Training in progress, step 14
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- config.json +62 -0
- model.safetensors +3 -0
- run-0/checkpoint-14/config.json +62 -0
- run-0/checkpoint-14/model.safetensors +3 -0
- run-0/checkpoint-14/optimizer.pt +3 -0
- run-0/checkpoint-14/rng_state.pth +3 -0
- run-0/checkpoint-14/scheduler.pt +3 -0
- run-0/checkpoint-14/special_tokens_map.json +7 -0
- run-0/checkpoint-14/tokenizer.json +0 -0
- run-0/checkpoint-14/tokenizer_config.json +56 -0
- run-0/checkpoint-14/trainer_state.json +47 -0
- run-0/checkpoint-14/training_args.bin +3 -0
- run-0/checkpoint-14/vocab.txt +0 -0
- run-0/checkpoint-20/config.json +63 -0
- run-0/checkpoint-20/model.safetensors +3 -0
- run-0/checkpoint-20/optimizer.pt +3 -0
- run-0/checkpoint-20/rng_state.pth +3 -0
- run-0/checkpoint-20/scheduler.pt +3 -0
- run-0/checkpoint-20/special_tokens_map.json +7 -0
- run-0/checkpoint-20/tokenizer.json +0 -0
- run-0/checkpoint-20/tokenizer_config.json +56 -0
- run-0/checkpoint-20/trainer_state.json +74 -0
- run-0/checkpoint-20/training_args.bin +3 -0
- run-0/checkpoint-20/vocab.txt +0 -0
- run-1/checkpoint-12/config.json +63 -0
- run-1/checkpoint-12/model.safetensors +3 -0
- run-1/checkpoint-12/optimizer.pt +3 -0
- run-1/checkpoint-12/rng_state.pth +3 -0
- run-1/checkpoint-12/scheduler.pt +3 -0
- run-1/checkpoint-12/special_tokens_map.json +7 -0
- run-1/checkpoint-12/tokenizer.json +0 -0
- run-1/checkpoint-12/tokenizer_config.json +56 -0
- run-1/checkpoint-12/trainer_state.json +56 -0
- run-1/checkpoint-12/training_args.bin +3 -0
- run-1/checkpoint-12/vocab.txt +0 -0
- run-2/checkpoint-8/config.json +63 -0
- run-2/checkpoint-8/model.safetensors +3 -0
- run-2/checkpoint-8/optimizer.pt +3 -0
- run-2/checkpoint-8/rng_state.pth +3 -0
- run-2/checkpoint-8/scheduler.pt +3 -0
- run-2/checkpoint-8/special_tokens_map.json +7 -0
- run-2/checkpoint-8/tokenizer.json +0 -0
- run-2/checkpoint-8/tokenizer_config.json +56 -0
- run-2/checkpoint-8/trainer_state.json +47 -0
- run-2/checkpoint-8/training_args.bin +3 -0
- run-2/checkpoint-8/vocab.txt +0 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
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 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a70896cda70c39157466e77a386e43d614d7340d26d1719e4aa7130a3a66c35
|
3 |
+
size 263187752
|
run-0/checkpoint-14/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-0/checkpoint-14/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a70896cda70c39157466e77a386e43d614d7340d26d1719e4aa7130a3a66c35
|
3 |
+
size 263187752
|
run-0/checkpoint-14/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25b2494ab1b9dac2e6484e9d3478241e16951cdd84a8149adac7ac0685da688f
|
3 |
+
size 526434810
|
run-0/checkpoint-14/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c0060471a9340f7cc602c9a86d1d9d308db5b4a83df50147b0235d18be03463
|
3 |
+
size 13990
|
run-0/checkpoint-14/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27c53eed2722d60729f122e697a32e584798b0e53daf02ec90e6986cd0796210
|
3 |
+
size 1064
|
run-0/checkpoint-14/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-0/checkpoint-14/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-14/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-0/checkpoint-14/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": 14,
|
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": 2.4279966354370117,
|
15 |
+
"eval_runtime": 17.893,
|
16 |
+
"eval_samples_per_second": 2.794,
|
17 |
+
"eval_steps_per_second": 0.391,
|
18 |
+
"step": 7
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 14,
|
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": 8,
|
40 |
+
"trial_name": null,
|
41 |
+
"trial_params": {
|
42 |
+
"learning_rate": 0.0003461152202579902,
|
43 |
+
"num_train_epochs": 2,
|
44 |
+
