Upload folder using huggingface_hub
Browse files- training_checkpoints/checkpoint-6720/added_tokens.json +3 -0
- training_checkpoints/checkpoint-6720/config.json +41 -0
- training_checkpoints/checkpoint-6720/model.safetensors +3 -0
- training_checkpoints/checkpoint-6720/optimizer.pt +3 -0
- training_checkpoints/checkpoint-6720/rng_state.pth +3 -0
- training_checkpoints/checkpoint-6720/scheduler.pt +3 -0
- training_checkpoints/checkpoint-6720/special_tokens_map.json +13 -0
- training_checkpoints/checkpoint-6720/tokenizer.json +0 -0
- training_checkpoints/checkpoint-6720/tokenizer_config.json +65 -0
- training_checkpoints/checkpoint-6720/trainer_state.json +772 -0
- training_checkpoints/checkpoint-6720/training_args.bin +3 -0
- training_checkpoints/checkpoint-6720/vocab.txt +0 -0
training_checkpoints/checkpoint-6720/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 30522
|
| 3 |
+
}
|
training_checkpoints/checkpoint-6720/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "law-ai/InLegalBERT",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_ids": 0,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "positive",
|
| 15 |
+
"1": "negative",
|
| 16 |
+
"2": "neutral",
|
| 17 |
+
"3": "rel_by_party"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"negative": 1,
|
| 23 |
+
"neutral": 2,
|
| 24 |
+
"positive": 0,
|
| 25 |
+
"rel_by_party": 3
|
| 26 |
+
},
|
| 27 |
+
"layer_norm_eps": 1e-12,
|
| 28 |
+
"max_position_embeddings": 512,
|
| 29 |
+
"model_type": "bert",
|
| 30 |
+
"num_attention_heads": 12,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"output_past": true,
|
| 33 |
+
"pad_token_id": 30522,
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.39.3",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 30523
|
| 41 |
+
}
|
training_checkpoints/checkpoint-6720/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:681956eb351c6cac17d8bf1b119ba3254aae485be0d7b05f71077b96c6f036e5
|
| 3 |
+
size 437967872
|
training_checkpoints/checkpoint-6720/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8907c87fbc3ac980044723e4d684c35fd4d64289e8a0feaa79340bc27cff7ded
|
| 3 |
+
size 876056826
|
training_checkpoints/checkpoint-6720/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c051796db7a8fd8b691e9b0582ea1a4a65237504c907717d6f64624858c0cac1
|
| 3 |
+
size 14244
|
training_checkpoints/checkpoint-6720/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fea6b06751fd544073018c634bf5756f794d308adb01dc2a1f8783d100304f96
|
| 3 |
+
size 1064
|
training_checkpoints/checkpoint-6720/special_tokens_map.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"sep_token": "[SEP]",
|
| 12 |
+
"unk_token": "[UNK]"
|
| 13 |
+
}
|
training_checkpoints/checkpoint-6720/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_checkpoints/checkpoint-6720/tokenizer_config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"30522": {
|
| 44 |
+
"content": "<pad>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"clean_up_tokenization_spaces": true,
|
| 53 |
+
"cls_token": "[CLS]",
|
| 54 |
+
"do_basic_tokenize": true,
|
| 55 |
+
"do_lower_case": true,
|
| 56 |
+
"mask_token": "[MASK]",
|
| 57 |
+
"model_max_length": 512,
|
| 58 |
+
"never_split": null,
|
| 59 |
+
"pad_token": "<pad>",
|
| 60 |
+
"sep_token": "[SEP]",
|
| 61 |
+
"strip_accents": null,
|
| 62 |
+
"tokenize_chinese_chars": true,
|
| 63 |
+
"tokenizer_class": "BertTokenizer",
|
| 64 |
+
"unk_token": "[UNK]"
|
| 65 |
+
}
|
training_checkpoints/checkpoint-6720/trainer_state.json
ADDED
|
@@ -0,0 +1,772 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6690246389304302,
|
| 3 |
+
"best_model_checkpoint": "case-analysis-InLegalBERT/checkpoint-1344",
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6720,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.8017817371937639,
|
| 14 |
+
"eval_f1_macro": 0.5936102522033613,
|
| 15 |
+
"eval_f1_micro": 0.8017817371937639,
|
| 16 |
+
"eval_f1_weighted": 0.7819923339877444,
|
| 17 |
+
"eval_loss": 0.6545999050140381,
|
| 18 |
+
"eval_macro_fpr": 0.09781883735656886,
|
| 19 |
+
"eval_macro_sensitivity": 0.6106003826592061,
|
| 20 |
+
"eval_macro_specificity": 0.9112420642353884,
|
| 21 |
+
"eval_precision": 0.763240968439436,
|
| 22 |
+
"eval_precision_macro": 0.5776616905319997,
|
| 23 |
+
"eval_recall": 0.8017817371937639,
|
| 24 |
+
"eval_recall_macro": 0.6106003826592061,
|
| 25 |
+
"eval_runtime": 9.2925,
|
| 26 |
+
"eval_samples_per_second": 48.318,
|
| 27 |
+
"eval_steps_per_second": 6.134,
|
| 28 |
+
"eval_weighted_fpr": 0.07613344739093242,
|
| 29 |
+
"eval_weighted_sensitivity": 0.8017817371937639,
|
| 30 |
+
"eval_weighted_specificity": 0.84318651974779,
