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-3/checkpoint-18/config.json +31 -0
- run-3/checkpoint-18/model.safetensors +3 -0
- run-3/checkpoint-18/optimizer.pt +3 -0
- run-3/checkpoint-18/rng_state.pth +3 -0
- run-3/checkpoint-18/scheduler.pt +3 -0
- run-3/checkpoint-18/special_tokens_map.json +7 -0
- run-3/checkpoint-18/tokenizer.json +0 -0
- run-3/checkpoint-18/tokenizer_config.json +55 -0
- run-3/checkpoint-18/trainer_state.json +46 -0
- run-3/checkpoint-18/training_args.bin +3 -0
- run-3/checkpoint-18/vocab.txt +0 -0
- run-3/checkpoint-27/config.json +31 -0
- run-3/checkpoint-27/model.safetensors +3 -0
- run-3/checkpoint-27/optimizer.pt +3 -0
- run-3/checkpoint-27/rng_state.pth +3 -0
- run-3/checkpoint-27/scheduler.pt +3 -0
- run-3/checkpoint-27/special_tokens_map.json +7 -0
- run-3/checkpoint-27/tokenizer.json +0 -0
- run-3/checkpoint-27/tokenizer_config.json +55 -0
- run-3/checkpoint-27/trainer_state.json +56 -0
- run-3/checkpoint-27/training_args.bin +3 -0
- run-3/checkpoint-27/vocab.txt +0 -0
- run-3/checkpoint-36/config.json +31 -0
- run-3/checkpoint-36/model.safetensors +3 -0
- run-3/checkpoint-36/optimizer.pt +3 -0
- run-3/checkpoint-36/rng_state.pth +3 -0
- run-3/checkpoint-36/scheduler.pt +3 -0
- run-3/checkpoint-36/special_tokens_map.json +7 -0
- run-3/checkpoint-36/tokenizer.json +0 -0
- run-3/checkpoint-36/tokenizer_config.json +55 -0
- run-3/checkpoint-36/trainer_state.json +66 -0
- run-3/checkpoint-36/training_args.bin +3 -0
- run-3/checkpoint-36/vocab.txt +0 -0
- run-3/checkpoint-45/config.json +31 -0
- run-3/checkpoint-45/model.safetensors +3 -0
- run-3/checkpoint-45/optimizer.pt +3 -0
- run-3/checkpoint-45/rng_state.pth +3 -0
- run-3/checkpoint-45/scheduler.pt +3 -0
- run-3/checkpoint-45/special_tokens_map.json +7 -0
- run-3/checkpoint-45/tokenizer.json +0 -0
- run-3/checkpoint-45/tokenizer_config.json +55 -0
- run-3/checkpoint-45/trainer_state.json +76 -0
- run-3/checkpoint-45/training_args.bin +3 -0
- run-3/checkpoint-45/vocab.txt +0 -0
- run-4/checkpoint-36/config.json +31 -0
- run-4/checkpoint-36/model.safetensors +3 -0
- run-4/checkpoint-36/optimizer.pt +3 -0
- run-4/checkpoint-36/rng_state.pth +3 -0
- run-4/checkpoint-36/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 sha256:7415615791e29904ce088212da37b0c3848feffe108ed1ca7a498483bbfd324d
|
3 |
size 267829484
|
run-3/checkpoint-18/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "distilbert",
|
20 |
+
"n_heads": 12,
|
21 |
+
"n_layers": 6,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"problem_type": "regression",
|
24 |
+
"qa_dropout": 0.1,
|
25 |
+
"seq_classif_dropout": 0.2,
|
26 |
+
"sinusoidal_pos_embds": false,
|
27 |
+
"tie_weights_": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.38.2",
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
run-3/checkpoint-18/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f670a7bc2e85b36d63192f0d128ca6f674d4cb95702f386cdd32b99e598fa2f9
|
3 |
+
size 267829484
|
run-3/checkpoint-18/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5163a1827246a3df71f6f6739c8028fe0195075ca2294f8781ae566c7f5eef5c
|
3 |
+
size 535721146
|
run-3/checkpoint-18/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccd3b20d13cc947d3fe8837480a28641637ef12d62750314c6901be85133cb70
|
3 |
+
size 14180
|
run-3/checkpoint-18/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e51ba4afa0d8569a56a97e7f179262890d3b642b3394523af8148fdb6fcb3d28
|
3 |
+
size 1064
|
run-3/checkpoint-18/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-3/checkpoint-18/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-18/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-3/checkpoint-18/trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0470495796010619,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-18",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 18,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 7.199407577514648,
|
14 |
+
"eval_pearson": 0.024278120881494558,
|
15 |
+
"eval_runtime": 0.9268,
|
16 |
+
"eval_samples_per_second": 1618.438,
|
17 |
+
"eval_spearmanr": 0.025433044219399577,
|
18 |
+
"eval_steps_per_second": 101.422,
|
19 |
+
