Upload folder using huggingface_hub
Browse files- config.json +30 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +982 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "FacebookAI/roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForPromptBasedMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"label_no": 117,
|
| 16 |
+
"label_yes": 4420,
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"mask_token_id": 50264,
|
| 19 |
+
"max_position_embeddings": 514,
|
| 20 |
+
"model_type": "roberta",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 1,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.39.1",
|
| 27 |
+
"type_vocab_size": 1,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 50265
|
| 30 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7c75d446326cc4975520c68e71fb94851c5a7db737789e8556e0c774bf4b351
|
| 3 |
+
size 498813948
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db5286950968693c0b249ac8534351b302ffd83069f619aa0c0c271dde0739c9
|
| 3 |
+
size 997748346
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:380cf0998f0477b2aef8b53857d5d105c844a6860cffca7a866e1365f5770c2c
|
| 3 |
+
size 14180
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed72818eec59ff3fff91411ab558b4d4769f66989dcb0544dfcf05c77a40ede6
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,982 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9205694310134601,
|
| 3 |
+
"best_model_checkpoint": "./saved_models/roberta_prompt_sbdh_gpt4_v2_0/checkpoint-744",
|
| 4 |
+
"epoch": 31.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 744,
|
| 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 |
+
"grad_norm": 1.8722108602523804,
|
| 14 |
+
"learning_rate": 2.5e-06,
|
| 15 |
+
"loss": 0.7199,
|
| 16 |
+
"step": 24
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_acc_macro": 0.07035287889134419,
|
| 21 |
+
"eval_acc_micro": 0.15675280351047888,
|
| 22 |
+
"eval_auc_macro": 0.663313870197172,
|
| 23 |
+
"eval_auc_micro": 0.6559659079771284,
|
| 24 |
+
"eval_f1_at_5": 0.2619950790125531,
|
| 25 |
+
"eval_f1_at_8": 0.24094809864446162,
|
| 26 |
+
"eval_f1_macro": 0.11929565026205535,
|
| 27 |
+
"eval_f1_micro": 0.2710221285563637,
|
| 28 |
+
"eval_loss": 0.3433417081832886,
|
| 29 |
+
"eval_prec_at_5": 0.1684931506849315,
|
| 30 |
+
"eval_prec_at_8": 0.14169520547945205,
|
| 31 |
+
"eval_prec_macro": 0.11362671803403451,
|
| 32 |
+
"eval_prec_micro": 0.18168974286521103,
|
| 33 |
+
"eval_rec_at_5": 0.5886605783866058,
|
| 34 |
+
"eval_rec_at_8": 0.8044140030441401,
|
| 35 |
+
"eval_rec_macro": 0.3442251461985764,
|
| 36 |
+
"eval_rec_micro": 0.5331674958540188,
|
| 37 |
+
"eval_runtime": 6.2217,
|
| 38 |
+
"eval_samples_per_second": 140.798,
|
| 39 |
+
"eval_steps_per_second": 17.68,
|
| 40 |
+
"step": 24
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 2.0,
|
| 44 |
+
"grad_norm": 5.086896896362305,
|
| 45 |
+
"learning_rate": 5e-06,
|
| 46 |
+
"loss": 0.3297,
|
| 47 |
+
"step": 48
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.0,
|
| 51 |
+
"eval_acc_macro": 0.5110805606565244,
|
| 52 |
+
"eval_acc_micro": 0.543895747599414,
|
| 53 |
+
"eval_auc_macro": 0.9371959387131173,
|
| 54 |
+
"eval_auc_micro": 0.9373504192626666,
|
| 55 |
+
"eval_f1_at_5": 0.4096411096246807,
|
| 56 |
+
"eval_f1_at_8": 0.2899510119744706,
|
| 57 |
+
"eval_f1_macro": 0.6473524785746846,
|
| 58 |
+
"eval_f1_micro": 0.7045757441136646,
|
| 59 |
+
"eval_loss": 0.1864374279975891,
|
| 60 |
+
"eval_prec_at_5": 0.2621004566210046,
|
| 61 |
+
"eval_prec_at_8": 0.1703767123287671,
|
| 62 |
+
"eval_prec_macro": 0.8055450466236987,
|
| 63 |
+
"eval_prec_micro": 0.7588516746410757,
|
| 64 |
+
"eval_rec_at_5": 0.9372146118721462,
|
| 65 |
+
"eval_rec_at_8": 0.9724124809741247,
|
| 66 |
+
"eval_rec_macro": 0.6042332875883025,
|
| 67 |
+
"eval_rec_micro": 0.6575456053067448,
|
| 68 |
+
"eval_runtime": 6.2474,
|
| 69 |
+
"eval_samples_per_second": 140.219,
|
| 70 |
+
"eval_steps_per_second": 17.607,
|
| 71 |
+
"step": 48
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.0,
|
| 75 |
+
"grad_norm": 1.4806246757507324,
|
| 76 |
+
"learning_rate": 7.500000000000001e-06,
|
| 77 |
+
"loss": 0.1717,
|
| 78 |
+
"step": 72
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.0,
|
| 82 |
+
"eval_acc_macro": 0.7353572773142955,
|
| 83 |
+
"eval_acc_micro": 0.7442348008385224,
|
| 84 |
+
"eval_auc_macro": 0.9820663738220755,
|
| 85 |
+
"eval_auc_micro": 0.9835785967362127,
|
| 86 |
+
"eval_f1_at_5": 0.42686614175859805,
|
| 87 |
+
"eval_f1_at_8": 0.2922793659426448,
|
| 88 |
+
"eval_f1_macro": 0.841220323579556,
|
| 89 |
+
"eval_f1_micro": 0.8533653846153163,
|
| 90 |
+
"eval_loss": 0.1064019426703453,
|
| 91 |
+
"eval_prec_at_5": 0.2732876712328767,
|
| 92 |
+
"eval_prec_at_8": 0.17180365296803654,
|
| 93 |
+
"eval_prec_macro": 0.8250237186513111,
|
| 94 |
+
"eval_prec_micro": 0.8255813953487732,
|
| 95 |
+
"eval_rec_at_5": 0.9745053272450532,
|
| 96 |
+
"eval_rec_at_8": 0.978310502283105,
|
| 97 |
+
"eval_rec_macro": 0.8662646242524481,
|
| 98 |
+
"eval_rec_micro": 0.8830845771143546,
|
| 99 |
+
"eval_runtime": 6.1744,
|
| 100 |
+
"eval_samples_per_second": 141.876,
|
| 101 |
+
"eval_steps_per_second": 17.815,
|
| 102 |
+
"step": 72
