Abdoel03 commited on
Commit
0a57fa6
·
verified ·
1 Parent(s): ed41e72

Upload 9 files

Browse files
README.md CHANGED
@@ -1,3 +1,3 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
1
+ ---
2
+ license: apache-2.0
3
+ ---
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 5,
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": null,
9
+ "classifier_dropout": null,
10
+ "decoder_start_token_id": null,
11
+ "directionality": "bidi",
12
+ "dtype": "float32",
13
+ "eos_token_id": null,
14
+ "finetuning_task": null,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.1,
17
+ "hidden_size": 768,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "is_decoder": false,
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "pooler_fc_size": 768,
29
+ "pooler_num_attention_heads": 12,
30
+ "pooler_num_fc_layers": 3,
31
+ "pooler_size_per_head": 128,
32
+ "pooler_type": "first_token_transform",
33
+ "prefix": null,
34
+ "problem_type": "single_label_classification",
35
+ "pruned_heads": {},
36
+ "task_specific_params": null,
37
+ "tie_word_embeddings": true,
38
+ "torchscript": false,
39
+ "transformers_version": "5.13.1",
40
+ "type_vocab_size": 2,
41
+ "use_bfloat16": false,
42
+ "use_cache": false,
43
+ "vocab_size": 50000
44
+ }
mbg_preprocessing.csv ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47cc5d6720b14c538ab2b0f6a20051174f8dd5ee6f6543362df2a0b574356f86
3
+ size 497795072
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93bc9d651bdc2700ea55900731c2c9996799cc9c66ed4e89fe12e76a4294e714
3
+ size 995714443
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8256ac0134803a475840d835e7f872d1d79ed39fc42f3674f13442a79bf3d2b6
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b8cbc8816e4a06570df52fe92e3f1840eefa89f6d1884679cb2160af0b62d7d
3
+ size 1465
trainer_state.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 422,
3
+ "best_metric": 0.11706770956516266,
4
+ "best_model_checkpoint": "./results/checkpoint-422",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1266,
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": 0.968583283935981,
15
+ "eval_loss": 0.11706770956516266,
16
+ "eval_runtime": 12.1043,
17
+ "eval_samples_per_second": 139.372,
18
+ "eval_steps_per_second": 8.757,
19
+ "step": 422
20
+ },
21
+ {
22
+ "epoch": 1.1848341232227488,
23
+ "grad_norm": 0.7388460636138916,
24
+ "learning_rate": 1.2116903633491312e-05,
25
+ "loss": 0.12352166748046875,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_accuracy": 0.973325429756965,
31
+ "eval_loss": 0.12481112033128738,
32
+ "eval_runtime": 12.1825,
33
+ "eval_samples_per_second": 138.477,
34
+ "eval_steps_per_second": 8.701,
35
+ "step": 844
36
+ },
37
+ {
38
+ "epoch": 2.3696682464454977,
39
+ "grad_norm": 0.02850360795855522,
40
+ "learning_rate": 4.218009478672986e-06,
41
+ "loss": 0.04376292037963867,
42
+ "step": 1000
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_accuracy": 0.969768820391227,
47
+ "eval_loss": 0.15332327783107758,
48
+ "eval_runtime": 12.1589,
49
+ "eval_samples_per_second": 138.746,
50
+ "eval_steps_per_second": 8.718,
51
+ "step": 1266
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 1266,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 3,
58
+ "save_steps": 500,
59
+ "stateful_callbacks": {
60
+ "TrainerControl": {
61
+ "args": {
62
+ "should_epoch_stop": false,
63
+ "should_evaluate": false,
64
+ "should_log": false,
65
+ "should_save": true,
66
+ "should_training_stop": true
67
+ },
68
+ "attributes": {}
69
+ }
70
+ },
71
+ "total_flos": 1331013051302400.0,
72
+ "train_batch_size": 16,
73
+ "trial_name": null,
74
+ "trial_params": null
75
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38ae7365fff5c6521054bf5f6d7d8ce38ce45190234164d6a530c6fd68b367e0
3
+ size 5201