Upload folder using huggingface_hub
Browse files- all-mpnet-base-v2/subtaskA/0/best/config.json +33 -0
- all-mpnet-base-v2/subtaskA/0/best/model.safetensors +3 -0
- all-mpnet-base-v2/subtaskA/0/best/special_tokens_map.json +51 -0
- all-mpnet-base-v2/subtaskA/0/best/tokenizer.json +0 -0
- all-mpnet-base-v2/subtaskA/0/best/tokenizer_config.json +73 -0
- all-mpnet-base-v2/subtaskA/0/best/training_args.bin +3 -0
- all-mpnet-base-v2/subtaskA/0/best/vocab.txt +0 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-11976/config.json +33 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-11976/model.safetensors +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-11976/optimizer.pt +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-11976/rng_state.pth +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-11976/scheduler.pt +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-11976/special_tokens_map.json +51 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-11976/tokenizer.json +0 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-11976/tokenizer_config.json +73 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-11976/trainer_state.json +212 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-11976/training_args.bin +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-11976/vocab.txt +0 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-17964/config.json +33 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-17964/model.safetensors +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-17964/optimizer.pt +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-17964/rng_state.pth +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-17964/scheduler.pt +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-17964/special_tokens_map.json +51 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-17964/tokenizer.json +0 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-17964/tokenizer_config.json +73 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-17964/trainer_state.json +305 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-17964/training_args.bin +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-17964/vocab.txt +0 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-5988/config.json +33 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-5988/model.safetensors +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-5988/optimizer.pt +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-5988/rng_state.pth +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-5988/scheduler.pt +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-5988/special_tokens_map.json +51 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-5988/tokenizer.json +0 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-5988/tokenizer_config.json +73 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-5988/trainer_state.json +119 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-5988/training_args.bin +3 -0
- all-mpnet-base-v2/subtaskA/0/checkpoint-5988/vocab.txt +0 -0
all-mpnet-base-v2/subtaskA/0/best/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sentence-transformers/all-mpnet-base-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MPNetForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "human",
|
| 14 |
+
"1": "machine"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"human": 0,
|
| 20 |
+
"machine": 1
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-05,
|
| 23 |
+
"max_position_embeddings": 514,
|
| 24 |
+
"model_type": "mpnet",
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"pad_token_id": 1,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"relative_attention_num_buckets": 32,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.47.0",
|
| 32 |
+
"vocab_size": 30527
|
| 33 |
+
}
|
all-mpnet-base-v2/subtaskA/0/best/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cba62768b49d0b384168db4597814c2e2c93830870dcd33f270d71d825cce0e4
|
| 3 |
+
size 437975200
|
all-mpnet-base-v2/subtaskA/0/best/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
all-mpnet-base-v2/subtaskA/0/best/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
all-mpnet-base-v2/subtaskA/0/best/tokenizer_config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"104": {
