Training in progress, step 500
Browse files- model.safetensors +1 -1
- run-797xqzmq/checkpoint-1000/config.json +36 -0
- run-797xqzmq/checkpoint-1000/model.safetensors +3 -0
- run-797xqzmq/checkpoint-1000/optimizer.pt +3 -0
- run-797xqzmq/checkpoint-1000/rng_state.pth +3 -0
- run-797xqzmq/checkpoint-1000/scheduler.pt +3 -0
- run-797xqzmq/checkpoint-1000/special_tokens_map.json +7 -0
- run-797xqzmq/checkpoint-1000/tokenizer.json +0 -0
- run-797xqzmq/checkpoint-1000/tokenizer_config.json +55 -0
- run-797xqzmq/checkpoint-1000/trainer_state.json +95 -0
- run-797xqzmq/checkpoint-1000/training_args.bin +3 -0
- run-797xqzmq/checkpoint-1000/vocab.txt +0 -0
- run-797xqzmq/checkpoint-1500/config.json +36 -0
- run-797xqzmq/checkpoint-1500/model.safetensors +3 -0
- run-797xqzmq/checkpoint-1500/optimizer.pt +3 -0
- run-797xqzmq/checkpoint-1500/rng_state.pth +3 -0
- run-797xqzmq/checkpoint-1500/scheduler.pt +3 -0
- run-797xqzmq/checkpoint-1500/special_tokens_map.json +7 -0
- run-797xqzmq/checkpoint-1500/tokenizer.json +0 -0
- run-797xqzmq/checkpoint-1500/tokenizer_config.json +55 -0
- run-797xqzmq/checkpoint-1500/trainer_state.json +116 -0
- run-797xqzmq/checkpoint-1500/training_args.bin +3 -0
- run-797xqzmq/checkpoint-1500/vocab.txt +0 -0
- run-zhekmzi0/checkpoint-500/config.json +36 -0
- run-zhekmzi0/checkpoint-500/model.safetensors +3 -0
- run-zhekmzi0/checkpoint-500/optimizer.pt +3 -0
- run-zhekmzi0/checkpoint-500/rng_state.pth +3 -0
- run-zhekmzi0/checkpoint-500/scheduler.pt +3 -0
- run-zhekmzi0/checkpoint-500/special_tokens_map.json +7 -0
- run-zhekmzi0/checkpoint-500/tokenizer.json +0 -0
- run-zhekmzi0/checkpoint-500/tokenizer_config.json +55 -0
- run-zhekmzi0/checkpoint-500/trainer_state.json +60 -0
- run-zhekmzi0/checkpoint-500/training_args.bin +3 -0
- run-zhekmzi0/checkpoint-500/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 430911284
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:637071f6b94ca4846fdb162f4d57f6c6e63a66b4ea34a374baf7e778c56adfa2
|
3 |
size 430911284
|
run-797xqzmq/checkpoint-1000/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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": "O",
|
14 |
+
"1": "I-S",
|
15 |
+
"2": "B-S"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"B-S": 2,
|
21 |
+
"I-S": 1,
|
22 |
+
"O": 0
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.41.1",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 28996
|
36 |
+
}
|
run-797xqzmq/checkpoint-1000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0155bcffbbe6c3cbfb7145a28d0bac7a5d915b54dd57f1fe25d3578e7497d38d
|
3 |
+
size 430911284
|
run-797xqzmq/checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccb6626b0e9a6948a42e5cecd4aa621069ea6705566aa80e89c459aa62bd28c7
|
3 |
+
size 861942330
|
run-797xqzmq/checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a6506071cda30ec363ad5c19299436106e9bc716569a13a88656f006a4610af
|
3 |
+
size 14244
|
run-797xqzmq/checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8817b5054667784af48d9e26890ad2db76283eee4da6599cf860dfd5afcb8e19
|
3 |
+
size 1064
|
run-797xqzmq/checkpoint-1000/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-797xqzmq/checkpoint-1000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-797xqzmq/checkpoint-1000/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": false,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-797xqzmq/checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.2679738562091503,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
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_f1": 0.381578947368421,
|
14 |
+
"eval_f1_sklearn": 0.9460166282836957,
|
15 |
+
"eval_loss": 0.1464981883764267,
|
16 |
+
"eval_precision": 0.45609436435124506,
|
17 |
+
"eval_precision_sklearn": 0.9460166282836957,
|
18 |
