Upload folder using huggingface_hub
Browse files- README.md +14 -0
- added_tokens.json +12 -0
- checkpoint-12021/added_tokens.json +12 -0
- checkpoint-12021/config.json +39 -0
- checkpoint-12021/model.safetensors +3 -0
- checkpoint-12021/optimizer.pt +3 -0
- checkpoint-12021/scheduler.pt +3 -0
- checkpoint-12021/special_tokens_map.json +15 -0
- checkpoint-12021/spm.model +3 -0
- checkpoint-12021/tokenizer_config.json +131 -0
- checkpoint-12021/trainer_state.json +1714 -0
- checkpoint-12021/training_args.bin +3 -0
- checkpoint-8014/added_tokens.json +12 -0
- checkpoint-8014/config.json +39 -0
- checkpoint-8014/model.safetensors +3 -0
- checkpoint-8014/optimizer.pt +3 -0
- checkpoint-8014/scheduler.pt +3 -0
- checkpoint-8014/special_tokens_map.json +15 -0
- checkpoint-8014/spm.model +3 -0
- checkpoint-8014/tokenizer_config.json +131 -0
- checkpoint-8014/trainer_state.json +1154 -0
- checkpoint-8014/training_args.bin +3 -0
- config.json +39 -0
- model.safetensors +3 -0
- reward_iso.joblib +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +131 -0
- training_args.bin +3 -0
- year_z_stats.json +1 -0
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- regression
|
| 5 |
+
- creativity
|
| 6 |
+
- iclr
|
| 7 |
+
license: mit
|
| 8 |
+
pipeline_tag: text-classification
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# IRM High Ver
|
| 12 |
+
|
| 13 |
+
DeBERTa-v3-large をベースにした Idea Reward Model(不確実性回帰 + Isotonic 校正)。
|
| 14 |
+
入力: タイトル + アブストラクト → 回帰スコア(μ)と 0–1 の報酬にマッピング。
|
added_tokens.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000,
|
| 3 |
+
"[YEAR=2017]": 128001,
|
| 4 |
+
"[YEAR=2018]": 128002,
|
| 5 |
+
"[YEAR=2019]": 128003,
|
| 6 |
+
"[YEAR=2020]": 128004,
|
| 7 |
+
"[YEAR=2021]": 128005,
|
| 8 |
+
"[YEAR=2022]": 128006,
|
| 9 |
+
"[YEAR=2023]": 128007,
|
| 10 |
+
"[YEAR=2024]": 128008,
|
| 11 |
+
"[YEAR=2025]": 128009
|
| 12 |
+
}
|
checkpoint-12021/added_tokens.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000,
|
| 3 |
+
"[YEAR=2017]": 128001,
|
| 4 |
+
"[YEAR=2018]": 128002,
|
| 5 |
+
"[YEAR=2019]": 128003,
|
| 6 |
+
"[YEAR=2020]": 128004,
|
| 7 |
+
"[YEAR=2021]": 128005,
|
| 8 |
+
"[YEAR=2022]": 128006,
|
| 9 |
+
"[YEAR=2023]": 128007,
|
| 10 |
+
"[YEAR=2024]": 128008,
|
| 11 |
+
"[YEAR=2025]": 128009
|
| 12 |
+
}
|
checkpoint-12021/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4096,
|
| 14 |
+
"layer_norm_eps": 1e-07,
|
| 15 |
+
"legacy": true,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"max_relative_positions": -1,
|
| 18 |
+
"model_type": "deberta-v2",
|
| 19 |
+
"norm_rel_ebd": "layer_norm",
|
| 20 |
+
"num_attention_heads": 16,
|
| 21 |
+
"num_hidden_layers": 24,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pooler_dropout": 0,
|
| 24 |
+
"pooler_hidden_act": "gelu",
|
| 25 |
+
"pooler_hidden_size": 1024,
|
| 26 |
+
"pos_att_type": [
|
| 27 |
+
"p2c",
|
| 28 |
+
"c2p"
|
| 29 |
+
],
|
| 30 |
+
"position_biased_input": false,
|
| 31 |
+
"position_buckets": 256,
|
| 32 |
+
"problem_type": "regression",
|
| 33 |
+
"relative_attention": true,
|
| 34 |
+
"share_att_key": true,
|
| 35 |
+
"transformers_version": "4.57.1",
|
| 36 |
+
"type_vocab_size": 0,
|
| 37 |
+
"use_cache": false,
|
| 38 |
+
"vocab_size": 128010
|
| 39 |
+
}
|
checkpoint-12021/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d86a3010e49a8679374ce449892b0a9e1d2aa6ba56a7b03394df30bd9a755a13
|
| 3 |
+
size 1739935800
|
checkpoint-12021/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9a2767a4f0ebca56ea99d5c80876dffd33a80166cebe90640b13f05cdfb96cc
|
| 3 |
+
size 3480108865
|
checkpoint-12021/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ebaa22576169a7fb46fd44883e5c1f9acc98767ead9b6d2849d606d42a5ecfa
|
| 3 |
+
size 1465
|
checkpoint-12021/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
checkpoint-12021/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-12021/tokenizer_config.json
ADDED
|
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128001": {
|
| 44 |
+
"content": "[YEAR=2017]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"128002": {
|
| 52 |
+
"content": "[YEAR=2018]",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"128003": {
|
| 60 |
+
"content": "[YEAR=2019]",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"128004": {
|
| 68 |
+
"content": "[YEAR=2020]",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"128005": {
|
| 76 |
+
"content": "[YEAR=2021]",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"128006": {
|
| 84 |
+
"content": "[YEAR=2022]",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"128007": {
|
| 92 |
+
"content": "[YEAR=2023]",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"128008": {
|
| 100 |
+
"content": "[YEAR=2024]",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"128009": {
|
| 108 |
+
"content": "[YEAR=2025]",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
}
|
| 115 |
+
},
|
| 116 |
+
"bos_token": "[CLS]",
|
| 117 |
+
"clean_up_tokenization_spaces": false,
|
| 118 |
+
"cls_token": "[CLS]",
|
| 119 |
+
"do_lower_case": false,
|
| 120 |
+
"eos_token": "[SEP]",
|
| 121 |
+
"extra_special_tokens": {},
|
| 122 |
+
"mask_token": "[MASK]",
|
| 123 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 124 |
+
"pad_token": "[PAD]",
|
| 125 |
+
"sep_token": "[SEP]",
|
| 126 |
+
"sp_model_kwargs": {},
|
| 127 |
+
"split_by_punct": false,
|
| 128 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 129 |
+
"unk_token": "[UNK]",
|
| 130 |
+
"vocab_type": "spm"
|
| 131 |
+
}
|
checkpoint-12021/trainer_state.json
ADDED
|
@@ -0,0 +1,1714 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 12021,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.012478163214374845,
|
| 14 |
+
"grad_norm": 4.458792209625244,
|
| 15 |
+
"learning_rate": 6.786703601108035e-07,
|
| 16 |
+
