gchhablani
commited on
Commit
•
575261d
1
Parent(s):
3ca5615
Training in progress, epoch 4
Browse files- checkpoint-3668/config.json +42 -0
- checkpoint-3668/optimizer.pt +3 -0
- checkpoint-3668/pytorch_model.bin +3 -0
- checkpoint-3668/rng_state.pth +3 -0
- checkpoint-3668/scheduler.pt +3 -0
- checkpoint-3668/special_tokens_map.json +1 -0
- checkpoint-3668/tokenizer.json +0 -0
- checkpoint-3668/tokenizer_config.json +1 -0
- checkpoint-3668/trainer_state.json +84 -0
- checkpoint-3668/training_args.bin +3 -0
- checkpoint-3668/vocab.txt +0 -0
- pytorch_model.bin +1 -1
- runs/Sep22_06-07-26_patrick-general-gpu/events.out.tfevents.1632290866.patrick-general-gpu.751022.0 +2 -2
checkpoint-3668/config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"finetuning_task": "mrpc",
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"id2label": {
|
15 |
+
"0": "not_equivalent",
|
16 |
+
"1": "equivalent"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 4096,
|
20 |
+
"label2id": {
|
21 |
+
"equivalent": 1,
|
22 |
+
"not_equivalent": 0
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 16,
|
28 |
+
"num_hidden_layers": 24,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"pooler_fc_size": 768,
|
31 |
+
"pooler_num_attention_heads": 12,
|
32 |
+
"pooler_num_fc_layers": 3,
|
33 |
+
"pooler_size_per_head": 128,
|
34 |
+
"pooler_type": "first_token_transform",
|
35 |
+
"position_embedding_type": "absolute",
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.11.0.dev0",
|
39 |
+
"type_vocab_size": 2,
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 28996
|
42 |
+
}
|
checkpoint-3668/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:942738bfc422ba3903e5e6aaa2a056098ca6f01b3ba124e9234d2c30f09ded19
|
3 |
+
size 2668879261
|
checkpoint-3668/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c08bf7442608b6a2697ed2786c764408299d061d63e1eac5c2c4d34677aa343b
|
3 |
+
size 1334486957
|
checkpoint-3668/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8088a8a9c5f0a2f11eaf8fe92d9b4d5d92fbb372e3c3c9859401576b43b04733
|
3 |
+
size 14503
|
checkpoint-3668/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aff0894304e2fef9b08254d2b9e80857b7723e16fb0299d164d287cb7e9a1547
|
3 |
+
size 623
|
checkpoint-3668/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
checkpoint-3668/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
checkpoint-3668/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-large-cased", "tokenizer_class": "BertTokenizer"}
|
checkpoint-3668/trainer_state.json
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 3668,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 1.6000000000000003e-05,
|
13 |
+
"loss": 0.6441,
|
14 |
+
"step": 917
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.6838235294117647,
|
19 |
+
"eval_combined_score": 0.7480253018237863,
|
20 |
+
"eval_f1": 0.8122270742358079,
|
21 |
+
"eval_loss": 0.6369990706443787,
|
22 |
+
"eval_runtime": 13.1449,
|
23 |
+
"eval_samples_per_second": 31.039,
|
24 |
+
"eval_steps_per_second": 3.88,
|
25 |
+
"step": 917
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"learning_rate": 1.2e-05,
|
30 |
+
"loss": 0.6451,
|
31 |
+
"step": 1834
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_accuracy": 0.6838235294117647,
|
36 |
+
"eval_combined_score": 0.7480253018237863,
|
37 |
+
"eval_f1": 0.8122270742358079,
|
38 |
+
"eval_loss": 0.6552556157112122,
|
39 |
+
"eval_runtime": 13.1957,
|
40 |
+
"eval_samples_per_second": 30.919,
|
41 |
+
"eval_steps_per_second": 3.865,
|
42 |
+
"step": 1834
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"learning_rate": 8.000000000000001e-06,
|
47 |
+
"loss": 0.6428,
|
48 |
+
"step": 2751
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_accuracy": 0.6838235294117647,
|
53 |
+
"eval_combined_score": 0.7480253018237863,
|
54 |
+
"eval_f1": 0.8122270742358079,
|
55 |
+
"eval_loss": 0.6332471966743469,
|
56 |
+
"eval_runtime": 13.1447,
|
57 |
+
"eval_samples_per_second": 31.039,
|
58 |
+
"eval_steps_per_second": 3.88,
|
59 |
+
"step": 2751
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"learning_rate": 4.000000000000001e-06,
|
64 |
+
"loss": 0.6476,
|
65 |
+
"step": 3668
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 4.0,
|
69 |
+
"eval_accuracy": 0.6838235294117647,
|
70 |
+
"eval_combined_score": 0.7480253018237863,
|
71 |
+
"eval_f1": 0.8122270742358079,
|
72 |
+
"eval_loss": 0.6247974634170532,
|
73 |
+
"eval_runtime": 13.1288,
|
74 |
+
"eval_samples_per_second": 31.077,
|
75 |
+
"eval_steps_per_second": 3.885,
|
76 |
+
"step": 3668
|
77 |
+
}
|
78 |
+
],
|
79 |
+
"max_steps": 4585,
|
80 |
+
"num_train_epochs": 5,
|
81 |
+
"total_flos": 1.3673296962748416e+16,
|
82 |
+
"trial_name": null,
|
83 |
+
"trial_params": null
|
84 |
+
}
|
checkpoint-3668/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b497fdf35eb49ca9dc4a49ae7289bd94d2105c9dfbca8e37d973c3bb6758058d
|
3 |
+
size 2799
|
checkpoint-3668/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1334486957
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c08bf7442608b6a2697ed2786c764408299d061d63e1eac5c2c4d34677aa343b
|
3 |
size 1334486957
|
runs/Sep22_06-07-26_patrick-general-gpu/events.out.tfevents.1632290866.patrick-general-gpu.751022.0
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:e348dd702912706743d2e5010fc98144c5b6a38731aaae094e36ca639653c654
|
3 |
+
size 5777
|