Upload folder using huggingface_hub
Browse files- checkpoint-3993/config.json +26 -0
- checkpoint-3993/model.safetensors +3 -0
- checkpoint-3993/optimizer.pt +3 -0
- checkpoint-3993/rng_state.pth +3 -0
- checkpoint-3993/scheduler.pt +3 -0
- checkpoint-3993/special_tokens_map.json +7 -0
- checkpoint-3993/tokenizer.json +0 -0
- checkpoint-3993/tokenizer_config.json +56 -0
- checkpoint-3993/trainer_state.json +616 -0
- checkpoint-3993/training_args.bin +3 -0
- checkpoint-3993/vocab.txt +0 -0
- config.json +26 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- vocab.txt +0 -0
checkpoint-3993/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilbert-base-multilingual-cased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"output_past": true,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"problem_type": "single_label_classification",
|
| 19 |
+
"qa_dropout": 0.1,
|
| 20 |
+
"seq_classif_dropout": 0.2,
|
| 21 |
+
"sinusoidal_pos_embds": false,
|
| 22 |
+
"tie_weights_": true,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.48.3",
|
| 25 |
+
"vocab_size": 119547
|
| 26 |
+
}
|
checkpoint-3993/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ea9b5e7183bbf5cf8fa18a035400a551437fae62101ab6a9f9b5deb3b2f5b8c
|
| 3 |
+
size 541317368
|
checkpoint-3993/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:790a47a1e084ea24a5141b94cd9e7642464dcde31589e665983af95a17982f9d
|
| 3 |
+
size 1082696890
|
checkpoint-3993/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f77155ef51b39b582fee6b7532a11655f8bbce22f1a1541c851f69568820fae
|
| 3 |
+
size 14244
|
checkpoint-3993/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c9a100e2f2b7b8fc6eaa82083fc485d0bcbe8913f96de28b5d46bbcaee0f201
|
| 3 |
+
size 1064
|
checkpoint-3993/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-3993/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3993/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-3993/trainer_state.json
ADDED
|
@@ -0,0 +1,616 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3993,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.037565740045078885,
|
| 13 |
+
"grad_norm": 1.0086880922317505,
|
| 14 |
+
"learning_rate": 4.937390433258202e-05,
|
| 15 |
+
"loss": 0.6372,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07513148009015777,
|
| 20 |
+
"grad_norm": 2.3579623699188232,
|
| 21 |
+
"learning_rate": 4.874780866516404e-05,
|
| 22 |
+
"loss": 0.5979,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.11269722013523667,
|
| 27 |
+
"grad_norm": 1.6555202007293701,
|
| 28 |
+
"learning_rate": 4.812171299774606e-05,
|
| 29 |
+
"loss": 0.5668,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.15026296018031554,
|
| 34 |
+
"grad_norm": 2.134246587753296,
|
| 35 |
+
"learning_rate": 4.749561733032808e-05,
|
| 36 |
+
"loss": 0.5677,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.18782870022539444,
|
| 41 |
+
"grad_norm": 1.2070592641830444,
|
| 42 |
+
"learning_rate": 4.6869521662910095e-05,
|
| 43 |
+
"loss": 0.5519,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.22539444027047334,
|
| 48 |
+
"grad_norm": 1.7169790267944336,
|
| 49 |
+
"learning_rate": 4.6243425995492114e-05,
|
| 50 |
+
"loss": 0.5403,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.26296018031555224,
|
| 55 |
+
"grad_norm": 2.367072105407715,
|
| 56 |
+
"learning_rate": 4.561733032807413e-05,
|
| 57 |
+
"loss": 0.5375,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3005259203606311,
|
| 62 |
+
"grad_norm": 1.7623053789138794,
|
| 63 |
+
"learning_rate": 4.499123466065615e-05,
|
| 64 |
+
