Upload folder using huggingface_hub
Browse files- README.md +39 -0
- checkpoint-8398/config.json +79 -0
- checkpoint-8398/model.safetensors +3 -0
- checkpoint-8398/optimizer.pt +3 -0
- checkpoint-8398/rng_state.pth +3 -0
- checkpoint-8398/scheduler.pt +3 -0
- checkpoint-8398/trainer_state.json +2423 -0
- checkpoint-8398/training_args.bin +3 -0
- config.json +79 -0
- model.safetensors +3 -0
- runs/Mar08_21-48-47_umit-MS-7E07/events.out.tfevents.1741459728.umit-MS-7E07.5173.0 +2 -2
- runs/Mar08_21-48-47_umit-MS-7E07/events.out.tfevents.1741463362.umit-MS-7E07.5173.1 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +945 -0
- training_args.bin +3 -0
- training_params.json +30 -0
README.md
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- autotrain
|
6 |
+
- text-classification
|
7 |
+
base_model: answerdotai/ModernBERT-large
|
8 |
+
widget:
|
9 |
+
- text: "I love AutoTrain"
|
10 |
+
datasets:
|
11 |
+
- uisikdag/42news
|
12 |
+
---
|
13 |
+
|
14 |
+
# Model Trained Using AutoTrain
|
15 |
+
|
16 |
+
- Problem type: Text Classification
|
17 |
+
|
18 |
+
## Validation Metrics
|
19 |
+
loss: 1.0703290700912476
|
20 |
+
|
21 |
+
f1_macro: 0.5315462561949883
|
22 |
+
|
23 |
+
f1_micro: 0.6112102820421278
|
24 |
+
|
25 |
+
f1_weighted: 0.6025346871719214
|
26 |
+
|
27 |
+
precision_macro: 0.6157278778731476
|
28 |
+
|
29 |
+
precision_micro: 0.6112102820421278
|
30 |
+
|
31 |
+
precision_weighted: 0.635344882882464
|
32 |
+
|
33 |
+
recall_macro: 0.5271202118810513
|
34 |
+
|
35 |
+
recall_micro: 0.6112102820421278
|
36 |
+
|
37 |
+
recall_weighted: 0.6112102820421278
|
38 |
+
|
39 |
+
accuracy: 0.6112102820421278
|
checkpoint-8398/config.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "answerdotai/ModernBERT-large",
|
3 |
+
"_num_labels": 13,
|
4 |
+
"architectures": [
|
5 |
+
"ModernBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_bias": false,
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 50281,
|
10 |
+
"classifier_activation": "gelu",
|
11 |
+
"classifier_bias": false,
|
12 |
+
"classifier_dropout": 0.0,
|
13 |
+
"classifier_pooling": "mean",
|
14 |
+
"cls_token_id": 50281,
|
15 |
+
"decoder_bias": true,
|
16 |
+
"deterministic_flash_attn": false,
|
17 |
+
"embedding_dropout": 0.0,
|
18 |
+
"eos_token_id": 50282,
|
19 |
+
"global_attn_every_n_layers": 3,
|
20 |
+
"global_rope_theta": 160000.0,
|
21 |
+
"gradient_checkpointing": false,
|
22 |
+
"hidden_activation": "gelu",
|
23 |
+
"hidden_size": 1024,
|
24 |
+
"id2label": {
|
25 |
+
"0": "dunya",
|
26 |
+
"1": "ekonomi",
|
27 |
+
"2": "genel",
|
28 |
+
"3": "guncel",
|
29 |
+
"4": "kultur-sanat",
|
30 |
+
"5": "magazin",
|
31 |
+
"6": "planet",
|
32 |
+
"7": "saglik",
|
33 |
+
"8": "siyaset",
|
34 |
+
"9": "spor",
|
35 |
+
"10": "teknoloji",
|
36 |
+
"11": "turkiye",
|
37 |
+
"12": "yasam"
|
38 |
+
},
|
39 |
+
"initializer_cutoff_factor": 2.0,
|
40 |
+
"initializer_range": 0.02,
|
41 |
+
"intermediate_size": 2624,
|
42 |
+
"label2id": {
|
43 |
+
"dunya": 0,
|
44 |
+
"ekonomi": 1,
|
45 |
+
"genel": 2,
|
46 |
+
"guncel": 3,
|
47 |
+
"kultur-sanat": 4,
|
48 |
+
"magazin": 5,
|
49 |
+
"planet": 6,
|
50 |
+
"saglik": 7,
|
51 |
+
"siyaset": 8,
|
52 |
+
"spor": 9,
|
53 |
+
"teknoloji": 10,
|
54 |
+
"turkiye": 11,
|
55 |
+
"yasam": 12
|
56 |
+
},
|
57 |
+
"layer_norm_eps": 1e-05,
|
58 |
+
"local_attention": 128,
|
59 |
+
"local_rope_theta": 10000.0,
|
60 |
+
"max_position_embeddings": 8192,
|
61 |
+
"mlp_bias": false,
|
62 |
+
"mlp_dropout": 0.0,
|
63 |
+
"model_type": "modernbert",
|
64 |
+
"norm_bias": false,
|
65 |
+
"norm_eps": 1e-05,
|
66 |
+
"num_attention_heads": 16,
|
67 |
+
"num_hidden_layers": 28,
|
68 |
+
"pad_token_id": 50283,
|
69 |
+
"position_embedding_type": "absolute",
|
70 |
+
"problem_type": "single_label_classification",
|
71 |
+
"reference_compile": true,
|
72 |
+
"repad_logits_with_grad": false,
|
73 |
+
"sep_token_id": 50282,
|
74 |
+
"sparse_pred_ignore_index": -100,
|
75 |
+
"sparse_prediction": false,
|
76 |
+
"torch_dtype": "float32",
|
77 |
+
"transformers_version": "4.48.0",
|
78 |
+
"vocab_size": 50368
|
79 |
+
}
|
checkpoint-8398/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b75e3dd58b60ccea590aaa484c65e1584092399c75cb03d73d08cc771b5b9a22
|
3 |
+
size 1583396740
|
checkpoint-8398/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6df8d41534a9aee8cdb9a1d9c24ff3a8a8fc3bccabce88b77a0a23c1fdf9b975
|
3 |
+
size 3166903290
|
checkpoint-8398/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f37c40ce327861a7ca13b719d3aa37510a143368b6e74358bdb14becb3899e1e
|
3 |
+
size 14244
|
checkpoint-8398/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89d9ae34a0bc30130c48a9abe4b837d614c8c8d2abda68571fb298759f6810c4
|
3 |
+
size 1064
|
checkpoint-8398/trainer_state.json
ADDED
@@ -0,0 +1,2423 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.0703290700912476,
|
3 |
+
"best_model_checkpoint": "autotrain-modernBERT-large/checkpoint-8398",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 8398,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.005953798523457966,
|
13 |
+
"grad_norm": 86.369140625,
|
14 |
+
"learning_rate": 2.7387473207906647e-07,
|
15 |
+
"loss": 2.6586,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.011907597046915932,
|
20 |
+
"grad_norm": 20.970399856567383,
|
21 |
+
"learning_rate": 5.715646582519647e-07,
|
22 |
+
"loss": 2.41,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0178613955703739,
|
27 |
+
"grad_norm": 24.44964599609375,
|
28 |
+
"learning_rate": 8.573469873779472e-07,
|
29 |
+
"loss": 2.3485,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.023815194093831864,
|
34 |
+
"grad_norm": 27.326494216918945,
|
35 |
+
"learning_rate": 1.1550369135508456e-06,
|
36 |
+
"loss": 2.3665,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.02976899261728983,
|
41 |
+
"grad_norm": 26.42802619934082,
|
42 |
+
"learning_rate": 1.4527268397237438e-06,
|
43 |
+
"loss": 2.3727,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.0357227911407478,
|
48 |
+
"grad_norm": 21.59549903869629,
|
49 |
+
"learning_rate": 1.7504167658966421e-06,
|
50 |
+
"loss": 2.3285,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.04167658966420576,
|
55 |
+
"grad_norm": 20.33954620361328,
|
56 |
+
"learning_rate": 2.0481066920695406e-06,
|
57 |
+
"loss": 2.2651,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.04763038818766373,
|
62 |
+
"grad_norm": 18.53624153137207,
|
63 |
+
"learning_rate": 2.345796618242439e-06,
|
64 |
+
"loss": 2.294,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.053584186711121695,
|
69 |
+
"grad_norm": 18.521059036254883,
|
70 |
+
"learning_rate": 2.643486544415337e-06,
|
71 |
+
"loss": 2.244,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.05953798523457966,
|
76 |
+
"grad_norm": 22.079322814941406,
|
77 |
+
"learning_rate": 2.9411764705882355e-06,
|
78 |
+
"loss": 2.2435,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.06549178375803763,
|
83 |
+
"grad_norm": 14.750000953674316,
|
84 |
+
"learning_rate": 3.2388663967611337e-06,
|
85 |
+
"loss": 2.2774,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.0714455822814956,
|
90 |
+
"grad_norm": 18.668041229248047,
|
91 |
+
"learning_rate": 3.536556322934032e-06,
|
92 |
+
"loss": 2.1298,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.07739938080495357,
|
97 |
+
"grad_norm": 33.25010681152344,
|
98 |
+
"learning_rate": 3.83424624910693e-06,
|
99 |
+
"loss": 2.1615,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.08335317932841152,
|
104 |
+
"grad_norm": 120.11493682861328,
|
105 |
+
"learning_rate": 4.120028578232913e-06,
|
106 |
+
"loss": 2.3505,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.08930697785186949,
|
111 |
+
"grad_norm": 33.988765716552734,
|
112 |
+
"learning_rate": 4.417718504405811e-06,
|
113 |
+
"loss": 2.1311,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.09526077637532746,
|
118 |
+
"grad_norm": 21.629106521606445,
|
119 |
+
"learning_rate": 4.715408430578709e-06,
|
120 |
+
"loss": 2.0927,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.10121457489878542,
|
125 |
+
"grad_norm": 25.016613006591797,
|
126 |
+
"learning_rate": 5.013098356751608e-06,
|
127 |
+
"loss": 2.0797,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.10716837342224339,
|
132 |
+
"grad_norm": 18.86359214782715,
|
133 |
+
"learning_rate": 5.310788282924506e-06,
|
134 |
+
"loss": 1.9078,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.11312217194570136,
|
139 |
+
"grad_norm": 54.194664001464844,
|
140 |
+
"learning_rate": 5.608478209097404e-06,
|
141 |
+
"loss": 2.2279,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.11907597046915933,
|
146 |
+
"grad_norm": 37.876121520996094,
|
147 |
+
"learning_rate": 5.906168135270303e-06,
|
148 |
+
"loss": 2.1245,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.12502976899261728,
|
153 |
+
"grad_norm": 14.532075881958008,
|
154 |
+
"learning_rate": 6.203858061443201e-06,
|
155 |
+
"loss": 1.9028,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.13098356751607526,
|
160 |
+
"grad_norm": 16.258657455444336,
|
161 |
+
"learning_rate": 6.5015479876161e-06,
|
162 |
+
"loss": 2.0243,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.13693736603953321,
|
167 |
+
"grad_norm": 108.40977478027344,
|
168 |
+
"learning_rate": 6.7992379137889975e-06,
|
169 |
+
"loss": 2.0887,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.1428911645629912,
|
174 |
+
"grad_norm": 21.468217849731445,
|
175 |
+
"learning_rate": 7.096927839961896e-06,
|
176 |
+
"loss": 1.957,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.14884496308644915,
|
181 |
+
"grad_norm": 22.000276565551758,
|
182 |
+
"learning_rate": 7.394617766134794e-06,
|
183 |
+
"loss": 1.9793,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.15479876160990713,
|
188 |
+
"grad_norm": 35.44562530517578,
|
189 |
+
"learning_rate": 7.692307692307694e-06,
|
190 |
+
"loss": 1.8144,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.16075256013336509,
|
195 |
+
"grad_norm": 12.766996383666992,
|
196 |
+
"learning_rate": 7.989997618480591e-06,
|
197 |
+
"loss": 1.9096,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.16670635865682304,
|
202 |
+
"grad_norm": 15.658439636230469,
|
203 |
+
"learning_rate": 8.28768754465349e-06,
|
204 |
+
"loss": 1.9173,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.17266015718028102,
|
209 |
+
"grad_norm": 20.358219146728516,
|
210 |
+
"learning_rate": 8.585377470826387e-06,
|
211 |
+
"loss": 1.9496,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.17861395570373897,
|
216 |
+
"grad_norm": 80.19808959960938,
|
217 |
+
"learning_rate": 8.883067396999285e-06,
|
218 |
+
"loss": 1.976,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.18456775422719696,
|
223 |
+
"grad_norm": 17.19704818725586,
|
224 |
+
"learning_rate": 9.180757323172185e-06,
|
225 |
+
"loss": 1.9514,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.1905215527506549,
|
230 |
+
"grad_norm": 12.535808563232422,
|
231 |
+
"learning_rate": 9.478447249345082e-06,
|
232 |
+
"loss": 1.9032,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.1964753512741129,
|
237 |
+
"grad_norm": 10.427902221679688,
|
238 |
+
"learning_rate": 9.776137175517982e-06,
|
239 |
+
"loss": 1.8516,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.20242914979757085,
|
244 |
+
"grad_norm": 12.50812816619873,
|
245 |
+
"learning_rate": 1.0073827101690878e-05,
|
246 |
+
"loss": 1.8606,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.20838294832102883,
|
251 |
+
"grad_norm": 14.580496788024902,
|
252 |
+
"learning_rate": 1.0371517027863778e-05,
|
253 |
+
"loss": 1.8315,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.21433674684448678,
|
258 |
+
"grad_norm": 11.818653106689453,
|
259 |
+
"learning_rate": 1.0669206954036676e-05,
|
260 |
+
"loss": 1.8991,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.22029054536794476,
|
265 |
+
"grad_norm": 8.989337921142578,
|
266 |
+
"learning_rate": 1.095498928316266e-05,
|
267 |
+
"loss": 1.9776,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.22624434389140272,
|
272 |
+
"grad_norm": 20.0020809173584,
|
273 |
+
"learning_rate": 1.1252679209335557e-05,
|
274 |
+
"loss": 1.7,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.23219814241486067,
|
279 |
+
"grad_norm": 12.898697853088379,
|
280 |
+
"learning_rate": 1.1550369135508455e-05,
|
281 |
+
"loss": 1.7779,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.23815194093831865,
|
286 |
+
"grad_norm": 66.27762603759766,
|
287 |
+
"learning_rate": 1.1848059061681353e-05,
|
288 |
+
"loss": 1.6585,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.2441057394617766,
|
293 |
+
"grad_norm": 23.931554794311523,
|
294 |
+
"learning_rate": 1.2145748987854251e-05,
|
295 |
+
"loss": 1.9537,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.25005953798523456,
|
300 |
+
"grad_norm": 9.655719757080078,
|
301 |
+
