Training in progress, epoch 1
Browse files- logs/events.out.tfevents.1702163599.joseph_legion.21448.4 +2 -2
- logs/events.out.tfevents.1702164718.joseph_legion.21448.5 +3 -0
- model.safetensors +1 -1
- run-3/checkpoint-1200/config.json +37 -0
- run-3/checkpoint-1200/model.safetensors +3 -0
- run-3/checkpoint-1200/optimizer.pt +3 -0
- run-3/checkpoint-1200/rng_state.pth +3 -0
- run-3/checkpoint-1200/scheduler.pt +3 -0
- run-3/checkpoint-1200/special_tokens_map.json +37 -0
- run-3/checkpoint-1200/tokenizer_config.json +57 -0
- run-3/checkpoint-1200/trainer_state.json +102 -0
- run-3/checkpoint-1200/training_args.bin +3 -0
- run-3/checkpoint-1200/vocab.txt +0 -0
- run-4/checkpoint-240/config.json +37 -0
- run-4/checkpoint-240/model.safetensors +3 -0
- run-4/checkpoint-240/optimizer.pt +3 -0
- run-4/checkpoint-240/rng_state.pth +3 -0
- run-4/checkpoint-240/scheduler.pt +3 -0
- run-4/checkpoint-240/special_tokens_map.json +37 -0
- run-4/checkpoint-240/tokenizer_config.json +57 -0
- run-4/checkpoint-240/trainer_state.json +42 -0
- run-4/checkpoint-240/training_args.bin +3 -0
- run-4/checkpoint-240/vocab.txt +0 -0
- training_args.bin +1 -1
logs/events.out.tfevents.1702163599.joseph_legion.21448.4
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 sha256:049d48f9a2448d76e6e4eab8e87b11e61135a6583fcc26f068e0c5e75eeacd77
|
3 |
+
size 7210
|
logs/events.out.tfevents.1702164718.joseph_legion.21448.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21dee39d88848afd4379deaa42fd47474b8bc46b5d7c3525718b9fdc81407f32
|
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:dc92d20c7025494ee51b13306d31fc17abe12b75f30222c890b227012378e89f
|
3 |
size 267838720
|
run-3/checkpoint-1200/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-3/checkpoint-1200/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80fd190433149b7b5715aeee5f985c310066ff7de009dd96f99ca68c8f112c42
|
3 |
+
size 267838720
|
run-3/checkpoint-1200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80cef666b50b10464a89b0fc143b02fe3969d4ae07cd8b99cac0fb13d80af5e2
|
3 |
+
size 535739578
|
run-3/checkpoint-1200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:189fe8fafc9fd893b1200f4891d638437b4ff8fc23d11b9ad1f4330b6d696c36
|
3 |
+
size 14308
|
run-3/checkpoint-1200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc428d497cf297eacb6a3b56ebb8e75f5210d9f17fed0e039896fb61b50e624a
|
3 |
+
size 1064
|
run-3/checkpoint-1200/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-3/checkpoint-1200/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-3/checkpoint-1200/trainer_state.json
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8848263254113345,
|
3 |
+
"best_model_checkpoint": "distilbert-hate_speech18\\run-3\\checkpoint-960",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1200,
|
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": 2.741556032723218e-06,
|
14 |
+
"loss": 0.3969,
|
15 |
+
"step": 240
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_accuracy": 0.8606032906764168,
|
20 |
+
"eval_loss": 0.38725385069847107,
|
21 |
+
"eval_runtime": 13.634,
|
22 |
+
"eval_samples_per_second": 160.481,
|
23 |
+
"eval_steps_per_second": 5.061,
|
24 |
+
"step": 240
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"learning_rate": 2.0561670245424133e-06,
|
29 |
+
"loss": 0.3833,
|
30 |
+
"step": 480
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.8816270566727605,
|
35 |
+
"eval_loss": 0.3825770616531372,
|
36 |
+
"eval_runtime": 13.6065,
|
37 |
+
"eval_samples_per_second": 160.806,
|
38 |
+
"eval_steps_per_second": 5.071,
|
39 |
+
"step": 480
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 3.0,
|
43 |
+
"learning_rate": 1.370778016361609e-06,
|
44 |
+
"loss": 0.3791,
|
45 |
+
"step": 720
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.0,
|
49 |
+
"eval_accuracy": 0.8834552102376599,
|
50 |
+
"eval_loss": 0.38152310252189636,
|
51 |
+
