Training in progress, epoch 1
Browse files- logs/events.out.tfevents.1702166110.joseph_legion.21448.6 +2 -2
- logs/events.out.tfevents.1702166495.joseph_legion.21448.7 +3 -0
- model.safetensors +1 -1
- run-6/checkpoint-240/config.json +37 -0
- run-6/checkpoint-240/model.safetensors +3 -0
- run-6/checkpoint-240/optimizer.pt +3 -0
- run-6/checkpoint-240/rng_state.pth +3 -0
- run-6/checkpoint-240/scheduler.pt +3 -0
- run-6/checkpoint-240/special_tokens_map.json +37 -0
- run-6/checkpoint-240/tokenizer_config.json +57 -0
- run-6/checkpoint-240/trainer_state.json +42 -0
- run-6/checkpoint-240/training_args.bin +3 -0
- run-6/checkpoint-240/vocab.txt +0 -0
- training_args.bin +1 -1
logs/events.out.tfevents.1702166110.joseph_legion.21448.6
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 sha256:2ba6f09df987ef43561f988f49516e54fec5907486ed7328faf1a6c3ddb86b88
|
3 |
+
size 7336
|
logs/events.out.tfevents.1702166495.joseph_legion.21448.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80b7d8a7ec8a13c54737187fd23d1cfca3d4707ddee308500b2ea42ac5325b13
|
3 |
+
size 4935
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267838720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ea0265220308e862f1684e9e71f34b3696ec0f222b09cdcb5a23e05c6969a45
|
3 |
size 267838720
|
run-6/checkpoint-240/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
|
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": 0,
|
13 |
+
"1": 1,
|
14 |
+
"2": 2,
|
15 |
+
"3": 3
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"label2id": {
|
19 |
+
"0": 0,
|
20 |
+
"1": 1,
|
21 |
+
"2": 2,
|
22 |
+
"3": 3
|
23 |
+
},
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "distilbert",
|
26 |
+
"n_heads": 12,
|
27 |
+
"n_layers": 6,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"problem_type": "single_label_classification",
|
30 |
+
"qa_dropout": 0.1,
|
31 |
+
"seq_classif_dropout": 0.2,
|
32 |
+
"sinusoidal_pos_embds": false,
|
33 |
+
"tie_weights_": true,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.36.0.dev0",
|
36 |
+
"vocab_size": 30522
|
37 |
+
}
|
run-6/checkpoint-240/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ea0265220308e862f1684e9e71f34b3696ec0f222b09cdcb5a23e05c6969a45
|
3 |
+
size 267838720
|
run-6/checkpoint-240/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2045bbd2baab26bc47768172237bab1663e1d3ab442cf657d617791bb0fdb91f
|
3 |
+
size 535739578
|
run-6/checkpoint-240/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2fcff0827ca522e87f836d14f0cd5430b25ecce7f7ce5f905da8656f7dcf685
|
3 |
+
size 14308
|
run-6/checkpoint-240/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33fe2e1a1e10fdfe4295220bb3140665243332972b01f90446f5098668f5e35c
|
3 |
+
size 1064
|
run-6/checkpoint-240/special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
run-6/checkpoint-240/tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "DistilBertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
run-6/checkpoint-240/trainer_state.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8706581352833638,
|
3 |
+
"best_model_checkpoint": "distilbert-hate_speech18\\run-6\\checkpoint-240",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 240,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"learning_rate": 4.4189080485362326e-06,
|
14 |
+
"loss": 0.4732,
|
15 |
+
"step": 240
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_accuracy": 0.8706581352833638,
|
20 |
+
"eval_loss": 0.45438072085380554,
|
21 |
+
"eval_runtime": 8.0476,
|
22 |
+
"eval_samples_per_second": 271.882,
|
23 |
+
"eval_steps_per_second": 17.024,
|
24 |
+
"step": 240
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"logging_steps": 500,
|
28 |
+
"max_steps": 1920,
|
29 |
+
"num_input_tokens_seen": 0,
|
30 |
+
"num_train_epochs": 8,
|
31 |
+
"save_steps": 500,
|
32 |
+
"total_flos": 163370211234720.0,
|
33 |
+
"trial_name": null,
|
34 |
+
"trial_params": {
|
35 |
+
"alpha": 0.4787113643124785,
|
36 |
+
"learning_rate": 5.050180626898551e-06,
|
37 |
+
"num_train_epochs": 8,
|
38 |
+
"per_device_eval_batch_size": 16,
|
39 |
+
"per_device_train_batch_size": 32,
|
40 |
+
"temperature": 27
|
41 |
+
}
|
42 |
+
}
|
run-6/checkpoint-240/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2caa169e337c2cdce989f2ae2edb46d990d83d311ad8d0fa7b6a8a2e8b15c867
|
3 |
+
size 4792
|
run-6/checkpoint-240/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2caa169e337c2cdce989f2ae2edb46d990d83d311ad8d0fa7b6a8a2e8b15c867
|
3 |
size 4792
|