+
"eval_recall": 0.32799245994344955,
|
19 |
+
"eval_recall_sklearn": 0.9460166282836957,
|
20 |
+
"eval_runtime": 4.8912,
|
21 |
+
"eval_samples_per_second": 83.415,
|
22 |
+
"eval_steps_per_second": 20.854,
|
23 |
+
"step": 306
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.6339869281045751,
|
27 |
+
"grad_norm": 5.414730072021484,
|
28 |
+
"learning_rate": 3.3660130718954253e-06,
|
29 |
+
"loss": 0.1668,
|
30 |
+
"step": 500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_f1": 0.4384873145045477,
|
35 |
+
"eval_f1_sklearn": 0.9487099418400406,
|
36 |
+
"eval_loss": 0.1396203637123108,
|
37 |
+
"eval_precision": 0.4455252918287938,
|
38 |
+
"eval_precision_sklearn": 0.9487099418400406,
|
39 |
+
"eval_recall": 0.43166823751178135,
|
40 |
+
"eval_recall_sklearn": 0.9487099418400406,
|
41 |
+
"eval_runtime": 4.6437,
|
42 |
+
"eval_samples_per_second": 87.86,
|
43 |
+
"eval_steps_per_second": 21.965,
|
44 |
+
"step": 612
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_f1": 0.49019607843137253,
|
49 |
+
"eval_f1_sklearn": 0.9503103165619267,
|
50 |
+
"eval_loss": 0.14265619218349457,
|
51 |
+
"eval_precision": 0.46491969568892644,
|
52 |
+
"eval_precision_sklearn": 0.9503103165619267,
|
53 |
+
"eval_recall": 0.5183788878416589,
|
54 |
+
"eval_recall_sklearn": 0.9503103165619267,
|
55 |
+
"eval_runtime": 4.692,
|
56 |
+
"eval_samples_per_second": 86.957,
|
57 |
+
"eval_steps_per_second": 21.739,
|
58 |
+
"step": 918
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 3.2679738562091503,
|
62 |
+
"grad_norm": 4.938509464263916,
|
63 |
+
"learning_rate": 1.7320261437908499e-06,
|
64 |
+
"loss": 0.0872,
|
65 |
+
"step": 1000
|
66 |
+
}
|
67 |
+
],
|
68 |
+
"logging_steps": 500,
|
69 |
+
"max_steps": 1530,
|
70 |
+
"num_input_tokens_seen": 0,
|
71 |
+
"num_train_epochs": 5,
|
72 |
+
"save_steps": 500,
|
73 |
+
"stateful_callbacks": {
|
74 |
+
"TrainerControl": {
|
75 |
+
"args": {
|
76 |
+
"should_epoch_stop": false,
|
77 |
+
"should_evaluate": false,
|
78 |
+
"should_log": false,
|
79 |
+
"should_save": true,
|
80 |
+
"should_training_stop": false
|
81 |
+
},
|
82 |
+
"attributes": {}
|
83 |
+
}
|
84 |
+
},
|
85 |
+
"total_flos": 318346024442760.0,
|
86 |
+
"train_batch_size": 4,
|
87 |
+
"trial_name": null,
|
88 |
+
"trial_params": {
|
89 |
+
"_wandb": {},
|
90 |
+
"assignments": {},
|
91 |
+
"learning_rate": 5e-06,
|
92 |
+
"metric": "eval/loss",
|
93 |
+
"per_device_train_batch_size": 4
|
94 |
+
}
|
95 |
+
}
|
run-797xqzmq/checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4dd8f94ddd2e13e36e8e4087657740657b7454f82c774d6be138ea401df8b124
|
3 |
+
size 5112
|
run-797xqzmq/checkpoint-1000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-797xqzmq/checkpoint-1500/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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": "O",
|
14 |
+
"1": "I-S",
|
15 |
+
"2": "B-S"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"B-S": 2,
|
21 |
+
"I-S": 1,
|
22 |
+
"O": 0
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.41.1",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 28996
|
36 |
+
}
|
run-797xqzmq/checkpoint-1500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c1cf73a4fadec10e3fedf820eb888ae61fae09daf962133a98d779882663ac6
|
3 |
+
size 430911284
|
run-797xqzmq/checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e5c51969a4269a849df0dd252fb753a27373764e1aadc90a8629a119cd25ce1
|
3 |
+
size 861942330
|
run-797xqzmq/checkpoint-1500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2623190ade7475a14422c6523b005c8acd111f240775a08c6f4ab59256d8d57
|
3 |
+
size 14244
|
run-797xqzmq/checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:001b3e979cb1baf08147a47c664ea53728dbddc6de5c7fa4c4b1a0076090a670
|
3 |
+
size 1064
|