"eval_runtime": 13.6038,
|
52 |
+
"eval_samples_per_second": 160.837,
|
53 |
+
"eval_steps_per_second": 5.072,
|
54 |
+
"step": 720
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 4.0,
|
58 |
+
"learning_rate": 6.853890081808044e-07,
|
59 |
+
"loss": 0.3767,
|
60 |
+
"step": 960
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 4.0,
|
64 |
+
"eval_accuracy": 0.8848263254113345,
|
65 |
+
"eval_loss": 0.37997502088546753,
|
66 |
+
"eval_runtime": 13.589,
|
67 |
+
"eval_samples_per_second": 161.012,
|
68 |
+
"eval_steps_per_second": 5.078,
|
69 |
+
"step": 960
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 5.0,
|
73 |
+
"learning_rate": 0.0,
|
74 |
+
"loss": 0.3753,
|
75 |
+
"step": 1200
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.0,
|
79 |
+
"eval_accuracy": 0.8843692870201096,
|
80 |
+
"eval_loss": 0.37946945428848267,
|
81 |
+
"eval_runtime": 13.5775,
|
82 |
+
"eval_samples_per_second": 161.149,
|
83 |
+
"eval_steps_per_second": 5.082,
|
84 |
+
"step": 1200
|
85 |
+
}
|
86 |
+
],
|
87 |
+
"logging_steps": 500,
|
88 |
+
"max_steps": 1200,
|
89 |
+
"num_input_tokens_seen": 0,
|
90 |
+
"num_train_epochs": 5,
|
91 |
+
"save_steps": 500,
|
92 |
+
"total_flos": 814156076413344.0,
|
93 |
+
"trial_name": null,
|
94 |
+
"trial_params": {
|
95 |
+
"alpha": 0.3534065692399305,
|
96 |
+
"learning_rate": 3.4269450409040222e-06,
|
97 |
+
"num_train_epochs": 5,
|
98 |
+
"per_device_eval_batch_size": 32,
|
99 |
+
"per_device_train_batch_size": 32,
|
100 |
+
"temperature": 11
|
101 |
+
}
|
102 |
+
}
|
run-3/checkpoint-1200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5a387f5bff97f17f9ccdf5718f369b40c94efa84e41a438755774bcf08a1544
|
3 |
+
size 4792
|
run-3/checkpoint-1200/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/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-4/checkpoint-240/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc92d20c7025494ee51b13306d31fc17abe12b75f30222c890b227012378e89f
|
3 |
+
size 267838720
|
run-4/checkpoint-240/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:026058970c328fe11c278ebe569260370feb627f592a491bdcd79e46e6b5f355
|
3 |
+
size 535739578
|
run-4/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-4/checkpoint-240/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baf092e7fc9af76bae119c74a910bc9642d3404296bf10415fff0344cc168b0a
|
3 |
+
size 1064
|
run-4/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-4/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-4/checkpoint-240/trainer_state.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8820840950639853,
|
3 |
+
"best_model_checkpoint": "distilbert-hate_speech18\\run-4\\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": 5.8838345155265075e-06,
|
14 |
+
"loss": 0.549,
|
15 |
+
"step": 240
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_accuracy": 0.8820840950639853,
|
20 |
+
"eval_loss": 0.4940944314002991,
|
21 |
+
"eval_runtime": 8.0075,
|
22 |
+
"eval_samples_per_second": 273.244,
|
23 |
+
"eval_steps_per_second": 17.109,
|
24 |
+
"step": 240
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"logging_steps": 500,
|
28 |
+
"max_steps": 1680,
|
29 |
+
"num_input_tokens_seen": 0,
|
30 |
+
"num_train_epochs": 7,
|
31 |
+
"save_steps": 500,
|
32 |
+
"total_flos": 163370211234720.0,
|
33 |
+
"trial_name": null,
|
34 |
+
"trial_params": {
|
35 |
+
"alpha": 0.7641900951856909,
|
36 |
+
"learning_rate": 6.864473601447592e-06,
|
37 |
+
"num_train_epochs": 7,
|
38 |
+
"per_device_eval_batch_size": 16,
|
39 |
+
"per_device_train_batch_size": 32,
|
40 |
+
"temperature": 23
|
41 |
+
}
|
42 |
+
}
|
run-4/checkpoint-240/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df4793e25c9769afa8c89f2422861506d79331fa4f305d344623de77c38fc088
|
3 |
+
size 4792
|
run-4/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:df4793e25c9769afa8c89f2422861506d79331fa4f305d344623de77c38fc088
|
3 |
size 4792
|