"loss": 0.5794,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02495632642874969,
|
| 21 |
+
"grad_norm": 3.041719436645508,
|
| 22 |
+
"learning_rate": 1.371191135734072e-06,
|
| 23 |
+
"loss": 0.5188,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.037434489643124534,
|
| 28 |
+
"grad_norm": 10.141822814941406,
|
| 29 |
+
"learning_rate": 2.0637119113573407e-06,
|
| 30 |
+
"loss": 0.5702,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04991265285749938,
|
| 35 |
+
"grad_norm": 4.34501838684082,
|
| 36 |
+
"learning_rate": 2.7562326869806094e-06,
|
| 37 |
+
"loss": 0.5027,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.062390816071874224,
|
| 42 |
+
"grad_norm": 6.478577613830566,
|
| 43 |
+
"learning_rate": 3.448753462603878e-06,
|
| 44 |
+
"loss": 0.5349,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07486897928624907,
|
| 49 |
+
"grad_norm": 4.510005950927734,
|
| 50 |
+
"learning_rate": 4.141274238227147e-06,
|
| 51 |
+
"loss": 0.5024,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0873471425006239,
|
| 56 |
+
"grad_norm": 4.612236976623535,
|
| 57 |
+
"learning_rate": 4.833795013850416e-06,
|
| 58 |
+
"loss": 0.4693,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.09982530571499876,
|
| 63 |
+
"grad_norm": 12.051955223083496,
|
| 64 |
+
"learning_rate": 5.526315789473685e-06,
|
| 65 |
+
"loss": 0.5274,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1123034689293736,
|
| 70 |
+
"grad_norm": 11.082642555236816,
|
| 71 |
+
"learning_rate": 6.218836565096953e-06,
|
| 72 |
+
"loss": 0.4646,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.12478163214374845,
|
| 77 |
+
"grad_norm": 5.821896553039551,
|
| 78 |
+
"learning_rate": 6.911357340720221e-06,
|
| 79 |
+
"loss": 0.4762,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.13725979535812327,
|
| 84 |
+
"grad_norm": 10.287369728088379,
|
| 85 |
+
"learning_rate": 7.6038781163434905e-06,
|
| 86 |
+
"loss": 0.5373,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.14973795857249814,
|
| 91 |
+
"grad_norm": 6.837547779083252,
|
| 92 |
+
"learning_rate": 8.29639889196676e-06,
|
| 93 |
+
"loss": 0.4746,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.16221612178687297,
|
| 98 |
+
"grad_norm": 5.090405464172363,
|
| 99 |
+
"learning_rate": 8.988919667590029e-06,
|
| 100 |
+
"loss": 0.4974,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1746942850012478,
|
| 105 |
+
"grad_norm": 7.571693420410156,
|
| 106 |
+
"learning_rate": 9.681440443213298e-06,
|
| 107 |
+
"loss": 0.4859,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.18717244821562265,
|
| 112 |
+
"grad_norm": 5.327805042266846,
|
| 113 |
+
"learning_rate": 9.999859108359658e-06,
|
| 114 |
+
"loss": 0.4728,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.19965061142999752,
|
| 119 |
+
"grad_norm": 8.96234130859375,
|
| 120 |
+
"learning_rate": 9.998854158364854e-06,
|
| 121 |
+
"loss": 0.4707,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.21212877464437235,
|
| 126 |
+
"grad_norm": 6.393317222595215,
|
| 127 |
+
"learning_rate": 9.996883105864235e-06,
|
| 128 |
+
"loss": 0.4647,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2246069378587472,
|
| 133 |
+
"grad_norm": 6.38814115524292,
|
| 134 |
+
"learning_rate": 9.993946331792856e-06,
|
| 135 |
+
"loss": 0.4589,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.23708510107312203,
|
| 140 |
+
"grad_norm": 16.268198013305664,
|
| 141 |
+
"learning_rate": 9.990044403725743e-06,
|
| 142 |
+
"loss": 0.4048,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2495632642874969,
|
| 147 |
+
"grad_norm": 3.3333048820495605,
|
| 148 |
+
"learning_rate": 9.985178075768209e-06,
|
| 149 |
+
"loss": 0.5081,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2620414275018717,
|
| 154 |
+
"grad_norm": 10.300507545471191,
|
| 155 |
+
"learning_rate": 9.979348288410111e-06,
|
| 156 |
+
"loss": 0.4608,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.27451959071624654,
|
| 161 |
+
"grad_norm": 6.351011276245117,
|
| 162 |
+
"learning_rate": 9.97255616834409e-06,
|
| 163 |
+
"loss": 0.4638,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.28699775393062144,
|
| 168 |
+
"grad_norm": 7.574777603149414,
|
| 169 |
+
"learning_rate": 9.964803028247807e-06,
|
| 170 |
+
"loss": 0.427,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.2994759171449963,
|
| 175 |
+
"grad_norm": 12.513327598571777,
|
| 176 |
+
"learning_rate": 9.95609036653027e-06,
|
| 177 |
+
"loss": 0.451,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.3119540803593711,
|
| 182 |
+
"grad_norm": 7.875536918640137,
|
| 183 |
+
"learning_rate": 9.946419867042226e-06,
|
| 184 |
+
"loss": 0.4535,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.32443224357374595,
|
| 189 |
+
"grad_norm": 3.6338303089141846,
|
| 190 |
+
"learning_rate": 9.935793398750741e-06,
|
| 191 |
+
"loss": 0.4618,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.3369104067881208,
|
| 196 |
+
"grad_norm": 122.68341827392578,
|
| 197 |
+
"learning_rate": 9.924213015377991e-06,
|
| 198 |
+
"loss": 0.4842,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.3493885700024956,
|
| 203 |
+
"grad_norm": 14.782501220703125,
|
| 204 |
+
"learning_rate": 9.911680955004353e-06,
|
| 205 |
+
"loss": 0.4984,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.36186673321687046,
|
| 210 |
+
"grad_norm": 8.127388000488281,
|
| 211 |
+
"learning_rate": 9.89819963963586e-06,
|
| 212 |
+
"loss": 0.5211,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3743448964312453,
|
| 217 |
+
"grad_norm": 9.87590503692627,
|
| 218 |
+
"learning_rate": 9.883771674736113e-06,
|
| 219 |
+
"loss": 0.4535,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.38682305964562014,
|
| 224 |
+
"grad_norm": 9.47072696685791,
|
| 225 |
+
"learning_rate": 9.868399848722738e-06,
|
| 226 |
+
