darwinsfavorite commited on
Commit
157968b
·
verified ·
1 Parent(s): c88b64e

Training in progress, epoch 1

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b674f25ded57ebf21f027e819429e0ebd48f4f0f60757952bc5281c6055705f8
3
  size 267838720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b9e9a6b8ba49bbcf96b7d178997ad067b3f203127b53dfd806de1467c36786
3
  size 267838720
run-4l35az4b/checkpoint-168/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
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "Business",
12
+ "1": "Personal",
13
+ "2": "Government",
14
+ "3": "Others"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "Business": 0,
19
+ "Government": 2,
20
+ "Others": 3,
21
+ "Personal": 1
22
+ },
23
+ "max_position_embeddings": 512,
24
+ "model_type": "distilbert",
25
+ "n_heads": 12,
26
+ "n_layers": 6,
27
+ "pad_token_id": 0,
28
+ "problem_type": "single_label_classification",
29
+ "qa_dropout": 0.1,
30
+ "seq_classif_dropout": 0.2,
31
+ "sinusoidal_pos_embds": false,
32
+ "tie_weights_": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.51.3",
35
+ "vocab_size": 30522
36
+ }
run-4l35az4b/checkpoint-168/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0f692f63c770e0ff6488ef311233e4213b6b556387a4df0faf2c8139bcd053b
3
+ size 267838720
run-4l35az4b/checkpoint-168/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a42d1c4d6e2ea8a989a6f0a2d121ae3c021e8bf5cb2ee6b452e0f1faab074128
3
+ size 535739578
run-4l35az4b/checkpoint-168/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df10782ae4230a691108b33cdc5ccad6e6e32cf4de741965aca54307a3b3a43
3
+ size 14244
run-4l35az4b/checkpoint-168/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1205207a0c91bc7ebb025224a3ff2d0f70298d74eee7da31175e53ba2798e6b7
3
+ size 1064
run-4l35az4b/checkpoint-168/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-4l35az4b/checkpoint-168/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4l35az4b/checkpoint-168/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-4l35az4b/checkpoint-168/trainer_state.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 84,
3
+ "best_metric": 0.9333333333333333,
4
+ "best_model_checkpoint": "website_prediction_model/run-4l35az4b/checkpoint-84",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 168,
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": 0.9333333333333333,
15
+ "eval_loss": 0.306448757648468,
16
+ "eval_runtime": 0.7576,
17
+ "eval_samples_per_second": 98.996,
18
+ "eval_steps_per_second": 6.6,
19
+ "step": 84
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.9333333333333333,
24
+ "eval_loss": 0.2007637321949005,
25
+ "eval_runtime": 0.816,
26
+ "eval_samples_per_second": 91.916,
27
+ "eval_steps_per_second": 6.128,
28
+ "step": 168
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 168,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 2,
35
+ "save_steps": 500,
36
+ "stateful_callbacks": {
37
+ "TrainerControl": {
38
+ "args": {
39
+ "should_epoch_stop": false,
40
+ "should_evaluate": false,
41
+ "should_log": false,
42
+ "should_save": true,
43
+ "should_training_stop": true
44
+ },
45
+ "attributes": {}
46
+ }
47
+ },
48
+ "total_flos": 0,
49
+ "train_batch_size": 8,
50
+ "trial_name": null,
51
+ "trial_params": {
52
+ "_wandb": {},
53
+ "assignments": {},
54
+ "learning_rate": 7.418475718661359e-05,
55
+ "metric": "eval/loss",
56
+ "num_train_epochs": 2,
57
+ "per_device_train_batch_size": 8,
58
+ "seed": 9
59
+ }
60
+ }
run-4l35az4b/checkpoint-168/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57deca4086c25b751c8273099eb9f10148f808b8084f39c5f3ea1db5a0e64ef4
3
+ size 5304
run-4l35az4b/checkpoint-168/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-iicq8ma8/checkpoint-21/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
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "Business",
12
+ "1": "Personal",
13
+ "2": "Government",
14
+ "3": "Others"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "Business": 0,
19
+ "Government": 2,
20
+ "Others": 3,
21
+ "Personal": 1
22
+ },
23
+ "max_position_embeddings": 512,
24
+ "model_type": "distilbert",
25
+ "n_heads": 12,
26
+ "n_layers": 6,
27
+ "pad_token_id": 0,
28
+ "problem_type": "single_label_classification",
29
+ "qa_dropout": 0.1,
30
+ "seq_classif_dropout": 0.2,
31
+ "sinusoidal_pos_embds": false,
32
+ "tie_weights_": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.51.3",
35
+ "vocab_size": 30522
36
+ }
run-iicq8ma8/checkpoint-21/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b9e9a6b8ba49bbcf96b7d178997ad067b3f203127b53dfd806de1467c36786
3
+ size 267838720
run-iicq8ma8/checkpoint-21/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a12b85159b6798678948c1a03578c81ff9ed9d3bc85ef5ba84d1774d53b38979
3
+ size 535739578
run-iicq8ma8/checkpoint-21/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf66b645bb709b63b65b8907f419a1ecb837402ea043eae8d9ba82fc2dfe638
3
+ size 14244
run-iicq8ma8/checkpoint-21/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3705e2863ccbf14af83014fbafcdeea5f62ec133312f7f4fcefaf90156558314
3
+ size 1064
run-iicq8ma8/checkpoint-21/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-iicq8ma8/checkpoint-21/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-iicq8ma8/checkpoint-21/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-iicq8ma8/checkpoint-21/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 21,
3
+ "best_metric": 0.6666666666666666,
4
+ "best_model_checkpoint": "website_prediction_model/run-iicq8ma8/checkpoint-21",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 21,
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": 0.6666666666666666,
15
+ "eval_loss": 1.2975796461105347,
16
+ "eval_runtime": 0.7433,
17
+ "eval_samples_per_second": 100.903,
18
+ "eval_steps_per_second": 6.727,
19
+ "step": 21
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 42,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 2,
26
+ "save_steps": 500,
27
+ "stateful_callbacks": {
28
+ "TrainerControl": {
29
+ "args": {
30
+ "should_epoch_stop": false,
31
+ "should_evaluate": false,
32
+ "should_log": false,
33
+ "should_save": true,
34
+ "should_training_stop": false
35
+ },
36
+ "attributes": {}
37
+ }
38
+ },
39
+ "total_flos": 0,
40
+ "train_batch_size": 32,
41
+ "trial_name": null,
42
+ "trial_params": {
43
+ "_wandb": {},
44
+ "assignments": {},
45
+ "learning_rate": 3.842872784434368e-05,
46
+ "metric": "eval/loss",
47
+ "num_train_epochs": 2,
48
+ "per_device_train_batch_size": 32,
49
+ "seed": 18
50
+ }
51
+ }
run-iicq8ma8/checkpoint-21/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3053f61c9a74dd6214452c566653ecb39f5b3015c5a32f57bd5a57a6fd7c7966
3
+ size 5304
run-iicq8ma8/checkpoint-21/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57deca4086c25b751c8273099eb9f10148f808b8084f39c5f3ea1db5a0e64ef4
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3053f61c9a74dd6214452c566653ecb39f5b3015c5a32f57bd5a57a6fd7c7966
3
  size 5304