|
| 36 |
+
"content": "[UNK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"30526": {
|
| 44 |
+
"content": "<mask>",
|
| 45 |
+
"lstrip": true,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "<s>",
|
| 53 |
+
"clean_up_tokenization_spaces": false,
|
| 54 |
+
"cls_token": "<s>",
|
| 55 |
+
"do_lower_case": true,
|
| 56 |
+
"eos_token": "</s>",
|
| 57 |
+
"extra_special_tokens": {},
|
| 58 |
+
"mask_token": "<mask>",
|
| 59 |
+
"max_length": 128,
|
| 60 |
+
"model_max_length": 512,
|
| 61 |
+
"pad_to_multiple_of": null,
|
| 62 |
+
"pad_token": "<pad>",
|
| 63 |
+
"pad_token_type_id": 0,
|
| 64 |
+
"padding_side": "right",
|
| 65 |
+
"sep_token": "</s>",
|
| 66 |
+
"stride": 0,
|
| 67 |
+
"strip_accents": null,
|
| 68 |
+
"tokenize_chinese_chars": true,
|
| 69 |
+
"tokenizer_class": "MPNetTokenizer",
|
| 70 |
+
"truncation_side": "right",
|
| 71 |
+
"truncation_strategy": "longest_first",
|
| 72 |
+
"unk_token": "[UNK]"
|
| 73 |
+
}
|
all-mpnet-base-v2/subtaskA/0/best/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28cbdde62fbb653885701d73afa3dca89af181e42a6555099a9913e54638c7f9
|
| 3 |
+
size 5432
|
all-mpnet-base-v2/subtaskA/0/best/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
all-mpnet-base-v2/subtaskA/0/checkpoint-11976/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sentence-transformers/all-mpnet-base-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MPNetForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "human",
|
| 14 |
+
"1": "machine"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"human": 0,
|
| 20 |
+
"machine": 1
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-05,
|
| 23 |
+
"max_position_embeddings": 514,
|
| 24 |
+
"model_type": "mpnet",
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"pad_token_id": 1,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"relative_attention_num_buckets": 32,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.47.0",
|
| 32 |
+
"vocab_size": 30527
|
| 33 |
+
}
|
all-mpnet-base-v2/subtaskA/0/checkpoint-11976/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d43b26af17f6d2471347fb4496ae85aa3abb247701e132c323930b4a53689db7
|
| 3 |
+
size 437975200
|
all-mpnet-base-v2/subtaskA/0/checkpoint-11976/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4acf4e3264f10d496704fe4e1cbac68c43be5ccc9d39c3a66b99bc2260a1572d
|
| 3 |
+
size 876072122
|
all-mpnet-base-v2/subtaskA/0/checkpoint-11976/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9a19b671ded04d32e284422db4c302104ce1fd289a58a305949e2d8c217b916
|
| 3 |
+
size 14244
|
all-mpnet-base-v2/subtaskA/0/checkpoint-11976/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21a7e490dd7ba5b964efc51ab601154df3d51941113d8df4cd10b24a787995b7
|
| 3 |
+
size 1064
|
all-mpnet-base-v2/subtaskA/0/checkpoint-11976/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
all-mpnet-base-v2/subtaskA/0/checkpoint-11976/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
all-mpnet-base-v2/subtaskA/0/checkpoint-11976/tokenizer_config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"104": {
|
| 36 |
+
"content": "[UNK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"30526": {
|
| 44 |
+
"content": "<mask>",
|
| 45 |
+
"lstrip": true,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "<s>",
|
| 53 |
+
"clean_up_tokenization_spaces": false,
|
| 54 |
+
"cls_token": "<s>",
|
| 55 |
+
"do_lower_case": true,
|
| 56 |
+
"eos_token": "</s>",
|
| 57 |
+
"extra_special_tokens": {},
|
| 58 |
+
"mask_token": "<mask>",
|
| 59 |
+
"max_length": 128,
|
| 60 |
+
"model_max_length": 512,
|
| 61 |
+
"pad_to_multiple_of": null,
|
| 62 |
+
"pad_token": "<pad>",
|
| 63 |
+
"pad_token_type_id": 0,
|
| 64 |
+
"padding_side": "right",
|
| 65 |
+
"sep_token": "</s>",
|
| 66 |
+
"stride": 0,
|
| 67 |
+
"strip_accents": null,
|
| 68 |
+
"tokenize_chinese_chars": true,
|
| 69 |
+
"tokenizer_class": "MPNetTokenizer",
|
| 70 |
+
"truncation_side": "right",
|
| 71 |
+
"truncation_strategy": "longest_first",
|
| 72 |
+
"unk_token": "[UNK]"
|
| 73 |
+
}
|
all-mpnet-base-v2/subtaskA/0/checkpoint-11976/trainer_state.json
ADDED
|
@@ -0,0 +1,212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.1430160403251648,
|
| 3 |
+
