Training in progress, epoch 1
Browse files- logs/events.out.tfevents.1702277265.joseph_legion.22340.18 +3 -0
- model.safetensors +1 -1
- run-5/checkpoint-197/config.json +34 -0
- run-5/checkpoint-197/model.safetensors +3 -0
- run-5/checkpoint-197/optimizer.pt +3 -0
- run-5/checkpoint-197/rng_state.pth +3 -0
- run-5/checkpoint-197/scheduler.pt +3 -0
- run-5/checkpoint-197/special_tokens_map.json +7 -0
- run-5/checkpoint-197/tokenizer_config.json +57 -0
- run-5/checkpoint-197/trainer_state.json +40 -0
- run-5/checkpoint-197/training_args.bin +3 -0
- run-5/checkpoint-197/vocab.txt +0 -0
- training_args.bin +1 -1
logs/events.out.tfevents.1702277265.joseph_legion.22340.18
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84de3c5d48a9c42b1d7435c1271ab6876d28d44cbfc97eee25fd1e21409ed6c4
|
3 |
+
size 4926
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 44692608
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9ac2ff50bd04bc8ef66ab95e4dc553e2d5f873d7e544379f76efd14636ceb00
|
3 |
size 44692608
|
run-5/checkpoint-197/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 256,
|
11 |
+
"id2label": {
|
12 |
+
"0": 0,
|
13 |
+
"1": 1
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 1024,
|
17 |
+
"label2id": {
|
18 |
+
"0": 0,
|
19 |
+
"1": 1
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "bert",
|
24 |
+
"num_attention_heads": 4,
|
25 |
+
"num_hidden_layers": 4,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.36.0.dev0",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
run-5/checkpoint-197/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9ac2ff50bd04bc8ef66ab95e4dc553e2d5f873d7e544379f76efd14636ceb00
|
3 |
+
size 44692608
|
run-5/checkpoint-197/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a43f4c6172253af87ce4135197354e17ebd174467adf53dd2cc27f82a7925623
|
3 |
+
size 89430010
|
run-5/checkpoint-197/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfce427b13a79881b8dd7c1ca79db1eca136c641f9f35f4f0773c5f01a793672
|
3 |
+
size 14308
|
run-5/checkpoint-197/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccd2c1b20b0193681ba16cbb2c4a2455ecc1c8b6d7ffde4f1012a27dddc506cf
|
3 |
+
size 1064
|
run-5/checkpoint-197/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-5/checkpoint-197/tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
run-5/checkpoint-197/trainer_state.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7540300166759311,
|
3 |
+
"best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-5\\checkpoint-197",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 197,
|
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 |
+
"learning_rate": 4.941433573951871e-06,
|
14 |
+
"loss": 0.3472,
|
15 |
+
"step": 197
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_accuracy": 0.7540300166759311,
|
20 |
+
"eval_loss": 0.3264233469963074,
|
21 |
+
"eval_runtime": 125.6102,
|
22 |
+
"eval_samples_per_second": 57.288,
|
23 |
+
"eval_steps_per_second": 0.454,
|
24 |
+
"step": 197
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"logging_steps": 500,
|
28 |
+
"max_steps": 1379,
|
29 |
+
"num_input_tokens_seen": 0,
|
30 |
+
"num_train_epochs": 7,
|
31 |
+
"save_steps": 500,
|
32 |
+
"total_flos": 44298765947484.0,
|
33 |
+
"trial_name": null,
|
34 |
+
"trial_params": {
|
35 |
+
"alpha": 0.5501861057464915,
|
36 |
+
"learning_rate": 5.7650058362771825e-06,
|
37 |
+
"num_train_epochs": 7,
|
38 |
+
"temperature": 15
|
39 |
+
}
|
40 |
+
}
|
run-5/checkpoint-197/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28cc7611006f792e9dd8ff296313a535b356cc6a1bb6db2c1180dd69535d0c93
|
3 |
+
size 4792
|
run-5/checkpoint-197/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 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28cc7611006f792e9dd8ff296313a535b356cc6a1bb6db2c1180dd69535d0c93
|
3 |
size 4792
|