Kavin R V commited on
Commit
a55cc80
·
1 Parent(s): 2e1c013

Training in progress, step 700

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "nlpproject2023/small-bert",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
 
1
  {
2
+ "_name_or_path": "carnival13/dist_ret_hpqa",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
last-checkpoint/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "carnival13/dist_ret_hpqa",
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": 512,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2048,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 8,
17
+ "num_hidden_layers": 4,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.27.4",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db08df54aeb5f5829db92f87e678a78c1c48aac336e7e4b968bd02d653a53544
3
+ size 230160133
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86566bfae574dbcd041436ba9b4bcb65aa994939623da99a1fdb5d2eb68de6f1
3
+ size 115087631
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574c4471ed76d2f351ec4ad624722a2805b6a5c4c35926a672d2cec2ddf8f8f4
3
+ size 14575
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93b5bea80b5ae5a8507d2f40a018540ad21b9208004de01a1d01ed8ee1bf80c9
3
+ size 557
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afe5c917400564191c0073fbd5f9f0b8ee074e9c8081a764f18a8d4cee68efc6
3
+ size 627
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.21333736181259155,
3
+ "best_model_checkpoint": "carnival13/dist_ret_hpqa/checkpoint-700",
4
+ "epoch": 0.1976284584980237,
5
+ "global_step": 700,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1,
12
+ "learning_rate": 4.511575381140599e-05,
13
+ "loss": 0.0506,
14
+ "step": 350
15
+ },
16
+ {
17
+ "epoch": 0.1,
18
+ "eval_accuracy": 0.9690729820556718,
19
+ "eval_loss": 0.22434338927268982,
20
+ "eval_runtime": 199.0141,
21
+ "eval_samples_per_second": 316.983,
22
+ "eval_steps_per_second": 4.954,
23
+ "step": 350
24
+ },
25
+ {
26
+ "epoch": 0.2,
27
+ "learning_rate": 4.017504234895539e-05,
28
+ "loss": 0.0544,
29
+ "step": 700
30
+ },
31
+ {
32
+ "epoch": 0.2,
33
+ "eval_accuracy": 0.9590387419948005,
34
+ "eval_loss": 0.21333736181259155,
35
+ "eval_runtime": 200.4029,
36
+ "eval_samples_per_second": 314.786,
37
+ "eval_steps_per_second": 4.92,
38
+ "step": 700
39
+ }
40
+ ],
41
+ "max_steps": 3542,
42
+ "num_train_epochs": 1,
43
+ "total_flos": 664434479923200.0,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18aa3a70a37ed7766092808c88c7a872e7e3ebcfb859869ae096b85046f9e260
3
+ size 3579
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:baa1eb7e31223f2f493917064347e244cbc4e499b665fa8cb54085453af05086
3
  size 115087631
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86566bfae574dbcd041436ba9b4bcb65aa994939623da99a1fdb5d2eb68de6f1
3
  size 115087631
runs/Apr09_11-50-03_04fce0895664/1681041113.367928/events.out.tfevents.1681041113.04fce0895664.204.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e70e4abb9194df93c67c3d5340c5747e017002be31c09448085148a0590a9bb
3
+ size 5859
runs/Apr09_11-50-03_04fce0895664/events.out.tfevents.1681041113.04fce0895664.204.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:970c3c6a416932b9aa421c3ea28bcf810ea993ce322cdba9143c0e1280d2ade0
3
+ size 5014
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ac113d594f3bcfebd56e7219703274ced6631c50434614b7a711e8984c6ca9e
3
  size 3579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18aa3a70a37ed7766092808c88c7a872e7e3ebcfb859869ae096b85046f9e260
3
  size 3579