"best_model_checkpoint": "/kaggle/working//model_sentence-transformers/all-mpnet-base-v2/subtaskA/0/checkpoint-5988",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 11976,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08350033400133601,
|
| 13 |
+
"grad_norm": 2.628113031387329,
|
| 14 |
+
"learning_rate": 1.944333110665776e-05,
|
| 15 |
+
"loss": 0.3143,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16700066800267202,
|
| 20 |
+
"grad_norm": 6.473922252655029,
|
| 21 |
+
"learning_rate": 1.888666221331552e-05,
|
| 22 |
+
"loss": 0.1553,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.250501002004008,
|
| 27 |
+
"grad_norm": 0.41650745272636414,
|
| 28 |
+
"learning_rate": 1.832999331997328e-05,
|
| 29 |
+
"loss": 0.1391,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.33400133600534404,
|
| 34 |
+
"grad_norm": 0.04540203511714935,
|
| 35 |
+
"learning_rate": 1.777332442663104e-05,
|
| 36 |
+
"loss": 0.1169,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.41750167000668004,
|
| 41 |
+
"grad_norm": 24.253005981445312,
|
| 42 |
+
"learning_rate": 1.72166555332888e-05,
|
| 43 |
+
"loss": 0.1199,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.501002004008016,
|
| 48 |
+
"grad_norm": 0.035162102431058884,
|
| 49 |
+
"learning_rate": 1.6659986639946563e-05,
|
| 50 |
+
"loss": 0.1105,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.584502338009352,
|
| 55 |
+
"grad_norm": 10.076239585876465,
|
| 56 |
+
"learning_rate": 1.6103317746604322e-05,
|
| 57 |
+
"loss": 0.1009,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6680026720106881,
|
| 62 |
+
"grad_norm": 1.568239450454712,
|
| 63 |
+
"learning_rate": 1.554664885326208e-05,
|
| 64 |
+
"loss": 0.1025,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.751503006012024,
|
| 69 |
+
"grad_norm": 11.781553268432617,
|
| 70 |
+
"learning_rate": 1.498997995991984e-05,
|
| 71 |
+
"loss": 0.0878,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8350033400133601,
|
| 76 |
+
"grad_norm": 0.042673539370298386,
|
| 77 |
+
"learning_rate": 1.44333110665776e-05,
|
| 78 |
+
"loss": 0.0931,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.918503674014696,
|
| 83 |
+
"grad_norm": 3.912463426589966,
|
| 84 |
+
"learning_rate": 1.3876642173235361e-05,
|
| 85 |
+
"loss": 0.0812,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0,
|
| 90 |
+
"eval_f1": 0.956496325985304,
|
| 91 |
+
"eval_loss": 0.1430160403251648,
|
| 92 |
+
"eval_runtime": 459.2333,
|
| 93 |
+
"eval_samples_per_second": 52.156,
|
| 94 |
+
"eval_steps_per_second": 3.26,
|
| 95 |
+
"step": 5988
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.002004008016032,
|
| 99 |
+
"grad_norm": 22.093093872070312,
|
| 100 |
+
"learning_rate": 1.331997327989312e-05,
|
| 101 |
+
"loss": 0.0763,
|
| 102 |
+
"step": 6000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.085504342017368,
|
| 106 |
+
"grad_norm": 0.22258451581001282,
|
| 107 |
+
"learning_rate": 1.2763304386550881e-05,
|
| 108 |
+
"loss": 0.0504,
|
| 109 |
+
"step": 6500
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.169004676018704,
|
| 113 |
+
"grad_norm": 0.008524572476744652,
|
| 114 |
+
"learning_rate": 1.220663549320864e-05,
|
| 115 |
+
"loss": 0.0576,
|
| 116 |
+
"step": 7000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.25250501002004,
|
| 120 |
+
"grad_norm": 0.04477648064494133,
|
| 121 |
+
"learning_rate": 1.16499665998664e-05,
|
| 122 |
+
"loss": 0.0491,
|
| 123 |
+
"step": 7500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.3360053440213762,
|
| 127 |
+
"grad_norm": 0.04618832841515541,
|
| 128 |
+
"learning_rate": 1.109329770652416e-05,
|
| 129 |
+
"loss": 0.0512,
|
| 130 |
+
"step": 8000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.4195056780227122,
|
| 134 |
+
"grad_norm": 0.008414031937718391,
|
| 135 |
+
"learning_rate": 1.053662881318192e-05,
|
| 136 |
+
"loss": 0.0477,
|
| 137 |
+
"step": 8500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.503006012024048,
|
| 141 |
+
"grad_norm": 0.20392121374607086,
|
| 142 |
+
"learning_rate": 9.97995991983968e-06,
|
| 143 |
+
"loss": 0.0551,
|
| 144 |
+
"step": 9000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.586506346025384,
|
| 148 |
+
"grad_norm": 9.472536087036133,
|
| 149 |
+
"learning_rate": 9.423291026497439e-06,