run-797xqzmq/checkpoint-1500/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-797xqzmq/checkpoint-1500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-797xqzmq/checkpoint-1500/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": false,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-797xqzmq/checkpoint-1500/trainer_state.json
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.901960784313726,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1500,
|
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_f1": 0.381578947368421,
|
14 |
+
"eval_f1_sklearn": 0.9460166282836957,
|
15 |
+
"eval_loss": 0.1464981883764267,
|
16 |
+
"eval_precision": 0.45609436435124506,
|
17 |
+
"eval_precision_sklearn": 0.9460166282836957,
|
18 |
+
"eval_recall": 0.32799245994344955,
|
19 |
+
"eval_recall_sklearn": 0.9460166282836957,
|
20 |
+
"eval_runtime": 4.8912,
|
21 |
+
"eval_samples_per_second": 83.415,
|
22 |
+
"eval_steps_per_second": 20.854,
|
23 |
+
"step": 306
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.6339869281045751,
|
27 |
+
"grad_norm": 5.414730072021484,
|
28 |
+
"learning_rate": 3.3660130718954253e-06,
|
29 |
+
"loss": 0.1668,
|
30 |
+
"step": 500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_f1": 0.4384873145045477,
|
35 |
+
"eval_f1_sklearn": 0.9487099418400406,
|
36 |
+
"eval_loss": 0.1396203637123108,
|
37 |
+
"eval_precision": 0.4455252918287938,
|
38 |
+
"eval_precision_sklearn": 0.9487099418400406,
|
39 |
+
"eval_recall": 0.43166823751178135,
|
40 |
+
"eval_recall_sklearn": 0.9487099418400406,
|
41 |
+
"eval_runtime": 4.6437,
|
42 |
+
"eval_samples_per_second": 87.86,
|
43 |
+
"eval_steps_per_second": 21.965,
|
44 |
+
"step": 612
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_f1": 0.49019607843137253,
|
49 |
+
"eval_f1_sklearn": 0.9503103165619267,
|
50 |
+
"eval_loss": 0.14265619218349457,
|
51 |
+
"eval_precision": 0.46491969568892644,
|
52 |
+
"eval_precision_sklearn": 0.9503103165619267,
|
53 |
+
"eval_recall": 0.5183788878416589,
|
54 |
+
"eval_recall_sklearn": 0.9503103165619267,
|
55 |
+
"eval_runtime": 4.692,
|
56 |
+
"eval_samples_per_second": 86.957,
|
57 |
+
"eval_steps_per_second": 21.739,
|
58 |
+
"step": 918
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 3.2679738562091503,
|
62 |
+
"grad_norm": 4.938509464263916,
|
63 |
+
"learning_rate": 1.7320261437908499e-06,
|
64 |
+
"loss": 0.0872,
|
65 |
+
"step": 1000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 4.0,
|
69 |
+
"eval_f1": 0.503803888419273,
|
70 |
+
"eval_f1_sklearn": 0.9477731371247902,
|
71 |
+
"eval_loss": 0.15120969712734222,
|
72 |
+
"eval_precision": 0.4567049808429119,
|
73 |
+
"eval_precision_sklearn": 0.9477731371247902,
|
74 |
+
"eval_recall": 0.5617342130065975,
|
75 |
+
"eval_recall_sklearn": 0.9477731371247902,
|
76 |
+
"eval_runtime": 6.0205,
|
77 |
+
"eval_samples_per_second": 67.769,
|
78 |
+
"eval_steps_per_second": 16.942,
|
79 |
+
"step": 1224
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 4.901960784313726,
|
83 |
+
"grad_norm": 1.531068205833435,
|
84 |
+
"learning_rate": 9.803921568627452e-08,
|
85 |
+
"loss": 0.0617,
|
86 |
+
"step": 1500
|
87 |
+
}
|
88 |
+
],
|
89 |
+
"logging_steps": 500,
|
90 |
+
"max_steps": 1530,
|
91 |
+
"num_input_tokens_seen": 0,
|
92 |
+
"num_train_epochs": 5,
|
93 |
+
"save_steps": 500,
|
94 |
+
"stateful_callbacks": {
|
95 |
+
"TrainerControl": {
|
96 |
+
"args": {
|
97 |
+
"should_epoch_stop": false,
|
98 |
+
"should_evaluate": false,
|
99 |
+
"should_log": false,
|
100 |
+
"should_save": true,
|
101 |
+
"should_training_stop": false
|
102 |
+
},
|
103 |
+
"attributes": {}
|
104 |
+
}
|
105 |
+
},
|
106 |
+
"total_flos": 470773232452584.0,
|
107 |
+
"train_batch_size": 4,
|
108 |
+
"trial_name": null,
|
109 |
+
"trial_params": {
|
110 |
+
