Hugging Face's logo

joseph10
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
text-embeddings-inference
Model card Files
xet
 Metrics Community
joseph10 commited on
Commit
2d969ec
·
1 Parent(s): 44a04f4

Training in progress, epoch 1

Browse files
Files changed (15) hide show
  1. logs/events.out.tfevents.1701811556.joseph_legion.26688.10 +3 -0
  2. logs/events.out.tfevents.1701811605.joseph_legion.26688.11 +3 -0
  3. model.safetensors +1 -1
  4. run-10/checkpoint-958/config.json +38 -0
  5. run-10/checkpoint-958/model.safetensors +3 -0
  6. run-10/checkpoint-958/optimizer.pt +3 -0
  7. run-10/checkpoint-958/rng_state.pth +3 -0
  8. run-10/checkpoint-958/scheduler.pt +3 -0
  9. run-10/checkpoint-958/special_tokens_map.json +7 -0
  10. run-10/checkpoint-958/tokenizer.json +0 -0
  11. run-10/checkpoint-958/tokenizer_config.json +57 -0
  12. run-10/checkpoint-958/trainer_state.json +39 -0
  13. run-10/checkpoint-958/training_args.bin +3 -0
  14. run-10/checkpoint-958/vocab.txt +0 -0
  15. training_args.bin +1 -1
logs/events.out.tfevents.1701811556.joseph_legion.26688.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adf68e085dc2e5b3ebd06adeb1d7ce7d0c0a4ba2732579c390df6ac640af1a45
3
+ size 4845
logs/events.out.tfevents.1701811605.joseph_legion.26688.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e124d6415c8a882378afd298f8b9047968350bd57b50ec134d07c1e71eda3086
3
+ size 4843
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17c052bbe40103153c77fc3efd2705acd7539d276e869c46dbdb2f11ec03ad41
3
  size 17550344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eaa198a3c3532c43fa2ae8bbe880dce1c1d3d51fa929f704a16a635f6e1f47f
3
  size 17550344
run-10/checkpoint-958/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "noHate",
13
+ "1": "hate",
14
+ "2": "idk/skip",
15
+ "3": "relation"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 512,
19
+ "label2id": {
20
+ "hate": "1",
21
+ "idk/skip": "2",
22
+ "noHate": "0",
23
+ "relation": "3"
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 2,
29
+ "num_hidden_layers": 2,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.35.2",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 30522
38
+ }
run-10/checkpoint-958/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eaa198a3c3532c43fa2ae8bbe880dce1c1d3d51fa929f704a16a635f6e1f47f
3
+ size 17550344
run-10/checkpoint-958/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f53589b1fe73a3d0890f945dcd74826732f91b4815474ff5a0665b5bca1f7f
3
+ size 35125946
run-10/checkpoint-958/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5248121aba147ed8617131a4e07dd5da8931107e82bef46fa7a5aaecf50f6add
3
+ size 14244
run-10/checkpoint-958/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e4277a1687fbcdc06479ac9955cda22baaa883a05575dd57e7f7dcb36a65f5c
3
+ size 1064
run-10/checkpoint-958/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-10/checkpoint-958/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-958/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-10/checkpoint-958/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8610603290676416,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-10\\checkpoint-958",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 958,
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
+ "learning_rate": 4.959730561951787e-05,
14
+ "loss": 0.4733,
15
+ "step": 958
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8610603290676416,
20
+ "eval_loss": 0.47912609577178955,
21
+ "eval_runtime": 26.8567,
22
+ "eval_samples_per_second": 81.47,
23
+ "eval_steps_per_second": 0.67,
24
+ "step": 958
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 1916,
29
+ "num_train_epochs": 2,
30
+ "save_steps": 500,
31
+ "total_flos": 1002950230176.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "learning_rate": 9.919461123903574e-05,
35
+ "num_train_epochs": 2,
36
+ "per_device_train_batch_size": 8,
37
+ "seed": 1
38
+ }
39
+ }
run-10/checkpoint-958/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b02917711da760ae5e24809199aea8e5e2fece4505221ba531518da290aef349
3
+ size 4664
run-10/checkpoint-958/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ac3c661dfdfaeffb120cf37b2343c838705b67166d08923f5463d7f052868ba
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b02917711da760ae5e24809199aea8e5e2fece4505221ba531518da290aef349
3
  size 4664