|
| 150 |
+
"loss": 0.0453,
|
| 151 |
+
"step": 9500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.6700066800267201,
|
| 155 |
+
"grad_norm": 9.246102333068848,
|
| 156 |
+
"learning_rate": 8.8666221331552e-06,
|
| 157 |
+
"loss": 0.047,
|
| 158 |
+
"step": 10000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.753507014028056,
|
| 162 |
+
"grad_norm": 0.15841872990131378,
|
| 163 |
+
"learning_rate": 8.30995323981296e-06,
|
| 164 |
+
"loss": 0.0507,
|
| 165 |
+
"step": 10500
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.8370073480293923,
|
| 169 |
+
"grad_norm": 0.0037080268375575542,
|
| 170 |
+
"learning_rate": 7.75328434647072e-06,
|
| 171 |
+
"loss": 0.0473,
|
| 172 |
+
"step": 11000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.920507682030728,
|
| 176 |
+
"grad_norm": 0.2187177985906601,
|
| 177 |
+
"learning_rate": 7.1966154531284795e-06,
|
| 178 |
+
"loss": 0.0425,
|
| 179 |
+
"step": 11500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.0,
|
| 183 |
+
"eval_f1": 0.9493987975951904,
|
| 184 |
+
"eval_loss": 0.2554616332054138,
|
| 185 |
+
"eval_runtime": 456.0761,
|
| 186 |
+
"eval_samples_per_second": 52.518,
|
| 187 |
+
"eval_steps_per_second": 3.282,
|
| 188 |
+
"step": 11976
|
| 189 |
+
}
|
| 190 |
+
],
|
| 191 |
+
"logging_steps": 500,
|
| 192 |
+
"max_steps": 17964,
|
| 193 |
+
"num_input_tokens_seen": 0,
|
| 194 |
+
"num_train_epochs": 3,
|
| 195 |
+
"save_steps": 500,
|
| 196 |
+
"stateful_callbacks": {
|
| 197 |
+
"TrainerControl": {
|
| 198 |
+
"args": {
|
| 199 |
+
"should_epoch_stop": false,
|
| 200 |
+
"should_evaluate": false,
|
| 201 |
+
"should_log": false,
|
| 202 |
+
"should_save": true,
|
| 203 |
+
"should_training_stop": false
|
| 204 |
+
},
|
| 205 |
+
"attributes": {}
|
| 206 |
+
}
|
| 207 |
+
},
|
| 208 |
+
"total_flos": 5.039593798817376e+16,
|
| 209 |
+
"train_batch_size": 16,
|
| 210 |
+
"trial_name": null,
|
| 211 |
+
"trial_params": null
|
| 212 |
+
}
|
all-mpnet-base-v2/subtaskA/0/checkpoint-11976/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28cbdde62fbb653885701d73afa3dca89af181e42a6555099a9913e54638c7f9
|
| 3 |
+
size 5432
|
all-mpnet-base-v2/subtaskA/0/checkpoint-11976/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
all-mpnet-base-v2/subtaskA/0/checkpoint-17964/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sentence-transformers/all-mpnet-base-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MPNetForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "human",
|
| 14 |
+
"1": "machine"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"human": 0,
|
| 20 |
+
"machine": 1
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-05,
|
| 23 |
+
"max_position_embeddings": 514,
|
| 24 |
+
"model_type": "mpnet",
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"pad_token_id": 1,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"relative_attention_num_buckets": 32,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.47.0",
|
| 32 |
+
"vocab_size": 30527
|
| 33 |
+
}
|
all-mpnet-base-v2/subtaskA/0/checkpoint-17964/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82b56f43aab82d59edd723f9e1d401a9420f1c2fb6ce8dba77616458ca146faf
|
| 3 |
+
size 437975200
|
all-mpnet-base-v2/subtaskA/0/checkpoint-17964/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b00bceb014b0c4e7dae1a496578d3375fb506f7d316b9bd09bd309f40e27020
|
| 3 |
+
size 876072122
|
all-mpnet-base-v2/subtaskA/0/checkpoint-17964/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:627637f1d2298bf70844386262ad8e5f3c036033d9cb739c3041ddfb5368c76f
|
| 3 |
+
size 14244
|
all-mpnet-base-v2/subtaskA/0/checkpoint-17964/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9c28a50aa02b23d416735f83d810e16f9dee4fb849fd61bc8d6353ce7335561
|
| 3 |
+
size 1064
|
all-mpnet-base-v2/subtaskA/0/checkpoint-17964/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
all-mpnet-base-v2/subtaskA/0/checkpoint-17964/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
all-mpnet-base-v2/subtaskA/0/checkpoint-17964/tokenizer_config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"104": {
|
| 36 |
+
"content": "[UNK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"30526": {
|
| 44 |
+
"content": "<mask>",
|
| 45 |
+