"loss": 0.4273,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.39930122285999503,
|
| 231 |
+
"grad_norm": 7.544781684875488,
|
| 232 |
+
"learning_rate": 9.852087132428483e-06,
|
| 233 |
+
"loss": 0.4068,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.41177938607436987,
|
| 238 |
+
"grad_norm": 8.554336547851562,
|
| 239 |
+
"learning_rate": 9.834836678527055e-06,
|
| 240 |
+
"loss": 0.4562,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.4242575492887447,
|
| 245 |
+
"grad_norm": 11.270395278930664,
|
| 246 |
+
"learning_rate": 9.816651820923832e-06,
|
| 247 |
+
"loss": 0.4057,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.43673571250311954,
|
| 252 |
+
"grad_norm": 4.841072082519531,
|
| 253 |
+
"learning_rate": 9.797536074111523e-06,
|
| 254 |
+
"loss": 0.5079,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.4492138757174944,
|
| 259 |
+
"grad_norm": 10.340139389038086,
|
| 260 |
+
"learning_rate": 9.777493132490945e-06,
|
| 261 |
+
"loss": 0.4431,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.4616920389318692,
|
| 266 |
+
"grad_norm": 4.847078800201416,
|
| 267 |
+
"learning_rate": 9.75652686965703e-06,
|
| 268 |
+
"loss": 0.4961,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.47417020214624406,
|
| 273 |
+
"grad_norm": 3.77082896232605,
|
| 274 |
+
"learning_rate": 9.734641337650186e-06,
|
| 275 |
+
"loss": 0.3592,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.4866483653606189,
|
| 280 |
+
"grad_norm": 11.575835227966309,
|
| 281 |
+
"learning_rate": 9.711840766173195e-06,
|
| 282 |
+
"loss": 0.493,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4991265285749938,
|
| 287 |
+
"grad_norm": 8.841684341430664,
|
| 288 |
+
"learning_rate": 9.688129561773742e-06,
|
| 289 |
+
"loss": 0.4283,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5116046917893686,
|
| 294 |
+
"grad_norm": 14.447687149047852,
|
| 295 |
+
"learning_rate": 9.663512306992797e-06,
|
| 296 |
+
"loss": 0.4683,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5240828550037434,
|
| 301 |
+
"grad_norm": 5.287663459777832,
|
| 302 |
+
"learning_rate": 9.637993759478972e-06,
|
| 303 |
+
"loss": 0.4147,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.5365610182181183,
|
| 308 |
+
"grad_norm": 5.344033718109131,
|
| 309 |
+
"learning_rate": 9.611578851069023e-06,
|
| 310 |
+
"loss": 0.4346,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.5490391814324931,
|
| 315 |
+
"grad_norm": 12.01088809967041,
|
| 316 |
+
"learning_rate": 9.584272686834716e-06,
|
| 317 |
+
"loss": 0.364,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.561517344646868,
|
| 322 |
+
"grad_norm": 4.283223628997803,
|
| 323 |
+
"learning_rate": 9.55608054409618e-06,
|
| 324 |
+
"loss": 0.4039,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.5739955078612429,
|
| 329 |
+
"grad_norm": 5.19553804397583,
|
| 330 |
+
"learning_rate": 9.527007871402002e-06,
|
| 331 |
+
"loss": 0.4427,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5864736710756177,
|
| 336 |
+
"grad_norm": 13.137829780578613,
|
| 337 |
+
"learning_rate": 9.4970602874762e-06,
|
| 338 |
+
"loss": 0.515,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5989518342899925,
|
| 343 |
+
"grad_norm": 9.434691429138184,
|
| 344 |
+
"learning_rate": 9.466243580132336e-06,
|
| 345 |
+
"loss": 0.3969,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6114299975043673,
|
| 350 |
+
"grad_norm": 6.398521423339844,
|
| 351 |
+
"learning_rate": 9.434563705154922e-06,
|
| 352 |
+
"loss": 0.4726,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6239081607187422,
|
| 357 |
+
"grad_norm": 11.770699501037598,
|
| 358 |
+
"learning_rate": 9.402026785148385e-06,
|
| 359 |
+
"loss": 0.4433,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.636386323933117,
|
| 364 |
+
"grad_norm": 3.9562103748321533,
|
| 365 |
+
"learning_rate": 9.368639108353781e-06,
|
| 366 |
+
"loss": 0.3859,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6488644871474919,
|
| 371 |
+
"grad_norm": 8.58365535736084,
|
| 372 |
+
"learning_rate": 9.3344071274335e-06,
|
| 373 |
+
"loss": 0.5342,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6613426503618667,
|
| 378 |
+
"grad_norm": 5.637104511260986,
|
| 379 |
+
"learning_rate": 9.29933745822419e-06,
|
| 380 |
+
"loss": 0.3778,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6738208135762416,
|
| 385 |
+
"grad_norm": 7.481651306152344,
|
| 386 |
+
"learning_rate": 9.263436878458151e-06,
|
| 387 |
+
"loss": 0.4751,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6862989767906165,
|
| 392 |
+
"grad_norm": 5.351173400878906,
|
| 393 |
+
"learning_rate": 9.226712326453446e-06,
|
| 394 |
+
"loss": 0.4493,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.6987771400049912,
|
| 399 |
+
"grad_norm": 7.108247756958008,
|
| 400 |
+
"learning_rate": 9.189170899772949e-06,
|
| 401 |
+
"loss": 0.4515,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.7112553032193661,
|
| 406 |
+
"grad_norm": 8.506830215454102,
|
| 407 |
+
"learning_rate": 9.150819853852656e-06,
|
| 408 |
+
"loss": 0.3848,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.7237334664337409,
|
| 413 |
+
"grad_norm": 5.16771936416626,
|
| 414 |
+
"learning_rate": 9.111666600599455e-06,
|
| 415 |
+
"loss": 0.4331,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.7362116296481158,
|
| 420 |
+
"grad_norm": 6.397897243499756,
|
| 421 |
+
"learning_rate": 9.071718706958662e-06,
|
| 422 |
+
"loss": 0.374,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.7486897928624906,
|
| 427 |
+
"grad_norm": 11.78195571899414,
|
| 428 |
+
"learning_rate": 9.030983893451612e-06,
|
| 429 |
+
"loss": 0.415,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.7611679560768655,
|
| 434 |
+
"grad_norm": 16.80957794189453,
|
| 435 |
+
"learning_rate": 8.989470032683534e-06,
|
| 436 |
+
