Training in progress, epoch 1
Browse files- logs/events.out.tfevents.1702162733.joseph_legion.21448.2 +2 -2
- logs/events.out.tfevents.1702163282.joseph_legion.21448.3 +3 -0
- model.safetensors +1 -1
- run-1/checkpoint-3832/config.json +37 -0
- run-1/checkpoint-3832/model.safetensors +3 -0
- run-1/checkpoint-3832/optimizer.pt +3 -0
- run-1/checkpoint-3832/rng_state.pth +3 -0
- run-1/checkpoint-3832/scheduler.pt +3 -0
- run-1/checkpoint-3832/special_tokens_map.json +37 -0
- run-1/checkpoint-3832/tokenizer_config.json +57 -0
- run-1/checkpoint-3832/trainer_state.json +147 -0
- run-1/checkpoint-3832/training_args.bin +3 -0
- run-1/checkpoint-3832/vocab.txt +0 -0
- run-2/checkpoint-479/config.json +37 -0
- run-2/checkpoint-479/model.safetensors +3 -0
- run-2/checkpoint-479/optimizer.pt +3 -0
- run-2/checkpoint-479/rng_state.pth +3 -0
- run-2/checkpoint-479/scheduler.pt +3 -0
- run-2/checkpoint-479/special_tokens_map.json +37 -0
- run-2/checkpoint-479/tokenizer_config.json +57 -0
- run-2/checkpoint-479/trainer_state.json +42 -0
- run-2/checkpoint-479/training_args.bin +3 -0
- run-2/checkpoint-479/vocab.txt +0 -0
- training_args.bin +1 -1
logs/events.out.tfevents.1702162733.joseph_legion.21448.2
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 sha256:18e9f8e6ade4f649398e03d4f7e37f8ae3bb8ca99b75cb959559f8295b4126da
|
3 |
+
size 8648
|
logs/events.out.tfevents.1702163282.joseph_legion.21448.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:479d6df585ec8ce0c3cdae160eb026173beed30c8948fc165e4e6f0048d28fa8
|
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:e3cdf260f427e940f7219285f637131e94c525c7ad223c4822bf2a6f5ef516b5
|
3 |
size 267838720
|
run-1/checkpoint-3832/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-1/checkpoint-3832/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7c57d1892e9c1aae1a43bb0b165969cc81a1045cc800e6320b2ab8a5feb51eb
|
3 |
+
size 267838720
|
run-1/checkpoint-3832/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ae38033c84e7c20c6ab3749d055266d05f954f0e270eec26118f0585a462d32
|
3 |
+
size 535739578
|
run-1/checkpoint-3832/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f285adb7d89b36a0c41ebe3a1ff0286c70a3279c68e147d7a0ea7129fdf6ac4
|
3 |
+
size 14308
|
run-1/checkpoint-3832/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcfbcdb4bfd851d38b7d61a12b3992f25c2c7dd35c8f6e2baee45f03821bfc85
|
3 |
+
size 1064
|
run-1/checkpoint-3832/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-1/checkpoint-3832/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-1/checkpoint-3832/trainer_state.json
ADDED
@@ -0,0 +1,147 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8916819012797075,
|
3 |
+
"best_model_checkpoint": "distilbert-hate_speech18\\run-1\\checkpoint-958",
|
4 |
+
"epoch": 8.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3832,
|
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": 6.1414387289205385e-06,
|
14 |
+
"loss": 0.2985,
|
15 |
+
"step": 479
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_accuracy": 0.8784277879341865,
|
20 |
+
"eval_loss": 0.29401153326034546,
|
21 |
+
"eval_runtime": 9.4448,
|
22 |
+
"eval_samples_per_second": 231.661,
|
23 |
+
"eval_steps_per_second": 7.306,
|
24 |
+
"step": 479
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"learning_rate": 5.264090339074747e-06,
|
29 |
+
"loss": 0.2918,
|
30 |
+
"step": 958
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.8916819012797075,
|
35 |
+
"eval_loss": 0.29342585802078247,
|
36 |
+
"eval_runtime": 9.4536,
|
37 |
+
"eval_samples_per_second": 231.446,
|
38 |
+
"eval_steps_per_second": 7.299,
|
39 |
+
"step": 958
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 3.0,
|
43 |
+
"learning_rate": 4.386741949228956e-06,
|
44 |
+
"loss": 0.2879,
|
45 |
+
"step": 1437
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.0,
|
49 |
+
"eval_accuracy": 0.8875685557586838,
|
50 |
+
"eval_loss": 0.2938942015171051,
|
51 |
+
"eval_runtime": 9.4764,
|
52 |
+
"eval_samples_per_second": 230.889,
|
53 |
+
"eval_steps_per_second": 7.281,
|
54 |
+
"step": 1437
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 4.0,
|
58 |
+
"learning_rate": 3.509393559383165e-06,
|
59 |
+
"loss": 0.2853,
|
60 |
+
"step": 1916
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 4.0,
|
64 |
+
"eval_accuracy": 0.8848263254113345,
|
65 |
+
"eval_loss": 0.293885737657547,
|
66 |
+
"eval_runtime": 9.4687,
|
67 |
+
"eval_samples_per_second": 231.076,
|
68 |
+
"eval_steps_per_second": 7.287,
|
69 |
+
"step": 1916
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 5.0,
|
73 |
+
"learning_rate": 2.6320451695373736e-06,
|
74 |
+
"loss": 0.2834,
|
75 |
+
"step": 2395
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.0,
