sibstrider
commited on
Commit
•
07f0c63
1
Parent(s):
f9c7a4d
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-4/checkpoint-138/config.json +54 -0
- run-4/checkpoint-138/model.safetensors +3 -0
- run-4/checkpoint-138/optimizer.pt +3 -0
- run-4/checkpoint-138/rng_state.pth +3 -0
- run-4/checkpoint-138/scheduler.pt +3 -0
- run-4/checkpoint-138/special_tokens_map.json +37 -0
- run-4/checkpoint-138/tokenizer.json +0 -0
- run-4/checkpoint-138/tokenizer_config.json +64 -0
- run-4/checkpoint-138/trainer_state.json +35 -0
- run-4/checkpoint-138/training_args.bin +3 -0
- run-4/checkpoint-138/vocab.txt +0 -0
- runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705261362.DESKTOP-RFEED41.20976.10 +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 116795404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e5d251b283ab154388853ca86692fa4d4a31346f25c0f5b5900182821ca942a
|
3 |
size 116795404
|
run-4/checkpoint-138/config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cointegrated/rubert-tiny2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_size": 312,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 312,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9",
|
24 |
+
"10": "LABEL_10"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 600,
|
28 |
+
"label2id": {
|
29 |
+
"LABEL_0": 0,
|
30 |
+
"LABEL_1": 1,
|
31 |
+
"LABEL_10": 10,
|
32 |
+
"LABEL_2": 2,
|
33 |
+
"LABEL_3": 3,
|
34 |
+
"LABEL_4": 4,
|
35 |
+
"LABEL_5": 5,
|
36 |
+
"LABEL_6": 6,
|
37 |
+
"LABEL_7": 7,
|
38 |
+
"LABEL_8": 8,
|
39 |
+
"LABEL_9": 9
|
40 |
+
},
|
41 |
+
"layer_norm_eps": 1e-12,
|
42 |
+
"max_position_embeddings": 2048,
|
43 |
+
"model_type": "bert",
|
44 |
+
"num_attention_heads": 12,
|
45 |
+
"num_hidden_layers": 3,
|
46 |
+
"pad_token_id": 0,
|
47 |
+
"position_embedding_type": "absolute",
|
48 |
+
"problem_type": "single_label_classification",
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.36.2",
|
51 |
+
"type_vocab_size": 2,
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 83828
|
54 |
+
}
|
run-4/checkpoint-138/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e5d251b283ab154388853ca86692fa4d4a31346f25c0f5b5900182821ca942a
|
3 |
+
size 116795404
|
run-4/checkpoint-138/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6b4075c34d1e841d9141710ea491fb4ad98b882964028ae7fb359057b8817a9
|
3 |
+
size 233621882
|
run-4/checkpoint-138/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2803c0c5e9b6bd7dbbb7de4f19a69079e2026f821c942c2eef3d2f7cda5d752c
|
3 |
+
size 13990
|
run-4/checkpoint-138/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8bfbee32cc0927626bb0467f53300f2f3ab968a479d1a006d4694568d21eb26
|
3 |
+
size 1064
|
run-4/checkpoint-138/special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
run-4/checkpoint-138/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-138/tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_length": 512,
|
50 |
+
"model_max_length": 2048,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "[SEP]",
|
57 |
+
"stride": 0,
|
58 |
+
"strip_accents": null,
|
59 |
+
"tokenize_chinese_chars": true,
|
60 |
+
"tokenizer_class": "BertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "[UNK]"
|
64 |
+
}
|
run-4/checkpoint-138/trainer_state.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.27346938775510204,
|
3 |
+
"best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-4\\checkpoint-138",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 138,
|
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_accuracy": 0.27346938775510204,
|
14 |
+
"eval_loss": 2.3406941890716553,
|
15 |
+
"eval_runtime": 1.1,
|
16 |
+
"eval_samples_per_second": 222.719,
|
17 |
+
"eval_steps_per_second": 14.545,
|
18 |
+
"step": 138
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 276,
|
23 |
+
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 2,
|
25 |
+
"save_steps": 500,
|
26 |
+
"total_flos": 0,
|
27 |
+
"train_batch_size": 16,
|
28 |
+
"trial_name": null,
|
29 |
+
"trial_params": {
|
30 |
+
"learning_rate": 3.631800261031757e-06,
|
31 |
+
"num_train_epochs": 2,
|
32 |
+
"per_device_train_batch_size": 16,
|
33 |
+
"seed": 19
|
34 |
+
}
|
35 |
+
}
|
run-4/checkpoint-138/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66c4a7f3b5e97737d2f6c9ad85248a2f6e3ecb3194cd0fd981c814acd6893c41
|
3 |
+
size 4728
|
run-4/checkpoint-138/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705261362.DESKTOP-RFEED41.20976.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86947918006960ba50af62699aa7185cf3c18ab355d4355e8e9065be235eb30b
|
3 |
+
size 5275
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66c4a7f3b5e97737d2f6c9ad85248a2f6e3ecb3194cd0fd981c814acd6893c41
|
3 |
size 4728
|