dog-in-the-box-studio commited on
Commit
c78e9af
·
verified ·
1 Parent(s): c0d55b5

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +27 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +89 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
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": "4.46.3",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6832875cc3ac33076ff20ebbbe81e2de051af0845e1cf708726aa1c9a268d27
3
+ size 437958648
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c333d947b55b45277c2c88762626b78d1147b072c044d285bf11fb51816242
3
+ size 876038330
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c8a82890e89cdb4d136a3c3f35673c7fe6afdc486eada62ed460ed8c769ba25
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61b56cafc5fbd69a28a2a2115870d17eb59cd270581ffb457887611c6c392b08
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4276,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23386342376052385,
13
+ "grad_norm": 7.437119483947754,
14
+ "learning_rate": 5e-05,
15
+ "loss": 0.6255,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.4677268475210477,
20
+ "grad_norm": 6.912251949310303,
21
+ "learning_rate": 4.337923728813559e-05,
22
+ "loss": 0.5989,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.7015902712815716,
27
+ "grad_norm": 10.695876121520996,
28
+ "learning_rate": 3.675847457627119e-05,
29
+ "loss": 0.5798,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.9354536950420954,
34
+ "grad_norm": 14.826552391052246,
35
+ "learning_rate": 3.013771186440678e-05,
36
+ "loss": 0.5655,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.1693171188026192,
41
+ "grad_norm": 0.20372487604618073,
42
+ "learning_rate": 2.3516949152542376e-05,
43
+ "loss": 0.5207,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.4031805425631432,
48
+ "grad_norm": 19.185436248779297,
49
+ "learning_rate": 1.6896186440677965e-05,
50
+ "loss": 0.5016,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.637043966323667,
55
+ "grad_norm": 38.33837127685547,
56
+ "learning_rate": 1.027542372881356e-05,
57
+ "loss": 0.4931,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 1.8709073900841908,
62
+ "grad_norm": 0.7482150197029114,
63
+ "learning_rate": 3.654661016949153e-06,
64
+ "loss": 0.4665,
65
+ "step": 4000
66
+ }
67
+ ],
68
+ "logging_steps": 500,
69
+ "max_steps": 4276,
70
+ "num_input_tokens_seen": 0,
71
+ "num_train_epochs": 2,
72
+ "save_steps": 500,
73
+ "stateful_callbacks": {
74
+ "TrainerControl": {
75
+ "args": {
76
+ "should_epoch_stop": false,
77
+ "should_evaluate": false,
78
+ "should_log": false,
79
+ "should_save": true,
80
+ "should_training_stop": true
81
+ },
82
+ "attributes": {}
83
+ }
84
+ },
85
+ "total_flos": 4499725268766720.0,
86
+ "train_batch_size": 4,
87
+ "trial_name": null,
88
+ "trial_params": null
89
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a339baca0dcb9588a6b6d19f018dfd05fd03dc2ffe1788e27bf89a79e253ca96
3
+ size 5240