Training in progress, epoch 2
Browse files- model.safetensors +1 -1
- run-0/checkpoint-536/config.json +25 -0
- run-0/checkpoint-536/model.safetensors +3 -0
- run-0/checkpoint-536/optimizer.pt +3 -0
- run-0/checkpoint-536/rng_state.pth +3 -0
- run-0/checkpoint-536/scheduler.pt +3 -0
- run-0/checkpoint-536/special_tokens_map.json +7 -0
- run-0/checkpoint-536/tokenizer.json +0 -0
- run-0/checkpoint-536/tokenizer_config.json +55 -0
- run-0/checkpoint-536/trainer_state.json +51 -0
- run-0/checkpoint-536/training_args.bin +3 -0
- run-0/checkpoint-536/vocab.txt +0 -0
- runs/Apr05_13-35-05_48c5213de69d/events.out.tfevents.1712324929.48c5213de69d.790.2 +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 sha256:5386555c23a3845ebed14108419d4c40442962dff0e8f0c3c2adccae7ef8d069
|
3 |
size 267832560
|
run-0/checkpoint-536/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": "4.39.3",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-0/checkpoint-536/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5386555c23a3845ebed14108419d4c40442962dff0e8f0c3c2adccae7ef8d069
|
3 |
+
size 267832560
|
run-0/checkpoint-536/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba5048653cea997fc66740ad8c3182caea5dba515b40df4cce6ac57b90eda46c
|
3 |
+
size 535727290
|
run-0/checkpoint-536/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f827f37a1c9c2084582a7eebf927c4456d10117d230821f32569b32524a79921
|
3 |
+
size 14244
|
run-0/checkpoint-536/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:432f41fd2b6c42dd373353006f4bf55930d7735fb4d57b5ee114989a0bd8a061
|
3 |
+
size 1064
|
run-0/checkpoint-536/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-0/checkpoint-536/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-536/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-0/checkpoint-536/trainer_state.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.44944855113368687,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-536",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 536,
|
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": 0.5017370581626892,
|
14 |
+
"eval_matthews_correlation": 0.4386209168112411,
|
15 |
+
"eval_runtime": 0.9474,
|
16 |
+
"eval_samples_per_second": 1100.94,
|
17 |
+
"eval_steps_per_second": 69.666,
|
18 |
+
"step": 268
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.87,
|
22 |
+
"grad_norm": 9.115137100219727,
|
23 |
+
"learning_rate": 1.255312161688088e-06,
|
24 |
+
"loss": 0.4596,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_loss": 0.506603479385376,
|
30 |
+
"eval_matthews_correlation": 0.44944855113368687,
|
31 |
+
"eval_runtime": 0.7486,
|
32 |
+
"eval_samples_per_second": 1393.184,
|
33 |
+
"eval_steps_per_second": 88.159,
|
34 |
+
"step": 536
|
35 |
+
}
|
36 |
+
],
|
37 |
+
"logging_steps": 500,
|
38 |
+
"max_steps": 536,
|
39 |
+
"num_input_tokens_seen": 0,
|
40 |
+
"num_train_epochs": 2,
|
41 |
+
"save_steps": 500,
|
42 |
+
"total_flos": 95049498141888.0,
|
43 |
+
"train_batch_size": 32,
|
44 |
+
"trial_name": null,
|
45 |
+
"trial_params": {
|
46 |
+
"learning_rate": 1.8690203296244868e-05,
|
47 |
+
"num_train_epochs": 2,
|
48 |
+
"per_device_train_batch_size": 32,
|
49 |
+
"seed": 15
|
50 |
+
}
|
51 |
+
}
|
run-0/checkpoint-536/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:336fcd2eac216245af8a43eb6ce3300c8207fb1556028581e1cfb293d1259711
|
3 |
+
size 4984
|
run-0/checkpoint-536/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Apr05_13-35-05_48c5213de69d/events.out.tfevents.1712324929.48c5213de69d.790.2
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 sha256:8f225ef593f792719fb7cf4043e01ee62bac9eebd2b96128a96b74b1ffeff670
|
3 |
+
size 5829
|