"lstrip": true,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "<s>",
|
| 53 |
+
"clean_up_tokenization_spaces": false,
|
| 54 |
+
"cls_token": "<s>",
|
| 55 |
+
"do_lower_case": true,
|
| 56 |
+
"eos_token": "</s>",
|
| 57 |
+
"extra_special_tokens": {},
|
| 58 |
+
"mask_token": "<mask>",
|
| 59 |
+
"max_length": 128,
|
| 60 |
+
"model_max_length": 512,
|
| 61 |
+
"pad_to_multiple_of": null,
|
| 62 |
+
"pad_token": "<pad>",
|
| 63 |
+
"pad_token_type_id": 0,
|
| 64 |
+
"padding_side": "right",
|
| 65 |
+
"sep_token": "</s>",
|
| 66 |
+
"stride": 0,
|
| 67 |
+
"strip_accents": null,
|
| 68 |
+
"tokenize_chinese_chars": true,
|
| 69 |
+
"tokenizer_class": "MPNetTokenizer",
|
| 70 |
+
"truncation_side": "right",
|
| 71 |
+
"truncation_strategy": "longest_first",
|
| 72 |
+
"unk_token": "[UNK]"
|
| 73 |
+
}
|
all-mpnet-base-v2/subtaskA/0/checkpoint-17964/trainer_state.json
ADDED
|
@@ -0,0 +1,305 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.1430160403251648,
|
| 3 |
+
"best_model_checkpoint": "/kaggle/working//model_sentence-transformers/all-mpnet-base-v2/subtaskA/0/checkpoint-5988",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 17964,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08350033400133601,
|
| 13 |
+
"grad_norm": 2.628113031387329,
|
| 14 |
+
"learning_rate": 1.944333110665776e-05,
|
| 15 |
+
"loss": 0.3143,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16700066800267202,
|
| 20 |
+
"grad_norm": 6.473922252655029,
|
| 21 |
+
"learning_rate": 1.888666221331552e-05,
|
| 22 |
+
"loss": 0.1553,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.250501002004008,
|
| 27 |
+
"grad_norm": 0.41650745272636414,
|
| 28 |
+
"learning_rate": 1.832999331997328e-05,
|
| 29 |
+
"loss": 0.1391,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.33400133600534404,
|
| 34 |
+
"grad_norm": 0.04540203511714935,
|
| 35 |
+
"learning_rate": 1.777332442663104e-05,
|
| 36 |
+
"loss": 0.1169,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.41750167000668004,
|
| 41 |
+
"grad_norm": 24.253005981445312,
|
| 42 |
+
"learning_rate": 1.72166555332888e-05,
|
| 43 |
+
"loss": 0.1199,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.501002004008016,
|
| 48 |
+
"grad_norm": 0.035162102431058884,
|
| 49 |
+
"learning_rate": 1.6659986639946563e-05,
|
| 50 |
+
"loss": 0.1105,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.584502338009352,
|
| 55 |
+
"grad_norm": 10.076239585876465,
|
| 56 |
+
"learning_rate": 1.6103317746604322e-05,
|
| 57 |
+
"loss": 0.1009,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6680026720106881,
|
| 62 |
+
"grad_norm": 1.568239450454712,
|
| 63 |
+
"learning_rate": 1.554664885326208e-05,
|
| 64 |
+
"loss": 0.1025,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.751503006012024,
|
| 69 |
+
"grad_norm": 11.781553268432617,
|
| 70 |
+
"learning_rate": 1.498997995991984e-05,
|
| 71 |
+
"loss": 0.0878,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8350033400133601,
|
| 76 |
+
"grad_norm": 0.042673539370298386,
|
| 77 |
+
"learning_rate": 1.44333110665776e-05,
|
| 78 |
+
"loss": 0.0931,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.918503674014696,
|
| 83 |
+
"grad_norm": 3.912463426589966,
|
| 84 |
+
"learning_rate": 1.3876642173235361e-05,
|
| 85 |
+
"loss": 0.0812,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0,
|
| 90 |
+
"eval_f1": 0.956496325985304,
|
| 91 |
+
"eval_loss": 0.1430160403251648,
|
| 92 |
+
"eval_runtime": 459.2333,
|
| 93 |
+
"eval_samples_per_second": 52.156,
|
| 94 |
+
"eval_steps_per_second": 3.26,
|
| 95 |
+
"step": 5988
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.002004008016032,
|
| 99 |
+
"grad_norm": 22.093093872070312,
|
| 100 |
+
"learning_rate": 1.331997327989312e-05,
|
| 101 |
+
"loss": 0.0763,
|
| 102 |
+
"step": 6000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.085504342017368,
|
| 106 |
+
"grad_norm": 0.22258451581001282,
|
| 107 |
+
"learning_rate": 1.2763304386550881e-05,
|
| 108 |
+
"loss": 0.0504,
|
| 109 |
+
"step": 6500
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.169004676018704,
|
| 113 |
+
"grad_norm": 0.008524572476744652,
|
| 114 |
+
"learning_rate": 1.220663549320864e-05,
|
| 115 |
+
"loss": 0.0576,
|
| 116 |
+
"step": 7000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.25250501002004,
