abdurrahman22224
commited on
Commit
•
74d989f
1
Parent(s):
5e0ec4a
Training in progress, step 500
Browse files- fine_tuned_model/config.json +85 -0
- fine_tuned_model/model.safetensors +3 -0
- fine_tuned_model/special_tokens_map.json +7 -0
- fine_tuned_model/tokenizer.json +0 -0
- fine_tuned_model/tokenizer_config.json +55 -0
- fine_tuned_model/trainer_state.json +116 -0
- fine_tuned_model/training_args.bin +3 -0
- fine_tuned_model/vocab.txt +0 -0
- model.safetensors +1 -1
- runs/Jun06_07-24-55_8b69e68f16d6/events.out.tfevents.1717658722.8b69e68f16d6.214.2 +2 -2
- runs/Jun06_07-24-55_8b69e68f16d6/events.out.tfevents.1717659558.8b69e68f16d6.214.3 +3 -0
- runs/Jun06_07-39-47_8b69e68f16d6/events.out.tfevents.1717659593.8b69e68f16d6.214.4 +3 -0
- training_args.bin +1 -1
fine_tuned_model/config.json
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
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 |
+
"26": "LABEL_26",
|
39 |
+
"27": "LABEL_27"
|
40 |
+
},
|
41 |
+
"initializer_range": 0.02,
|
42 |
+
"label2id": {
|
43 |
+
"LABEL_0": 0,
|
44 |
+
"LABEL_1": 1,
|
45 |
+
"LABEL_10": 10,
|
46 |
+
"LABEL_11": 11,
|
47 |
+
"LABEL_12": 12,
|
48 |
+
"LABEL_13": 13,
|
49 |
+
"LABEL_14": 14,
|
50 |
+
"LABEL_15": 15,
|
51 |
+
"LABEL_16": 16,
|
52 |
+
"LABEL_17": 17,
|
53 |
+
"LABEL_18": 18,
|
54 |
+
"LABEL_19": 19,
|
55 |
+
"LABEL_2": 2,
|
56 |
+
"LABEL_20": 20,
|
57 |
+
"LABEL_21": 21,
|
58 |
+
"LABEL_22": 22,
|
59 |
+
"LABEL_23": 23,
|
60 |
+
"LABEL_24": 24,
|
61 |
+
"LABEL_25": 25,
|
62 |
+
"LABEL_26": 26,
|
63 |
+
"LABEL_27": 27,
|
64 |
+
"LABEL_3": 3,
|
65 |
+
"LABEL_4": 4,
|
66 |
+
"LABEL_5": 5,
|
67 |
+
"LABEL_6": 6,
|
68 |
+
"LABEL_7": 7,
|
69 |
+
"LABEL_8": 8,
|
70 |
+
"LABEL_9": 9
|
71 |
+
},
|
72 |
+
"max_position_embeddings": 512,
|
73 |
+
"model_type": "distilbert",
|
74 |
+
"n_heads": 12,
|
75 |
+
"n_layers": 6,
|
76 |
+
"pad_token_id": 0,
|
77 |
+
"problem_type": "single_label_classification",
|
78 |
+
"qa_dropout": 0.1,
|
79 |
+
"seq_classif_dropout": 0.2,
|
80 |
+
"sinusoidal_pos_embds": false,
|
81 |
+
"tie_weights_": true,
|
82 |
+
"torch_dtype": "float32",
|
83 |
+
"transformers_version": "4.41.2",
|
84 |
+
"vocab_size": 30522
|
85 |
+
}
|
fine_tuned_model/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7af31c6ca8b44ecee7a1f62d7be010e2d132b21fd8566e24d0066fd65a03fc4
|
3 |
+
size 267912544
|
fine_tuned_model/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 |
+
}
|
fine_tuned_model/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
fine_tuned_model/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
fine_tuned_model/trainer_state.json
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1310,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.49934036939313986,
|
14 |
+
"eval_f1": 0.3717562988500528,
|
15 |
+
"eval_loss": 1.9840989112854004,
|
16 |
+
"eval_runtime": 5.7809,
|
17 |
+
"eval_samples_per_second": 786.733,
|
18 |
+
"eval_steps_per_second": 12.455,
|
19 |
+
"step": 262
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 1.9083969465648853,
|
23 |
+
"grad_norm": 5.065511226654053,
|
24 |
+
"learning_rate": 6.18320610687023e-06,
|
25 |
+
"loss": 2.1649,
|
26 |
+
"step": 500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.0,
|
30 |
+
"eval_accuracy": 0.5507915567282322,
|
31 |
+
"eval_f1": 0.45462699909622,
|
32 |
+
"eval_loss": 1.6903139352798462,
|
33 |
+
"eval_runtime": 5.764,
|
34 |
+
"eval_samples_per_second": 789.038,
|
35 |
+
"eval_steps_per_second": 12.491,
|
36 |
+
"step": 524
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.0,
|
40 |