|
| 31 |
+
"step": 224
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.0,
|
| 35 |
+
"eval_accuracy": 0.8129175946547884,
|
| 36 |
+
"eval_f1_macro": 0.5995597405020452,
|
| 37 |
+
"eval_f1_micro": 0.8129175946547884,
|
| 38 |
+
"eval_f1_weighted": 0.7925821933419933,
|
| 39 |
+
"eval_loss": 0.6830806732177734,
|
| 40 |
+
"eval_macro_fpr": 0.0922965769071398,
|
| 41 |
+
"eval_macro_sensitivity": 0.615426637485461,
|
| 42 |
+
"eval_macro_specificity": 0.9170902440637451,
|
| 43 |
+
"eval_precision": 0.7732439444566204,
|
| 44 |
+
"eval_precision_macro": 0.5844969763606377,
|
| 45 |
+
"eval_recall": 0.8129175946547884,
|
| 46 |
+
"eval_recall_macro": 0.615426637485461,
|
| 47 |
+
"eval_runtime": 36.5377,
|
| 48 |
+
"eval_samples_per_second": 12.289,
|
| 49 |
+
"eval_steps_per_second": 1.56,
|
| 50 |
+
"eval_weighted_fpr": 0.07124681933842239,
|
| 51 |
+
"eval_weighted_sensitivity": 0.8129175946547884,
|
| 52 |
+
"eval_weighted_specificity": 0.8554433816001921,
|
| 53 |
+
"step": 448
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 2.23,
|
| 57 |
+
"grad_norm": 6.910687446594238,
|
| 58 |
+
"learning_rate": 4.6302083333333335e-05,
|
| 59 |
+
"loss": 0.607,
|
| 60 |
+
"step": 500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.0,
|
| 64 |
+
"eval_accuracy": 0.8262806236080178,
|
| 65 |
+
"eval_f1_macro": 0.6362135046138226,
|
| 66 |
+
"eval_f1_micro": 0.8262806236080178,
|
| 67 |
+
"eval_f1_weighted": 0.8105096248986687,
|
| 68 |
+
"eval_loss": 0.7626442909240723,
|
| 69 |
+
"eval_macro_fpr": 0.0885057964533289,
|
| 70 |
+
"eval_macro_sensitivity": 0.6341414944356121,
|
| 71 |
+
"eval_macro_specificity": 0.9181782637863818,
|
| 72 |
+
"eval_precision": 0.8060163824047696,
|
| 73 |
+
"eval_precision_macro": 0.6772816989326722,
|
| 74 |
+
"eval_recall": 0.8262806236080178,
|
| 75 |
+
"eval_recall_macro": 0.6341414944356121,
|
| 76 |
+
"eval_runtime": 35.6726,
|
| 77 |
+
"eval_samples_per_second": 12.587,
|
| 78 |
+
"eval_steps_per_second": 1.598,
|
| 79 |
+
"eval_weighted_fpr": 0.0654911838790932,
|
| 80 |
+
"eval_weighted_sensitivity": 0.8262806236080178,
|
| 81 |
+
"eval_weighted_specificity": 0.8464324315375095,
|
| 82 |
+
"step": 672
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 4.0,
|
| 86 |
+
"eval_accuracy": 0.8084632516703786,
|
| 87 |
+
"eval_f1_macro": 0.6313839669673806,
|
| 88 |
+
"eval_f1_micro": 0.8084632516703786,
|
| 89 |
+
"eval_f1_weighted": 0.8017481865377005,
|
| 90 |
+
"eval_loss": 0.7839008569717407,
|
| 91 |
+
"eval_macro_fpr": 0.08961602877899306,
|
| 92 |
+
"eval_macro_sensitivity": 0.630579873226932,
|
| 93 |
+
"eval_macro_specificity": 0.9209618973154744,
|
| 94 |
+
"eval_precision": 0.7990879202460494,
|
| 95 |
+
"eval_precision_macro": 0.6390850934968582,
|
| 96 |
+
"eval_recall": 0.8084632516703786,
|
| 97 |
+
"eval_recall_macro": 0.630579873226932,
|
| 98 |
+
"eval_runtime": 33.6763,
|
| 99 |
+
"eval_samples_per_second": 13.333,
|
| 100 |
+
"eval_steps_per_second": 1.693,
|
| 101 |
+
"eval_weighted_fpr": 0.07319148936170213,
|
| 102 |
+
"eval_weighted_sensitivity": 0.8084632516703786,
|
| 103 |
+
"eval_weighted_specificity": 0.8753843375915193,
|
| 104 |
+
"step": 896
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.46,
|
| 108 |
+
"grad_norm": 0.3201627731323242,
|
| 109 |
+
"learning_rate": 4.258184523809524e-05,
|
| 110 |
+
"loss": 0.316,
|
| 111 |
+
"step": 1000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 5.0,
|
| 115 |
+
"eval_accuracy": 0.8262806236080178,
|
| 116 |
+
"eval_f1_macro": 0.6513945578231293,
|
| 117 |
+
"eval_f1_micro": 0.8262806236080178,
|
| 118 |
+
"eval_f1_weighted": 0.8161065406117904,
|
| 119 |
+
"eval_loss": 0.9380576610565186,
|
| 120 |
+
"eval_macro_fpr": 0.08224137352531583,
|
| 121 |
+
"eval_macro_sensitivity": 0.6573161205514146,
|
| 122 |
+
"eval_macro_specificity": 0.9260657452373569,
|
| 123 |
+
"eval_precision": 0.8127349298285333,
|
| 124 |
+
"eval_precision_macro": 0.668810150869688,
|
| 125 |
+
"eval_recall": 0.8262806236080178,
|
| 126 |
+
"eval_recall_macro": 0.6573161205514146,
|
| 127 |
+
"eval_runtime": 34.3275,
|
| 128 |
+
"eval_samples_per_second": 13.08,
|
| 129 |
+
"eval_steps_per_second": 1.66,
|
| 130 |
+
"eval_weighted_fpr": 0.0654911838790932,
|
| 131 |
+
"eval_weighted_sensitivity": 0.8262806236080178,
|
| 132 |
+
"eval_weighted_specificity": 0.8779823573414097,
|
| 133 |
+
"step": 1120
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 6.0,
|
| 137 |
+
"eval_accuracy": 0.821826280623608,
|
| 138 |
+
"eval_f1_macro": 0.6690246389304302,
|
| 139 |
+
"eval_f1_micro": 0.821826280623608,
|
| 140 |
+
"eval_f1_weighted": 0.8159237291984361,
