-856/tokenizer_config.json +55 -0
- run-8/checkpoint-856/trainer_state.json +69 -0
- run-8/checkpoint-856/training_args.bin +3 -0
- run-8/checkpoint-856/vocab.txt +0 -0
- run-9/checkpoint-107/config.json +25 -0
- run-9/checkpoint-107/model.safetensors +3 -0
- run-9/checkpoint-107/optimizer.pt +3 -0
- run-9/checkpoint-107/rng_state.pth +3 -0
- run-9/checkpoint-107/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 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10975cd45cca99b5a53512ecb93237b5769b337819196a4c155f8c809d8ab671
|
3 |
size 267832560
|
run-8/checkpoint-1070/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.1",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-8/checkpoint-1070/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28f1d0a510f13f21456290ee48b066245999b74431c38af99b03bf4bee4595c9
|
3 |
+
size 267832560
|
run-8/checkpoint-1070/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:002b1a9f3ebc91c92de96c827efa7492af3b6f5cf22b58367a0e1a284b0bce2f
|
3 |
+
size 535727290
|
run-8/checkpoint-1070/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1df6b7b1ff6335db58bce89e3cedae9f448c487e2a4943b7e6ed61881bccbfd
|
3 |
+
size 14244
|
run-8/checkpoint-1070/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f13cbf730a570beb1cbdd11a5453150a31d229c6fd09e7c6c552ededa0c7b7b9
|
3 |
+
size 1064
|
run-8/checkpoint-1070/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-1070/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-8/checkpoint-1070/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": 1000000000000000019884624838656,
|
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-1070/trainer_state.json
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.11716571434177496,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-1070",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1070,
|
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": 0.6113265752792358,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.7181,
|
16 |
+
"eval_samples_per_second": 1452.535,
|
17 |
+
"eval_steps_per_second": 91.915,
|
18 |
+
"step": 214
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6063526272773743,
|
23 |
+
"eval_matthews_correlation": 0.0,
|
24 |
+
"eval_runtime": 0.817,
|
25 |
+
"eval_samples_per_second": 1276.639,
|
26 |
+
"eval_steps_per_second": 80.784,
|
27 |
+
"step": 428
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.336448598130841,
|
31 |
+
"grad_norm": 4.553454875946045,
|
32 |
+
"learning_rate": 1.5211627581163973e-06,
|
33 |
+
"loss": 0.6057,
|
34 |
+
"step": 500
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 3.0,
|
38 |
+
"eval_loss": 0.5852556228637695,
|
39 |
+
"eval_matthews_correlation": 0.0,
|
40 |
+
"eval_runtime": 0.8015,
|
41 |
+
"eval_samples_per_second": 1301.354,
|
42 |
+
"eval_steps_per_second": 82.348,
|
43 |
+
"step": 642
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 4.0,
|
47 |
+
"eval_loss": 0.5820844173431396,
|
48 |
+
"eval_matthews_correlation": 0.04161454566059593,
|
49 |
+
"eval_runtime": 0.8079,
|
50 |
+
"eval_samples_per_second": 1291.002,
|
51 |
+
"eval_steps_per_second": 81.693,
|
52 |
+
"step": 856
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 4.672897196261682,
|
56 |
+
"grad_norm": 5.679166793823242,
|
57 |
+
"learning_rate": 1.8680946152306634e-07,
|
58 |
+
"loss": 0.541,
|
59 |
+
"step": 1000
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 5.0,
|
63 |
+
"eval_loss": 0.5788400769233704,
|
64 |
+
"eval_matthews_correlation": 0.11716571434177496,
|
65 |
+
"eval_runtime": 1.3063,
|
66 |
+
"eval_samples_per_second": 798.409,
|
67 |
+
"eval_steps_per_second": 50.523,
|
68 |
+
"step": 1070
|
69 |
+
}
|
70 |
+
],
|
71 |
+
"logging_steps": 500,
|
72 |
+
"max_steps": 1070,
|
73 |
+
"num_input_tokens_seen": 0,
|
74 |
+
"num_train_epochs": 5,
|
75 |
+
"save_steps": 500,
|
76 |
+
"total_flos": 22137320373444.0,
|
77 |
+
"train_batch_size": 4,
|
78 |
+
"trial_name": null,
|
79 |
+
"trial_params": {
|
80 |
+
"learning_rate": 2.8555160547097285e-06,
|
81 |
+
"num_train_epochs": 5,
|
82 |
+
"per_device_train_batch_size": 4,
|
83 |
+
"seed": 12
|
84 |
+
}
|
85 |
+
}
|
run-8/checkpoint-1070/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:affaaf499b0bd474ec9330b36eb26ce187228c0390efde0fe9bd4b1b0f1775da
|
3 |
+
size 5048
|
run-8/checkpoint-1070/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-8/checkpoint-428/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.1",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-8/checkpoint-428/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e92c6d050f17c866408d65d416726987f8358d71ca47bf903664470ae155d46f