"learning_rate": 1.244343891402715e-05,
|
302 |
+
"loss": 1.6686,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.25601333650869257,
|
307 |
+
"grad_norm": 22.155933380126953,
|
308 |
+
"learning_rate": 1.2741128840200048e-05,
|
309 |
+
"loss": 1.6213,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.2619671350321505,
|
314 |
+
"grad_norm": 14.825516700744629,
|
315 |
+
"learning_rate": 1.3038818766372946e-05,
|
316 |
+
"loss": 1.5839,
|
317 |
+
"step": 1100
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.2679209335556085,
|
321 |
+
"grad_norm": 14.32667350769043,
|
322 |
+
"learning_rate": 1.3336508692545846e-05,
|
323 |
+
"loss": 1.5199,
|
324 |
+
"step": 1125
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.27387473207906643,
|
328 |
+
"grad_norm": 26.93867301940918,
|
329 |
+
"learning_rate": 1.3634198618718744e-05,
|
330 |
+
"loss": 1.5073,
|
331 |
+
"step": 1150
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.2798285306025244,
|
335 |
+
"grad_norm": 14.591392517089844,
|
336 |
+
"learning_rate": 1.3931888544891641e-05,
|
337 |
+
"loss": 1.5835,
|
338 |
+
"step": 1175
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.2857823291259824,
|
342 |
+
"grad_norm": 15.677992820739746,
|
343 |
+
"learning_rate": 1.422957847106454e-05,
|
344 |
+
"loss": 1.4797,
|
345 |
+
"step": 1200
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.29173612764944035,
|
349 |
+
"grad_norm": 27.357168197631836,
|
350 |
+
"learning_rate": 1.4527268397237437e-05,
|
351 |
+
"loss": 1.6069,
|
352 |
+
"step": 1225
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.2976899261728983,
|
356 |
+
"grad_norm": 13.1478271484375,
|
357 |
+
"learning_rate": 1.4824958323410337e-05,
|
358 |
+
"loss": 1.5262,
|
359 |
+
"step": 1250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.30364372469635625,
|
363 |
+
"grad_norm": 30.049888610839844,
|
364 |
+
"learning_rate": 1.5122648249583235e-05,
|
365 |
+
"loss": 1.4262,
|
366 |
+
"step": 1275
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.30959752321981426,
|
370 |
+
"grad_norm": 16.124225616455078,
|
371 |
+
"learning_rate": 1.5420338175756134e-05,
|
372 |
+
"loss": 1.4468,
|
373 |
+
"step": 1300
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.3155513217432722,
|
377 |
+
"grad_norm": 7.2687201499938965,
|
378 |
+
"learning_rate": 1.5718028101929032e-05,
|
379 |
+
"loss": 1.4336,
|
380 |
+
"step": 1325
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.32150512026673017,
|
384 |
+
"grad_norm": 13.536001205444336,
|
385 |
+
"learning_rate": 1.601571802810193e-05,
|
386 |
+
"loss": 1.538,
|
387 |
+
"step": 1350
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.3274589187901881,
|
391 |
+
"grad_norm": 12.899219512939453,
|
392 |
+
"learning_rate": 1.6313407954274828e-05,
|
393 |
+
"loss": 1.4305,
|
394 |
+
"step": 1375
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.3334127173136461,
|
398 |
+
"grad_norm": 10.809173583984375,
|
399 |
+
"learning_rate": 1.6611097880447726e-05,
|
400 |
+
"loss": 1.4204,
|
401 |
+
"step": 1400
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.3393665158371041,
|
405 |
+
"grad_norm": 24.460115432739258,
|
406 |
+
"learning_rate": 1.6908787806620623e-05,
|
407 |
+
"loss": 1.4973,
|
408 |
+
"step": 1425
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.34532031436056204,
|
412 |
+
"grad_norm": 11.75060749053955,
|
413 |
+
"learning_rate": 1.720647773279352e-05,
|
414 |
+
"loss": 1.4842,
|
415 |
+
"step": 1450
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.35127411288402,
|
419 |
+
"grad_norm": 10.996878623962402,
|
420 |
+
"learning_rate": 1.7504167658966422e-05,
|
421 |
+
"loss": 1.5807,
|
422 |
+
"step": 1475
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.35722791140747795,
|
426 |
+
"grad_norm": 7.269287109375,
|
427 |
+
"learning_rate": 1.780185758513932e-05,
|
428 |
+
"loss": 1.5171,
|
429 |
+
"step": 1500
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.36318170993093596,
|
433 |
+
"grad_norm": 68.14170837402344,
|
434 |
+
"learning_rate": 1.8099547511312218e-05,
|
435 |
+
"loss": 1.3387,
|
436 |
+
"step": 1525
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.3691355084543939,
|
440 |
+
"grad_norm": 11.084012985229492,
|
441 |
+
"learning_rate": 1.8397237437485116e-05,
|
442 |
+
"loss": 1.4908,
|
443 |
+
"step": 1550
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.37508930697785187,
|
447 |
+
"grad_norm": 20.108646392822266,
|
448 |
+
"learning_rate": 1.8694927363658017e-05,
|
449 |
+
"loss": 1.3158,
|
450 |
+
"step": 1575
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.3810431055013098,
|
454 |
+
"grad_norm": 11.305046081542969,
|
455 |
+
"learning_rate": 1.8992617289830915e-05,
|
456 |
+
"loss": 1.3865,
|
457 |
+
"step": 1600
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.38699690402476783,
|
461 |
+
"grad_norm": 15.740647315979004,
|
462 |
+
"learning_rate": 1.929030721600381e-05,
|
463 |
+
"loss": 1.4981,
|
464 |
+
"step": 1625
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.3929507025482258,
|
468 |
+
"grad_norm": 16.77447509765625,
|
469 |
+
"learning_rate": 1.9587997142176708e-05,
|
470 |
+
"loss": 1.286,
|
471 |
+
"step": 1650
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.39890450107168374,
|
475 |
+
"grad_norm": 21.543420791625977,
|
476 |
+
"learning_rate": 1.988568706834961e-05,
|
477 |
+
"loss": 1.4452,
|
478 |
+
"step": 1675
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.4048582995951417,
|
482 |
+
"grad_norm": 12.779708862304688,
|
483 |
+
"learning_rate": 2.0183376994522507e-05,
|
484 |
+
"loss": 1.3408,
|
485 |
+
"step": 1700
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.41081209811859964,
|
489 |
+
"grad_norm": 10.406266212463379,
|
490 |
+
"learning_rate": 2.0481066920695404e-05,
|
491 |
+
"loss": 1.3697,
|
492 |
+
"step": 1725
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.41676589664205765,
|
496 |
+
"grad_norm": 5.458737850189209,
|
497 |
+
"learning_rate": 2.0778756846868302e-05,
|
498 |
+
"loss": 1.337,
|
499 |
+
"step": 1750
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.4227196951655156,
|
503 |
+
"grad_norm": 14.178915023803711,
|
504 |
+
"learning_rate": 2.10764467730412e-05,
|
505 |
+
"loss": 1.4753,
|
506 |
+
"step": 1775
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.42867349368897356,
|
510 |
+
"grad_norm": 9.677695274353027,
|
511 |
+
"learning_rate": 2.13741366992141e-05,
|
512 |
+
"loss": 1.3992,
|
513 |
+
"step": 1800
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.4346272922124315,
|
517 |
+
"grad_norm": 13.21867847442627,
|
518 |
+
"learning_rate": 2.1671826625387e-05,
|
519 |
+
"loss": 1.4931,
|
520 |
+
"step": 1825
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.4405810907358895,
|
524 |
+
"grad_norm": 14.22286319732666,
|
525 |
+
"learning_rate": 2.1969516551559897e-05,
|
526 |
+
"loss": 1.3421,
|
527 |
+
"step": 1850
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.4465348892593475,
|
531 |
+
"grad_norm": 9.203393936157227,
|
532 |
+
"learning_rate": 2.2267206477732795e-05,
|
533 |
+
"loss": 1.5444,
|
534 |
+
"step": 1875
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.45248868778280543,
|
538 |
+
"grad_norm": 11.072060585021973,
|
539 |
+
"learning_rate": 2.2564896403905693e-05,
|
540 |
+
"loss": 1.2771,
|
541 |
+
"step": 1900
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.4584424863062634,
|
545 |
+
"grad_norm": 16.251949310302734,
|
546 |
+
"learning_rate": 2.286258633007859e-05,
|
547 |
+
"loss": 1.3691,
|
548 |
+
"step": 1925
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.46439628482972134,
|
552 |
+
"grad_norm": 13.69911003112793,
|
553 |
+
"learning_rate": 2.316027625625149e-05,
|
554 |
+
"loss": 1.4421,
|
555 |
+
"step": 1950
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.47035008335317935,
|
559 |
+
"grad_norm": 13.465357780456543,
|
560 |
+
"learning_rate": 2.3457966182424386e-05,
|
561 |
+
"loss": 1.3384,
|
562 |
+
"step": 1975
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.4763038818766373,
|
566 |
+
"grad_norm": 10.023835182189941,
|
567 |
+
"learning_rate": 2.3755656108597284e-05,
|
568 |
+
"loss": 1.4222,
|
569 |
+
"step": 2000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.48225768040009526,
|
573 |
+
"grad_norm": 13.331511497497559,
|
574 |
+
"learning_rate": 2.4053346034770186e-05,
|
575 |
+
"loss": 1.3014,
|
576 |
+
"step": 2025
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.4882114789235532,
|
580 |
+
"grad_norm": 20.458698272705078,
|
581 |
+
"learning_rate": 2.4351035960943083e-05,
|
582 |
+
"loss": 1.2347,
|
583 |
+
"step": 2050
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.4941652774470112,
|
587 |
+
"grad_norm": 20.585613250732422,
|
588 |
+
"learning_rate": 2.464872588711598e-05,
|
589 |
+
"loss": 1.3323,
|
590 |
+
"step": 2075
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.5001190759704691,
|
594 |
+
"grad_norm": 11.395628929138184,
|
595 |
+
"learning_rate": 2.494641581328888e-05,
|
596 |
+
"loss": 1.3655,
|
597 |
+
"step": 2100
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.5060728744939271,
|
601 |
+
"grad_norm": 12.15377426147461,
|
602 |
+
"learning_rate": 2.5244105739461777e-05,
|
603 |
+
"loss": 1.379,
|
604 |
+
"step": 2125
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.5120266730173851,
|
608 |
+
"grad_norm": 8.270852088928223,
|
609 |
+
"learning_rate": 2.5541795665634678e-05,
|
610 |
+
"loss": 1.2554,
|
611 |
+
"step": 2150
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.517980471540843,
|
615 |
+
"grad_norm": 10.243392944335938,
|
616 |
+
"learning_rate": 2.5839485591807573e-05,
|
617 |
+
"loss": 1.3906,
|
618 |
+
"step": 2175
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.523934270064301,
|
622 |
+
"grad_norm": 8.929010391235352,
|
623 |
+
"learning_rate": 2.6137175517980474e-05,
|
624 |
+
"loss": 1.1221,
|
625 |
+
"step": 2200
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.5298880685877589,
|
629 |
+
"grad_norm": 10.393013000488281,
|
630 |
+
"learning_rate": 2.6434865444153372e-05,
|
631 |
+
"loss": 1.1051,
|
632 |
+
"step": 2225
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.535841867111217,
|
636 |
+
"grad_norm": 8.302331924438477,
|
637 |
+
"learning_rate": 2.6732555370326266e-05,
|
638 |
+
"loss": 1.1744,
|
639 |
+
"step": 2250
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.541795665634675,
|
643 |
+
"grad_norm": 10.062777519226074,
|
644 |
+
"learning_rate": 2.7030245296499168e-05,
|
645 |
+
"loss": 1.3811,
|
646 |
+
"step": 2275
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.5477494641581329,
|
650 |
+
"grad_norm": 7.108260154724121,
|
651 |
+
"learning_rate": 2.732793522267207e-05,
|
652 |
+
"loss": 1.379,
|
653 |
+
"step": 2300
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.5537032626815909,
|
657 |
+
"grad_norm": 9.144970893859863,
|
658 |
+
"learning_rate": 2.7625625148844963e-05,
|
659 |
+
"loss": 1.3468,
|
660 |
+
"step": 2325
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.5596570612050488,
|
664 |
+
"grad_norm": 15.900981903076172,
|
665 |
+
"learning_rate": 2.7923315075017864e-05,
|
666 |
+
"loss": 1.2959,
|
667 |
+
"step": 2350
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.5656108597285068,
|
671 |
+
"grad_norm": 8.684926986694336,
|
672 |
+
"learning_rate": 2.822100500119076e-05,
|
673 |
+
"loss": 1.3474,
|
674 |
+
"step": 2375
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.5715646582519648,
|
678 |
+
"grad_norm": 10.27397346496582,
|
679 |
+
"learning_rate": 2.851869492736366e-05,
|
680 |
+
"loss": 1.41,
|
681 |
+
"step": 2400
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.5775184567754227,
|
685 |
+
"grad_norm": 1371.0750732421875,
|
686 |
+
"learning_rate": 2.881638485353656e-05,
|
687 |
+
"loss": 1.3659,
|
688 |
+
"step": 2425
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.5834722552988807,
|
692 |
+
"grad_norm": 24.350120544433594,
|
693 |
+
"learning_rate": 2.9114074779709456e-05,
|
694 |
+
"loss": 1.6975,
|
695 |
+
"step": 2450
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.5894260538223387,
|
699 |
+
"grad_norm": 8.823434829711914,
|
700 |
+
"learning_rate": 2.9411764705882354e-05,
|
701 |
+
"loss": 1.2569,
|
702 |
+
"step": 2475
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.5953798523457966,
|
706 |
+
"grad_norm": 10.762280464172363,
|
707 |
+
"learning_rate": 2.970945463205525e-05,
|
708 |
+
"loss": 1.3872,
|
709 |
+
"step": 2500
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.6013336508692546,
|
713 |
+
"grad_norm": 9.566682815551758,
|
714 |
+
"learning_rate": 3.000714455822815e-05,
|
715 |
+
"loss": 1.2105,
|
716 |
+
"step": 2525
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.6072874493927125,
|
720 |
+
"grad_norm": 9.695130348205566,
|
721 |
+
"learning_rate": 3.030483448440105e-05,
|
722 |
+
"loss": 1.3432,
|
723 |
+
"step": 2550