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 4.0,
|
| 106 |
+
"grad_norm": 1.224611759185791,
|
| 107 |
+
"learning_rate": 1e-05,
|
| 108 |
+
"loss": 0.0995,
|
| 109 |
+
"step": 96
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 4.0,
|
| 113 |
+
"eval_acc_macro": 0.801538415253349,
|
| 114 |
+
"eval_acc_micro": 0.8093126385808714,
|
| 115 |
+
"eval_auc_macro": 0.989204170129788,
|
| 116 |
+
"eval_auc_micro": 0.9911075755259093,
|
| 117 |
+
"eval_f1_at_5": 0.4288655829720509,
|
| 118 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 119 |
+
"eval_f1_macro": 0.8875969325055185,
|
| 120 |
+
"eval_f1_micro": 0.8946078431371818,
|
| 121 |
+
"eval_loss": 0.07651617377996445,
|
| 122 |
+
"eval_prec_at_5": 0.27465753424657535,
|
| 123 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 124 |
+
"eval_prec_macro": 0.881843938607854,
|
| 125 |
+
"eval_prec_micro": 0.8816425120772237,
|
| 126 |
+
"eval_rec_at_5": 0.9779299847792998,
|
| 127 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 128 |
+
"eval_rec_macro": 0.8961158899484207,
|
| 129 |
+
"eval_rec_micro": 0.9079601990048998,
|
| 130 |
+
"eval_runtime": 6.2178,
|
| 131 |
+
"eval_samples_per_second": 140.886,
|
| 132 |
+
"eval_steps_per_second": 17.691,
|
| 133 |
+
"step": 96
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 5.0,
|
| 137 |
+
"grad_norm": 1.1437005996704102,
|
| 138 |
+
"learning_rate": 9.722222222222223e-06,
|
| 139 |
+
"loss": 0.0805,
|
| 140 |
+
"step": 120
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 5.0,
|
| 144 |
+
"eval_acc_macro": 0.8121493747200438,
|
| 145 |
+
"eval_acc_micro": 0.8208841463414008,
|
| 146 |
+
"eval_auc_macro": 0.991491527290926,
|
| 147 |
+
"eval_auc_micro": 0.9929716878748317,
|
| 148 |
+
"eval_f1_at_5": 0.4291987915672543,
|
| 149 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 150 |
+
"eval_f1_macro": 0.8934495150714268,
|
| 151 |
+
"eval_f1_micro": 0.9016324822100543,
|
| 152 |
+
"eval_loss": 0.06796517223119736,
|
| 153 |
+
"eval_prec_at_5": 0.27488584474885847,
|
| 154 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 155 |
+
"eval_prec_macro": 0.901996461034861,
|
| 156 |
+
"eval_prec_micro": 0.9103972950126027,
|
| 157 |
+
"eval_rec_at_5": 0.9785007610350076,
|
| 158 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 159 |
+
"eval_rec_macro": 0.8880403796830154,
|
| 160 |
+
"eval_rec_micro": 0.8930348258705727,
|
| 161 |
+
"eval_runtime": 6.2151,
|
| 162 |
+
"eval_samples_per_second": 140.947,
|
| 163 |
+
"eval_steps_per_second": 17.699,
|
| 164 |
+
"step": 120
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 6.0,
|
| 168 |
+
"grad_norm": 2.1739773750305176,
|
| 169 |
+
"learning_rate": 9.444444444444445e-06,
|
| 170 |
+
"loss": 0.0718,
|
| 171 |
+
"step": 144
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 6.0,
|
| 175 |
+
"eval_acc_macro": 0.828523573268117,
|
| 176 |
+
"eval_acc_micro": 0.8335843373493348,
|
| 177 |
+
"eval_auc_macro": 0.9925057744832354,
|
| 178 |
+
"eval_auc_micro": 0.9937106144896979,
|
| 179 |
+
"eval_f1_at_5": 0.4291987915672543,
|
| 180 |
+
"eval_f1_at_8": 0.2925113305987028,
|
| 181 |
+
"eval_f1_macro": 0.9041659334919602,
|
| 182 |
+
"eval_f1_micro": 0.9092402464064961,
|
| 183 |
+
"eval_loss": 0.06353675574064255,
|
| 184 |
+
"eval_prec_at_5": 0.27488584474885847,
|
| 185 |
+
"eval_prec_at_8": 0.17194634703196346,
|
| 186 |
+
"eval_prec_macro": 0.8956330448729077,
|
| 187 |
+
"eval_prec_micro": 0.9007323026850366,
|
| 188 |
+
"eval_rec_at_5": 0.9785007610350076,
|
| 189 |
+
"eval_rec_at_8": 0.9788812785388128,
|
| 190 |
+
"eval_rec_macro": 0.9145914149826037,
|
| 191 |
+
"eval_rec_micro": 0.9179104477611179,
|
| 192 |
+
"eval_runtime": 6.2166,
|
| 193 |
+
"eval_samples_per_second": 140.913,
|
| 194 |
+
"eval_steps_per_second": 17.695,
|
| 195 |
+
"step": 144
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 7.0,
|
| 199 |
+
"grad_norm": 1.558062195777893,
|
| 200 |
+
"learning_rate": 9.166666666666666e-06,
|
| 201 |
+
"loss": 0.0669,
|
| 202 |
+
"step": 168
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 7.0,
|
| 206 |
+
"eval_acc_macro": 0.8323133875195107,
|
| 207 |
+
"eval_acc_micro": 0.8400918133128661,
|
| 208 |
+
"eval_auc_macro": 0.9934557716722295,
|
| 209 |
+
"eval_auc_micro": 0.9948184252460742,
|
| 210 |
+
"eval_f1_at_5": 0.4291987915672543,
|
| 211 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 212 |
+
"eval_f1_macro": 0.9059398386358487,
|
| 213 |
+
"eval_f1_micro": 0.913097713097637,
|
| 214 |
+
"eval_loss": 0.06089127063751221,
|
| 215 |
+
"eval_prec_at_5": 0.27488584474885847,
|
| 216 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 217 |
+
"eval_prec_macro": 0.9108588887690331,
|
| 218 |
+
"eval_prec_micro": 0.9157631359465458,
|
| 219 |
+
"eval_rec_at_5": 0.9785007610350076,
|
| 220 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 221 |
+
"eval_rec_macro": 0.9032889716188378,
|
| 222 |
+
"eval_rec_micro": 0.9104477611939543,
|
| 223 |
+
"eval_runtime": 6.2143,
|
| 224 |
+
"eval_samples_per_second": 140.965,
|
| 225 |
+
"eval_steps_per_second": 17.701,
|
| 226 |
+
"step": 168
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 8.0,
|
| 230 |
+
"grad_norm": 1.132032871246338,
|
| 231 |
