Upload folder using huggingface_hub
Browse files- README.md +26 -0
- checkpoint-3924/config.json +71 -0
- checkpoint-3924/model.safetensors +3 -0
- checkpoint-3924/optimizer.pt +3 -0
- checkpoint-3924/rng_state_0.pth +3 -0
- checkpoint-3924/rng_state_1.pth +3 -0
- checkpoint-3924/scheduler.pt +3 -0
- checkpoint-3924/trainer_state.json +1182 -0
- checkpoint-3924/training_args.bin +3 -0
- config.json +71 -0
- model.safetensors +3 -0
- runs/Nov05_18-51-38_ficino/events.out.tfevents.1730829100.ficino.3820667.0 +2 -2
- runs/Nov05_18-51-38_ficino/events.out.tfevents.1730830078.ficino.3820667.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- token-classification
|
6 |
+
base_model: NbAiLab/nb-bert-base
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
datasets:
|
10 |
+
- ltgoslo/norne
|
11 |
+
---
|
12 |
+
|
13 |
+
# Model Trained Using AutoTrain
|
14 |
+
|
15 |
+
- Problem type: Token Classification
|
16 |
+
|
17 |
+
## Validation Metrics
|
18 |
+
loss: 0.0650700181722641
|
19 |
+
|
20 |
+
precision: 0.985085078075765
|
21 |
+
|
22 |
+
recall: 0.9877826148012919
|
23 |
+
|
24 |
+
f1: 0.9864320022438031
|
25 |
+
|
26 |
+
accuracy: 0.9861949007001629
|
checkpoint-3924/config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "NbAiLab/nb-bert-base",
|
3 |
+
"_num_labels": 17,
|
4 |
+
"architectures": [
|
5 |
+
"BertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "NOUN",
|
16 |
+
"1": "PUNCT",
|
17 |
+
"2": "ADP",
|
18 |
+
"3": "NUM",
|
19 |
+
"4": "SYM",
|
20 |
+
"5": "SCONJ",
|
21 |
+
"6": "ADJ",
|
22 |
+
"7": "PART",
|
23 |
+
"8": "DET",
|
24 |
+
"9": "CCONJ",
|
25 |
+
"10": "PROPN",
|
26 |
+
"11": "PRON",
|
27 |
+
"12": "X",
|
28 |
+
"13": "ADV",
|
29 |
+
"14": "INTJ",
|
30 |
+
"15": "VERB",
|
31 |
+
"16": "AUX"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 3072,
|
35 |
+
"label2id": {
|
36 |
+
"ADJ": 6,
|
37 |
+
"ADP": 2,
|
38 |
+
"ADV": 13,
|
39 |
+
"AUX": 16,
|
40 |
+
"CCONJ": 9,
|
41 |
+
"DET": 8,
|
42 |
+
"INTJ": 14,
|
43 |
+
"NOUN": 0,
|
44 |
+
"NUM": 3,
|
45 |
+
"PART": 7,
|
46 |
+
"PRON": 11,
|
47 |
+
"PROPN": 10,
|
48 |
+
"PUNCT": 1,
|
49 |
+
"SCONJ": 5,
|
50 |
+
"SYM": 4,
|
51 |
+
"VERB": 15,
|
52 |
+
"X": 12
|
53 |
+
},
|
54 |
+
"layer_norm_eps": 1e-12,
|
55 |
+
"max_position_embeddings": 512,
|
56 |
+
"model_type": "bert",
|
57 |
+
"num_attention_heads": 12,
|
58 |
+
"num_hidden_layers": 12,
|
59 |
+
"pad_token_id": 0,
|
60 |
+
"pooler_fc_size": 768,
|
61 |
+
"pooler_num_attention_heads": 12,
|
62 |
+
"pooler_num_fc_layers": 3,
|
63 |
+
"pooler_size_per_head": 128,
|
64 |
+
"pooler_type": "first_token_transform",
|
65 |
+
"position_embedding_type": "absolute",
|
66 |
+
"torch_dtype": "float32",
|
67 |
+
"transformers_version": "4.45.0",
|
68 |
+
"type_vocab_size": 2,
|
69 |
+
"use_cache": true,
|
70 |
+
"vocab_size": 119547
|
71 |
+
}
|
checkpoint-3924/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fec2dddda2f2863c9860b68f2970f8f9e441f254d3b38692add9e30738f6230a
|
3 |
+
size 709127044
|
checkpoint-3924/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc99fd55ca410cfe12e16cefe154cde77623fe32d82a4a5a346dcf4de2aa26c
|
3 |
+
size 1418373818
|
checkpoint-3924/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6400c5d9d37e3116c743653b85cb23f5d2476222059565c35d00a8dee8394b76
|
3 |
+
size 14512
|
checkpoint-3924/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:395d4f8dc2fd1265234965ac087bc4c323a3f257c75500302578d89b0ad0cebb
|
3 |
+
size 14512
|
checkpoint-3924/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2711dca1f6bd3fa3dfb19a7522c38521aa284ab1ee41c4b017e21f7242278786
|
3 |
+
size 1064
|
checkpoint-3924/trainer_state.json
ADDED
@@ -0,0 +1,1182 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0650700181722641,
|
3 |
+
"best_model_checkpoint": "nb-bert-base-pos-ltgnorne-lr3e-5-e5/checkpoint-3924",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3924,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0254841997961264,
|
13 |
+
"grad_norm": 4.497822284698486,
|
14 |
+
"learning_rate": 1.4663951120162932e-06,
|
15 |
+
"loss": 2.8613,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0509683995922528,
|
20 |
+
"grad_norm": 4.501702308654785,
|
21 |
+
"learning_rate": 2.993890020366599e-06,
|
22 |
+
"loss": 2.6378,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0764525993883792,
|
27 |
+
"grad_norm": 3.225400447845459,
|
28 |
+
"learning_rate": 4.521384928716905e-06,
|
29 |
+
"loss": 2.3048,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1019367991845056,
|
34 |
+
"grad_norm": 2.7836780548095703,
|
35 |
+
"learning_rate": 6.048879837067211e-06,
|
36 |
+
"loss": 1.9637,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.127420998980632,
|
41 |
+
"grad_norm": 2.729814291000366,
|
42 |
+
"learning_rate": 7.5763747454175154e-06,
|
43 |
+
"loss": 1.5022,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.1529051987767584,
|
48 |
+
"grad_norm": 2.058290958404541,
|
49 |
+
"learning_rate": 9.103869653767821e-06,
|
50 |
+
"loss": 0.9212,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.1783893985728848,
|
55 |
+
"grad_norm": 2.431959629058838,
|
56 |
+
"learning_rate": 1.0631364562118128e-05,
|
57 |
+
"loss": 0.4504,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.2038735983690112,
|
62 |
+
"grad_norm": 3.45493221282959,
|