|
79 |
+
"eval_accuracy": 0.8843692870201096,
|
80 |
+
"eval_loss": 0.2947681248188019,
|
81 |
+
"eval_runtime": 9.4769,
|
82 |
+
"eval_samples_per_second": 230.877,
|
83 |
+
"eval_steps_per_second": 7.281,
|
84 |
+
"step": 2395
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.0,
|
88 |
+
"learning_rate": 1.7546967796915825e-06,
|
89 |
+
"loss": 0.2825,
|
90 |
+
"step": 2874
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 6.0,
|
94 |
+
"eval_accuracy": 0.8916819012797075,
|
95 |
+
"eval_loss": 0.2950766682624817,
|
96 |
+
"eval_runtime": 9.4662,
|
97 |
+
"eval_samples_per_second": 231.137,
|
98 |
+
"eval_steps_per_second": 7.289,
|
99 |
+
"step": 2874
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 7.0,
|
103 |
+
"learning_rate": 8.773483898457912e-07,
|
104 |
+
"loss": 0.2816,
|
105 |
+
"step": 3353
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 7.0,
|
109 |
+
"eval_accuracy": 0.8875685557586838,
|
110 |
+
"eval_loss": 0.29531416296958923,
|
111 |
+
"eval_runtime": 9.4698,
|
112 |
+
"eval_samples_per_second": 231.049,
|
113 |
+
"eval_steps_per_second": 7.286,
|
114 |
+
"step": 3353
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 8.0,
|
118 |
+
"learning_rate": 0.0,
|
119 |
+
"loss": 0.2812,
|
120 |
+
"step": 3832
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 8.0,
|
124 |
+
"eval_accuracy": 0.886654478976234,
|
125 |
+
"eval_loss": 0.2952781617641449,
|
126 |
+
"eval_runtime": 9.4795,
|
127 |
+
"eval_samples_per_second": 230.814,
|
128 |
+
"eval_steps_per_second": 7.279,
|
129 |
+
"step": 3832
|
130 |
+
}
|
131 |
+
],
|
132 |
+
"logging_steps": 500,
|
133 |
+
"max_steps": 3832,
|
134 |
+
"num_input_tokens_seen": 0,
|
135 |
+
"num_train_epochs": 8,
|
136 |
+
"save_steps": 500,
|
137 |
+
"total_flos": 1031238558991200.0,
|
138 |
+
"trial_name": null,
|
139 |
+
"trial_params": {
|
140 |
+
"alpha": 0.24491283832577226,
|
141 |
+
"learning_rate": 7.01878711876633e-06,
|
142 |
+
"num_train_epochs": 8,
|
143 |
+
"per_device_eval_batch_size": 32,
|
144 |
+
"per_device_train_batch_size": 16,
|
145 |
+
"temperature": 13
|
146 |
+
}
|
147 |
+
}
|
run-1/checkpoint-3832/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ee892723378b580d5a01e9f7cceabcc4dca2ffb2b9cb62681992da17760585a
|
3 |
+
size 4792
|
run-1/checkpoint-3832/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-479/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-2/checkpoint-479/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3cdf260f427e940f7219285f637131e94c525c7ad223c4822bf2a6f5ef516b5
|
3 |
+
size 267838720
|
run-2/checkpoint-479/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8bdafdf0f41fe29ff517e2aa31a06dcdbf55f89e4cb27e9b4079bc1d034c52c
|
3 |
+
size 535739578
|
run-2/checkpoint-479/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d46f5609acc4df73766b0f33b30656411024250c2f745a536c9e1d5d95ae5105
|
3 |
+
size 14308
|
run-2/checkpoint-479/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1e0a94f1b49e4dd1e6f232be2bfa2f882e7d37973bd54cc2fa40eb6e063a534
|
3 |
+
size 1064
|
run-2/checkpoint-479/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-2/checkpoint-479/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-2/checkpoint-479/trainer_state.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6846435100548446,
|
3 |
+
"best_model_checkpoint": "distilbert-hate_speech18\\run-2\\checkpoint-479",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 479,
|
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": 3.7733581062071546e-06,
|
14 |
+
"loss": 0.1726,
|
15 |
+
"step": 479
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_accuracy": 0.6846435100548446,
|
20 |
+
"eval_loss": 0.1708744764328003,
|
21 |
+
"eval_runtime": 8.1063,
|
22 |
+
"eval_samples_per_second": 269.915,
|
23 |
+
"eval_steps_per_second": 16.901,
|
24 |
+
"step": 479
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"logging_steps": 500,
|
28 |
+
"max_steps": 2395,
|
29 |
+
"num_input_tokens_seen": 0,
|
30 |
+
"num_train_epochs": 5,
|
31 |
+
"save_steps": 500,
|
32 |
+
"total_flos": 128356173120672.0,
|
33 |
+
"trial_name": null,
|
34 |
+
"trial_params": {
|
35 |
+
"alpha": 0.1262637885395267,
|
36 |
+
"learning_rate": 4.716697632758943e-06,
|
37 |
+
"num_train_epochs": 5,
|
38 |
+
"per_device_eval_batch_size": 16,
|
39 |
+
"per_device_train_batch_size": 16,
|
40 |
+
"temperature": 6
|
41 |
+
}
|
42 |
+
}
|
run-2/checkpoint-479/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e990dcbf9bfae76dd476bdfbf6976f1f851bf842dfffef516a3bb508e91e93fa
|
3 |
+
size 4792
|
run-2/checkpoint-479/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:e990dcbf9bfae76dd476bdfbf6976f1f851bf842dfffef516a3bb508e91e93fa
|
3 |
size 4792
|