+
"learning_rate": 8.888888888888888e-06,
|
| 232 |
+
"loss": 0.0611,
|
| 233 |
+
"step": 192
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 8.0,
|
| 237 |
+
"eval_acc_macro": 0.8399125580413327,
|
| 238 |
+
"eval_acc_micro": 0.8451563691837647,
|
| 239 |
+
"eval_auc_macro": 0.9939843717869511,
|
| 240 |
+
"eval_auc_micro": 0.9950275486953798,
|
| 241 |
+
"eval_f1_at_5": 0.4291987915672543,
|
| 242 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 243 |
+
"eval_f1_macro": 0.9107249879766437,
|
| 244 |
+
"eval_f1_micro": 0.916081025216956,
|
| 245 |
+
"eval_loss": 0.06228514760732651,
|
| 246 |
+
"eval_prec_at_5": 0.27488584474885847,
|
| 247 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 248 |
+
"eval_prec_macro": 0.9075154035613321,
|
| 249 |
+
"eval_prec_micro": 0.913437757625646,
|
| 250 |
+
"eval_rec_at_5": 0.9785007610350076,
|
| 251 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 252 |
+
"eval_rec_macro": 0.9155563129570495,
|
| 253 |
+
"eval_rec_micro": 0.9187396351574694,
|
| 254 |
+
"eval_runtime": 6.1966,
|
| 255 |
+
"eval_samples_per_second": 141.368,
|
| 256 |
+
"eval_steps_per_second": 17.752,
|
| 257 |
+
"step": 192
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 9.0,
|
| 261 |
+
"grad_norm": 0.9028905034065247,
|
| 262 |
+
"learning_rate": 8.611111111111112e-06,
|
| 263 |
+
"loss": 0.0561,
|
| 264 |
+
"step": 216
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 9.0,
|
| 268 |
+
"eval_acc_macro": 0.8453726969988299,
|
| 269 |
+
"eval_acc_micro": 0.850689127105601,
|
| 270 |
+
"eval_auc_macro": 0.9944939772465632,
|
| 271 |
+
"eval_auc_micro": 0.9954155898635628,
|
| 272 |
+
"eval_f1_at_5": 0.4291987915672543,
|
| 273 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 274 |
+
"eval_f1_macro": 0.914643073353695,
|
| 275 |
+
"eval_f1_micro": 0.9193214729002135,
|
| 276 |
+
"eval_loss": 0.05663854256272316,
|
| 277 |
+
"eval_prec_at_5": 0.27488584474885847,
|
| 278 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 279 |
+
"eval_prec_macro": 0.9126789502644125,
|
| 280 |
+
"eval_prec_micro": 0.9174236168455063,
|
| 281 |
+
"eval_rec_at_5": 0.9785007610350076,
|
| 282 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 283 |
+
"eval_rec_macro": 0.9185389204843853,
|
| 284 |
+
"eval_rec_micro": 0.9212271973465239,
|
| 285 |
+
"eval_runtime": 6.145,
|
| 286 |
+
"eval_samples_per_second": 142.554,
|
| 287 |
+
"eval_steps_per_second": 17.901,
|
| 288 |
+
"step": 216
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 10.0,
|
| 292 |
+
"grad_norm": 1.0204308032989502,
|
| 293 |
+
"learning_rate": 8.333333333333334e-06,
|
| 294 |
+
"loss": 0.0535,
|
| 295 |
+
"step": 240
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 10.0,
|
| 299 |
+
"eval_acc_macro": 0.8498863755077791,
|
| 300 |
+
"eval_acc_micro": 0.858365758754797,
|
| 301 |
+
"eval_auc_macro": 0.9946638093104078,
|
| 302 |
+
"eval_auc_micro": 0.9956081402572352,
|
| 303 |
+
"eval_f1_at_5": 0.4291987915672543,
|
| 304 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 305 |
+
"eval_f1_macro": 0.916676493616951,
|
| 306 |
+
"eval_f1_micro": 0.9237855946397886,
|
| 307 |
+
"eval_loss": 0.05517387017607689,
|
| 308 |
+
"eval_prec_at_5": 0.27488584474885847,
|
| 309 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 310 |
+
"eval_prec_macro": 0.9255652453336515,
|
| 311 |
+
"eval_prec_micro": 0.9331641285955217,
|
| 312 |
+
"eval_rec_at_5": 0.9785007610350076,
|
| 313 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 314 |
+
"eval_rec_macro": 0.9088352191837838,
|
| 315 |
+
"eval_rec_micro": 0.9145936981757119,
|
| 316 |
+
"eval_runtime": 6.1446,
|
| 317 |
+
"eval_samples_per_second": 142.564,
|
| 318 |
+
"eval_steps_per_second": 17.902,
|
| 319 |
+
"step": 240
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 11.0,
|
| 323 |
+
"grad_norm": 1.0917142629623413,
|
| 324 |
+
"learning_rate": 8.055555555555557e-06,
|
| 325 |
+
"loss": 0.0501,
|
| 326 |
+
"step": 264
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 11.0,
|
| 330 |
+
"eval_acc_macro": 0.8493708087290419,
|
| 331 |
+
"eval_acc_micro": 0.8584758942456564,
|
| 332 |
+
"eval_auc_macro": 0.9949027930572298,
|
| 333 |
+
"eval_auc_micro": 0.9961340229150117,
|
| 334 |
+
"eval_f1_at_5": 0.4295319911779049,
|
| 335 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 336 |
+
"eval_f1_macro": 0.9165770410883837,
|
| 337 |
+
"eval_f1_micro": 0.92384937238486,
|
| 338 |
+
"eval_loss": 0.05478766933083534,
|
| 339 |
+
"eval_prec_at_5": 0.2751141552511416,
|
| 340 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 341 |
+
"eval_prec_macro": 0.9246420093584519,
|
| 342 |
+
"eval_prec_micro": 0.9324324324323536,
|
| 343 |
+
"eval_rec_at_5": 0.9790715372907153,
|
| 344 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 345 |
+
"eval_rec_macro": 0.9096237229214146,
|
| 346 |
+
"eval_rec_micro": 0.9154228855720634,
|
| 347 |
+
"eval_runtime": 6.1786,
|
| 348 |
+
"eval_samples_per_second": 141.779,
|
| 349 |
+
"eval_steps_per_second": 17.803,
|
| 350 |
+
"step": 264
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 12.0,
|
| 354 |
+
"grad_norm": 1.1021435260772705,
|
| 355 |
+
"learning_rate": 7.77777777777778e-06,
|
| 356 |
+
"loss": 0.0474,
