TetorisAce commited on
Commit
4ed273c
·
verified ·
1 Parent(s): d3d7489

Training in progress, epoch 3

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:103aa9e4cb35b82bf057824aa26e3962934a680263b3ac07249da491cd159f6a
3
  size 267838720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d86ee9a441976965ae34a54c5fd490554d8c5661e99a64e75278df9e7ae40f7f
3
  size 267838720
run-33tpx14s/checkpoint-375/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "dtype": "float32",
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "LABEL_0": 0,
20
+ "LABEL_1": 1,
21
+ "LABEL_2": 2,
22
+ "LABEL_3": 3
23
+ },
24
+ "max_position_embeddings": 512,
25
+ "model_type": "distilbert",
26
+ "n_heads": 12,
27
+ "n_layers": 6,
28
+ "pad_token_id": 0,
29
+ "problem_type": "single_label_classification",
30
+ "qa_dropout": 0.1,
31
+ "seq_classif_dropout": 0.2,
32
+ "sinusoidal_pos_embds": false,
33
+ "tie_weights_": true,
34
+ "transformers_version": "4.56.1",
35
+ "vocab_size": 30522
36
+ }
run-33tpx14s/checkpoint-375/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d86ee9a441976965ae34a54c5fd490554d8c5661e99a64e75278df9e7ae40f7f
3
+ size 267838720
run-33tpx14s/checkpoint-375/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:036d6d0bc95348be5e4c99095628c239be141c4cc020a89ecc2d5936c8e3d08a
3
+ size 535737163
run-33tpx14s/checkpoint-375/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca0635622c8ba430d4c4202c51fb9ae865d80082f7c883fab5445d5ad18eaf58
3
+ size 14391
run-33tpx14s/checkpoint-375/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5435677c52547eaa4c1e71125bd7087d3131c06e5c322a70af7ea9b1e6a55202
3
+ size 1465
run-33tpx14s/checkpoint-375/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-33tpx14s/checkpoint-375/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-33tpx14s/checkpoint-375/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-33tpx14s/checkpoint-375/trainer_state.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 250,
3
+ "best_metric": 0.4288104772567749,
4
+ "best_model_checkpoint": "topic_classifier_model/run-33tpx14s/checkpoint-250",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 375,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.87,
15
+ "eval_loss": 0.4858984351158142,
16
+ "eval_runtime": 157.7699,
17
+ "eval_samples_per_second": 6.338,
18
+ "eval_steps_per_second": 0.399,
19
+ "step": 125
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.884,
24
+ "eval_loss": 0.4288104772567749,
25
+ "eval_runtime": 158.8393,
26
+ "eval_samples_per_second": 6.296,
27
+ "eval_steps_per_second": 0.397,
28
+ "step": 250
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.879,
33
+ "eval_loss": 0.46461522579193115,
34
+ "eval_runtime": 163.4525,
35
+ "eval_samples_per_second": 6.118,
36
+ "eval_steps_per_second": 0.385,
37
+ "step": 375
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 375,
42
+ "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 3,
44
+ "save_steps": 500,
45
+ "stateful_callbacks": {
46
+ "TrainerControl": {
47
+ "args": {
48
+ "should_epoch_stop": false,
49
+ "should_evaluate": false,
50
+ "should_log": false,
51
+ "should_save": true,
52
+ "should_training_stop": true
53
+ },
54
+ "attributes": {}
55
+ }
56
+ },
57
+ "total_flos": 0,
58
+ "train_batch_size": 8,
59
+ "trial_name": null,
60
+ "trial_params": {
61
+ "_wandb": {
62
+ "cli_version": "0.21.3",
63
+ "m": [],
64
+ "python_version": "3.12.11",
65
+ "t": {
66
+ "1": [
67
+ 1,
68
+ 2,
69
+ 3,
70
+ 5,
71
+ 11,
72
+ 12,
73
+ 41,
74
+ 49,
75
+ 51,
76
+ 53,
77
+ 71,
78
+ 98,
79
+ 100,
80
+ 105
81
+ ],
82
+ "12": "0.21.3",
83
+ "13": "linux-x86_64",
84
+ "3": [
85
+ 14
86
+ ],
87
+ "4": "3.12.11",
88
+ "5": "0.21.3",
89
+ "6": "4.56.1",
90
+ "8": [
91
+ 1,
92
+ 12
93
+ ]
94
+ }
95
+ },
96
+ "assignments": {},
97
+ "learning_rate": 5.791706128698021e-05,
98
+ "metric": "eval/loss",
99
+ "num_train_epochs": 3,
100
+ "per_device_train_batch_size": 8,
101
+ "seed": 3
102
+ }
103
+ }
run-33tpx14s/checkpoint-375/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a39848412b97fe857dade1b2e88fbdb3ba986d0186e4ea1a9e7466c2be59d6
3
+ size 5777
run-33tpx14s/checkpoint-375/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Sep19_06-20-34_ea3a691caa9c/events.out.tfevents.1758263992.ea3a691caa9c.6934.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:204724e98ba4532dc6af60897fe7afe5bc2f6271f3e58951da38f1f737e4faea
3
- size 5704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae5e5debd37dfac42e14cfd851f0b99ead70791856f3919e395b7c69728b906
3
+ size 6381