Hugging Face's logo

heavyhelium
/
electra-small-touche-rawplusctx-binary

Text Classification
Transformers
Safetensors
electra
Generated from Trainer
Model card Files
xet
 Community
heavyhelium commited on
Commit
760e5fc
·
verified ·
1 Parent(s): 4f81a49

Training in progress, epoch 1, checkpoint

Browse files
Files changed (10) hide show
  1. checkpoint-47/config.json +43 -0
  2. checkpoint-47/model.safetensors +3 -0
  3. checkpoint-47/optimizer.pt +3 -0
  4. checkpoint-47/rng_state.pth +3 -0
  5. checkpoint-47/scaler.pt +3 -0
  6. checkpoint-47/scheduler.pt +3 -0
  7. checkpoint-47/tokenizer.json +0 -0
  8. checkpoint-47/tokenizer_config.json +15 -0
  9. checkpoint-47/trainer_state.json +73 -0
  10. checkpoint-47/training_args.bin +3 -0
checkpoint-47/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "embedding_size": 128,
11
+ "eos_token_id": null,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 256,
15
+ "id2label": {
16
+ "0": "valid",
17
+ "1": "fallacy"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 1024,
21
+ "is_decoder": false,
22
+ "label2id": {
23
+ "fallacy": 1,
24
+ "valid": 0
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "electra",
29
+ "num_attention_heads": 4,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "summary_activation": "gelu",
35
+ "summary_last_dropout": 0.1,
36
+ "summary_type": "first",
37
+ "summary_use_proj": true,
38
+ "tie_word_embeddings": true,
39
+ "transformers_version": "5.9.0",
40
+ "type_vocab_size": 2,
41
+ "use_cache": false,
42
+ "vocab_size": 30522
43
+ }
checkpoint-47/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92fb921654963df2dd65a687ead7d692c1d3947b1d42429768aeb00d3917a177
3
+ size 54221200
checkpoint-47/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47cb685511cb986efae32e6b2a2f4f3a21cd6c17172a850c567db02b27efb95f
3
+ size 108567563
checkpoint-47/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeac2027eb2664c4b9a00faaf43f8883d2a3cac80c4f87642e34c597af840cfc
3
+ size 14645
checkpoint-47/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59488e5d9b4471d0d0555788046a08b8f749cb53682e1378f178ec2ec3004869
3
+ size 1383
checkpoint-47/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee3d0854f9a688512b45d4e25ab288193398346491a8acd92bc143f7d5879989
3
+ size 1465
checkpoint-47/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-47/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
checkpoint-47/trainer_state.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 47,
3
+ "best_metric": 0.42028985507246375,
4
+ "best_model_checkpoint": "models/electra-small-touche-rawplusctx-binary/trainer/checkpoint-47",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 47,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.2127659574468085,
14
+ "grad_norm": 0.6402145624160767,
15
+ "learning_rate": 1.125e-05,
16
+ "loss": 0.694329833984375,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.425531914893617,
21
+ "grad_norm": 1.1600931882858276,
22
+ "learning_rate": 2.3749999999999998e-05,
23
+ "loss": 0.69599609375,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.6382978723404256,
28
+ "grad_norm": 0.6479201912879944,
29
+ "learning_rate": 2.928909952606635e-05,
30
+ "loss": 0.6899505615234375,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.851063829787234,
35
+ "grad_norm": 1.7243105173110962,
36
+ "learning_rate": 2.7867298578199053e-05,
37
+ "loss": 0.69215087890625,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_accuracy": 0.525,
43
+ "eval_fallacy_f1": 0.17391304347826086,
44
+ "eval_loss": 0.6910571455955505,
45
+ "eval_macro_f1": 0.42028985507246375,
46
+ "eval_runtime": 0.2773,
47
+ "eval_samples_per_second": 721.362,
48
+ "eval_steps_per_second": 14.427,
49
+ "step": 47
50
+ }
51
+ ],
52
+ "logging_steps": 10,
53
+ "max_steps": 235,
54
+ "num_input_tokens_seen": 0,
55
+ "num_train_epochs": 5,
56
+ "save_steps": 500,
57
+ "stateful_callbacks": {
58
+ "TrainerControl": {
59
+ "args": {
60
+ "should_epoch_stop": false,
61
+ "should_evaluate": false,
62
+ "should_log": false,
63
+ "should_save": true,
64
+ "should_training_stop": false
65
+ },
66
+ "attributes": {}
67
+ }
68
+ },
69
+ "total_flos": 10753453326456.0,
70
+ "train_batch_size": 16,
71
+ "trial_name": null,
72
+ "trial_params": null
73
+ }
checkpoint-47/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc5901dd89bc4001eae56c39d102ead320c920268eead43685a352ba001b4959
3
+ size 5457