|
| 357 |
+
"step": 288
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 12.0,
|
| 361 |
+
"eval_acc_macro": 0.8453196602235581,
|
| 362 |
+
"eval_acc_micro": 0.856143079315641,
|
| 363 |
+
"eval_auc_macro": 0.9949355514759608,
|
| 364 |
+
"eval_auc_micro": 0.9959768461938463,
|
| 365 |
+
"eval_f1_at_5": 0.4291987915672543,
|
| 366 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 367 |
+
"eval_f1_macro": 0.9135326281320886,
|
| 368 |
+
"eval_f1_micro": 0.9224968579806515,
|
| 369 |
+
"eval_loss": 0.05536971986293793,
|
| 370 |
+
"eval_prec_at_5": 0.27488584474885847,
|
| 371 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 372 |
+
"eval_prec_macro": 0.9280234523786058,
|
| 373 |
+
"eval_prec_micro": 0.9322607959355688,
|
| 374 |
+
"eval_rec_at_5": 0.9785007610350076,
|
| 375 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 376 |
+
"eval_rec_macro": 0.9026177068383121,
|
| 377 |
+
"eval_rec_micro": 0.9129353233830089,
|
| 378 |
+
"eval_runtime": 6.2635,
|
| 379 |
+
"eval_samples_per_second": 139.858,
|
| 380 |
+
"eval_steps_per_second": 17.562,
|
| 381 |
+
"step": 288
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 13.0,
|
| 385 |
+
"grad_norm": 1.661024570465088,
|
| 386 |
+
"learning_rate": 7.500000000000001e-06,
|
| 387 |
+
"loss": 0.0456,
|
| 388 |
+
"step": 312
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 13.0,
|
| 392 |
+
"eval_acc_macro": 0.8539896866112132,
|
| 393 |
+
"eval_acc_micro": 0.8623924941359763,
|
| 394 |
+
"eval_auc_macro": 0.9951266438356762,
|
| 395 |
+
"eval_auc_micro": 0.9960736114541555,
|
| 396 |
+
"eval_f1_at_5": 0.42918048633589306,
|
| 397 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 398 |
+
"eval_f1_macro": 0.9193621316490773,
|
| 399 |
+
"eval_f1_micro": 0.9261125104953043,
|
| 400 |
+
"eval_loss": 0.05397089943289757,
|
| 401 |
+
"eval_prec_at_5": 0.27488584474885847,
|
| 402 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 403 |
+
"eval_prec_macro": 0.9310933950333862,
|
| 404 |
+
"eval_prec_micro": 0.9379251700679474,
|
| 405 |
+
"eval_rec_at_5": 0.978310502283105,
|
| 406 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 407 |
+
"eval_rec_macro": 0.9090157207820031,
|
| 408 |
+
"eval_rec_micro": 0.9145936981757119,
|
| 409 |
+
"eval_runtime": 6.188,
|
| 410 |
+
"eval_samples_per_second": 141.564,
|
| 411 |
+
"eval_steps_per_second": 17.776,
|
| 412 |
+
"step": 312
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 14.0,
|
| 416 |
+
"grad_norm": 1.8844163417816162,
|
| 417 |
+
"learning_rate": 7.222222222222223e-06,
|
| 418 |
+
"loss": 0.0448,
|
| 419 |
+
"step": 336
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 14.0,
|
| 423 |
+
"eval_acc_macro": 0.8471019101615411,
|
| 424 |
+
"eval_acc_micro": 0.8584831899921143,
|
| 425 |
+
"eval_auc_macro": 0.9954775103594954,
|
| 426 |
+
"eval_auc_micro": 0.9964240959398153,
|
| 427 |
+
"eval_f1_at_5": 0.4295319911779049,
|
| 428 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 429 |
+
"eval_f1_macro": 0.9145784925942765,
|
| 430 |
+
"eval_f1_micro": 0.9238535969708941,
|
| 431 |
+
"eval_loss": 0.05232784524559975,
|
| 432 |
+
"eval_prec_at_5": 0.2751141552511416,
|
| 433 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 434 |
+
"eval_prec_macro": 0.9310832701535142,
|
| 435 |
+
"eval_prec_micro": 0.937660119555855,
|
| 436 |
+
"eval_rec_at_5": 0.9790715372907153,
|
| 437 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 438 |
+
"eval_rec_macro": 0.900954322532269,
|
| 439 |
+
"eval_rec_micro": 0.9104477611939543,
|
| 440 |
+
"eval_runtime": 6.196,
|
| 441 |
+
"eval_samples_per_second": 141.382,
|
| 442 |
+
"eval_steps_per_second": 17.753,
|
| 443 |
+
"step": 336
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 15.0,
|
| 447 |
+
"grad_norm": 1.3576740026474,
|
| 448 |
+
"learning_rate": 6.944444444444445e-06,
|
| 449 |
+
"loss": 0.0425,
|
| 450 |
+
"step": 360
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 15.0,
|
| 454 |
+
"eval_acc_macro": 0.8512337950118664,
|
| 455 |
+
"eval_acc_micro": 0.8615863141523435,
|
| 456 |
+
"eval_auc_macro": 0.9951475121132285,
|
| 457 |
+
"eval_auc_micro": 0.9962107846753767,
|
| 458 |
+
"eval_f1_at_5": 0.4295319911779049,
|
| 459 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 460 |
+
"eval_f1_macro": 0.9173794915227328,
|
| 461 |
+
"eval_f1_micro": 0.925647451963164,
|
| 462 |
+
"eval_loss": 0.053657278418540955,
|
| 463 |
+
"eval_prec_at_5": 0.2751141552511416,
|
| 464 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 465 |
+
"eval_prec_macro": 0.9267018062985609,
|
| 466 |
+
"eval_prec_micro": 0.9326599326598541,
|
| 467 |
+
"eval_rec_at_5": 0.9790715372907153,
|
| 468 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 469 |
+
"eval_rec_macro": 0.9096846119468953,
|
| 470 |
+
"eval_rec_micro": 0.9187396351574694,
|
| 471 |
+
"eval_runtime": 6.1516,
|
| 472 |
+
"eval_samples_per_second": 142.402,
|
| 473 |
+
"eval_steps_per_second": 17.882,
|
| 474 |
+
"step": 360
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 16.0,
|
| 478 |
+
"grad_norm": 0.7812018990516663,
|
| 479 |
+
"learning_rate": 6.666666666666667e-06,
|
| 480 |
+
"loss": 0.0402,
|
| 481 |
+
"step": 384
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 16.0,
