xuancoblab2023
commited on
Commit
•
b665783
1
Parent(s):
6af1d32
Training in progress, epoch 3
Browse files- logs/events.out.tfevents.1721967234.98acc6742512.15262.39 +2 -2
- model.safetensors +1 -1
- run-38/checkpoint-516/config.json +34 -0
- run-38/checkpoint-516/model.safetensors +3 -0
- run-38/checkpoint-516/optimizer.pt +3 -0
- run-38/checkpoint-516/rng_state.pth +3 -0
- run-38/checkpoint-516/scheduler.pt +3 -0
- run-38/checkpoint-516/special_tokens_map.json +7 -0
- run-38/checkpoint-516/tokenizer.json +0 -0
- run-38/checkpoint-516/tokenizer_config.json +55 -0
- run-38/checkpoint-516/trainer_state.json +98 -0
- run-38/checkpoint-516/training_args.bin +3 -0
- run-38/checkpoint-516/vocab.txt +0 -0
logs/events.out.tfevents.1721967234.98acc6742512.15262.39
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 sha256:6ba8a86a89f355357ca9c46d5026e75e4b1086c62fb4a6f27369c2185c788f9d
|
3 |
+
size 7159
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17549312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0587607e939fc5a9f9211afd789481a824eb8d952b36d29ab5b3cb2e2de183a0
|
3 |
size 17549312
|
run-38/checkpoint-516/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 128,
|
11 |
+
"id2label": {
|
12 |
+
"0": "negative",
|
13 |
+
"1": "positive"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 512,
|
17 |
+
"label2id": {
|
18 |
+
"negative": "0",
|
19 |
+
"positive": "1"
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "bert",
|
24 |
+
"num_attention_heads": 2,
|
25 |
+
"num_hidden_layers": 2,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.43.2",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
run-38/checkpoint-516/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0587607e939fc5a9f9211afd789481a824eb8d952b36d29ab5b3cb2e2de183a0
|
3 |
+
size 17549312
|
run-38/checkpoint-516/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bd9ac78eca46cee63cb4cc34c93739d97565e4d7b48d14601f62eca75d03713
|
3 |
+
size 35123898
|
run-38/checkpoint-516/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e559bd010dfad806644ec9950fc1246348c344f69faad3d9fcd91973ca8dae1e
|
3 |
+
size 14308
|
run-38/checkpoint-516/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9db975b8b36ab61f801f1c0558e3ab3a68003daccce71dd03013023a27f897b6
|
3 |
+
size 1064
|
run-38/checkpoint-516/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-38/checkpoint-516/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-38/checkpoint-516/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-38/checkpoint-516/trainer_state.json
ADDED
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.804,
|
3 |
+
"best_model_checkpoint": "Bert_tinybert-distilled/run-38/checkpoint-516",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 516,
|
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 |
+
"grad_norm": 2.369624614715576,
|
14 |
+
"learning_rate": 0.00010150235987388685,
|
15 |
+
"loss": 0.641,
|
16 |
+
"step": 172
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_AUC": 0.8192835555555557,
|
21 |
+
"eval_BAC": 0.7393333333333334,
|
22 |
+
"eval_MCC": 0.478738589243997,
|
23 |
+
"eval_PR_AUC": 0.7668773893377483,
|
24 |
+
"eval_accuracy": 0.7393333333333333,
|
25 |
+
"eval_loss": 0.5342645645141602,
|
26 |
+
"eval_runtime": 6.2413,
|
27 |
+
"eval_samples_per_second": 240.333,
|
28 |
+
"eval_steps_per_second": 7.53,
|
29 |
+
"step": 172
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"grad_norm": 2.409252643585205,
|
34 |
+
"learning_rate": 9.022431988789944e-05,
|
35 |
+
"loss": 0.5812,
|
36 |
+
"step": 344
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.0,
|
40 |
+
"eval_AUC": 0.8472373333333332,
|
41 |
+
"eval_BAC": 0.7773333333333333,
|
42 |
+
"eval_MCC": 0.5854511255434387,
|
43 |
+
"eval_PR_AUC": 0.7929492844718843,
|
44 |
+
"eval_accuracy": 0.7773333333333333,
|
45 |
+
"eval_loss": 0.508563756942749,
|
46 |
+
"eval_runtime": 6.2422,
|
47 |
+
"eval_samples_per_second": 240.301,
|
48 |
+
"eval_steps_per_second": 7.529,
|
49 |
+
"step": 344
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 3.0,
|
53 |
+
"grad_norm": 3.4908885955810547,
|
54 |
+
"learning_rate": 7.894627990191199e-05,
|
55 |
+
"loss": 0.5572,
|
56 |
+
"step": 516
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.0,
|
60 |
+
"eval_AUC": 0.8623342222222222,
|
61 |
+
"eval_BAC": 0.804,
|
62 |
+
"eval_MCC": 0.6144035052075252,
|
63 |
+
"eval_PR_AUC": 0.821901299271215,
|
64 |
+
"eval_accuracy": 0.804,
|
65 |
+
"eval_loss": 0.4822913408279419,
|
66 |
+
"eval_runtime": 6.2667,
|
67 |
+
"eval_samples_per_second": 239.362,
|
68 |
+
"eval_steps_per_second": 7.5,
|
69 |
+
"step": 516
|
70 |
+
}
|
71 |
+
],
|
72 |
+
"logging_steps": 500,
|
73 |
+
"max_steps": 1720,
|
74 |
+
"num_input_tokens_seen": 0,
|
75 |
+
"num_train_epochs": 10,
|
76 |
+
"save_steps": 500,
|
77 |
+
"stateful_callbacks": {
|
78 |
+
"TrainerControl": {
|
79 |
+
"args": {
|
80 |
+
"should_epoch_stop": false,
|
81 |
+
"should_evaluate": false,
|
82 |
+
"should_log": false,
|
83 |
+
"should_save": true,
|
84 |
+
"should_training_stop": false
|
85 |
+
},
|
86 |
+
"attributes": {}
|
87 |
+
}
|
88 |
+
},
|
89 |
+
"total_flos": 1351133190000.0,
|
90 |
+
"train_batch_size": 32,
|
91 |
+
"trial_name": null,
|
92 |
+
"trial_params": {
|
93 |
+
"alpha": 0.9992013304702073,
|
94 |
+
"learning_rate": 0.00011278039985987428,
|
95 |
+
"num_train_epochs": 10,
|
96 |
+
"temperature": 16
|
97 |
+
}
|
98 |
+
}
|
run-38/checkpoint-516/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37a13935aa97cc10365d1c8e6e7192e80b697c42d9d84bdb7192c8b7ddc978dd
|
3 |
+
size 5240
|
run-38/checkpoint-516/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|