63 |
+
"learning_rate": 1.2158859470468432e-05,
|
64 |
+
"loss": 0.2543,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.22935779816513763,
|
69 |
+
"grad_norm": 5.069894790649414,
|
70 |
+
"learning_rate": 1.3686354378818739e-05,
|
71 |
+
"loss": 0.1895,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.254841997961264,
|
76 |
+
"grad_norm": 2.2221596240997314,
|
77 |
+
"learning_rate": 1.5213849287169042e-05,
|
78 |
+
"loss": 0.1606,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.2803261977573904,
|
83 |
+
"grad_norm": 0.943159282207489,
|
84 |
+
"learning_rate": 1.6741344195519347e-05,
|
85 |
+
"loss": 0.1191,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.3058103975535168,
|
90 |
+
"grad_norm": 1.4674568176269531,
|
91 |
+
"learning_rate": 1.8268839103869655e-05,
|
92 |
+
"loss": 0.1128,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.3312945973496432,
|
97 |
+
"grad_norm": 2.1226422786712646,
|
98 |
+
"learning_rate": 1.979633401221996e-05,
|
99 |
+
"loss": 0.118,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.3567787971457696,
|
104 |
+
"grad_norm": 1.1651442050933838,
|
105 |
+
"learning_rate": 2.1323828920570265e-05,
|
106 |
+
"loss": 0.1069,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.382262996941896,
|
111 |
+
"grad_norm": 2.2320973873138428,
|
112 |
+
"learning_rate": 2.285132382892057e-05,
|
113 |
+
"loss": 0.1289,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.4077471967380224,
|
118 |
+
"grad_norm": 2.247786521911621,
|
119 |
+
"learning_rate": 2.4378818737270878e-05,
|
120 |
+
"loss": 0.1052,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.4332313965341488,
|
125 |
+
"grad_norm": 3.606870651245117,
|
126 |
+
"learning_rate": 2.5906313645621183e-05,
|
127 |
+
"loss": 0.0896,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.45871559633027525,
|
132 |
+
"grad_norm": 0.5746941566467285,
|
133 |
+
"learning_rate": 2.7433808553971487e-05,
|
134 |
+
"loss": 0.093,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.4841997961264016,
|
139 |
+
"grad_norm": 1.509137749671936,
|
140 |
+
"learning_rate": 2.8961303462321792e-05,
|
141 |
+
"loss": 0.0928,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.509683995922528,
|
146 |
+
"grad_norm": 1.3736240863800049,
|
147 |
+
"learning_rate": 2.9945627548708655e-05,
|
148 |
+
"loss": 0.0933,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.5351681957186545,
|
153 |
+
"grad_norm": 2.923942804336548,
|
154 |
+
"learning_rate": 2.9775713638423202e-05,
|
155 |
+
"loss": 0.0717,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.5606523955147809,
|
160 |
+
"grad_norm": 1.3372660875320435,
|
161 |
+
"learning_rate": 2.9605799728137742e-05,
|
162 |
+
"loss": 0.0757,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.5861365953109072,
|
167 |
+
"grad_norm": 2.0181891918182373,
|
168 |
+
"learning_rate": 2.943588581785229e-05,
|
169 |
+
"loss": 0.0796,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.6116207951070336,
|
174 |
+
"grad_norm": 1.258780837059021,
|
175 |
+
"learning_rate": 2.9265971907566832e-05,
|
176 |
+
"loss": 0.076,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.6371049949031601,
|
181 |
+
"grad_norm": 2.01127028465271,
|
182 |
+
"learning_rate": 2.909605799728138e-05,
|
183 |
+
"loss": 0.0791,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.6625891946992865,
|
188 |
+
"grad_norm": 1.2377755641937256,
|
189 |
+
"learning_rate": 2.8926144086995923e-05,
|
190 |
+
"loss": 0.065,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.6880733944954128,
|
195 |
+
"grad_norm": 2.2438857555389404,
|
196 |
+
"learning_rate": 2.8756230176710466e-05,
|
197 |
+
"loss": 0.0716,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.7135575942915392,
|
202 |
+
"grad_norm": 1.5645134449005127,
|
203 |
+
"learning_rate": 2.8586316266425013e-05,
|
204 |
+
"loss": 0.057,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.7390417940876657,
|
209 |
+
"grad_norm": 1.144615650177002,
|
210 |
+
"learning_rate": 2.841640235613956e-05,
|
211 |
+
"loss": 0.0598,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.764525993883792,
|
216 |
+
"grad_norm": 1.8201572895050049,
|
217 |
+
"learning_rate": 2.82464884458541e-05,
|
218 |
+
"loss": 0.0648,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.7900101936799184,
|
223 |
+
"grad_norm": 0.7320142388343811,
|
224 |
+
"learning_rate": 2.8076574535568647e-05,
|
225 |
+
"loss": 0.0561,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.8154943934760448,
|
230 |
+
"grad_norm": 1.0732890367507935,
|
231 |
+
"learning_rate": 2.790666062528319e-05,
|
232 |
+
"loss": 0.0498,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.8409785932721713,
|
237 |
+
"grad_norm": 2.709826707839966,
|
238 |
+
"learning_rate": 2.7736746714997733e-05,
|
239 |
+
"loss": 0.0701,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.8664627930682977,
|
244 |
+
"grad_norm": 1.808638572692871,
|
245 |
+
"learning_rate": 2.756683280471228e-05,
|
246 |
+
"loss": 0.0676,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.891946992864424,
|
251 |
+
"grad_norm": 5.431212425231934,
|
252 |
+
"learning_rate": 2.7396918894426824e-05,
|
253 |
+
"loss": 0.0504,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.9174311926605505,
|
258 |
+
"grad_norm": 2.724369525909424,