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.6132412479161705,
|
727 |
+
"grad_norm": 9.360527992248535,
|
728 |
+
"learning_rate": 3.060252441057395e-05,
|
729 |
+
"loss": 1.3176,
|
730 |
+
"step": 2575
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.6191950464396285,
|
734 |
+
"grad_norm": 8.286338806152344,
|
735 |
+
"learning_rate": 3.090021433674685e-05,
|
736 |
+
"loss": 1.116,
|
737 |
+
"step": 2600
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.6251488449630864,
|
741 |
+
"grad_norm": 12.3185453414917,
|
742 |
+
"learning_rate": 3.1197904262919744e-05,
|
743 |
+
"loss": 1.365,
|
744 |
+
"step": 2625
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.6311026434865444,
|
748 |
+
"grad_norm": 9.384039878845215,
|
749 |
+
"learning_rate": 3.149559418909264e-05,
|
750 |
+
"loss": 1.4109,
|
751 |
+
"step": 2650
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.6370564420100023,
|
755 |
+
"grad_norm": 5.262876033782959,
|
756 |
+
"learning_rate": 3.179328411526554e-05,
|
757 |
+
"loss": 1.2308,
|
758 |
+
"step": 2675
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.6430102405334603,
|
762 |
+
"grad_norm": 36.93815612792969,
|
763 |
+
"learning_rate": 3.2090974041438434e-05,
|
764 |
+
"loss": 1.3553,
|
765 |
+
"step": 2700
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.6489640390569184,
|
769 |
+
"grad_norm": 13.990893363952637,
|
770 |
+
"learning_rate": 3.2388663967611336e-05,
|
771 |
+
"loss": 1.236,
|
772 |
+
"step": 2725
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.6549178375803762,
|
776 |
+
"grad_norm": 8.869446754455566,
|
777 |
+
"learning_rate": 3.268635389378424e-05,
|
778 |
+
"loss": 1.3907,
|
779 |
+
"step": 2750
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.6608716361038343,
|
783 |
+
"grad_norm": 17.166791915893555,
|
784 |
+
"learning_rate": 3.298404381995713e-05,
|
785 |
+
"loss": 1.2713,
|
786 |
+
"step": 2775
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.6668254346272922,
|
790 |
+
"grad_norm": 12.74843978881836,
|
791 |
+
"learning_rate": 3.328173374613003e-05,
|
792 |
+
"loss": 1.3094,
|
793 |
+
"step": 2800
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.6727792331507502,
|
797 |
+
"grad_norm": 7.5820512771606445,
|
798 |
+
"learning_rate": 3.357942367230293e-05,
|
799 |
+
"loss": 1.0775,
|
800 |
+
"step": 2825
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.6787330316742082,
|
804 |
+
"grad_norm": 15.891313552856445,
|
805 |
+
"learning_rate": 3.387711359847583e-05,
|
806 |
+
"loss": 1.3757,
|
807 |
+
"step": 2850
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.6846868301976661,
|
811 |
+
"grad_norm": 11.398141860961914,
|
812 |
+
"learning_rate": 3.417480352464873e-05,
|
813 |
+
"loss": 1.2442,
|
814 |
+
"step": 2875
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.6906406287211241,
|
818 |
+
"grad_norm": 61.32708740234375,
|
819 |
+
"learning_rate": 3.4472493450821624e-05,
|
820 |
+
"loss": 1.1729,
|
821 |
+
"step": 2900
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.6965944272445821,
|
825 |
+
"grad_norm": 28.35745620727539,
|
826 |
+
"learning_rate": 3.4770183376994525e-05,
|
827 |
+
"loss": 1.337,
|
828 |
+
"step": 2925
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.70254822576804,
|
832 |
+
"grad_norm": 7.083935260772705,
|
833 |
+
"learning_rate": 3.506787330316742e-05,
|
834 |
+
"loss": 1.1934,
|
835 |
+
"step": 2950
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.708502024291498,
|
839 |
+
"grad_norm": 7.402154445648193,
|
840 |
+
"learning_rate": 3.536556322934032e-05,
|
841 |
+
"loss": 1.2614,
|
842 |
+
"step": 2975
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.7144558228149559,
|
846 |
+
"grad_norm": 56.07618713378906,
|
847 |
+
"learning_rate": 3.566325315551322e-05,
|
848 |
+
"loss": 1.1574,
|
849 |
+
"step": 3000
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.7204096213384139,
|
853 |
+
"grad_norm": 6.627118110656738,
|
854 |
+
"learning_rate": 3.596094308168612e-05,
|
855 |
+
"loss": 1.3132,
|
856 |
+
"step": 3025
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.7263634198618719,
|
860 |
+
"grad_norm": 10.03258228302002,
|
861 |
+
"learning_rate": 3.625863300785902e-05,
|
862 |
+
"loss": 1.268,
|
863 |
+
"step": 3050
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.7323172183853298,
|
867 |
+
"grad_norm": 10.155272483825684,
|
868 |
+
"learning_rate": 3.655632293403192e-05,
|
869 |
+
"loss": 1.2333,
|
870 |
+
"step": 3075
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.7382710169087878,
|
874 |
+
"grad_norm": 15.690239906311035,
|
875 |
+
"learning_rate": 3.6854012860204814e-05,
|
876 |
+
"loss": 1.1231,
|
877 |
+
"step": 3100
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.7442248154322457,
|
881 |
+
"grad_norm": 25.206863403320312,
|
882 |
+
"learning_rate": 3.7151702786377715e-05,
|
883 |
+
"loss": 1.0407,
|
884 |
+
"step": 3125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.7501786139557037,
|
888 |
+
"grad_norm": 9.354549407958984,
|
889 |
+
"learning_rate": 3.744939271255061e-05,
|
890 |
+
"loss": 1.2782,
|
891 |
+
"step": 3150
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.7561324124791617,
|
895 |
+
"grad_norm": 4.694754123687744,
|
896 |
+
"learning_rate": 3.774708263872351e-05,
|
897 |
+
"loss": 1.1833,
|
898 |
+
"step": 3175
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.7620862110026196,
|
902 |
+
"grad_norm": 6.081759929656982,
|
903 |
+
"learning_rate": 3.8044772564896405e-05,
|
904 |
+
"loss": 1.2752,
|
905 |
+
"step": 3200
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.7680400095260776,
|
909 |
+
"grad_norm": 10.599677085876465,
|
910 |
+
"learning_rate": 3.8342462491069306e-05,
|
911 |
+
"loss": 1.151,
|
912 |
+
"step": 3225
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.7739938080495357,
|
916 |
+
"grad_norm": 12.136550903320312,
|
917 |
+
"learning_rate": 3.86401524172422e-05,
|
918 |
+
"loss": 1.2274,
|
919 |
+
"step": 3250
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.7799476065729936,
|
923 |
+
"grad_norm": 9.010398864746094,
|
924 |
+
"learning_rate": 3.8937842343415095e-05,
|
925 |
+
"loss": 1.4731,
|
926 |
+
"step": 3275
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.7859014050964516,
|
930 |
+
"grad_norm": 8.991976737976074,
|
931 |
+
"learning_rate": 3.9235532269588e-05,
|
932 |
+
"loss": 1.2017,
|
933 |
+
"step": 3300
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.7918552036199095,
|
937 |
+
"grad_norm": 7.551704406738281,
|
938 |
+
"learning_rate": 3.95332221957609e-05,
|
939 |
+
"loss": 1.3538,
|
940 |
+
"step": 3325
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.7978090021433675,
|
944 |
+
"grad_norm": 7.305477142333984,
|
945 |
+
"learning_rate": 3.983091212193379e-05,
|
946 |
+
"loss": 1.2053,
|
947 |
+
"step": 3350
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.8037628006668255,
|
951 |
+
"grad_norm": 8.888703346252441,
|
952 |
+
"learning_rate": 4.0128602048106694e-05,
|
953 |
+
"loss": 1.3227,
|
954 |
+
"step": 3375
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.8097165991902834,
|
958 |
+
"grad_norm": 12.521051406860352,
|
959 |
+
"learning_rate": 4.042629197427959e-05,
|
960 |
+
"loss": 1.0516,
|
961 |
+
"step": 3400
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.8156703977137414,
|
965 |
+
"grad_norm": 7.238898277282715,
|
966 |
+
"learning_rate": 4.072398190045249e-05,
|
967 |
+
"loss": 1.1264,
|
968 |
+
"step": 3425
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.8216241962371993,
|
972 |
+
"grad_norm": 10.125123977661133,
|
973 |
+
"learning_rate": 4.102167182662539e-05,
|
974 |
+
"loss": 1.2358,
|
975 |
+
"step": 3450
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.8275779947606573,
|
979 |
+
"grad_norm": 8.186086654663086,
|
980 |
+
"learning_rate": 4.1319361752798285e-05,
|
981 |
+
"loss": 1.0426,
|
982 |
+
"step": 3475
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.8335317932841153,
|
986 |
+
"grad_norm": 10.613844871520996,
|
987 |
+
"learning_rate": 4.1617051678971186e-05,
|
988 |
+
"loss": 1.3352,
|
989 |
+
"step": 3500
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.8394855918075732,
|
993 |
+
"grad_norm": 8.161314964294434,
|
994 |
+
"learning_rate": 4.191474160514409e-05,
|
995 |
+
"loss": 0.9903,
|
996 |
+
"step": 3525
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.8454393903310312,
|
1000 |
+
"grad_norm": 12.542242050170898,
|
1001 |
+
"learning_rate": 4.221243153131698e-05,
|
1002 |
+
"loss": 1.2685,
|
1003 |
+
"step": 3550
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.8513931888544891,
|
1007 |
+
"grad_norm": 7.340167999267578,
|
1008 |
+
"learning_rate": 4.251012145748988e-05,
|
1009 |
+
"loss": 1.0443,
|
1010 |
+
"step": 3575
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.8573469873779471,
|
1014 |
+
"grad_norm": 9.599905967712402,
|
1015 |
+
"learning_rate": 4.280781138366278e-05,
|
1016 |
+
"loss": 1.2975,
|
1017 |
+
"step": 3600
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.8633007859014051,
|
1021 |
+
"grad_norm": 20.305580139160156,
|
1022 |
+
"learning_rate": 4.310550130983568e-05,
|
1023 |
+
"loss": 1.1385,
|
1024 |
+
"step": 3625
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.869254584424863,
|
1028 |
+
"grad_norm": 8.58128833770752,
|
1029 |
+
"learning_rate": 4.340319123600858e-05,
|
1030 |
+
"loss": 1.2755,
|
1031 |
+
"step": 3650
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.875208382948321,
|
1035 |
+
"grad_norm": 7.283664226531982,
|
1036 |
+
"learning_rate": 4.3700881162181475e-05,
|
1037 |
+
"loss": 1.2377,
|
1038 |
+
"step": 3675
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.881162181471779,
|
1042 |
+
"grad_norm": 10.471671104431152,
|
1043 |
+
"learning_rate": 4.3998571088354376e-05,
|
1044 |
+
"loss": 1.274,
|
1045 |
+
"step": 3700
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.887115979995237,
|
1049 |
+
"grad_norm": 11.106354713439941,
|
1050 |
+
"learning_rate": 4.429626101452727e-05,
|
1051 |
+
"loss": 1.3215,
|
1052 |
+
"step": 3725
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.893069778518695,
|
1056 |
+
"grad_norm": 8.006999015808105,
|
1057 |
+
"learning_rate": 4.459395094070017e-05,
|
1058 |
+
"loss": 1.2153,
|
1059 |
+
"step": 3750
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.8990235770421529,
|
1063 |
+
"grad_norm": 12.414172172546387,
|
1064 |
+
"learning_rate": 4.4891640866873066e-05,
|
1065 |
+
"loss": 1.1706,
|
1066 |
+
"step": 3775
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.9049773755656109,
|
1070 |
+
"grad_norm": 8.146134376525879,
|
1071 |
+
"learning_rate": 4.518933079304597e-05,
|
1072 |
+
"loss": 1.245,
|
1073 |
+
"step": 3800
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.9109311740890689,
|
1077 |
+
"grad_norm": 11.50550651550293,
|
1078 |
+
"learning_rate": 4.548702071921886e-05,
|
1079 |
+
"loss": 1.2334,
|
1080 |
+
"step": 3825
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.9168849726125268,
|
1084 |
+
"grad_norm": 5.041258335113525,
|
1085 |
+
"learning_rate": 4.5784710645391756e-05,
|
1086 |
+
"loss": 1.1547,
|
1087 |
+
"step": 3850
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.9228387711359848,
|
1091 |
+
"grad_norm": 5.170175075531006,
|
1092 |
+
"learning_rate": 4.608240057156466e-05,
|
1093 |
+
"loss": 1.2673,
|
1094 |
+
"step": 3875
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.9287925696594427,
|
1098 |
+
"grad_norm": 3.370030641555786,
|
1099 |
+
"learning_rate": 4.638009049773756e-05,
|
1100 |
+
"loss": 1.2161,
|
1101 |
+
"step": 3900
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.9347463681829007,
|
1105 |
+
"grad_norm": 8.174607276916504,
|
1106 |
+
"learning_rate": 4.667778042391045e-05,
|
1107 |
+
"loss": 1.2999,
|
1108 |
+
"step": 3925
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.9407001667063587,
|
1112 |
+
"grad_norm": 8.648737907409668,
|
1113 |
+
"learning_rate": 4.6975470350083354e-05,
|
1114 |
+
"loss": 1.1796,
|
1115 |
+
"step": 3950
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.9466539652298166,
|
1119 |
+
"grad_norm": 4.100658893585205,
|
1120 |
+
"learning_rate": 4.7273160276256256e-05,
|
1121 |
+
"loss": 1.175,
|
1122 |
+
"step": 3975
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.9526077637532746,
|
1126 |
+
"grad_norm": 8.320395469665527,
|
1127 |
+
"learning_rate": 4.757085020242915e-05,
|
1128 |
+
"loss": 1.2008,
|
1129 |
+
"step": 4000
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.9585615622767325,
|
1133 |
+
"grad_norm": 8.804771423339844,
|
1134 |
+
"learning_rate": 4.786854012860205e-05,
|
1135 |
+
"loss": 1.2601,
|
1136 |
+
"step": 4025
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.9645153608001905,
|
1140 |
+
"grad_norm": 6.604278564453125,
|
1141 |
+
"learning_rate": 4.8166230054774946e-05,
|
1142 |
+
"loss": 1.2309,
|
1143 |
+
"step": 4050