"loss": 0.3573,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.7736461192912403,
|
| 441 |
+
"grad_norm": 7.505095958709717,
|
| 442 |
+
"learning_rate": 8.947185147822064e-06,
|
| 443 |
+
"loss": 0.4102,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.7861242825056152,
|
| 448 |
+
"grad_norm": 8.942618370056152,
|
| 449 |
+
"learning_rate": 8.904137411046656e-06,
|
| 450 |
+
"loss": 0.385,
|
| 451 |
+
"step": 3150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.7986024457199901,
|
| 455 |
+
"grad_norm": 12.872928619384766,
|
| 456 |
+
"learning_rate": 8.860335141969173e-06,
|
| 457 |
+
"loss": 0.4918,
|
| 458 |
+
"step": 3200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.8110806089343648,
|
| 462 |
+
"grad_norm": 7.009009838104248,
|
| 463 |
+
"learning_rate": 8.815786806026008e-06,
|
| 464 |
+
"loss": 0.3944,
|
| 465 |
+
"step": 3250
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.8235587721487397,
|
| 469 |
+
"grad_norm": 9.012943267822266,
|
| 470 |
+
"learning_rate": 8.77050101284201e-06,
|
| 471 |
+
"loss": 0.4019,
|
| 472 |
+
"step": 3300
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.8360369353631145,
|
| 476 |
+
"grad_norm": 4.293410301208496,
|
| 477 |
+
"learning_rate": 8.72448651456655e-06,
|
| 478 |
+
"loss": 0.4727,
|
| 479 |
+
"step": 3350
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.8485150985774894,
|
| 483 |
+
"grad_norm": 6.573951721191406,
|
| 484 |
+
"learning_rate": 8.677752204182038e-06,
|
| 485 |
+
"loss": 0.3932,
|
| 486 |
+
"step": 3400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.8609932617918642,
|
| 490 |
+
"grad_norm": 7.871060848236084,
|
| 491 |
+
"learning_rate": 8.630307113785214e-06,
|
| 492 |
+
"loss": 0.4232,
|
| 493 |
+
"step": 3450
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.8734714250062391,
|
| 497 |
+
"grad_norm": 6.599925994873047,
|
| 498 |
+
"learning_rate": 8.582160412841578e-06,
|
| 499 |
+
"loss": 0.4354,
|
| 500 |
+
"step": 3500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.8859495882206139,
|
| 504 |
+
"grad_norm": 8.174042701721191,
|
| 505 |
+
"learning_rate": 8.533321406413238e-06,
|
| 506 |
+
"loss": 0.4637,
|
| 507 |
+
"step": 3550
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.8984277514349888,
|
| 511 |
+
"grad_norm": 11.967002868652344,
|
| 512 |
+
"learning_rate": 8.48379953336058e-06,
|
| 513 |
+
"loss": 0.3552,
|
| 514 |
+
"step": 3600
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.9109059146493637,
|
| 518 |
+
"grad_norm": 21.131765365600586,
|
| 519 |
+
"learning_rate": 8.433604364518067e-06,
|
| 520 |
+
"loss": 0.3665,
|
| 521 |
+
"step": 3650
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.9233840778637384,
|
| 525 |
+
"grad_norm": 7.3277907371521,
|
| 526 |
+
"learning_rate": 8.38274560084453e-06,
|
| 527 |
+
"loss": 0.4076,
|
| 528 |
+
"step": 3700
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.9358622410781133,
|
| 532 |
+
"grad_norm": 6.7681732177734375,
|
| 533 |
+
"learning_rate": 8.331233071548318e-06,
|
| 534 |
+
"loss": 0.4331,
|
| 535 |
+
"step": 3750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.9483404042924881,
|
| 539 |
+
"grad_norm": 5.008552551269531,
|
| 540 |
+
"learning_rate": 8.27907673218766e-06,
|
| 541 |
+
"loss": 0.4162,
|
| 542 |
+
"step": 3800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.960818567506863,
|
| 546 |
+
"grad_norm": 11.283330917358398,
|
| 547 |
+
"learning_rate": 8.226286662746594e-06,
|
| 548 |
+
"loss": 0.3277,
|
| 549 |
+
"step": 3850
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.9732967307212378,
|
| 553 |
+
"grad_norm": 7.3569746017456055,
|
| 554 |
+
"learning_rate": 8.172873065686877e-06,
|
| 555 |
+
"loss": 0.4533,
|
| 556 |
+
"step": 3900
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.9857748939356127,
|
| 560 |
+
"grad_norm": 15.550161361694336,
|
| 561 |
+
"learning_rate": 8.1188462639762e-06,
|
| 562 |
+
"loss": 0.4304,
|
| 563 |
+
"step": 3950
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.9982530571499876,
|
| 567 |
+
"grad_norm": 9.424723625183105,
|
| 568 |
+
"learning_rate": 8.06421669909312e-06,
|
| 569 |
+
"loss": 0.4069,
|
| 570 |
+
"step": 4000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.0107312203643624,
|
| 574 |
+
"grad_norm": 5.943562030792236,
|
| 575 |
+
"learning_rate": 8.008994929009097e-06,
|
| 576 |
+
"loss": 0.3779,
|
| 577 |
+
"step": 4050
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.0232093835787373,
|
| 581 |
+
"grad_norm": 13.873172760009766,
|
| 582 |
+
"learning_rate": 7.953191626148002e-06,
|
| 583 |
+
"loss": 0.3955,
|
| 584 |
+
"step": 4100
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.0356875467931121,
|
| 588 |
+
"grad_norm": 6.041378974914551,
|
| 589 |
+
"learning_rate": 7.896817575323516e-06,
|
| 590 |
+
"loss": 0.3335,
|
| 591 |
+
"step": 4150
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.0481657100074868,
|
| 595 |
+
"grad_norm": 9.297985076904297,
|
| 596 |
+
"learning_rate": 7.839883671654814e-06,
|
| 597 |
+
"loss": 0.3622,
|
| 598 |
+
"step": 4200
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.0606438732218617,
|
| 602 |
+
"grad_norm": 4.703738689422607,
|
| 603 |
+
"learning_rate": 7.7824009184609e-06,
|
| 604 |
+
"loss": 0.3698,
|
| 605 |
+
"step": 4250
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.0731220364362366,
|
| 609 |
+
"grad_norm": 8.91132926940918,
|
| 610 |
+
"learning_rate": 7.724380425134082e-06,
|
| 611 |
+
"loss": 0.2974,
|
| 612 |
+
"step": 4300
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.0856001996506115,
|
| 616 |
+
"grad_norm": 9.209162712097168,
|
| 617 |
+
"learning_rate": 7.66583340499289e-06,
|
| 618 |
+
"loss": 0.4056,
|
| 619 |
+
"step": 4350
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.0980783628649862,
|
| 623 |
+