|
| 485 |
+
"eval_acc_macro": 0.8482275698613361,
|
| 486 |
+
"eval_acc_micro": 0.861502347417773,
|
| 487 |
+
"eval_auc_macro": 0.9952181846925838,
|
| 488 |
+
"eval_auc_micro": 0.9963574918587093,
|
| 489 |
+
"eval_f1_at_5": 0.4298468624753246,
|
| 490 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 491 |
+
"eval_f1_macro": 0.9150689476603097,
|
| 492 |
+
"eval_f1_micro": 0.9255989911726837,
|
| 493 |
+
"eval_loss": 0.055027130991220474,
|
| 494 |
+
"eval_prec_at_5": 0.2753424657534247,
|
| 495 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 496 |
+
"eval_prec_macro": 0.9321798187054336,
|
| 497 |
+
"eval_prec_micro": 0.9386189258311219,
|
| 498 |
+
"eval_rec_at_5": 0.9794520547945206,
|
| 499 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 500 |
+
"eval_rec_macro": 0.9015047595626373,
|
| 501 |
+
"eval_rec_micro": 0.9129353233830089,
|
| 502 |
+
"eval_runtime": 6.1964,
|
| 503 |
+
"eval_samples_per_second": 141.373,
|
| 504 |
+
"eval_steps_per_second": 17.752,
|
| 505 |
+
"step": 384
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 17.0,
|
| 509 |
+
"grad_norm": 0.6827139854431152,
|
| 510 |
+
"learning_rate": 6.3888888888888885e-06,
|
| 511 |
+
"loss": 0.0388,
|
| 512 |
+
"step": 408
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 17.0,
|
| 516 |
+
"eval_acc_macro": 0.8515875486589554,
|
| 517 |
+
"eval_acc_micro": 0.8601236476042612,
|
| 518 |
+
"eval_auc_macro": 0.9951263473453763,
|
| 519 |
+
"eval_auc_micro": 0.9961734953002022,
|
| 520 |
+
"eval_f1_at_5": 0.4295136788854873,
|
| 521 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 522 |
+
"eval_f1_macro": 0.9176542506423578,
|
| 523 |
+
"eval_f1_micro": 0.9248026589114312,
|
| 524 |
+
"eval_loss": 0.05326356366276741,
|
| 525 |
+
"eval_prec_at_5": 0.2751141552511416,
|
| 526 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 527 |
+
"eval_prec_macro": 0.9224814917404568,
|
| 528 |
+
"eval_prec_micro": 0.9267277268941776,
|
| 529 |
+
"eval_rec_at_5": 0.9788812785388128,
|
| 530 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 531 |
+
"eval_rec_macro": 0.9138993691616202,
|
| 532 |
+
"eval_rec_micro": 0.922885572139227,
|
| 533 |
+
"eval_runtime": 6.2448,
|
| 534 |
+
"eval_samples_per_second": 140.276,
|
| 535 |
+
"eval_steps_per_second": 17.615,
|
| 536 |
+
"step": 408
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 18.0,
|
| 540 |
+
"grad_norm": 2.072528123855591,
|
| 541 |
+
"learning_rate": 6.111111111111112e-06,
|
| 542 |
+
"loss": 0.0379,
|
| 543 |
+
"step": 432
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 18.0,
|
| 547 |
+
"eval_acc_macro": 0.8504993062436726,
|
| 548 |
+
"eval_acc_micro": 0.8585780525501655,
|
| 549 |
+
"eval_auc_macro": 0.9950323486570704,
|
| 550 |
+
"eval_auc_micro": 0.9961765247834898,
|
| 551 |
+
"eval_f1_at_5": 0.4298468624753246,
|
| 552 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 553 |
+
"eval_f1_macro": 0.917328682822007,
|
| 554 |
+
"eval_f1_micro": 0.923908523908447,
|
| 555 |
+
"eval_loss": 0.05443555489182472,
|
| 556 |
+
"eval_prec_at_5": 0.2753424657534247,
|
| 557 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 558 |
+
"eval_prec_macro": 0.9227209928734593,
|
| 559 |
+
"eval_prec_micro": 0.9266055045870787,
|
| 560 |
+
"eval_rec_at_5": 0.9794520547945206,
|
| 561 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 562 |
+
"eval_rec_macro": 0.9127347764028103,
|
| 563 |
+
"eval_rec_micro": 0.9212271973465239,
|
| 564 |
+
"eval_runtime": 6.1606,
|
| 565 |
+
"eval_samples_per_second": 142.194,
|
| 566 |
+
"eval_steps_per_second": 17.855,
|
| 567 |
+
"step": 432
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 19.0,
|
| 571 |
+
"grad_norm": 1.0216673612594604,
|
| 572 |
+
"learning_rate": 5.833333333333334e-06,
|
| 573 |
+
"loss": 0.0367,
|
| 574 |
+
"step": 456
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 19.0,
|
| 578 |
+
"eval_acc_macro": 0.8491462024293238,
|
| 579 |
+
"eval_acc_micro": 0.8604832424005564,
|
| 580 |
+
"eval_auc_macro": 0.9952033636321062,
|
| 581 |
+
"eval_auc_micro": 0.9961533581465836,
|
| 582 |
+
"eval_f1_at_5": 0.42918048633589306,
|
| 583 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 584 |
+
"eval_f1_macro": 0.9162533148683757,
|
| 585 |
+
"eval_f1_micro": 0.9250104733974928,
|
| 586 |
+
"eval_loss": 0.053822897374629974,
|
| 587 |
+
"eval_prec_at_5": 0.27488584474885847,
|
| 588 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 589 |
+
"eval_prec_macro": 0.9302531226804523,
|
| 590 |
+
"eval_prec_micro": 0.9348010160879818,
|
| 591 |
+
"eval_rec_at_5": 0.978310502283105,
|
| 592 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 593 |
+
"eval_rec_macro": 0.9044133701637805,
|
| 594 |
+
"eval_rec_micro": 0.9154228855720634,
|
| 595 |
+
"eval_runtime": 6.2679,
|
| 596 |
+
"eval_samples_per_second": 139.759,
|
| 597 |
+
"eval_steps_per_second": 17.55,
|
| 598 |
+
"step": 456
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 20.0,
|
| 602 |
+
"grad_norm": 0.8565398454666138,
|
| 603 |
+
"learning_rate": 5.555555555555557e-06,
|
| 604 |
+
"loss": 0.035,
|
| 605 |
+
"step": 480
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 20.0,
|
| 609 |
+
"eval_acc_macro": 0.8539275510220851,