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.9704691593236485,
|
1147 |
+
"grad_norm": 8.478154182434082,
|
1148 |
+
"learning_rate": 4.846391998094785e-05,
|
1149 |
+
"loss": 1.1459,
|
1150 |
+
"step": 4075
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.9764229578471064,
|
1154 |
+
"grad_norm": 9.920053482055664,
|
1155 |
+
"learning_rate": 4.876160990712075e-05,
|
1156 |
+
"loss": 1.058,
|
1157 |
+
"step": 4100
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.9823767563705644,
|
1161 |
+
"grad_norm": 7.725985050201416,
|
1162 |
+
"learning_rate": 4.905929983329364e-05,
|
1163 |
+
"loss": 1.2026,
|
1164 |
+
"step": 4125
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.9883305548940224,
|
1168 |
+
"grad_norm": 6.322876930236816,
|
1169 |
+
"learning_rate": 4.9356989759466544e-05,
|
1170 |
+
"loss": 1.2808,
|
1171 |
+
"step": 4150
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.9942843534174803,
|
1175 |
+
"grad_norm": 6.014225959777832,
|
1176 |
+
"learning_rate": 4.965467968563944e-05,
|
1177 |
+
"loss": 1.324,
|
1178 |
+
"step": 4175
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 1.0,
|
1182 |
+
"eval_accuracy": 0.5966916577412829,
|
1183 |
+
"eval_f1_macro": 0.4947213544811146,
|
1184 |
+
"eval_f1_micro": 0.5966916577412829,
|
1185 |
+
"eval_f1_weighted": 0.5697156949348047,
|
1186 |
+
"eval_loss": 1.2080416679382324,
|
1187 |
+
"eval_precision_macro": 0.4954154541683826,
|
1188 |
+
"eval_precision_micro": 0.5966916577412829,
|
1189 |
+
"eval_precision_weighted": 0.5767902087270278,
|
1190 |
+
"eval_recall_macro": 0.5315721027405438,
|
1191 |
+
"eval_recall_micro": 0.5966916577412829,
|
1192 |
+
"eval_recall_weighted": 0.5966916577412829,
|
1193 |
+
"eval_runtime": 26.7531,
|
1194 |
+
"eval_samples_per_second": 314.095,
|
1195 |
+
"eval_steps_per_second": 19.661,
|
1196 |
+
"step": 4199
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 1.0002381519409382,
|
1200 |
+
"grad_norm": 5.634415149688721,
|
1201 |
+
"learning_rate": 4.995236961181234e-05,
|
1202 |
+
"loss": 1.1611,
|
1203 |
+
"step": 4200
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 1.0061919504643964,
|
1207 |
+
"grad_norm": 6.43670654296875,
|
1208 |
+
"learning_rate": 4.997221560689053e-05,
|
1209 |
+
"loss": 1.0431,
|
1210 |
+
"step": 4225
|
1211 |
+
},
|
1212 |
+
{
|
1213 |
+
"epoch": 1.0121457489878543,
|
1214 |
+
"grad_norm": 9.240684509277344,
|
1215 |
+
"learning_rate": 4.993913894842688e-05,
|
1216 |
+
"loss": 1.2435,
|
1217 |
+
"step": 4250
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 1.0180995475113122,
|
1221 |
+
"grad_norm": 18.92078399658203,
|
1222 |
+
"learning_rate": 4.9906062289963226e-05,
|
1223 |
+
"loss": 1.1391,
|
1224 |
+
"step": 4275
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 1.0240533460347703,
|
1228 |
+
"grad_norm": 7.0122833251953125,
|
1229 |
+
"learning_rate": 4.9872985631499567e-05,
|
1230 |
+
"loss": 1.1175,
|
1231 |
+
"step": 4300
|
1232 |
+
},
|
1233 |
+
{
|
1234 |
+
"epoch": 1.0300071445582282,
|
1235 |
+
"grad_norm": 8.408838272094727,
|
1236 |
+
"learning_rate": 4.983990897303591e-05,
|
1237 |
+
"loss": 1.1911,
|
1238 |
+
"step": 4325
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 1.035960943081686,
|
1242 |
+
"grad_norm": 11.10263442993164,
|
1243 |
+
"learning_rate": 4.9806832314572254e-05,
|
1244 |
+
"loss": 1.1391,
|
1245 |
+
"step": 4350
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 1.0419147416051442,
|
1249 |
+
"grad_norm": 10.539508819580078,
|
1250 |
+
"learning_rate": 4.97737556561086e-05,
|
1251 |
+
"loss": 1.1194,
|
1252 |
+
"step": 4375
|
1253 |
+
},
|
1254 |
+
{
|
1255 |
+
"epoch": 1.047868540128602,
|
1256 |
+
"grad_norm": 5.538053512573242,
|
1257 |
+
"learning_rate": 4.974067899764495e-05,
|
1258 |
+
"loss": 1.0865,
|
1259 |
+
"step": 4400
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 1.05382233865206,
|
1263 |
+
"grad_norm": 6.905600547790527,
|
1264 |
+
"learning_rate": 4.970760233918128e-05,
|
1265 |
+
"loss": 1.0655,
|
1266 |
+
"step": 4425
|
1267 |
+
},
|
1268 |
+
{
|
1269 |
+
"epoch": 1.0597761371755179,
|
1270 |
+
"grad_norm": 11.629922866821289,
|
1271 |
+
"learning_rate": 4.967452568071763e-05,
|
1272 |
+
"loss": 1.0756,
|
1273 |
+
"step": 4450
|
1274 |
+
},
|
1275 |
+
{
|
1276 |
+
"epoch": 1.065729935698976,
|
1277 |
+
"grad_norm": 7.342074394226074,
|
1278 |
+
"learning_rate": 4.964144902225398e-05,
|
1279 |
+
"loss": 1.0758,
|
1280 |
+
"step": 4475
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 1.071683734222434,
|
1284 |
+
"grad_norm": 11.207491874694824,
|
1285 |
+
"learning_rate": 4.9608372363790325e-05,
|
1286 |
+
"loss": 1.0862,
|
1287 |
+
"step": 4500
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 1.0776375327458918,
|
1291 |
+
"grad_norm": 4.95857048034668,
|
1292 |
+
"learning_rate": 4.9575295705326665e-05,
|
1293 |
+
"loss": 1.1427,
|
1294 |
+
"step": 4525
|
1295 |
+
},
|
1296 |
+
{
|
1297 |
+
"epoch": 1.08359133126935,
|
1298 |
+
"grad_norm": 8.11075496673584,
|
1299 |
+
"learning_rate": 4.954221904686301e-05,
|
1300 |
+
"loss": 1.1302,
|
1301 |
+
"step": 4550
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 1.0895451297928078,
|
1305 |
+
"grad_norm": 6.039332389831543,
|
1306 |
+
"learning_rate": 4.950914238839935e-05,
|
1307 |
+
"loss": 1.1051,
|
1308 |
+
"step": 4575
|
1309 |
+
},
|
1310 |
+
{
|
1311 |
+
"epoch": 1.0954989283162657,
|
1312 |
+
"grad_norm": 6.331399440765381,
|
1313 |
+
"learning_rate": 4.94760657299357e-05,
|
1314 |
+
"loss": 1.0596,
|
1315 |
+
"step": 4600
|
1316 |
+
},
|
1317 |
+
{
|
1318 |
+
"epoch": 1.1014527268397238,
|
1319 |
+
"grad_norm": 7.124811172485352,
|
1320 |
+
"learning_rate": 4.944298907147205e-05,
|
1321 |
+
"loss": 1.0274,
|
1322 |
+
"step": 4625
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 1.1074065253631817,
|
1326 |
+
"grad_norm": 11.322517395019531,
|
1327 |
+
"learning_rate": 4.940991241300839e-05,
|
1328 |
+
"loss": 1.0636,
|
1329 |
+
"step": 4650
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 1.1133603238866396,
|
1333 |
+
"grad_norm": 4.297452449798584,
|
1334 |
+
"learning_rate": 4.9376835754544736e-05,
|
1335 |
+
"loss": 1.0874,
|
1336 |
+
"step": 4675
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 1.1193141224100978,
|
1340 |
+
"grad_norm": 7.16676664352417,
|
1341 |
+
"learning_rate": 4.934375909608108e-05,
|
1342 |
+
"loss": 1.014,
|
1343 |
+
"step": 4700
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 1.1252679209335557,
|
1347 |
+
"grad_norm": 5.3235182762146,
|
1348 |
+
"learning_rate": 4.9310682437617424e-05,
|
1349 |
+
"loss": 1.0657,
|
1350 |
+
"step": 4725
|
1351 |
+
},
|
1352 |
+
{
|
1353 |
+
"epoch": 1.1312217194570136,
|
1354 |
+
"grad_norm": 9.627723693847656,
|
1355 |
+
"learning_rate": 4.927760577915377e-05,
|
1356 |
+
"loss": 1.0914,
|
1357 |
+
"step": 4750
|
1358 |
+
},
|
1359 |
+
{
|
1360 |
+
"epoch": 1.1371755179804715,
|
1361 |
+
"grad_norm": 9.456254005432129,
|
1362 |
+
"learning_rate": 4.924452912069011e-05,
|
1363 |
+
"loss": 1.1473,
|
1364 |
+
"step": 4775
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 1.1431293165039296,
|
1368 |
+
"grad_norm": 24.08217430114746,
|
1369 |
+
"learning_rate": 4.921145246222646e-05,
|
1370 |
+
"loss": 0.9844,
|
1371 |
+
"step": 4800
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 1.1490831150273875,
|
1375 |
+
"grad_norm": 9.077038764953613,
|
1376 |
+
"learning_rate": 4.9178375803762806e-05,
|
1377 |
+
"loss": 1.0039,
|
1378 |
+
"step": 4825
|
1379 |
+
},
|
1380 |
+
{
|
1381 |
+
"epoch": 1.1550369135508454,
|
1382 |
+
"grad_norm": 9.616080284118652,
|
1383 |
+
"learning_rate": 4.9145299145299147e-05,
|
1384 |
+
"loss": 1.0242,
|
1385 |
+
"step": 4850
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 1.1609907120743035,
|
1389 |
+
"grad_norm": 7.154841423034668,
|
1390 |
+
"learning_rate": 4.9112222486835494e-05,
|
1391 |
+
"loss": 1.0895,
|
1392 |
+
"step": 4875
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 1.1669445105977614,
|
1396 |
+
"grad_norm": 9.329425811767578,
|
1397 |
+
"learning_rate": 4.9079145828371834e-05,
|
1398 |
+
"loss": 1.1656,
|
1399 |
+
"step": 4900
|
1400 |
+
},
|
1401 |
+
{
|
1402 |
+
"epoch": 1.1728983091212193,
|
1403 |
+
"grad_norm": 8.157685279846191,
|
1404 |
+
"learning_rate": 4.904606916990818e-05,
|
1405 |
+
"loss": 1.0478,
|
1406 |
+
"step": 4925
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 1.1788521076446772,
|
1410 |
+
"grad_norm": 9.068069458007812,
|
1411 |
+
"learning_rate": 4.901299251144453e-05,
|
1412 |
+
"loss": 1.0124,
|
1413 |
+
"step": 4950
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 1.1848059061681353,
|
1417 |
+
"grad_norm": 6.130595684051514,
|
1418 |
+
"learning_rate": 4.8979915852980876e-05,
|
1419 |
+
"loss": 1.1044,
|
1420 |
+
"step": 4975
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 1.1907597046915932,
|
1424 |
+
"grad_norm": 7.725107192993164,
|
1425 |
+
"learning_rate": 4.894683919451721e-05,
|
1426 |
+
"loss": 1.1225,
|
1427 |
+
"step": 5000
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 1.1967135032150513,
|
1431 |
+
"grad_norm": 102.51948547363281,
|
1432 |
+
"learning_rate": 4.891376253605356e-05,
|
1433 |
+
"loss": 1.1308,
|
1434 |
+
"step": 5025
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 1.2026673017385092,
|
1438 |
+
"grad_norm": 3.6292245388031006,
|
1439 |
+
"learning_rate": 4.8880685877589905e-05,
|
1440 |
+
"loss": 0.9875,
|
1441 |
+
"step": 5050
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 1.2086211002619671,
|
1445 |
+
"grad_norm": 8.71126937866211,
|
1446 |
+
"learning_rate": 4.884760921912625e-05,
|
1447 |
+
"loss": 1.0871,
|
1448 |
+
"step": 5075
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 1.214574898785425,
|
1452 |
+
"grad_norm": 13.922643661499023,
|
1453 |
+
"learning_rate": 4.881453256066259e-05,
|
1454 |
+
"loss": 1.0194,
|
1455 |
+
"step": 5100
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 1.2205286973088831,
|
1459 |
+
"grad_norm": 5.713569164276123,
|
1460 |
+
"learning_rate": 4.878145590219893e-05,
|
1461 |
+
"loss": 1.0232,
|
1462 |
+
"step": 5125
|
1463 |
+
},
|
1464 |
+
{
|
1465 |
+
"epoch": 1.226482495832341,
|
1466 |
+
"grad_norm": 8.962621688842773,
|
1467 |
+
"learning_rate": 4.874837924373528e-05,
|
1468 |
+
"loss": 1.1381,
|
1469 |
+
"step": 5150
|
1470 |
+
},
|
1471 |
+
{
|
1472 |
+
"epoch": 1.232436294355799,
|
1473 |
+
"grad_norm": 8.474043846130371,
|
1474 |
+
"learning_rate": 4.871530258527163e-05,
|
1475 |
+
"loss": 1.1649,
|
1476 |
+
"step": 5175
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"epoch": 1.238390092879257,
|
1480 |
+
"grad_norm": 6.489732265472412,
|
1481 |
+
"learning_rate": 4.8682225926807975e-05,
|
1482 |
+
"loss": 1.1688,
|
1483 |
+
"step": 5200
|
1484 |
+
},
|
1485 |
+
{
|
1486 |
+
"epoch": 1.244343891402715,
|
1487 |
+
"grad_norm": 8.985735893249512,
|
1488 |
+
"learning_rate": 4.8649149268344316e-05,
|
1489 |
+
"loss": 1.0109,
|
1490 |
+
"step": 5225
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 1.2502976899261729,
|
1494 |
+
"grad_norm": 4.531099319458008,
|
1495 |
+
"learning_rate": 4.861607260988066e-05,
|
1496 |
+
"loss": 0.8664,
|
1497 |
+
"step": 5250
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 1.2562514884496307,
|
1501 |
+
"grad_norm": 7.692714214324951,
|
1502 |
+
"learning_rate": 4.8582995951417004e-05,
|
1503 |
+
"loss": 0.993,
|
1504 |
+
"step": 5275
|
1505 |
+
},
|
1506 |
+
{
|
1507 |
+
"epoch": 1.2622052869730889,
|
1508 |
+
"grad_norm": 10.812503814697266,
|
1509 |
+
"learning_rate": 4.854991929295335e-05,
|
1510 |
+
"loss": 1.2124,
|
1511 |
+
"step": 5300
|
1512 |
+
},
|
1513 |
+
{
|
1514 |
+
"epoch": 1.2681590854965468,
|
1515 |
+
"grad_norm": 4.077712059020996,
|
1516 |
+
"learning_rate": 4.85168426344897e-05,
|
1517 |
+
"loss": 1.0187,
|
1518 |
+
"step": 5325
|
1519 |
+
},
|
1520 |
+
{
|
1521 |
+
"epoch": 1.2741128840200049,
|
1522 |
+
"grad_norm": 3.8732829093933105,
|
1523 |
+
"learning_rate": 4.848376597602604e-05,
|
1524 |
+
"loss": 1.0097,
|
1525 |
+
"step": 5350
|
1526 |
+
},
|
1527 |
+
{
|
1528 |
+
"epoch": 1.2800666825434628,
|
1529 |
+
"grad_norm": 16.588850021362305,
|
1530 |
+
"learning_rate": 4.8450689317562386e-05,
|
1531 |
+
"loss": 0.9223,
|
1532 |
+
"step": 5375
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 1.2860204810669207,
|
1536 |
+
"grad_norm": 11.135323524475098,
|
1537 |
+
"learning_rate": 4.8418935725437275e-05,
|
1538 |
+
"loss": 1.3406,
|
1539 |
+
"step": 5400
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 1.2919742795903786,
|
1543 |
+
"grad_norm": 10.437847137451172,
|
1544 |
+
"learning_rate": 4.838585906697362e-05,
|
1545 |
+
"loss": 1.0457,
|
1546 |
+
"step": 5425
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 1.2979280781138367,
|
1550 |
+
"grad_norm": 5.263082981109619,
|
1551 |
+
"learning_rate": 4.835278240850997e-05,
|
1552 |
+
"loss": 1.1183,
|
1553 |
+
"step": 5450
|
1554 |
+
},
|