|
| 141 |
+
"eval_loss": 1.0433590412139893,
|
| 142 |
+
"eval_macro_fpr": 0.08967976675610558,
|
| 143 |
+
"eval_macro_sensitivity": 0.6533037047742931,
|
| 144 |
+
"eval_macro_specificity": 0.9186687903009794,
|
| 145 |
+
"eval_precision": 0.8145202780918083,
|
| 146 |
+
"eval_precision_macro": 0.6906556062141168,
|
| 147 |
+
"eval_recall": 0.821826280623608,
|
| 148 |
+
"eval_recall_macro": 0.6533037047742931,
|
| 149 |
+
"eval_runtime": 43.316,
|
| 150 |
+
"eval_samples_per_second": 10.366,
|
| 151 |
+
"eval_steps_per_second": 1.316,
|
| 152 |
+
"eval_weighted_fpr": 0.06739679865206402,
|
| 153 |
+
"eval_weighted_sensitivity": 0.821826280623608,
|
| 154 |
+
"eval_weighted_specificity": 0.8528488805803094,
|
| 155 |
+
"step": 1344
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 6.7,
|
| 159 |
+
"grad_norm": 0.028867056593298912,
|
| 160 |
+
"learning_rate": 3.8869047619047625e-05,
|
| 161 |
+
"loss": 0.1513,
|
| 162 |
+
"step": 1500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 7.0,
|
| 166 |
+
"eval_accuracy": 0.8017817371937639,
|
| 167 |
+
"eval_f1_macro": 0.6374820990180032,
|
| 168 |
+
"eval_f1_micro": 0.8017817371937639,
|
| 169 |
+
"eval_f1_weighted": 0.8030061499337195,
|
| 170 |
+
"eval_loss": 1.2181551456451416,
|
| 171 |
+
"eval_macro_fpr": 0.09161393040768498,
|
| 172 |
+
"eval_macro_sensitivity": 0.6398633163339046,
|
| 173 |
+
"eval_macro_specificity": 0.9204902964282863,
|
| 174 |
+
"eval_precision": 0.8065681635796801,
|
| 175 |
+
"eval_precision_macro": 0.6382217224720973,
|
| 176 |
+
"eval_recall": 0.8017817371937639,
|
| 177 |
+
"eval_recall_macro": 0.6398633163339046,
|
| 178 |
+
"eval_runtime": 38.5257,
|
| 179 |
+
"eval_samples_per_second": 11.655,
|
| 180 |
+
"eval_steps_per_second": 1.48,
|
| 181 |
+
"eval_weighted_fpr": 0.07613344739093242,
|
| 182 |
+
"eval_weighted_sensitivity": 0.8017817371937639,
|
| 183 |
+
"eval_weighted_specificity": 0.8801794485193812,
|
| 184 |
+
"step": 1568
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 8.0,
|
| 188 |
+
"eval_accuracy": 0.8285077951002228,
|
| 189 |
+
"eval_f1_macro": 0.6375618771468077,
|
| 190 |
+
"eval_f1_micro": 0.8285077951002228,
|
| 191 |
+
"eval_f1_weighted": 0.8152450374079808,
|
| 192 |
+
"eval_loss": 1.3192639350891113,
|
| 193 |
+
"eval_macro_fpr": 0.08815434538353528,
|
| 194 |
+
"eval_macro_sensitivity": 0.6279757603287015,
|
| 195 |
+
"eval_macro_specificity": 0.9201548104191046,
|
| 196 |
+
"eval_precision": 0.8069973553326301,
|
| 197 |
+
"eval_precision_macro": 0.6565998635009741,
|
| 198 |
+
"eval_recall": 0.8285077951002228,
|
| 199 |
+
"eval_recall_macro": 0.6279757603287015,
|
| 200 |
+
"eval_runtime": 33.4932,
|
| 201 |
+
"eval_samples_per_second": 13.406,
|
| 202 |
+
"eval_steps_per_second": 1.702,
|
| 203 |
+
"eval_weighted_fpr": 0.06454316848281642,
|
| 204 |
+
"eval_weighted_sensitivity": 0.8285077951002228,
|
| 205 |
+
"eval_weighted_specificity": 0.8521114465761961,
|
| 206 |
+
"step": 1792
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 8.93,
|
| 210 |
+
"grad_norm": 0.008128850720822811,
|
| 211 |
+
"learning_rate": 3.514880952380952e-05,
|
| 212 |
+
"loss": 0.0491,
|
| 213 |
+
"step": 2000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 9.0,
|
| 217 |
+
"eval_accuracy": 0.8329621380846325,
|
| 218 |
+
"eval_f1_macro": 0.6687059701183248,
|
| 219 |
+
"eval_f1_micro": 0.8329621380846325,
|
| 220 |
+
"eval_f1_weighted": 0.8234691462881575,
|
| 221 |
+
"eval_loss": 1.3168540000915527,
|
| 222 |
+
"eval_macro_fpr": 0.08276943574584078,
|
| 223 |
+
"eval_macro_sensitivity": 0.6554578833990599,
|
| 224 |
+
"eval_macro_specificity": 0.9245723745022232,
|
| 225 |
+
"eval_precision": 0.8179557632761028,
|
| 226 |
+
"eval_precision_macro": 0.6949834258114409,
|
| 227 |
+
"eval_recall": 0.8329621380846325,
|
| 228 |
+
"eval_recall_macro": 0.6554578833990599,
|
| 229 |
+
"eval_runtime": 36.7708,
|
| 230 |
+
"eval_samples_per_second": 12.211,
|
| 231 |
+
"eval_steps_per_second": 1.55,
|
| 232 |
+
"eval_weighted_fpr": 0.06265664160401002,
|
| 233 |
+
"eval_weighted_sensitivity": 0.8329621380846325,
|
| 234 |
+
"eval_weighted_specificity": 0.86532735992426,
|
| 235 |
+
"step": 2016
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 10.0,
|
| 239 |
+
"eval_accuracy": 0.8307349665924276,
|
| 240 |
+
"eval_f1_macro": 0.6397801007606054,
|
| 241 |
+
"eval_f1_micro": 0.8307349665924276,
|
| 242 |
+
"eval_f1_weighted": 0.8183915457597033,
|
| 243 |
+
"eval_loss": 1.4459574222564697,
|
| 244 |
+
"eval_macro_fpr": 0.08684003094467867,
|
| 245 |
+
"eval_macro_sensitivity": 0.6290898423251364,
|
| 246 |
+