|
| 610 |
+
"eval_acc_micro": 0.8656832298135974,
|
| 611 |
+
"eval_auc_macro": 0.9953444620919104,
|
| 612 |
+
"eval_auc_micro": 0.9962831804157093,
|
| 613 |
+
"eval_f1_at_5": 0.4288472848093916,
|
| 614 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 615 |
+
"eval_f1_macro": 0.9186680652840996,
|
| 616 |
+
"eval_f1_micro": 0.9280066583436597,
|
| 617 |
+
"eval_loss": 0.05500434711575508,
|
| 618 |
+
"eval_prec_at_5": 0.27465753424657535,
|
| 619 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 620 |
+
"eval_prec_macro": 0.9265469458942642,
|
| 621 |
+
"eval_prec_micro": 0.9314954051795379,
|
| 622 |
+
"eval_rec_at_5": 0.9777397260273972,
|
| 623 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 624 |
+
"eval_rec_macro": 0.9134436001515955,
|
| 625 |
+
"eval_rec_micro": 0.92454394693193,
|
| 626 |
+
"eval_runtime": 6.1331,
|
| 627 |
+
"eval_samples_per_second": 142.831,
|
| 628 |
+
"eval_steps_per_second": 17.935,
|
| 629 |
+
"step": 480
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 21.0,
|
| 633 |
+
"grad_norm": 0.8573027849197388,
|
| 634 |
+
"learning_rate": 5.2777777777777785e-06,
|
| 635 |
+
"loss": 0.034,
|
| 636 |
+
"step": 504
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 21.0,
|
| 640 |
+
"eval_acc_macro": 0.8487139365583213,
|
| 641 |
+
"eval_acc_micro": 0.8599071207429675,
|
| 642 |
+
"eval_auc_macro": 0.9952593352184999,
|
| 643 |
+
"eval_auc_micro": 0.99623096638022,
|
| 644 |
+
"eval_f1_at_5": 0.4295136788854873,
|
| 645 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 646 |
+
"eval_f1_macro": 0.9158985967502566,
|
| 647 |
+
"eval_f1_micro": 0.9246774864751622,
|
| 648 |
+
"eval_loss": 0.05316817760467529,
|
| 649 |
+
"eval_prec_at_5": 0.2751141552511416,
|
| 650 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 651 |
+
"eval_prec_macro": 0.9212276417335067,
|
| 652 |
+
"eval_prec_micro": 0.9281537176273242,
|
| 653 |
+
"eval_rec_at_5": 0.9788812785388128,
|
| 654 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 655 |
+
"eval_rec_macro": 0.9117274622825242,
|
| 656 |
+
"eval_rec_micro": 0.9212271973465239,
|
| 657 |
+
"eval_runtime": 6.2044,
|
| 658 |
+
"eval_samples_per_second": 141.191,
|
| 659 |
+
"eval_steps_per_second": 17.729,
|
| 660 |
+
"step": 504
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 22.0,
|
| 664 |
+
"grad_norm": 0.6982609033584595,
|
| 665 |
+
"learning_rate": 5e-06,
|
| 666 |
+
"loss": 0.0321,
|
| 667 |
+
"step": 528
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 22.0,
|
| 671 |
+
"eval_acc_macro": 0.8491707056123833,
|
| 672 |
+
"eval_acc_micro": 0.8597986057319241,
|
| 673 |
+
"eval_auc_macro": 0.995166189612911,
|
| 674 |
+
"eval_auc_micro": 0.9962029882110331,
|
| 675 |
+
"eval_f1_at_5": 0.42918048633589306,
|
| 676 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 677 |
+
"eval_f1_macro": 0.9161030038339234,
|
| 678 |
+
"eval_f1_micro": 0.9246147438566493,
|
| 679 |
+
"eval_loss": 0.056650497019290924,
|
| 680 |
+
"eval_prec_at_5": 0.27488584474885847,
|
| 681 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 682 |
+
"eval_prec_macro": 0.9201734731045618,
|
| 683 |
+
"eval_prec_micro": 0.9288702928869516,
|
| 684 |
+
"eval_rec_at_5": 0.978310502283105,
|
| 685 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 686 |
+
"eval_rec_macro": 0.9130204494213245,
|
| 687 |
+
"eval_rec_micro": 0.9203980099501724,
|
| 688 |
+
"eval_runtime": 6.2454,
|
| 689 |
+
"eval_samples_per_second": 140.262,
|
| 690 |
+
"eval_steps_per_second": 17.613,
|
| 691 |
+
"step": 528
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 23.0,
|
| 695 |
+
"grad_norm": 0.7926116585731506,
|
| 696 |
+
"learning_rate": 4.722222222222222e-06,
|
| 697 |
+
"loss": 0.0303,
|
| 698 |
+
"step": 552
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 23.0,
|
| 702 |
+
"eval_acc_macro": 0.8491868722119115,
|
| 703 |
+
"eval_acc_micro": 0.8571428571427916,
|
| 704 |
+
"eval_auc_macro": 0.9953682041367656,
|
| 705 |
+
"eval_auc_micro": 0.9962074433335152,
|
| 706 |
+
"eval_f1_at_5": 0.42918048633589306,
|
| 707 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 708 |
+
"eval_f1_macro": 0.9157423579975225,
|
| 709 |
+
"eval_f1_micro": 0.9230769230768471,
|
| 710 |
+
"eval_loss": 0.056672144681215286,
|
| 711 |
+
"eval_prec_at_5": 0.27488584474885847,
|
| 712 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 713 |
+
"eval_prec_macro": 0.9083006225839708,
|
| 714 |
+
"eval_prec_micro": 0.9159183673468639,
|
| 715 |
+
"eval_rec_at_5": 0.978310502283105,
|
| 716 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 717 |
+
"eval_rec_macro": 0.9239908582927064,
|
| 718 |
+
"eval_rec_micro": 0.9303482587063905,
|
| 719 |
+
"eval_runtime": 6.2236,
|
| 720 |
+
"eval_samples_per_second": 140.755,
|
| 721 |
+
"eval_steps_per_second": 17.675,
|
| 722 |
+
"step": 552
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 24.0,
|
| 726 |
+
"grad_norm": 1.125510573387146,
|
| 727 |
+
"learning_rate": 4.444444444444444e-06,
|
| 728 |
+
"loss": 0.0301,
|
| 729 |
+
"step": 576
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 24.0,
|
| 733 |
+
"eval_acc_macro": 0.8485250231781508,
|
| 734 |
+
"eval_acc_micro": 0.8570318570317904,
|
| 735 |
