Tech-oriented
commited on
Commit
•
5fcfeac
1
Parent(s):
d704f25
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-13/checkpoint-422/config.json +27 -0
- run-13/checkpoint-422/model.safetensors +3 -0
- run-13/checkpoint-422/optimizer.pt +3 -0
- run-13/checkpoint-422/rng_state.pth +3 -0
- run-13/checkpoint-422/scheduler.pt +3 -0
- run-13/checkpoint-422/special_tokens_map.json +7 -0
- run-13/checkpoint-422/tokenizer.json +0 -0
- run-13/checkpoint-422/tokenizer_config.json +55 -0
- run-13/checkpoint-422/trainer_state.json +44 -0
- run-13/checkpoint-422/training_args.bin +3 -0
- run-13/checkpoint-422/vocab.txt +0 -0
- run-13/checkpoint-633/config.json +27 -0
- run-13/checkpoint-633/model.safetensors +3 -0
- run-13/checkpoint-633/optimizer.pt +3 -0
- run-13/checkpoint-633/rng_state.pth +3 -0
- run-13/checkpoint-633/scheduler.pt +3 -0
- run-13/checkpoint-633/special_tokens_map.json +7 -0
- run-13/checkpoint-633/tokenizer.json +0 -0
- run-13/checkpoint-633/tokenizer_config.json +55 -0
- run-13/checkpoint-633/trainer_state.json +60 -0
- run-13/checkpoint-633/training_args.bin +3 -0
- run-13/checkpoint-633/vocab.txt +0 -0
- run-13/checkpoint-844/config.json +27 -0
- run-13/checkpoint-844/model.safetensors +3 -0
- run-13/checkpoint-844/optimizer.pt +3 -0
- run-13/checkpoint-844/rng_state.pth +3 -0
- run-13/checkpoint-844/scheduler.pt +3 -0
- run-13/checkpoint-844/special_tokens_map.json +7 -0
- run-13/checkpoint-844/tokenizer.json +0 -0
- run-13/checkpoint-844/tokenizer_config.json +55 -0
- run-13/checkpoint-844/trainer_state.json +69 -0
- run-13/checkpoint-844/training_args.bin +3 -0
- run-13/checkpoint-844/vocab.txt +0 -0
- run-14/checkpoint-211/config.json +27 -0
- run-14/checkpoint-211/model.safetensors +3 -0
- run-14/checkpoint-211/optimizer.pt +3 -0
- run-14/checkpoint-211/rng_state.pth +3 -0
- run-14/checkpoint-211/scheduler.pt +3 -0
- run-14/checkpoint-211/special_tokens_map.json +7 -0
- run-14/checkpoint-211/tokenizer.json +0 -0
- run-14/checkpoint-211/tokenizer_config.json +55 -0
- run-14/checkpoint-211/trainer_state.json +35 -0
- run-14/checkpoint-211/training_args.bin +3 -0
- run-14/checkpoint-211/vocab.txt +0 -0
- runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709500313.90708aaa767a.21824.32 +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:a5c5f56d58275b7ca5aff88f4674048359c5ac305e1eccf8dad77e9cf33ce553
|
3 |
size 437958648
|
run-13/checkpoint-422/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-13/checkpoint-422/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a166081f726c60e7ce270a9571877df89562a6c9e608d6bdb1024423f1445956
|
3 |
+
size 437958648
|
run-13/checkpoint-422/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dae477d0dae618c9b9178112f837cd443684f89e055cd3b90612af92175df983
|
3 |
+
size 876038394
|
run-13/checkpoint-422/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d805adbe90e7ac16068e4f1bf4ef628c91c5a4853ffaf76aa988302ea652806
|
3 |
+
size 14244
|
run-13/checkpoint-422/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c5724f4ab43ae045b9d05d4cd732a56ae44a9fd02a17e3b2fddfa56665b29ca
|
3 |
+
size 1064
|
run-13/checkpoint-422/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-13/checkpoint-422/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-13/checkpoint-422/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-13/checkpoint-422/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.911697247706422,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-13/checkpoint-211",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 422,
|
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": 0.911697247706422,
|
14 |
+
"eval_loss": 0.22412490844726562,
|
15 |
+
"eval_runtime": 2.4274,
|
16 |
+
"eval_samples_per_second": 359.236,
|
17 |
+
"eval_steps_per_second": 22.658,
|
18 |
+
"step": 211
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.9105504587155964,
|
23 |
+
"eval_loss": 0.25786927342414856,
|
24 |
+
"eval_runtime": 2.4527,
|
25 |
+
"eval_samples_per_second": 355.532,
|
26 |
+
"eval_steps_per_second": 22.425,
|
27 |
+
"step": 422
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 844,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 4,
|
34 |
+
"save_steps": 500,
|
35 |
+
"total_flos": 0,
|
36 |
+
"train_batch_size": 32,
|
37 |
+
"trial_name": null,
|
38 |
+
"trial_params": {
|
39 |
+
"learning_rate": 5.753483017575571e-05,
|
40 |
