Training in progress, step 4
Browse files- model.safetensors +1 -1
- run-2/checkpoint-4/config.json +62 -0
- run-2/checkpoint-4/model.safetensors +3 -0
- run-2/checkpoint-4/optimizer.pt +3 -0
- run-2/checkpoint-4/rng_state.pth +3 -0
- run-2/checkpoint-4/scheduler.pt +3 -0
- run-2/checkpoint-4/special_tokens_map.json +7 -0
- run-2/checkpoint-4/tokenizer.json +0 -0
- run-2/checkpoint-4/tokenizer_config.json +56 -0
- run-2/checkpoint-4/trainer_state.json +47 -0
- run-2/checkpoint-4/training_args.bin +3 -0
- run-2/checkpoint-4/vocab.txt +0 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 263187752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac995762e1c1ad0373969e1655e873a33e1af4db0a3e678b6ee4d2bb90a40463
|
3 |
size 263187752
|
run-2/checkpoint-4/config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
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": "business",
|
13 |
+
"1": "civil-law",
|
14 |
+
"2": "constitutional-law",
|
15 |
+
"3": "contract",
|
16 |
+
"4": "contract-law",
|
17 |
+
"5": "copyright",
|
18 |
+
"6": "criminal-law",
|
19 |
+
"7": "employment",
|
20 |
+
"8": "intellectual-property",
|
21 |
+
"9": "internet",
|
22 |
+
"10": "liability",
|
23 |
+
"11": "licensing",
|
24 |
+
"12": "privacy",
|
25 |
+
"13": "software",
|
26 |
+
"14": "tax-law",
|
27 |
+
"15": "trademark"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"label2id": {
|
31 |
+
"business": 0,
|
32 |
+
"civil-law": 1,
|
33 |
+
"constitutional-law": 2,
|
34 |
+
"contract": 3,
|
35 |
+
"contract-law": 4,
|
36 |
+
"copyright": 5,
|
37 |
+
"criminal-law": 6,
|
38 |
+
"employment": 7,
|
39 |
+
"intellectual-property": 8,
|
40 |
+
"internet": 9,
|
41 |
+
"liability": 10,
|
42 |
+
"licensing": 11,
|
43 |
+
"privacy": 12,
|
44 |
+
"software": 13,
|
45 |
+
"tax-law": 14,
|
46 |
+
"trademark": 15
|
47 |
+
},
|
48 |
+
"max_position_embeddings": 512,
|
49 |
+
"model_type": "distilbert",
|
50 |
+
"n_heads": 12,
|
51 |
+
"n_layers": 6,
|
52 |
+
"output_past": true,
|
53 |
+
"pad_token_id": 0,
|
54 |
+
"problem_type": "single_label_classification",
|
55 |
+
"qa_dropout": 0.1,
|
56 |
+
"seq_classif_dropout": 0.2,
|
57 |
+
"sinusoidal_pos_embds": false,
|
58 |
+
"tie_weights_": true,
|
59 |
+
"torch_dtype": "float32",
|
60 |
+
"transformers_version": "4.47.1",
|
61 |
+
"vocab_size": 28996
|
62 |
+
}
|
run-2/checkpoint-4/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac995762e1c1ad0373969e1655e873a33e1af4db0a3e678b6ee4d2bb90a40463
|
3 |
+
size 263187752
|
run-2/checkpoint-4/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08310813def7568c8a09359058b9f2c1c0b7186860004047fced14fc19b782de
|
3 |
+
size 526434810
|
run-2/checkpoint-4/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c78f6ae3a8fcdc7691c97ecf56e2f6bec15b48d07ce1f0ad87aef91eb202a68b
|
3 |
+
size 13990
|
run-2/checkpoint-4/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e8023696fa8dcae76a6884273a206226d60c00f9b70fefd6a8a72f065c65b83
|
3 |
+
size 1064
|
run-2/checkpoint-4/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-2/checkpoint-4/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-4/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": false,
|
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-2/checkpoint-4/trainer_state.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.32,
|
14 |
+
"eval_loss": 2.6143014430999756,
|
15 |
+
"eval_runtime": 15.4498,
|
16 |
+
"eval_samples_per_second": 3.236,
|
17 |
+
"eval_steps_per_second": 0.453,
|
18 |
+
"step": 2
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 4,
|
23 |
+
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 2,
|
25 |
+
"save_steps": 500,
|
26 |
+
"stateful_callbacks": {
|
27 |
+
"TrainerControl": {
|
28 |
+
"args": {
|
29 |
+
"should_epoch_stop": false,
|
30 |
+
"should_evaluate": false,
|
31 |
+
"should_log": false,
|
32 |
+
"should_save": true,
|
33 |
+
"should_training_stop": true
|
34 |
+
},
|
35 |
+
"attributes": {}
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"total_flos": 0,
|
39 |
+
"train_batch_size": 32,
|
40 |
+
"trial_name": null,
|
41 |
+
"trial_params": {
|
42 |
+
"learning_rate": 7.575378303780058e-05,
|
43 |
+
"num_train_epochs": 2,
|
44 |
+
"per_device_train_batch_size": 32,
|
45 |
+
"weight_decay": 0.07004510590061262
|
46 |
+
}
|
47 |
+
}
|
run-2/checkpoint-4/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82ecc3bae80bb619cbe2fbbd4aae03066a6f0122beb9b5afeb343667a6af69d0
|
3 |
+
size 5240
|
run-2/checkpoint-4/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:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82ecc3bae80bb619cbe2fbbd4aae03066a6f0122beb9b5afeb343667a6af69d0
|
3 |
size 5240
|