|
| 120 |
+
"grad_norm": 0.04477648064494133,
|
| 121 |
+
"learning_rate": 1.16499665998664e-05,
|
| 122 |
+
"loss": 0.0491,
|
| 123 |
+
"step": 7500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.3360053440213762,
|
| 127 |
+
"grad_norm": 0.04618832841515541,
|
| 128 |
+
"learning_rate": 1.109329770652416e-05,
|
| 129 |
+
"loss": 0.0512,
|
| 130 |
+
"step": 8000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.4195056780227122,
|
| 134 |
+
"grad_norm": 0.008414031937718391,
|
| 135 |
+
"learning_rate": 1.053662881318192e-05,
|
| 136 |
+
"loss": 0.0477,
|
| 137 |
+
"step": 8500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.503006012024048,
|
| 141 |
+
"grad_norm": 0.20392121374607086,
|
| 142 |
+
"learning_rate": 9.97995991983968e-06,
|
| 143 |
+
"loss": 0.0551,
|
| 144 |
+
"step": 9000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.586506346025384,
|
| 148 |
+
"grad_norm": 9.472536087036133,
|
| 149 |
+
"learning_rate": 9.423291026497439e-06,
|
| 150 |
+
"loss": 0.0453,
|
| 151 |
+
"step": 9500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.6700066800267201,
|
| 155 |
+
"grad_norm": 9.246102333068848,
|
| 156 |
+
"learning_rate": 8.8666221331552e-06,
|
| 157 |
+
"loss": 0.047,
|
| 158 |
+
"step": 10000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.753507014028056,
|
| 162 |
+
"grad_norm": 0.15841872990131378,
|
| 163 |
+
"learning_rate": 8.30995323981296e-06,
|
| 164 |
+
"loss": 0.0507,
|
| 165 |
+
"step": 10500
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.8370073480293923,
|
| 169 |
+
"grad_norm": 0.0037080268375575542,
|
| 170 |
+
"learning_rate": 7.75328434647072e-06,
|
| 171 |
+
"loss": 0.0473,
|
| 172 |
+
"step": 11000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.920507682030728,
|
| 176 |
+
"grad_norm": 0.2187177985906601,
|
| 177 |
+
"learning_rate": 7.1966154531284795e-06,
|
| 178 |
+
"loss": 0.0425,
|
| 179 |
+
"step": 11500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.0,
|
| 183 |
+
"eval_f1": 0.9493987975951904,
|
| 184 |
+
"eval_loss": 0.2554616332054138,
|
| 185 |
+
"eval_runtime": 456.0761,
|
| 186 |
+
"eval_samples_per_second": 52.518,
|
| 187 |
+
"eval_steps_per_second": 3.282,
|
| 188 |
+
"step": 11976
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.004008016032064,
|
| 192 |
+
"grad_norm": 0.008010332472622395,
|
| 193 |
+
"learning_rate": 6.63994655978624e-06,
|
| 194 |
+
"loss": 0.0428,
|
| 195 |
+
"step": 12000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.0875083500334,
|
| 199 |
+
"grad_norm": 0.0018331800820305943,
|
| 200 |
+
"learning_rate": 6.083277666443999e-06,
|
| 201 |
+
"loss": 0.0173,
|
| 202 |
+
"step": 12500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.171008684034736,
|
| 206 |
+
"grad_norm": 0.3650914430618286,
|
| 207 |
+
"learning_rate": 5.526608773101759e-06,
|
| 208 |
+
"loss": 0.0222,
|
| 209 |
+
"step": 13000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.2545090180360723,
|
| 213 |
+
"grad_norm": 0.012613438069820404,
|
| 214 |
+
"learning_rate": 4.969939879759519e-06,
|
| 215 |
+
"loss": 0.0243,
|
| 216 |
+
"step": 13500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.338009352037408,
|
| 220 |
+
"grad_norm": 0.005795360077172518,
|
| 221 |
+
"learning_rate": 4.41327098641728e-06,
|
| 222 |
+
"loss": 0.0235,
|
| 223 |
+
"step": 14000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.4215096860387444,
|
| 227 |
+
"grad_norm": 0.008829685859382153,
|
| 228 |
+
"learning_rate": 3.856602093075039e-06,
|
| 229 |
+
"loss": 0.0219,
|
| 230 |
+
"step": 14500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.50501002004008,
|
| 234 |
+
"grad_norm": 0.44782987236976624,
|
| 235 |
+
"learning_rate": 3.2999331997327993e-06,
|
| 236 |
+
"loss": 0.0197,
|
| 237 |
+
"step": 15000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.588510354041416,
|
| 241 |
+
"grad_norm": 0.39951595664024353,
|
| 242 |
+
"learning_rate": 2.743264306390559e-06,
|
| 243 |
+
"loss": 0.0233,
|
| 244 |
+
"step": 15500
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.6720106880427523,
|
| 248 |
+
"grad_norm": 0.007351418025791645,
|
| 249 |
+
"learning_rate": 2.186595413048319e-06,
|
| 250 |
+
"loss": 0.0184,
|
| 251 |
+