"eval_macro_specificity": 0.9210102525156295,
|
| 247 |
+
"eval_precision": 0.8108965608714154,
|
| 248 |
+
"eval_precision_macro": 0.6584470636889992,
|
| 249 |
+
"eval_recall": 0.8307349665924276,
|
| 250 |
+
"eval_recall_macro": 0.6290898423251364,
|
| 251 |
+
"eval_runtime": 36.4367,
|
| 252 |
+
"eval_samples_per_second": 12.323,
|
| 253 |
+
"eval_steps_per_second": 1.564,
|
| 254 |
+
"eval_weighted_fpr": 0.06359832635983263,
|
| 255 |
+
"eval_weighted_sensitivity": 0.8307349665924276,
|
| 256 |
+
"eval_weighted_specificity": 0.8533060434700906,
|
| 257 |
+
"step": 2240
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 11.0,
|
| 261 |
+
"eval_accuracy": 0.8418708240534521,
|
| 262 |
+
"eval_f1_macro": 0.6463830564509832,
|
| 263 |
+
"eval_f1_micro": 0.8418708240534521,
|
| 264 |
+
"eval_f1_weighted": 0.8263008274936262,
|
| 265 |
+
"eval_loss": 1.4100018739700317,
|
| 266 |
+
"eval_macro_fpr": 0.08061341387649999,
|
| 267 |
+
"eval_macro_sensitivity": 0.6398590148590149,
|
| 268 |
+
"eval_macro_specificity": 0.9265216670805116,
|
| 269 |
+
"eval_precision": 0.8165947524130448,
|
| 270 |
+
"eval_precision_macro": 0.6717971143983426,
|
| 271 |
+
"eval_recall": 0.8418708240534521,
|
| 272 |
+
"eval_recall_macro": 0.6398590148590149,
|
| 273 |
+
"eval_runtime": 33.4877,
|
| 274 |
+
"eval_samples_per_second": 13.408,
|
| 275 |
+
"eval_steps_per_second": 1.702,
|
| 276 |
+
"eval_weighted_fpr": 0.05892116182572614,
|
| 277 |
+
"eval_weighted_sensitivity": 0.8418708240534521,
|
| 278 |
+
"eval_weighted_specificity": 0.8642158442685944,
|
| 279 |
+
"step": 2464
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 11.16,
|
| 283 |
+
"grad_norm": 0.002102190162986517,
|
| 284 |
+
"learning_rate": 3.143601190476191e-05,
|
| 285 |
+
"loss": 0.0148,
|
| 286 |
+
"step": 2500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 12.0,
|
| 290 |
+
"eval_accuracy": 0.821826280623608,
|
| 291 |
+
"eval_f1_macro": 0.6469130501099637,
|
| 292 |
+
"eval_f1_micro": 0.821826280623608,
|
| 293 |
+
"eval_f1_weighted": 0.8136991543918022,
|
| 294 |
+
"eval_loss": 1.5364338159561157,
|
| 295 |
+
"eval_macro_fpr": 0.09029608603507376,
|
| 296 |
+
"eval_macro_sensitivity": 0.6339926634044281,
|
| 297 |
+
"eval_macro_specificity": 0.918073461922396,
|
| 298 |
+
"eval_precision": 0.810454717235043,
|
| 299 |
+
"eval_precision_macro": 0.6661052171615551,
|
| 300 |
+
"eval_recall": 0.821826280623608,
|
| 301 |
+
"eval_recall_macro": 0.6339926634044281,
|
| 302 |
+
"eval_runtime": 39.7939,
|
| 303 |
+
"eval_samples_per_second": 11.283,
|
| 304 |
+
"eval_steps_per_second": 1.432,
|
| 305 |
+
"eval_weighted_fpr": 0.06739679865206402,
|
| 306 |
+
"eval_weighted_sensitivity": 0.821826280623608,
|
| 307 |
+
"eval_weighted_specificity": 0.8504675670659761,
|
| 308 |
+
"step": 2688
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 13.0,
|
| 312 |
+
"eval_accuracy": 0.8307349665924276,
|
| 313 |
+
"eval_f1_macro": 0.640882554945055,
|
| 314 |
+
"eval_f1_micro": 0.8307349665924276,
|
| 315 |
+
"eval_f1_weighted": 0.8185461995317229,
|
| 316 |
+
"eval_loss": 1.5380131006240845,
|
| 317 |
+
"eval_macro_fpr": 0.08703201531958343,
|
| 318 |
+
"eval_macro_sensitivity": 0.6304267407208584,
|
| 319 |
+
"eval_macro_specificity": 0.9204826437177868,
|
| 320 |
+
"eval_precision": 0.8117655167499301,
|
| 321 |
+
"eval_precision_macro": 0.6596365191762517,
|
| 322 |
+
"eval_recall": 0.8307349665924276,
|
| 323 |
+
"eval_recall_macro": 0.6304267407208584,
|
| 324 |
+
"eval_runtime": 33.439,
|
| 325 |
+
"eval_samples_per_second": 13.427,
|
| 326 |
+
"eval_steps_per_second": 1.705,
|
| 327 |
+
"eval_weighted_fpr": 0.06359832635983263,
|
| 328 |
+
"eval_weighted_sensitivity": 0.8307349665924276,
|
| 329 |
+
"eval_weighted_specificity": 0.8511956082787195,
|
| 330 |
+
"step": 2912
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 13.39,
|
| 334 |
+
"grad_norm": 0.0014135402161628008,
|
| 335 |
+
"learning_rate": 2.771577380952381e-05,
|
| 336 |
+
"loss": 0.0031,
|
| 337 |
+
"step": 3000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 14.0,
|
| 341 |
+
"eval_accuracy": 0.821826280623608,
|
| 342 |
+
"eval_f1_macro": 0.6395988579768073,
|
| 343 |
+
"eval_f1_micro": 0.821826280623608,
|
| 344 |
+
"eval_f1_weighted": 0.815862362792072,
|
| 345 |
+
"eval_loss": 1.6139171123504639,
|
| 346 |
+
"eval_macro_fpr": 0.08597973295573909,
|
| 347 |
+
"eval_macro_sensitivity": 0.6353312823901058,
|
| 348 |
+
"eval_macro_specificity": 0.9225779839960111,
|
| 349 |
+
"eval_precision": 0.8107609861928602,
|
| 350 |
+
"eval_precision_macro": 0.645071813948659,
|
| 351 |
+
"eval_recall": 0.821826280623608,
|
| 352 |