"per_device_train_batch_size": 8,
|
45 |
+
"weight_decay": 0.014902312802435893
|
46 |
+
}
|
47 |
+
}
|
run-0/checkpoint-14/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1ed3819cb2fe27bc2256360d46825e1851f5dc0f656a064e111a2321bc7183d
|
3 |
+
size 5240
|
run-0/checkpoint-14/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-20/config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6",
|
20 |
+
"7": "LABEL_7",
|
21 |
+
"8": "LABEL_8",
|
22 |
+
"9": "LABEL_9",
|
23 |
+
"10": "LABEL_10",
|
24 |
+
"11": "LABEL_11",
|
25 |
+
"12": "LABEL_12",
|
26 |
+
"13": "LABEL_13",
|
27 |
+
"14": "LABEL_14",
|
28 |
+
"15": "LABEL_15"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"label2id": {
|
33 |
+
"LABEL_0": 0,
|
34 |
+
"LABEL_1": 1,
|
35 |
+
"LABEL_10": 10,
|
36 |
+
"LABEL_11": 11,
|
37 |
+
"LABEL_12": 12,
|
38 |
+
"LABEL_13": 13,
|
39 |
+
"LABEL_14": 14,
|
40 |
+
"LABEL_15": 15,
|
41 |
+
"LABEL_2": 2,
|
42 |
+
"LABEL_3": 3,
|
43 |
+
"LABEL_4": 4,
|
44 |
+
"LABEL_5": 5,
|
45 |
+
"LABEL_6": 6,
|
46 |
+
"LABEL_7": 7,
|
47 |
+
"LABEL_8": 8,
|
48 |
+
"LABEL_9": 9
|
49 |
+
},
|
50 |
+
"layer_norm_eps": 1e-12,
|
51 |
+
"max_position_embeddings": 512,
|
52 |
+
"model_type": "bert",
|
53 |
+
"num_attention_heads": 12,
|
54 |
+
"num_hidden_layers": 12,
|
55 |
+
"pad_token_id": 0,
|
56 |
+
"position_embedding_type": "absolute",
|
57 |
+
"problem_type": "single_label_classification",
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.47.1",
|
60 |
+
"type_vocab_size": 2,
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 28996
|
63 |
+
}
|
run-0/checkpoint-20/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b5c78f06d53acb708acbededcab71be33db1f82befa21988d544cf84e01a340
|
3 |
+
size 433313832
|
run-0/checkpoint-20/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebdba344973f22ac06783a08cb9d50a765090a0451d50ceee301dfe9109d9a6c
|
3 |
+
size 866743162
|
run-0/checkpoint-20/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a5e70f9a75e0aac0493ef5d71898140525e32ebc99cfd539bb3be380e6c5d74
|
3 |
+
size 13990
|
run-0/checkpoint-20/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f443f63848e306442cd3d7354d278af7ad02b517bd970aab51ae156d07ab0146
|
3 |
+
size 1064
|
run-0/checkpoint-20/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-0/checkpoint-20/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-20/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": "BertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
run-0/checkpoint-20/trainer_state.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 20,
|
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": 2.5643558502197266,
|
15 |
+
"eval_runtime": 390.6347,
|
16 |
+
"eval_samples_per_second": 0.128,
|
17 |
+
"eval_steps_per_second": 0.018,
|
18 |
+
"step": 4
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.04,
|
23 |
+
"eval_loss": 2.9646835327148438,
|
24 |
+
"eval_runtime": 34.0619,
|
25 |
+
"eval_samples_per_second": 1.468,
|
26 |
+
"eval_steps_per_second": 0.206,
|
27 |
+
"step": 8
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_accuracy": 0.32,
|
32 |
+
"eval_loss": 2.424799680709839,
|
33 |
+
"eval_runtime": 36.2929,
|
34 |
+
"eval_samples_per_second": 1.378,
|
35 |
+
"eval_steps_per_second": 0.193,
|
36 |
+
"step": 12
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_accuracy": 0.32,
|
41 |
+
"eval_loss": 2.441561460494995,
|
42 |
+
"eval_runtime": 37.5071,
|
43 |
+
"eval_samples_per_second": 1.333,
|
44 |
+
"eval_steps_per_second": 0.187,
|
45 |
+
"step": 16
|
46 |
+
}
|
47 |
+
],
|
48 |
+
"logging_steps": 500,
|
49 |
+
"max_steps": 20,
|
50 |
+
"num_input_tokens_seen": 0,
|
51 |
+
"num_train_epochs": 5,
|
52 |
+
"save_steps": 500,
|
53 |
+
"stateful_callbacks": {
|
54 |
+
"TrainerControl": {
|
55 |
+
"args": {
|
56 |
+