"grad_norm": 6.217947959899902,
|
| 624 |
+
"learning_rate": 7.606771173114962e-06,
|
| 625 |
+
"loss": 0.4447,
|
| 626 |
+
"step": 4400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.110556526079361,
|
| 630 |
+
"grad_norm": 7.217406272888184,
|
| 631 |
+
"learning_rate": 7.547205144150211e-06,
|
| 632 |
+
"loss": 0.3444,
|
| 633 |
+
"step": 4450
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.123034689293736,
|
| 637 |
+
"grad_norm": 9.686402320861816,
|
| 638 |
+
"learning_rate": 7.487146830114797e-06,
|
| 639 |
+
"loss": 0.39,
|
| 640 |
+
"step": 4500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.1355128525081108,
|
| 644 |
+
"grad_norm": 7.340874671936035,
|
| 645 |
+
"learning_rate": 7.426607838166252e-06,
|
| 646 |
+
"loss": 0.3825,
|
| 647 |
+
"step": 4550
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.1479910157224857,
|
| 651 |
+
"grad_norm": 24.946033477783203,
|
| 652 |
+
"learning_rate": 7.36559986836022e-06,
|
| 653 |
+
"loss": 0.3891,
|
| 654 |
+
"step": 4600
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.1604691789368604,
|
| 658 |
+
"grad_norm": 9.491501808166504,
|
| 659 |
+
"learning_rate": 7.304134711389256e-06,
|
| 660 |
+
"loss": 0.3215,
|
| 661 |
+
"step": 4650
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1729473421512353,
|
| 665 |
+
"grad_norm": 7.190339088439941,
|
| 666 |
+
"learning_rate": 7.242224246304095e-06,
|
| 667 |
+
"loss": 0.3614,
|
| 668 |
+
"step": 4700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.1854255053656102,
|
| 672 |
+
"grad_norm": 32.30070877075195,
|
| 673 |
+
"learning_rate": 7.179880438217854e-06,
|
| 674 |
+
"loss": 0.3325,
|
| 675 |
+
"step": 4750
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.197903668579985,
|
| 679 |
+
"grad_norm": 8.440774917602539,
|
| 680 |
+
"learning_rate": 7.1171153359935945e-06,
|
| 681 |
+
"loss": 0.3708,
|
| 682 |
+
"step": 4800
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.21038183179436,
|
| 686 |
+
"grad_norm": 7.894869804382324,
|
| 687 |
+
"learning_rate": 7.0539410699156995e-06,
|
| 688 |
+
"loss": 0.3683,
|
| 689 |
+
"step": 4850
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2228599950087347,
|
| 693 |
+
"grad_norm": 10.961115837097168,
|
| 694 |
+
"learning_rate": 6.990369849345519e-06,
|
| 695 |
+
"loss": 0.3572,
|
| 696 |
+
"step": 4900
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.2353381582231096,
|
| 700 |
+
"grad_norm": 7.400118350982666,
|
| 701 |
+
"learning_rate": 6.926413960361734e-06,
|
| 702 |
+
"loss": 0.2907,
|
| 703 |
+
"step": 4950
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.2478163214374844,
|
| 707 |
+
"grad_norm": 7.078188419342041,
|
| 708 |
+
"learning_rate": 6.862085763385882e-06,
|
| 709 |
+
"loss": 0.3524,
|
| 710 |
+
"step": 5000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.2602944846518591,
|
| 714 |
+
"grad_norm": 7.620141983032227,
|
| 715 |
+
"learning_rate": 6.797397690793528e-06,
|
| 716 |
+
"loss": 0.3271,
|
| 717 |
+
"step": 5050
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.272772647866234,
|
| 721 |
+
"grad_norm": 7.046457290649414,
|
| 722 |
+
"learning_rate": 6.732362244511523e-06,
|
| 723 |
+
"loss": 0.4414,
|
| 724 |
+
"step": 5100
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.285250811080609,
|
| 728 |
+
"grad_norm": 15.27204704284668,
|
| 729 |
+
"learning_rate": 6.666991993601821e-06,
|
| 730 |
+
"loss": 0.297,
|
| 731 |
+
"step": 5150
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.2977289742949838,
|
| 735 |
+
"grad_norm": 10.220624923706055,
|
| 736 |
+
"learning_rate": 6.601299571832325e-06,
|
| 737 |
+
"loss": 0.3015,
|
| 738 |
+
"step": 5200
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.3102071375093587,
|
| 742 |
+
"grad_norm": 12.588732719421387,
|
| 743 |
+
"learning_rate": 6.535297675235221e-06,
|
| 744 |
+
"loss": 0.3472,
|
| 745 |
+
"step": 5250
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.3226853007237334,
|
| 749 |
+
"grad_norm": 10.140027046203613,
|
| 750 |
+
"learning_rate": 6.46899905965328e-06,
|
| 751 |
+
"loss": 0.3691,
|
| 752 |
+
"step": 5300
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.3351634639381083,
|
| 756 |
+
"grad_norm": 7.856444358825684,
|
| 757 |
+
"learning_rate": 6.402416538274609e-06,
|
| 758 |
+
"loss": 0.3839,
|
| 759 |
+
"step": 5350
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.3476416271524831,
|
| 763 |
+
"grad_norm": 7.6511712074279785,
|
| 764 |
+
"learning_rate": 6.3355629791563085e-06,
|
| 765 |
+
"loss": 0.361,
|
| 766 |
+
"step": 5400
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.360119790366858,
|
| 770 |
+
"grad_norm": 4.789505481719971,
|
| 771 |
+
"learning_rate": 6.2684513027375336e-06,
|
| 772 |
+
"loss": 0.4478,
|
| 773 |
+
"step": 5450
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.372597953581233,
|
| 777 |
+
"grad_norm": 7.044528007507324,
|
| 778 |
+
"learning_rate": 6.201094479342419e-06,
|
| 779 |
+
"loss": 0.3199,
|
| 780 |
+
"step": 5500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.3850761167956076,
|
| 784 |
+
"grad_norm": 8.48816967010498,
|
| 785 |
+
"learning_rate": 6.133505526673387e-06,
|
| 786 |
+
"loss": 0.3087,
|
| 787 |
+
"step": 5550
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.3975542800099825,
|
| 791 |
+
"grad_norm": 11.27566146850586,
|
| 792 |
+
"learning_rate": 6.065697507295267e-06,
|
| 793 |
+
"loss": 0.3392,
|
| 794 |
+
"step": 5600
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.4100324432243574,
|
| 798 |
+
"grad_norm": 8.946170806884766,
|
| 799 |
+
"learning_rate": 5.997683526110779e-06,
|
| 800 |
+
"loss": 0.3173,
|
| 801 |
+
"step": 5650
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.4225106064387323,
|
| 805 |
+
"grad_norm": 14.0136137008667,
|
| 806 |
+
"learning_rate": 5.929476727827801e-06,
|
| 807 |
+
