Pavankalyan
commited on
Commit
·
7531066
1
Parent(s):
d97da10
Upload 7 files
Browse files- config.json +27 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +52 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.25.1",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 28996
|
27 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e21666f05242a25d241bbb4a6fcdd50fa2accd2b81d5553d3f61db639d8af57d
|
3 |
+
size 866610973
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d477fd64ce25f20697584c14177fb5a62fb1ae804805fcecfe70a4e1d0cc91d
|
3 |
+
size 433318253
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:935cf1538e374ee96545e923419582591cb046e575bab4f377e7bd371808be85
|
3 |
+
size 15523
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:679d710b4f371f5d68ac54cc3362e2514b511b7dfdea737b93087fa57242aeab
|
3 |
+
size 623
|
trainer_state.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.1156558533145273,
|
5 |
+
"global_step": 1500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.71,
|
12 |
+
"learning_rate": 3.824635637047485e-06,
|
13 |
+
"loss": 0.2885,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.9333333333333333,
|
19 |
+
"eval_loss": 0.2095741480588913,
|
20 |
+
"eval_runtime": 14.7617,
|
21 |
+
"eval_samples_per_second": 192.051,
|
22 |
+
"eval_steps_per_second": 12.058,
|
23 |
+
"step": 709
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.41,
|
27 |
+
"learning_rate": 2.6492712740949693e-06,
|
28 |
+
"loss": 0.1876,
|
29 |
+
"step": 1000
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.9354497354497354,
|
34 |
+
"eval_loss": 0.22086860239505768,
|
35 |
+
"eval_runtime": 14.1485,
|
36 |
+
"eval_samples_per_second": 200.374,
|
37 |
+
"eval_steps_per_second": 12.581,
|
38 |
+
"step": 1418
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 2.12,
|
42 |
+
"learning_rate": 1.4739069111424542e-06,
|
43 |
+
"loss": 0.1728,
|
44 |
+
"step": 1500
|
45 |
+
}
|
46 |
+
],
|
47 |
+
"max_steps": 2127,
|
48 |
+
"num_train_epochs": 3,
|
49 |
+
"total_flos": 6311507995975680.0,
|
50 |
+
"trial_name": null,
|
51 |
+
"trial_params": null
|
52 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c69ccae0d7d47d91deb512ceafc53e07092bdb894dc86f45d8c3ff6a188f830
|
3 |
+
size 3375
|