+
"eval_recall_macro": 0.6353312823901058,
|
| 353 |
+
"eval_runtime": 35.159,
|
| 354 |
+
"eval_samples_per_second": 12.771,
|
| 355 |
+
"eval_steps_per_second": 1.621,
|
| 356 |
+
"eval_weighted_fpr": 0.06739679865206402,
|
| 357 |
+
"eval_weighted_sensitivity": 0.821826280623608,
|
| 358 |
+
"eval_weighted_specificity": 0.8684856553604362,
|
| 359 |
+
"step": 3136
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 15.0,
|
| 363 |
+
"eval_accuracy": 0.8262806236080178,
|
| 364 |
+
"eval_f1_macro": 0.6528829170983883,
|
| 365 |
+
"eval_f1_micro": 0.8262806236080178,
|
| 366 |
+
"eval_f1_weighted": 0.8182677483705266,
|
| 367 |
+
"eval_loss": 1.6356003284454346,
|
| 368 |
+
"eval_macro_fpr": 0.08418800458446203,
|
| 369 |
+
"eval_macro_sensitivity": 0.6476601697189932,
|
| 370 |
+
"eval_macro_specificity": 0.9240743105590999,
|
| 371 |
+
"eval_precision": 0.8116961318417609,
|
| 372 |
+
"eval_precision_macro": 0.6625920024552541,
|
| 373 |
+
"eval_recall": 0.8262806236080178,
|
| 374 |
+
"eval_recall_macro": 0.6476601697189932,
|
| 375 |
+
"eval_runtime": 36.6347,
|
| 376 |
+
"eval_samples_per_second": 12.256,
|
| 377 |
+
"eval_steps_per_second": 1.556,
|
| 378 |
+
"eval_weighted_fpr": 0.0654911838790932,
|
| 379 |
+
"eval_weighted_sensitivity": 0.8262806236080178,
|
| 380 |
+
"eval_weighted_specificity": 0.870016618628382,
|
| 381 |
+
"step": 3360
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 15.62,
|
| 385 |
+
"grad_norm": 0.001976704690605402,
|
| 386 |
+
"learning_rate": 2.3995535714285717e-05,
|
| 387 |
+
"loss": 0.0043,
|
| 388 |
+
"step": 3500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 16.0,
|
| 392 |
+
"eval_accuracy": 0.8240534521158129,
|
| 393 |
+
"eval_f1_macro": 0.6230761302189873,
|
| 394 |
+
"eval_f1_micro": 0.8240534521158129,
|
| 395 |
+
"eval_f1_weighted": 0.8107699279191485,
|
| 396 |
+
"eval_loss": 1.6745187044143677,
|
| 397 |
+
"eval_macro_fpr": 0.08839478151630284,
|
| 398 |
+
"eval_macro_sensitivity": 0.6229266891031597,
|
| 399 |
+
"eval_macro_specificity": 0.9195796367703915,
|
| 400 |
+
"eval_precision": 0.7994292873051225,
|
| 401 |
+
"eval_precision_macro": 0.6243675595238095,
|
| 402 |
+
"eval_recall": 0.8240534521158129,
|
| 403 |
+
"eval_recall_macro": 0.6229266891031597,
|
| 404 |
+
"eval_runtime": 36.8951,
|
| 405 |
+
"eval_samples_per_second": 12.17,
|
| 406 |
+
"eval_steps_per_second": 1.545,
|
| 407 |
+
"eval_weighted_fpr": 0.06644238856181665,
|
| 408 |
+
"eval_weighted_sensitivity": 0.8240534521158129,
|
| 409 |
+
"eval_weighted_specificity": 0.8542650949657526,
|
| 410 |
+
"step": 3584
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 17.0,
|
| 414 |
+
"eval_accuracy": 0.8084632516703786,
|
| 415 |
+
"eval_f1_macro": 0.6229483308619814,
|
| 416 |
+
"eval_f1_micro": 0.8084632516703786,
|
| 417 |
+
"eval_f1_weighted": 0.7995562278022648,
|
| 418 |
+
"eval_loss": 1.7866648435592651,
|
| 419 |
+
"eval_macro_fpr": 0.0906391329862678,
|
| 420 |
+
"eval_macro_sensitivity": 0.6335504717857658,
|
| 421 |
+
"eval_macro_specificity": 0.9190564535065532,
|
| 422 |
+
"eval_precision": 0.7946422596815907,
|
| 423 |
+
"eval_precision_macro": 0.6220543197936814,
|
| 424 |
+
"eval_recall": 0.8084632516703786,
|
| 425 |
+
"eval_recall_macro": 0.6335504717857658,
|
| 426 |
+
"eval_runtime": 45.6812,
|
| 427 |
+
"eval_samples_per_second": 9.829,
|
| 428 |
+
"eval_steps_per_second": 1.248,
|
| 429 |
+
"eval_weighted_fpr": 0.07319148936170213,
|
| 430 |
+
"eval_weighted_sensitivity": 0.8084632516703786,
|
| 431 |
+
"eval_weighted_specificity": 0.867762562355834,
|
| 432 |
+
"step": 3808
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 17.86,
|
| 436 |
+
"grad_norm": 0.006524547468870878,
|
| 437 |
+
"learning_rate": 2.027529761904762e-05,
|
| 438 |
+
"loss": 0.0008,
|
| 439 |
+
"step": 4000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 18.0,
|
| 443 |
+
"eval_accuracy": 0.8151447661469933,
|
| 444 |
+
"eval_f1_macro": 0.6145391737322028,
|
| 445 |
+
"eval_f1_micro": 0.8151447661469933,
|
| 446 |
+
"eval_f1_weighted": 0.804610905907616,
|
| 447 |
+
"eval_loss": 1.751076102256775,
|
| 448 |
+
"eval_macro_fpr": 0.09007773933363768,
|
| 449 |
+
"eval_macro_sensitivity": 0.6215906510024157,
|
| 450 |
+
"eval_macro_specificity": 0.9198908245530938,
|
| 451 |
+
"eval_precision": 0.7971492204899776,
|
| 452 |
+
"eval_precision_macro": 0.6109523809523809,
|
| 453 |
+
"eval_recall": 0.8151447661469933,
|
| 454 |
+
"eval_recall_macro": 0.6215906510024157,
|
| 455 |
+
"eval_runtime": 38.3557,
|
| 456 |
+
"eval_samples_per_second": 11.706,
|
| 457 |
+
"eval_steps_per_second": 1.486,
|
| 458 |
+