"loss": 0.5425,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.33809166040571,
|
| 69 |
+
"grad_norm": 1.7148823738098145,
|
| 70 |
+
"learning_rate": 4.436513899323817e-05,
|
| 71 |
+
"loss": 0.5454,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3756574004507889,
|
| 76 |
+
"grad_norm": 1.318366527557373,
|
| 77 |
+
"learning_rate": 4.373904332582019e-05,
|
| 78 |
+
"loss": 0.5353,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4132231404958678,
|
| 83 |
+
"grad_norm": 2.0299246311187744,
|
| 84 |
+
"learning_rate": 4.311294765840221e-05,
|
| 85 |
+
"loss": 0.5296,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4507888805409467,
|
| 90 |
+
"grad_norm": 1.5541517734527588,
|
| 91 |
+
"learning_rate": 4.2486851990984225e-05,
|
| 92 |
+
"loss": 0.5433,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4883546205860255,
|
| 97 |
+
"grad_norm": 1.6975432634353638,
|
| 98 |
+
"learning_rate": 4.1860756323566244e-05,
|
| 99 |
+
"loss": 0.5142,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5259203606311045,
|
| 104 |
+
"grad_norm": 1.6241447925567627,
|
| 105 |
+
"learning_rate": 4.123466065614826e-05,
|
| 106 |
+
"loss": 0.5139,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5634861006761833,
|
| 111 |
+
"grad_norm": 1.4247183799743652,
|
| 112 |
+
"learning_rate": 4.060856498873028e-05,
|
| 113 |
+
"loss": 0.5102,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6010518407212622,
|
| 118 |
+
"grad_norm": 2.266134023666382,
|
| 119 |
+
"learning_rate": 3.99824693213123e-05,
|
| 120 |
+
"loss": 0.5036,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6386175807663411,
|
| 125 |
+
"grad_norm": 1.5822668075561523,
|
| 126 |
+
"learning_rate": 3.935637365389432e-05,
|
| 127 |
+
"loss": 0.5203,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.67618332081142,
|
| 132 |
+
"grad_norm": 2.1509227752685547,
|
| 133 |
+
"learning_rate": 3.873027798647634e-05,
|
| 134 |
+
"loss": 0.5116,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7137490608564989,
|
| 139 |
+
"grad_norm": 1.511104941368103,
|
| 140 |
+
"learning_rate": 3.810418231905835e-05,
|
| 141 |
+
"loss": 0.5048,
|
| 142 |
+
"step": 950
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.7513148009015778,
|
| 146 |
+
"grad_norm": 2.872206211090088,
|
| 147 |
+
"learning_rate": 3.747808665164037e-05,
|
| 148 |
+
"loss": 0.5137,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7888805409466566,
|
| 153 |
+
"grad_norm": 3.4886534214019775,
|
| 154 |
+
"learning_rate": 3.685199098422239e-05,
|
| 155 |
+
"loss": 0.4881,
|
| 156 |
+
"step": 1050
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8264462809917356,
|
| 160 |
+
"grad_norm": 2.8081490993499756,
|
| 161 |
+
"learning_rate": 3.622589531680441e-05,
|
| 162 |
+
"loss": 0.4764,
|
| 163 |
+
"step": 1100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.8640120210368144,
|
| 167 |
+
"grad_norm": 1.6759647130966187,
|
| 168 |
+
"learning_rate": 3.559979964938643e-05,
|
| 169 |
+
"loss": 0.5082,
|
| 170 |
+
"step": 1150
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9015777610818934,
|
| 174 |
+
"grad_norm": 2.0700764656066895,
|
| 175 |
+
"learning_rate": 3.497370398196845e-05,
|
| 176 |
+
"loss": 0.5035,
|
| 177 |
+
"step": 1200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9391435011269722,
|
| 181 |
+
"grad_norm": 1.5199862718582153,
|
| 182 |
+
"learning_rate": 3.434760831455047e-05,
|
| 183 |
+
"loss": 0.5007,
|
| 184 |
+
"step": 1250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.976709241172051,
|
| 188 |
+
"grad_norm": 2.5575571060180664,
|
| 189 |
+
"learning_rate": 3.3721512647132486e-05,
|
| 190 |