1555 |
+
{
|
1556 |
+
"epoch": 1.3038818766372946,
|
1557 |
+
"grad_norm": 34.92927169799805,
|
1558 |
+
"learning_rate": 4.831970575004631e-05,
|
1559 |
+
"loss": 0.9997,
|
1560 |
+
"step": 5475
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"epoch": 1.3098356751607525,
|
1564 |
+
"grad_norm": 5.171608924865723,
|
1565 |
+
"learning_rate": 4.828662909158265e-05,
|
1566 |
+
"loss": 0.9876,
|
1567 |
+
"step": 5500
|
1568 |
+
},
|
1569 |
+
{
|
1570 |
+
"epoch": 1.3157894736842106,
|
1571 |
+
"grad_norm": 8.702177047729492,
|
1572 |
+
"learning_rate": 4.8253552433119e-05,
|
1573 |
+
"loss": 1.1814,
|
1574 |
+
"step": 5525
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 1.3217432722076685,
|
1578 |
+
"grad_norm": 5.145864963531494,
|
1579 |
+
"learning_rate": 4.8220475774655346e-05,
|
1580 |
+
"loss": 1.1428,
|
1581 |
+
"step": 5550
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 1.3276970707311264,
|
1585 |
+
"grad_norm": 6.461662292480469,
|
1586 |
+
"learning_rate": 4.8187399116191686e-05,
|
1587 |
+
"loss": 0.9919,
|
1588 |
+
"step": 5575
|
1589 |
+
},
|
1590 |
+
{
|
1591 |
+
"epoch": 1.3336508692545843,
|
1592 |
+
"grad_norm": 8.598640441894531,
|
1593 |
+
"learning_rate": 4.8154322457728034e-05,
|
1594 |
+
"loss": 0.8621,
|
1595 |
+
"step": 5600
|
1596 |
+
},
|
1597 |
+
{
|
1598 |
+
"epoch": 1.3396046677780424,
|
1599 |
+
"grad_norm": 8.139167785644531,
|
1600 |
+
"learning_rate": 4.8121245799264374e-05,
|
1601 |
+
"loss": 1.0601,
|
1602 |
+
"step": 5625
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 1.3455584663015003,
|
1606 |
+
"grad_norm": 10.176492691040039,
|
1607 |
+
"learning_rate": 4.808816914080072e-05,
|
1608 |
+
"loss": 1.0045,
|
1609 |
+
"step": 5650
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 1.3515122648249585,
|
1613 |
+
"grad_norm": 8.443796157836914,
|
1614 |
+
"learning_rate": 4.805509248233707e-05,
|
1615 |
+
"loss": 1.1288,
|
1616 |
+
"step": 5675
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 1.3574660633484164,
|
1620 |
+
"grad_norm": 4.203782081604004,
|
1621 |
+
"learning_rate": 4.802201582387341e-05,
|
1622 |
+
"loss": 1.0624,
|
1623 |
+
"step": 5700
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 1.3634198618718743,
|
1627 |
+
"grad_norm": 5.534155368804932,
|
1628 |
+
"learning_rate": 4.798893916540976e-05,
|
1629 |
+
"loss": 1.1066,
|
1630 |
+
"step": 5725
|
1631 |
+
},
|
1632 |
+
{
|
1633 |
+
"epoch": 1.3693736603953321,
|
1634 |
+
"grad_norm": 7.605154991149902,
|
1635 |
+
"learning_rate": 4.7955862506946104e-05,
|
1636 |
+
"loss": 1.0867,
|
1637 |
+
"step": 5750
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"epoch": 1.3753274589187903,
|
1641 |
+
"grad_norm": 7.6452107429504395,
|
1642 |
+
"learning_rate": 4.7922785848482445e-05,
|
1643 |
+
"loss": 1.0049,
|
1644 |
+
"step": 5775
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 1.3812812574422482,
|
1648 |
+
"grad_norm": 7.743738651275635,
|
1649 |
+
"learning_rate": 4.788970919001879e-05,
|
1650 |
+
"loss": 1.124,
|
1651 |
+
"step": 5800
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 1.387235055965706,
|
1655 |
+
"grad_norm": 5.369507789611816,
|
1656 |
+
"learning_rate": 4.785663253155513e-05,
|
1657 |
+
"loss": 1.1801,
|
1658 |
+
"step": 5825
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 1.3931888544891642,
|
1662 |
+
"grad_norm": 4.630309581756592,
|
1663 |
+
"learning_rate": 4.782355587309148e-05,
|
1664 |
+
"loss": 0.9165,
|
1665 |
+
"step": 5850
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 1.399142653012622,
|
1669 |
+
"grad_norm": 15.509940147399902,
|
1670 |
+
"learning_rate": 4.779047921462783e-05,
|
1671 |
+
"loss": 0.9489,
|
1672 |
+
"step": 5875
|
1673 |
+
},
|
1674 |
+
{
|
1675 |
+
"epoch": 1.40509645153608,
|
1676 |
+
"grad_norm": 6.903754234313965,
|
1677 |
+
"learning_rate": 4.775740255616417e-05,
|
1678 |
+
"loss": 0.8236,
|
1679 |
+
"step": 5900
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"epoch": 1.4110502500595379,
|
1683 |
+
"grad_norm": 13.870335578918457,
|
1684 |
+
"learning_rate": 4.772432589770051e-05,
|
1685 |
+
"loss": 1.2049,
|
1686 |
+
"step": 5925
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 1.417004048582996,
|
1690 |
+
"grad_norm": 7.386574745178223,
|
1691 |
+
"learning_rate": 4.7691249239236855e-05,
|
1692 |
+
"loss": 1.0842,
|
1693 |
+
"step": 5950
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 1.422957847106454,
|
1697 |
+
"grad_norm": 9.026902198791504,
|
1698 |
+
"learning_rate": 4.76581725807732e-05,
|
1699 |
+
"loss": 1.1066,
|
1700 |
+
"step": 5975
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 1.428911645629912,
|
1704 |
+
"grad_norm": 7.694133281707764,
|
1705 |
+
"learning_rate": 4.762509592230955e-05,
|
1706 |
+
"loss": 0.9639,
|
1707 |
+
"step": 6000
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 1.43486544415337,
|
1711 |
+
"grad_norm": 7.63619327545166,
|
1712 |
+
"learning_rate": 4.759201926384589e-05,
|
1713 |
+
"loss": 1.1174,
|
1714 |
+
"step": 6025
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 1.4408192426768278,
|
1718 |
+
"grad_norm": 11.331910133361816,
|
1719 |
+
"learning_rate": 4.755894260538223e-05,
|
1720 |
+
"loss": 1.0762,
|
1721 |
+
"step": 6050
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 1.4467730412002857,
|
1725 |
+
"grad_norm": 5.851023197174072,
|
1726 |
+
"learning_rate": 4.752586594691858e-05,
|
1727 |
+
"loss": 1.1457,
|
1728 |
+
"step": 6075
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 1.4527268397237436,
|
1732 |
+
"grad_norm": 5.016726016998291,
|
1733 |
+
"learning_rate": 4.7492789288454926e-05,
|
1734 |
+
"loss": 1.1557,
|
1735 |
+
"step": 6100
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 1.4586806382472017,
|
1739 |
+
"grad_norm": 6.742854595184326,
|
1740 |
+
"learning_rate": 4.7461035696329815e-05,
|
1741 |
+
"loss": 1.0926,
|
1742 |
+
"step": 6125
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 1.4646344367706596,
|
1746 |
+
"grad_norm": 7.604907989501953,
|
1747 |
+
"learning_rate": 4.742795903786616e-05,
|
1748 |
+
"loss": 1.1302,
|
1749 |
+
"step": 6150
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 1.4705882352941178,
|
1753 |
+
"grad_norm": 17.53195571899414,
|
1754 |
+
"learning_rate": 4.73948823794025e-05,
|
1755 |
+
"loss": 1.0213,
|
1756 |
+
"step": 6175
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 1.4765420338175756,
|
1760 |
+
"grad_norm": 6.960255146026611,
|
1761 |
+
"learning_rate": 4.736180572093885e-05,
|
1762 |
+
"loss": 1.1129,
|
1763 |
+
"step": 6200
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 1.4824958323410335,
|
1767 |
+
"grad_norm": 10.175301551818848,
|
1768 |
+
"learning_rate": 4.73287290624752e-05,
|
1769 |
+
"loss": 1.2069,
|
1770 |
+
"step": 6225
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 1.4884496308644914,
|
1774 |
+
"grad_norm": 10.815943717956543,
|
1775 |
+
"learning_rate": 4.729565240401154e-05,
|
1776 |
+
"loss": 1.1805,
|
1777 |
+
"step": 6250
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 1.4944034293879496,
|
1781 |
+
"grad_norm": 2.322054386138916,
|
1782 |
+
"learning_rate": 4.7262575745547886e-05,
|
1783 |
+
"loss": 0.9646,
|
1784 |
+
"step": 6275
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 1.5003572279114075,
|
1788 |
+
"grad_norm": 4.6621809005737305,
|
1789 |
+
"learning_rate": 4.7229499087084226e-05,
|
1790 |
+
"loss": 1.1626,
|
1791 |
+
"step": 6300
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 1.5063110264348656,
|
1795 |
+
"grad_norm": 10.837236404418945,
|
1796 |
+
"learning_rate": 4.719642242862057e-05,
|
1797 |
+
"loss": 0.9685,
|
1798 |
+
"step": 6325
|
1799 |
+
},
|
1800 |
+
{
|
1801 |
+
"epoch": 1.5122648249583235,
|
1802 |
+
"grad_norm": 6.7249436378479,
|
1803 |
+
"learning_rate": 4.716334577015692e-05,
|
1804 |
+
"loss": 1.2021,
|
1805 |
+
"step": 6350
|
1806 |
+
},
|
1807 |
+
{
|
1808 |
+
"epoch": 1.5182186234817814,
|
1809 |
+
"grad_norm": 12.020308494567871,
|
1810 |
+
"learning_rate": 4.713026911169327e-05,
|
1811 |
+
"loss": 0.9582,
|
1812 |
+
"step": 6375
|
1813 |
+
},
|
1814 |
+
{
|
1815 |
+
"epoch": 1.5241724220052393,
|
1816 |
+
"grad_norm": 7.54368782043457,
|
1817 |
+
"learning_rate": 4.70971924532296e-05,
|
1818 |
+
"loss": 0.8267,
|
1819 |
+
"step": 6400
|
1820 |
+
},
|
1821 |
+
{
|
1822 |
+
"epoch": 1.5301262205286972,
|
1823 |
+
"grad_norm": 7.932629585266113,
|
1824 |
+
"learning_rate": 4.706411579476595e-05,
|
1825 |
+
"loss": 1.108,
|
1826 |
+
"step": 6425
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 1.5360800190521553,
|
1830 |
+
"grad_norm": 5.615595817565918,
|
1831 |
+
"learning_rate": 4.7031039136302296e-05,
|
1832 |
+
"loss": 1.04,
|
1833 |
+
"step": 6450
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 1.5420338175756132,
|
1837 |
+
"grad_norm": 6.620110988616943,
|
1838 |
+
"learning_rate": 4.6997962477838644e-05,
|
1839 |
+
"loss": 1.1267,
|
1840 |
+
"step": 6475
|
1841 |
+
},
|
1842 |
+
{
|
1843 |
+
"epoch": 1.5479876160990713,
|
1844 |
+
"grad_norm": 5.139624118804932,
|
1845 |
+
"learning_rate": 4.6964885819374984e-05,
|
1846 |
+
"loss": 1.1831,
|
1847 |
+
"step": 6500
|
1848 |
+
},
|
1849 |
+
{
|
1850 |
+
"epoch": 1.5539414146225292,
|
1851 |
+
"grad_norm": 12.21379566192627,
|
1852 |
+
"learning_rate": 4.693180916091133e-05,
|
1853 |
+
"loss": 0.9852,
|
1854 |
+
"step": 6525
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 1.5598952131459871,
|
1858 |
+
"grad_norm": 4.394635200500488,
|
1859 |
+
"learning_rate": 4.689873250244767e-05,
|
1860 |
+
"loss": 0.9538,
|
1861 |
+
"step": 6550
|
1862 |
+
},
|
1863 |
+
{
|
1864 |
+
"epoch": 1.565849011669445,
|
1865 |
+
"grad_norm": 17.616371154785156,
|
1866 |
+
"learning_rate": 4.686565584398402e-05,
|
1867 |
+
"loss": 1.1278,
|
1868 |
+
"step": 6575
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 1.571802810192903,
|
1872 |
+
"grad_norm": 11.440567016601562,
|
1873 |
+
"learning_rate": 4.683257918552037e-05,
|
1874 |
+
"loss": 0.9045,
|
1875 |
+
"step": 6600
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 1.577756608716361,
|
1879 |
+
"grad_norm": 7.166686058044434,
|
1880 |
+
"learning_rate": 4.679950252705671e-05,
|
1881 |
+
"loss": 1.012,
|
1882 |
+
"step": 6625
|
1883 |
+
},
|
1884 |
+
{
|
1885 |
+
"epoch": 1.5837104072398192,
|
1886 |
+
"grad_norm": 3.898224115371704,
|
1887 |
+
"learning_rate": 4.6766425868593055e-05,
|
1888 |
+
"loss": 1.0239,
|
1889 |
+
"step": 6650
|
1890 |
+
},
|
1891 |
+
{
|
1892 |
+
"epoch": 1.589664205763277,
|
1893 |
+
"grad_norm": 6.445250511169434,
|
1894 |
+
"learning_rate": 4.6733349210129395e-05,
|
1895 |
+
"loss": 1.0405,
|
1896 |
+
"step": 6675
|
1897 |
+
},
|
1898 |
+
{
|
1899 |
+
"epoch": 1.595618004286735,
|
1900 |
+
"grad_norm": 6.74089241027832,
|
1901 |
+
"learning_rate": 4.670027255166574e-05,
|
1902 |
+
"loss": 1.0741,
|
1903 |
+
"step": 6700
|
1904 |
+
},
|
1905 |
+
{
|
1906 |
+
"epoch": 1.6015718028101928,
|
1907 |
+
"grad_norm": 8.296637535095215,
|
1908 |
+
"learning_rate": 4.666719589320209e-05,
|
1909 |
+
"loss": 1.0257,
|
1910 |
+
"step": 6725
|
1911 |
+
},
|
1912 |
+
{
|
1913 |
+
"epoch": 1.6075256013336507,
|
1914 |
+
"grad_norm": 4.417313575744629,
|
1915 |
+
"learning_rate": 4.663411923473843e-05,
|
1916 |
+
"loss": 1.04,
|
1917 |
+
"step": 6750
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 1.6134793998571089,
|
1921 |
+
"grad_norm": 9.14215087890625,
|
1922 |
+
"learning_rate": 4.660104257627478e-05,
|
1923 |
+
"loss": 0.953,
|
1924 |
+
"step": 6775
|
1925 |
+
},
|
1926 |
+
{
|
1927 |
+
"epoch": 1.6194331983805668,
|
1928 |
+
"grad_norm": 6.057753562927246,
|
1929 |
+
"learning_rate": 4.6567965917811125e-05,
|
1930 |
+
"loss": 1.0497,
|
1931 |
+
"step": 6800
|
1932 |
+
},
|
1933 |
+
{
|
1934 |
+
"epoch": 1.6253869969040249,
|
1935 |
+
"grad_norm": 5.951107501983643,
|
1936 |
+
"learning_rate": 4.6534889259347466e-05,
|
1937 |
+
"loss": 0.9889,
|
1938 |
+
"step": 6825
|
1939 |
+
},
|
1940 |
+
{
|
1941 |
+
"epoch": 1.6313407954274828,
|
1942 |
+
"grad_norm": 7.338003158569336,
|
1943 |
+
"learning_rate": 4.650181260088381e-05,
|
1944 |
+
"loss": 0.9164,
|
1945 |
+
"step": 6850
|
1946 |
+
},
|
1947 |
+
{
|
1948 |
+
"epoch": 1.6372945939509407,
|
1949 |
+
"grad_norm": 6.255341053009033,
|
1950 |
+
"learning_rate": 4.646873594242015e-05,
|
1951 |
+
"loss": 1.0507,
|
1952 |
+
"step": 6875
|
1953 |
+
},
|
1954 |
+
{
|
1955 |
+
"epoch": 1.6432483924743986,
|
1956 |
+
"grad_norm": 5.0770344734191895,
|
1957 |
+
"learning_rate": 4.64356592839565e-05,
|
1958 |
+
"loss": 0.988,
|
1959 |
+
"step": 6900
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 1.6492021909978565,
|
1963 |
+
"grad_norm": 10.511390686035156,
|
1964 |
+
"learning_rate": 4.640258262549285e-05,
|
1965 |
+
"loss": 1.1466,
|
1966 |
+
"step": 6925
|
1967 |
+
},
|
1968 |
+
{
|
1969 |
+
"epoch": 1.6551559895213146,
|
1970 |
+
"grad_norm": 4.4176201820373535,
|
1971 |
+
