Training in progress, epoch 7
Browse files- logs/events.out.tfevents.1702287558.joseph_legion.22340.22 +2 -2
- model.safetensors +1 -1
- run-9/checkpoint-1379/config.json +34 -0
- run-9/checkpoint-1379/model.safetensors +3 -0
- run-9/checkpoint-1379/optimizer.pt +3 -0
- run-9/checkpoint-1379/rng_state.pth +3 -0
- run-9/checkpoint-1379/scheduler.pt +3 -0
- run-9/checkpoint-1379/special_tokens_map.json +7 -0
- run-9/checkpoint-1379/tokenizer_config.json +57 -0
- run-9/checkpoint-1379/trainer_state.json +130 -0
- run-9/checkpoint-1379/training_args.bin +3 -0
- run-9/checkpoint-1379/vocab.txt +0 -0
logs/events.out.tfevents.1702287558.joseph_legion.22340.22
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 sha256:3d20a8196be5bcb64ed76fcd776ae3d46e6d6fcf8e32c712902e87a49410d5ee
|
3 |
+
size 7806
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 44692608
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1dfeebb0640c7f2821faeac1bbfb79f2eda297930ff584af2cc6f1f2404d9ce
|
3 |
size 44692608
|
run-9/checkpoint-1379/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
|
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": 256,
|
11 |
+
"id2label": {
|
12 |
+
"0": 0,
|
13 |
+
"1": 1
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 1024,
|
17 |
+
"label2id": {
|
18 |
+
"0": 0,
|
19 |
+
"1": 1
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "bert",
|
24 |
+
"num_attention_heads": 4,
|
25 |
+
"num_hidden_layers": 4,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.36.0.dev0",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
run-9/checkpoint-1379/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1dfeebb0640c7f2821faeac1bbfb79f2eda297930ff584af2cc6f1f2404d9ce
|
3 |
+
size 44692608
|
run-9/checkpoint-1379/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c569527c88c246fcb742afcc304f02c2b7d3eb4bc2ad47a665b86890c0d156c4
|
3 |
+
size 89430010
|
run-9/checkpoint-1379/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90950b6bd01ee491d86df75c6186784a03589a99164b435c5e7a35996764ac98
|
3 |
+
size 14308
|
run-9/checkpoint-1379/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7572a67e78c853684ca208cdbb214c355b22ed9d49d4e4350e2f89bab9b591a
|
3 |
+
size 1064
|
run-9/checkpoint-1379/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-9/checkpoint-1379/tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
run-9/checkpoint-1379/trainer_state.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8100333518621456,
|
3 |
+
"best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-9\\checkpoint-1182",
|
4 |
+
"epoch": 7.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1379,
|
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 |
+
"learning_rate": 1.1884492449582221e-05,
|
14 |
+
"loss": 0.3771,
|
15 |
+
"step": 197
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_accuracy": 0.7761256253474152,
|
20 |
+
"eval_loss": 0.35103824734687805,
|
21 |
+
"eval_runtime": 125.0972,
|
22 |
+
"eval_samples_per_second": 57.523,
|
23 |
+
"eval_steps_per_second": 0.456,
|
24 |
+
"step": 197
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"learning_rate": 1.0186707813927618e-05,
|
29 |
+
"loss": 0.356,
|
30 |
+
"step": 394
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.7898832684824902,
|
35 |
+
"eval_loss": 0.3439778685569763,
|
36 |
+
"eval_runtime": 125.0439,
|
37 |
+
"eval_samples_per_second": 57.548,
|
38 |
+
"eval_steps_per_second": 0.456,
|
39 |
+
"step": 394
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 3.0,
|
43 |
+
"learning_rate": 8.488923178273016e-06,
|
44 |
+
"loss": 0.3473,
|
45 |
+
"step": 591
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.0,
|
49 |
+
"eval_accuracy": 0.797526403557532,
|
50 |
+
"eval_loss": 0.34075456857681274,
|
51 |
+
"eval_runtime": 125.2215,
|
52 |
+
"eval_samples_per_second": 57.466,
|
53 |
+
"eval_steps_per_second": 0.455,
|
54 |
+
"step": 591
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 4.0,
|
58 |
+
"learning_rate": 6.791138542618412e-06,
|
59 |
+
"loss": 0.3428,
|
60 |
+
"step": 788
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 4.0,
|
64 |
+
"eval_accuracy": 0.8030850472484714,
|
65 |
+
"eval_loss": 0.33721399307250977,
|
66 |
+
"eval_runtime": 124.8586,
|
67 |
+
"eval_samples_per_second": 57.633,
|
68 |
+
"eval_steps_per_second": 0.457,
|
69 |
+
"step": 788
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 5.0,
|
73 |
+
"learning_rate": 5.093353906963809e-06,
|
74 |
+
"loss": 0.3391,
|
75 |
+
"step": 985
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.0,
|
79 |
+
"eval_accuracy": 0.8060033351862146,
|
80 |
+
"eval_loss": 0.33657532930374146,
|
81 |
+
"eval_runtime": 125.0566,
|
82 |
+
"eval_samples_per_second": 57.542,
|
83 |
+
"eval_steps_per_second": 0.456,
|
84 |
+
"step": 985
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.0,
|
88 |
+
"learning_rate": 3.395569271309206e-06,
|
89 |
+
"loss": 0.3354,
|
90 |
+
"step": 1182
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 6.0,
|
94 |
+
"eval_accuracy": 0.8100333518621456,
|
95 |
+
"eval_loss": 0.33524009585380554,
|
96 |
+
"eval_runtime": 124.7339,
|
97 |
+
"eval_samples_per_second": 57.691,
|
98 |
+
"eval_steps_per_second": 0.457,
|
99 |
+
"step": 1182
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 7.0,
|
103 |
+
"learning_rate": 1.697784635654603e-06,
|
104 |
+
"loss": 0.3337,
|
105 |
+
"step": 1379
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 7.0,
|
109 |
+
"eval_accuracy": 0.8090605892162313,
|
110 |
+
"eval_loss": 0.33525848388671875,
|
111 |
+
"eval_runtime": 125.0522,
|
112 |
+
"eval_samples_per_second": 57.544,
|
113 |
+
"eval_steps_per_second": 0.456,
|
114 |
+
"step": 1379
|
115 |
+
}
|
116 |
+
],
|
117 |
+
"logging_steps": 500,
|
118 |
+
"max_steps": 1576,
|
119 |
+
"num_input_tokens_seen": 0,
|
120 |
+
"num_train_epochs": 8,
|
121 |
+
"save_steps": 500,
|
122 |
+
"total_flos": 309665393535204.0,
|
123 |
+
"trial_name": null,
|
124 |
+
"trial_params": {
|
125 |
+
"alpha": 0.625656755680376,
|
126 |
+
"learning_rate": 1.3582277085236825e-05,
|
127 |
+
"num_train_epochs": 8,
|
128 |
+
"temperature": 10
|
129 |
+
}
|
130 |
+
}
|
run-9/checkpoint-1379/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c910c119accf4bbf865cec75218ffcb177b5dd17c6f67c36518b8f592afcb473
|
3 |
+
size 4792
|
run-9/checkpoint-1379/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|