+
"eval_auc_macro": 0.9952185441458874,
|
| 736 |
+
"eval_auc_micro": 0.9962312336875689,
|
| 737 |
+
"eval_f1_at_5": 0.42918048633589306,
|
| 738 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 739 |
+
"eval_f1_macro": 0.9157383370149551,
|
| 740 |
+
"eval_f1_micro": 0.923012552301178,
|
| 741 |
+
"eval_loss": 0.06080281734466553,
|
| 742 |
+
"eval_prec_at_5": 0.27488584474885847,
|
| 743 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 744 |
+
"eval_prec_macro": 0.9252875267591651,
|
| 745 |
+
"eval_prec_micro": 0.9315878378377591,
|
| 746 |
+
"eval_rec_at_5": 0.978310502283105,
|
| 747 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 748 |
+
"eval_rec_macro": 0.9073331635314181,
|
| 749 |
+
"eval_rec_micro": 0.9145936981757119,
|
| 750 |
+
"eval_runtime": 6.1671,
|
| 751 |
+
"eval_samples_per_second": 142.044,
|
| 752 |
+
"eval_steps_per_second": 17.837,
|
| 753 |
+
"step": 576
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 25.0,
|
| 757 |
+
"grad_norm": 1.347324013710022,
|
| 758 |
+
"learning_rate": 4.166666666666667e-06,
|
| 759 |
+
"loss": 0.0282,
|
| 760 |
+
"step": 600
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 25.0,
|
| 764 |
+
"eval_acc_macro": 0.842166168753605,
|
| 765 |
+
"eval_acc_micro": 0.8551068883609774,
|
| 766 |
+
"eval_auc_macro": 0.9949314011679055,
|
| 767 |
+
"eval_auc_micro": 0.9960538307103354,
|
| 768 |
+
"eval_f1_at_5": 0.4288472848093916,
|
| 769 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 770 |
+
"eval_f1_macro": 0.9119808094359786,
|
| 771 |
+
"eval_f1_micro": 0.9218950064019699,
|
| 772 |
+
"eval_loss": 0.056968480348587036,
|
| 773 |
+
"eval_prec_at_5": 0.27465753424657535,
|
| 774 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 775 |
+
"eval_prec_macro": 0.9426243208291692,
|
| 776 |
+
"eval_prec_micro": 0.9498680738785444,
|
| 777 |
+
"eval_rec_at_5": 0.9777397260273972,
|
| 778 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 779 |
+
"eval_rec_macro": 0.8854364498112819,
|
| 780 |
+
"eval_rec_micro": 0.8955223880596273,
|
| 781 |
+
"eval_runtime": 6.2218,
|
| 782 |
+
"eval_samples_per_second": 140.795,
|
| 783 |
+
"eval_steps_per_second": 17.68,
|
| 784 |
+
"step": 600
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 26.0,
|
| 788 |
+
"grad_norm": 0.7992838025093079,
|
| 789 |
+
"learning_rate": 3.88888888888889e-06,
|
| 790 |
+
"loss": 0.0271,
|
| 791 |
+
"step": 624
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 26.0,
|
| 795 |
+
"eval_acc_macro": 0.850448503713554,
|
| 796 |
+
"eval_acc_micro": 0.8584544758989396,
|
| 797 |
+
"eval_auc_macro": 0.994964877927155,
|
| 798 |
+
"eval_auc_micro": 0.9959627234555783,
|
| 799 |
+
"eval_f1_at_5": 0.42851407428878907,
|
| 800 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 801 |
+
"eval_f1_macro": 0.916988259808195,
|
| 802 |
+
"eval_f1_micro": 0.923836969946404,
|
| 803 |
+
"eval_loss": 0.062447551637887955,
|
| 804 |
+
"eval_prec_at_5": 0.27442922374429224,
|
| 805 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 806 |
+
"eval_prec_macro": 0.9094336920398504,
|
| 807 |
+
"eval_prec_micro": 0.9174161896973902,
|
| 808 |
+
"eval_rec_at_5": 0.9771689497716894,
|
| 809 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 810 |
+
"eval_rec_macro": 0.9249848527276295,
|
| 811 |
+
"eval_rec_micro": 0.9303482587063905,
|
| 812 |
+
"eval_runtime": 6.205,
|
| 813 |
+
"eval_samples_per_second": 141.177,
|
| 814 |
+
"eval_steps_per_second": 17.728,
|
| 815 |
+
"step": 624
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 27.0,
|
| 819 |
+
"grad_norm": 0.7699769735336304,
|
| 820 |
+
"learning_rate": 3.6111111111111115e-06,
|
| 821 |
+
"loss": 0.0264,
|
| 822 |
+
"step": 648
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 27.0,
|
| 826 |
+
"eval_acc_macro": 0.8509862309003138,
|
| 827 |
+
"eval_acc_micro": 0.857365549493308,
|
| 828 |
+
"eval_auc_macro": 0.9948429133410858,
|
| 829 |
+
"eval_auc_micro": 0.9958119175595623,
|
| 830 |
+
"eval_f1_at_5": 0.42851407428878907,
|
| 831 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 832 |
+
"eval_f1_macro": 0.9178276987832569,
|
| 833 |
+
"eval_f1_micro": 0.9232060428031118,
|
| 834 |
+
"eval_loss": 0.06019788607954979,
|
| 835 |
+
"eval_prec_at_5": 0.27442922374429224,
|
| 836 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 837 |
+
"eval_prec_macro": 0.9247554610597524,
|
| 838 |
+
"eval_prec_micro": 0.9345794392522571,
|
| 839 |
+
"eval_rec_at_5": 0.9771689497716894,
|
| 840 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 841 |
+
"eval_rec_macro": 0.9123211173889221,
|
| 842 |
+
"eval_rec_micro": 0.9121061359866574,
|
| 843 |
+
"eval_runtime": 6.199,
|
| 844 |
+
"eval_samples_per_second": 141.314,
|
| 845 |
+
"eval_steps_per_second": 17.745,
|
| 846 |
+
"step": 648
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 28.0,
|
| 850 |
+
"grad_norm": 0.8111199736595154,
|
| 851 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 852 |
+
"loss": 0.0247,
|
| 853 |
+
"step": 672
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 28.0,
|
| 857 |
+
"eval_acc_macro": 0.8539050124448745,
|
| 858 |
+
"eval_acc_micro": 0.8599397590360798,
|
| 859 |
+
"eval_auc_macro": 0.9949311017267249,
|
| 860 |
+