"eval_weighted_fpr": 0.07027942421676546,
|
| 459 |
+
"eval_weighted_sensitivity": 0.8151447661469933,
|
| 460 |
+
"eval_weighted_specificity": 0.8644185320653821,
|
| 461 |
+
"step": 4032
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 19.0,
|
| 465 |
+
"eval_accuracy": 0.844097995545657,
|
| 466 |
+
"eval_f1_macro": 0.6311281016984356,
|
| 467 |
+
"eval_f1_micro": 0.844097995545657,
|
| 468 |
+
"eval_f1_weighted": 0.8249191682820878,
|
| 469 |
+
"eval_loss": 1.5909010171890259,
|
| 470 |
+
"eval_macro_fpr": 0.07919449683227583,
|
| 471 |
+
"eval_macro_sensitivity": 0.637408034466858,
|
| 472 |
+
"eval_macro_specificity": 0.9277706532935693,
|
| 473 |
+
"eval_precision": 0.807872223982319,
|
| 474 |
+
"eval_precision_macro": 0.6259502280219871,
|
| 475 |
+
"eval_recall": 0.844097995545657,
|
| 476 |
+
"eval_recall_macro": 0.637408034466858,
|
| 477 |
+
"eval_runtime": 36.5788,
|
| 478 |
+
"eval_samples_per_second": 12.275,
|
| 479 |
+
"eval_steps_per_second": 1.558,
|
| 480 |
+
"eval_weighted_fpr": 0.0579950289975145,
|
| 481 |
+
"eval_weighted_sensitivity": 0.844097995545657,
|
| 482 |
+
"eval_weighted_specificity": 0.8669846176286206,
|
| 483 |
+
"step": 4256
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 20.0,
|
| 487 |
+
"eval_accuracy": 0.8463251670378619,
|
| 488 |
+
"eval_f1_macro": 0.6547364441338015,
|
| 489 |
+
"eval_f1_micro": 0.8463251670378619,
|
| 490 |
+
"eval_f1_weighted": 0.8315565827780101,
|
| 491 |
+
"eval_loss": 1.5720769166946411,
|
| 492 |
+
"eval_macro_fpr": 0.07608631782920582,
|
| 493 |
+
"eval_macro_sensitivity": 0.654565757506934,
|
| 494 |
+
"eval_macro_specificity": 0.9304116223657872,
|
| 495 |
+
"eval_precision": 0.8212372897985063,
|
| 496 |
+
"eval_precision_macro": 0.6726868339007814,
|
| 497 |
+
"eval_recall": 0.8463251670378619,
|
| 498 |
+
"eval_recall_macro": 0.654565757506934,
|
| 499 |
+
"eval_runtime": 41.5006,
|
| 500 |
+
"eval_samples_per_second": 10.819,
|
| 501 |
+
"eval_steps_per_second": 1.373,
|
| 502 |
+
"eval_weighted_fpr": 0.05707196029776675,
|
| 503 |
+
"eval_weighted_sensitivity": 0.8463251670378619,
|
| 504 |
+
"eval_weighted_specificity": 0.8753213224252874,
|
| 505 |
+
"step": 4480
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 20.09,
|
| 509 |
+
"grad_norm": 0.0007016769959591329,
|
| 510 |
+
"learning_rate": 1.6555059523809523e-05,
|
| 511 |
+
"loss": 0.0039,
|
| 512 |
+
"step": 4500
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 21.0,
|
| 516 |
+
"eval_accuracy": 0.8396436525612472,
|
| 517 |
+
"eval_f1_macro": 0.6245224000790541,
|
| 518 |
+
"eval_f1_micro": 0.8396436525612472,
|
| 519 |
+
"eval_f1_weighted": 0.8198946368768828,
|
| 520 |
+
"eval_loss": 1.581870436668396,
|
| 521 |
+
"eval_macro_fpr": 0.08431444554533195,
|
| 522 |
+
"eval_macro_sensitivity": 0.6200274950274951,
|
| 523 |
+
"eval_macro_specificity": 0.9230817527274316,
|
| 524 |
+
"eval_precision": 0.805352891482989,
|
| 525 |
+
"eval_precision_macro": 0.6336598746081504,
|
| 526 |
+
"eval_recall": 0.8396436525612472,
|
| 527 |
+
"eval_recall_macro": 0.6200274950274951,
|
| 528 |
+
"eval_runtime": 40.6373,
|
| 529 |
+
"eval_samples_per_second": 11.049,
|
| 530 |
+
"eval_steps_per_second": 1.403,
|
| 531 |
+
"eval_weighted_fpr": 0.059850374064837904,
|
| 532 |
+
"eval_weighted_sensitivity": 0.8396436525612472,
|
| 533 |
+
"eval_weighted_specificity": 0.8526833583484795,
|
| 534 |
+
"step": 4704
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 22.0,
|
| 538 |
+
"eval_accuracy": 0.8485523385300668,
|
| 539 |
+
"eval_f1_macro": 0.6570090324388094,
|
| 540 |
+
"eval_f1_micro": 0.8485523385300668,
|
| 541 |
+
"eval_f1_weighted": 0.8332610613057768,
|
| 542 |
+
"eval_loss": 1.590599536895752,
|
| 543 |
+
"eval_macro_fpr": 0.07699645285854685,
|
| 544 |
+
"eval_macro_sensitivity": 0.6512226512226512,
|
| 545 |
+
"eval_macro_specificity": 0.9291429395829165,
|
| 546 |
+
"eval_precision": 0.8235592739775757,
|
| 547 |
+
"eval_precision_macro": 0.6814160825828637,
|
| 548 |
+
"eval_recall": 0.8485523385300668,
|
| 549 |
+
"eval_recall_macro": 0.6512226512226512,
|
| 550 |
+
"eval_runtime": 40.0378,
|
| 551 |
+
"eval_samples_per_second": 11.214,
|
| 552 |
+
"eval_steps_per_second": 1.424,
|
| 553 |
+
"eval_weighted_fpr": 0.05615194054500413,
|
| 554 |
+
"eval_weighted_sensitivity": 0.8485523385300668,
|
| 555 |
+
"eval_weighted_specificity": 0.8680194198015992,
|
| 556 |
+
"step": 4928
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 22.32,
|
| 560 |
+
"grad_norm": 0.0008124363957904279,
|
| 561 |
+
"learning_rate": 1.2834821428571428e-05,
|
| 562 |
+
"loss": 0.0005,
|
| 563 |
+
"step": 5000