"learning_rate": 4.636950596702919e-05,
|
1972 |
+
"loss": 0.9668,
|
1973 |
+
"step": 6950
|
1974 |
+
},
|
1975 |
+
{
|
1976 |
+
"epoch": 1.6611097880447727,
|
1977 |
+
"grad_norm": 7.061136722564697,
|
1978 |
+
"learning_rate": 4.633642930856553e-05,
|
1979 |
+
"loss": 1.1601,
|
1980 |
+
"step": 6975
|
1981 |
+
},
|
1982 |
+
{
|
1983 |
+
"epoch": 1.6670635865682306,
|
1984 |
+
"grad_norm": 6.016676425933838,
|
1985 |
+
"learning_rate": 4.6303352650101876e-05,
|
1986 |
+
"loss": 1.1006,
|
1987 |
+
"step": 7000
|
1988 |
+
},
|
1989 |
+
{
|
1990 |
+
"epoch": 1.6730173850916885,
|
1991 |
+
"grad_norm": 5.641656875610352,
|
1992 |
+
"learning_rate": 4.6270275991638224e-05,
|
1993 |
+
"loss": 0.9667,
|
1994 |
+
"step": 7025
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 1.6789711836151464,
|
1998 |
+
"grad_norm": 6.386135101318359,
|
1999 |
+
"learning_rate": 4.623719933317457e-05,
|
2000 |
+
"loss": 1.0356,
|
2001 |
+
"step": 7050
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 1.6849249821386043,
|
2005 |
+
"grad_norm": 6.999917507171631,
|
2006 |
+
"learning_rate": 4.620412267471091e-05,
|
2007 |
+
"loss": 1.0388,
|
2008 |
+
"step": 7075
|
2009 |
+
},
|
2010 |
+
{
|
2011 |
+
"epoch": 1.6908787806620624,
|
2012 |
+
"grad_norm": 6.0239129066467285,
|
2013 |
+
"learning_rate": 4.617104601624725e-05,
|
2014 |
+
"loss": 0.8963,
|
2015 |
+
"step": 7100
|
2016 |
+
},
|
2017 |
+
{
|
2018 |
+
"epoch": 1.6968325791855203,
|
2019 |
+
"grad_norm": 7.390036106109619,
|
2020 |
+
"learning_rate": 4.61379693577836e-05,
|
2021 |
+
"loss": 1.1959,
|
2022 |
+
"step": 7125
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 1.7027863777089784,
|
2026 |
+
"grad_norm": 5.598720550537109,
|
2027 |
+
"learning_rate": 4.610489269931995e-05,
|
2028 |
+
"loss": 1.0214,
|
2029 |
+
"step": 7150
|
2030 |
+
},
|
2031 |
+
{
|
2032 |
+
"epoch": 1.7087401762324363,
|
2033 |
+
"grad_norm": 4.715810298919678,
|
2034 |
+
"learning_rate": 4.6071816040856294e-05,
|
2035 |
+
"loss": 0.8499,
|
2036 |
+
"step": 7175
|
2037 |
+
},
|
2038 |
+
{
|
2039 |
+
"epoch": 1.7146939747558942,
|
2040 |
+
"grad_norm": 4.418345928192139,
|
2041 |
+
"learning_rate": 4.6038739382392635e-05,
|
2042 |
+
"loss": 0.9179,
|
2043 |
+
"step": 7200
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 1.7206477732793521,
|
2047 |
+
"grad_norm": 4.199166774749756,
|
2048 |
+
"learning_rate": 4.6005662723928975e-05,
|
2049 |
+
"loss": 0.9991,
|
2050 |
+
"step": 7225
|
2051 |
+
},
|
2052 |
+
{
|
2053 |
+
"epoch": 1.72660157180281,
|
2054 |
+
"grad_norm": 6.189085960388184,
|
2055 |
+
"learning_rate": 4.597258606546532e-05,
|
2056 |
+
"loss": 1.0998,
|
2057 |
+
"step": 7250
|
2058 |
+
},
|
2059 |
+
{
|
2060 |
+
"epoch": 1.7325553703262682,
|
2061 |
+
"grad_norm": 6.4427809715271,
|
2062 |
+
"learning_rate": 4.593950940700167e-05,
|
2063 |
+
"loss": 0.8524,
|
2064 |
+
"step": 7275
|
2065 |
+
},
|
2066 |
+
{
|
2067 |
+
"epoch": 1.7385091688497263,
|
2068 |
+
"grad_norm": 3.7036330699920654,
|
2069 |
+
"learning_rate": 4.590643274853802e-05,
|
2070 |
+
"loss": 0.9207,
|
2071 |
+
"step": 7300
|
2072 |
+
},
|
2073 |
+
{
|
2074 |
+
"epoch": 1.7444629673731842,
|
2075 |
+
"grad_norm": 10.30667495727539,
|
2076 |
+
"learning_rate": 4.587335609007436e-05,
|
2077 |
+
"loss": 1.0137,
|
2078 |
+
"step": 7325
|
2079 |
+
},
|
2080 |
+
{
|
2081 |
+
"epoch": 1.750416765896642,
|
2082 |
+
"grad_norm": 5.976552486419678,
|
2083 |
+
"learning_rate": 4.5840279431610705e-05,
|
2084 |
+
"loss": 1.0607,
|
2085 |
+
"step": 7350
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 1.7563705644201,
|
2089 |
+
"grad_norm": 5.703713893890381,
|
2090 |
+
"learning_rate": 4.5807202773147046e-05,
|
2091 |
+
"loss": 0.9637,
|
2092 |
+
"step": 7375
|
2093 |
+
},
|
2094 |
+
{
|
2095 |
+
"epoch": 1.7623243629435579,
|
2096 |
+
"grad_norm": 4.452537536621094,
|
2097 |
+
"learning_rate": 4.577412611468339e-05,
|
2098 |
+
"loss": 0.969,
|
2099 |
+
"step": 7400
|
2100 |
+
},
|
2101 |
+
{
|
2102 |
+
"epoch": 1.768278161467016,
|
2103 |
+
"grad_norm": 3.4350435733795166,
|
2104 |
+
"learning_rate": 4.574104945621973e-05,
|
2105 |
+
"loss": 1.0022,
|
2106 |
+
"step": 7425
|
2107 |
+
},
|
2108 |
+
{
|
2109 |
+
"epoch": 1.774231959990474,
|
2110 |
+
"grad_norm": 4.28000545501709,
|
2111 |
+
"learning_rate": 4.570797279775608e-05,
|
2112 |
+
"loss": 1.0655,
|
2113 |
+
"step": 7450
|
2114 |
+
},
|
2115 |
+
{
|
2116 |
+
"epoch": 1.780185758513932,
|
2117 |
+
"grad_norm": 5.708723545074463,
|
2118 |
+
"learning_rate": 4.567489613929243e-05,
|
2119 |
+
"loss": 0.9273,
|
2120 |
+
"step": 7475
|
2121 |
+
},
|
2122 |
+
{
|
2123 |
+
"epoch": 1.78613955703739,
|
2124 |
+
"grad_norm": 6.020782470703125,
|
2125 |
+
"learning_rate": 4.5641819480828775e-05,
|
2126 |
+
"loss": 0.945,
|
2127 |
+
"step": 7500
|
2128 |
+
},
|
2129 |
+
{
|
2130 |
+
"epoch": 1.7920933555608478,
|
2131 |
+
"grad_norm": 4.774454593658447,
|
2132 |
+
"learning_rate": 4.5608742822365116e-05,
|
2133 |
+
"loss": 1.017,
|
2134 |
+
"step": 7525
|
2135 |
+
},
|
2136 |
+
{
|
2137 |
+
"epoch": 1.7980471540843057,
|
2138 |
+
"grad_norm": 5.020348072052002,
|
2139 |
+
"learning_rate": 4.5575666163901456e-05,
|
2140 |
+
"loss": 1.0637,
|
2141 |
+
"step": 7550
|
2142 |
+
},
|
2143 |
+
{
|
2144 |
+
"epoch": 1.8040009526077636,
|
2145 |
+
"grad_norm": 7.373719692230225,
|
2146 |
+
"learning_rate": 4.5542589505437804e-05,
|
2147 |
+
"loss": 1.0,
|
2148 |
+
"step": 7575
|
2149 |
+
},
|
2150 |
+
{
|
2151 |
+
"epoch": 1.8099547511312217,
|
2152 |
+
"grad_norm": 3.8169615268707275,
|
2153 |
+
"learning_rate": 4.550951284697415e-05,
|
2154 |
+
"loss": 0.9843,
|
2155 |
+
"step": 7600
|
2156 |
+
},
|
2157 |
+
{
|
2158 |
+
"epoch": 1.8159085496546798,
|
2159 |
+
"grad_norm": 6.140167236328125,
|
2160 |
+
"learning_rate": 4.54764361885105e-05,
|
2161 |
+
"loss": 0.9415,
|
2162 |
+
"step": 7625
|
2163 |
+
},
|
2164 |
+
{
|
2165 |
+
"epoch": 1.8218623481781377,
|
2166 |
+
"grad_norm": 9.949686050415039,
|
2167 |
+
"learning_rate": 4.544335953004684e-05,
|
2168 |
+
"loss": 1.0756,
|
2169 |
+
"step": 7650
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 1.8278161467015956,
|
2173 |
+
"grad_norm": 5.582162380218506,
|
2174 |
+
"learning_rate": 4.541028287158318e-05,
|
2175 |
+
"loss": 0.9648,
|
2176 |
+
"step": 7675
|
2177 |
+
},
|
2178 |
+
{
|
2179 |
+
"epoch": 1.8337699452250535,
|
2180 |
+
"grad_norm": 7.782459259033203,
|
2181 |
+
"learning_rate": 4.537720621311953e-05,
|
2182 |
+
"loss": 1.0866,
|
2183 |
+
"step": 7700
|
2184 |
+
},
|
2185 |
+
{
|
2186 |
+
"epoch": 1.8397237437485114,
|
2187 |
+
"grad_norm": 4.777675151824951,
|
2188 |
+
"learning_rate": 4.5344129554655874e-05,
|
2189 |
+
"loss": 0.8936,
|
2190 |
+
"step": 7725
|
2191 |
+
},
|
2192 |
+
{
|
2193 |
+
"epoch": 1.8456775422719696,
|
2194 |
+
"grad_norm": 4.16018009185791,
|
2195 |
+
"learning_rate": 4.531105289619222e-05,
|
2196 |
+
"loss": 0.9454,
|
2197 |
+
"step": 7750
|
2198 |
+
},
|
2199 |
+
{
|
2200 |
+
"epoch": 1.8516313407954275,
|
2201 |
+
"grad_norm": 4.443974494934082,
|
2202 |
+
"learning_rate": 4.527797623772856e-05,
|
2203 |
+
"loss": 1.0104,
|
2204 |
+
"step": 7775
|
2205 |
+
},
|
2206 |
+
{
|
2207 |
+
"epoch": 1.8575851393188856,
|
2208 |
+
"grad_norm": 6.139829158782959,
|
2209 |
+
"learning_rate": 4.52448995792649e-05,
|
2210 |
+
"loss": 0.9752,
|
2211 |
+
"step": 7800
|
2212 |
+
},
|
2213 |
+
{
|
2214 |
+
"epoch": 1.8635389378423435,
|
2215 |
+
"grad_norm": 8.074860572814941,
|
2216 |
+
"learning_rate": 4.521182292080125e-05,
|
2217 |
+
"loss": 1.0173,
|
2218 |
+
"step": 7825
|
2219 |
+
},
|
2220 |
+
{
|
2221 |
+
"epoch": 1.8694927363658014,
|
2222 |
+
"grad_norm": 5.377435684204102,
|
2223 |
+
"learning_rate": 4.51787462623376e-05,
|
2224 |
+
"loss": 0.8224,
|
2225 |
+
"step": 7850
|
2226 |
+
},
|
2227 |
+
{
|
2228 |
+
"epoch": 1.8754465348892593,
|
2229 |
+
"grad_norm": 8.767934799194336,
|
2230 |
+
"learning_rate": 4.5145669603873944e-05,
|
2231 |
+
"loss": 1.1385,
|
2232 |
+
"step": 7875
|
2233 |
+
},
|
2234 |
+
{
|
2235 |
+
"epoch": 1.8814003334127172,
|
2236 |
+
"grad_norm": 7.324585914611816,
|
2237 |
+
"learning_rate": 4.5112592945410285e-05,
|
2238 |
+
"loss": 1.0644,
|
2239 |
+
"step": 7900
|
2240 |
+
},
|
2241 |
+
{
|
2242 |
+
"epoch": 1.8873541319361753,
|
2243 |
+
"grad_norm": 9.182265281677246,
|
2244 |
+
"learning_rate": 4.5079516286946626e-05,
|
2245 |
+
"loss": 1.102,
|
2246 |
+
"step": 7925
|
2247 |
+
},
|
2248 |
+
{
|
2249 |
+
"epoch": 1.8933079304596332,
|
2250 |
+
"grad_norm": 7.2876715660095215,
|
2251 |
+
"learning_rate": 4.504643962848297e-05,
|
2252 |
+
"loss": 0.9735,
|
2253 |
+
"step": 7950
|
2254 |
+
},
|
2255 |
+
{
|
2256 |
+
"epoch": 1.8992617289830913,
|
2257 |
+
"grad_norm": 6.998351097106934,
|
2258 |
+
"learning_rate": 4.501336297001932e-05,
|
2259 |
+
"loss": 0.956,
|
2260 |
+
"step": 7975
|
2261 |
+
},
|
2262 |
+
{
|
2263 |
+
"epoch": 1.9052155275065492,
|
2264 |
+
"grad_norm": 4.216850280761719,
|
2265 |
+
"learning_rate": 4.498028631155566e-05,
|
2266 |
+
"loss": 0.9517,
|
2267 |
+
"step": 8000
|
2268 |
+
},
|
2269 |
+
{
|
2270 |
+
"epoch": 1.911169326030007,
|
2271 |
+
"grad_norm": 3.5328800678253174,
|
2272 |
+
"learning_rate": 4.494720965309201e-05,
|
2273 |
+
"loss": 1.0805,
|
2274 |
+
"step": 8025
|
2275 |
+
},
|
2276 |
+
{
|
2277 |
+
"epoch": 1.917123124553465,
|
2278 |
+
"grad_norm": 6.827732086181641,
|
2279 |
+
"learning_rate": 4.4914132994628355e-05,
|
2280 |
+
"loss": 1.0643,
|
2281 |
+
"step": 8050
|
2282 |
+
},
|
2283 |
+
{
|
2284 |
+
"epoch": 1.9230769230769231,
|
2285 |
+
"grad_norm": 6.08967399597168,
|
2286 |
+
"learning_rate": 4.4881056336164696e-05,
|
2287 |
+
"loss": 1.0416,
|
2288 |
+
"step": 8075
|
2289 |
+
},
|
2290 |
+
{
|
2291 |
+
"epoch": 1.929030721600381,
|
2292 |
+
"grad_norm": 8.008926391601562,
|
2293 |
+
"learning_rate": 4.484797967770104e-05,
|
2294 |
+
"loss": 0.9322,
|
2295 |
+
"step": 8100
|
2296 |
+
},
|
2297 |
+
{
|
2298 |
+
"epoch": 1.9349845201238391,
|
2299 |
+
"grad_norm": 13.753870964050293,
|
2300 |
+
"learning_rate": 4.4814903019237384e-05,
|
2301 |
+
"loss": 0.8809,
|
2302 |
+
"step": 8125
|
2303 |
+
},
|
2304 |
+
{
|
2305 |
+
"epoch": 1.940938318647297,
|
2306 |
+
"grad_norm": 9.109087944030762,
|
2307 |
+
"learning_rate": 4.478182636077373e-05,
|
2308 |
+
"loss": 0.9042,
|
2309 |
+
"step": 8150
|
2310 |
+
},
|
2311 |
+
{
|
2312 |
+
"epoch": 1.946892117170755,
|
2313 |
+
"grad_norm": 6.401242256164551,
|
2314 |
+
"learning_rate": 4.474874970231008e-05,
|
2315 |
+
"loss": 0.9542,
|
2316 |
+
"step": 8175
|
2317 |
+
},
|
2318 |
+
{
|
2319 |
+
"epoch": 1.9528459156942128,
|
2320 |
+
"grad_norm": 10.232426643371582,
|
2321 |
+
"learning_rate": 4.4715673043846426e-05,
|
2322 |
+
"loss": 1.1949,
|
2323 |
+
"step": 8200
|
2324 |
+
},
|
2325 |
+
{
|
2326 |
+
"epoch": 1.9587997142176707,
|
2327 |
+
"grad_norm": 5.458783149719238,
|
2328 |
+
"learning_rate": 4.4682596385382766e-05,
|
2329 |
+
"loss": 0.8728,
|
2330 |
+
"step": 8225
|
2331 |
+
},
|
2332 |
+
{
|
2333 |
+
"epoch": 1.9647535127411289,
|
2334 |
+
"grad_norm": 8.005071640014648,
|
2335 |
+
"learning_rate": 4.464951972691911e-05,
|
2336 |
+
"loss": 1.0506,
|
2337 |
+
"step": 8250
|
2338 |
+
},
|
2339 |
+
{
|
2340 |
+
"epoch": 1.9707073112645868,
|
2341 |
+
"grad_norm": 8.608522415161133,
|
2342 |
+
"learning_rate": 4.4616443068455454e-05,
|
2343 |
+
"loss": 1.0458,
|
2344 |
+
"step": 8275
|
2345 |
+
},
|
2346 |
+
{
|
2347 |
+
"epoch": 1.9766611097880449,
|
2348 |
+
"grad_norm": 7.659764289855957,
|
2349 |
+
"learning_rate": 4.45833664099918e-05,
|
2350 |
+
"loss": 0.9629,
|
2351 |
+
"step": 8300
|
2352 |
+
},
|
2353 |
+
{
|
2354 |
+
"epoch": 1.9826149083115028,
|
2355 |
+
"grad_norm": 6.268425464630127,
|
2356 |
+
"learning_rate": 4.455028975152815e-05,
|
2357 |
+
"loss": 0.9374,
|
2358 |
+
"step": 8325
|
2359 |
+
},
|
2360 |
+
{
|
2361 |
+
"epoch": 1.9885687068349607,
|
2362 |
+
"grad_norm": 6.64276123046875,
|
2363 |
+
"learning_rate": 4.451721309306449e-05,
|
2364 |
+
"loss": 0.9243,
|
2365 |
+
"step": 8350
|
2366 |
+
},
|
2367 |
+
{
|
2368 |
+
"epoch": 1.9945225053584186,
|
2369 |
+
"grad_norm": 7.175469398498535,
|
2370 |
+
"learning_rate": 4.448413643460083e-05,
|
2371 |
+
"loss": 1.1004,
|
2372 |
+
"step": 8375
|
2373 |
+
},
|
2374 |
+
{
|
2375 |
+
"epoch": 2.0,
|
2376 |
+
"eval_accuracy": 0.6112102820421278,
|
2377 |
+
"eval_f1_macro": 0.5315462561949883,
|
2378 |
+
"eval_f1_micro": 0.6112102820421278,
|
2379 |
+
"eval_f1_weighted": 0.6025346871719214,
|
2380 |
+
"eval_loss": 1.0703290700912476,
|
2381 |
+
"eval_precision_macro": 0.6157278778731476,
|
2382 |
+
"eval_precision_micro": 0.6112102820421278,
|
2383 |
+
"eval_precision_weighted": 0.635344882882464,
|
2384 |
+
"eval_recall_macro": 0.5271202118810513,
|
2385 |
+
"eval_recall_micro": 0.6112102820421278,
|
2386 |
+
"eval_recall_weighted": 0.6112102820421278,
|
2387 |
+
"eval_runtime": 25.2331,
|
2388 |
+
"eval_samples_per_second": 333.014,
