Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-1124/config.json +28 -0
- checkpoint-1124/model.safetensors +3 -0
- checkpoint-1124/optimizer.pt +3 -0
- checkpoint-1124/rng_state.pth +3 -0
- checkpoint-1124/scheduler.pt +3 -0
- checkpoint-1124/special_tokens_map.json +37 -0
- checkpoint-1124/tokenizer.json +0 -0
- checkpoint-1124/tokenizer_config.json +58 -0
- checkpoint-1124/trainer_state.json +922 -0
- checkpoint-1124/training_args.bin +3 -0
- checkpoint-1124/vocab.txt +0 -0
- checkpoint-281/config.json +28 -0
- checkpoint-281/model.safetensors +3 -0
- checkpoint-281/optimizer.pt +3 -0
- checkpoint-281/rng_state.pth +3 -0
- checkpoint-281/scheduler.pt +3 -0
- checkpoint-281/special_tokens_map.json +37 -0
- checkpoint-281/tokenizer.json +0 -0
- checkpoint-281/tokenizer_config.json +58 -0
- checkpoint-281/trainer_state.json +262 -0
- checkpoint-281/training_args.bin +3 -0
- checkpoint-281/vocab.txt +0 -0
- checkpoint-562/config.json +28 -0
- checkpoint-562/model.safetensors +3 -0
- checkpoint-562/optimizer.pt +3 -0
- checkpoint-562/rng_state.pth +3 -0
- checkpoint-562/scheduler.pt +3 -0
- checkpoint-562/special_tokens_map.json +37 -0
- checkpoint-562/tokenizer.json +0 -0
- checkpoint-562/tokenizer_config.json +58 -0
- checkpoint-562/trainer_state.json +482 -0
- checkpoint-562/training_args.bin +3 -0
- checkpoint-562/vocab.txt +0 -0
- checkpoint-843/config.json +28 -0
- checkpoint-843/model.safetensors +3 -0
- checkpoint-843/optimizer.pt +3 -0
- checkpoint-843/rng_state.pth +3 -0
- checkpoint-843/scheduler.pt +3 -0
- checkpoint-843/special_tokens_map.json +37 -0
- checkpoint-843/tokenizer.json +0 -0
- checkpoint-843/tokenizer_config.json +58 -0
- checkpoint-843/trainer_state.json +702 -0
- checkpoint-843/training_args.bin +3 -0
- checkpoint-843/vocab.txt +0 -0
- config.json +28 -0
- events.out.tfevents.1735166948.12b685f0bef2.317.0 +3 -0
- events.out.tfevents.1735167321.12b685f0bef2.317.1 +3 -0
- events.out.tfevents.1735167522.12b685f0bef2.317.2 +3 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
checkpoint-1124/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"output_past": true,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.47.1",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 31002
|
28 |
+
}
|
checkpoint-1124/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e177e2a47fdac098a1f71d136199e251cd143f5f231b72b9c61a1ba37daf395b
|
3 |
+
size 439433208
|
checkpoint-1124/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bef0b4be91ff88def6f22ff783080da4a10d95afddb1821844e4e5509a56aeb0
|
3 |
+
size 878987514
|
checkpoint-1124/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:021dafcf09515589eb5b96af4bf26593ca1bfd3e97d9e2105bd5d30b530c14ef
|
3 |
+
size 14244
|
checkpoint-1124/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d70b37b1c5b5de28c487e573ab9b4f4517b10d5f7302c777cee3c4b45873974
|
3 |
+
size 1064
|
checkpoint-1124/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 |
+
}
|
checkpoint-1124/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1124/tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[MASK]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"3": {
|
20 |
+
"content": "[UNK]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"4": {
|
28 |
+
"content": "[CLS]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"5": {
|
36 |
+
"content": "[SEP]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": false,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": false,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
checkpoint-1124/trainer_state.json
ADDED
@@ -0,0 +1,922 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.03607647866010666,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/HateSpeech-BETO-cased/checkpoint-1124",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1124,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03558718861209965,
|
13 |
+
"grad_norm": 7.08419132232666,
|
14 |
+
"learning_rate": 2.2271714922049e-07,
|
15 |
+
"loss": 0.4085,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0711743772241993,
|
20 |
+
"grad_norm": 23.322711944580078,
|
21 |
+
"learning_rate": 4.4543429844098e-07,
|
22 |
+
"loss": 0.3565,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.10676156583629894,
|
27 |
+
"grad_norm": 8.696600914001465,
|
28 |
+
"learning_rate": 6.6815144766147e-07,
|
29 |
+
"loss": 0.3482,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1423487544483986,
|
34 |
+
"grad_norm": 14.429851531982422,
|
35 |
+
"learning_rate": 8.9086859688196e-07,
|
36 |
+
"loss": 0.3711,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.17793594306049823,
|
41 |
+
"grad_norm": 9.41112995147705,
|
42 |
+
"learning_rate": 1.11358574610245e-06,
|
43 |
+
"loss": 0.337,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.21352313167259787,
|
48 |
+
"grad_norm": 12.487126350402832,
|
49 |
+
"learning_rate": 1.33630289532294e-06,
|
50 |
+
"loss": 0.3413,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2491103202846975,
|
55 |
+
"grad_norm": 17.9010009765625,
|
56 |
+
"learning_rate": 1.55902004454343e-06,
|
57 |
+
"loss": 0.3154,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.2846975088967972,
|
62 |
+
"grad_norm": 17.09844207763672,
|
63 |
+
"learning_rate": 1.78173719376392e-06,
|
64 |
+
"loss": 0.2304,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.3202846975088968,
|
69 |
+
"grad_norm": 19.929523468017578,
|
70 |
+
"learning_rate": 2.00445434298441e-06,
|
71 |
+
"loss": 0.308,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.35587188612099646,
|
76 |
+
"grad_norm": 5.709442615509033,
|
77 |
+
"learning_rate": 2.2271714922049e-06,
|
78 |
+
"loss": 0.2692,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.3914590747330961,
|
83 |
+
"grad_norm": 19.828474044799805,
|
84 |
+
"learning_rate": 2.44988864142539e-06,
|
85 |
+
"loss": 0.2255,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.42704626334519574,
|
90 |
+
"grad_norm": 17.53233528137207,
|
91 |
+
"learning_rate": 2.67260579064588e-06,
|
92 |
+
"loss": 0.1917,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.4626334519572954,
|
97 |
+
"grad_norm": 14.940444946289062,
|
98 |
+
"learning_rate": 2.8953229398663702e-06,
|
99 |
+
"loss": 0.3019,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.498220640569395,
|
104 |
+
"grad_norm": 1.711176872253418,
|
105 |
+
"learning_rate": 3.11804008908686e-06,
|
106 |
+
"loss": 0.2032,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.5338078291814946,
|
111 |
+
"grad_norm": 7.716080665588379,
|
112 |
+
"learning_rate": 3.34075723830735e-06,
|
113 |
+
"loss": 0.2764,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.5693950177935944,
|
118 |
+
"grad_norm": 20.839887619018555,
|
119 |
+
"learning_rate": 3.56347438752784e-06,
|
120 |
+
"loss": 0.2067,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.604982206405694,
|
125 |
+
"grad_norm": 2.853170156478882,
|
126 |
+
"learning_rate": 3.78619153674833e-06,
|
127 |
+
"loss": 0.243,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.6405693950177936,
|
132 |
+
"grad_norm": 6.61458683013916,
|
133 |
+
"learning_rate": 4.00890868596882e-06,
|
134 |
+
"loss": 0.1886,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6761565836298933,
|
139 |
+
"grad_norm": 3.499279022216797,
|
140 |
+
"learning_rate": 4.231625835189309e-06,
|
141 |
+
"loss": 0.1987,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.7117437722419929,
|
146 |
+
"grad_norm": 32.111114501953125,
|
147 |
+
"learning_rate": 4.4543429844098e-06,
|
148 |
+
"loss": 0.2239,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.7473309608540926,
|
153 |
+
"grad_norm": 3.83589506149292,
|
154 |
+
"learning_rate": 4.67706013363029e-06,
|
155 |
+
"loss": 0.1891,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.7829181494661922,
|
160 |
+
"grad_norm": 3.3233108520507812,
|
161 |
+
"learning_rate": 4.89977728285078e-06,
|
162 |
+
"loss": 0.1335,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.8185053380782918,
|
167 |
+
"grad_norm": 19.36582374572754,
|
168 |
+
"learning_rate": 5.12249443207127e-06,
|
169 |
+
"loss": 0.0513,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.8540925266903915,
|
174 |
+
"grad_norm": 0.7740408182144165,
|
175 |
+
"learning_rate": 5.34521158129176e-06,
|
176 |
+
"loss": 0.1499,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.8896797153024911,
|
181 |
+
"grad_norm": 0.18774119019508362,
|
182 |
+
"learning_rate": 5.5679287305122494e-06,
|
183 |
+
"loss": 0.1303,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.9252669039145908,
|
188 |
+
"grad_norm": 0.2991533875465393,
|
189 |
+
"learning_rate": 5.7906458797327404e-06,
|
190 |
+
"loss": 0.0695,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.9608540925266904,
|
195 |
+
"grad_norm": 0.08448722958564758,
|
196 |
+
"learning_rate": 6.01336302895323e-06,
|
197 |
+
"loss": 0.1109,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.99644128113879,
|
202 |
+
"grad_norm": 30.85651397705078,
|
203 |
+
"learning_rate": 6.23608017817372e-06,
|
204 |
+
"loss": 0.2155,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.0,
|
209 |
+
"eval_accuracy": 0.9559412550066756,
|
210 |
+
"eval_f1_per_label": [
|
211 |
+
0.9255079006772009,
|
212 |
+
0.9687203791469194
|
213 |
+
],
|
214 |
+
"eval_f1_weighted": 0.9556239404117711,
|
215 |
+
"eval_loss": 0.17148031294345856,
|
216 |
+
"eval_precision_per_label": [
|
217 |
+
0.9490740740740741,
|
218 |
+
0.9587242026266416
|
219 |
+
],
|
220 |
+
"eval_precision_weighted": 0.9557995308223255,
|
221 |
+
"eval_recall_per_label": [
|
222 |
+
0.9030837004405287,
|
223 |
+
0.9789272030651341
|
224 |
+
],
|
225 |
+
"eval_recall_weighted": 0.9559412550066756,
|
226 |
+
"eval_runtime": 1.3508,
|
227 |
+
"eval_samples_per_second": 554.494,
|
228 |
+
"eval_steps_per_second": 69.589,
|
229 |
+
"step": 281
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 1.0320284697508897,
|