"step": 9
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 6.31046724319458,
|
24 |
+
"eval_pearson": 0.0470495796010619,
|
25 |
+
"eval_runtime": 0.9557,
|
26 |
+
"eval_samples_per_second": 1569.521,
|
27 |
+
"eval_spearmanr": 0.048936574609921006,
|
28 |
+
"eval_steps_per_second": 98.357,
|
29 |
+
"step": 18
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"logging_steps": 500,
|
33 |
+
"max_steps": 45,
|
34 |
+
"num_input_tokens_seen": 0,
|
35 |
+
"num_train_epochs": 5,
|
36 |
+
"save_steps": 500,
|
37 |
+
"total_flos": 0,
|
38 |
+
"train_batch_size": 64,
|
39 |
+
"trial_name": null,
|
40 |
+
"trial_params": {
|
41 |
+
"learning_rate": 5.243560941114439e-06,
|
42 |
+
"num_train_epochs": 5,
|
43 |
+
"per_device_train_batch_size": 64,
|
44 |
+
"seed": 10
|
45 |
+
}
|
46 |
+
}
|
run-3/checkpoint-18/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43dea477fd3be8f6b457027410de4c6f7cf07a2710d25756956ebe9bfbdf4e31
|
3 |
+
size 4920
|
run-3/checkpoint-18/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-27/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "distilbert",
|
20 |
+
"n_heads": 12,
|
21 |
+
"n_layers": 6,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"problem_type": "regression",
|
24 |
+
"qa_dropout": 0.1,
|
25 |
+
"seq_classif_dropout": 0.2,
|
26 |
+
"sinusoidal_pos_embds": false,
|
27 |
+
"tie_weights_": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.38.2",
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
run-3/checkpoint-27/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e698e612426ff730d573fd75d791a225076371ff8a36ad1591451c3d75ed2fe
|
3 |
+
size 267829484
|
run-3/checkpoint-27/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:139bc6f51504facdd9adc3719caa9e62ef93409add07d855913aa534889cb737
|
3 |
+
size 535721146
|
run-3/checkpoint-27/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e36808ed814219680d29bcb5adc567b3fc23a005176ca2885d7e2c70b3412de8
|
3 |
+
size 14180
|
run-3/checkpoint-27/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d58cda4dc8a86e6a77e408072203e5a513a344d6bb368dadbd0740d08209488c
|
3 |
+
size 1064
|
run-3/checkpoint-27/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-3/checkpoint-27/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-27/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-3/checkpoint-27/trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.05278675976955915,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-27",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 27,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 7.199407577514648,
|
14 |
+
"eval_pearson": 0.024278120881494558,
|
15 |
+
"eval_runtime": 0.9268,
|
16 |
+
"eval_samples_per_second": 1618.438,
|
17 |
+
"eval_spearmanr": 0.025433044219399577,
|
18 |
+
"eval_steps_per_second": 101.422,
|
19 |
+
"step": 9
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 6.31046724319458,
|
24 |
+
"eval_pearson": 0.0470495796010619,
|
25 |
+
"eval_runtime": 0.9557,
|
26 |
+
"eval_samples_per_second": 1569.521,
|
27 |
+
"eval_spearmanr": 0.048936574609921006,
|
28 |
+
"eval_steps_per_second": 98.357,
|
29 |
+
"step": 18
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 5.604863166809082,
|
34 |
+
"eval_pearson": 0.05278675976955915,
|
35 |
+
"eval_runtime": 0.9249,
|
36 |
+
"eval_samples_per_second": 1621.719,
|
37 |
+
"eval_spearmanr": 0.05579666652056003,
|
38 |
+
"eval_steps_per_second": 101.628,
|
39 |
+
"step": 27
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 500,
|
43 |
+
"max_steps": 45,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 5,
|
46 |
+
"save_steps": 500,
|
47 |
+
"total_flos": 0,
|
48 |
+
"train_batch_size": 64,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": {
|
51 |
+
"learning_rate": 5.243560941114439e-06,
|
52 |
+
"num_train_epochs": 5,
|
53 |
+
"per_device_train_batch_size": 64,
|
54 |
+
"seed": 10
|
55 |
+
}
|
56 |
+
}
|
run-3/checkpoint-27/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43dea477fd3be8f6b457027410de4c6f7cf07a2710d25756956ebe9bfbdf4e31
|
3 |
+
size 4920
|
run-3/checkpoint-27/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-36/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "distilbert",
