Training in progress, epoch 6
Browse files- logs/events.out.tfevents.1702280530.joseph_legion.22340.19 +2 -2
- model.safetensors +1 -1
- run-6/checkpoint-1182/config.json +34 -0
- run-6/checkpoint-1182/model.safetensors +3 -0
- run-6/checkpoint-1182/optimizer.pt +3 -0
- run-6/checkpoint-1182/rng_state.pth +3 -0
- run-6/checkpoint-1182/scheduler.pt +3 -0
- run-6/checkpoint-1182/special_tokens_map.json +7 -0
- run-6/checkpoint-1182/tokenizer_config.json +57 -0
- run-6/checkpoint-1182/trainer_state.json +115 -0
- run-6/checkpoint-1182/training_args.bin +3 -0
- run-6/checkpoint-1182/vocab.txt +0 -0
logs/events.out.tfevents.1702280530.joseph_legion.22340.19
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 sha256:00c4aef8bfe2fa6cf09a95237ab6d91977c273f9ebb8a3f436f98584d3dd165b
|
3 |
+
size 7326
|
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:dd1a3bece42063489d522b268eacf8a8fdbcb5f40a282878eaf7c1250703a0dc
|
3 |
size 44692608
|
run-6/checkpoint-1182/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-6/checkpoint-1182/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd1a3bece42063489d522b268eacf8a8fdbcb5f40a282878eaf7c1250703a0dc
|
3 |
+
size 44692608
|
run-6/checkpoint-1182/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef5a6763c55a85465b0338b090c6108eb52b94a6ec0adf38c5fd11975fc01aa7
|
3 |
+
size 89430010
|
run-6/checkpoint-1182/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a9511e5e4163d669edd4526e0777794d8936c52493f7e77dc7be042cfeed886
|
3 |
+
size 14308
|
run-6/checkpoint-1182/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe3b69c5c766fc9f2234cac440dba1114e5dca164a7a4b855456331a967607d7
|
3 |
+
size 1064
|
run-6/checkpoint-1182/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-6/checkpoint-1182/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-6/checkpoint-1182/trainer_state.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7896053362979433,
|
3 |
+
"best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-6\\checkpoint-1182",
|
4 |
+
"epoch": 6.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1182,
|
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": 1.0611700032566007e-05,
|
14 |
+
"loss": 0.1259,
|
15 |
+
"step": 197
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_accuracy": 0.7536131183991106,
|
20 |
+
"eval_loss": 0.12161022424697876,
|
21 |
+
"eval_runtime": 125.6824,
|
22 |
+
"eval_samples_per_second": 57.255,
|
23 |
+
"eval_steps_per_second": 0.454,
|
24 |
+
"step": 197
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"learning_rate": 9.095742885056578e-06,
|
29 |
+
"loss": 0.1236,
|
30 |
+
"step": 394
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.7745969983324069,
|
35 |
+
"eval_loss": 0.12096704542636871,
|
36 |
+
"eval_runtime": 125.4944,
|
37 |
+
"eval_samples_per_second": 57.341,
|
38 |
+
"eval_steps_per_second": 0.454,
|
39 |
+
"step": 394
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 3.0,
|
43 |
+
"learning_rate": 7.579785737547148e-06,
|
44 |
+
"loss": 0.1229,
|
45 |
+
"step": 591
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.0,
|
49 |
+
"eval_accuracy": 0.7848804891606448,
|
50 |
+
"eval_loss": 0.12066732347011566,
|
51 |
+
"eval_runtime": 125.5947,
|
52 |
+
"eval_samples_per_second": 57.295,
|
53 |
+
"eval_steps_per_second": 0.454,
|
54 |
+
"step": 591
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 4.0,
|
58 |
+
"learning_rate": 6.063828590037718e-06,
|
59 |
+
"loss": 0.1224,
|
60 |
+
"step": 788
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 4.0,
|
64 |
+
"eval_accuracy": 0.7804335742078933,
|
65 |
+
"eval_loss": 0.12036041915416718,
|
66 |
+
"eval_runtime": 125.5933,
|
67 |
+
"eval_samples_per_second": 57.296,
|
68 |
+
"eval_steps_per_second": 0.454,
|
69 |
+
"step": 788
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 5.0,
|
73 |
+
"learning_rate": 4.547871442528289e-06,
|
74 |
+
"loss": 0.1221,
|
75 |
+
"step": 985
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.0,
|
79 |
+
"eval_accuracy": 0.7887715397443024,
|
80 |
+
"eval_loss": 0.12023670971393585,
|
81 |
+
"eval_runtime": 125.4555,
|
82 |
+
"eval_samples_per_second": 57.359,
|
83 |
+
"eval_steps_per_second": 0.454,
|
84 |
+
"step": 985
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.0,
|
88 |
+
"learning_rate": 3.031914295018859e-06,
|
89 |
+
"loss": 0.1218,
|
90 |
+
"step": 1182
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 6.0,
|
94 |
+
"eval_accuracy": 0.7896053362979433,
|
95 |
+
"eval_loss": 0.12014192342758179,
|
96 |
+
"eval_runtime": 125.3237,
|
97 |
+
"eval_samples_per_second": 57.419,
|
98 |
+
"eval_steps_per_second": 0.455,
|
99 |
+
"step": 1182
|
100 |
+
}
|
101 |
+
],
|
102 |
+
"logging_steps": 500,
|
103 |
+
"max_steps": 1576,
|
104 |
+
"num_input_tokens_seen": 0,
|
105 |
+
"num_train_epochs": 8,
|
106 |
+
"save_steps": 500,
|
107 |
+
"total_flos": 265501203931764.0,
|
108 |
+
"trial_name": null,
|
109 |
+
"trial_params": {
|
110 |
+
"alpha": 0.18717092492624732,
|
111 |
+
"learning_rate": 1.2127657180075437e-05,
|
112 |
+
"num_train_epochs": 8,
|
113 |
+
"temperature": 5
|
114 |
+
}
|
115 |
+
}
|
run-6/checkpoint-1182/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40dcaec467c321bbd4ff99afc7a2ae4bf90159a9a099a7339cfff83b49ccfbc6
|
3 |
+
size 4792
|
run-6/checkpoint-1182/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|