233 |
+
"grad_norm": 37.36682891845703,
|
234 |
+
"learning_rate": 6.458797327394209e-06,
|
235 |
+
"loss": 0.2318,
|
236 |
+
"step": 290
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.0676156583629894,
|
240 |
+
"grad_norm": 3.181389093399048,
|
241 |
+
"learning_rate": 6.6815144766147e-06,
|
242 |
+
"loss": 0.29,
|
243 |
+
"step": 300
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 1.103202846975089,
|
247 |
+
"grad_norm": 0.6792677640914917,
|
248 |
+
"learning_rate": 6.9042316258351895e-06,
|
249 |
+
"loss": 0.0621,
|
250 |
+
"step": 310
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 1.1387900355871885,
|
254 |
+
"grad_norm": 31.2163143157959,
|
255 |
+
"learning_rate": 7.12694877505568e-06,
|
256 |
+
"loss": 0.3279,
|
257 |
+
"step": 320
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 1.1743772241992882,
|
261 |
+
"grad_norm": 32.702980041503906,
|
262 |
+
"learning_rate": 7.349665924276171e-06,
|
263 |
+
"loss": 0.0851,
|
264 |
+
"step": 330
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 1.209964412811388,
|
268 |
+
"grad_norm": 76.18331146240234,
|
269 |
+
"learning_rate": 7.57238307349666e-06,
|
270 |
+
"loss": 0.3339,
|
271 |
+
"step": 340
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 1.2455516014234875,
|
275 |
+
"grad_norm": 76.69121551513672,
|
276 |
+
"learning_rate": 7.79510022271715e-06,
|
277 |
+
"loss": 0.0757,
|
278 |
+
"step": 350
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.281138790035587,
|
282 |
+
"grad_norm": 0.06500601023435593,
|
283 |
+
"learning_rate": 8.01781737193764e-06,
|
284 |
+
"loss": 0.188,
|
285 |
+
"step": 360
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 1.3167259786476868,
|
289 |
+
"grad_norm": 95.82825469970703,
|
290 |
+
"learning_rate": 8.24053452115813e-06,
|
291 |
+
"loss": 0.2278,
|
292 |
+
"step": 370
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 1.3523131672597866,
|
296 |
+
"grad_norm": 49.43801498413086,
|
297 |
+
"learning_rate": 8.463251670378619e-06,
|
298 |
+
"loss": 0.2501,
|
299 |
+
"step": 380
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 1.387900355871886,
|
303 |
+
"grad_norm": 40.980369567871094,
|
304 |
+
"learning_rate": 8.68596881959911e-06,
|
305 |
+
"loss": 0.1424,
|
306 |
+
"step": 390
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 1.4234875444839858,
|
310 |
+
"grad_norm": 1.2029680013656616,
|
311 |
+
"learning_rate": 8.9086859688196e-06,
|
312 |
+
"loss": 0.1464,
|
313 |
+
"step": 400
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 1.4590747330960854,
|
317 |
+
"grad_norm": 26.718364715576172,
|
318 |
+
"learning_rate": 9.13140311804009e-06,
|
319 |
+
"loss": 0.2213,
|
320 |
+
"step": 410
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.4946619217081851,
|
324 |
+
"grad_norm": 29.254457473754883,
|
325 |
+
"learning_rate": 9.35412026726058e-06,
|
326 |
+
"loss": 0.1796,
|
327 |
+
"step": 420
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 1.5302491103202847,
|
331 |
+
"grad_norm": 0.17349238693714142,
|
332 |
+
"learning_rate": 9.57683741648107e-06,
|
333 |
+
"loss": 0.1021,
|
334 |
+
"step": 430
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 1.5658362989323842,
|
338 |
+
"grad_norm": 0.27866968512535095,
|
339 |
+
"learning_rate": 9.79955456570156e-06,
|
340 |
+
"loss": 0.2656,
|
341 |
+
"step": 440
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 1.601423487544484,
|
345 |
+
"grad_norm": 0.02428502030670643,
|
346 |
+
"learning_rate": 9.985185185185185e-06,
|
347 |
+
"loss": 0.0504,
|
348 |
+
"step": 450
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 1.6370106761565837,
|
352 |
+
"grad_norm": 0.0974503755569458,
|
353 |
+
"learning_rate": 9.837037037037038e-06,
|
354 |
+
"loss": 0.062,
|
355 |
+
"step": 460
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 1.6725978647686834,
|
359 |
+
"grad_norm": 1.3685508966445923,
|
360 |
+
"learning_rate": 9.688888888888889e-06,
|
361 |
+
"loss": 0.0459,
|
362 |
+
"step": 470
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.708185053380783,
|
366 |
+
"grad_norm": 1.2251461744308472,
|
367 |
+
"learning_rate": 9.540740740740742e-06,
|
368 |
+
"loss": 0.1173,
|
369 |
+
"step": 480
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 1.7437722419928825,
|
373 |
+
"grad_norm": 62.15313720703125,
|
374 |
+
"learning_rate": 9.392592592592593e-06,
|
375 |
+
"loss": 0.1621,
|
376 |
+
"step": 490
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 1.7793594306049823,
|
380 |
+
"grad_norm": 0.03026748262345791,
|
381 |
+
"learning_rate": 9.244444444444445e-06,
|
382 |
+
"loss": 0.1064,
|
383 |
+
"step": 500
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 1.814946619217082,
|
387 |
+
"grad_norm": 0.4413605332374573,
|
388 |
+
"learning_rate": 9.096296296296298e-06,
|
389 |
+
"loss": 0.1794,
|
390 |
+
"step": 510
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 1.8505338078291815,
|
394 |
+
"grad_norm": 0.08637289702892303,
|
395 |
+
"learning_rate": 8.948148148148149e-06,
|
396 |
+
"loss": 0.0915,
|
397 |
+
"step": 520
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 1.886120996441281,
|
401 |
+
"grad_norm": 0.09529650211334229,
|
402 |
+
"learning_rate": 8.8e-06,
|
403 |
+
"loss": 0.052,
|
404 |
+
"step": 530
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 1.9217081850533808,
|
408 |
+
"grad_norm": 107.46017456054688,
|
409 |
+
"learning_rate": 8.651851851851852e-06,
|
410 |
+
"loss": 0.1408,
|
411 |
+
"step": 540
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 1.9572953736654806,
|
415 |
+
"grad_norm": 26.60268211364746,
|
416 |
+
"learning_rate": 8.503703703703705e-06,
|
417 |
+
"loss": 0.1605,
|
418 |
+
"step": 550
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 1.99288256227758,
|
422 |
+
"grad_norm": 0.018591415137052536,
|
423 |
+
"learning_rate": 8.355555555555556e-06,
|
424 |
+
"loss": 0.0914,
|
425 |
+
"step": 560
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 2.0,
|
429 |
+
"eval_accuracy": 0.9732977303070761,
|
430 |
+
"eval_f1_per_label": [
|
431 |
+
0.9541284403669725,
|
432 |
+
0.9811676082862524
|
433 |
+
],
|
434 |
+
"eval_f1_weighted": 0.9729728270877522,
|
435 |
+
"eval_loss": 0.1353287547826767,
|
436 |
+
"eval_precision_per_label": [
|
437 |
+
0.9952153110047847,
|
438 |
+
0.9648148148148148
|
439 |
+
],
|
440 |
+
"eval_precision_weighted": 0.9740283163303329,
|
441 |
+
"eval_recall_per_label": [
|
442 |
+
0.9162995594713657,
|
443 |
+
0.9980842911877394
|
444 |
+
],
|
445 |
+
"eval_recall_weighted": 0.9732977303070761,
|
446 |
+
"eval_runtime": 1.309,
|
447 |
+
"eval_samples_per_second": 572.195,
|
448 |
+
"eval_steps_per_second": 71.811,
|
449 |
+
"step": 562
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 2.0284697508896796,
|
453 |
+
"grad_norm": 0.015944845974445343,
|
454 |
+
"learning_rate": 8.207407407407409e-06,
|
455 |
+
"loss": 0.0011,
|
456 |
+
"step": 570
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 2.0640569395017794,
|
460 |
+
"grad_norm": 0.03662079572677612,
|
461 |
+
"learning_rate": 8.05925925925926e-06,
|
462 |
+
"loss": 0.0475,
|
463 |
+
"step": 580
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 2.099644128113879,
|
467 |
+
"grad_norm": 0.03478744253516197,
|
468 |
+
"learning_rate": 7.911111111111112e-06,
|
469 |
+
"loss": 0.0017,
|
470 |
+
"step": 590
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 2.135231316725979,
|
474 |
+
"grad_norm": 0.03390470892190933,
|
475 |
+
"learning_rate": 7.762962962962963e-06,
|
476 |
+
"loss": 0.0054,
|
477 |
+
"step": 600
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 2.170818505338078,
|
481 |
+
"grad_norm": 0.007953139953315258,
|
482 |
+
"learning_rate": 7.614814814814816e-06,
|
483 |
+
"loss": 0.0096,
|
484 |
+
"step": 610
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 2.206405693950178,
|
488 |
+
"grad_norm": 45.853023529052734,
|
489 |
+
"learning_rate": 7.4666666666666675e-06,
|
490 |
+
"loss": 0.0893,
|
491 |
+
"step": 620
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 2.2419928825622777,
|
495 |
+
"grad_norm": 0.03887489438056946,
|
496 |
+
"learning_rate": 7.31851851851852e-06,
|
497 |
+
"loss": 0.0004,
|
498 |
+
"step": 630
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 2.277580071174377,
|
502 |
+
"grad_norm": 0.04745912551879883,
|
503 |
+
"learning_rate": 7.170370370370371e-06,
|
504 |
+
"loss": 0.1963,
|
505 |
+
"step": 640
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 2.3131672597864767,
|
509 |
+
"grad_norm": 0.05072787404060364,
|
510 |
+
"learning_rate": 7.022222222222222e-06,
|
511 |
+
"loss": 0.0231,
|
512 |
+
"step": 650
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 2.3487544483985765,
|
516 |
+
"grad_norm": 0.026582635939121246,
|
517 |
+
"learning_rate": 6.8740740740740745e-06,
|
518 |
+
"loss": 0.0149,
|
519 |
+
"step": 660
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 2.3843416370106763,
|
523 |
+
"grad_norm": 0.014482633210718632,
|
524 |
+
"learning_rate": 6.725925925925927e-06,
|
525 |
+
"loss": 0.0994,
|
526 |
+
"step": 670
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 2.419928825622776,
|
530 |
+
"grad_norm": 0.025208059698343277,
|
531 |
+
"learning_rate": 6.577777777777779e-06,
|
532 |
+
"loss": 0.0006,
|
533 |
+
"step": 680
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 2.4555160142348753,
|
537 |
+
"grad_norm": 0.01709064655005932,
|
538 |
+
"learning_rate": 6.42962962962963e-06,
|
539 |
+
"loss": 0.1219,
|
540 |
+
"step": 690
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 2.491103202846975,
|
544 |
+
"grad_norm": 0.1339588463306427,
|
545 |
+
"learning_rate": 6.2814814814814814e-06,
|
546 |
+
"loss": 0.0006,
|
547 |
+
"step": 700
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 2.526690391459075,
|
551 |
+
"grad_norm": 24.798721313476562,
|
552 |
+
"learning_rate": 6.133333333333334e-06,
|
553 |
+
"loss": 0.0029,
|
554 |
+
"step": 710