|
259 |
+
"learning_rate": 2.722700498414137e-05,
|
260 |
+
"loss": 0.0539,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.9429153924566769,
|
265 |
+
"grad_norm": 0.9031899571418762,
|
266 |
+
"learning_rate": 2.7057091073855914e-05,
|
267 |
+
"loss": 0.0479,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.9683995922528033,
|
272 |
+
"grad_norm": 1.0398321151733398,
|
273 |
+
"learning_rate": 2.6887177163570457e-05,
|
274 |
+
"loss": 0.0569,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.9938837920489296,
|
279 |
+
"grad_norm": 4.719447612762451,
|
280 |
+
"learning_rate": 2.6717263253285004e-05,
|
281 |
+
"loss": 0.0587,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.0,
|
286 |
+
"eval_accuracy": 0.9830243515786693,
|
287 |
+
"eval_f1": 0.9817582841221721,
|
288 |
+
"eval_loss": 0.0652645155787468,
|
289 |
+
"eval_precision": 0.980058076479026,
|
290 |
+
"eval_recall": 0.9834644010672658,
|
291 |
+
"eval_runtime": 4.374,
|
292 |
+
"eval_samples_per_second": 443.301,
|
293 |
+
"eval_steps_per_second": 13.946,
|
294 |
+
"step": 981
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 1.019367991845056,
|
298 |
+
"grad_norm": 0.5373720526695251,
|
299 |
+
"learning_rate": 2.6547349342999548e-05,
|
300 |
+
"loss": 0.0465,
|
301 |
+
"step": 1000
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 1.0448521916411824,
|
305 |
+
"grad_norm": 0.31597161293029785,
|
306 |
+
"learning_rate": 2.637743543271409e-05,
|
307 |
+
"loss": 0.0347,
|
308 |
+
"step": 1025
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.070336391437309,
|
312 |
+
"grad_norm": 0.08823961019515991,
|
313 |
+
"learning_rate": 2.6207521522428638e-05,
|
314 |
+
"loss": 0.0387,
|
315 |
+
"step": 1050
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 1.0958205912334353,
|
319 |
+
"grad_norm": 1.0735955238342285,
|
320 |
+
"learning_rate": 2.603760761214318e-05,
|
321 |
+
"loss": 0.0327,
|
322 |
+
"step": 1075
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 1.1213047910295617,
|
326 |
+
"grad_norm": 0.6932256817817688,
|
327 |
+
"learning_rate": 2.5867693701857728e-05,
|
328 |
+
"loss": 0.0332,
|
329 |
+
"step": 1100
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 1.146788990825688,
|
333 |
+
"grad_norm": 1.1093873977661133,
|
334 |
+
"learning_rate": 2.569777979157227e-05,
|
335 |
+
"loss": 0.0456,
|
336 |
+
"step": 1125
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 1.1722731906218145,
|
340 |
+
"grad_norm": 3.3177976608276367,
|
341 |
+
"learning_rate": 2.5527865881286815e-05,
|
342 |
+
"loss": 0.0381,
|
343 |
+
"step": 1150
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 1.1977573904179408,
|
347 |
+
"grad_norm": 5.12001371383667,
|
348 |
+
"learning_rate": 2.535795197100136e-05,
|
349 |
+
"loss": 0.0351,
|
350 |
+
"step": 1175
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.2232415902140672,
|
354 |
+
"grad_norm": 0.8894160389900208,
|
355 |
+
"learning_rate": 2.5188038060715902e-05,
|
356 |
+
"loss": 0.034,
|
357 |
+
"step": 1200
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 1.2487257900101936,
|
361 |
+
"grad_norm": 0.8692567348480225,
|
362 |
+
"learning_rate": 2.501812415043045e-05,
|
363 |
+
"loss": 0.0482,
|
364 |
+
"step": 1225
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 1.2742099898063202,
|
368 |
+
"grad_norm": 0.5012984275817871,
|
369 |
+
"learning_rate": 2.4848210240144995e-05,
|
370 |
+
"loss": 0.0515,
|
371 |
+
"step": 1250
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 1.2996941896024465,
|
375 |
+
"grad_norm": 1.6234453916549683,
|
376 |
+
"learning_rate": 2.467829632985954e-05,
|
377 |
+
"loss": 0.0303,
|
378 |
+
"step": 1275
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 1.325178389398573,
|
382 |
+
"grad_norm": 0.32807931303977966,
|
383 |
+
"learning_rate": 2.4508382419574082e-05,
|
384 |
+
"loss": 0.0371,
|
385 |
+
"step": 1300
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 1.3506625891946993,
|
389 |
+
"grad_norm": 0.29069948196411133,
|
390 |
+
"learning_rate": 2.4338468509288626e-05,
|
391 |
+
"loss": 0.0381,
|
392 |
+
"step": 1325
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 1.3761467889908257,
|
396 |
+
"grad_norm": 0.2267286479473114,
|
397 |
+
"learning_rate": 2.4168554599003172e-05,
|
398 |
+
"loss": 0.0335,
|
399 |
+
"step": 1350
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 1.401630988786952,
|
403 |
+
"grad_norm": 0.6649707555770874,
|
404 |
+
"learning_rate": 2.399864068871772e-05,
|
405 |
+
"loss": 0.028,
|
406 |
+
"step": 1375
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 1.4271151885830786,
|
410 |
+
"grad_norm": 0.4773367941379547,
|
411 |
+
"learning_rate": 2.382872677843226e-05,
|
412 |
+
"loss": 0.0378,
|
413 |
+
"step": 1400
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 1.452599388379205,
|
417 |
+
"grad_norm": 0.7523585557937622,
|
418 |
+
"learning_rate": 2.3658812868146806e-05,
|
419 |
+
"loss": 0.0276,
|
420 |
+
"step": 1425
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 1.4780835881753314,
|
424 |
+
"grad_norm": 0.694980800151825,
|
425 |
+
"learning_rate": 2.3488898957861353e-05,
|
426 |
+
"loss": 0.0488,
|
427 |
+
"step": 1450
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 1.5035677879714577,
|
431 |
+
"grad_norm": 1.879299521446228,