"loss": 0.3957,
|
| 808 |
+
"step": 5700
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.4349887696531072,
|
| 812 |
+
"grad_norm": 8.724675178527832,
|
| 813 |
+
"learning_rate": 5.861090294418973e-06,
|
| 814 |
+
"loss": 0.4072,
|
| 815 |
+
"step": 5750
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.4474669328674818,
|
| 819 |
+
"grad_norm": 7.454153537750244,
|
| 820 |
+
"learning_rate": 5.792537442574076e-06,
|
| 821 |
+
"loss": 0.3562,
|
| 822 |
+
"step": 5800
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.4599450960818567,
|
| 826 |
+
"grad_norm": 8.835644721984863,
|
| 827 |
+
"learning_rate": 5.723831421145718e-06,
|
| 828 |
+
"loss": 0.3093,
|
| 829 |
+
"step": 5850
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.4724232592962316,
|
| 833 |
+
"grad_norm": 26.4691219329834,
|
| 834 |
+
"learning_rate": 5.6549855085887925e-06,
|
| 835 |
+
"loss": 0.3797,
|
| 836 |
+
"step": 5900
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.4849014225106063,
|
| 840 |
+
"grad_norm": 7.992363452911377,
|
| 841 |
+
"learning_rate": 5.586013010394226e-06,
|
| 842 |
+
"loss": 0.2999,
|
| 843 |
+
"step": 5950
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.4973795857249814,
|
| 847 |
+
"grad_norm": 8.84736156463623,
|
| 848 |
+
"learning_rate": 5.5169272565174866e-06,
|
| 849 |
+
"loss": 0.3515,
|
| 850 |
+
"step": 6000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.509857748939356,
|
| 854 |
+
"grad_norm": 14.053621292114258,
|
| 855 |
+
"learning_rate": 5.447741598802384e-06,
|
| 856 |
+
"loss": 0.3372,
|
| 857 |
+
"step": 6050
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.522335912153731,
|
| 861 |
+
"grad_norm": 12.153364181518555,
|
| 862 |
+
"learning_rate": 5.378469408400618e-06,
|
| 863 |
+
"loss": 0.3291,
|
| 864 |
+
"step": 6100
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.5348140753681059,
|
| 868 |
+
"grad_norm": 8.285240173339844,
|
| 869 |
+
"learning_rate": 5.309124073187613e-06,
|
| 870 |
+
"loss": 0.3676,
|
| 871 |
+
"step": 6150
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.5472922385824806,
|
| 875 |
+
"grad_norm": 11.175989151000977,
|
| 876 |
+
"learning_rate": 5.239718995175107e-06,
|
| 877 |
+
"loss": 0.3833,
|
| 878 |
+
"step": 6200
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.5597704017968557,
|
| 882 |
+
"grad_norm": 7.0034003257751465,
|
| 883 |
+
"learning_rate": 5.170267587921021e-06,
|
| 884 |
+
"loss": 0.3275,
|
| 885 |
+
"step": 6250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.5722485650112303,
|
| 889 |
+
"grad_norm": 14.088438987731934,
|
| 890 |
+
"learning_rate": 5.100783273937084e-06,
|
| 891 |
+
"loss": 0.3754,
|
| 892 |
+
"step": 6300
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.5847267282256052,
|
| 896 |
+
"grad_norm": 7.637153625488281,
|
| 897 |
+
"learning_rate": 5.031279482094741e-06,
|
| 898 |
+
"loss": 0.2582,
|
| 899 |
+
"step": 6350
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.5972048914399801,
|
| 903 |
+
"grad_norm": 16.597148895263672,
|
| 904 |
+
"learning_rate": 4.961769645029815e-06,
|
| 905 |
+
"loss": 0.3279,
|
| 906 |
+
"step": 6400
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.6096830546543548,
|
| 910 |
+
"grad_norm": 5.401224613189697,
|
| 911 |
+
"learning_rate": 4.892267196546468e-06,
|
| 912 |
+
"loss": 0.3662,
|
| 913 |
+
"step": 6450
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.6221612178687297,
|
| 917 |
+
"grad_norm": 17.39789390563965,
|
| 918 |
+
"learning_rate": 4.822785569020898e-06,
|
| 919 |
+
"loss": 0.3882,
|
| 920 |
+
"step": 6500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.6346393810831046,
|
| 924 |
+
"grad_norm": 7.322461128234863,
|
| 925 |
+
"learning_rate": 4.753338190805354e-06,
|
| 926 |
+
"loss": 0.3656,
|
| 927 |
+
"step": 6550
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.6471175442974793,
|
| 931 |
+
"grad_norm": 11.221035957336426,
|
| 932 |
+
"learning_rate": 4.683938483632893e-06,
|
| 933 |
+
"loss": 0.3346,
|
| 934 |
+
"step": 6600
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.6595957075118544,
|
| 938 |
+
"grad_norm": 12.337651252746582,
|
| 939 |
+
"learning_rate": 4.6145998600234405e-06,
|
| 940 |
+
"loss": 0.2959,
|
| 941 |
+
"step": 6650
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.672073870726229,
|
| 945 |
+
"grad_norm": 9.140985488891602,
|
| 946 |
+
"learning_rate": 4.545335720691619e-06,
|
| 947 |
+
"loss": 0.2888,
|
| 948 |
+
"step": 6700
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.684552033940604,
|
| 952 |
+
"grad_norm": 12.107025146484375,
|
| 953 |
+
"learning_rate": 4.476159451956864e-06,
|
| 954 |
+
"loss": 0.3458,
|
| 955 |
+
"step": 6750
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.6970301971549788,
|
| 959 |
+
"grad_norm": 12.792327880859375,
|
| 960 |
+
"learning_rate": 4.407084423156318e-06,
|
| 961 |
+
"loss": 0.3031,
|
| 962 |
+
"step": 6800
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.7095083603693535,
|
| 966 |
+
"grad_norm": 7.57142448425293,
|
| 967 |
+
"learning_rate": 4.338123984061008e-06,
|
| 968 |
+
"loss": 0.3177,
|
| 969 |
+
"step": 6850
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.7219865235837286,
|
| 973 |
+
"grad_norm": 13.280131340026855,
|
| 974 |
+
"learning_rate": 4.269291462295805e-06,
|
| 975 |
+
"loss": 0.3068,
|
| 976 |
+
"step": 6900
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.7344646867981033,
|
| 980 |
+
"grad_norm": 19.578649520874023,
|
| 981 |
+
"learning_rate": 4.200600160763666e-06,
|
| 982 |
+
"loss": 0.2977,
|
| 983 |
+
"step": 6950
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.7469428500124782,
|
| 987 |
+
"grad_norm": 13.223540306091309,
|
| 988 |
+
"learning_rate": 4.1320633550746464e-06,
|
| 989 |
+
"loss": 0.3542,
|
| 990 |
+
