Tech-oriented
commited on
Commit
•
ed1d14d
1
Parent(s):
0ea6e38
Training in progress, epoch 2
Browse files- model.safetensors +1 -1
- run-1/checkpoint-1684/config.json +27 -0
- run-1/checkpoint-1684/model.safetensors +3 -0
- run-1/checkpoint-1684/optimizer.pt +3 -0
- run-1/checkpoint-1684/rng_state.pth +3 -0
- run-1/checkpoint-1684/scheduler.pt +3 -0
- run-1/checkpoint-1684/special_tokens_map.json +7 -0
- run-1/checkpoint-1684/tokenizer.json +0 -0
- run-1/checkpoint-1684/tokenizer_config.json +55 -0
- run-1/checkpoint-1684/trainer_state.json +65 -0
- run-1/checkpoint-1684/training_args.bin +3 -0
- run-1/checkpoint-1684/vocab.txt +0 -0
- runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709492125.90708aaa767a.21824.8 +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:a5efabf1f88cd44ea53f885c75e4a7636dd8f42a9d952269e26691757825d813
|
3 |
size 437958648
|
run-1/checkpoint-1684/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-1/checkpoint-1684/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5efabf1f88cd44ea53f885c75e4a7636dd8f42a9d952269e26691757825d813
|
3 |
+
size 437958648
|
run-1/checkpoint-1684/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0399d8b7c5b5f60b16511e086de8116831f8aceeaca33b5ace4521d5fae14571
|
3 |
+
size 876038394
|
run-1/checkpoint-1684/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:802dbca11663e9f78fc58385ef96632f9c8202e35cc0f0af207cb5f9c7ca6cf9
|
3 |
+
size 14308
|
run-1/checkpoint-1684/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32732bc4fdf005a2387820424092da13828d7704e2ef31410c899225e7739ee8
|
3 |
+
size 1064
|
run-1/checkpoint-1684/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-1684/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-1684/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-1/checkpoint-1684/trainer_state.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9139908256880734,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-1/checkpoint-1684",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1684,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.59,
|
13 |
+
"grad_norm": 5.992064476013184,
|
14 |
+
"learning_rate": 2.846915930651389e-05,
|
15 |
+
"loss": 0.4119,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.8646788990825688,
|
21 |
+
"eval_loss": 0.40675637125968933,
|
22 |
+
"eval_runtime": 2.35,
|
23 |
+
"eval_samples_per_second": 371.063,
|
24 |
+
"eval_steps_per_second": 23.404,
|
25 |
+
"step": 842
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.19,
|
29 |
+
"grad_norm": 0.04706716537475586,
|
30 |
+
"learning_rate": 1.6446710275046875e-05,
|
31 |
+
"loss": 0.2691,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.78,
|
36 |
+
"grad_norm": 0.055366575717926025,
|
37 |
+
"learning_rate": 4.424261243579861e-06,
|
38 |
+
"loss": 0.1703,
|
39 |
+
"step": 1500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.0,
|
43 |
+
"eval_accuracy": 0.9139908256880734,
|
44 |
+
"eval_loss": 0.3520638048648834,
|
45 |
+
"eval_runtime": 2.3883,
|
46 |
+
"eval_samples_per_second": 365.121,
|
47 |
+
"eval_steps_per_second": 23.029,
|
48 |
+
"step": 1684
|
49 |
+
}
|
50 |
+
],
|
51 |
+
"logging_steps": 500,
|
52 |
+
"max_steps": 1684,
|
53 |
+
"num_input_tokens_seen": 0,
|
54 |
+
"num_train_epochs": 2,
|
55 |
+
"save_steps": 500,
|
56 |
+
"total_flos": 185893613388420.0,
|
57 |
+
"train_batch_size": 8,
|
58 |
+
"trial_name": null,
|
59 |
+
"trial_params": {
|
60 |
+
"learning_rate": 4.0491608337980904e-05,
|
61 |
+
"num_train_epochs": 2,
|
62 |
+
"per_device_train_batch_size": 8,
|
63 |
+
"seed": 26
|
64 |
+
}
|
65 |
+
}
|
run-1/checkpoint-1684/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d58728a4c98462c056199818a16dc9ffabb0131d677c081afc7148b4da7bd4e
|
3 |
+
size 4920
|
run-1/checkpoint-1684/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.1709492125.90708aaa767a.21824.8
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:ef531be39c413076889a0df164536fa6cf9caf5b27610da551217024a015b910
|
3 |
+
size 6257
|