+
"eval_accuracy": 0.5732189973614775,
|
41 |
+
"eval_f1": 0.4991615500418303,
|
42 |
+
"eval_loss": 1.5778752565383911,
|
43 |
+
"eval_runtime": 5.7728,
|
44 |
+
"eval_samples_per_second": 787.828,
|
45 |
+
"eval_steps_per_second": 12.472,
|
46 |
+
"step": 786
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 3.816793893129771,
|
50 |
+
"grad_norm": 5.689663410186768,
|
51 |
+
"learning_rate": 2.3664122137404585e-06,
|
52 |
+
"loss": 1.5746,
|
53 |
+
"step": 1000
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"eval_accuracy": 0.5800351802990326,
|
58 |
+
"eval_f1": 0.5113533283207169,
|
59 |
+
"eval_loss": 1.53199303150177,
|
60 |
+
"eval_runtime": 5.8524,
|
61 |
+
"eval_samples_per_second": 777.122,
|
62 |
+
"eval_steps_per_second": 12.303,
|
63 |
+
"step": 1048
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 5.0,
|
67 |
+
"eval_accuracy": 0.5844327176781002,
|
68 |
+
"eval_f1": 0.5241148509205591,
|
69 |
+
"eval_loss": 1.5220619440078735,
|
70 |
+
"eval_runtime": 5.7662,
|
71 |
+
"eval_samples_per_second": 788.739,
|
72 |
+
"eval_steps_per_second": 12.487,
|
73 |
+
"step": 1310
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 5.0,
|
77 |
+
"step": 1310,
|
78 |
+
"total_flos": 2489878738824600.0,
|
79 |
+
"train_loss": 1.7738796088531728,
|
80 |
+
"train_runtime": 796.3576,
|
81 |
+
"train_samples_per_second": 105.034,
|
82 |
+
"train_steps_per_second": 1.645
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 5.0,
|
86 |
+
"eval_accuracy": 0.5844327176781002,
|
87 |
+
"eval_f1": 0.5241148509205591,
|
88 |
+
"eval_loss": 1.5220619440078735,
|
89 |
+
"eval_runtime": 5.5624,
|
90 |
+
"eval_samples_per_second": 817.632,
|
91 |
+
"eval_steps_per_second": 12.944,
|
92 |
+
"step": 1310
|
93 |
+
}
|
94 |
+
],
|
95 |
+
"logging_steps": 500,
|
96 |
+
"max_steps": 1310,
|
97 |
+
"num_input_tokens_seen": 0,
|
98 |
+
"num_train_epochs": 5,
|
99 |
+
"save_steps": 500,
|
100 |
+
"stateful_callbacks": {
|
101 |
+
"TrainerControl": {
|
102 |
+
"args": {
|
103 |
+
"should_epoch_stop": false,
|
104 |
+
"should_evaluate": false,
|
105 |
+
"should_log": false,
|
106 |
+
"should_save": true,
|
107 |
+
"should_training_stop": false
|
108 |
+
},
|
109 |
+
"attributes": {}
|
110 |
+
}
|
111 |
+
},
|
112 |
+
"total_flos": 2489878738824600.0,
|
113 |
+
"train_batch_size": 64,
|
114 |
+
"trial_name": null,
|
115 |
+
"trial_params": null
|
116 |
+
}
|
fine_tuned_model/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d31ca1b6309f8cda37216cd54cdf2061678046f22f4a6d6d67af7a3b7a15c2c7
|
3 |
+
size 5240
|
fine_tuned_model/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267912544
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f21e99ca4b6efa89d28d057d87c14eb171185962a7487439d99c73ca5af76aeb
|
3 |
size 267912544
|
runs/Jun06_07-24-55_8b69e68f16d6/events.out.tfevents.1717658722.8b69e68f16d6.214.2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd25b0b0c8e70e97608a607188b7ac1698dc51fb8b612173355817afc5885567
|
3 |
+
size 8737
|
runs/Jun06_07-24-55_8b69e68f16d6/events.out.tfevents.1717659558.8b69e68f16d6.214.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2b0eae59f4b24ece168706e925823b306056c0e6ad9167bb543ea94a41fc611
|
3 |
+
size 457
|
runs/Jun06_07-39-47_8b69e68f16d6/events.out.tfevents.1717659593.8b69e68f16d6.214.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39b82ff625acce49c9e19cae12f980c201fcebf07a262cf93c1c8bc24b142578
|
3 |
+
size 6697
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cd298b51e279c421485b37a08ff496e4f2546bad60f7bf6c0cca77739b18c49
|
3 |
size 5240
|