|
432 |
+
"learning_rate": 2.3318985047575896e-05,
|
433 |
+
"loss": 0.0336,
|
434 |
+
"step": 1475
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 1.529051987767584,
|
438 |
+
"grad_norm": 0.8800904750823975,
|
439 |
+
"learning_rate": 2.314907113729044e-05,
|
440 |
+
"loss": 0.035,
|
441 |
+
"step": 1500
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 1.5545361875637105,
|
445 |
+
"grad_norm": 3.8236799240112305,
|
446 |
+
"learning_rate": 2.2979157227004983e-05,
|
447 |
+
"loss": 0.035,
|
448 |
+
"step": 1525
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 1.5800203873598369,
|
452 |
+
"grad_norm": 0.3992440402507782,
|
453 |
+
"learning_rate": 2.280924331671953e-05,
|
454 |
+
"loss": 0.0292,
|
455 |
+
"step": 1550
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 1.6055045871559632,
|
459 |
+
"grad_norm": 0.6917338371276855,
|
460 |
+
"learning_rate": 2.2639329406434073e-05,
|
461 |
+
"loss": 0.0318,
|
462 |
+
"step": 1575
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 1.6309887869520896,
|
466 |
+
"grad_norm": 2.00313663482666,
|
467 |
+
"learning_rate": 2.2469415496148617e-05,
|
468 |
+
"loss": 0.0357,
|
469 |
+
"step": 1600
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"epoch": 1.656472986748216,
|
473 |
+
"grad_norm": 0.45046761631965637,
|
474 |
+
"learning_rate": 2.2299501585863164e-05,
|
475 |
+
"loss": 0.0408,
|
476 |
+
"step": 1625
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 1.6819571865443423,
|
480 |
+
"grad_norm": 0.23316547274589539,
|
481 |
+
"learning_rate": 2.212958767557771e-05,
|
482 |
+
"loss": 0.0357,
|
483 |
+
"step": 1650
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 1.707441386340469,
|
487 |
+
"grad_norm": 0.5247312784194946,
|
488 |
+
"learning_rate": 2.195967376529225e-05,
|
489 |
+
"loss": 0.0386,
|
490 |
+
"step": 1675
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 1.7329255861365953,
|
494 |
+
"grad_norm": 6.273862361907959,
|
495 |
+
"learning_rate": 2.1789759855006797e-05,
|
496 |
+
"loss": 0.0321,
|
497 |
+
"step": 1700
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 1.7584097859327217,
|
501 |
+
"grad_norm": 0.7023279666900635,
|
502 |
+
"learning_rate": 2.161984594472134e-05,
|
503 |
+
"loss": 0.0399,
|
504 |
+
"step": 1725
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 1.7838939857288483,
|
508 |
+
"grad_norm": 2.0238797664642334,
|
509 |
+
"learning_rate": 2.1449932034435888e-05,
|
510 |
+
"loss": 0.038,
|
511 |
+
"step": 1750
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 1.8093781855249746,
|
515 |
+
"grad_norm": 0.5117468237876892,
|
516 |
+
"learning_rate": 2.128001812415043e-05,
|
517 |
+
"loss": 0.0293,
|
518 |
+
"step": 1775
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 1.834862385321101,
|
522 |
+
"grad_norm": 0.052200186997652054,
|
523 |
+
"learning_rate": 2.1110104213864974e-05,
|
524 |
+
"loss": 0.0231,
|
525 |
+
"step": 1800
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 1.8603465851172274,
|
529 |
+
"grad_norm": 0.2978757619857788,
|
530 |
+
"learning_rate": 2.094019030357952e-05,
|
531 |
+
"loss": 0.0253,
|
532 |
+
"step": 1825
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 1.8858307849133538,
|
536 |
+
"grad_norm": 0.7025816440582275,
|
537 |
+
"learning_rate": 2.0770276393294068e-05,
|
538 |
+
"loss": 0.037,
|
539 |
+
"step": 1850
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 1.9113149847094801,
|
543 |
+
"grad_norm": 2.105027914047241,
|
544 |
+
"learning_rate": 2.0600362483008608e-05,
|
545 |
+
"loss": 0.0402,
|
546 |
+
"step": 1875
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 1.9367991845056065,
|
550 |
+
"grad_norm": 1.320366621017456,
|
551 |
+
"learning_rate": 2.0430448572723155e-05,
|
552 |
+
"loss": 0.0299,
|
553 |
+
"step": 1900
|
554 |
+
},
|
555 |
+
{
|
556 |
+
"epoch": 1.9622833843017329,
|
557 |
+
"grad_norm": 1.0839900970458984,
|
558 |
+
"learning_rate": 2.02605346624377e-05,
|
559 |
+
"loss": 0.0465,
|
560 |
+
"step": 1925
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 1.9877675840978593,
|
564 |
+
"grad_norm": 1.192915678024292,
|
565 |
+
"learning_rate": 2.0090620752152242e-05,
|
566 |
+
"loss": 0.0356,
|
567 |
+
"step": 1950
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 2.0,
|
571 |
+
"eval_accuracy": 0.9837729534545775,
|
572 |
+
"eval_f1": 0.9838220601896482,
|
573 |
+
"eval_loss": 0.06676298379898071,
|
574 |
+
"eval_precision": 0.9823585004725401,
|
575 |
+
"eval_recall": 0.9852899873613257,
|
576 |
+
"eval_runtime": 4.1484,
|
577 |
+
"eval_samples_per_second": 467.414,
|
578 |
+
"eval_steps_per_second": 14.705,
|
579 |
+
"step": 1962
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 2.0132517838939856,
|
583 |
+
"grad_norm": 0.05750567093491554,
|
584 |
+
"learning_rate": 1.992070684186679e-05,
|
585 |
+
"loss": 0.0254,
|
586 |
+
"step": 1975
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 2.038735983690112,
|
590 |
+
"grad_norm": 0.5030219554901123,
|
591 |
+
"learning_rate": 1.9750792931581332e-05,
|
592 |
+
"loss": 0.016,
|
593 |
+
"step": 2000
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 2.0642201834862384,
|
597 |
+
"grad_norm": 0.5581088066101074,
|
598 |
+
"learning_rate": 1.958087902129588e-05,
|
599 |
+
"loss": 0.0274,
|
600 |
+
"step": 2025