"should_epoch_stop": false,
|
57 |
+
"should_evaluate": false,
|
58 |
+
"should_log": false,
|
59 |
+
"should_save": true,
|
60 |
+
"should_training_stop": true
|
61 |
+
},
|
62 |
+
"attributes": {}
|
63 |
+
}
|
64 |
+
},
|
65 |
+
"total_flos": 0,
|
66 |
+
"train_batch_size": 16,
|
67 |
+
"trial_name": null,
|
68 |
+
"trial_params": {
|
69 |
+
"learning_rate": 0.0003155201980058913,
|
70 |
+
"num_train_epochs": 5,
|
71 |
+
"per_device_train_batch_size": 16,
|
72 |
+
"weight_decay": 0.08349846837378451
|
73 |
+
}
|
74 |
+
}
|
run-0/checkpoint-20/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:416fa693723afbe856dcf1cebbf9340c6ae11df99f25c7e0b635d211fd4eee07
|
3 |
+
size 5240
|
run-0/checkpoint-20/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-12/config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6",
|
20 |
+
"7": "LABEL_7",
|
21 |
+
"8": "LABEL_8",
|
22 |
+
"9": "LABEL_9",
|
23 |
+
"10": "LABEL_10",
|
24 |
+
"11": "LABEL_11",
|
25 |
+
"12": "LABEL_12",
|
26 |
+
"13": "LABEL_13",
|
27 |
+
"14": "LABEL_14",
|
28 |
+
"15": "LABEL_15"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"label2id": {
|
33 |
+
"LABEL_0": 0,
|
34 |
+
"LABEL_1": 1,
|
35 |
+
"LABEL_10": 10,
|
36 |
+
"LABEL_11": 11,
|
37 |
+
"LABEL_12": 12,
|
38 |
+
"LABEL_13": 13,
|
39 |
+
"LABEL_14": 14,
|
40 |
+
"LABEL_15": 15,
|
41 |
+
"LABEL_2": 2,
|
42 |
+
"LABEL_3": 3,
|
43 |
+
"LABEL_4": 4,
|
44 |
+
"LABEL_5": 5,
|
45 |
+
"LABEL_6": 6,
|
46 |
+
"LABEL_7": 7,
|
47 |
+
"LABEL_8": 8,
|
48 |
+
"LABEL_9": 9
|
49 |
+
},
|
50 |
+
"layer_norm_eps": 1e-12,
|
51 |
+
"max_position_embeddings": 512,
|
52 |
+
"model_type": "bert",
|
53 |
+
"num_attention_heads": 12,
|
54 |
+
"num_hidden_layers": 12,
|
55 |
+
"pad_token_id": 0,
|
56 |
+
"position_embedding_type": "absolute",
|
57 |
+
"problem_type": "single_label_classification",
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.47.1",
|
60 |
+
"type_vocab_size": 2,
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 28996
|
63 |
+
}
|
run-1/checkpoint-12/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30520ddf055b0086a5163e36b5ada08bd1c3e9a6f51e2571fa49704ca27339ea
|
3 |
+
size 433313832
|
run-1/checkpoint-12/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac0234d7747b84c444f6eeb87ec5b8551c1e637989c561c85a404a7e66dad78a
|
3 |
+
size 866743162
|
run-1/checkpoint-12/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59cc0ca17123db86667fe2b999dc4d45bc2292f0becb83d9a367470fdcfcb14d
|
3 |
+
size 13990
|
run-1/checkpoint-12/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e3d6714bfd9178c1fcd6acd23754c8b42175fb1c04f634c3dec9fe783e15bda
|
3 |
+
size 1064
|
run-1/checkpoint-12/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-1/checkpoint-12/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-12/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": "BertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
run-1/checkpoint-12/trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 12,
|
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": 0.06,
|
14 |
+
"eval_loss": 2.7594950199127197,
|
15 |
+
"eval_runtime": 33.7649,
|
16 |
+
"eval_samples_per_second": 1.481,
|
17 |
+
"eval_steps_per_second": 0.207,
|
18 |
+
"step": 4
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.08,
|
23 |
+
"eval_loss": 2.6855175495147705,
|
24 |
+
"eval_runtime": 36.3771,
|
25 |
+
"eval_samples_per_second": 1.374,
|
26 |
+
"eval_steps_per_second": 0.192,
|
27 |
+
"step": 8
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 12,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 3,
|
34 |
+
"save_steps": 500,
|
35 |
+
"stateful_callbacks": {
|
36 |
+
"TrainerControl": {
|
37 |
+
"args": {
|
38 |
+
"should_epoch_stop": false,
|
39 |
+
"should_evaluate": false,
|
40 |
+
"should_log": false,
|
41 |
+