"step": 16000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.755511022044088,
|
| 255 |
+
"grad_norm": 0.001717477454803884,
|
| 256 |
+
"learning_rate": 1.629926519706079e-06,
|
| 257 |
+
"loss": 0.0166,
|
| 258 |
+
"step": 16500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.8390113560454244,
|
| 262 |
+
"grad_norm": 0.0019090324640274048,
|
| 263 |
+
"learning_rate": 1.073257626363839e-06,
|
| 264 |
+
"loss": 0.0136,
|
| 265 |
+
"step": 17000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.9225116900467603,
|
| 269 |
+
"grad_norm": 0.0018055830150842667,
|
| 270 |
+
"learning_rate": 5.165887330215988e-07,
|
| 271 |
+
"loss": 0.0154,
|
| 272 |
+
"step": 17500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.0,
|
| 276 |
+
"eval_f1": 0.9534485637942551,
|
| 277 |
+
"eval_loss": 0.26986005902290344,
|
| 278 |
+
"eval_runtime": 456.6331,
|
| 279 |
+
"eval_samples_per_second": 52.453,
|
| 280 |
+
"eval_steps_per_second": 3.278,
|
| 281 |
+
"step": 17964
|
| 282 |
+
}
|
| 283 |
+
],
|
| 284 |
+
"logging_steps": 500,
|
| 285 |
+
"max_steps": 17964,
|
| 286 |
+
"num_input_tokens_seen": 0,
|
| 287 |
+
"num_train_epochs": 3,
|
| 288 |
+
"save_steps": 500,
|
| 289 |
+
"stateful_callbacks": {
|
| 290 |
+
"TrainerControl": {
|
| 291 |
+
"args": {
|
| 292 |
+
"should_epoch_stop": false,
|
| 293 |
+
"should_evaluate": false,
|
| 294 |
+
"should_log": false,
|
| 295 |
+
"should_save": true,
|
| 296 |
+
"should_training_stop": true
|
| 297 |
+
},
|
| 298 |
+
"attributes": {}
|
| 299 |
+
}
|
| 300 |
+
},
|
| 301 |
+
"total_flos": 7.559459353767072e+16,
|
| 302 |
+
"train_batch_size": 16,
|
| 303 |
+
"trial_name": null,
|
| 304 |
+
"trial_params": null
|
| 305 |
+
}
|
all-mpnet-base-v2/subtaskA/0/checkpoint-17964/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28cbdde62fbb653885701d73afa3dca89af181e42a6555099a9913e54638c7f9
|
| 3 |
+
size 5432
|
all-mpnet-base-v2/subtaskA/0/checkpoint-17964/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
all-mpnet-base-v2/subtaskA/0/checkpoint-5988/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sentence-transformers/all-mpnet-base-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MPNetForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "human",
|
| 14 |
+
"1": "machine"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"human": 0,
|
| 20 |
+
"machine": 1
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-05,
|
| 23 |
+
"max_position_embeddings": 514,
|
| 24 |
+
"model_type": "mpnet",
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"pad_token_id": 1,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"relative_attention_num_buckets": 32,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.47.0",
|
| 32 |
+
"vocab_size": 30527
|
| 33 |
+
}
|
all-mpnet-base-v2/subtaskA/0/checkpoint-5988/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cba62768b49d0b384168db4597814c2e2c93830870dcd33f270d71d825cce0e4
|
| 3 |
+
size 437975200
|
all-mpnet-base-v2/subtaskA/0/checkpoint-5988/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64533a05e62f1198834ce40a288a35fa8f9d010cff0b046d6ef02fed59b9e76e
|
| 3 |
+
size 876072122
|
all-mpnet-base-v2/subtaskA/0/checkpoint-5988/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0637236a8fd4143675655f8380f80997921353f4d652b936cf1a24ff1d0c68f
|
| 3 |
+
size 14244
|
all-mpnet-base-v2/subtaskA/0/checkpoint-5988/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2353e592b4c15a14108650654598f64c876dbf876ecb36772fd6a6a782491504
|
| 3 |
+
size 1064
|
all-mpnet-base-v2/subtaskA/0/checkpoint-5988/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
all-mpnet-base-v2/subtaskA/0/checkpoint-5988/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
all-mpnet-base-v2/subtaskA/0/checkpoint-5988/tokenizer_config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"104": {
|
| 36 |
+
"content": "[UNK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"30526": {
|
| 44 |
+
"content": "<mask>",
|
| 45 |
+
"lstrip": true,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "<s>",
|
| 53 |
+
"clean_up_tokenization_spaces": false,
|
| 54 |
+
"cls_token": "<s>",
|
| 55 |
+
"do_lower_case": true,
|
| 56 |
+
"eos_token": "</s>",
|
| 57 |
+
"extra_special_tokens": {},
|
| 58 |
+
"mask_token": "<mask>",
|
| 59 |
