Safetensors
Bulgarian
bert
sillviag commited on
Commit
77fe05c
·
verified ·
1 Parent(s): f18d907

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +33 -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 +84 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "No Renarrative",
12
+ "1": "Renarrative"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "label2id": {
17
+ "No Renarrative": 0,
18
+ "Renarrative": 1
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "position_embedding_type": "absolute",
27
+ "problem_type": "single_label_classification",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.53.0",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 30522
33
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd123eea768d3278ac7cf2b7789103aad6b3bf83e5e5160b8f6d01300975d811
3
+ size 437958648
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca9c106f4b74b02259aa56931cbd4f5070f9991dc25eb8a8415c363c5ff8b0e
3
+ size 876038394
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79a2b501d102819035f41f1f4b79fcc4f058b3e415164380473599f195f9e2a4
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ed5dd6031c6e48596320731dd0c54369d76f6c0c1267369d18e49abfd8cdf1
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1140,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.9513888888888888,
15
+ "eval_loss": 0.25660452246665955,
16
+ "eval_runtime": 9.1525,
17
+ "eval_samples_per_second": 31.467,
18
+ "eval_steps_per_second": 3.933,
19
+ "step": 285
20
+ },
21
+ {
22
+ "epoch": 1.7543859649122808,
23
+ "grad_norm": 0.02743104100227356,
24
+ "learning_rate": 3.249122807017544e-05,
25
+ "loss": 0.0946,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_accuracy": 0.9826388888888888,
31
+ "eval_loss": 0.10773849487304688,
32
+ "eval_runtime": 9.0685,
33
+ "eval_samples_per_second": 31.758,
34
+ "eval_steps_per_second": 3.97,
35
+ "step": 570
36
+ },
37
+ {
38
+ "epoch": 3.0,
39
+ "eval_accuracy": 0.9861111111111112,
40
+ "eval_loss": 0.04608719050884247,
41
+ "eval_runtime": 8.9558,
42
+ "eval_samples_per_second": 32.158,
43
+ "eval_steps_per_second": 4.02,
44
+ "step": 855
45
+ },
46
+ {
47
+ "epoch": 3.5087719298245617,
48
+ "grad_norm": 0.015116340480744839,
49
+ "learning_rate": 1.4947368421052632e-05,
50
+ "loss": 0.0468,
51
+ "step": 1000
52
+ },
53
+ {
54
+ "epoch": 4.0,
55
+ "eval_accuracy": 0.9826388888888888,
56
+ "eval_loss": 0.08199767768383026,
57
+ "eval_runtime": 9.0401,
58
+ "eval_samples_per_second": 31.858,
59
+ "eval_steps_per_second": 3.982,
60
+ "step": 1140
61
+ }
62
+ ],
63
+ "logging_steps": 500,
64
+ "max_steps": 1425,
65
+ "num_input_tokens_seen": 0,
66
+ "num_train_epochs": 5,
67
+ "save_steps": 500,
68
+ "stateful_callbacks": {
69
+ "TrainerControl": {
70
+ "args": {
71
+ "should_epoch_stop": false,
72
+ "should_evaluate": false,
73
+ "should_log": false,
74
+ "should_save": true,
75
+ "should_training_stop": false
76
+ },
77
+ "attributes": {}
78
+ }
79
+ },
80
+ "total_flos": 2397467936440320.0,
81
+ "train_batch_size": 8,
82
+ "trial_name": null,
83
+ "trial_params": null
84
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce98e6b607a645e6b005c94d06ed53ec859aa8d53075e70c70118db33b30ef6
3
+ size 5304