+
"num_train_epochs": 4,
|
41 |
+
"per_device_train_batch_size": 32,
|
42 |
+
"seed": 7
|
43 |
+
}
|
44 |
+
}
|
run-13/checkpoint-422/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a51d8d59c5596bf2142132b64ad5dd777499bc79824c005ef44e203b20d6ffa8
|
3 |
+
size 4920
|
run-13/checkpoint-422/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-13/checkpoint-633/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-13/checkpoint-633/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d650b17822a2eb6f49fef3c4f334eb4686f7221f431f842dc6ea1fa8e112f96
|
3 |
+
size 437958648
|
run-13/checkpoint-633/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:383be3c2b1ef6213e415fda9cd8db03dc054de193ec74157f155fb8912b9531e
|
3 |
+
size 876038394
|
run-13/checkpoint-633/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81a5ac9a06f088d39a06f9ff96e4b0ca471a797b92a3103669baac3344b9eade
|
3 |
+
size 14244
|
run-13/checkpoint-633/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf665bcce3c0a7b289ea93338dd12037961f6ae55c0e84e1a92a3ab3f4eb64e2
|
3 |
+
size 1064
|
run-13/checkpoint-633/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-13/checkpoint-633/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-13/checkpoint-633/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-13/checkpoint-633/trainer_state.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9197247706422018,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-13/checkpoint-633",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 633,
|
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": 0.911697247706422,
|
14 |
+
"eval_loss": 0.22412490844726562,
|
15 |
+
"eval_runtime": 2.4274,
|
16 |
+
"eval_samples_per_second": 359.236,
|
17 |
+
"eval_steps_per_second": 22.658,
|
18 |
+
"step": 211
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.9105504587155964,
|
23 |
+
"eval_loss": 0.25786927342414856,
|
24 |
+
"eval_runtime": 2.4527,
|
25 |
+
"eval_samples_per_second": 355.532,
|
26 |
+
"eval_steps_per_second": 22.425,
|
27 |
+
"step": 422
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.37,
|
31 |
+
"grad_norm": 30.697444915771484,
|
32 |
+
"learning_rate": 2.3450215142725074e-05,
|
33 |
+
"loss": 0.2117,
|
34 |
+
"step": 500
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 3.0,
|
38 |
+
"eval_accuracy": 0.9197247706422018,
|
39 |
+
"eval_loss": 0.3487926125526428,
|
40 |
+
"eval_runtime": 2.4283,
|
41 |
+
"eval_samples_per_second": 359.093,
|
42 |
+
"eval_steps_per_second": 22.649,
|
43 |
+
"step": 633
|
44 |
+
}
|
45 |
+
],
|
46 |
+
"logging_steps": 500,
|
47 |
+
"max_steps": 844,
|
48 |
+
"num_input_tokens_seen": 0,
|
49 |
+
"num_train_epochs": 4,
|
50 |
+
"save_steps": 500,
|
51 |
+
"total_flos": 422743410424080.0,
|
52 |
+
"train_batch_size": 32,
|
53 |
+
"trial_name": null,
|
54 |
+
"trial_params": {
|
55 |
+
"learning_rate": 5.753483017575571e-05,
|
56 |
+
"num_train_epochs": 4,
|
57 |
+
"per_device_train_batch_size": 32,
|
58 |
+
"seed": 7
|
59 |
+
}
|
60 |
+
}
|
run-13/checkpoint-633/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a51d8d59c5596bf2142132b64ad5dd777499bc79824c005ef44e203b20d6ffa8
|
3 |
+
size 4920
|
run-13/checkpoint-633/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-13/checkpoint-844/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-13/checkpoint-844/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4c0e6e6301b51a2563c583b09ed430732c2614d43a73e82a0668305ea3f6a9f
|
3 |
+
size 437958648
|
run-13/checkpoint-844/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fb26da2d94e4428c966a745852afe8b658ccfb5646fd6d0570aa178b5be2288
|
3 |
+
size 876038394
|
run-13/checkpoint-844/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77d6fc9cc6f9964c9cf94bd4e40809fd39c631599c8f9284ba3389216ffad037
|
3 |
+
size 14244
|
run-13/checkpoint-844/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3522aed650445a3402dbb983abe91e06027db69f066b5a909efb10ae0fa2f87
|
3 |
+
size 1064
|
run-13/checkpoint-844/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-13/checkpoint-844/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-13/checkpoint-844/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-13/checkpoint-844/trainer_state.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9243119266055045,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-13/checkpoint-844",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 844,