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 2.562277580071174,
|
558 |
+
"grad_norm": 1.3540862798690796,
|
559 |
+
"learning_rate": 5.985185185185186e-06,
|
560 |
+
"loss": 0.081,
|
561 |
+
"step": 720
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 2.597864768683274,
|
565 |
+
"grad_norm": 0.04109741002321243,
|
566 |
+
"learning_rate": 5.837037037037038e-06,
|
567 |
+
"loss": 0.0006,
|
568 |
+
"step": 730
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 2.6334519572953736,
|
572 |
+
"grad_norm": 0.010597619228065014,
|
573 |
+
"learning_rate": 5.688888888888889e-06,
|
574 |
+
"loss": 0.013,
|
575 |
+
"step": 740
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 2.6690391459074734,
|
579 |
+
"grad_norm": 0.02383551187813282,
|
580 |
+
"learning_rate": 5.540740740740741e-06,
|
581 |
+
"loss": 0.0008,
|
582 |
+
"step": 750
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 2.704626334519573,
|
586 |
+
"grad_norm": 1.2794164419174194,
|
587 |
+
"learning_rate": 5.392592592592593e-06,
|
588 |
+
"loss": 0.1707,
|
589 |
+
"step": 760
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 2.7402135231316724,
|
593 |
+
"grad_norm": 0.014402506873011589,
|
594 |
+
"learning_rate": 5.244444444444445e-06,
|
595 |
+
"loss": 0.0864,
|
596 |
+
"step": 770
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 2.775800711743772,
|
600 |
+
"grad_norm": 0.013125807978212833,
|
601 |
+
"learning_rate": 5.096296296296297e-06,
|
602 |
+
"loss": 0.0205,
|
603 |
+
"step": 780
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 2.811387900355872,
|
607 |
+
"grad_norm": 0.2091672271490097,
|
608 |
+
"learning_rate": 4.9481481481481485e-06,
|
609 |
+
"loss": 0.0027,
|
610 |
+
"step": 790
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 2.8469750889679717,
|
614 |
+
"grad_norm": 0.13218224048614502,
|
615 |
+
"learning_rate": 4.800000000000001e-06,
|
616 |
+
"loss": 0.0004,
|
617 |
+
"step": 800
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 2.882562277580071,
|
621 |
+
"grad_norm": 2.1445350646972656,
|
622 |
+
"learning_rate": 4.651851851851853e-06,
|
623 |
+
"loss": 0.1045,
|
624 |
+
"step": 810
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 2.9181494661921707,
|
628 |
+
"grad_norm": 0.016628708690404892,
|
629 |
+
"learning_rate": 4.503703703703704e-06,
|
630 |
+
"loss": 0.0005,
|
631 |
+
"step": 820
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 2.9537366548042705,
|
635 |
+
"grad_norm": 0.04098201170563698,
|
636 |
+
"learning_rate": 4.3555555555555555e-06,
|
637 |
+
"loss": 0.0569,
|
638 |
+
"step": 830
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 2.9893238434163703,
|
642 |
+
"grad_norm": 0.7140023708343506,
|
643 |
+
"learning_rate": 4.207407407407408e-06,
|
644 |
+
"loss": 0.0014,
|
645 |
+
"step": 840
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 3.0,
|
649 |
+
"eval_accuracy": 0.9893190921228304,
|
650 |
+
"eval_f1_per_label": [
|
651 |
+
0.9821428571428571,
|
652 |
+
0.9923809523809524
|
653 |
+
],
|
654 |
+
"eval_f1_weighted": 0.989278085065802,
|
655 |
+
"eval_loss": 0.050094157457351685,
|
656 |
+
"eval_precision_per_label": [
|
657 |
+
0.995475113122172,
|
658 |
+
0.9867424242424242
|
659 |
+
],
|
660 |
+
"eval_precision_weighted": 0.9893890469069138,
|
661 |
+
"eval_recall_per_label": [
|
662 |
+
0.9691629955947136,
|
663 |
+
0.9980842911877394
|
664 |
+
],
|
665 |
+
"eval_recall_weighted": 0.9893190921228304,
|
666 |
+
"eval_runtime": 1.3422,
|
667 |
+
"eval_samples_per_second": 558.027,
|
668 |
+
"eval_steps_per_second": 70.033,
|
669 |
+
"step": 843
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 3.0249110320284696,
|
673 |
+
"grad_norm": 0.009055254980921745,
|
674 |
+
"learning_rate": 4.05925925925926e-06,
|
675 |
+
"loss": 0.124,
|
676 |
+
"step": 850
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 3.0604982206405693,
|
680 |
+
"grad_norm": 0.005354477558284998,
|
681 |
+
"learning_rate": 3.911111111111112e-06,
|
682 |
+
"loss": 0.0008,
|
683 |
+
"step": 860
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 3.096085409252669,
|
687 |
+
"grad_norm": 0.006784161552786827,
|
688 |
+
"learning_rate": 3.7629629629629633e-06,
|
689 |
+
"loss": 0.0736,
|
690 |
+
"step": 870
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 3.131672597864769,
|
694 |
+
"grad_norm": 0.007448482792824507,
|
695 |
+
"learning_rate": 3.614814814814815e-06,
|
696 |
+
"loss": 0.0047,
|
697 |
+
"step": 880
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 3.167259786476868,
|
701 |
+
"grad_norm": 0.0065169306471943855,
|
702 |
+
"learning_rate": 3.4666666666666672e-06,
|
703 |
+
"loss": 0.0003,
|
704 |
+
"step": 890
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 3.202846975088968,
|
708 |
+
"grad_norm": 0.00644827401265502,
|
709 |
+
"learning_rate": 3.3185185185185185e-06,
|
710 |
+
"loss": 0.0007,
|
711 |
+
"step": 900
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 3.2384341637010676,
|
715 |
+
"grad_norm": 12.251897811889648,
|
716 |
+
"learning_rate": 3.1703703703703707e-06,
|
717 |
+
"loss": 0.0016,
|
718 |
+
"step": 910
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 3.2740213523131674,
|
722 |
+
"grad_norm": 0.010300640016794205,
|
723 |
+
"learning_rate": 3.0222222222222225e-06,
|
724 |
+
"loss": 0.0002,
|
725 |
+
"step": 920
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 3.309608540925267,
|
729 |
+
"grad_norm": 0.006541989278048277,
|
730 |
+
"learning_rate": 2.874074074074074e-06,
|
731 |
+
"loss": 0.0054,
|
732 |
+
"step": 930
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 3.3451957295373664,
|
736 |
+
"grad_norm": 0.08283556252717972,
|
737 |
+
"learning_rate": 2.7259259259259264e-06,
|
738 |
+
"loss": 0.0006,
|
739 |
+
"step": 940
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 3.380782918149466,
|
743 |
+
"grad_norm": 0.005921730771660805,
|
744 |
+
"learning_rate": 2.577777777777778e-06,
|
745 |
+
"loss": 0.0003,
|
746 |
+
"step": 950
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 3.416370106761566,
|
750 |
+
"grad_norm": 0.004639245569705963,
|
751 |
+
"learning_rate": 2.42962962962963e-06,
|
752 |
+
"loss": 0.0003,
|
753 |
+
"step": 960
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 3.4519572953736652,
|
757 |
+
"grad_norm": 0.16998454928398132,
|
758 |
+
"learning_rate": 2.2814814814814816e-06,
|
759 |
+
"loss": 0.0007,
|
760 |
+
"step": 970
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 3.487544483985765,
|
764 |
+
"grad_norm": 0.005660816095769405,
|
765 |
+
"learning_rate": 2.133333333333334e-06,
|
766 |
+
"loss": 0.0241,
|
767 |
+
"step": 980
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 3.5231316725978647,
|
771 |
+
"grad_norm": 0.01572972722351551,
|
772 |
+
"learning_rate": 1.985185185185185e-06,
|
773 |
+
"loss": 0.0022,
|
774 |
+
"step": 990
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 3.5587188612099645,
|
778 |
+
"grad_norm": 0.01506053563207388,
|
779 |
+
"learning_rate": 1.837037037037037e-06,
|
780 |
+
"loss": 0.0017,
|
781 |
+
"step": 1000
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 3.5943060498220643,
|
785 |
+
"grad_norm": 0.06420188397169113,
|
786 |
+
"learning_rate": 1.688888888888889e-06,
|
787 |
+
"loss": 0.0981,
|
788 |
+
"step": 1010
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 3.6298932384341636,
|
792 |
+
"grad_norm": 0.050418056547641754,
|
793 |
+
"learning_rate": 1.540740740740741e-06,
|
794 |
+
"loss": 0.0002,
|
795 |
+
"step": 1020
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 3.6654804270462633,
|
799 |
+
"grad_norm": 0.1331329494714737,
|
800 |
+
"learning_rate": 1.3925925925925925e-06,
|
801 |
+
"loss": 0.0002,
|
802 |
+
"step": 1030
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 3.701067615658363,
|
806 |
+
"grad_norm": 0.0047861747443675995,
|
807 |
+
"learning_rate": 1.2444444444444445e-06,
|
808 |
+
"loss": 0.0007,
|
809 |
+
"step": 1040
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 3.7366548042704624,
|
813 |
+
"grad_norm": 0.004302954766899347,
|
814 |
+
"learning_rate": 1.0962962962962965e-06,
|
815 |
+
"loss": 0.0002,
|
816 |
+
"step": 1050
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 3.772241992882562,
|
820 |
+
"grad_norm": 0.0052270120941102505,
|
821 |
+
"learning_rate": 9.481481481481482e-07,
|
822 |
+
"loss": 0.0003,
|
823 |
+
"step": 1060
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 3.807829181494662,
|
827 |
+
"grad_norm": 0.006781002506613731,
|
828 |
+
"learning_rate": 8.000000000000001e-07,
|
829 |
+
"loss": 0.0003,
|
830 |
+
"step": 1070
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 3.8434163701067616,
|
834 |
+
"grad_norm": 0.006440193857997656,
|
835 |
+
"learning_rate": 6.518518518518518e-07,
|
836 |
+
"loss": 0.0003,
|
837 |
+
"step": 1080
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 3.8790035587188614,
|
841 |
+
"grad_norm": 0.009248029440641403,
|
842 |
+
"learning_rate": 5.037037037037038e-07,
|
843 |
+
"loss": 0.0061,
|
844 |
+
"step": 1090
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 3.914590747330961,
|
848 |
+
"grad_norm": 0.011829700320959091,
|
849 |
+
"learning_rate": 3.555555555555556e-07,
|
850 |
+
"loss": 0.0003,
|
851 |
+
"step": 1100
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 3.9501779359430604,
|
855 |
+
"grad_norm": 0.024425974115729332,
|
856 |
+
"learning_rate": 2.074074074074074e-07,
|
857 |
+
"loss": 0.0676,
|
858 |
+
"step": 1110
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 3.98576512455516,
|
862 |
+
"grad_norm": 0.00512115890160203,
|
863 |
+
"learning_rate": 5.9259259259259263e-08,
|
864 |
+
"loss": 0.0002,
|
865 |
+
"step": 1120
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 4.0,
|
869 |
+
"eval_accuracy": 0.9933244325767691,
|
870 |
+
"eval_f1_per_label": [
|
871 |
+
0.9888641425389755,
|
872 |
+
0.9952335557673975
|
873 |
+
],
|
874 |
+
"eval_f1_weighted": 0.9933031728530427,
