Swoodplays
commited on
Commit
•
ce02e7e
1
Parent(s):
a7b9f8a
Upload folder using huggingface_hub
Browse files- checkpoint-1000/config.json +41 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +7 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer_config.json +55 -0
- checkpoint-1000/trainer_state.json +103 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1000/vocab.txt +0 -0
checkpoint-1000/config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"label2id": {
|
21 |
+
"LABEL_0": 0,
|
22 |
+
"LABEL_1": 1,
|
23 |
+
"LABEL_2": 2,
|
24 |
+
"LABEL_3": 3,
|
25 |
+
"LABEL_4": 4,
|
26 |
+
"LABEL_5": 5
|
27 |
+
},
|
28 |
+
"max_position_embeddings": 512,
|
29 |
+
"model_type": "distilbert",
|
30 |
+
"n_heads": 12,
|
31 |
+
"n_layers": 6,
|
32 |
+
"pad_token_id": 0,
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"qa_dropout": 0.1,
|
35 |
+
"seq_classif_dropout": 0.2,
|
36 |
+
"sinusoidal_pos_embds": false,
|
37 |
+
"tie_weights_": true,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.44.0",
|
40 |
+
"vocab_size": 30522
|
41 |
+
}
|
checkpoint-1000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1773b1f406e8aea0d891e34b87b983ea0fe968be31c49a380725991b6779ea3a
|
3 |
+
size 267844872
|
checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b03dd6eba49048e3b98c364b9817d3eb89f9d6c3fd53b718b748b5e55035e9b7
|
3 |
+
size 535751866
|
checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fe91c7812cc2605dbb79e8164f657798fd238b502ba458a9f0a7cd69cd7941a
|
3 |
+
size 14244
|
checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80a7140325c88f1fe534fe1fa803aa583acf9c14aa02a6b34c8cc8f46b6ce085
|
3 |
+
size 1064
|
checkpoint-1000/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 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1000/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 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
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": 0.873,
|
14 |
+
"eval_f1 score": 0.8653944242728573,
|
15 |
+
"eval_loss": 0.4448868930339813,
|
16 |
+
"eval_runtime": 2.5176,
|
17 |
+
"eval_samples_per_second": 794.416,
|
18 |
+
"eval_steps_per_second": 6.355,
|
19 |
+
"step": 125
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 2.0,
|
23 |
+
"eval_accuracy": 0.9265,
|
24 |
+
"eval_f1 score": 0.9269527312677431,
|
25 |
+
"eval_loss": 0.2165956199169159,
|
26 |
+
"eval_runtime": 2.544,
|
27 |
+
"eval_samples_per_second": 786.152,
|
28 |
+
"eval_steps_per_second": 6.289,
|
29 |
+
"step": 250
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_accuracy": 0.933,
|
34 |
+
"eval_f1 score": 0.9338650823124836,
|
35 |
+
"eval_loss": 0.17256759107112885,
|
36 |
+
"eval_runtime": 2.5585,
|
37 |
+
"eval_samples_per_second": 781.698,
|
38 |
+
"eval_steps_per_second": 6.254,
|
39 |
+
"step": 375
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 4.0,
|
43 |
+
"eval_accuracy": 0.9385,
|
44 |
+
"eval_f1 score": 0.9386048187212848,
|
45 |
+
"eval_loss": 0.15524688363075256,
|
46 |
+
"eval_runtime": 2.5676,
|
47 |
+
"eval_samples_per_second": 778.947,
|
48 |
+
"eval_steps_per_second": 6.232,
|
49 |
+
"step": 500
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 5.0,
|
53 |
+
"eval_accuracy": 0.938,
|
54 |
+
"eval_f1 score": 0.9382616136983211,
|
55 |
+
"eval_loss": 0.14387381076812744,
|
56 |
+
"eval_runtime": 2.5374,
|
57 |
+
"eval_samples_per_second": 788.208,
|
58 |
+
"eval_steps_per_second": 6.306,
|
59 |
+
"step": 625
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 6.0,
|
63 |
+
"eval_accuracy": 0.937,
|
64 |
+
"eval_f1 score": 0.9370370279908306,
|
65 |
+
"eval_loss": 0.14351172745227814,
|
66 |
+
"eval_runtime": 2.5532,
|
67 |
+
"eval_samples_per_second": 783.329,
|
68 |
+
"eval_steps_per_second": 6.267,
|
69 |
+
"step": 750
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 7.0,
|
73 |
+
"eval_accuracy": 0.9355,
|
74 |
+
"eval_f1 score": 0.9355950438866585,
|
75 |
+
"eval_loss": 0.14806246757507324,
|
76 |
+
"eval_runtime": 2.566,
|
77 |
+
"eval_samples_per_second": 779.421,
|
78 |
+
"eval_steps_per_second": 6.235,
|
79 |
+
"step": 875
|
80 |
+
}
|
81 |
+
],
|
82 |
+
"logging_steps": 16000,
|
83 |
+
"max_steps": 1250,
|
84 |
+
"num_input_tokens_seen": 0,
|
85 |
+
"num_train_epochs": 10,
|
86 |
+
"save_steps": 500,
|
87 |
+
"stateful_callbacks": {
|
88 |
+
"TrainerControl": {
|
89 |
+
"args": {
|
90 |
+
"should_epoch_stop": false,
|
91 |
+
"should_evaluate": false,
|
92 |
+
"should_log": false,
|
93 |
+
"should_save": true,
|
94 |
+
"should_training_stop": false
|
95 |
+
},
|
96 |
+
"attributes": {}
|
97 |
+
}
|
98 |
+
},
|
99 |
+
"total_flos": 2881371446784000.0,
|
100 |
+
"train_batch_size": 128,
|
101 |
+
"trial_name": null,
|
102 |
+
"trial_params": null
|
103 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94a71234e1b393aa0417c3ffa5a6a5c172d975359a29a0717a1aa874d82aff97
|
3 |
+
size 5304
|
checkpoint-1000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|