"should_save": true,
|
42 |
+
"should_training_stop": true
|
43 |
+
},
|
44 |
+
"attributes": {}
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"total_flos": 0,
|
48 |
+
"train_batch_size": 16,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": {
|
51 |
+
"learning_rate": 3.057465826568694e-05,
|
52 |
+
"num_train_epochs": 3,
|
53 |
+
"per_device_train_batch_size": 16,
|
54 |
+
"weight_decay": 0.03723974867102458
|
55 |
+
}
|
56 |
+
}
|
run-1/checkpoint-12/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a57174aa6cf65fa9f420f1adf1f57db12599f6d01b36cbb0bd8ebf327a14f28e
|
3 |
+
size 5240
|
run-1/checkpoint-12/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-8/config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6",
|
20 |
+
"7": "LABEL_7",
|
21 |
+
"8": "LABEL_8",
|
22 |
+
"9": "LABEL_9",
|
23 |
+
"10": "LABEL_10",
|
24 |
+
"11": "LABEL_11",
|
25 |
+
"12": "LABEL_12",
|
26 |
+
"13": "LABEL_13",
|
27 |
+
"14": "LABEL_14",
|
28 |
+
"15": "LABEL_15"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"label2id": {
|
33 |
+
"LABEL_0": 0,
|
34 |
+
"LABEL_1": 1,
|
35 |
+
"LABEL_10": 10,
|
36 |
+
"LABEL_11": 11,
|
37 |
+
"LABEL_12": 12,
|
38 |
+
"LABEL_13": 13,
|
39 |
+
"LABEL_14": 14,
|
40 |
+
"LABEL_15": 15,
|
41 |
+
"LABEL_2": 2,
|
42 |
+
"LABEL_3": 3,
|
43 |
+
"LABEL_4": 4,
|
44 |
+
"LABEL_5": 5,
|
45 |
+
"LABEL_6": 6,
|
46 |
+
"LABEL_7": 7,
|
47 |
+
"LABEL_8": 8,
|
48 |
+
"LABEL_9": 9
|
49 |
+
},
|
50 |
+
"layer_norm_eps": 1e-12,
|
51 |
+
"max_position_embeddings": 512,
|
52 |
+
"model_type": "bert",
|
53 |
+
"num_attention_heads": 12,
|
54 |
+
"num_hidden_layers": 12,
|
55 |
+
"pad_token_id": 0,
|
56 |
+
"position_embedding_type": "absolute",
|
57 |
+
"problem_type": "single_label_classification",
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.47.1",
|
60 |
+
"type_vocab_size": 2,
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 28996
|
63 |
+
}
|
run-2/checkpoint-8/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d0ff9d7553e5f401f66acc306718599e93884dd508d791993f33833deb328ca
|
3 |
+
size 433313832
|
run-2/checkpoint-8/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:454214c0144d04c453ea1d2ec2b5a7df1c3423f6818f9756a14284705fa8283a
|
3 |
+
size 866743162
|
run-2/checkpoint-8/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feb9296950c146245afd5a3147821b22e6313de8735f850c30a3188a431ebf85
|
3 |
+
size 13990
|
run-2/checkpoint-8/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af27b588f87c0fb3db5b0d16c4f98bbfbf7bb779576355ce3f3345eaaa70abdc
|
3 |
+
size 1064
|
run-2/checkpoint-8/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-8/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-8/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": "BertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
run-2/checkpoint-8/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": 8,
|
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": 0.08,
|
14 |
+
"eval_loss": 2.832538366317749,
|
15 |
+
"eval_runtime": 34.3925,
|
16 |
+
"eval_samples_per_second": 1.454,
|
17 |
+
"eval_steps_per_second": 0.204,
|
18 |
+
"step": 4
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 8,
|
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": 16,
|
40 |
+
"trial_name": null,
|
41 |
+
"trial_params": {
|
42 |
+
"learning_rate": 1.2303999115294106e-05,
|
43 |
+
"num_train_epochs": 2,
|
44 |
+
"per_device_train_batch_size": 16,
|
45 |
+
"weight_decay": 0.08430555410163074
|
46 |
+
}
|
47 |
+
}
|
run-2/checkpoint-8/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e6eda4fffe5514c3c46c347e7e1ea3b00ffee475601396824284afe9850a3a9
|
3 |
+
size 5240
|
run-2/checkpoint-8/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1ed3819cb2fe27bc2256360d46825e1851f5dc0f656a064e111a2321bc7183d
|
3 |
+
size 5240
|