|
2389 |
+
"eval_steps_per_second": 20.846,
|
2390 |
+
"step": 8398
|
2391 |
+
}
|
2392 |
+
],
|
2393 |
+
"logging_steps": 25,
|
2394 |
+
"max_steps": 41990,
|
2395 |
+
"num_input_tokens_seen": 0,
|
2396 |
+
"num_train_epochs": 10,
|
2397 |
+
"save_steps": 500,
|
2398 |
+
"stateful_callbacks": {
|
2399 |
+
"EarlyStoppingCallback": {
|
2400 |
+
"args": {
|
2401 |
+
"early_stopping_patience": 5,
|
2402 |
+
"early_stopping_threshold": 0.01
|
2403 |
+
},
|
2404 |
+
"attributes": {
|
2405 |
+
"early_stopping_patience_counter": 0
|
2406 |
+
}
|
2407 |
+
},
|
2408 |
+
"TrainerControl": {
|
2409 |
+
"args": {
|
2410 |
+
"should_epoch_stop": false,
|
2411 |
+
"should_evaluate": false,
|
2412 |
+
"should_log": false,
|
2413 |
+
"should_save": true,
|
2414 |
+
"should_training_stop": false
|
2415 |
+
},
|
2416 |
+
"attributes": {}
|
2417 |
+
}
|
2418 |
+
},
|
2419 |
+
"total_flos": 1.7761706134611456e+16,
|
2420 |
+
"train_batch_size": 8,
|
2421 |
+
"trial_name": null,
|
2422 |
+
"trial_params": null
|
2423 |
+
}
|
checkpoint-8398/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81528ef86348f13753ac9c95b4717d84c6154cea233a98a91f71c7af256567a1
|
3 |
+
size 5368
|
config.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "answerdotai/ModernBERT-large",
|
3 |
+
"_num_labels": 13,
|
4 |
+
"architectures": [
|
5 |
+
"ModernBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_bias": false,
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 50281,
|
10 |
+
"classifier_activation": "gelu",
|
11 |
+
"classifier_bias": false,
|
12 |
+
"classifier_dropout": 0.0,
|
13 |
+
"classifier_pooling": "mean",
|
14 |
+
"cls_token_id": 50281,
|
15 |
+
"decoder_bias": true,
|
16 |
+
"deterministic_flash_attn": false,
|
17 |
+
"embedding_dropout": 0.0,
|
18 |
+
"eos_token_id": 50282,
|
19 |
+
"global_attn_every_n_layers": 3,
|
20 |
+
"global_rope_theta": 160000.0,
|
21 |
+
"gradient_checkpointing": false,
|
22 |
+
"hidden_activation": "gelu",
|
23 |
+
"hidden_size": 1024,
|
24 |
+
"id2label": {
|
25 |
+
"0": "dunya",
|
26 |
+
"1": "ekonomi",
|
27 |
+
"2": "genel",
|
28 |
+
"3": "guncel",
|
29 |
+
"4": "kultur-sanat",
|
30 |
+
"5": "magazin",
|
31 |
+
"6": "planet",
|
32 |
+
"7": "saglik",
|
33 |
+
"8": "siyaset",
|
34 |
+
"9": "spor",
|
35 |
+
"10": "teknoloji",
|
36 |
+
"11": "turkiye",
|
37 |
+
"12": "yasam"
|
38 |
+
},
|
39 |
+
"initializer_cutoff_factor": 2.0,
|
40 |
+
"initializer_range": 0.02,
|
41 |
+
"intermediate_size": 2624,
|
42 |
+
"label2id": {
|
43 |
+
"dunya": 0,
|
44 |
+
"ekonomi": 1,
|
45 |
+
"genel": 2,
|
46 |
+
"guncel": 3,
|
47 |
+
"kultur-sanat": 4,
|
48 |
+
"magazin": 5,
|
49 |
+
"planet": 6,
|
50 |
+
"saglik": 7,
|
51 |
+
"siyaset": 8,
|
52 |
+
"spor": 9,
|
53 |
+
"teknoloji": 10,
|
54 |
+
"turkiye": 11,
|
55 |
+
"yasam": 12
|
56 |
+
},
|
57 |
+
"layer_norm_eps": 1e-05,
|
58 |
+
"local_attention": 128,
|
59 |
+
"local_rope_theta": 10000.0,
|
60 |
+
"max_position_embeddings": 8192,
|
61 |
+
"mlp_bias": false,
|
62 |
+
"mlp_dropout": 0.0,
|
63 |
+
"model_type": "modernbert",
|
64 |
+
"norm_bias": false,
|
65 |
+
"norm_eps": 1e-05,
|
66 |
+
"num_attention_heads": 16,
|
67 |
+
"num_hidden_layers": 28,
|
68 |
+
"pad_token_id": 50283,
|
69 |
+
"position_embedding_type": "absolute",
|
70 |
+
"problem_type": "single_label_classification",
|
71 |
+
"reference_compile": true,
|
72 |
+
"repad_logits_with_grad": false,
|
73 |
+
"sep_token_id": 50282,
|
74 |
+
"sparse_pred_ignore_index": -100,
|
75 |
+
"sparse_prediction": false,
|
76 |
+
"torch_dtype": "float32",
|
77 |
+
"transformers_version": "4.48.0",
|
78 |
+
"vocab_size": 50368
|
79 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b75e3dd58b60ccea590aaa484c65e1584092399c75cb03d73d08cc771b5b9a22
|
3 |
+
size 1583396740
|
runs/Mar08_21-48-47_umit-MS-7E07/events.out.tfevents.1741459728.umit-MS-7E07.5173.0
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 sha256:0b60c077d2c5ab0a7211c386d0f2f00aeebbd480956e4c64046478d30b81de54
|
3 |
+
size 262513
|
runs/Mar08_21-48-47_umit-MS-7E07/events.out.tfevents.1741463362.umit-MS-7E07.5173.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c19606b6f7caef3e3123097a93456174e54f78c184fca57fb1d81c1028e886f
|
3 |
+
size 936
|
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": true,
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,945 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "|||IP_ADDRESS|||",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<|padding|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"50254": {
|
20 |
+
"content": " ",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": false
|
26 |
+
},
|
27 |
+
"50255": {
|
28 |
+
"content": " ",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": false
|
34 |
+
},
|
35 |
+
"50256": {
|
36 |
+
"content": " ",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": false
|
42 |
+
},
|
43 |
+
"50257": {
|
44 |
+
"content": " ",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"50258": {
|
52 |
+
"content": " ",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"50259": {
|
60 |
+
"content": " ",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"50260": {
|
68 |
+
"content": " ",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": true,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"50261": {
|
76 |
+
"content": " ",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": true,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"50262": {
|
84 |
+
"content": " ",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": true,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"50263": {
|
92 |
+
"content": " ",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": true,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"50264": {
|
100 |
+
"content": " ",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
},
|
107 |
+
"50265": {
|
108 |
+
"content": " ",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": true,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": false
|
114 |
+
},
|
115 |
+
"50266": {
|
116 |
+
"content": " ",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
"50267": {
|
124 |
+
"content": " ",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": true,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": false
|
130 |
+
},
|
131 |
+
"50268": {
|
132 |
+
"content": " ",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": true,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": false
|
138 |
+
},
|
139 |
+
"50269": {
|
140 |
+
"content": " ",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": true,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": false
|
146 |
+
},
|
147 |
+
"50270": {
|
148 |
+
"content": " ",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": true,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
"50271": {
|
156 |
+
"content": " ",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": true,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": false
|
162 |
+
},
|
163 |
+
"50272": {
|
164 |
+
"content": " ",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": true,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": false
|
170 |
+
},
|
171 |
+
"50273": {
|
172 |
+
"content": " ",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": true,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": false
|
178 |
+
},
|
179 |
+
"50274": {
|
180 |
+
"content": " ",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": true,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"50275": {
|
188 |
+
"content": " ",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": true,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"50276": {
|
196 |
+
"content": " ",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": true,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
},
|
203 |
+
"50277": {
|
204 |
+
"content": "|||EMAIL_ADDRESS|||",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": true,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": false
|
210 |
+
},
|
211 |
+
"50278": {
|
212 |
+
"content": "|||PHONE_NUMBER|||",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": true,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": false
|
218 |
+
},
|
219 |
+
"50279": {
|
220 |
+
"content": "<|endoftext|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"50280": {
|
228 |
+
"content": "[UNK]",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"50281": {
|
236 |
+
"content": "[CLS]",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"50282": {
|
244 |
+
"content": "[SEP]",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"50283": {
|
252 |
+
"content": "[PAD]",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"50284": {
|
260 |
+
"content": "[MASK]",
|
261 |
+
"lstrip": true,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"50285": {
|
268 |
+
"content": "[unused0]",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": true,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": false
|
274 |
+
},
|
275 |
+
"50286": {
|
276 |
+
"content": "[unused1]",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": true,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": false
|
282 |
+
},
|
283 |
+
"50287": {
|
284 |
+
"content": "[unused2]",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": true,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": false
|
290 |
+
},
|
291 |
+
"50288": {
|
292 |
+
"content": "[unused3]",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": true,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": false
|
298 |
+
},
|
299 |
+
"50289": {
|
300 |
+
"content": "[unused4]",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": true,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": false
|
306 |
+
},
|
307 |
+
"50290": {
|
308 |
+
"content": "[unused5]",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": true,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": false
|
314 |
+
},
|
315 |
+
"50291": {
|
316 |
+
"content": "[unused6]",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": true,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": false
|
322 |
+
},
|
323 |
+
"50292": {
|
324 |
+
"content": "[unused7]",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": true,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": false
|
330 |
+
},
|
331 |
+
"50293": {
|
332 |
+
"content": "[unused8]",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": true,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": false
|
338 |
+
},
|
339 |
+
"50294": {
|
340 |
+
"content": "[unused9]",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": true,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": false
|
346 |
+
},
|
347 |
+
"50295": {
|
348 |
+
"content": "[unused10]",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": true,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": false
|
354 |
+
},
|
355 |
+
"50296": {
|
356 |
+
"content": "[unused11]",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": true,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": false
|
362 |
+
},
|
363 |
+
"50297": {
|
364 |
+
"content": "[unused12]",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": true,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": false
|
370 |
+
},
|
371 |
+
"50298": {
|
372 |
+
"content": "[unused13]",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": true,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": false
|
378 |
+
},
|
379 |
+
"50299": {
|
380 |
+
"content": "[unused14]",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": true,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": false
|
386 |
+
},
|
387 |
+
"50300": {
|
388 |
+
"content": "[unused15]",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": true,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": false
|
394 |
+
},
|
395 |
+
"50301": {
|
396 |
+
"content": "[unused16]",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": true,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": false
|
402 |
+
},
|
403 |
+
"50302": {
|
404 |
+
"content": "[unused17]",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": true,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": false
|
410 |
+
},
|
411 |
+
"50303": {
|
412 |
+
"content": "[unused18]",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": true,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": false
|
418 |
+
},
|
419 |
+
"50304": {
|
420 |
+
"content": "[unused19]",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": true,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": false
|
426 |
+
},
|
427 |
+
"50305": {
|
428 |
+
"content": "[unused20]",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": true,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": false
|
434 |
+
},
|
435 |
+
"50306": {
|
436 |
+
"content": "[unused21]",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": true,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": false
