gchhablani
commited on
Commit
•
d4ca208
1
Parent(s):
a1d195e
Training in progress, epoch 2
Browse files- checkpoint-4276/config.json +42 -0
- checkpoint-4276/optimizer.pt +3 -0
- checkpoint-4276/pytorch_model.bin +3 -0
- checkpoint-4276/rng_state.pth +3 -0
- checkpoint-4276/scheduler.pt +3 -0
- checkpoint-4276/special_tokens_map.json +1 -0
- checkpoint-4276/tokenizer.json +0 -0
- checkpoint-4276/tokenizer_config.json +1 -0
- checkpoint-4276/trainer_state.json +46 -0
- checkpoint-4276/training_args.bin +3 -0
- checkpoint-4276/vocab.txt +0 -0
- pytorch_model.bin +1 -1
- runs/Sep20_22-32-10_patrick-general-gpu/events.out.tfevents.1632177149.patrick-general-gpu.544040.0 +2 -2
checkpoint-4276/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": "cola",
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"id2label": {
|
15 |
+
"0": "unacceptable",
|
16 |
+
"1": "acceptable"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 4096,
|
20 |
+
"label2id": {
|
21 |
+
"acceptable": 1,
|
22 |
+
"unacceptable": 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-4276/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a68d3b33ffe5363016155fe43a78d89f63d8e091415d4563d33c7d694db4c86
|
3 |
+
size 2668879261
|
checkpoint-4276/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0f96175681192f904f6107cea32d96fac92b064f6896fb6d019b07ce100f822
|
3 |
+
size 1334486957
|
checkpoint-4276/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74066af61b3f74807f92418e979ea5ed360fe681a7bc19a31033d65c593bc48a
|
3 |
+
size 14503
|
checkpoint-4276/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f0a259137f292bea24e409cb5a3632b03c80113a545ea2ee2d856760ee41b38
|
3 |
+
size 623
|
checkpoint-4276/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-4276/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4276/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-4276/trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 4276,
|
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": 0.5533,
|
14 |
+
"step": 2138
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 0.794291079044342,
|
19 |
+
"eval_matthews_correlation": 0.44394615350761574,
|
20 |
+
"eval_runtime": 33.9254,
|
21 |
+
"eval_samples_per_second": 30.744,
|
22 |
+
"eval_steps_per_second": 3.861,
|
23 |
+
"step": 2138
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 6.666666666666667e-06,
|
28 |
+
"loss": 0.5004,
|
29 |
+
"step": 4276
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_loss": 0.7272064685821533,
|
34 |
+
"eval_matthews_correlation": 0.5678267214677118,
|
35 |
+
"eval_runtime": 33.839,
|
36 |
+
"eval_samples_per_second": 30.822,
|
37 |
+
"eval_steps_per_second": 3.871,
|
38 |
+
"step": 4276
|
39 |
+
}
|
40 |
+
],
|
41 |
+
"max_steps": 6414,
|
42 |
+
"num_train_epochs": 3,
|
43 |
+
"total_flos": 1.5937890175635456e+16,
|
44 |
+
"trial_name": null,
|
45 |
+
"trial_params": null
|
46 |
+
}
|
checkpoint-4276/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5e08ee36c363c8414e6988b7d0bd6135c0abd07da04ef00bf126d316cb97ce7
|
3 |
+
size 2799
|
checkpoint-4276/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:c0f96175681192f904f6107cea32d96fac92b064f6896fb6d019b07ce100f822
|
3 |
size 1334486957
|
runs/Sep20_22-32-10_patrick-general-gpu/events.out.tfevents.1632177149.patrick-general-gpu.544040.0
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:b28400bc539e8a19bf5e36c98815999c5cce4e63ef088136737313ca4c9bb24e
|
3 |
+
size 4421
|