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 2.0897043832823647,
|
604 |
+
"grad_norm": 0.4084581434726715,
|
605 |
+
"learning_rate": 1.941096511101042e-05,
|
606 |
+
"loss": 0.0185,
|
607 |
+
"step": 2050
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 2.115188583078491,
|
611 |
+
"grad_norm": 0.5078397989273071,
|
612 |
+
"learning_rate": 1.9241051200724966e-05,
|
613 |
+
"loss": 0.012,
|
614 |
+
"step": 2075
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 2.140672782874618,
|
618 |
+
"grad_norm": 1.139233946800232,
|
619 |
+
"learning_rate": 1.9071137290439512e-05,
|
620 |
+
"loss": 0.0219,
|
621 |
+
"step": 2100
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 2.1661569826707443,
|
625 |
+
"grad_norm": 0.3767656683921814,
|
626 |
+
"learning_rate": 1.8901223380154056e-05,
|
627 |
+
"loss": 0.0232,
|
628 |
+
"step": 2125
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 2.1916411824668707,
|
632 |
+
"grad_norm": 0.4100117087364197,
|
633 |
+
"learning_rate": 1.87313094698686e-05,
|
634 |
+
"loss": 0.0209,
|
635 |
+
"step": 2150
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 2.217125382262997,
|
639 |
+
"grad_norm": 0.3346911370754242,
|
640 |
+
"learning_rate": 1.8561395559583146e-05,
|
641 |
+
"loss": 0.0142,
|
642 |
+
"step": 2175
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 2.2426095820591234,
|
646 |
+
"grad_norm": 0.44971033930778503,
|
647 |
+
"learning_rate": 1.839148164929769e-05,
|
648 |
+
"loss": 0.0207,
|
649 |
+
"step": 2200
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 2.26809378185525,
|
653 |
+
"grad_norm": 0.0442005917429924,
|
654 |
+
"learning_rate": 1.8228364295423653e-05,
|
655 |
+
"loss": 0.0255,
|
656 |
+
"step": 2225
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 2.293577981651376,
|
660 |
+
"grad_norm": 0.018714234232902527,
|
661 |
+
"learning_rate": 1.8058450385138197e-05,
|
662 |
+
"loss": 0.0149,
|
663 |
+
"step": 2250
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 2.3190621814475025,
|
667 |
+
"grad_norm": 1.526605248451233,
|
668 |
+
"learning_rate": 1.788853647485274e-05,
|
669 |
+
"loss": 0.0182,
|
670 |
+
"step": 2275
|
671 |
+
},
|
672 |
+
{
|
673 |
+
"epoch": 2.344546381243629,
|
674 |
+
"grad_norm": 0.1787564605474472,
|
675 |
+
"learning_rate": 1.7718622564567287e-05,
|
676 |
+
"loss": 0.0153,
|
677 |
+
"step": 2300
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 2.3700305810397553,
|
681 |
+
"grad_norm": 1.280836582183838,
|
682 |
+
"learning_rate": 1.755550521069325e-05,
|
683 |
+
"loss": 0.0259,
|
684 |
+
"step": 2325
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 2.3955147808358817,
|
688 |
+
"grad_norm": 0.41557249426841736,
|
689 |
+
"learning_rate": 1.7385591300407794e-05,
|
690 |
+
"loss": 0.0192,
|
691 |
+
"step": 2350
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 2.420998980632008,
|
695 |
+
"grad_norm": 0.4954489469528198,
|
696 |
+
"learning_rate": 1.7215677390122338e-05,
|
697 |
+
"loss": 0.0244,
|
698 |
+
"step": 2375
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 2.4464831804281344,
|
702 |
+
"grad_norm": 0.25688356161117554,
|
703 |
+
"learning_rate": 1.7045763479836884e-05,
|
704 |
+
"loss": 0.0178,
|
705 |
+
"step": 2400
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 2.4719673802242608,
|
709 |
+
"grad_norm": 0.1957683563232422,
|
710 |
+
"learning_rate": 1.6875849569551428e-05,
|
711 |
+
"loss": 0.0193,
|
712 |
+
"step": 2425
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 2.497451580020387,
|
716 |
+
"grad_norm": 0.0999796912074089,
|
717 |
+
"learning_rate": 1.670593565926597e-05,
|
718 |
+
"loss": 0.0239,
|
719 |
+
"step": 2450
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 2.522935779816514,
|
723 |
+
"grad_norm": 0.20732557773590088,
|
724 |
+
"learning_rate": 1.6536021748980518e-05,
|
725 |
+
"loss": 0.0213,
|
726 |
+
"step": 2475
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 2.5484199796126403,
|
730 |
+
"grad_norm": 0.1995435357093811,
|
731 |
+
"learning_rate": 1.636610783869506e-05,
|
732 |
+
"loss": 0.0187,
|
733 |
+
"step": 2500
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 2.5739041794087667,
|
737 |
+
"grad_norm": 0.25311583280563354,
|
738 |
+
"learning_rate": 1.6196193928409605e-05,
|
739 |
+
"loss": 0.0272,
|
740 |
+
"step": 2525
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 2.599388379204893,
|
744 |
+
"grad_norm": 0.4466765224933624,
|
745 |
+
"learning_rate": 1.602628001812415e-05,
|
746 |
+
"loss": 0.0212,
|
747 |
+
"step": 2550
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 2.6248725790010194,
|
751 |
+
"grad_norm": 0.12018584460020065,
|
752 |
+
"learning_rate": 1.5856366107838695e-05,
|
753 |
+
"loss": 0.023,
|
754 |
+
"step": 2575
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 2.650356778797146,
|
758 |
+
"grad_norm": 0.6461846232414246,
|
759 |
+
"learning_rate": 1.5686452197553242e-05,
|
760 |
+
"loss": 0.023,
|
761 |
+
"step": 2600
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 2.675840978593272,
|
765 |
+
"grad_norm": 0.08898350596427917,
|
766 |
+
"learning_rate": 1.5516538287267785e-05,
|
767 |
+
"loss": 0.0208,
|
768 |
+
"step": 2625
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 2.7013251783893986,
|
772 |
+
"grad_norm": 0.18236540257930756,