"_wandb": {},
|
111 |
+
"assignments": {},
|
112 |
+
"learning_rate": 5e-06,
|
113 |
+
"metric": "eval/loss",
|
114 |
+
"per_device_train_batch_size": 4
|
115 |
+
}
|
116 |
+
}
|
run-797xqzmq/checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4dd8f94ddd2e13e36e8e4087657740657b7454f82c774d6be138ea401df8b124
|
3 |
+
size 5112
|
run-797xqzmq/checkpoint-1500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-zhekmzi0/checkpoint-500/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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": "O",
|
14 |
+
"1": "I-S",
|
15 |
+
"2": "B-S"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"B-S": 2,
|
21 |
+
"I-S": 1,
|
22 |
+
"O": 0
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.41.1",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 28996
|
36 |
+
}
|
run-zhekmzi0/checkpoint-500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:637071f6b94ca4846fdb162f4d57f6c6e63a66b4ea34a374baf7e778c56adfa2
|
3 |
+
size 430911284
|
run-zhekmzi0/checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0b12b5b2bfcb7d3bc3793d3ca6ccb9df55c4715cacebd136a404c01eed846bc
|
3 |
+
size 861942330
|
run-zhekmzi0/checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4cf6712a80c786c6516b565e21ebf119dfb938fa91f074f5c2e6ac6eb8a3d9f
|
3 |
+
size 14244
|
run-zhekmzi0/checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5323f0063b38e41b8b1d7249d7671d3eef375e28ec9f0547aa5f9ad7614e142d
|
3 |
+
size 1064
|
run-zhekmzi0/checkpoint-500/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-zhekmzi0/checkpoint-500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-zhekmzi0/checkpoint-500/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": false,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-zhekmzi0/checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.6339869281045751,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
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_f1": 0.515569167942828,
|
14 |
+
"eval_f1_sklearn": 0.9512861548069792,
|
15 |
+
"eval_loss": 0.1222936138510704,
|
16 |
+
"eval_precision": 0.5623608017817372,
|
17 |
+
"eval_precision_sklearn": 0.9512861548069792,
|
18 |
+
"eval_recall": 0.4759660697455231,
|
19 |
+
"eval_recall_sklearn": 0.9512861548069792,
|
20 |
+
"eval_runtime": 4.769,
|
21 |
+
"eval_samples_per_second": 85.553,
|
22 |
+
"eval_steps_per_second": 21.388,
|
23 |
+
"step": 306
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.6339869281045751,
|
27 |
+
"grad_norm": 1.8479167222976685,
|
28 |
+
"learning_rate": 6.73202614379085e-05,
|
29 |
+
"loss": 0.1033,
|
30 |
+
"step": 500
|
31 |
+
}
|
32 |
+
],
|
33 |
+
"logging_steps": 500,
|
34 |
+
"max_steps": 1530,
|
35 |
+
"num_input_tokens_seen": 0,
|
36 |
+
"num_train_epochs": 5,
|
37 |
+
"save_steps": 500,
|
38 |
+
"stateful_callbacks": {
|
39 |
+
"TrainerControl": {
|
40 |
+
"args": {
|
41 |
+
"should_epoch_stop": false,
|
42 |
+
"should_evaluate": false,
|
43 |
+
"should_log": false,
|
44 |
+
"should_save": true,
|
45 |
+
"should_training_stop": false
|
46 |
+
},
|
47 |
+
"attributes": {}
|
48 |
+
}
|
49 |
+
},
|
50 |
+
"total_flos": 156577372924968.0,
|
51 |
+
"train_batch_size": 4,
|
52 |
+
"trial_name": null,
|
53 |
+
"trial_params": {
|
54 |
+
"_wandb": {},
|
55 |
+
"assignments": {},
|
56 |
+
"learning_rate": 0.0001,
|
57 |
+
"metric": "eval/loss",
|
58 |
+
"per_device_train_batch_size": 4
|
59 |
+
}
|
60 |
+
}
|
run-zhekmzi0/checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca5e8846bf2c23aa1f92199215b96f27a6aef16cc262f5408c515283e6c3691b
|
3 |
+
size 5112
|
run-zhekmzi0/checkpoint-500/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 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca5e8846bf2c23aa1f92199215b96f27a6aef16cc262f5408c515283e6c3691b
|
3 |
size 5112
|