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 23.0,
|
| 567 |
+
"eval_accuracy": 0.8262806236080178,
|
| 568 |
+
"eval_f1_macro": 0.6367361055170875,
|
| 569 |
+
"eval_f1_micro": 0.8262806236080178,
|
| 570 |
+
"eval_f1_weighted": 0.814300283167707,
|
| 571 |
+
"eval_loss": 1.7133090496063232,
|
| 572 |
+
"eval_macro_fpr": 0.08305536825615172,
|
| 573 |
+
"eval_macro_sensitivity": 0.6430558709970474,
|
| 574 |
+
"eval_macro_specificity": 0.9251990803757544,
|
| 575 |
+
"eval_precision": 0.8046809929872609,
|
| 576 |
+
"eval_precision_macro": 0.6403149200464413,
|
| 577 |
+
"eval_recall": 0.8262806236080178,
|
| 578 |
+
"eval_recall_macro": 0.6430558709970474,
|
| 579 |
+
"eval_runtime": 52.0234,
|
| 580 |
+
"eval_samples_per_second": 8.631,
|
| 581 |
+
"eval_steps_per_second": 1.096,
|
| 582 |
+
"eval_weighted_fpr": 0.0654911838790932,
|
| 583 |
+
"eval_weighted_sensitivity": 0.8262806236080178,
|
| 584 |
+
"eval_weighted_specificity": 0.8745156978949993,
|
| 585 |
+
"step": 5152
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 24.0,
|
| 589 |
+
"eval_accuracy": 0.8240534521158129,
|
| 590 |
+
"eval_f1_macro": 0.6347558645874186,
|
| 591 |
+
"eval_f1_micro": 0.8240534521158129,
|
| 592 |
+
"eval_f1_weighted": 0.810797465939838,
|
| 593 |
+
"eval_loss": 1.7812680006027222,
|
| 594 |
+
"eval_macro_fpr": 0.08937438461243138,
|
| 595 |
+
"eval_macro_sensitivity": 0.6290167172520114,
|
| 596 |
+
"eval_macro_specificity": 0.9182544571718577,
|
| 597 |
+
"eval_precision": 0.8021696990280875,
|
| 598 |
+
"eval_precision_macro": 0.6515469776148849,
|
| 599 |
+
"eval_recall": 0.8240534521158129,
|
| 600 |
+
"eval_recall_macro": 0.6290167172520114,
|
| 601 |
+
"eval_runtime": 37.1087,
|
| 602 |
+
"eval_samples_per_second": 12.1,
|
| 603 |
+
"eval_steps_per_second": 1.536,
|
| 604 |
+
"eval_weighted_fpr": 0.06644238856181665,
|
| 605 |
+
"eval_weighted_sensitivity": 0.8240534521158129,
|
| 606 |
+
"eval_weighted_specificity": 0.848964376571618,
|
| 607 |
+
"step": 5376
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 24.55,
|
| 611 |
+
"grad_norm": 0.00044807096128351986,
|
| 612 |
+
"learning_rate": 9.114583333333334e-06,
|
| 613 |
+
"loss": 0.0033,
|
| 614 |
+
"step": 5500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 25.0,
|
| 618 |
+
"eval_accuracy": 0.821826280623608,
|
| 619 |
+
"eval_f1_macro": 0.6327917307584591,
|
| 620 |
+
"eval_f1_micro": 0.821826280623608,
|
| 621 |
+
"eval_f1_weighted": 0.8087513198727686,
|
| 622 |
+
"eval_loss": 1.7982960939407349,
|
| 623 |
+
"eval_macro_fpr": 0.09016628720802765,
|
| 624 |
+
"eval_macro_sensitivity": 0.6280514662867603,
|
| 625 |
+
"eval_macro_specificity": 0.9176017156574975,
|
| 626 |
+
"eval_precision": 0.80013123038614,
|
| 627 |
+
"eval_precision_macro": 0.6484922578565337,
|
| 628 |
+
"eval_recall": 0.821826280623608,
|
| 629 |
+
"eval_recall_macro": 0.6280514662867603,
|
| 630 |
+
"eval_runtime": 38.9568,
|
| 631 |
+
"eval_samples_per_second": 11.526,
|
| 632 |
+
"eval_steps_per_second": 1.463,
|
| 633 |
+
"eval_weighted_fpr": 0.06739679865206402,
|
| 634 |
+
"eval_weighted_sensitivity": 0.821826280623608,
|
| 635 |
+
"eval_weighted_specificity": 0.8485805820063818,
|
| 636 |
+
"step": 5600
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 26.0,
|
| 640 |
+
"eval_accuracy": 0.821826280623608,
|
| 641 |
+
"eval_f1_macro": 0.6327917307584591,
|
| 642 |
+
"eval_f1_micro": 0.821826280623608,
|
| 643 |
+
"eval_f1_weighted": 0.8087513198727686,
|
| 644 |
+
"eval_loss": 1.807039499282837,
|
| 645 |
+
"eval_macro_fpr": 0.09016628720802765,
|
| 646 |
+
"eval_macro_sensitivity": 0.6280514662867603,
|
| 647 |
+
"eval_macro_specificity": 0.9176017156574975,
|
| 648 |
+
"eval_precision": 0.80013123038614,
|
| 649 |
+
"eval_precision_macro": 0.6484922578565337,
|
| 650 |
+
"eval_recall": 0.821826280623608,
|
| 651 |
+
"eval_recall_macro": 0.6280514662867603,
|
| 652 |
+
"eval_runtime": 36.8299,
|
| 653 |
+
"eval_samples_per_second": 12.191,
|
| 654 |
+
"eval_steps_per_second": 1.548,
|
| 655 |
+
"eval_weighted_fpr": 0.06739679865206402,
|
| 656 |
+
"eval_weighted_sensitivity": 0.821826280623608,
|
| 657 |
+
"eval_weighted_specificity": 0.8485805820063818,
|
| 658 |
+
"step": 5824
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 26.79,
|
| 662 |
+
"grad_norm": 0.06853985786437988,
|
| 663 |
+
"learning_rate": 5.394345238095239e-06,
|
| 664 |
+
"loss": 0.0,
|
| 665 |
+
"step": 6000
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 27.0,
|
| 669 |
+
"eval_accuracy": 0.821826280623608,
|
| 670 |
+
"eval_f1_macro": 0.6335334678819144,
|
| 671 |
+
"eval_f1_micro": 0.821826280623608,
|
| 672 |
+