|
875 |
+
"eval_loss": 0.03607647866010666,
|
876 |
+
"eval_precision_per_label": [
|
877 |
+
1.0,
|
878 |
+
0.9905123339658444
|
879 |
+
],
|
880 |
+
"eval_precision_weighted": 0.9933877681310691,
|
881 |
+
"eval_recall_per_label": [
|
882 |
+
0.9779735682819384,
|
883 |
+
1.0
|
884 |
+
],
|
885 |
+
"eval_recall_weighted": 0.9933244325767691,
|
886 |
+
"eval_runtime": 5.013,
|
887 |
+
"eval_samples_per_second": 149.411,
|
888 |
+
"eval_steps_per_second": 18.751,
|
889 |
+
"step": 1124
|
890 |
+
}
|
891 |
+
],
|
892 |
+
"logging_steps": 10,
|
893 |
+
"max_steps": 1124,
|
894 |
+
"num_input_tokens_seen": 0,
|
895 |
+
"num_train_epochs": 4,
|
896 |
+
"save_steps": 500,
|
897 |
+
"stateful_callbacks": {
|
898 |
+
"EarlyStoppingCallback": {
|
899 |
+
"args": {
|
900 |
+
"early_stopping_patience": 3,
|
901 |
+
"early_stopping_threshold": 0.0
|
902 |
+
},
|
903 |
+
"attributes": {
|
904 |
+
"early_stopping_patience_counter": 0
|
905 |
+
}
|
906 |
+
},
|
907 |
+
"TrainerControl": {
|
908 |
+
"args": {
|
909 |
+
"should_epoch_stop": false,
|
910 |
+
"should_evaluate": false,
|
911 |
+
"should_log": false,
|
912 |
+
"should_save": true,
|
913 |
+
"should_training_stop": true
|
914 |
+
},
|
915 |
+
"attributes": {}
|
916 |
+
}
|
917 |
+
},
|
918 |
+
"total_flos": 87830786944920.0,
|
919 |
+
"train_batch_size": 8,
|
920 |
+
"trial_name": null,
|
921 |
+
"trial_params": null
|
922 |
+
}
|
checkpoint-1124/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b507d5295c042031ea8738de84bfa33f52abd9440ecb04319aeef48c60251cc
|
3 |
+
size 5368
|
checkpoint-1124/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-281/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"output_past": true,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.47.1",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 31002
|
28 |
+
}
|
checkpoint-281/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efdb993d49b41c4c1fcbbb39dbc455ee9d162c89a4c768e8a7a5ccae5440c764
|
3 |
+
size 439433208
|
checkpoint-281/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:771a327041481181f4909d2f2cd4e95738535c6e48b1d36c9ad4850215e49913
|
3 |
+
size 878987514
|
checkpoint-281/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b5a76b935800a43630c09c75898ccd728dcc94793a2964832f19ec46670522f
|
3 |
+
size 14244
|
checkpoint-281/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6cfc827ec3fd27bbfd0b5cb5e18a8d936dac58d028a6d7a8b604d7c97cc3381
|
3 |
+
size 1064
|
checkpoint-281/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 |
+
}
|
checkpoint-281/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-281/tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[MASK]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"3": {
|
20 |
+
"content": "[UNK]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"4": {
|
28 |
+
"content": "[CLS]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"5": {
|
36 |
+
"content": "[SEP]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": false,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": false,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
checkpoint-281/trainer_state.json
ADDED
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.17148031294345856,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/HateSpeech-BETO-cased/checkpoint-281",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 281,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03558718861209965,
|
13 |
+
"grad_norm": 7.08419132232666,
|
14 |
+
"learning_rate": 2.2271714922049e-07,
|
15 |
+
"loss": 0.4085,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0711743772241993,
|
20 |
+
"grad_norm": 23.322711944580078,
|
21 |
+
"learning_rate": 4.4543429844098e-07,
|
22 |
+
"loss": 0.3565,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.10676156583629894,
|
27 |
+
"grad_norm": 8.696600914001465,
|
28 |
+
"learning_rate": 6.6815144766147e-07,
|
29 |
+
"loss": 0.3482,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1423487544483986,
|
34 |
+
"grad_norm": 14.429851531982422,
|
35 |
+
"learning_rate": 8.9086859688196e-07,
|
36 |
+
"loss": 0.3711,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.17793594306049823,
|
41 |
+
"grad_norm": 9.41112995147705,
|
42 |
+
"learning_rate": 1.11358574610245e-06,
|
43 |
+
"loss": 0.337,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.21352313167259787,
|
48 |
+
"grad_norm": 12.487126350402832,
|
49 |
+
"learning_rate": 1.33630289532294e-06,
|
50 |
+
"loss": 0.3413,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2491103202846975,
|
55 |
+
"grad_norm": 17.9010009765625,
|
56 |
+
"learning_rate": 1.55902004454343e-06,
|
57 |
+
"loss": 0.3154,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.2846975088967972,
|
62 |
+
"grad_norm": 17.09844207763672,
|
63 |
+
"learning_rate": 1.78173719376392e-06,
|
64 |
+
"loss": 0.2304,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.3202846975088968,
|
69 |
+
"grad_norm": 19.929523468017578,
|
70 |
+
"learning_rate": 2.00445434298441e-06,
|
71 |
+
"loss": 0.308,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.35587188612099646,
|
76 |
+
"grad_norm": 5.709442615509033,
|
77 |
+
"learning_rate": 2.2271714922049e-06,
|
78 |
+
"loss": 0.2692,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.3914590747330961,
|
83 |
+
"grad_norm": 19.828474044799805,
|
84 |
+
"learning_rate": 2.44988864142539e-06,
|
85 |
+
"loss": 0.2255,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.42704626334519574,
|
90 |
+
"grad_norm": 17.53233528137207,
|
91 |
+
"learning_rate": 2.67260579064588e-06,
|
92 |
+
"loss": 0.1917,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.4626334519572954,
|
97 |
+
"grad_norm": 14.940444946289062,
|
98 |
+
"learning_rate": 2.8953229398663702e-06,
|
99 |
+
"loss": 0.3019,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.498220640569395,
|
104 |
+
"grad_norm": 1.711176872253418,
|
105 |
+
"learning_rate": 3.11804008908686e-06,
|
106 |
+
"loss": 0.2032,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.5338078291814946,
|
111 |
+
"grad_norm": 7.716080665588379,
|
112 |
+
"learning_rate": 3.34075723830735e-06,
|
113 |
+
"loss": 0.2764,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.5693950177935944,
|
118 |
+
"grad_norm": 20.839887619018555,
|
119 |
+
"learning_rate": 3.56347438752784e-06,
|
120 |
+
"loss": 0.2067,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.604982206405694,
|
125 |
+
"grad_norm": 2.853170156478882,
|
126 |
+
"learning_rate": 3.78619153674833e-06,
|
127 |
+
"loss": 0.243,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.6405693950177936,
|
132 |
+
"grad_norm": 6.61458683013916,
|
133 |
+
"learning_rate": 4.00890868596882e-06,
|
134 |
+
"loss": 0.1886,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6761565836298933,
|
139 |
+
"grad_norm": 3.499279022216797,
|
140 |
+
"learning_rate": 4.231625835189309e-06,
|
141 |
+
"loss": 0.1987,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.7117437722419929,
|
146 |
+
"grad_norm": 32.111114501953125,
|
147 |
+
"learning_rate": 4.4543429844098e-06,
|
148 |
+
"loss": 0.2239,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.7473309608540926,
|
153 |
+
"grad_norm": 3.83589506149292,
|
154 |
+
"learning_rate": 4.67706013363029e-06,
|
155 |
+
"loss": 0.1891,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.7829181494661922,
|
160 |
+
"grad_norm": 3.3233108520507812,
|
161 |
+
"learning_rate": 4.89977728285078e-06,
|
162 |
+
"loss": 0.1335,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.8185053380782918,
|
167 |
+
"grad_norm": 19.36582374572754,
|
168 |
+
"learning_rate": 5.12249443207127e-06,
|
169 |
+
"loss": 0.0513,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.8540925266903915,
|
174 |
+
"grad_norm": 0.7740408182144165,
|
175 |
+
"learning_rate": 5.34521158129176e-06,
|
176 |
+
"loss": 0.1499,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.8896797153024911,
|
181 |
+
"grad_norm": 0.18774119019508362,
|
182 |
+
"learning_rate": 5.5679287305122494e-06,
|
183 |
+
"loss": 0.1303,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.9252669039145908,
|
188 |
+
"grad_norm": 0.2991533875465393,
|
189 |
+
"learning_rate": 5.7906458797327404e-06,
|
190 |
+
"loss": 0.0695,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.9608540925266904,
|
195 |
+
"grad_norm": 0.08448722958564758,
|
196 |
+
"learning_rate": 6.01336302895323e-06,
|
197 |
+
"loss": 0.1109,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.99644128113879,
|
202 |
+
"grad_norm": 30.85651397705078,
|
203 |
+
"learning_rate": 6.23608017817372e-06,
|
204 |
+
"loss": 0.2155,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.0,
|
209 |
+
"eval_accuracy": 0.9559412550066756,
|
210 |
+
"eval_f1_per_label": [
|
211 |
+
0.9255079006772009,
|
212 |
+
0.9687203791469194
|
213 |
+
],
|
214 |
+
"eval_f1_weighted": 0.9556239404117711,
|
215 |
+
"eval_loss": 0.17148031294345856,
|
216 |
+
"eval_precision_per_label": [
|
217 |
+
0.9490740740740741,
|
218 |
+
0.9587242026266416
|
219 |
+
],
|
220 |
+
"eval_precision_weighted": 0.9557995308223255,
|
221 |
+
"eval_recall_per_label": [
|
222 |
+
0.9030837004405287,
|
223 |
+
0.9789272030651341
|
224 |
+
],
|
225 |
+
"eval_recall_weighted": 0.9559412550066756,
|
226 |
+
"eval_runtime": 1.3508,
|
227 |
+
"eval_samples_per_second": 554.494,
|
228 |
+
"eval_steps_per_second": 69.589,
|
229 |
+
"step": 281
|
230 |
+
}
|
231 |
+
],
|
232 |
+
"logging_steps": 10,
|
233 |
+
"max_steps": 1124,
|
234 |
+
"num_input_tokens_seen": 0,
|
235 |
+
"num_train_epochs": 4,
|
236 |
+
"save_steps": 500,
|
237 |
+
"stateful_callbacks": {
|
238 |
+
"EarlyStoppingCallback": {
|
239 |
+
"args": {
|
240 |
+
"early_stopping_patience": 3,
|
241 |
+
"early_stopping_threshold": 0.0
|
242 |
+
},
|
243 |
+
"attributes": {
|
244 |
+
"early_stopping_patience_counter": 0
|
245 |
+
}
|
246 |
+
},
|
247 |
+
"TrainerControl": {
|
248 |
+
"args": {
|
249 |