|
20 |
+
"n_heads": 12,
|
21 |
+
"n_layers": 6,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"problem_type": "regression",
|
24 |
+
"qa_dropout": 0.1,
|
25 |
+
"seq_classif_dropout": 0.2,
|
26 |
+
"sinusoidal_pos_embds": false,
|
27 |
+
"tie_weights_": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.38.2",
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
run-3/checkpoint-36/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6c629568e16dc74409d4dfa02a57321ba6ae6562c21d2fc48ffa505ded3a4e6
|
3 |
+
size 267829484
|
run-3/checkpoint-36/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60f8e6feef4eb32f7ba3f7c0faf9f4c6ae8f291f6e1418fea38e79ce1dc3601
|
3 |
+
size 535721146
|
run-3/checkpoint-36/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d83c4a58d2ee55cb30b32045e660936fc993b17a15c3e3f39a67e2c75fae7ec7
|
3 |
+
size 14180
|
run-3/checkpoint-36/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:660ee25a0ddd4682dcd06e6ffe649e6382c31e6ac22a1275061d2ccb894eb7da
|
3 |
+
size 1064
|
run-3/checkpoint-36/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-3/checkpoint-36/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-36/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-3/checkpoint-36/trainer_state.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.06186573722446415,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-36",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 36,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 7.199407577514648,
|
14 |
+
"eval_pearson": 0.024278120881494558,
|
15 |
+
"eval_runtime": 0.9268,
|
16 |
+
"eval_samples_per_second": 1618.438,
|
17 |
+
"eval_spearmanr": 0.025433044219399577,
|
18 |
+
"eval_steps_per_second": 101.422,
|
19 |
+
"step": 9
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 6.31046724319458,
|
24 |
+
"eval_pearson": 0.0470495796010619,
|
25 |
+
"eval_runtime": 0.9557,
|
26 |
+
"eval_samples_per_second": 1569.521,
|
27 |
+
"eval_spearmanr": 0.048936574609921006,
|
28 |
+
"eval_steps_per_second": 98.357,
|
29 |
+
"step": 18
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 5.604863166809082,
|
34 |
+
"eval_pearson": 0.05278675976955915,
|
35 |
+
"eval_runtime": 0.9249,
|
36 |
+
"eval_samples_per_second": 1621.719,
|
37 |
+
"eval_spearmanr": 0.05579666652056003,
|
38 |
+
"eval_steps_per_second": 101.628,
|
39 |
+
"step": 27
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 4.0,
|
43 |
+
"eval_loss": 5.163288593292236,
|
44 |
+
"eval_pearson": 0.06186573722446415,
|
45 |
+
"eval_runtime": 0.9496,
|
46 |
+
"eval_samples_per_second": 1579.549,
|
47 |
+
"eval_spearmanr": 0.06678878974516303,
|
48 |
+
"eval_steps_per_second": 98.985,
|
49 |
+
"step": 36
|
50 |
+
}
|
51 |
+
],
|
52 |
+
"logging_steps": 500,
|
53 |
+
"max_steps": 45,
|
54 |
+
"num_input_tokens_seen": 0,
|
55 |
+
"num_train_epochs": 5,
|
56 |
+
"save_steps": 500,
|
57 |
+
"total_flos": 0,
|
58 |
+
"train_batch_size": 64,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": {
|
61 |
+
"learning_rate": 5.243560941114439e-06,
|
62 |
+
"num_train_epochs": 5,
|
63 |
+
"per_device_train_batch_size": 64,
|
64 |
+
"seed": 10
|
65 |
+
}
|
66 |
+
}
|
run-3/checkpoint-36/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43dea477fd3be8f6b457027410de4c6f7cf07a2710d25756956ebe9bfbdf4e31
|
3 |
+
size 4920
|
run-3/checkpoint-36/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-45/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "distilbert",
|
20 |
+
"n_heads": 12,
|
21 |
+
"n_layers": 6,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"problem_type": "regression",
|
24 |
+
"qa_dropout": 0.1,
|
25 |
+
"seq_classif_dropout": 0.2,
|
26 |
+
"sinusoidal_pos_embds": false,
|
27 |
+
"tie_weights_": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.38.2",
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
run-3/checkpoint-45/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86d0c83a7bd7c921e1bcc37c1fda02d35c4caaf3fe5fb2bdcfdd912e0193d273
|
3 |
+
size 267829484
|
run-3/checkpoint-45/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:152420f0357b982a437d54e165de9582b42e491cf214643b8a1a7f1e077876b4