"step": 7000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.759421013226853,
|
| 994 |
+
"grad_norm": 13.519241333007812,
|
| 995 |
+
"learning_rate": 4.063694290980198e-06,
|
| 996 |
+
"loss": 0.2883,
|
| 997 |
+
"step": 7050
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.7718991764412277,
|
| 1001 |
+
"grad_norm": 14.22149658203125,
|
| 1002 |
+
"learning_rate": 3.995506181813225e-06,
|
| 1003 |
+
"loss": 0.2897,
|
| 1004 |
+
"step": 7100
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.7843773396556029,
|
| 1008 |
+
"grad_norm": 15.721160888671875,
|
| 1009 |
+
"learning_rate": 3.927512205934419e-06,
|
| 1010 |
+
"loss": 0.383,
|
| 1011 |
+
"step": 7150
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.7968555028699775,
|
| 1015 |
+
"grad_norm": 8.207934379577637,
|
| 1016 |
+
"learning_rate": 3.859725504185337e-06,
|
| 1017 |
+
"loss": 0.2854,
|
| 1018 |
+
"step": 7200
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.8093336660843524,
|
| 1022 |
+
"grad_norm": 13.97625732421875,
|
| 1023 |
+
"learning_rate": 3.7921591773487496e-06,
|
| 1024 |
+
"loss": 0.296,
|
| 1025 |
+
"step": 7250
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.8218118292987273,
|
| 1029 |
+
"grad_norm": 12.828845024108887,
|
| 1030 |
+
"learning_rate": 3.7248262836167133e-06,
|
| 1031 |
+
"loss": 0.2767,
|
| 1032 |
+
"step": 7300
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.834289992513102,
|
| 1036 |
+
"grad_norm": 12.510878562927246,
|
| 1037 |
+
"learning_rate": 3.6577398360668858e-06,
|
| 1038 |
+
"loss": 0.3011,
|
| 1039 |
+
"step": 7350
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.8467681557274769,
|
| 1043 |
+
"grad_norm": 9.349883079528809,
|
| 1044 |
+
"learning_rate": 3.5909128001475523e-06,
|
| 1045 |
+
"loss": 0.4221,
|
| 1046 |
+
"step": 7400
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.8592463189418518,
|
| 1050 |
+
"grad_norm": 6.913302898406982,
|
| 1051 |
+
"learning_rate": 3.5243580911718666e-06,
|
| 1052 |
+
"loss": 0.3221,
|
| 1053 |
+
"step": 7450
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.8717244821562264,
|
| 1057 |
+
"grad_norm": 7.532046318054199,
|
| 1058 |
+
"learning_rate": 3.45808857182177e-06,
|
| 1059 |
+
"loss": 0.2691,
|
| 1060 |
+
"step": 7500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.8842026453706016,
|
| 1064 |
+
"grad_norm": 6.2996296882629395,
|
| 1065 |
+
"learning_rate": 3.3921170496620926e-06,
|
| 1066 |
+
"loss": 0.3504,
|
| 1067 |
+
"step": 7550
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.8966808085849762,
|
| 1071 |
+
"grad_norm": 13.062787055969238,
|
| 1072 |
+
"learning_rate": 3.3264562746652963e-06,
|
| 1073 |
+
"loss": 0.2446,
|
| 1074 |
+
"step": 7600
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.9091589717993511,
|
| 1078 |
+
"grad_norm": 16.110904693603516,
|
| 1079 |
+
"learning_rate": 3.261118936747362e-06,
|
| 1080 |
+
"loss": 0.3326,
|
| 1081 |
+
"step": 7650
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.921637135013726,
|
| 1085 |
+
"grad_norm": 13.394048690795898,
|
| 1086 |
+
"learning_rate": 3.1961176633152657e-06,
|
| 1087 |
+
"loss": 0.3525,
|
| 1088 |
+
"step": 7700
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.9341152982281007,
|
| 1092 |
+
"grad_norm": 9.24908447265625,
|
| 1093 |
+
"learning_rate": 3.131465016826556e-06,
|
| 1094 |
+
"loss": 0.3851,
|
| 1095 |
+
"step": 7750
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.9465934614424758,
|
| 1099 |
+
"grad_norm": 6.787208080291748,
|
| 1100 |
+
"learning_rate": 3.067173492361465e-06,
|
| 1101 |
+
"loss": 0.3336,
|
| 1102 |
+
"step": 7800
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.9590716246568505,
|
| 1106 |
+
"grad_norm": 7.182611465454102,
|
| 1107 |
+
"learning_rate": 3.003255515208052e-06,
|
| 1108 |
+
"loss": 0.332,
|
| 1109 |
+
"step": 7850
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.9715497878712254,
|
| 1113 |
+
"grad_norm": 12.668556213378906,
|
| 1114 |
+
"learning_rate": 2.9397234384608347e-06,
|
| 1115 |
+
"loss": 0.3065,
|
| 1116 |
+
"step": 7900
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.9840279510856003,
|
| 1120 |
+
"grad_norm": 8.110651969909668,
|
| 1121 |
+
"learning_rate": 2.8765895406333688e-06,
|
| 1122 |
+
"loss": 0.3478,
|
| 1123 |
+
"step": 7950
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.996506114299975,
|
| 1127 |
+
"grad_norm": 7.546565532684326,
|
| 1128 |
+
"learning_rate": 2.8138660232852413e-06,
|
| 1129 |
+
"loss": 0.2889,
|
| 1130 |
+
"step": 8000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.00898427751435,
|
| 1134 |
+
"grad_norm": 9.974661827087402,
|
| 1135 |
+
"learning_rate": 2.751565008663948e-06,
|
| 1136 |
+
"loss": 0.2843,
|
| 1137 |
+
"step": 8050
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.0214624407287247,
|
| 1141 |
+
"grad_norm": 17.447463989257812,
|
| 1142 |
+
"learning_rate": 2.6896985373620765e-06,
|
| 1143 |
+
"loss": 0.186,
|
| 1144 |
+
"step": 8100
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.0339406039430994,
|
| 1148 |
+
"grad_norm": 10.162267684936523,
|
| 1149 |
+
"learning_rate": 2.6282785659902933e-06,
|
| 1150 |
+
"loss": 0.1835,
|
| 1151 |
+
"step": 8150
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.0464187671574745,
|
| 1155 |
+
"grad_norm": 58.194740295410156,
|
| 1156 |
+
"learning_rate": 2.567316964866552e-06,
|
| 1157 |
+
"loss": 0.2702,
|
| 1158 |
+
"step": 8200
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.058896930371849,
|
| 1162 |
+
"grad_norm": 15.600176811218262,
|
| 1163 |
+
"learning_rate": 2.506825515721969e-06,
|
| 1164 |
+
"loss": 0.2462,
|
| 1165 |
+
"step": 8250
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.0713750935862243,
|
| 1169 |
+
"grad_norm": 8.652205467224121,
|
| 1170 |
+
"learning_rate": 2.4468159094238447e-06,
|
| 1171 |
+
"loss": 0.183,
|
| 1172 |