+
"should_epoch_stop": false,
|
250 |
+
"should_evaluate": false,
|
251 |
+
"should_log": false,
|
252 |
+
"should_save": true,
|
253 |
+
"should_training_stop": false
|
254 |
+
},
|
255 |
+
"attributes": {}
|
256 |
+
}
|
257 |
+
},
|
258 |
+
"total_flos": 21962578679640.0,
|
259 |
+
"train_batch_size": 8,
|
260 |
+
"trial_name": null,
|
261 |
+
"trial_params": null
|
262 |
+
}
|
checkpoint-281/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b507d5295c042031ea8738de84bfa33f52abd9440ecb04319aeef48c60251cc
|
3 |
+
size 5368
|
checkpoint-281/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-562/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"output_past": true,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.47.1",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 31002
|
28 |
+
}
|
checkpoint-562/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b19f9c00971c19b2edf8e1d8be4d704e00d162677a0ad1b622d5e94f0f6b8ce5
|
3 |
+
size 439433208
|
checkpoint-562/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2d2e4a01719d785dc02d76374f1a32373d4892ed92e45cb81ba5f0507333a0c
|
3 |
+
size 878987514
|
checkpoint-562/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4320cf79393d41a5c3747b22ed1eb9ca5f29d5f3ce7110a2a19afe7013a6e8c
|
3 |
+
size 14244
|
checkpoint-562/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b061e09194d1c509c3f2204af9e5d068a8b8fffa0a8816fafb4a31f7f39f8e56
|
3 |
+
size 1064
|
checkpoint-562/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 |
+
}
|
checkpoint-562/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-562/tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[MASK]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"3": {
|
20 |
+
"content": "[UNK]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"4": {
|
28 |
+
"content": "[CLS]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"5": {
|
36 |
+
"content": "[SEP]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": false,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": false,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
checkpoint-562/trainer_state.json
ADDED
@@ -0,0 +1,482 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.1353287547826767,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/HateSpeech-BETO-cased/checkpoint-562",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 562,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03558718861209965,
|
13 |
+
"grad_norm": 7.08419132232666,
|
14 |
+
"learning_rate": 2.2271714922049e-07,
|
15 |
+
"loss": 0.4085,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0711743772241993,
|
20 |
+
"grad_norm": 23.322711944580078,
|
21 |
+
"learning_rate": 4.4543429844098e-07,
|
22 |
+
"loss": 0.3565,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.10676156583629894,
|
27 |
+
"grad_norm": 8.696600914001465,
|
28 |
+
"learning_rate": 6.6815144766147e-07,
|
29 |
+
"loss": 0.3482,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1423487544483986,
|
34 |
+
"grad_norm": 14.429851531982422,
|
35 |
+
"learning_rate": 8.9086859688196e-07,
|
36 |
+
"loss": 0.3711,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.17793594306049823,
|
41 |
+
"grad_norm": 9.41112995147705,
|
42 |
+
"learning_rate": 1.11358574610245e-06,
|
43 |
+
"loss": 0.337,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.21352313167259787,
|
48 |
+
"grad_norm": 12.487126350402832,
|
49 |
+
"learning_rate": 1.33630289532294e-06,
|
50 |
+
"loss": 0.3413,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2491103202846975,
|
55 |
+
"grad_norm": 17.9010009765625,
|
56 |
+
"learning_rate": 1.55902004454343e-06,
|
57 |
+
"loss": 0.3154,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.2846975088967972,
|
62 |
+
"grad_norm": 17.09844207763672,
|
63 |
+
"learning_rate": 1.78173719376392e-06,
|
64 |
+
"loss": 0.2304,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.3202846975088968,
|
69 |
+
"grad_norm": 19.929523468017578,
|
70 |
+
"learning_rate": 2.00445434298441e-06,
|
71 |
+
"loss": 0.308,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.35587188612099646,
|
76 |
+
"grad_norm": 5.709442615509033,
|
77 |
+
"learning_rate": 2.2271714922049e-06,
|
78 |
+
"loss": 0.2692,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.3914590747330961,
|
83 |
+
"grad_norm": 19.828474044799805,
|
84 |
+
"learning_rate": 2.44988864142539e-06,
|
85 |
+
"loss": 0.2255,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.42704626334519574,
|
90 |
+
"grad_norm": 17.53233528137207,
|
91 |
+
"learning_rate": 2.67260579064588e-06,
|
92 |
+
"loss": 0.1917,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.4626334519572954,
|
97 |
+
"grad_norm": 14.940444946289062,
|
98 |
+
"learning_rate": 2.8953229398663702e-06,
|
99 |
+
"loss": 0.3019,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.498220640569395,
|
104 |
+
"grad_norm": 1.711176872253418,
|
105 |
+
"learning_rate": 3.11804008908686e-06,
|
106 |
+
"loss": 0.2032,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.5338078291814946,
|
111 |
+
"grad_norm": 7.716080665588379,
|
112 |
+
"learning_rate": 3.34075723830735e-06,
|
113 |
+
"loss": 0.2764,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.5693950177935944,
|
118 |
+
"grad_norm": 20.839887619018555,
|
119 |
+
"learning_rate": 3.56347438752784e-06,
|
120 |
+
"loss": 0.2067,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.604982206405694,
|
125 |
+
"grad_norm": 2.853170156478882,
|
126 |
+
"learning_rate": 3.78619153674833e-06,
|
127 |
+
"loss": 0.243,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.6405693950177936,
|
132 |
+
"grad_norm": 6.61458683013916,
|
133 |
+
"learning_rate": 4.00890868596882e-06,
|
134 |
+
"loss": 0.1886,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6761565836298933,
|
139 |
+
"grad_norm": 3.499279022216797,
|
140 |
+
"learning_rate": 4.231625835189309e-06,
|
141 |
+
"loss": 0.1987,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.7117437722419929,
|
146 |
+
"grad_norm": 32.111114501953125,
|
147 |
+
"learning_rate": 4.4543429844098e-06,
|
148 |
+
"loss": 0.2239,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.7473309608540926,
|
153 |
+
"grad_norm": 3.83589506149292,
|
154 |
+
"learning_rate": 4.67706013363029e-06,
|
155 |
+
"loss": 0.1891,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.7829181494661922,
|
160 |
+
"grad_norm": 3.3233108520507812,
|
161 |
+
"learning_rate": 4.89977728285078e-06,
|
162 |
+
"loss": 0.1335,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.8185053380782918,
|
167 |
+
"grad_norm": 19.36582374572754,
|
168 |
+
"learning_rate": 5.12249443207127e-06,
|
169 |
+
"loss": 0.0513,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.8540925266903915,
|
174 |
+
"grad_norm": 0.7740408182144165,
|
175 |
+
"learning_rate": 5.34521158129176e-06,
|
176 |
+
"loss": 0.1499,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.8896797153024911,
|
181 |
+
"grad_norm": 0.18774119019508362,
|
182 |
+
"learning_rate": 5.5679287305122494e-06,
|
183 |
+
"loss": 0.1303,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.9252669039145908,
|
188 |
+
"grad_norm": 0.2991533875465393,
|
189 |
+
"learning_rate": 5.7906458797327404e-06,
|
190 |
+
"loss": 0.0695,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.9608540925266904,
|
195 |
+
"grad_norm": 0.08448722958564758,
|
196 |
+
"learning_rate": 6.01336302895323e-06,
|
197 |
+
"loss": 0.1109,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.99644128113879,
|
202 |
+
"grad_norm": 30.85651397705078,
|
203 |
+
"learning_rate": 6.23608017817372e-06,
|
204 |
+
"loss": 0.2155,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.0,
|
209 |
+
"eval_accuracy": 0.9559412550066756,
|
210 |
+
"eval_f1_per_label": [
|
211 |
+
0.9255079006772009,
|
212 |
+
0.9687203791469194
|
213 |
+
],
|
214 |
+
"eval_f1_weighted": 0.9556239404117711,
|
215 |
+
"eval_loss": 0.17148031294345856,
|
216 |
+
"eval_precision_per_label": [
|
217 |
+
0.9490740740740741,
|
218 |
+
0.9587242026266416
|
219 |
+
],
|
220 |
+
"eval_precision_weighted": 0.9557995308223255,
|
221 |
+
"eval_recall_per_label": [
|
222 |
+
0.9030837004405287,
|
223 |
+
0.9789272030651341
|
224 |
+
],
|
225 |
+
"eval_recall_weighted": 0.9559412550066756,
|
226 |
+
"eval_runtime": 1.3508,
|
227 |
+
"eval_samples_per_second": 554.494,
|
228 |
+
"eval_steps_per_second": 69.589,
|
229 |
+
"step": 281
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 1.0320284697508897,
|
233 |
+
"grad_norm": 37.36682891845703,
|
234 |
+
"learning_rate": 6.458797327394209e-06,
|
235 |
+
"loss": 0.2318,
|
236 |
+
"step": 290
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.0676156583629894,
|
240 |
+
"grad_norm": 3.181389093399048,
|
241 |
+
"learning_rate": 6.6815144766147e-06,
|
242 |
+
"loss": 0.29,
|
243 |
+
"step": 300
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 1.103202846975089,
|
247 |
+
"grad_norm": 0.6792677640914917,
|
248 |
+
"learning_rate": 6.9042316258351895e-06,
|
249 |
+
"loss": 0.0621,
|
250 |
+
"step": 310
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 1.1387900355871885,
|
254 |
+
"grad_norm": 31.2163143157959,
|
255 |
+
"learning_rate": 7.12694877505568e-06,
|
256 |
+
"loss": 0.3279,
|
257 |
+
"step": 320
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 1.1743772241992882,
|
261 |
+
"grad_norm": 32.702980041503906,
|
262 |
+
"learning_rate": 7.349665924276171e-06,
|
263 |
+
"loss": 0.0851,
|
264 |
+
"step": 330
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 1.209964412811388,
|
268 |
+
"grad_norm": 76.18331146240234,
|
269 |
+
"learning_rate": 7.57238307349666e-06,
|
270 |
+
"loss": 0.3339,
|
271 |
+
"step": 340
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 1.2455516014234875,
|
275 |
+
"grad_norm": 76.69121551513672,
|
276 |
+
"learning_rate": 7.79510022271715e-06,
|
277 |
+
"loss": 0.0757,
|
278 |
+
"step": 350
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.281138790035587,
