Hugging Face's logo

samuelcolvin26
/
RoBERTa_Hatespeech_Classifier

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Metrics Community
samuelcolvin26 commited on
Commit
36e9ec1
·
verified ·
1 Parent(s): f71c63a

Training in progress, epoch 1

Browse files
Files changed (13) hide show
  1. model.safetensors +1 -1
  2. run-abl7jl8d/checkpoint-2542/config.json +28 -0
  3. run-abl7jl8d/checkpoint-2542/merges.txt +0 -0
  4. run-abl7jl8d/checkpoint-2542/model.safetensors +3 -0
  5. run-abl7jl8d/checkpoint-2542/optimizer.pt +3 -0
  6. run-abl7jl8d/checkpoint-2542/rng_state.pth +3 -0
  7. run-abl7jl8d/checkpoint-2542/scheduler.pt +3 -0
  8. run-abl7jl8d/checkpoint-2542/special_tokens_map.json +51 -0
  9. run-abl7jl8d/checkpoint-2542/tokenizer_config.json +56 -0
  10. run-abl7jl8d/checkpoint-2542/trainer_state.json +75 -0
  11. run-abl7jl8d/checkpoint-2542/training_args.bin +3 -0
  12. run-abl7jl8d/checkpoint-2542/vocab.json +0 -0
  13. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62c44c0a2bfb9495eef4f7449274c4c10590be12c94afd30ef2335ecf6d3258c
3
  size 498612824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cb41d37af8e3d51353c0dd1b9d0425d4619bc7ec30d3951cb5b5175cc1cc006
3
  size 498612824
run-abl7jl8d/checkpoint-2542/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.39.3",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
run-abl7jl8d/checkpoint-2542/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-abl7jl8d/checkpoint-2542/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cb41d37af8e3d51353c0dd1b9d0425d4619bc7ec30d3951cb5b5175cc1cc006
3
+ size 498612824
run-abl7jl8d/checkpoint-2542/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8dc62089a2ef20d1fcac115ce26c3d598f15d9816c39637718f2dc598e120d2
3
+ size 997345530
run-abl7jl8d/checkpoint-2542/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a4c11d74deaee83a2d533a3f52094793cf70b68f8216e5191bf5ef6362bffc7
3
+ size 14180
run-abl7jl8d/checkpoint-2542/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77fae71b067cbfd41e501b59a6204207bb30fc5e9adbf19441e85c2a3d70c344
3
+ size 1064
run-abl7jl8d/checkpoint-2542/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
run-abl7jl8d/checkpoint-2542/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "unk_token": "<unk>"
56
+ }
run-abl7jl8d/checkpoint-2542/trainer_state.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2542,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2,
13
+ "grad_norm": 4.194170951843262,
14
+ "learning_rate": 2.8524783634933124e-05,
15
+ "loss": 0.3088,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.39,
20
+ "grad_norm": 6.946930408477783,
21
+ "learning_rate": 2.7049567269866248e-05,
22
+ "loss": 0.2727,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.59,
27
+ "grad_norm": 6.29566764831543,
28
+ "learning_rate": 2.557435090479937e-05,
29
+ "loss": 0.2493,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.79,
34
+ "grad_norm": 2.268385171890259,
35
+ "learning_rate": 2.4099134539732495e-05,
36
+ "loss": 0.233,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.98,
41
+ "grad_norm": 10.843997955322266,
42
+ "learning_rate": 2.262391817466562e-05,
43
+ "loss": 0.2186,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_Accuracy": 0.9149422743535834,
49
+ "eval_F1": 0.8761679733648372,
50
+ "eval_Precision": 0.9256779757176897,
51
+ "eval_Recall": 0.8316851870730961,
52
+ "eval_loss": 0.21612036228179932,
53
+ "eval_runtime": 100.741,
54
+ "eval_samples_per_second": 269.116,
55
+ "eval_steps_per_second": 33.641,
56
+ "step": 2542
57
+ }
58
+ ],
59
+ "logging_steps": 500,
60
+ "max_steps": 10168,
61
+ "num_input_tokens_seen": 0,
62
+ "num_train_epochs": 4,
63
+ "save_steps": 500,
64
+ "total_flos": 4542234148648320.0,
65
+ "train_batch_size": 32,
66
+ "trial_name": null,
67
+ "trial_params": {
68
+ "_wandb": {},
69
+ "assignments": {},
70
+ "learning_rate": 3e-05,
71
+ "metric": "eval/loss",
72
+ "num_train_epochs": 4,
73
+ "per_device_train_batch_size": 32
74
+ }
75
+ }
run-abl7jl8d/checkpoint-2542/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dde10c28a53365df9182bc3888d1f202abddeabc74f43518071c9ce1357949d
3
+ size 4920
run-abl7jl8d/checkpoint-2542/vocab.json 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 sha256:2f591bcc7bb3d751c372b9e555545d558094f5e42774fe55fce79687d449affc
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dde10c28a53365df9182bc3888d1f202abddeabc74f43518071c9ce1357949d
3
  size 4920