pilotj commited on
Commit
105ea00
·
verified ·
1 Parent(s): 4dce6ad

Training in progress, step 500, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pilotj/distilbert-base-uncased-fibe-full-finetuned",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25"
38
+ },
39
+ "initializer_range": 0.02,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_10": 10,
44
+ "LABEL_11": 11,
45
+ "LABEL_12": 12,
46
+ "LABEL_13": 13,
47
+ "LABEL_14": 14,
48
+ "LABEL_15": 15,
49
+ "LABEL_16": 16,
50
+ "LABEL_17": 17,
51
+ "LABEL_18": 18,
52
+ "LABEL_19": 19,
53
+ "LABEL_2": 2,
54
+ "LABEL_20": 20,
55
+ "LABEL_21": 21,
56
+ "LABEL_22": 22,
57
+ "LABEL_23": 23,
58
+ "LABEL_24": 24,
59
+ "LABEL_25": 25,
60
+ "LABEL_3": 3,
61
+ "LABEL_4": 4,
62
+ "LABEL_5": 5,
63
+ "LABEL_6": 6,
64
+ "LABEL_7": 7,
65
+ "LABEL_8": 8,
66
+ "LABEL_9": 9
67
+ },
68
+ "max_position_embeddings": 512,
69
+ "model_type": "distilbert",
70
+ "n_heads": 12,
71
+ "n_layers": 6,
72
+ "pad_token_id": 0,
73
+ "problem_type": "single_label_classification",
74
+ "qa_dropout": 0.1,
75
+ "seq_classif_dropout": 0.2,
76
+ "sinusoidal_pos_embds": false,
77
+ "tie_weights_": true,
78
+ "torch_dtype": "float32",
79
+ "transformers_version": "4.44.2",
80
+ "vocab_size": 30522
81
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15cbb923a4355813b46ea8954e05ab8effa2eda9f1b8f64d439a26f31842a1f7
3
+ size 267906392
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cae84f72cdbd7570e20899135afc83db92d91a9d4d25239d3b1a7bf152a5288
3
+ size 535874874
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:974b44f0327aeed05d181ead40f57037df659928bde69b43d9f210068728bd5d
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119a850c14f30baeb469a3d205fd6f7c599519c63cd1111506a3c44f6d44bd04
3
+ size 1064
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5638089776039124,
3
+ "best_model_checkpoint": "/kaggle/working/results/checkpoint-500",
4
+ "epoch": 0.19047619047619047,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.19047619047619047,
13
+ "grad_norm": 280717.46875,
14
+ "learning_rate": 7.616146230007617e-05,
15
+ "loss": 0.396,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.19047619047619047,
20
+ "eval_loss": 0.5638089776039124,
21
+ "eval_runtime": 244.4233,
22
+ "eval_samples_per_second": 106.991,
23
+ "eval_steps_per_second": 0.839,
24
+ "step": 500
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 2625,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 1,
31
+ "save_steps": 500,
32
+ "stateful_callbacks": {
33
+ "TrainerControl": {
34
+ "args": {
35
+ "should_epoch_stop": false,
36
+ "should_evaluate": false,
37
+ "should_log": false,
38
+ "should_save": true,
39
+ "should_training_stop": false
40
+ },
41
+ "attributes": {}
42
+ }
43
+ },
44
+ "total_flos": 2120385527808000.0,
45
+ "train_batch_size": 32,
46
+ "trial_name": null,
47
+ "trial_params": null
48
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2108f8a59b7a937ff2416112d40f2053ee3034987ade2881502fa804a2fd165f
3
+ size 5240