+
"loss": 0.5015,
|
| 191 |
+
"step": 1300
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.0,
|
| 195 |
+
"eval_accuracy": 0.7457595263825588,
|
| 196 |
+
"eval_f1": 0.7615774399647499,
|
| 197 |
+
"eval_loss": 0.47971779108047485,
|
| 198 |
+
"eval_runtime": 154.8323,
|
| 199 |
+
"eval_samples_per_second": 137.458,
|
| 200 |
+
"eval_steps_per_second": 2.151,
|
| 201 |
+
"step": 1331
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.01427498121713,
|
| 205 |
+
"grad_norm": 1.657974362373352,
|
| 206 |
+
"learning_rate": 3.30954169797145e-05,
|
| 207 |
+
"loss": 0.4846,
|
| 208 |
+
"step": 1350
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.051840721262209,
|
| 212 |
+
"grad_norm": 2.831270217895508,
|
| 213 |
+
"learning_rate": 3.2469321312296516e-05,
|
| 214 |
+
"loss": 0.4359,
|
| 215 |
+
"step": 1400
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.0894064613072878,
|
| 219 |
+
"grad_norm": 2.0967586040496826,
|
| 220 |
+
"learning_rate": 3.184322564487854e-05,
|
| 221 |
+
"loss": 0.4352,
|
| 222 |
+
"step": 1450
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.1269722013523666,
|
| 226 |
+
"grad_norm": 2.5382165908813477,
|
| 227 |
+
"learning_rate": 3.121712997746056e-05,
|
| 228 |
+
"loss": 0.423,
|
| 229 |
+
"step": 1500
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.1645379413974455,
|
| 233 |
+
"grad_norm": 1.702189326286316,
|
| 234 |
+
"learning_rate": 3.059103431004258e-05,
|
| 235 |
+
"loss": 0.4178,
|
| 236 |
+
"step": 1550
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.2021036814425243,
|
| 240 |
+
"grad_norm": 2.0063211917877197,
|
| 241 |
+
"learning_rate": 2.9964938642624597e-05,
|
| 242 |
+
"loss": 0.4235,
|
| 243 |
+
"step": 1600
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.2396694214876034,
|
| 247 |
+
"grad_norm": 2.133720874786377,
|
| 248 |
+
"learning_rate": 2.9338842975206616e-05,
|
| 249 |
+
"loss": 0.4381,
|
| 250 |
+
"step": 1650
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.2772351615326822,
|
| 254 |
+
"grad_norm": 1.841479778289795,
|
| 255 |
+
"learning_rate": 2.8712747307788628e-05,
|
| 256 |
+
"loss": 0.4531,
|
| 257 |
+
"step": 1700
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.314800901577761,
|
| 261 |
+
"grad_norm": 2.0691092014312744,
|
| 262 |
+
"learning_rate": 2.808665164037065e-05,
|
| 263 |
+
"loss": 0.4247,
|
| 264 |
+
"step": 1750
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.35236664162284,
|
| 268 |
+
"grad_norm": 4.776940822601318,
|
| 269 |
+
"learning_rate": 2.7460555972952668e-05,
|
| 270 |
+
"loss": 0.4265,
|
| 271 |
+
"step": 1800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.389932381667919,
|
| 275 |
+
"grad_norm": 1.9305018186569214,
|
| 276 |
+
"learning_rate": 2.6834460305534687e-05,
|
| 277 |
+
"loss": 0.4306,
|
| 278 |
+
"step": 1850
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.4274981217129978,
|
| 282 |
+
"grad_norm": 2.0644538402557373,
|
| 283 |
+
"learning_rate": 2.6208364638116705e-05,
|
| 284 |
+
"loss": 0.4255,
|
| 285 |
+
"step": 1900
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.4650638617580767,
|
| 289 |
+
"grad_norm": 3.263160228729248,
|
| 290 |
+
"learning_rate": 2.5582268970698724e-05,
|
| 291 |
+
"loss": 0.4427,
|
| 292 |
+
"step": 1950
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.5026296018031555,
|
| 296 |
+
"grad_norm": 3.1235225200653076,
|
| 297 |
+
"learning_rate": 2.4956173303280743e-05,
|
| 298 |
+
"loss": 0.4433,
|
| 299 |
+
"step": 2000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.5401953418482344,
|
| 303 |
+
"grad_norm": 1.4947174787521362,