|
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": 0.911697247706422,
|
14 |
+
"eval_loss": 0.22412490844726562,
|
15 |
+
"eval_runtime": 2.4274,
|
16 |
+
"eval_samples_per_second": 359.236,
|
17 |
+
"eval_steps_per_second": 22.658,
|
18 |
+
"step": 211
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.9105504587155964,
|
23 |
+
"eval_loss": 0.25786927342414856,
|
24 |
+
"eval_runtime": 2.4527,
|
25 |
+
"eval_samples_per_second": 355.532,
|
26 |
+
"eval_steps_per_second": 22.425,
|
27 |
+
"step": 422
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.37,
|
31 |
+
"grad_norm": 30.697444915771484,
|
32 |
+
"learning_rate": 2.3450215142725074e-05,
|
33 |
+
"loss": 0.2117,
|
34 |
+
"step": 500
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 3.0,
|
38 |
+
"eval_accuracy": 0.9197247706422018,
|
39 |
+
"eval_loss": 0.3487926125526428,
|
40 |
+
"eval_runtime": 2.4283,
|
41 |
+
"eval_samples_per_second": 359.093,
|
42 |
+
"eval_steps_per_second": 22.649,
|
43 |
+
"step": 633
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 4.0,
|
47 |
+
"eval_accuracy": 0.9243119266055045,
|
48 |
+
"eval_loss": 0.3896058201789856,
|
49 |
+
"eval_runtime": 2.4333,
|
50 |
+
"eval_samples_per_second": 358.356,
|
51 |
+
"eval_steps_per_second": 22.603,
|
52 |
+
"step": 844
|
53 |
+
}
|
54 |
+
],
|
55 |
+
"logging_steps": 500,
|
56 |
+
"max_steps": 844,
|
57 |
+
"num_input_tokens_seen": 0,
|
58 |
+
"num_train_epochs": 4,
|
59 |
+
"save_steps": 500,
|
60 |
+
"total_flos": 422743410424080.0,
|
61 |
+
"train_batch_size": 32,
|
62 |
+
"trial_name": null,
|
63 |
+
"trial_params": {
|
64 |
+
"learning_rate": 5.753483017575571e-05,
|
65 |
+
"num_train_epochs": 4,
|
66 |
+
"per_device_train_batch_size": 32,
|
67 |
+
"seed": 7
|
68 |
+
}
|
69 |
+
}
|
run-13/checkpoint-844/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a51d8d59c5596bf2142132b64ad5dd777499bc79824c005ef44e203b20d6ffa8
|
3 |
+
size 4920
|
run-13/checkpoint-844/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-14/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": 0.1,
|
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-14/checkpoint-211/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5c5f56d58275b7ca5aff88f4674048359c5ac305e1eccf8dad77e9cf33ce553
|
3 |
+
size 437958648
|
run-14/checkpoint-211/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:858a9e7be7a64c1d691de0eef1e442ffa00011902efe30a35d2c43a734bc304a
|
3 |
+
size 876038394
|
run-14/checkpoint-211/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d67d48dd627e20be8af76a6920edffb31b5162d073c1917ccf4c44e04681556
|
3 |
+
size 14244
|
run-14/checkpoint-211/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f63be7aa4e3472fdf09144e86c89beabab597451b6a5baf2b612a9a1196cc180
|
3 |
+
size 1064
|
run-14/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-14/checkpoint-211/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-14/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-14/checkpoint-211/trainer_state.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9128440366972477,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-14/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": 0.9128440366972477,
|
14 |
+
"eval_loss": 0.22454452514648438,
|
15 |
+
"eval_runtime": 2.2271,
|
16 |
+
"eval_samples_per_second": 391.546,
|
17 |
+
"eval_steps_per_second": 24.696,
|
18 |
+
"step": 211
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 844,
|
23 |
+
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 4,
|
25 |
+
"save_steps": 500,
|
26 |
+
"total_flos": 0,
|
27 |
+
"train_batch_size": 32,
|
28 |
+
"trial_name": null,
|
29 |
+
"trial_params": {
|
30 |
+
"learning_rate": 5.7889259461894204e-05,
|
31 |
+
"num_train_epochs": 4,
|
32 |
+
"per_device_train_batch_size": 32,
|
33 |
+
"seed": 9
|
34 |
+
}
|
35 |
+
}
|
run-14/checkpoint-211/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48e02327ec5b769ae9d1aa41027147acf0d116194331a5346cfaaf9b87861cb7
|
3 |
+
size 4920
|
run-14/checkpoint-211/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709500313.90708aaa767a.21824.32
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad365f49a8b968efdce50453233796fac027a295cc75601d5b40690daa4794db
|
3 |
+
size 6127
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48e02327ec5b769ae9d1aa41027147acf0d116194331a5346cfaaf9b87861cb7
|
3 |
size 4920
|