|
773 |
+
"learning_rate": 1.534662437698233e-05,
|
774 |
+
"loss": 0.0172,
|
775 |
+
"step": 2650
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 2.726809378185525,
|
779 |
+
"grad_norm": 0.09674384444952011,
|
780 |
+
"learning_rate": 1.5176710466696876e-05,
|
781 |
+
"loss": 0.0176,
|
782 |
+
"step": 2675
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 2.7522935779816513,
|
786 |
+
"grad_norm": 0.5571973919868469,
|
787 |
+
"learning_rate": 1.5006796556411417e-05,
|
788 |
+
"loss": 0.0219,
|
789 |
+
"step": 2700
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 2.7777777777777777,
|
793 |
+
"grad_norm": 0.7178367376327515,
|
794 |
+
"learning_rate": 1.4836882646125962e-05,
|
795 |
+
"loss": 0.0175,
|
796 |
+
"step": 2725
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 2.803261977573904,
|
800 |
+
"grad_norm": 1.9719717502593994,
|
801 |
+
"learning_rate": 1.4666968735840508e-05,
|
802 |
+
"loss": 0.0152,
|
803 |
+
"step": 2750
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 2.8287461773700304,
|
807 |
+
"grad_norm": 0.782957136631012,
|
808 |
+
"learning_rate": 1.4497054825555051e-05,
|
809 |
+
"loss": 0.0199,
|
810 |
+
"step": 2775
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 2.8542303771661572,
|
814 |
+
"grad_norm": 1.0010164976119995,
|
815 |
+
"learning_rate": 1.4327140915269598e-05,
|
816 |
+
"loss": 0.0181,
|
817 |
+
"step": 2800
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 2.879714576962283,
|
821 |
+
"grad_norm": 0.12285976111888885,
|
822 |
+
"learning_rate": 1.4157227004984141e-05,
|
823 |
+
"loss": 0.0167,
|
824 |
+
"step": 2825
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 2.90519877675841,
|
828 |
+
"grad_norm": 0.4028477668762207,
|
829 |
+
"learning_rate": 1.3987313094698686e-05,
|
830 |
+
"loss": 0.0194,
|
831 |
+
"step": 2850
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 2.930682976554536,
|
835 |
+
"grad_norm": 0.14099347591400146,
|
836 |
+
"learning_rate": 1.381739918441323e-05,
|
837 |
+
"loss": 0.0137,
|
838 |
+
"step": 2875
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 2.9561671763506627,
|
842 |
+
"grad_norm": 0.23822110891342163,
|
843 |
+
"learning_rate": 1.3647485274127777e-05,
|
844 |
+
"loss": 0.0142,
|
845 |
+
"step": 2900
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 2.981651376146789,
|
849 |
+
"grad_norm": 0.32884514331817627,
|
850 |
+
"learning_rate": 1.347757136384232e-05,
|
851 |
+
"loss": 0.0159,
|
852 |
+
"step": 2925
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 3.0,
|
856 |
+
"eval_accuracy": 0.984609626139416,
|
857 |
+
"eval_f1": 0.9847512882532338,
|
858 |
+
"eval_loss": 0.07444457709789276,
|
859 |
+
"eval_precision": 0.983269163458173,
|
860 |
+
"eval_recall": 0.9862378879370874,
|
861 |
+
"eval_runtime": 4.2552,
|
862 |
+
"eval_samples_per_second": 455.676,
|
863 |
+
"eval_steps_per_second": 14.335,
|
864 |
+
"step": 2943
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 3.0071355759429155,
|
868 |
+
"grad_norm": 0.492354154586792,
|
869 |
+
"learning_rate": 1.3307657453556865e-05,
|
870 |
+
"loss": 0.0185,
|
871 |
+
"step": 2950
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 3.032619775739042,
|
875 |
+
"grad_norm": 0.17601044476032257,
|
876 |
+
"learning_rate": 1.3137743543271409e-05,
|
877 |
+
"loss": 0.0124,
|
878 |
+
"step": 2975
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 3.058103975535168,
|
882 |
+
"grad_norm": 0.3945290446281433,
|
883 |
+
"learning_rate": 1.2967829632985955e-05,
|
884 |
+
"loss": 0.0092,
|
885 |
+
"step": 3000
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 3.0835881753312946,
|
889 |
+
"grad_norm": 0.4073391258716583,
|
890 |
+
"learning_rate": 1.2797915722700499e-05,
|
891 |
+
"loss": 0.0073,
|
892 |
+
"step": 3025
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 3.109072375127421,
|
896 |
+
"grad_norm": 0.31910163164138794,
|
897 |
+
"learning_rate": 1.2628001812415044e-05,
|
898 |
+
"loss": 0.0102,
|
899 |
+
"step": 3050
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 3.1345565749235473,
|
903 |
+
"grad_norm": 0.15057243406772614,
|
904 |
+
"learning_rate": 1.2458087902129587e-05,
|
905 |
+
"loss": 0.0134,
|
906 |
+
"step": 3075
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 3.1600407747196737,
|
910 |
+
"grad_norm": 0.24187231063842773,
|
911 |
+
"learning_rate": 1.2288173991844132e-05,
|
912 |
+
"loss": 0.0128,
|
913 |
+
"step": 3100
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 3.1855249745158,
|
917 |
+
"grad_norm": 0.2588340640068054,
|
918 |
+
"learning_rate": 1.2118260081558678e-05,
|
919 |
+
"loss": 0.0083,
|
920 |
+
"step": 3125
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 3.2110091743119265,
|
924 |
+
"grad_norm": 0.2568691372871399,
|
925 |
+
"learning_rate": 1.1948346171273221e-05,
|
926 |
+
"loss": 0.0126,
|
927 |
+
"step": 3150
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 3.236493374108053,
|
931 |
+
"grad_norm": 0.17430084943771362,
|
932 |
+
"learning_rate": 1.1778432260987766e-05,
|
933 |
+
"loss": 0.0092,
|
934 |
+
"step": 3175
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 3.261977573904179,
|
938 |
+
"grad_norm": 0.8101614713668823,
|
939 |
+
"learning_rate": 1.1608518350702311e-05,
|
940 |
+
"loss": 0.0116,
|