|
| 304 |
+
"learning_rate": 2.433007763586276e-05,
|
| 305 |
+
"loss": 0.4359,
|
| 306 |
+
"step": 2050
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.5777610818933132,
|
| 310 |
+
"grad_norm": 1.4775031805038452,
|
| 311 |
+
"learning_rate": 2.370398196844478e-05,
|
| 312 |
+
"loss": 0.4397,
|
| 313 |
+
"step": 2100
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.615326821938392,
|
| 317 |
+
"grad_norm": 3.387707233428955,
|
| 318 |
+
"learning_rate": 2.30778863010268e-05,
|
| 319 |
+
"loss": 0.4202,
|
| 320 |
+
"step": 2150
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.6528925619834711,
|
| 324 |
+
"grad_norm": 3.0223426818847656,
|
| 325 |
+
"learning_rate": 2.2451790633608817e-05,
|
| 326 |
+
"loss": 0.4275,
|
| 327 |
+
"step": 2200
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.69045830202855,
|
| 331 |
+
"grad_norm": 2.5161309242248535,
|
| 332 |
+
"learning_rate": 2.1825694966190836e-05,
|
| 333 |
+
"loss": 0.406,
|
| 334 |
+
"step": 2250
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.7280240420736288,
|
| 338 |
+
"grad_norm": 2.2194652557373047,
|
| 339 |
+
"learning_rate": 2.1199599298772854e-05,
|
| 340 |
+
"loss": 0.416,
|
| 341 |
+
"step": 2300
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.7655897821187079,
|
| 345 |
+
"grad_norm": 2.4205820560455322,
|
| 346 |
+
"learning_rate": 2.057350363135487e-05,
|
| 347 |
+
"loss": 0.4315,
|
| 348 |
+
"step": 2350
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.8031555221637867,
|
| 352 |
+
"grad_norm": 1.2840783596038818,
|
| 353 |
+
"learning_rate": 1.994740796393689e-05,
|
| 354 |
+
"loss": 0.4155,
|
| 355 |
+
"step": 2400
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.8407212622088656,
|
| 359 |
+
"grad_norm": 1.456228256225586,
|
| 360 |
+
"learning_rate": 1.932131229651891e-05,
|
| 361 |
+
"loss": 0.4247,
|
| 362 |
+
"step": 2450
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.8782870022539444,
|
| 366 |
+
"grad_norm": 2.8294334411621094,
|
| 367 |
+
"learning_rate": 1.869521662910093e-05,
|
| 368 |
+
"loss": 0.4305,
|
| 369 |
+
"step": 2500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.9158527422990232,
|
| 373 |
+
"grad_norm": 2.2248728275299072,
|
| 374 |
+
"learning_rate": 1.8069120961682944e-05,
|
| 375 |
+
"loss": 0.4349,
|
| 376 |
+
"step": 2550
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.953418482344102,
|
| 380 |
+
"grad_norm": 1.7025116682052612,
|
| 381 |
+
"learning_rate": 1.7443025294264966e-05,
|
| 382 |
+
"loss": 0.423,
|
| 383 |
+
"step": 2600
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.990984222389181,
|
| 387 |
+
"grad_norm": 3.388554811477661,
|
| 388 |
+
"learning_rate": 1.6816929626846984e-05,
|
| 389 |
+
"loss": 0.4265,
|
| 390 |
+
"step": 2650
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.0,
|
| 394 |
+
"eval_accuracy": 0.7559084715500635,
|
| 395 |
+
"eval_f1": 0.764024528730411,
|
| 396 |
+
"eval_loss": 0.47860267758369446,
|
| 397 |
+
"eval_runtime": 149.5526,
|
| 398 |
+
"eval_samples_per_second": 142.311,
|
| 399 |
+
"eval_steps_per_second": 2.227,
|
| 400 |
+
"step": 2662
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.02854996243426,
|
| 404 |
+
"grad_norm": 6.253864765167236,
|
| 405 |
+
"learning_rate": 1.6190833959429003e-05,
|
| 406 |
+
"loss": 0.3602,
|
| 407 |
+
"step": 2700
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.0661157024793386,
|
| 411 |
+
"grad_norm": 2.9103243350982666,
|
| 412 |
+
"learning_rate": 1.5564738292011018e-05,
|
| 413 |
+
"loss": 0.3674,
|
| 414 |
+
"step": 2750
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.103681442524418,
