gchhablani
commited on
Commit
•
6d35716
1
Parent(s):
c40d5a1
Training in progress, epoch 3
Browse files- checkpoint-1605/config.json +36 -0
- checkpoint-1605/optimizer.pt +3 -0
- checkpoint-1605/pytorch_model.bin +3 -0
- checkpoint-1605/rng_state.pth +3 -0
- checkpoint-1605/scheduler.pt +3 -0
- checkpoint-1605/special_tokens_map.json +1 -0
- checkpoint-1605/tokenizer.json +0 -0
- checkpoint-1605/tokenizer_config.json +1 -0
- checkpoint-1605/trainer_state.json +61 -0
- checkpoint-1605/training_args.bin +3 -0
- checkpoint-1605/vocab.txt +0 -0
- pytorch_model.bin +1 -1
- runs/Sep16_18-47-00_patrick-general-gpu/events.out.tfevents.1631818036.patrick-general-gpu.195949.0 +2 -2
checkpoint-1605/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"finetuning_task": "cola",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "unacceptable",
|
15 |
+
"1": "acceptable"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"acceptable": 1,
|
21 |
+
"unacceptable": 0
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "bert",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.11.0.dev0",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 28996
|
36 |
+
}
|
checkpoint-1605/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f235a1c260e34df3bd5c2d4ccb8d05362b6fa614863b0eeb46c09a44d25ba532
|
3 |
+
size 866610973
|
checkpoint-1605/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe2163d3552f2846fd747ceaae7357dd4cd629634aa16df59974a0c97bdb6a84
|
3 |
+
size 433331373
|
checkpoint-1605/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5391cf57c0f5c8f846b9d8ef7acacef437d581ab551a6b897300a4c03fa29bd0
|
3 |
+
size 14503
|
checkpoint-1605/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1acca92a8b10bd06cc866eafb8aeb9d4f85bcdb2d57143bebcfe2bc573e5d33a
|
3 |
+
size 623
|
checkpoint-1605/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-1605/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1605/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-base-cased", "tokenizer_class": "BertTokenizer"}
|
checkpoint-1605/trainer_state.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 1605,
|
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": 1.3333333333333333e-05,
|
13 |
+
"loss": 0.4921,
|
14 |
+
"step": 535
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 0.5283351540565491,
|
19 |
+
"eval_matthews_correlation": 0.5068375331988826,
|
20 |
+
"eval_runtime": 10.6748,
|
21 |
+
"eval_samples_per_second": 97.706,
|
22 |
+
"eval_steps_per_second": 12.272,
|
23 |
+
"step": 535
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 6.666666666666667e-06,
|
28 |
+
"loss": 0.2837,
|
29 |
+
"step": 1070
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_loss": 0.5132979154586792,
|
34 |
+
"eval_matthews_correlation": 0.5521390429003941,
|
35 |
+
"eval_runtime": 10.6848,
|
36 |
+
"eval_samples_per_second": 97.616,
|
37 |
+
"eval_steps_per_second": 12.26,
|
38 |
+
"step": 1070
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 0.0,
|
43 |
+
"loss": 0.1775,
|
44 |
+
"step": 1605
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_loss": 0.6747468709945679,
|
49 |
+
"eval_matthews_correlation": 0.5956649094312695,
|
50 |
+
"eval_runtime": 10.6837,
|
51 |
+
"eval_samples_per_second": 97.625,
|
52 |
+
"eval_steps_per_second": 12.262,
|
53 |
+
"step": 1605
|
54 |
+
}
|
55 |
+
],
|
56 |
+
"max_steps": 1605,
|
57 |
+
"num_train_epochs": 3,
|
58 |
+
"total_flos": 6749587903150080.0,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": null
|
61 |
+
}
|
checkpoint-1605/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b87834190b4349f44daee6994b83db673da78267ee1f4f353723565d6835dfed
|
3 |
+
size 2799
|
checkpoint-1605/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 433331373
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe2163d3552f2846fd747ceaae7357dd4cd629634aa16df59974a0c97bdb6a84
|
3 |
size 433331373
|
runs/Sep16_18-47-00_patrick-general-gpu/events.out.tfevents.1631818036.patrick-general-gpu.195949.0
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 sha256:7c447af10216b49105989d4df5e3389964565ffe80b87aa63e1eddc7f19ce119
|
3 |
+
size 4718
|