|
442 |
+
},
|
443 |
+
"50307": {
|
444 |
+
"content": "[unused22]",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": true,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": false
|
450 |
+
},
|
451 |
+
"50308": {
|
452 |
+
"content": "[unused23]",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": true,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": false
|
458 |
+
},
|
459 |
+
"50309": {
|
460 |
+
"content": "[unused24]",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": true,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": false
|
466 |
+
},
|
467 |
+
"50310": {
|
468 |
+
"content": "[unused25]",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": true,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": false
|
474 |
+
},
|
475 |
+
"50311": {
|
476 |
+
"content": "[unused26]",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": true,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": false
|
482 |
+
},
|
483 |
+
"50312": {
|
484 |
+
"content": "[unused27]",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": true,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": false
|
490 |
+
},
|
491 |
+
"50313": {
|
492 |
+
"content": "[unused28]",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": true,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": false
|
498 |
+
},
|
499 |
+
"50314": {
|
500 |
+
"content": "[unused29]",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": true,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": false
|
506 |
+
},
|
507 |
+
"50315": {
|
508 |
+
"content": "[unused30]",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": true,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": false
|
514 |
+
},
|
515 |
+
"50316": {
|
516 |
+
"content": "[unused31]",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": true,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": false
|
522 |
+
},
|
523 |
+
"50317": {
|
524 |
+
"content": "[unused32]",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": true,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": false
|
530 |
+
},
|
531 |
+
"50318": {
|
532 |
+
"content": "[unused33]",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": true,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": false
|
538 |
+
},
|
539 |
+
"50319": {
|
540 |
+
"content": "[unused34]",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": true,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": false
|
546 |
+
},
|
547 |
+
"50320": {
|
548 |
+
"content": "[unused35]",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": true,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": false
|
554 |
+
},
|
555 |
+
"50321": {
|
556 |
+
"content": "[unused36]",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": true,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": false
|
562 |
+
},
|
563 |
+
"50322": {
|
564 |
+
"content": "[unused37]",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": true,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": false
|
570 |
+
},
|
571 |
+
"50323": {
|
572 |
+
"content": "[unused38]",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": true,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": false
|
578 |
+
},
|
579 |
+
"50324": {
|
580 |
+
"content": "[unused39]",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": true,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": false
|
586 |
+
},
|
587 |
+
"50325": {
|
588 |
+
"content": "[unused40]",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": true,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": false
|
594 |
+
},
|
595 |
+
"50326": {
|
596 |
+
"content": "[unused41]",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": true,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": false
|
602 |
+
},
|
603 |
+
"50327": {
|
604 |
+
"content": "[unused42]",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": true,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": false
|
610 |
+
},
|
611 |
+
"50328": {
|
612 |
+
"content": "[unused43]",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": true,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": false
|
618 |
+
},
|
619 |
+
"50329": {
|
620 |
+
"content": "[unused44]",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": true,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": false
|
626 |
+
},
|
627 |
+
"50330": {
|
628 |
+
"content": "[unused45]",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": true,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": false
|
634 |
+
},
|
635 |
+
"50331": {
|
636 |
+
"content": "[unused46]",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": true,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": false
|
642 |
+
},
|
643 |
+
"50332": {
|
644 |
+
"content": "[unused47]",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": true,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": false
|
650 |
+
},
|
651 |
+
"50333": {
|
652 |
+
"content": "[unused48]",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": true,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": false
|
658 |
+
},
|
659 |
+
"50334": {
|
660 |
+
"content": "[unused49]",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": true,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": false
|
666 |
+
},
|
667 |
+
"50335": {
|
668 |
+
"content": "[unused50]",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": true,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": false
|
674 |
+
},
|
675 |
+
"50336": {
|
676 |
+
"content": "[unused51]",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": true,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": false
|
682 |
+
},
|
683 |
+
"50337": {
|
684 |
+
"content": "[unused52]",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": true,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": false
|
690 |
+
},
|
691 |
+
"50338": {
|
692 |
+
"content": "[unused53]",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": true,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": false
|
698 |
+
},
|
699 |
+
"50339": {
|
700 |
+
"content": "[unused54]",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": true,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": false
|
706 |
+
},
|
707 |
+
"50340": {
|
708 |
+
"content": "[unused55]",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": true,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": false
|
714 |
+
},
|
715 |
+
"50341": {
|
716 |
+
"content": "[unused56]",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": true,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": false
|
722 |
+
},
|
723 |
+
"50342": {
|
724 |
+
"content": "[unused57]",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": true,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": false
|
730 |
+
},
|
731 |
+
"50343": {
|
732 |
+
"content": "[unused58]",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": true,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": false
|
738 |
+
},
|
739 |
+
"50344": {
|
740 |
+
"content": "[unused59]",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": true,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": false
|
746 |
+
},
|
747 |
+
"50345": {
|
748 |
+
"content": "[unused60]",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": true,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": false
|
754 |
+
},
|
755 |
+
"50346": {
|
756 |
+
"content": "[unused61]",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": true,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": false
|
762 |
+
},
|
763 |
+
"50347": {
|
764 |
+
"content": "[unused62]",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": true,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": false
|
770 |
+
},
|
771 |
+
"50348": {
|
772 |
+
"content": "[unused63]",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": true,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": false
|
778 |
+
},
|
779 |
+
"50349": {
|
780 |
+
"content": "[unused64]",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": true,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": false
|
786 |
+
},
|
787 |
+
"50350": {
|
788 |
+
"content": "[unused65]",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": true,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": false
|
794 |
+
},
|
795 |
+
"50351": {
|
796 |
+
"content": "[unused66]",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": true,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": false
|
802 |
+
},
|
803 |
+
"50352": {
|
804 |
+
"content": "[unused67]",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": true,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": false
|
810 |
+
},
|
811 |
+
"50353": {
|
812 |
+
"content": "[unused68]",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": true,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": false
|
818 |
+
},
|
819 |
+
"50354": {
|
820 |
+
"content": "[unused69]",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": true,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": false
|
826 |
+
},
|
827 |
+
"50355": {
|
828 |
+
"content": "[unused70]",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": true,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": false
|
834 |
+
},
|
835 |
+
"50356": {
|
836 |
+
"content": "[unused71]",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": true,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": false
|
842 |
+
},
|
843 |
+
"50357": {
|
844 |
+
"content": "[unused72]",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": true,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": false
|
850 |
+
},
|
851 |
+
"50358": {
|
852 |
+
"content": "[unused73]",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": true,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": false
|
858 |
+
},
|
859 |
+
"50359": {
|
860 |
+
"content": "[unused74]",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": true,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": false
|
866 |
+
},
|
867 |
+
"50360": {
|
868 |
+
"content": "[unused75]",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": true,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": false
|
874 |
+
},
|
875 |
+
"50361": {
|
876 |
+
"content": "[unused76]",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": true,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": false
|
882 |
+
},
|
883 |
+
"50362": {
|
884 |
+
"content": "[unused77]",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": true,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": false
|
890 |
+
},
|
891 |
+
"50363": {
|
892 |
+
"content": "[unused78]",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": true,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": false
|
898 |
+
},
|
899 |
+
"50364": {
|
900 |
+
"content": "[unused79]",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": true,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": false
|
906 |
+
},
|
907 |
+
"50365": {
|
908 |
+
"content": "[unused80]",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": true,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": false
|
914 |
+
},
|
915 |
+
"50366": {
|
916 |
+
"content": "[unused81]",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": true,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": false
|
922 |
+
},
|
923 |
+
"50367": {
|
924 |
+
"content": "[unused82]",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": true,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": false
|
930 |
+
}
|
931 |
+
},
|
932 |
+
"clean_up_tokenization_spaces": true,
|
933 |
+
"cls_token": "[CLS]",
|
934 |
+
"extra_special_tokens": {},
|
935 |
+
"mask_token": "[MASK]",
|
936 |
+
"model_input_names": [
|
937 |
+
"input_ids",
|
938 |
+
"attention_mask"
|
939 |
+
],
|
940 |
+
"model_max_length": 8192,
|
941 |
+
"pad_token": "[PAD]",
|
942 |
+
"sep_token": "[SEP]",
|
943 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
944 |
+
"unk_token": "[UNK]"
|
945 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81528ef86348f13753ac9c95b4717d84c6154cea233a98a91f71c7af256567a1
|
3 |
+
size 5368
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "uisikdag/42news",
|
3 |
+
"model": "answerdotai/ModernBERT-large",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 10,
|
6 |
+
"max_seq_length": 128,
|
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": "train",
|
16 |
+
"valid_split": "test",
|
17 |
+
"text_column": "text",
|
18 |
+
"target_column": "label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "autotrain-modernBERT-large",
|
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": "uisikdag",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|