ana-grassmann
commited on
Commit
•
ad30db3
1
Parent(s):
9ee7907
Training in progress, epoch 2
Browse files- model.safetensors +1 -1
- run-2/checkpoint-157/config.json +27 -0
- run-2/checkpoint-157/model.safetensors +3 -0
- run-2/checkpoint-157/optimizer.pt +3 -0
- run-2/checkpoint-157/rng_state.pth +3 -0
- run-2/checkpoint-157/scheduler.pt +3 -0
- run-2/checkpoint-157/special_tokens_map.json +7 -0
- run-2/checkpoint-157/tokenizer.json +0 -0
- run-2/checkpoint-157/tokenizer_config.json +55 -0
- run-2/checkpoint-157/trainer_state.json +53 -0
- run-2/checkpoint-157/training_args.bin +3 -0
- run-2/checkpoint-157/vocab.txt +0 -0
- runs/Apr14_18-31-48_6ec9497f7a76/events.out.tfevents.1713120899.6ec9497f7a76.2144.2 +2 -2
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:a6bc46733237ac944dc44623c146016d3d1e41b375fc5646b4157890c4392eff
|
3 |
size 437958648
|
run-2/checkpoint-157/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": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
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-2/checkpoint-157/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6bc46733237ac944dc44623c146016d3d1e41b375fc5646b4157890c4392eff
|
3 |
+
size 437958648
|
run-2/checkpoint-157/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:432049c96f1c86c26c4f12a55feab772af0ddb24c55c54482d7d9eb8ac0c2888
|
3 |
+
size 876038394
|
run-2/checkpoint-157/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a71ba6580bcc2449d186726bb4ff0a19560603a167232b7333c671698a6fdddc
|
3 |
+
size 14244
|
run-2/checkpoint-157/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:334cc04cf5ab76a2a2261e95f5e21a42ea16c101f856eb6f459e29d5ca887ffb
|
3 |
+
size 1064
|
run-2/checkpoint-157/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-2/checkpoint-157/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-157/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-2/checkpoint-157/trainer_state.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9808268424206111,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-2/checkpoint-105",
|
4 |
+
"epoch": 2.9904761904761905,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 157,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.99,
|
13 |
+
"eval_accuracy": 0.9720191731575794,
|
14 |
+
"eval_loss": 0.08049887418746948,
|
15 |
+
"eval_runtime": 129.4849,
|
16 |
+
"eval_samples_per_second": 128.895,
|
17 |
+
"eval_steps_per_second": 16.118,
|
18 |
+
"step": 52
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.9808268424206111,
|
23 |
+
"eval_loss": 0.0663532018661499,
|
24 |
+
"eval_runtime": 129.584,
|
25 |
+
"eval_samples_per_second": 128.797,
|
26 |
+
"eval_steps_per_second": 16.105,
|
27 |
+
"step": 105
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.99,
|
31 |
+
"eval_accuracy": 0.9679448771719592,
|
32 |
+
"eval_loss": 0.11977529525756836,
|
33 |
+
"eval_runtime": 129.6054,
|
34 |
+
"eval_samples_per_second": 128.776,
|
35 |
+
"eval_steps_per_second": 16.103,
|
36 |
+
"step": 157
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"logging_steps": 500,
|
40 |
+
"max_steps": 208,
|
41 |
+
"num_input_tokens_seen": 0,
|
42 |
+
"num_train_epochs": 4,
|
43 |
+
"save_steps": 500,
|
44 |
+
"total_flos": 0,
|
45 |
+
"train_batch_size": 32,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": {
|
48 |
+
"learning_rate": 3.848744961833747e-05,
|
49 |
+
"num_train_epochs": 4,
|
50 |
+
"per_device_train_batch_size": 32,
|
51 |
+
"seed": 40
|
52 |
+
}
|
53 |
+
}
|
run-2/checkpoint-157/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f83691e4cee6baa5a8511f8f79336b31f5cd88f53b70ea13a4b286e00edbb6da
|
3 |
+
size 4920
|
run-2/checkpoint-157/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Apr14_18-31-48_6ec9497f7a76/events.out.tfevents.1713120899.6ec9497f7a76.2144.2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd2d5737dcff6f013493722c074dacb4d67708f6adae0f00e07ee311c7cdb89f
|
3 |
+
size 5595
|