941 |
+
"step": 3200
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 3.287461773700306,
|
945 |
+
"grad_norm": 0.5102636218070984,
|
946 |
+
"learning_rate": 1.1438604440416856e-05,
|
947 |
+
"loss": 0.0089,
|
948 |
+
"step": 3225
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 3.3129459734964324,
|
952 |
+
"grad_norm": 0.3798113763332367,
|
953 |
+
"learning_rate": 1.12686905301314e-05,
|
954 |
+
"loss": 0.02,
|
955 |
+
"step": 3250
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 3.3384301732925588,
|
959 |
+
"grad_norm": 0.09234433621168137,
|
960 |
+
"learning_rate": 1.1098776619845945e-05,
|
961 |
+
"loss": 0.0086,
|
962 |
+
"step": 3275
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 3.363914373088685,
|
966 |
+
"grad_norm": 0.2918802499771118,
|
967 |
+
"learning_rate": 1.092886270956049e-05,
|
968 |
+
"loss": 0.0114,
|
969 |
+
"step": 3300
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 3.3893985728848115,
|
973 |
+
"grad_norm": 1.4922930002212524,
|
974 |
+
"learning_rate": 1.0758948799275035e-05,
|
975 |
+
"loss": 0.0082,
|
976 |
+
"step": 3325
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 3.414882772680938,
|
980 |
+
"grad_norm": 0.1827608048915863,
|
981 |
+
"learning_rate": 1.0589034888989579e-05,
|
982 |
+
"loss": 0.0086,
|
983 |
+
"step": 3350
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 3.4403669724770642,
|
987 |
+
"grad_norm": 1.0763217210769653,
|
988 |
+
"learning_rate": 1.0419120978704124e-05,
|
989 |
+
"loss": 0.0091,
|
990 |
+
"step": 3375
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 3.4658511722731906,
|
994 |
+
"grad_norm": 0.6879101395606995,
|
995 |
+
"learning_rate": 1.0249207068418669e-05,
|
996 |
+
"loss": 0.0089,
|
997 |
+
"step": 3400
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 3.491335372069317,
|
1001 |
+
"grad_norm": 0.19432714581489563,
|
1002 |
+
"learning_rate": 1.0079293158133214e-05,
|
1003 |
+
"loss": 0.0116,
|
1004 |
+
"step": 3425
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 3.5168195718654434,
|
1008 |
+
"grad_norm": 1.8157362937927246,
|
1009 |
+
"learning_rate": 9.909379247847757e-06,
|
1010 |
+
"loss": 0.0098,
|
1011 |
+
"step": 3450
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 3.5423037716615697,
|
1015 |
+
"grad_norm": 1.372643232345581,
|
1016 |
+
"learning_rate": 9.739465337562302e-06,
|
1017 |
+
"loss": 0.0116,
|
1018 |
+
"step": 3475
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 3.567787971457696,
|
1022 |
+
"grad_norm": 0.549085259437561,
|
1023 |
+
"learning_rate": 9.569551427276846e-06,
|
1024 |
+
"loss": 0.0141,
|
1025 |
+
"step": 3500
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 3.5932721712538225,
|
1029 |
+
"grad_norm": 0.33806735277175903,
|
1030 |
+
"learning_rate": 9.399637516991391e-06,
|
1031 |
+
"loss": 0.0135,
|
1032 |
+
"step": 3525
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 3.6187563710499493,
|
1036 |
+
"grad_norm": 0.3857904374599457,
|
1037 |
+
"learning_rate": 9.229723606705936e-06,
|
1038 |
+
"loss": 0.0114,
|
1039 |
+
"step": 3550
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 3.6442405708460752,
|
1043 |
+
"grad_norm": 0.23262465000152588,
|
1044 |
+
"learning_rate": 9.05980969642048e-06,
|
1045 |
+
"loss": 0.0097,
|
1046 |
+
"step": 3575
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 3.669724770642202,
|
1050 |
+
"grad_norm": 0.26560139656066895,
|
1051 |
+
"learning_rate": 8.889895786135025e-06,
|
1052 |
+
"loss": 0.0099,
|
1053 |
+
"step": 3600
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 3.695208970438328,
|
1057 |
+
"grad_norm": 0.18409286439418793,
|
1058 |
+
"learning_rate": 8.71998187584957e-06,
|
1059 |
+
"loss": 0.0108,
|
1060 |
+
"step": 3625
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 3.720693170234455,
|
1064 |
+
"grad_norm": 0.47193974256515503,
|
1065 |
+
"learning_rate": 8.550067965564115e-06,
|
1066 |
+
"loss": 0.0118,
|
1067 |
+
"step": 3650
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 3.746177370030581,
|
1071 |
+
"grad_norm": 0.3622497022151947,
|
1072 |
+
"learning_rate": 8.380154055278658e-06,
|
1073 |
+
"loss": 0.0079,
|
1074 |
+
"step": 3675
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 3.7716615698267075,
|
1078 |
+
"grad_norm": 0.04132566228508949,
|
1079 |
+
"learning_rate": 8.210240144993203e-06,
|
1080 |
+
"loss": 0.0265,
|
1081 |
+
"step": 3700
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 3.797145769622834,
|
1085 |
+
"grad_norm": 0.27798858284950256,
|
1086 |
+
"learning_rate": 8.040326234707749e-06,
|
1087 |
+
"loss": 0.0077,
|
1088 |
+
"step": 3725
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 3.8226299694189603,
|
1092 |
+
"grad_norm": 0.34569182991981506,
|
1093 |
+
"learning_rate": 7.870412324422294e-06,
|
1094 |
+
"loss": 0.0135,
|
1095 |
+
"step": 3750
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 3.8481141692150866,
|
1099 |
+
"grad_norm": 0.2387148141860962,
|
1100 |
+
"learning_rate": 7.700498414136837e-06,
|
1101 |
+
"loss": 0.0086,
|
1102 |
+
"step": 3775
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 3.873598369011213,
|
1106 |
+
"grad_norm": 0.12353157252073288,
|
1107 |
+
"learning_rate": 7.530584503851381e-06,
|
1108 |
+
"loss": 0.0104,
|
1109 |
+
"step": 3800