|
282 |
+
"grad_norm": 0.06500601023435593,
|
283 |
+
"learning_rate": 8.01781737193764e-06,
|
284 |
+
"loss": 0.188,
|
285 |
+
"step": 360
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 1.3167259786476868,
|
289 |
+
"grad_norm": 95.82825469970703,
|
290 |
+
"learning_rate": 8.24053452115813e-06,
|
291 |
+
"loss": 0.2278,
|
292 |
+
"step": 370
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 1.3523131672597866,
|
296 |
+
"grad_norm": 49.43801498413086,
|
297 |
+
"learning_rate": 8.463251670378619e-06,
|
298 |
+
"loss": 0.2501,
|
299 |
+
"step": 380
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 1.387900355871886,
|
303 |
+
"grad_norm": 40.980369567871094,
|
304 |
+
"learning_rate": 8.68596881959911e-06,
|
305 |
+
"loss": 0.1424,
|
306 |
+
"step": 390
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 1.4234875444839858,
|
310 |
+
"grad_norm": 1.2029680013656616,
|
311 |
+
"learning_rate": 8.9086859688196e-06,
|
312 |
+
"loss": 0.1464,
|
313 |
+
"step": 400
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 1.4590747330960854,
|
317 |
+
"grad_norm": 26.718364715576172,
|
318 |
+
"learning_rate": 9.13140311804009e-06,
|
319 |
+
"loss": 0.2213,
|
320 |
+
"step": 410
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.4946619217081851,
|
324 |
+
"grad_norm": 29.254457473754883,
|
325 |
+
"learning_rate": 9.35412026726058e-06,
|
326 |
+
"loss": 0.1796,
|
327 |
+
"step": 420
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 1.5302491103202847,
|
331 |
+
"grad_norm": 0.17349238693714142,
|
332 |
+
"learning_rate": 9.57683741648107e-06,
|
333 |
+
"loss": 0.1021,
|
334 |
+
"step": 430
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 1.5658362989323842,
|
338 |
+
"grad_norm": 0.27866968512535095,
|
339 |
+
"learning_rate": 9.79955456570156e-06,
|
340 |
+
"loss": 0.2656,
|
341 |
+
"step": 440
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 1.601423487544484,
|
345 |
+
"grad_norm": 0.02428502030670643,
|
346 |
+
"learning_rate": 9.985185185185185e-06,
|
347 |
+
"loss": 0.0504,
|
348 |
+
"step": 450
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 1.6370106761565837,
|
352 |
+
"grad_norm": 0.0974503755569458,
|
353 |
+
"learning_rate": 9.837037037037038e-06,
|
354 |
+
"loss": 0.062,
|
355 |
+
"step": 460
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 1.6725978647686834,
|
359 |
+
"grad_norm": 1.3685508966445923,
|
360 |
+
"learning_rate": 9.688888888888889e-06,
|
361 |
+
"loss": 0.0459,
|
362 |
+
"step": 470
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.708185053380783,
|
366 |
+
"grad_norm": 1.2251461744308472,
|
367 |
+
"learning_rate": 9.540740740740742e-06,
|
368 |
+
"loss": 0.1173,
|
369 |
+
"step": 480
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 1.7437722419928825,
|
373 |
+
"grad_norm": 62.15313720703125,
|
374 |
+
"learning_rate": 9.392592592592593e-06,
|
375 |
+
"loss": 0.1621,
|
376 |
+
"step": 490
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 1.7793594306049823,
|
380 |
+
"grad_norm": 0.03026748262345791,
|
381 |
+
"learning_rate": 9.244444444444445e-06,
|
382 |
+
"loss": 0.1064,
|
383 |
+
"step": 500
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 1.814946619217082,
|
387 |
+
"grad_norm": 0.4413605332374573,
|
388 |
+
"learning_rate": 9.096296296296298e-06,
|
389 |
+
"loss": 0.1794,
|
390 |
+
"step": 510
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 1.8505338078291815,
|
394 |
+
"grad_norm": 0.08637289702892303,
|
395 |
+
"learning_rate": 8.948148148148149e-06,
|
396 |
+
"loss": 0.0915,
|
397 |
+
"step": 520
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 1.886120996441281,
|
401 |
+
"grad_norm": 0.09529650211334229,
|
402 |
+
"learning_rate": 8.8e-06,
|
403 |
+
"loss": 0.052,
|
404 |
+
"step": 530
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 1.9217081850533808,
|
408 |
+
"grad_norm": 107.46017456054688,
|
409 |
+
"learning_rate": 8.651851851851852e-06,
|
410 |
+
"loss": 0.1408,
|
411 |
+
"step": 540
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 1.9572953736654806,
|
415 |
+
"grad_norm": 26.60268211364746,
|
416 |
+
"learning_rate": 8.503703703703705e-06,
|
417 |
+
"loss": 0.1605,
|
418 |
+
"step": 550
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 1.99288256227758,
|
422 |
+
"grad_norm": 0.018591415137052536,
|
423 |
+
"learning_rate": 8.355555555555556e-06,
|
424 |
+
"loss": 0.0914,
|
425 |
+
"step": 560
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 2.0,
|
429 |
+
"eval_accuracy": 0.9732977303070761,
|
430 |
+
"eval_f1_per_label": [
|
431 |
+
0.9541284403669725,
|
432 |
+
0.9811676082862524
|
433 |
+
],
|
434 |
+
"eval_f1_weighted": 0.9729728270877522,
|
435 |
+
"eval_loss": 0.1353287547826767,
|
436 |
+
"eval_precision_per_label": [
|
437 |
+
0.9952153110047847,
|
438 |
+
0.9648148148148148
|
439 |
+
],
|
440 |
+
"eval_precision_weighted": 0.9740283163303329,
|
441 |
+
"eval_recall_per_label": [
|
442 |
+
0.9162995594713657,
|
443 |
+
0.9980842911877394
|
444 |
+
],
|
445 |
+
"eval_recall_weighted": 0.9732977303070761,
|
446 |
+
"eval_runtime": 1.309,
|
447 |
+
"eval_samples_per_second": 572.195,
|
448 |
+
"eval_steps_per_second": 71.811,
|
449 |
+
"step": 562
|
450 |
+
}
|
451 |
+
],
|
452 |
+
"logging_steps": 10,
|
453 |
+
"max_steps": 1124,
|
454 |
+
"num_input_tokens_seen": 0,
|
455 |
+
"num_train_epochs": 4,
|
456 |
+
"save_steps": 500,
|
457 |
+
"stateful_callbacks": {
|
458 |
+
"EarlyStoppingCallback": {
|
459 |
+
"args": {
|
460 |
+
"early_stopping_patience": 3,
|
461 |
+
"early_stopping_threshold": 0.0
|
462 |
+
},
|
463 |
+
"attributes": {
|
464 |
+
"early_stopping_patience_counter": 0
|
465 |
+
}
|
466 |
+
},
|
467 |
+
"TrainerControl": {
|
468 |
+
"args": {
|
469 |
+
"should_epoch_stop": false,
|
470 |
+
"should_evaluate": false,
|
471 |
+
"should_log": false,
|
472 |
+
"should_save": true,
|
473 |
+
"should_training_stop": false
|
474 |
+
},
|
475 |
+
"attributes": {}
|
476 |
+
}
|
477 |
+
},
|
478 |
+
"total_flos": 43858865706660.0,
|
479 |
+
"train_batch_size": 8,
|
480 |
+
"trial_name": null,
|
481 |
+
"trial_params": null
|
482 |
+
}
|
checkpoint-562/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b507d5295c042031ea8738de84bfa33f52abd9440ecb04319aeef48c60251cc
|
3 |
+
size 5368
|
checkpoint-562/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-843/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"output_past": true,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.47.1",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 31002
|
28 |
+
}
|
checkpoint-843/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0956304b7ff12d2dfee5adad24464b7ae977468deed34bd98521a2984d4f1735
|
3 |
+
size 439433208
|
checkpoint-843/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef750725ca960bf0392c7ac97b92dc6719a0ea1dabae966d2ea046a2c16a4774
|
3 |
+
size 878987514
|
checkpoint-843/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:899371b0d2e8ffb9842a0871af4aa027406ec3d0f4861c7f41740823936b6822
|
3 |
+
size 14244
|
checkpoint-843/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae2e18e385abc3535d6a780402aa1cd9a5a9884f425ffb90f1a8d74382d5897a
|
3 |
+
size 1064
|
checkpoint-843/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 |
+
}
|
checkpoint-843/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-843/tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[MASK]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"3": {
|
20 |
+
"content": "[UNK]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"4": {
|
28 |
+
"content": "[CLS]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"5": {
|
36 |
+
"content": "[SEP]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": false,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": false,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
checkpoint-843/trainer_state.json
ADDED
@@ -0,0 +1,702 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.050094157457351685,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/HateSpeech-BETO-cased/checkpoint-843",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 843,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03558718861209965,
|
13 |
+
"grad_norm": 7.08419132232666,
|
14 |
+
"learning_rate": 2.2271714922049e-07,
|
15 |
+
"loss": 0.4085,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0711743772241993,
|
20 |
+
"grad_norm": 23.322711944580078,
|
21 |
+
"learning_rate": 4.4543429844098e-07,
|
22 |
+
"loss": 0.3565,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.10676156583629894,
|
27 |
+
"grad_norm": 8.696600914001465,
|
28 |
+
"learning_rate": 6.6815144766147e-07,
|
29 |
+
"loss": 0.3482,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1423487544483986,
|
34 |
+
"grad_norm": 14.429851531982422,
|
35 |
+
"learning_rate": 8.9086859688196e-07,
|
36 |
+
"loss": 0.3711,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.17793594306049823,
|
41 |
+
"grad_norm": 9.41112995147705,
|
42 |
+
"learning_rate": 1.11358574610245e-06,
|
43 |
+
"loss": 0.337,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.21352313167259787,
|
48 |
+
"grad_norm": 12.487126350402832,
|
49 |
+
"learning_rate": 1.33630289532294e-06,
|
50 |
+
"loss": 0.3413,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2491103202846975,
|
55 |
+
"grad_norm": 17.9010009765625,
|
56 |
+
"learning_rate": 1.55902004454343e-06,
|
57 |
+
"loss": 0.3154,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.2846975088967972,
|
62 |
+
"grad_norm": 17.09844207763672,
|
63 |
+
"learning_rate": 1.78173719376392e-06,
|
64 |
+
"loss": 0.2304,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.3202846975088968,
|
69 |
+
"grad_norm": 19.929523468017578,
|
70 |
+
"learning_rate": 2.00445434298441e-06,
|
71 |
+
"loss": 0.308,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.35587188612099646,
|
76 |
+
"grad_norm": 5.709442615509033,
|
77 |
+
"learning_rate": 2.2271714922049e-06,
