Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +38 -0
- last-checkpoint/config.json +38 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +1 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +1 -0
- last-checkpoint/trainer_state.json +33 -0
- last-checkpoint/training_args.bin +3 -0
- last-checkpoint/vocab.txt +0 -0
- pytorch_model.bin +3 -0
- runs/May20_16-45-11_1556878e54c8/1653065256.0461662/events.out.tfevents.1653065256.1556878e54c8.71.1 +3 -0
- runs/May20_16-45-11_1556878e54c8/events.out.tfevents.1653065256.1556878e54c8.71.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "anger",
|
13 |
+
"1": "joy",
|
14 |
+
"2": "optimism",
|
15 |
+
"3": "sadness"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"label2id": {
|
19 |
+
"anger": 0,
|
20 |
+
"joy": 1,
|
21 |
+
"optimism": 2,
|
22 |
+
"sadness": 3
|
23 |
+
},
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "distilbert",
|
26 |
+
"n_heads": 12,
|
27 |
+
"n_layers": 6,
|
28 |
+
"output_past": true,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"qa_dropout": 0.1,
|
32 |
+
"seq_classif_dropout": 0.2,
|
33 |
+
"sinusoidal_pos_embds": false,
|
34 |
+
"tie_weights_": true,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.19.2",
|
37 |
+
"vocab_size": 28996
|
38 |
+
}
|
last-checkpoint/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "anger",
|
13 |
+
"1": "joy",
|
14 |
+
"2": "optimism",
|
15 |
+
"3": "sadness"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"label2id": {
|
19 |
+
"anger": 0,
|
20 |
+
"joy": 1,
|
21 |
+
"optimism": 2,
|
22 |
+
"sadness": 3
|
23 |
+
},
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "distilbert",
|
26 |
+
"n_heads": 12,
|
27 |
+
"n_layers": 6,
|
28 |
+
"output_past": true,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"qa_dropout": 0.1,
|
32 |
+
"seq_classif_dropout": 0.2,
|
33 |
+
"sinusoidal_pos_embds": false,
|
34 |
+
"tie_weights_": true,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.19.2",
|
37 |
+
"vocab_size": 28996
|
38 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c73959244780ed2bba8e269a5f5733ee0285e79e761a18e2426204da083e85e7
|
3 |
+
size 526333665
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcd4a646170bae452fd479376c51512baf9048ba690f562eced96391ff6f7489
|
3 |
+
size 263171185
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28a456a7185f5f7b097c752c4b588206eb05b773927f71481138433c212d65fd
|
3 |
+
size 13547
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9998664b834a185ccdcd3c7330ca4087af0250e9ebfcea64daaa2d74d72c1e00
|
3 |
+
size 623
|
last-checkpoint/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
last-checkpoint/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/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": "distilbert-base-cased", "tokenizer_class": "DistilBertTokenizer"}
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6013594903216822,
|
3 |
+
"best_model_checkpoint": "bert-emotion/checkpoint-815",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 815,
|
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": 3.3333333333333335e-05,
|
13 |
+
"loss": 0.8385,
|
14 |
+
"step": 815
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_fscore": 0.6013594903216822,
|
19 |
+
"eval_loss": 0.8365974426269531,
|
20 |
+
"eval_precision": 0.7865216201423099,
|
21 |
+
"eval_recall": 0.5968172119855704,
|
22 |
+
"eval_runtime": 25.3715,
|
23 |
+
"eval_samples_per_second": 14.741,
|
24 |
+
"eval_steps_per_second": 3.705,
|
25 |
+
"step": 815
|
26 |
+
}
|
27 |
+
],
|
28 |
+
"max_steps": 2445,
|
29 |
+
"num_train_epochs": 3,
|
30 |
+
"total_flos": 31667823325320.0,
|
31 |
+
"trial_name": null,
|
32 |
+
"trial_params": null
|
33 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbc667b516670c12acdc42c9ec685b6ee505fd524ed8290c611a769ee87bbb9c
|
3 |
+
size 3183
|
last-checkpoint/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcd4a646170bae452fd479376c51512baf9048ba690f562eced96391ff6f7489
|
3 |
+
size 263171185
|
runs/May20_16-45-11_1556878e54c8/1653065256.0461662/events.out.tfevents.1653065256.1556878e54c8.71.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:434adc85a06b4a262a4e4351246a237f2a09dccbdf9fdfc030e5ac7ee53301fe
|
3 |
+
size 5150
|
runs/May20_16-45-11_1556878e54c8/events.out.tfevents.1653065256.1556878e54c8.71.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2763aae57ab09c095b4a983a76823fc686059c063aaa1d19e0614e744c3b01ae
|
3 |
+
size 4109
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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": "distilbert-base-cased", "tokenizer_class": "DistilBertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbc667b516670c12acdc42c9ec685b6ee505fd524ed8290c611a769ee87bbb9c
|
3 |
+
size 3183
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|