Commit
•
b61aa79
1
Parent(s):
ab6d30f
Training in progress, epoch 3
Browse files- checkpoint-120/config.json +36 -0
- checkpoint-120/optimizer.pt +3 -0
- checkpoint-120/pytorch_model.bin +3 -0
- checkpoint-120/rng_state.pth +3 -0
- checkpoint-120/scheduler.pt +3 -0
- checkpoint-120/special_tokens_map.json +1 -0
- checkpoint-120/tokenizer.json +0 -0
- checkpoint-120/tokenizer_config.json +1 -0
- checkpoint-120/trainer_state.json +61 -0
- checkpoint-120/training_args.bin +3 -0
- checkpoint-120/vocab.txt +0 -0
- pytorch_model.bin +1 -1
- runs/Sep16_17-01-08_patrick-general-gpu/events.out.tfevents.1631811685.patrick-general-gpu.176909.0 +2 -2
checkpoint-120/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": "wnli",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "not_entailment",
|
15 |
+
"1": "entailment"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"entailment": 1,
|
21 |
+
"not_entailment": 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-120/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96a9721c6d31e9668411916ac4bc18f156d3d5d7ea7a9d2c7d87bb133e6a4d86
|
3 |
+
size 866610781
|
checkpoint-120/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4014ea032366f69241cd6cfef8d01c930c919de2fdaf5a449d7333a4ee496995
|
3 |
+
size 433331373
|
checkpoint-120/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc7ddf052faf6f88a4572fb4a7a70cc4209c9052a1c3ce5b6b4ba27f86d8fb0c
|
3 |
+
size 14503
|
checkpoint-120/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de61dd29fb42e4c932e8f4a396e611c7144e38fd3e299dc2a56ff1fd5b96e50f
|
3 |
+
size 623
|
checkpoint-120/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-120/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-120/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-120/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": 120,
|
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": 0.7299,
|
14 |
+
"step": 40
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.5633802816901409,
|
19 |
+
"eval_loss": 0.6923056840896606,
|
20 |
+
"eval_runtime": 0.73,
|
21 |
+
"eval_samples_per_second": 97.265,
|
22 |
+
"eval_steps_per_second": 12.329,
|
23 |
+
"step": 40
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 1.2e-05,
|
28 |
+
"loss": 0.6982,
|
29 |
+
"step": 80
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.38028169014084506,
|
34 |
+
"eval_loss": 0.7026631832122803,
|
35 |
+
"eval_runtime": 0.7338,
|
36 |
+
"eval_samples_per_second": 96.754,
|
37 |
+
"eval_steps_per_second": 12.265,
|
38 |
+
"step": 80
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 8.000000000000001e-06,
|
43 |
+
"loss": 0.6972,
|
44 |
+
"step": 120
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_accuracy": 0.4507042253521127,
|
49 |
+
"eval_loss": 0.7005189657211304,
|
50 |
+
"eval_runtime": 0.7321,
|
51 |
+
"eval_samples_per_second": 96.982,
|
52 |
+
"eval_steps_per_second": 12.293,
|
53 |
+
"step": 120
|
54 |
+
}
|
55 |
+
],
|
56 |
+
"max_steps": 200,
|
57 |
+
"num_train_epochs": 5,
|
58 |
+
"total_flos": 501226560460800.0,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": null
|
61 |
+
}
|
checkpoint-120/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04198b57eef90f34dae9a352cd24db86f2af39af571e6944ddb87456406dcc51
|
3 |
+
size 2799
|
checkpoint-120/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 sha256:4014ea032366f69241cd6cfef8d01c930c919de2fdaf5a449d7333a4ee496995
|
3 |
size 433331373
|
runs/Sep16_17-01-08_patrick-general-gpu/events.out.tfevents.1631811685.patrick-general-gpu.176909.0
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 sha256:069a71c10dfcf7c07852fa38df8c7f28a9d2bf57cf2000202fb179b01301ddea
|
3 |
+
size 4659
|