|
78 |
+
"loss": 0.2692,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.3914590747330961,
|
83 |
+
"grad_norm": 19.828474044799805,
|
84 |
+
"learning_rate": 2.44988864142539e-06,
|
85 |
+
"loss": 0.2255,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.42704626334519574,
|
90 |
+
"grad_norm": 17.53233528137207,
|
91 |
+
"learning_rate": 2.67260579064588e-06,
|
92 |
+
"loss": 0.1917,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.4626334519572954,
|
97 |
+
"grad_norm": 14.940444946289062,
|
98 |
+
"learning_rate": 2.8953229398663702e-06,
|
99 |
+
"loss": 0.3019,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.498220640569395,
|
104 |
+
"grad_norm": 1.711176872253418,
|
105 |
+
"learning_rate": 3.11804008908686e-06,
|
106 |
+
"loss": 0.2032,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.5338078291814946,
|
111 |
+
"grad_norm": 7.716080665588379,
|
112 |
+
"learning_rate": 3.34075723830735e-06,
|
113 |
+
"loss": 0.2764,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.5693950177935944,
|
118 |
+
"grad_norm": 20.839887619018555,
|
119 |
+
"learning_rate": 3.56347438752784e-06,
|
120 |
+
"loss": 0.2067,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.604982206405694,
|
125 |
+
"grad_norm": 2.853170156478882,
|
126 |
+
"learning_rate": 3.78619153674833e-06,
|
127 |
+
"loss": 0.243,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.6405693950177936,
|
132 |
+
"grad_norm": 6.61458683013916,
|
133 |
+
"learning_rate": 4.00890868596882e-06,
|
134 |
+
"loss": 0.1886,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6761565836298933,
|
139 |
+
"grad_norm": 3.499279022216797,
|
140 |
+
"learning_rate": 4.231625835189309e-06,
|
141 |
+
"loss": 0.1987,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.7117437722419929,
|
146 |
+
"grad_norm": 32.111114501953125,
|
147 |
+
"learning_rate": 4.4543429844098e-06,
|
148 |
+
"loss": 0.2239,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.7473309608540926,
|
153 |
+
"grad_norm": 3.83589506149292,
|
154 |
+
"learning_rate": 4.67706013363029e-06,
|
155 |
+
"loss": 0.1891,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.7829181494661922,
|
160 |
+
"grad_norm": 3.3233108520507812,
|
161 |
+
"learning_rate": 4.89977728285078e-06,
|
162 |
+
"loss": 0.1335,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.8185053380782918,
|
167 |
+
"grad_norm": 19.36582374572754,
|
168 |
+
"learning_rate": 5.12249443207127e-06,
|
169 |
+
"loss": 0.0513,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.8540925266903915,
|
174 |
+
"grad_norm": 0.7740408182144165,
|
175 |
+
"learning_rate": 5.34521158129176e-06,
|
176 |
+
"loss": 0.1499,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.8896797153024911,
|
181 |
+
"grad_norm": 0.18774119019508362,
|
182 |
+
"learning_rate": 5.5679287305122494e-06,
|
183 |
+
"loss": 0.1303,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.9252669039145908,
|
188 |
+
"grad_norm": 0.2991533875465393,
|
189 |
+
"learning_rate": 5.7906458797327404e-06,
|
190 |
+
"loss": 0.0695,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.9608540925266904,
|
195 |
+
"grad_norm": 0.08448722958564758,
|
196 |
+
"learning_rate": 6.01336302895323e-06,
|
197 |
+
"loss": 0.1109,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.99644128113879,
|
202 |
+
"grad_norm": 30.85651397705078,
|
203 |
+
"learning_rate": 6.23608017817372e-06,
|
204 |
+
"loss": 0.2155,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.0,
|
209 |
+
"eval_accuracy": 0.9559412550066756,
|
210 |
+
"eval_f1_per_label": [
|
211 |
+
0.9255079006772009,
|
212 |
+
0.9687203791469194
|
213 |
+
],
|
214 |
+
"eval_f1_weighted": 0.9556239404117711,
|
215 |
+
"eval_loss": 0.17148031294345856,
|
216 |
+
"eval_precision_per_label": [
|
217 |
+
0.9490740740740741,
|
218 |
+
0.9587242026266416
|
219 |
+
],
|
220 |
+
"eval_precision_weighted": 0.9557995308223255,
|
221 |
+
"eval_recall_per_label": [
|
222 |
+
0.9030837004405287,
|
223 |
+
0.9789272030651341
|
224 |
+
],
|
225 |
+
"eval_recall_weighted": 0.9559412550066756,
|
226 |
+
"eval_runtime": 1.3508,
|
227 |
+
"eval_samples_per_second": 554.494,
|
228 |
+
"eval_steps_per_second": 69.589,
|
229 |
+
"step": 281
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 1.0320284697508897,
|
233 |
+
"grad_norm": 37.36682891845703,
|
234 |
+
"learning_rate": 6.458797327394209e-06,
|
235 |
+
"loss": 0.2318,
|
236 |
+
"step": 290
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.0676156583629894,
|
240 |
+
"grad_norm": 3.181389093399048,
|
241 |
+
"learning_rate": 6.6815144766147e-06,
|
242 |
+
"loss": 0.29,
|
243 |
+
"step": 300
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 1.103202846975089,
|
247 |
+
"grad_norm": 0.6792677640914917,
|
248 |
+
"learning_rate": 6.9042316258351895e-06,
|
249 |
+
"loss": 0.0621,
|
250 |
+
"step": 310
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 1.1387900355871885,
|
254 |
+
"grad_norm": 31.2163143157959,
|
255 |
+
"learning_rate": 7.12694877505568e-06,
|
256 |
+
"loss": 0.3279,
|
257 |
+
"step": 320
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 1.1743772241992882,
|
261 |
+
"grad_norm": 32.702980041503906,
|
262 |
+
"learning_rate": 7.349665924276171e-06,
|
263 |
+
"loss": 0.0851,
|
264 |
+
"step": 330
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 1.209964412811388,
|
268 |
+
"grad_norm": 76.18331146240234,
|
269 |
+
"learning_rate": 7.57238307349666e-06,
|
270 |
+
"loss": 0.3339,
|
271 |
+
"step": 340
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 1.2455516014234875,
|
275 |
+
"grad_norm": 76.69121551513672,
|
276 |
+
"learning_rate": 7.79510022271715e-06,
|
277 |
+
"loss": 0.0757,
|
278 |
+
"step": 350
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.281138790035587,
|
282 |
+
"grad_norm": 0.06500601023435593,
|
283 |
+
"learning_rate": 8.01781737193764e-06,
|
284 |
+
"loss": 0.188,
|
285 |
+
"step": 360
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 1.3167259786476868,
|
289 |
+
"grad_norm": 95.82825469970703,
|
290 |
+
"learning_rate": 8.24053452115813e-06,
|
291 |
+
"loss": 0.2278,
|
292 |
+
"step": 370
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 1.3523131672597866,
|
296 |
+
"grad_norm": 49.43801498413086,
|
297 |
+
"learning_rate": 8.463251670378619e-06,
|
298 |
+
"loss": 0.2501,
|
299 |
+
"step": 380
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 1.387900355871886,
|
303 |
+
"grad_norm": 40.980369567871094,
|
304 |
+
"learning_rate": 8.68596881959911e-06,
|
305 |
+
"loss": 0.1424,
|
306 |
+
"step": 390
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 1.4234875444839858,
|
310 |
+
"grad_norm": 1.2029680013656616,
|
311 |
+
"learning_rate": 8.9086859688196e-06,
|
312 |
+
"loss": 0.1464,
|
313 |
+
"step": 400
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 1.4590747330960854,
|
317 |
+
"grad_norm": 26.718364715576172,
|
318 |
+
"learning_rate": 9.13140311804009e-06,
|
319 |
+
"loss": 0.2213,
|
320 |
+
"step": 410
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.4946619217081851,
|
324 |
+
"grad_norm": 29.254457473754883,
|
325 |
+
"learning_rate": 9.35412026726058e-06,
|
326 |
+
"loss": 0.1796,
|
327 |
+
"step": 420
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 1.5302491103202847,
|
331 |
+
"grad_norm": 0.17349238693714142,
|
332 |
+
"learning_rate": 9.57683741648107e-06,
|
333 |
+
"loss": 0.1021,
|
334 |
+
"step": 430
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 1.5658362989323842,
|
338 |
+
"grad_norm": 0.27866968512535095,
|
339 |
+
"learning_rate": 9.79955456570156e-06,
|
340 |
+
"loss": 0.2656,
|
341 |
+
"step": 440
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 1.601423487544484,
|
345 |
+
"grad_norm": 0.02428502030670643,
|
346 |
+
"learning_rate": 9.985185185185185e-06,
|
347 |
+
"loss": 0.0504,
|
348 |
+
"step": 450
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 1.6370106761565837,
|
352 |
+
"grad_norm": 0.0974503755569458,
|
353 |
+
"learning_rate": 9.837037037037038e-06,
|
354 |
+
"loss": 0.062,
|
355 |
+
"step": 460
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 1.6725978647686834,
|
359 |
+
"grad_norm": 1.3685508966445923,
|
360 |
+
"learning_rate": 9.688888888888889e-06,
|
361 |
+
"loss": 0.0459,
|
362 |
+
"step": 470
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.708185053380783,
|
366 |
+
"grad_norm": 1.2251461744308472,
|
367 |
+
"learning_rate": 9.540740740740742e-06,
|
368 |
+
"loss": 0.1173,
|
369 |
+
"step": 480
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 1.7437722419928825,
|
373 |
+
"grad_norm": 62.15313720703125,
|
374 |
+
"learning_rate": 9.392592592592593e-06,
|
375 |
+
"loss": 0.1621,
|
376 |
+
"step": 490
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 1.7793594306049823,
|
380 |
+
"grad_norm": 0.03026748262345791,
|
381 |
+
"learning_rate": 9.244444444444445e-06,
|
382 |
+
"loss": 0.1064,
|
383 |
+
"step": 500
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 1.814946619217082,
|
387 |
+
"grad_norm": 0.4413605332374573,
|
388 |
+
"learning_rate": 9.096296296296298e-06,
|
389 |
+
"loss": 0.1794,
|
390 |
+
"step": 510
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 1.8505338078291815,
|
394 |
+
"grad_norm": 0.08637289702892303,
|
395 |
+
"learning_rate": 8.948148148148149e-06,
|
396 |
+
"loss": 0.0915,
|
397 |
+
"step": 520
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 1.886120996441281,
|
401 |
+
"grad_norm": 0.09529650211334229,
|
402 |
+
"learning_rate": 8.8e-06,
|
403 |
+
"loss": 0.052,
|
404 |
+
"step": 530
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 1.9217081850533808,
|
408 |
+
"grad_norm": 107.46017456054688,
|
409 |
+
"learning_rate": 8.651851851851852e-06,
|
410 |
+
"loss": 0.1408,
|
411 |
+
"step": 540
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 1.9572953736654806,
|
415 |
+
"grad_norm": 26.60268211364746,
|
416 |
+
"learning_rate": 8.503703703703705e-06,