|
| 418 |
+
"grad_norm": 2.6558964252471924,
|
| 419 |
+
"learning_rate": 1.4938642624593038e-05,
|
| 420 |
+
"loss": 0.3632,
|
| 421 |
+
"step": 2800
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.1412471825694968,
|
| 425 |
+
"grad_norm": 2.243708610534668,
|
| 426 |
+
"learning_rate": 1.4312546957175057e-05,
|
| 427 |
+
"loss": 0.3729,
|
| 428 |
+
"step": 2850
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.1788129226145756,
|
| 432 |
+
"grad_norm": 2.718883752822876,
|
| 433 |
+
"learning_rate": 1.3686451289757077e-05,
|
| 434 |
+
"loss": 0.3564,
|
| 435 |
+
"step": 2900
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.2163786626596544,
|
| 439 |
+
"grad_norm": 5.29821252822876,
|
| 440 |
+
"learning_rate": 1.3060355622339094e-05,
|
| 441 |
+
"loss": 0.3617,
|
| 442 |
+
"step": 2950
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.2539444027047333,
|
| 446 |
+
"grad_norm": 4.189558982849121,
|
| 447 |
+
"learning_rate": 1.2434259954921113e-05,
|
| 448 |
+
"loss": 0.3653,
|
| 449 |
+
"step": 3000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.291510142749812,
|
| 453 |
+
"grad_norm": 1.6549113988876343,
|
| 454 |
+
"learning_rate": 1.180816428750313e-05,
|
| 455 |
+
"loss": 0.3727,
|
| 456 |
+
"step": 3050
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.329075882794891,
|
| 460 |
+
"grad_norm": 1.1492334604263306,
|
| 461 |
+
"learning_rate": 1.118206862008515e-05,
|
| 462 |
+
"loss": 0.3649,
|
| 463 |
+
"step": 3100
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 2.36664162283997,
|
| 467 |
+
"grad_norm": 2.9691059589385986,
|
| 468 |
+
"learning_rate": 1.0555972952667167e-05,
|
| 469 |
+
"loss": 0.3558,
|
| 470 |
+
"step": 3150
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.4042073628850487,
|
| 474 |
+
"grad_norm": 2.8758184909820557,
|
| 475 |
+
"learning_rate": 9.929877285249187e-06,
|
| 476 |
+
"loss": 0.3605,
|
| 477 |
+
"step": 3200
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.441773102930128,
|
| 481 |
+
"grad_norm": 2.866455554962158,
|
| 482 |
+
"learning_rate": 9.303781617831204e-06,
|
| 483 |
+
"loss": 0.3459,
|
| 484 |
+
"step": 3250
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 2.479338842975207,
|
| 488 |
+
"grad_norm": 2.672839879989624,
|
| 489 |
+
"learning_rate": 8.677685950413224e-06,
|
| 490 |
+
"loss": 0.3553,
|
| 491 |
+
"step": 3300
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.5169045830202856,
|
| 495 |
+
"grad_norm": 3.4048142433166504,
|
| 496 |
+
"learning_rate": 8.051590282995241e-06,
|
| 497 |
+
"loss": 0.3502,
|
| 498 |
+
"step": 3350
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.5544703230653645,
|
| 502 |
+
"grad_norm": 2.534475564956665,
|
| 503 |
+
"learning_rate": 7.4254946155772605e-06,
|
| 504 |
+
"loss": 0.3519,
|
| 505 |
+
"step": 3400
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.5920360631104433,
|
| 509 |
+
"grad_norm": 5.125302791595459,
|
| 510 |
+
"learning_rate": 6.799398948159279e-06,
|
| 511 |
+
"loss": 0.3561,
|
| 512 |
+
"step": 3450
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.629601803155522,
|
| 516 |
+
"grad_norm": 3.038414478302002,
|
| 517 |
+
"learning_rate": 6.173303280741298e-06,
|
| 518 |
+
"loss": 0.3708,
|
| 519 |
+
"step": 3500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.667167543200601,
|
| 523 |
+
"grad_norm": 3.264307975769043,
|
| 524 |
+
"learning_rate": 5.5472076133233154e-06,
|
| 525 |
+
"loss": 0.3688,
|
| 526 |
+
"step": 3550
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.70473328324568,
|
| 530 |
+
"grad_norm": 3.3217625617980957,
