Tech-oriented
commited on
Commit
•
a36afc9
1
Parent(s):
431242a
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-6/checkpoint-211/config.json +27 -0
- run-6/checkpoint-211/model.safetensors +3 -0
- run-6/checkpoint-211/optimizer.pt +3 -0
- run-6/checkpoint-211/rng_state.pth +3 -0
- run-6/checkpoint-211/scheduler.pt +3 -0
- run-6/checkpoint-211/special_tokens_map.json +7 -0
- run-6/checkpoint-211/tokenizer.json +0 -0
- run-6/checkpoint-211/tokenizer_config.json +55 -0
- run-6/checkpoint-211/trainer_state.json +36 -0
- run-6/checkpoint-211/training_args.bin +3 -0
- run-6/checkpoint-211/vocab.txt +0 -0
- runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709653115.9d72474d753b.33271.6 +3 -0
- runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709653247.9d72474d753b.33271.7 +3 -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 437958648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44ba4a73a1a6db121a171990bfc4e5f4a58ae75f23bcb6104548cd2d3b4db41f
|
3 |
size 437958648
|
run-6/checkpoint-211/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.3,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.3,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
run-6/checkpoint-211/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44ba4a73a1a6db121a171990bfc4e5f4a58ae75f23bcb6104548cd2d3b4db41f
|
3 |
+
size 437958648
|
run-6/checkpoint-211/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df2fb018705deefcfb142ad93ff2a725eaec7c6d67ad7290714629cf1116b6f8
|
3 |
+
size 876038394
|
run-6/checkpoint-211/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88f32836b6ec42796af79c34c405c939c727f21fb5dbdf6b6ea1890e0b52c4c8
|
3 |
+
size 14244
|
run-6/checkpoint-211/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:063b41872d3fba532f674b9b8a80c1525d380814212bfddbee203f46ed0c4491
|
3 |
+
size 1064
|
run-6/checkpoint-211/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-6/checkpoint-211/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-6/checkpoint-211/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": true,
|
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-6/checkpoint-211/trainer_state.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7912844036697247,
|
3 |
+
"best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-6/checkpoint-211",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 211,
|
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": 0.7912844036697247,
|
14 |
+
"eval_loss": 0.601198136806488,
|
15 |
+
"eval_runtime": 2.3532,
|
16 |
+
"eval_samples_per_second": 370.566,
|
17 |
+
"eval_steps_per_second": 23.373,
|
18 |
+
"step": 211
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 4209,
|
22 |
+
"max_steps": 633,
|
23 |
+
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 3,
|
25 |
+
"save_steps": 500,
|
26 |
+
"total_flos": 0,
|
27 |
+
"train_batch_size": 32,
|
28 |
+
"trial_name": null,
|
29 |
+
"trial_params": {
|
30 |
+
"learning_rate": 5.0863520721840915e-06,
|
31 |
+
"num_train_epochs": 3,
|
32 |
+
"per_device_train_batch_size": 32,
|
33 |
+
"seed": 1,
|
34 |
+
"weight_decay": 0.2453037416510182
|
35 |
+
}
|
36 |
+
}
|
run-6/checkpoint-211/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6aab0ec7dd284e071e10bb2a680fcd747a52e98f49e19609a2cef23d3c8ba02
|
3 |
+
size 4984
|
run-6/checkpoint-211/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709653115.9d72474d753b.33271.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8446d91c631d88fc5d8165f6af7f218eeb5f4807b0b962ea82ff93de99d6ebec
|
3 |
+
size 5071
|
runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709653247.9d72474d753b.33271.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a840352fce6a914695c80ab01347ea7e54139b93b4024c8649942f378dd7ebe4
|
3 |
+
size 5073
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6aab0ec7dd284e071e10bb2a680fcd747a52e98f49e19609a2cef23d3c8ba02
|
3 |
size 4984
|