|
417 |
+
"loss": 0.1605,
|
418 |
+
"step": 550
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 1.99288256227758,
|
422 |
+
"grad_norm": 0.018591415137052536,
|
423 |
+
"learning_rate": 8.355555555555556e-06,
|
424 |
+
"loss": 0.0914,
|
425 |
+
"step": 560
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 2.0,
|
429 |
+
"eval_accuracy": 0.9732977303070761,
|
430 |
+
"eval_f1_per_label": [
|
431 |
+
0.9541284403669725,
|
432 |
+
0.9811676082862524
|
433 |
+
],
|
434 |
+
"eval_f1_weighted": 0.9729728270877522,
|
435 |
+
"eval_loss": 0.1353287547826767,
|
436 |
+
"eval_precision_per_label": [
|
437 |
+
0.9952153110047847,
|
438 |
+
0.9648148148148148
|
439 |
+
],
|
440 |
+
"eval_precision_weighted": 0.9740283163303329,
|
441 |
+
"eval_recall_per_label": [
|
442 |
+
0.9162995594713657,
|
443 |
+
0.9980842911877394
|
444 |
+
],
|
445 |
+
"eval_recall_weighted": 0.9732977303070761,
|
446 |
+
"eval_runtime": 1.309,
|
447 |
+
"eval_samples_per_second": 572.195,
|
448 |
+
"eval_steps_per_second": 71.811,
|
449 |
+
"step": 562
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 2.0284697508896796,
|
453 |
+
"grad_norm": 0.015944845974445343,
|
454 |
+
"learning_rate": 8.207407407407409e-06,
|
455 |
+
"loss": 0.0011,
|
456 |
+
"step": 570
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 2.0640569395017794,
|
460 |
+
"grad_norm": 0.03662079572677612,
|
461 |
+
"learning_rate": 8.05925925925926e-06,
|
462 |
+
"loss": 0.0475,
|
463 |
+
"step": 580
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 2.099644128113879,
|
467 |
+
"grad_norm": 0.03478744253516197,
|
468 |
+
"learning_rate": 7.911111111111112e-06,
|
469 |
+
"loss": 0.0017,
|
470 |
+
"step": 590
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 2.135231316725979,
|
474 |
+
"grad_norm": 0.03390470892190933,
|
475 |
+
"learning_rate": 7.762962962962963e-06,
|
476 |
+
"loss": 0.0054,
|
477 |
+
"step": 600
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 2.170818505338078,
|
481 |
+
"grad_norm": 0.007953139953315258,
|
482 |
+
"learning_rate": 7.614814814814816e-06,
|
483 |
+
"loss": 0.0096,
|
484 |
+
"step": 610
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 2.206405693950178,
|
488 |
+
"grad_norm": 45.853023529052734,
|
489 |
+
"learning_rate": 7.4666666666666675e-06,
|
490 |
+
"loss": 0.0893,
|
491 |
+
"step": 620
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 2.2419928825622777,
|
495 |
+
"grad_norm": 0.03887489438056946,
|
496 |
+
"learning_rate": 7.31851851851852e-06,
|
497 |
+
"loss": 0.0004,
|
498 |
+
"step": 630
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 2.277580071174377,
|
502 |
+
"grad_norm": 0.04745912551879883,
|
503 |
+
"learning_rate": 7.170370370370371e-06,
|
504 |
+
"loss": 0.1963,
|
505 |
+
"step": 640
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 2.3131672597864767,
|
509 |
+
"grad_norm": 0.05072787404060364,
|
510 |
+
"learning_rate": 7.022222222222222e-06,
|
511 |
+
"loss": 0.0231,
|
512 |
+
"step": 650
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 2.3487544483985765,
|
516 |
+
"grad_norm": 0.026582635939121246,
|
517 |
+
"learning_rate": 6.8740740740740745e-06,
|
518 |
+
"loss": 0.0149,
|
519 |
+
"step": 660
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 2.3843416370106763,
|
523 |
+
"grad_norm": 0.014482633210718632,
|
524 |
+
"learning_rate": 6.725925925925927e-06,
|
525 |
+
"loss": 0.0994,
|
526 |
+
"step": 670
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 2.419928825622776,
|
530 |
+
"grad_norm": 0.025208059698343277,
|
531 |
+
"learning_rate": 6.577777777777779e-06,
|
532 |
+
"loss": 0.0006,
|
533 |
+
"step": 680
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 2.4555160142348753,
|
537 |
+
"grad_norm": 0.01709064655005932,
|
538 |
+
"learning_rate": 6.42962962962963e-06,
|
539 |
+
"loss": 0.1219,
|
540 |
+
"step": 690
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 2.491103202846975,
|
544 |
+
"grad_norm": 0.1339588463306427,
|
545 |
+
"learning_rate": 6.2814814814814814e-06,
|
546 |
+
"loss": 0.0006,
|
547 |
+
"step": 700
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 2.526690391459075,
|
551 |
+
"grad_norm": 24.798721313476562,
|
552 |
+
"learning_rate": 6.133333333333334e-06,
|
553 |
+
"loss": 0.0029,
|
554 |
+
"step": 710
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 2.562277580071174,
|
558 |
+
"grad_norm": 1.3540862798690796,
|
559 |
+
"learning_rate": 5.985185185185186e-06,
|
560 |
+
"loss": 0.081,
|
561 |
+
"step": 720
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 2.597864768683274,
|
565 |
+
"grad_norm": 0.04109741002321243,
|
566 |
+
"learning_rate": 5.837037037037038e-06,
|
567 |
+
"loss": 0.0006,
|
568 |
+
"step": 730
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 2.6334519572953736,
|
572 |
+
"grad_norm": 0.010597619228065014,
|
573 |
+
"learning_rate": 5.688888888888889e-06,
|
574 |
+
"loss": 0.013,
|
575 |
+
"step": 740
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 2.6690391459074734,
|
579 |
+
"grad_norm": 0.02383551187813282,
|
580 |
+
"learning_rate": 5.540740740740741e-06,
|
581 |
+
"loss": 0.0008,
|
582 |
+
"step": 750
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 2.704626334519573,
|
586 |
+
"grad_norm": 1.2794164419174194,
|
587 |
+
"learning_rate": 5.392592592592593e-06,
|
588 |
+
"loss": 0.1707,
|
589 |
+
"step": 760
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 2.7402135231316724,
|
593 |
+
"grad_norm": 0.014402506873011589,
|
594 |
+
"learning_rate": 5.244444444444445e-06,
|
595 |
+
"loss": 0.0864,
|
596 |
+
"step": 770
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 2.775800711743772,
|
600 |
+
"grad_norm": 0.013125807978212833,
|
601 |
+
"learning_rate": 5.096296296296297e-06,
|
602 |
+
"loss": 0.0205,
|
603 |
+
"step": 780
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 2.811387900355872,
|
607 |
+
"grad_norm": 0.2091672271490097,
|
608 |
+
"learning_rate": 4.9481481481481485e-06,
|
609 |
+
"loss": 0.0027,
|
610 |
+
"step": 790
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 2.8469750889679717,
|
614 |
+
"grad_norm": 0.13218224048614502,
|
615 |
+
"learning_rate": 4.800000000000001e-06,
|
616 |
+
"loss": 0.0004,
|
617 |
+
"step": 800
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 2.882562277580071,
|
621 |
+
"grad_norm": 2.1445350646972656,
|
622 |
+
"learning_rate": 4.651851851851853e-06,
|
623 |
+
"loss": 0.1045,
|
624 |
+
"step": 810
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 2.9181494661921707,
|
628 |
+
"grad_norm": 0.016628708690404892,
|
629 |
+
"learning_rate": 4.503703703703704e-06,
|
630 |
+
"loss": 0.0005,
|
631 |
+
"step": 820
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 2.9537366548042705,
|
635 |
+
"grad_norm": 0.04098201170563698,
|
636 |
+
"learning_rate": 4.3555555555555555e-06,
|
637 |
+
"loss": 0.0569,
|
638 |
+
"step": 830
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 2.9893238434163703,
|
642 |
+
"grad_norm": 0.7140023708343506,
|
643 |
+
"learning_rate": 4.207407407407408e-06,
|
644 |
+
"loss": 0.0014,
|
645 |
+
"step": 840
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 3.0,
|
649 |
+
"eval_accuracy": 0.9893190921228304,
|
650 |
+
"eval_f1_per_label": [
|
651 |
+
0.9821428571428571,
|
652 |
+
0.9923809523809524
|
653 |
+
],
|
654 |
+
"eval_f1_weighted": 0.989278085065802,
|
655 |
+
"eval_loss": 0.050094157457351685,
|
656 |
+
"eval_precision_per_label": [
|
657 |
+
0.995475113122172,
|
658 |
+
0.9867424242424242
|
659 |
+
],
|
660 |
+
"eval_precision_weighted": 0.9893890469069138,
|
661 |
+
"eval_recall_per_label": [
|
662 |
+
0.9691629955947136,
|
663 |
+
0.9980842911877394
|
664 |
+
],
|
665 |
+
"eval_recall_weighted": 0.9893190921228304,
|
666 |
+
"eval_runtime": 1.3422,
|
667 |
+
"eval_samples_per_second": 558.027,
|
668 |
+
"eval_steps_per_second": 70.033,
|
669 |
+
"step": 843
|
670 |
+
}
|
671 |
+
],
|
672 |
+
"logging_steps": 10,
|
673 |
+
"max_steps": 1124,
|
674 |
+
"num_input_tokens_seen": 0,
|
675 |
+
"num_train_epochs": 4,
|
676 |
+
"save_steps": 500,
|
677 |
+
"stateful_callbacks": {
|
678 |
+
"EarlyStoppingCallback": {
|
679 |
+
"args": {
|
680 |
+
"early_stopping_patience": 3,
|
681 |
+
"early_stopping_threshold": 0.0
|
682 |
+
},
|
683 |
+
"attributes": {
|
684 |
+
"early_stopping_patience_counter": 0
|
685 |
+
}
|
686 |
+
},
|
687 |
+
"TrainerControl": {
|
688 |
+
"args": {
|
689 |
+
"should_epoch_stop": false,
|
690 |
+
"should_evaluate": false,
|
691 |
+
"should_log": false,
|
692 |
+
"should_save": true,
|
693 |
+
"should_training_stop": false
|
694 |
+
},
|
695 |
+
"attributes": {}
|
696 |
+
}
|
697 |
+
},
|
698 |
+
"total_flos": 65856902712120.0,
|
699 |
+
"train_batch_size": 8,
|
700 |
+
"trial_name": null,
|
701 |
+
"trial_params": null
|
702 |
+
}
|
checkpoint-843/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b507d5295c042031ea8738de84bfa33f52abd9440ecb04319aeef48c60251cc
|
3 |
+
size 5368
|
checkpoint-843/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"output_past": true,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.47.1",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 31002
|
28 |
+
}
|
events.out.tfevents.1735166948.12b685f0bef2.317.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff91e417d90b57e5fa0a3824672bd41da0d9670c92dcfd54df562d1a9f836b30
|
3 |
+
size 11045
|
events.out.tfevents.1735167321.12b685f0bef2.317.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f45c584ea0ccbe8d9495fdcc132559045a571b8a2082ef60d3bd0399ded2b887
|
3 |
+
size 31168
|
events.out.tfevents.1735167522.12b685f0bef2.317.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0172fd6d57dbc3c59c6e4699a0f9a0a40f70d0704844e1adee60f8440f076b2
|
3 |
+
size 1086
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e177e2a47fdac098a1f71d136199e251cd143f5f231b72b9c61a1ba37daf395b
|
3 |
+
size 439433208
|
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 |
+
}
|