"eval_f1_weighted": 0.8105761794538233,
|
| 673 |
+
"eval_loss": 1.8198280334472656,
|
| 674 |
+
"eval_macro_fpr": 0.08902145853933485,
|
| 675 |
+
"eval_macro_sensitivity": 0.6295371957136663,
|
| 676 |
+
"eval_macro_specificity": 0.9190623344175122,
|
| 677 |
+
"eval_precision": 0.8023633868156814,
|
| 678 |
+
"eval_precision_macro": 0.6439485798270974,
|
| 679 |
+
"eval_recall": 0.821826280623608,
|
| 680 |
+
"eval_recall_macro": 0.6295371957136663,
|
| 681 |
+
"eval_runtime": 38.8069,
|
| 682 |
+
"eval_samples_per_second": 11.57,
|
| 683 |
+
"eval_steps_per_second": 1.469,
|
| 684 |
+
"eval_weighted_fpr": 0.06739679865206402,
|
| 685 |
+
"eval_weighted_sensitivity": 0.821826280623608,
|
| 686 |
+
"eval_weighted_specificity": 0.8544230570464407,
|
| 687 |
+
"step": 6048
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 28.0,
|
| 691 |
+
"eval_accuracy": 0.821826280623608,
|
| 692 |
+
"eval_f1_macro": 0.6335334678819144,
|
| 693 |
+
"eval_f1_micro": 0.821826280623608,
|
| 694 |
+
"eval_f1_weighted": 0.8105761794538233,
|
| 695 |
+
"eval_loss": 1.8243361711502075,
|
| 696 |
+
"eval_macro_fpr": 0.08902145853933485,
|
| 697 |
+
"eval_macro_sensitivity": 0.6295371957136663,
|
| 698 |
+
"eval_macro_specificity": 0.9190623344175122,
|
| 699 |
+
"eval_precision": 0.8023633868156814,
|
| 700 |
+
"eval_precision_macro": 0.6439485798270974,
|
| 701 |
+
"eval_recall": 0.821826280623608,
|
| 702 |
+
"eval_recall_macro": 0.6295371957136663,
|
| 703 |
+
"eval_runtime": 43.8782,
|
| 704 |
+
"eval_samples_per_second": 10.233,
|
| 705 |
+
"eval_steps_per_second": 1.299,
|
| 706 |
+
"eval_weighted_fpr": 0.06739679865206402,
|
| 707 |
+
"eval_weighted_sensitivity": 0.821826280623608,
|
| 708 |
+
"eval_weighted_specificity": 0.8544230570464407,
|
| 709 |
+
"step": 6272
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 29.0,
|
| 713 |
+
"eval_accuracy": 0.821826280623608,
|
| 714 |
+
"eval_f1_macro": 0.6335334678819144,
|
| 715 |
+
"eval_f1_micro": 0.821826280623608,
|
| 716 |
+
"eval_f1_weighted": 0.8105761794538233,
|
| 717 |
+
"eval_loss": 1.827745795249939,
|
| 718 |
+
"eval_macro_fpr": 0.08902145853933485,
|
| 719 |
+
"eval_macro_sensitivity": 0.6295371957136663,
|
| 720 |
+
"eval_macro_specificity": 0.9190623344175122,
|
| 721 |
+
"eval_precision": 0.8023633868156814,
|
| 722 |
+
"eval_precision_macro": 0.6439485798270974,
|
| 723 |
+
"eval_recall": 0.821826280623608,
|
| 724 |
+
"eval_recall_macro": 0.6295371957136663,
|
| 725 |
+
"eval_runtime": 32.6221,
|
| 726 |
+
"eval_samples_per_second": 13.764,
|
| 727 |
+
"eval_steps_per_second": 1.747,
|
| 728 |
+
"eval_weighted_fpr": 0.06739679865206402,
|
| 729 |
+
"eval_weighted_sensitivity": 0.821826280623608,
|
| 730 |
+
"eval_weighted_specificity": 0.8544230570464407,
|
| 731 |
+
"step": 6496
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 29.02,
|
| 735 |
+
"grad_norm": 0.00035208536428399384,
|
| 736 |
+
"learning_rate": 1.681547619047619e-06,
|
| 737 |
+
"loss": 0.0003,
|
| 738 |
+
"step": 6500
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 30.0,
|
| 742 |
+
"eval_accuracy": 0.821826280623608,
|
| 743 |
+
"eval_f1_macro": 0.6335334678819144,
|
| 744 |
+
"eval_f1_micro": 0.821826280623608,
|
| 745 |
+
"eval_f1_weighted": 0.8105761794538233,
|
| 746 |
+
"eval_loss": 1.82924485206604,
|
| 747 |
+
"eval_macro_fpr": 0.08902145853933485,
|
| 748 |
+
"eval_macro_sensitivity": 0.6295371957136663,
|
| 749 |
+
"eval_macro_specificity": 0.9190623344175122,
|
| 750 |
+
"eval_precision": 0.8023633868156814,
|
| 751 |
+
"eval_precision_macro": 0.6439485798270974,
|
| 752 |
+
"eval_recall": 0.821826280623608,
|
| 753 |
+
"eval_recall_macro": 0.6295371957136663,
|
| 754 |
+
"eval_runtime": 41.8213,
|
| 755 |
+
"eval_samples_per_second": 10.736,
|
| 756 |
+
"eval_steps_per_second": 1.363,
|
| 757 |
+
"eval_weighted_fpr": 0.06739679865206402,
|
| 758 |
+
"eval_weighted_sensitivity": 0.821826280623608,
|
| 759 |
+
"eval_weighted_specificity": 0.8544230570464407,
|
| 760 |
+
"step": 6720
|
| 761 |
+
}
|
| 762 |
+
],
|
| 763 |
+
"logging_steps": 500,
|
| 764 |
+
"max_steps": 6720,
|
| 765 |
+
"num_input_tokens_seen": 0,
|
| 766 |
+
"num_train_epochs": 30,
|
| 767 |
+
"save_steps": 500,
|
| 768 |
+
"total_flos": 1.414510433796096e+16,
|
| 769 |
+
"train_batch_size": 8,
|
| 770 |
+
"trial_name": null,
|
| 771 |
+
"trial_params": null
|
| 772 |
+
}
|
training_checkpoints/checkpoint-6720/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4168c8c84941deb81d05fe2d714c7e20c482e1e8b4900f8d6b307d6f8c3828dd
|
| 3 |
+
size 4984
|
training_checkpoints/checkpoint-6720/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|