Hugging Face's logo

LexcentraAI
/
lex-cross-encoder-mdeberta-v3-base-5neg

Safetensors
deberta-v2
Generated from Trainer
Model card Files Community
kimlong22 commited on
Commit
995369d
·
verified ·
1 Parent(s): bf6966d

Training in progress, epoch 1, checkpoint

Browse files
Files changed (14) hide show
  1. last-checkpoint/config.json +35 -0
  2. last-checkpoint/model.safetensors +3 -0
  3. last-checkpoint/optimizer.pt +3 -0
  4. last-checkpoint/rng_state_0.pth +3 -0
  5. last-checkpoint/rng_state_1.pth +3 -0
  6. last-checkpoint/rng_state_2.pth +3 -0
  7. last-checkpoint/rng_state_3.pth +3 -0
  8. last-checkpoint/rng_state_4.pth +3 -0
  9. last-checkpoint/rng_state_5.pth +3 -0
  10. last-checkpoint/rng_state_6.pth +3 -0
  11. last-checkpoint/rng_state_7.pth +3 -0
  12. last-checkpoint/scheduler.pt +3 -0
  13. last-checkpoint/trainer_state.json +39 -0
  14. last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/mdeberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.39.1",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 251000
35
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c03989f75d0aa4bd09aa494db2abf9fdb0699814577f09a2b8630feeff3136
3
+ size 1115268200
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:122128e68accfbfaa61106e4a08a7177da6af52b3b3da0e1b17c0c52f40ef1dc
3
+ size 2230655994
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c2e0a4cab570225070feda692b2162a9b40fcabdd5637926e2d942260865f5
3
+ size 15984
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:719551c691645b80be6d64346b6b37cbcf1c3bcf115735210b293531a14241f1
3
+ size 15984
last-checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1abbaa3e61df15650b0b8d5e31d1765de2d084229bfb2c0930169fd3f38b650
3
+ size 15984
last-checkpoint/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:697b606be1130775bd88ffdee4a1649261f6a26edeb2e1eb8717d55a9b3c7246
3
+ size 15984
last-checkpoint/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2308ce4ffc571a690001de8ba0878d90739f84e4e4454d446e6a0d99a5cf7725
3
+ size 15984
last-checkpoint/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9979034fcf548b3e23fd45a62872fd7ef6105dc04e4dd23df2112f398552a57
3
+ size 15984
last-checkpoint/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:449907656080f489d0957ade04723380fc9c1022cbe70db248bd76c2479b6cb3
3
+ size 15984
last-checkpoint/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d07c008bd2cdb25b485adf5e638dba6920e10d6fcd21f404a65d134bb5f6bf5
3
+ size 15984
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd329b76d03f410648ef363897eabe18ec0afb682154549bd5a0ea9c20f875eb
3
+ size 1064
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5555555524691358,
3
+ "best_model_checkpoint": "checkpoint/cross_encoder_20250522_full_data/checkpoint-1",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 3.537013292312622,
14
+ "learning_rate": 1e-06,
15
+ "loss": 0.7455,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_f2": 0.5555555524691358,
21
+ "eval_loss": 0.6809892654418945,
22
+ "eval_precision": 0.2,
23
+ "eval_recall": 1.0,
24
+ "eval_runtime": 0.1671,
25
+ "eval_samples_per_second": 59.844,
26
+ "eval_steps_per_second": 5.984,
27
+ "step": 1
28
+ }
29
+ ],
30
+ "logging_steps": 200,
31
+ "max_steps": 2,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "total_flos": 16839409139712.0,
36
+ "train_batch_size": 8,
37
+ "trial_name": null,
38
+ "trial_params": null
39
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c35a0a052756eed7c3a8019317fe0fdeda73d19c1f4811fdf8efcef22ec1a7d
3
+ size 5048