|
| 531 |
+
"learning_rate": 4.921111945905334e-06,
|
| 532 |
+
"loss": 0.3538,
|
| 533 |
+
"step": 3600
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.7422990232907587,
|
| 537 |
+
"grad_norm": 1.3763796091079712,
|
| 538 |
+
"learning_rate": 4.295016278487353e-06,
|
| 539 |
+
"loss": 0.3463,
|
| 540 |
+
"step": 3650
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.779864763335838,
|
| 544 |
+
"grad_norm": 4.890012741088867,
|
| 545 |
+
"learning_rate": 3.6689206110693716e-06,
|
| 546 |
+
"loss": 0.3514,
|
| 547 |
+
"step": 3700
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 2.8174305033809164,
|
| 551 |
+
"grad_norm": 2.0561699867248535,
|
| 552 |
+
"learning_rate": 3.0428249436513902e-06,
|
| 553 |
+
"loss": 0.3619,
|
| 554 |
+
"step": 3750
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.8549962434259957,
|
| 558 |
+
"grad_norm": 3.4119489192962646,
|
| 559 |
+
"learning_rate": 2.4167292762334084e-06,
|
| 560 |
+
"loss": 0.3557,
|
| 561 |
+
"step": 3800
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.8925619834710745,
|
| 565 |
+
"grad_norm": 4.181868553161621,
|
| 566 |
+
"learning_rate": 1.7906336088154272e-06,
|
| 567 |
+
"loss": 0.3526,
|
| 568 |
+
"step": 3850
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 2.9301277235161534,
|
| 572 |
+
"grad_norm": 2.8571691513061523,
|
| 573 |
+
"learning_rate": 1.1645379413974456e-06,
|
| 574 |
+
"loss": 0.37,
|
| 575 |
+
"step": 3900
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 2.967693463561232,
|
| 579 |
+
"grad_norm": 7.221222877502441,
|
| 580 |
+
"learning_rate": 5.38442273979464e-07,
|
| 581 |
+
"loss": 0.3626,
|
| 582 |
+
"step": 3950
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 3.0,
|
| 586 |
+
"eval_accuracy": 0.7501292111074567,
|
| 587 |
+
"eval_f1": 0.7617169997311587,
|
| 588 |
+
"eval_loss": 0.5218836665153503,
|
| 589 |
+
"eval_runtime": 144.5779,
|
| 590 |
+
"eval_samples_per_second": 147.208,
|
| 591 |
+
"eval_steps_per_second": 2.303,
|
| 592 |
+
"step": 3993
|
| 593 |
+
}
|
| 594 |
+
],
|
| 595 |
+
"logging_steps": 50,
|
| 596 |
+
"max_steps": 3993,
|
| 597 |
+
"num_input_tokens_seen": 0,
|
| 598 |
+
"num_train_epochs": 3,
|
| 599 |
+
"save_steps": 500,
|
| 600 |
+
"stateful_callbacks": {
|
| 601 |
+
"TrainerControl": {
|
| 602 |
+
"args": {
|
| 603 |
+
"should_epoch_stop": false,
|
| 604 |
+
"should_evaluate": false,
|
| 605 |
+
"should_log": false,
|
| 606 |
+
"should_save": true,
|
| 607 |
+
"should_training_stop": true
|
| 608 |
+
},
|
| 609 |
+
"attributes": {}
|
| 610 |
+
}
|
| 611 |
+
},
|
| 612 |
+
"total_flos": 3.3829656736167936e+16,
|
| 613 |
+
"train_batch_size": 64,
|
| 614 |
+
"trial_name": null,
|
| 615 |
+
"trial_params": null
|
| 616 |
+
}
|
checkpoint-3993/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:497b1fb162099a485fef5d85839946a6214e40e81d40b13c3ef06199d07ece80
|
| 3 |
+
size 5304
|
checkpoint-3993/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilbert-base-multilingual-cased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"output_past": true,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"problem_type": "single_label_classification",
|
| 19 |
+
"qa_dropout": 0.1,
|
| 20 |
+
"seq_classif_dropout": 0.2,
|
| 21 |
+
"sinusoidal_pos_embds": false,
|
| 22 |
+
"tie_weights_": true,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.48.3",
|
| 25 |
+
"vocab_size": 119547
|
| 26 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ea9b5e7183bbf5cf8fa18a035400a551437fae62101ab6a9f9b5deb3b2f5b8c
|
| 3 |
+
size 541317368
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|