"eval_auc_micro": 0.9958826649045767,
|
| 861 |
+
"eval_f1_at_5": 0.4288472848093916,
|
| 862 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 863 |
+
"eval_f1_macro": 0.9187578667846501,
|
| 864 |
+
"eval_f1_micro": 0.9246963562752287,
|
| 865 |
+
"eval_loss": 0.06124128773808479,
|
| 866 |
+
"eval_prec_at_5": 0.27465753424657535,
|
| 867 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 868 |
+
"eval_prec_macro": 0.898554094667798,
|
| 869 |
+
"eval_prec_micro": 0.9034810126581564,
|
| 870 |
+
"eval_rec_at_5": 0.9777397260273972,
|
| 871 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 872 |
+
"eval_rec_macro": 0.9403712267485004,
|
| 873 |
+
"eval_rec_micro": 0.9469320066334206,
|
| 874 |
+
"eval_runtime": 6.2175,
|
| 875 |
+
"eval_samples_per_second": 140.893,
|
| 876 |
+
"eval_steps_per_second": 17.692,
|
| 877 |
+
"step": 672
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 29.0,
|
| 881 |
+
"grad_norm": 0.8091293573379517,
|
| 882 |
+
"learning_rate": 3.055555555555556e-06,
|
| 883 |
+
"loss": 0.0236,
|
| 884 |
+
"step": 696
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 29.0,
|
| 888 |
+
"eval_acc_macro": 0.8515123078962853,
|
| 889 |
+
"eval_acc_micro": 0.8605182926828612,
|
| 890 |
+
"eval_auc_macro": 0.9949441815288761,
|
| 891 |
+
"eval_auc_micro": 0.9957389426533069,
|
| 892 |
+
"eval_f1_at_5": 0.42918048633589306,
|
| 893 |
+
"eval_f1_at_8": 0.2925113305987028,
|
| 894 |
+
"eval_f1_macro": 0.9176180291221252,
|
| 895 |
+
"eval_f1_micro": 0.9250307251125829,
|
| 896 |
+
"eval_loss": 0.06163506582379341,
|
| 897 |
+
"eval_prec_at_5": 0.27488584474885847,
|
| 898 |
+
"eval_prec_at_8": 0.17194634703196346,
|
| 899 |
+
"eval_prec_macro": 0.9064412973486995,
|
| 900 |
+
"eval_prec_micro": 0.9141700404857559,
|
| 901 |
+
"eval_rec_at_5": 0.978310502283105,
|
| 902 |
+
"eval_rec_at_8": 0.9788812785388128,
|
| 903 |
+
"eval_rec_macro": 0.9296481224485932,
|
| 904 |
+
"eval_rec_micro": 0.936152570480851,
|
| 905 |
+
"eval_runtime": 6.2226,
|
| 906 |
+
"eval_samples_per_second": 140.776,
|
| 907 |
+
"eval_steps_per_second": 17.677,
|
| 908 |
+
"step": 696
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 30.0,
|
| 912 |
+
"grad_norm": 0.7638717889785767,
|
| 913 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 914 |
+
"loss": 0.0242,
|
| 915 |
+
"step": 720
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 30.0,
|
| 919 |
+
"eval_acc_macro": 0.8514782533320497,
|
| 920 |
+
"eval_acc_micro": 0.8610897927858127,
|
| 921 |
+
"eval_auc_macro": 0.9950854271410213,
|
| 922 |
+
"eval_auc_micro": 0.9960944168761464,
|
| 923 |
+
"eval_f1_at_5": 0.4295136788854873,
|
| 924 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 925 |
+
"eval_f1_macro": 0.9177801984021922,
|
| 926 |
+
"eval_f1_micro": 0.9253608247421917,
|
| 927 |
+
"eval_loss": 0.06092337146401405,
|
| 928 |
+
"eval_prec_at_5": 0.2751141552511416,
|
| 929 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 930 |
+
"eval_prec_macro": 0.9134538753515611,
|
| 931 |
+
"eval_prec_micro": 0.920426579163173,
|
| 932 |
+
"eval_rec_at_5": 0.9788812785388128,
|
| 933 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 934 |
+
"eval_rec_macro": 0.9227004606245881,
|
| 935 |
+
"eval_rec_micro": 0.9303482587063905,
|
| 936 |
+
"eval_runtime": 6.1492,
|
| 937 |
+
"eval_samples_per_second": 142.457,
|
| 938 |
+
"eval_steps_per_second": 17.888,
|
| 939 |
+
"step": 720
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 31.0,
|
| 943 |
+
"grad_norm": 0.9947636127471924,
|
| 944 |
+
"learning_rate": 2.5e-06,
|
| 945 |
+
"loss": 0.023,
|
| 946 |
+
"step": 744
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 31.0,
|
| 950 |
+
"eval_acc_macro": 0.8560068706371594,
|
| 951 |
+
"eval_acc_micro": 0.8637770897832149,
|
| 952 |
+
"eval_auc_macro": 0.9947951862441506,
|
| 953 |
+
"eval_auc_micro": 0.9958837341339722,
|
| 954 |
+
"eval_f1_at_5": 0.4295136788854873,
|
| 955 |
+
"eval_f1_at_8": 0.29274329072668936,
|
| 956 |
+
"eval_f1_macro": 0.9205694310134601,
|
| 957 |
+
"eval_f1_micro": 0.9269102990032453,
|
| 958 |
+
"eval_loss": 0.06532252579927444,
|
| 959 |
+
"eval_prec_at_5": 0.2751141552511416,
|
| 960 |
+
"eval_prec_at_8": 0.1720890410958904,
|
| 961 |
+
"eval_prec_macro": 0.9201882436524288,
|
| 962 |
+
"eval_prec_micro": 0.9284525790348644,
|
| 963 |
+
"eval_rec_at_5": 0.9788812785388128,
|
| 964 |
+
"eval_rec_at_8": 0.9794520547945206,
|
| 965 |
+
"eval_rec_macro": 0.9217575019308203,
|
| 966 |
+
"eval_rec_micro": 0.9253731343282815,
|
| 967 |
+
"eval_runtime": 6.1427,
|
| 968 |
+
"eval_samples_per_second": 142.608,
|
| 969 |
+
"eval_steps_per_second": 17.907,
|
| 970 |
+
"step": 744
|
| 971 |
+
}
|
| 972 |
+
],
|
| 973 |
+
"logging_steps": 500,
|
| 974 |
+
"max_steps": 960,
|
| 975 |
+
"num_input_tokens_seen": 0,
|
| 976 |
+
"num_train_epochs": 40,
|
| 977 |
+
"save_steps": 500,
|
| 978 |
+
"total_flos": 2.503865168315597e+16,
|
| 979 |
+
"train_batch_size": 32,
|
| 980 |
+
"trial_name": null,
|
| 981 |
+
"trial_params": null
|
| 982 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9ccbc95b8b2ee50380681dc01c600b9283cb323ef4f186375685f7b198b03fe
|
| 3 |
+
size 5048
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|