|
3 |
+
size 267832560
|
run-8/checkpoint-428/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbeab260ee19b36407602c8bddf76988396267a1e1b07f8bf59a77716081378e
|
3 |
+
size 535727290
|
run-8/checkpoint-428/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:123a5343f68ec13b68a2b560055939797bee709d54072612e9bb907a91476f28
|
3 |
+
size 14244
|
run-8/checkpoint-428/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df1db741919e3de876f26d79c24bbd05efbb1971375c0eaa701767f4af4fb3b5
|
3 |
+
size 1064
|
run-8/checkpoint-428/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-428/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-8/checkpoint-428/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": 1000000000000000019884624838656,
|
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-428/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-214",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 428,
|
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": 0.6113265752792358,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.7181,
|
16 |
+
"eval_samples_per_second": 1452.535,
|
17 |
+
"eval_steps_per_second": 91.915,
|
18 |
+
"step": 214
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6063526272773743,
|
23 |
+
"eval_matthews_correlation": 0.0,
|
24 |
+
"eval_runtime": 0.817,
|
25 |
+
"eval_samples_per_second": 1276.639,
|
26 |
+
"eval_steps_per_second": 80.784,
|
27 |
+
"step": 428
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 1070,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 5,
|
34 |
+
"save_steps": 500,
|
35 |
+
"total_flos": 0,
|
36 |
+
"train_batch_size": 4,
|
37 |
+
"trial_name": null,
|
38 |
+
"trial_params": {
|
39 |
+
"learning_rate": 2.8555160547097285e-06,
|
40 |
+
"num_train_epochs": 5,
|
41 |
+
"per_device_train_batch_size": 4,
|
42 |
+
"seed": 12
|
43 |
+
}
|
44 |
+
}
|
run-8/checkpoint-428/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:affaaf499b0bd474ec9330b36eb26ce187228c0390efde0fe9bd4b1b0f1775da
|
3 |
+
size 5048
|
run-8/checkpoint-428/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-8/checkpoint-642/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.1",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-8/checkpoint-642/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81331b9c9709241991a4994bd56003cd4554683c39301d5f632851c944faa862
|
3 |
+
size 267832560
|
run-8/checkpoint-642/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:870a67736ae7649d22cf7a18fa6f95d66c456a578a14de43fe6ac6e515ee1770
|
3 |
+
size 535727290
|
run-8/checkpoint-642/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:459a440c9d15ba5e5b2229c7ffbe3145e047b6e5e97660610634d47c20f261e5
|
3 |
+
size 14244
|
run-8/checkpoint-642/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35ccb58ff070d2f1640734745f85d5d9398c07c157892728fa1550f972d8067a
|
3 |
+
size 1064
|
run-8/checkpoint-642/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-642/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-8/checkpoint-642/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": 1000000000000000019884624838656,
|
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-642/trainer_state.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-214",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 642,
|
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": 0.6113265752792358,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.7181,
|
16 |
+
"eval_samples_per_second": 1452.535,
|
17 |
+
"eval_steps_per_second": 91.915,
|
18 |
+
"step": 214
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6063526272773743,
|
23 |
+
"eval_matthews_correlation": 0.0,
|
24 |
+
"eval_runtime": 0.817,
|
25 |
+
"eval_samples_per_second": 1276.639,
|
26 |
+
"eval_steps_per_second": 80.784,
|
27 |
+
"step": 428
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.336448598130841,
|
31 |
+
"grad_norm": 4.553454875946045,
|
32 |
+
"learning_rate": 1.5211627581163973e-06,
|
33 |
+
"loss": 0.6057,
|
34 |
+
"step": 500
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 3.0,
|
38 |
+
"eval_loss": 0.5852556228637695,
|
39 |
+
"eval_matthews_correlation": 0.0,
|
40 |
+
"eval_runtime": 0.8015,
|
41 |
+
"eval_samples_per_second": 1301.354,
|
42 |
+
"eval_steps_per_second": 82.348,
|
43 |
+
"step": 642
|
44 |
+
}
|
45 |
+
],
|
46 |
+
"logging_steps": 500,
|
47 |
+
"max_steps": 1070,
|
48 |
+
"num_input_tokens_seen": 0,
|
49 |
+
"num_train_epochs": 5,
|
50 |
+
"save_steps": 500,
|
51 |
+
