Training in progress, epoch 4
Browse files- model.safetensors +1 -1
- run-1/checkpoint-216/config.json +25 -0
- run-1/checkpoint-216/model.safetensors +3 -0
- run-1/checkpoint-216/optimizer.pt +3 -0
- run-1/checkpoint-216/rng_state.pth +3 -0
- run-1/checkpoint-216/scheduler.pt +3 -0
- run-1/checkpoint-216/special_tokens_map.json +7 -0
- run-1/checkpoint-216/tokenizer.json +0 -0
- run-1/checkpoint-216/tokenizer_config.json +55 -0
- run-1/checkpoint-216/trainer_state.json +62 -0
- run-1/checkpoint-216/training_args.bin +3 -0
- run-1/checkpoint-216/vocab.txt +0 -0
- runs/Jan26_08-04-50_7ac5f092fd85/events.out.tfevents.1706283789.7ac5f092fd85.1710.5 +2 -2
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7c3eb9e3a3d55b639ba84794b72b17a7bd88ad4d98b09e4af35531ca3c5f046
|
3 |
size 267832560
|
run-1/checkpoint-216/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.37.1",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-1/checkpoint-216/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7c3eb9e3a3d55b639ba84794b72b17a7bd88ad4d98b09e4af35531ca3c5f046
|
3 |
+
size 267832560
|
run-1/checkpoint-216/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d72450b324ec4807f57b7543628697dee6786ea1f8e50d5be5d19f3faae7c1b5
|
3 |
+
size 535724410
|
run-1/checkpoint-216/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f73e6fc59b3306d5d7841b7ebaacf21065007f35e86d24f7c5d9259aaab475c3
|
3 |
+
size 13990
|
run-1/checkpoint-216/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdc766fe5d663ab5cb83956e1dcc9adc941d3190d3e007429f0f0c273cfbb9ea
|
3 |
+
size 1064
|
run-1/checkpoint-216/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-1/checkpoint-216/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-216/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": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-1/checkpoint-216/trainer_state.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.31087774676686925,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-216",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 216,
|
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_loss": 0.5931112766265869,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 30.6162,
|
16 |
+
"eval_samples_per_second": 34.067,
|
17 |
+
"eval_steps_per_second": 2.156,
|
18 |
+
"step": 54
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.556400716304779,
|
23 |
+
"eval_matthews_correlation": 0.25285211471364255,
|
24 |
+
"eval_runtime": 30.8319,
|
25 |
+
"eval_samples_per_second": 33.829,
|
26 |
+
"eval_steps_per_second": 2.141,
|
27 |
+
"step": 108
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.561941921710968,
|
32 |
+
"eval_matthews_correlation": 0.31016392231638445,
|
33 |
+
"eval_runtime": 30.9625,
|
34 |
+
"eval_samples_per_second": 33.686,
|
35 |
+
"eval_steps_per_second": 2.132,
|
36 |
+
"step": 162
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_loss": 0.5864373445510864,
|
41 |
+
"eval_matthews_correlation": 0.31087774676686925,
|
42 |
+
"eval_runtime": 37.4586,
|
43 |
+
"eval_samples_per_second": 27.844,
|
44 |
+
"eval_steps_per_second": 1.762,
|
45 |
+
"step": 216
|
46 |
+
}
|
47 |
+
],
|
48 |
+
"logging_steps": 500,
|
49 |
+
"max_steps": 216,
|
50 |
+
"num_input_tokens_seen": 0,
|
51 |
+
"num_train_epochs": 4,
|
52 |
+
"save_steps": 500,
|
53 |
+
"total_flos": 0,
|
54 |
+
"train_batch_size": 16,
|
55 |
+
"trial_name": null,
|
56 |
+
"trial_params": {
|
57 |
+
"learning_rate": 1.7766946372870676e-05,
|
58 |
+
"num_train_epochs": 4,
|
59 |
+
"per_device_train_batch_size": 16,
|
60 |
+
"seed": 23
|
61 |
+
}
|
62 |
+
}
|
run-1/checkpoint-216/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02704f8f4bf0ed2b371cb83cfa9d1a20fd4bc70307b6bbf4e9b3f48403165e54
|
3 |
+
size 4792
|
run-1/checkpoint-216/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Jan26_08-04-50_7ac5f092fd85/events.out.tfevents.1706283789.7ac5f092fd85.1710.5
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 sha256:287870595d89eeb17c427f552fcb76bd025afc3f6517199bd70b49b2b4740dc6
|
3 |
+
size 6014
|