|
3 |
+
size 535721146
|
run-3/checkpoint-45/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbcadd327627ae50e7f089d46c5c091d80109e82be93e683b481080fb575a398
|
3 |
+
size 14180
|
run-3/checkpoint-45/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fae0be6c677ba4f8be1649bfda912af77981545adc6b777962a94b21590d0eec
|
3 |
+
size 1064
|
run-3/checkpoint-45/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-3/checkpoint-45/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-45/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-3/checkpoint-45/trainer_state.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.06585301202568708,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-45",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 45,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 7.199407577514648,
|
14 |
+
"eval_pearson": 0.024278120881494558,
|
15 |
+
"eval_runtime": 0.9268,
|
16 |
+
"eval_samples_per_second": 1618.438,
|
17 |
+
"eval_spearmanr": 0.025433044219399577,
|
18 |
+
"eval_steps_per_second": 101.422,
|
19 |
+
"step": 9
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 6.31046724319458,
|
24 |
+
"eval_pearson": 0.0470495796010619,
|
25 |
+
"eval_runtime": 0.9557,
|
26 |
+
"eval_samples_per_second": 1569.521,
|
27 |
+
"eval_spearmanr": 0.048936574609921006,
|
28 |
+
"eval_steps_per_second": 98.357,
|
29 |
+
"step": 18
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 5.604863166809082,
|
34 |
+
"eval_pearson": 0.05278675976955915,
|
35 |
+
"eval_runtime": 0.9249,
|
36 |
+
"eval_samples_per_second": 1621.719,
|
37 |
+
"eval_spearmanr": 0.05579666652056003,
|
38 |
+
"eval_steps_per_second": 101.628,
|
39 |
+
"step": 27
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 4.0,
|
43 |
+
"eval_loss": 5.163288593292236,
|
44 |
+
"eval_pearson": 0.06186573722446415,
|
45 |
+
"eval_runtime": 0.9496,
|
46 |
+
"eval_samples_per_second": 1579.549,
|
47 |
+
"eval_spearmanr": 0.06678878974516303,
|
48 |
+
"eval_steps_per_second": 98.985,
|
49 |
+
"step": 36
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 5.0,
|
53 |
+
"eval_loss": 5.004383087158203,
|
54 |
+
"eval_pearson": 0.06585301202568708,
|
55 |
+
"eval_runtime": 0.9372,
|
56 |
+
"eval_samples_per_second": 1600.561,
|
57 |
+
"eval_spearmanr": 0.0703178793629636,
|
58 |
+
"eval_steps_per_second": 100.302,
|
59 |
+
"step": 45
|
60 |
+
}
|
61 |
+
],
|
62 |
+
"logging_steps": 500,
|
63 |
+
"max_steps": 45,
|
64 |
+
"num_input_tokens_seen": 0,
|
65 |
+
"num_train_epochs": 5,
|
66 |
+
"save_steps": 500,
|
67 |
+
"total_flos": 0,
|
68 |
+
"train_batch_size": 64,
|
69 |
+
"trial_name": null,
|
70 |
+
"trial_params": {
|
71 |
+
"learning_rate": 5.243560941114439e-06,
|
72 |
+
"num_train_epochs": 5,
|
73 |
+
"per_device_train_batch_size": 64,
|
74 |
+
"seed": 10
|
75 |
+
}
|
76 |
+
}
|
run-3/checkpoint-45/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43dea477fd3be8f6b457027410de4c6f7cf07a2710d25756956ebe9bfbdf4e31
|
3 |
+
size 4920
|
run-3/checkpoint-45/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-36/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "distilbert",
|
20 |
+
"n_heads": 12,
|
21 |
+
"n_layers": 6,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"problem_type": "regression",
|
24 |
+
"qa_dropout": 0.1,
|
25 |
+
"seq_classif_dropout": 0.2,
|
26 |
+
"sinusoidal_pos_embds": false,
|
27 |
+
"tie_weights_": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.38.2",
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
run-4/checkpoint-36/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7415615791e29904ce088212da37b0c3848feffe108ed1ca7a498483bbfd324d
|
3 |
+
size 267829484
|
run-4/checkpoint-36/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e6c030837ee5d91a25afb3b90af6b4da7c853e6408b3730749bf425f6118a70
|
3 |
+
size 535721146
|
run-4/checkpoint-36/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c909ba14abaaa8e7d3fd7f122fa501d6634b5a3b0ecd373bceaece83b57fe976
|
3 |
+
size 14244
|
run-4/checkpoint-36/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66eed04a6c940ae505a3f5b371ec603313b051552fce9bbd465bcf3623cfb59e
|
3 |
+
size 1064
|