"total_flos": 13764449366988.0,
|
52 |
+
"train_batch_size": 4,
|
53 |
+
"trial_name": null,
|
54 |
+
"trial_params": {
|
55 |
+
"learning_rate": 2.8555160547097285e-06,
|
56 |
+
"num_train_epochs": 5,
|
57 |
+
"per_device_train_batch_size": 4,
|
58 |
+
"seed": 12
|
59 |
+
}
|
60 |
+
}
|
run-8/checkpoint-642/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:affaaf499b0bd474ec9330b36eb26ce187228c0390efde0fe9bd4b1b0f1775da
|
3 |
+
size 5048
|
run-8/checkpoint-642/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-8/checkpoint-856/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.1",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-8/checkpoint-856/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29f49ab24e7d22d11ea5fb3ec8978279b279a248c2352b0bc078a8a5c86e2ce6
|
3 |
+
size 267832560
|
run-8/checkpoint-856/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe702d1ea48a951017b9c507d5da793328f373f1afd0fc8d157ecb28d7696706
|
3 |
+
size 535727290
|
run-8/checkpoint-856/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0959e4fc49f256382e0dc2b5eaaf6de1ebc7372d1c9b5b34f8bda98d7f54a5b9
|
3 |
+
size 14244
|
run-8/checkpoint-856/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:804b4fbdfb9d63b5e676e7dd2f217c2f522198918f56ba5eb71a98a9018ff3af
|
3 |
+
size 1064
|
run-8/checkpoint-856/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-856/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-8/checkpoint-856/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": 1000000000000000019884624838656,
|
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-856/trainer_state.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.04161454566059593,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-856",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 856,
|
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": 0.6113265752792358,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.7181,
|
16 |
+
"eval_samples_per_second": 1452.535,
|
17 |
+
"eval_steps_per_second": 91.915,
|
18 |
+
"step": 214
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6063526272773743,
|
23 |
+
"eval_matthews_correlation": 0.0,
|
24 |
+
"eval_runtime": 0.817,
|
25 |
+
"eval_samples_per_second": 1276.639,
|
26 |
+
"eval_steps_per_second": 80.784,
|
27 |
+
"step": 428
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.336448598130841,
|
31 |
+
"grad_norm": 4.553454875946045,
|
32 |
+
"learning_rate": 1.5211627581163973e-06,
|
33 |
+
"loss": 0.6057,
|
34 |
+
"step": 500
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 3.0,
|
38 |
+
"eval_loss": 0.5852556228637695,
|
39 |
+
"eval_matthews_correlation": 0.0,
|
40 |
+
"eval_runtime": 0.8015,
|
41 |
+
"eval_samples_per_second": 1301.354,
|
42 |
+
"eval_steps_per_second": 82.348,
|
43 |
+
"step": 642
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 4.0,
|
47 |
+
"eval_loss": 0.5820844173431396,
|
48 |
+
"eval_matthews_correlation": 0.04161454566059593,
|
49 |
+
"eval_runtime": 0.8079,
|
50 |
+
"eval_samples_per_second": 1291.002,
|
51 |
+
"eval_steps_per_second": 81.693,
|
52 |
+
"step": 856
|
53 |
+
}
|
54 |
+
],
|
55 |
+
"logging_steps": 500,
|
56 |
+
"max_steps": 1070,
|
57 |
+
"num_input_tokens_seen": 0,
|
58 |
+
"num_train_epochs": 5,
|
59 |
+
"save_steps": 500,
|
60 |
+
"total_flos": 13764449366988.0,
|
61 |
+
"train_batch_size": 4,
|
62 |
+
"trial_name": null,
|
63 |
+
"trial_params": {
|
64 |
+
"learning_rate": 2.8555160547097285e-06,
|
65 |
+
"num_train_epochs": 5,
|
66 |
+
"per_device_train_batch_size": 4,
|
67 |
+
"seed": 12
|
68 |
+
}
|
69 |
+
}
|
run-8/checkpoint-856/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:affaaf499b0bd474ec9330b36eb26ce187228c0390efde0fe9bd4b1b0f1775da
|
3 |
+
size 5048
|
run-8/checkpoint-856/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-9/checkpoint-107/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.1",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-9/checkpoint-107/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10975cd45cca99b5a53512ecb93237b5769b337819196a4c155f8c809d8ab671
|
3 |
+
size 267832560
|
run-9/checkpoint-107/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04f47081ad5906b050150b4523996190145fc3cae463f2e6482915be7814ff3e
|
3 |
+
size 535727290
|
run-9/checkpoint-107/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66755335e6748a75fdabe0d7df9f0951658c11d0b7f82a50b7a6da403db52f29
|
3 |
+
size 14308
|
run-9/checkpoint-107/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:595c6bfef730728da4d2e55fdd9562ecb44b9c8380544da90784a3b9261783e5
|
3 |
+
size 1064
|