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 3.8990825688073394,
|
1113 |
+
"grad_norm": 0.038017626851797104,
|
1114 |
+
"learning_rate": 7.3606705935659265e-06,
|
1115 |
+
"loss": 0.0173,
|
1116 |
+
"step": 3825
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 3.9245667686034658,
|
1120 |
+
"grad_norm": 4.909209251403809,
|
1121 |
+
"learning_rate": 7.190756683280472e-06,
|
1122 |
+
"loss": 0.0158,
|
1123 |
+
"step": 3850
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 3.950050968399592,
|
1127 |
+
"grad_norm": 0.4103800654411316,
|
1128 |
+
"learning_rate": 7.020842772995016e-06,
|
1129 |
+
"loss": 0.009,
|
1130 |
+
"step": 3875
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 3.9755351681957185,
|
1134 |
+
"grad_norm": 0.574148952960968,
|
1135 |
+
"learning_rate": 6.850928862709561e-06,
|
1136 |
+
"loss": 0.0122,
|
1137 |
+
"step": 3900
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 4.0,
|
1141 |
+
"eval_accuracy": 0.9861949007001629,
|
1142 |
+
"eval_f1": 0.9864320022438031,
|
1143 |
+
"eval_loss": 0.0650700181722641,
|
1144 |
+
"eval_precision": 0.985085078075765,
|
1145 |
+
"eval_recall": 0.9877826148012919,
|
1146 |
+
"eval_runtime": 4.3604,
|
1147 |
+
"eval_samples_per_second": 444.679,
|
1148 |
+
"eval_steps_per_second": 13.989,
|
1149 |
+
"step": 3924
|
1150 |
+
}
|
1151 |
+
],
|
1152 |
+
"logging_steps": 25,
|
1153 |
+
"max_steps": 4905,
|
1154 |
+
"num_input_tokens_seen": 0,
|
1155 |
+
"num_train_epochs": 5,
|
1156 |
+
"save_steps": 500,
|
1157 |
+
"stateful_callbacks": {
|
1158 |
+
"EarlyStoppingCallback": {
|
1159 |
+
"args": {
|
1160 |
+
"early_stopping_patience": 5,
|
1161 |
+
"early_stopping_threshold": 0.01
|
1162 |
+
},
|
1163 |
+
"attributes": {
|
1164 |
+
"early_stopping_patience_counter": 3
|
1165 |
+
}
|
1166 |
+
},
|
1167 |
+
"TrainerControl": {
|
1168 |
+
"args": {
|
1169 |
+
"should_epoch_stop": false,
|
1170 |
+
"should_evaluate": false,
|
1171 |
+
"should_log": false,
|
1172 |
+
"should_save": true,
|
1173 |
+
"should_training_stop": false
|
1174 |
+
},
|
1175 |
+
"attributes": {}
|
1176 |
+
}
|
1177 |
+
},
|
1178 |
+
"total_flos": 1.6407480366006272e+16,
|
1179 |
+
"train_batch_size": 8,
|
1180 |
+
"trial_name": null,
|
1181 |
+
"trial_params": null
|
1182 |
+
}
|
checkpoint-3924/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a31d23ca2e2a99f58016d2e424d562875ff01e471842eafc05e1e286875705c
|
3 |
+
size 5240
|
config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "NbAiLab/nb-bert-base",
|
3 |
+
"_num_labels": 17,
|
4 |
+
"architectures": [
|
5 |
+
"BertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "NOUN",
|
16 |
+
"1": "PUNCT",
|
17 |
+
"2": "ADP",
|
18 |
+
"3": "NUM",
|
19 |
+
"4": "SYM",
|
20 |
+
"5": "SCONJ",
|
21 |
+
"6": "ADJ",
|
22 |
+
"7": "PART",
|
23 |
+
"8": "DET",
|
24 |
+
"9": "CCONJ",
|
25 |
+
"10": "PROPN",
|
26 |
+
"11": "PRON",
|
27 |
+
"12": "X",
|
28 |
+
"13": "ADV",
|
29 |
+
"14": "INTJ",
|
30 |
+
"15": "VERB",
|
31 |
+
"16": "AUX"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 3072,
|
35 |
+
"label2id": {
|
36 |
+
"ADJ": 6,
|
37 |
+
"ADP": 2,
|
38 |
+
"ADV": 13,
|
39 |
+
"AUX": 16,
|
40 |
+
"CCONJ": 9,
|
41 |
+
"DET": 8,
|
42 |
+
"INTJ": 14,
|
43 |
+
"NOUN": 0,
|
44 |
+
"NUM": 3,
|
45 |
+
"PART": 7,
|
46 |
+
"PRON": 11,
|
47 |
+
"PROPN": 10,
|
48 |
+
"PUNCT": 1,
|
49 |
+
"SCONJ": 5,
|
50 |
+
"SYM": 4,
|
51 |
+
"VERB": 15,
|
52 |
+
"X": 12
|
53 |
+
},
|
54 |
+
"layer_norm_eps": 1e-12,
|
55 |
+
"max_position_embeddings": 512,
|
56 |
+
"model_type": "bert",
|
57 |
+
"num_attention_heads": 12,
|
58 |
+
"num_hidden_layers": 12,
|
59 |
+
"pad_token_id": 0,
|
60 |
+
"pooler_fc_size": 768,
|
61 |
+
"pooler_num_attention_heads": 12,
|
62 |
+
"pooler_num_fc_layers": 3,
|
63 |
+
"pooler_size_per_head": 128,
|
64 |
+
"pooler_type": "first_token_transform",
|
65 |
+
"position_embedding_type": "absolute",
|
66 |
+
"torch_dtype": "float32",
|
67 |
+
"transformers_version": "4.45.0",
|
68 |
+
"type_vocab_size": 2,
|
69 |
+
"use_cache": true,
|
70 |
+
"vocab_size": 119547
|
71 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fec2dddda2f2863c9860b68f2970f8f9e441f254d3b38692add9e30738f6230a
|
3 |
+
size 709127044
|
runs/Nov05_18-51-38_ficino/events.out.tfevents.1730829100.ficino.3820667.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:666df6f1b6752efc6f92ef996d44cd6ab945332f333b9eaafba81033852f02cf
|
3 |
+
size 49775
|
runs/Nov05_18-51-38_ficino/events.out.tfevents.1730830078.ficino.3820667.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b59cfa4ea1d9f26682ad6cb332462745cf03782e8fab45430b1958399814bb64
|
3 |
+
size 560
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a31d23ca2e2a99f58016d2e424d562875ff01e471842eafc05e1e286875705c
|
3 |
+
size 5240
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "ltgoslo/norne",
|
3 |
+
"model": "NbAiLab/nb-bert-base",
|
4 |
+
"lr": 3e-05,
|
5 |
+
"epochs": 5,
|
6 |
+
"max_seq_length": 512,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "bokmaal:train",
|
16 |
+
"valid_split": "bokmaal:test",
|
17 |
+
"tokens_column": "tokens",
|
18 |
+
"tags_column": "pos_tags",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "nb-bert-base-pos-ltgnorne-lr3e-5-e5",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "versae",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|