+
"max_length": 128,
|
| 60 |
+
"model_max_length": 512,
|
| 61 |
+
"pad_to_multiple_of": null,
|
| 62 |
+
"pad_token": "<pad>",
|
| 63 |
+
"pad_token_type_id": 0,
|
| 64 |
+
"padding_side": "right",
|
| 65 |
+
"sep_token": "</s>",
|
| 66 |
+
"stride": 0,
|
| 67 |
+
"strip_accents": null,
|
| 68 |
+
"tokenize_chinese_chars": true,
|
| 69 |
+
"tokenizer_class": "MPNetTokenizer",
|
| 70 |
+
"truncation_side": "right",
|
| 71 |
+
"truncation_strategy": "longest_first",
|
| 72 |
+
"unk_token": "[UNK]"
|
| 73 |
+
}
|
all-mpnet-base-v2/subtaskA/0/checkpoint-5988/trainer_state.json
ADDED
|
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.1430160403251648,
|
| 3 |
+
"best_model_checkpoint": "/kaggle/working//model_sentence-transformers/all-mpnet-base-v2/subtaskA/0/checkpoint-5988",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5988,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08350033400133601,
|
| 13 |
+
"grad_norm": 2.628113031387329,
|
| 14 |
+
"learning_rate": 1.944333110665776e-05,
|
| 15 |
+
"loss": 0.3143,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16700066800267202,
|
| 20 |
+
"grad_norm": 6.473922252655029,
|
| 21 |
+
"learning_rate": 1.888666221331552e-05,
|
| 22 |
+
"loss": 0.1553,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.250501002004008,
|
| 27 |
+
"grad_norm": 0.41650745272636414,
|
| 28 |
+
"learning_rate": 1.832999331997328e-05,
|
| 29 |
+
"loss": 0.1391,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.33400133600534404,
|
| 34 |
+
"grad_norm": 0.04540203511714935,
|
| 35 |
+
"learning_rate": 1.777332442663104e-05,
|
| 36 |
+
"loss": 0.1169,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.41750167000668004,
|
| 41 |
+
"grad_norm": 24.253005981445312,
|
| 42 |
+
"learning_rate": 1.72166555332888e-05,
|
| 43 |
+
"loss": 0.1199,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.501002004008016,
|
| 48 |
+
"grad_norm": 0.035162102431058884,
|
| 49 |
+
"learning_rate": 1.6659986639946563e-05,
|
| 50 |
+
"loss": 0.1105,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.584502338009352,
|
| 55 |
+
"grad_norm": 10.076239585876465,
|
| 56 |
+
"learning_rate": 1.6103317746604322e-05,
|
| 57 |
+
"loss": 0.1009,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6680026720106881,
|
| 62 |
+
"grad_norm": 1.568239450454712,
|
| 63 |
+
"learning_rate": 1.554664885326208e-05,
|
| 64 |
+
"loss": 0.1025,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.751503006012024,
|
| 69 |
+
"grad_norm": 11.781553268432617,
|
| 70 |
+
"learning_rate": 1.498997995991984e-05,
|
| 71 |
+
"loss": 0.0878,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8350033400133601,
|
| 76 |
+
"grad_norm": 0.042673539370298386,
|
| 77 |
+
"learning_rate": 1.44333110665776e-05,
|
| 78 |
+
"loss": 0.0931,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.918503674014696,
|
| 83 |
+
"grad_norm": 3.912463426589966,
|
| 84 |
+
"learning_rate": 1.3876642173235361e-05,
|
| 85 |
+
"loss": 0.0812,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0,
|
| 90 |
+
"eval_f1": 0.956496325985304,
|
| 91 |
+
"eval_loss": 0.1430160403251648,
|
| 92 |
+
"eval_runtime": 459.2333,
|
| 93 |
+
"eval_samples_per_second": 52.156,
|
| 94 |
+
"eval_steps_per_second": 3.26,
|
| 95 |
+
"step": 5988
|
| 96 |
+
}
|
| 97 |
+
],
|
| 98 |
+
"logging_steps": 500,
|
| 99 |
+
"max_steps": 17964,
|
| 100 |
+
"num_input_tokens_seen": 0,
|
| 101 |
+
"num_train_epochs": 3,
|
| 102 |
+
"save_steps": 500,
|
| 103 |
+
"stateful_callbacks": {
|
| 104 |
+
"TrainerControl": {
|
| 105 |
+
"args": {
|
| 106 |
+
"should_epoch_stop": false,
|
| 107 |
+
"should_evaluate": false,
|
| 108 |
+
"should_log": false,
|
| 109 |
+
"should_save": true,
|
| 110 |
+
"should_training_stop": false
|
| 111 |
+
},
|
| 112 |
+
"attributes": {}
|
| 113 |
+
}
|
| 114 |
+
},
|
| 115 |
+
"total_flos": 2.519807177184288e+16,
|
| 116 |
+
"train_batch_size": 16,
|
| 117 |
+
"trial_name": null,
|
| 118 |
+
"trial_params": null
|
| 119 |
+
}
|
all-mpnet-base-v2/subtaskA/0/checkpoint-5988/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28cbdde62fbb653885701d73afa3dca89af181e42a6555099a9913e54638c7f9
|
| 3 |
+
size 5432
|
all-mpnet-base-v2/subtaskA/0/checkpoint-5988/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|