+
"step": 8300
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.083853256800599,
|
| 1176 |
+
"grad_norm": 22.57020378112793,
|
| 1177 |
+
"learning_rate": 2.3872997437162163e-06,
|
| 1178 |
+
"loss": 0.1453,
|
| 1179 |
+
"step": 8350
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.0963314200149736,
|
| 1183 |
+
"grad_norm": 19.869333267211914,
|
| 1184 |
+
"learning_rate": 2.32828852097843e-06,
|
| 1185 |
+
"loss": 0.1631,
|
| 1186 |
+
"step": 8400
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.1088095832293487,
|
| 1190 |
+
"grad_norm": 32.57496643066406,
|
| 1191 |
+
"learning_rate": 2.2697936460021323e-06,
|
| 1192 |
+
"loss": 0.3009,
|
| 1193 |
+
"step": 8450
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.1212877464437234,
|
| 1197 |
+
"grad_norm": 13.605443954467773,
|
| 1198 |
+
"learning_rate": 2.211826423787134e-06,
|
| 1199 |
+
"loss": 0.204,
|
| 1200 |
+
"step": 8500
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.1337659096580985,
|
| 1204 |
+
"grad_norm": 13.936535835266113,
|
| 1205 |
+
"learning_rate": 2.1543980573565375e-06,
|
| 1206 |
+
"loss": 0.2448,
|
| 1207 |
+
"step": 8550
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.146244072872473,
|
| 1211 |
+
"grad_norm": 38.21134948730469,
|
| 1212 |
+
"learning_rate": 2.0975196455915986e-06,
|
| 1213 |
+
"loss": 0.1699,
|
| 1214 |
+
"step": 8600
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.158722236086848,
|
| 1218 |
+
"grad_norm": 32.29157638549805,
|
| 1219 |
+
"learning_rate": 2.041202181086696e-06,
|
| 1220 |
+
"loss": 0.1233,
|
| 1221 |
+
"step": 8650
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.171200399301223,
|
| 1225 |
+
"grad_norm": 19.12054443359375,
|
| 1226 |
+
"learning_rate": 1.985456548024859e-06,
|
| 1227 |
+
"loss": 0.1861,
|
| 1228 |
+
"step": 8700
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.1836785625155977,
|
| 1232 |
+
"grad_norm": 44.0279655456543,
|
| 1233 |
+
"learning_rate": 1.9302935200742274e-06,
|
| 1234 |
+
"loss": 0.188,
|
| 1235 |
+
"step": 8750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.1961567257299723,
|
| 1239 |
+
"grad_norm": 19.22915267944336,
|
| 1240 |
+
"learning_rate": 1.8757237583058874e-06,
|
| 1241 |
+
"loss": 0.1243,
|
| 1242 |
+
"step": 8800
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.2086348889443475,
|
| 1246 |
+
"grad_norm": 15.253983497619629,
|
| 1247 |
+
"learning_rate": 1.8217578091334581e-06,
|
| 1248 |
+
"loss": 0.1867,
|
| 1249 |
+
"step": 8850
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.221113052158722,
|
| 1253 |
+
"grad_norm": 7.043644905090332,
|
| 1254 |
+
"learning_rate": 1.7684061022748488e-06,
|
| 1255 |
+
"loss": 0.2013,
|
| 1256 |
+
"step": 8900
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.2335912153730972,
|
| 1260 |
+
"grad_norm": 26.98235511779785,
|
| 1261 |
+
"learning_rate": 1.7156789487365517e-06,
|
| 1262 |
+
"loss": 0.1564,
|
| 1263 |
+
"step": 8950
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.246069378587472,
|
| 1267 |
+
"grad_norm": 10.906401634216309,
|
| 1268 |
+
"learning_rate": 1.66358653882089e-06,
|
| 1269 |
+
"loss": 0.2835,
|
| 1270 |
+
"step": 9000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.2585475418018466,
|
| 1274 |
+
"grad_norm": 19.038333892822266,
|
| 1275 |
+
"learning_rate": 1.6121389401566e-06,
|
| 1276 |
+
"loss": 0.1398,
|
| 1277 |
+
"step": 9050
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.2710257050162217,
|
| 1281 |
+
"grad_norm": 18.82282066345215,
|
| 1282 |
+
"learning_rate": 1.5613460957531006e-06,
|
| 1283 |
+
"loss": 0.0903,
|
| 1284 |
+
"step": 9100
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.2835038682305964,
|
| 1288 |
+
"grad_norm": 16.515575408935547,
|
| 1289 |
+
"learning_rate": 1.5112178220788659e-06,
|
| 1290 |
+
"loss": 0.2314,
|
| 1291 |
+
"step": 9150
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.2959820314449715,
|
| 1295 |
+
"grad_norm": 30.675432205200195,
|
| 1296 |
+
"learning_rate": 1.4617638071642465e-06,
|
| 1297 |
+
"loss": 0.1902,
|
| 1298 |
+
"step": 9200
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.308460194659346,
|
| 1302 |
+
"grad_norm": 20.497865676879883,
|
| 1303 |
+
"learning_rate": 1.4129936087291185e-06,
|
| 1304 |
+
"loss": 0.1729,
|
| 1305 |
+
"step": 9250
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.320938357873721,
|
| 1309 |
+
"grad_norm": 51.38520812988281,
|
| 1310 |
+
"learning_rate": 1.3649166523357032e-06,
|
| 1311 |
+
"loss": 0.2189,
|
| 1312 |
+
"step": 9300
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.333416521088096,
|
| 1316 |
+
"grad_norm": 32.2943229675293,
|
| 1317 |
+
"learning_rate": 1.3175422295669465e-06,
|
| 1318 |
+
"loss": 0.1505,
|
| 1319 |
+
"step": 9350
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.3458946843024706,
|
| 1323 |
+
"grad_norm": 19.56814193725586,
|
| 1324 |
+
"learning_rate": 1.270879496230778e-06,
|
| 1325 |
+
"loss": 0.2142,
|
| 1326 |
+
"step": 9400
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.3583728475168453,
|
| 1330 |
+
"grad_norm": 26.465316772460938,
|
| 1331 |
+
"learning_rate": 1.2249374705906213e-06,
|
| 1332 |
+
"loss": 0.2112,
|
| 1333 |
+
"step": 9450
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.3708510107312204,
|
| 1337 |
+
"grad_norm": 12.468720436096191,
|
| 1338 |
+
"learning_rate": 1.1797250316224735e-06,
|
| 1339 |
+
"loss": 0.2482,
|
| 1340 |
+
"step": 9500
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.383329173945595,
|
| 1344 |
+
"grad_norm": 20.90337562561035,
|
| 1345 |
+
"learning_rate": 1.1352509172989178e-06,
|
| 1346 |
+
"loss": 0.1546,
|
| 1347 |
+
"step": 9550
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.39580733715997,
|
| 1351 |
+
"grad_norm": 13.431262016296387,
|
| 1352 |
+
"learning_rate": 1.0915237229003773e-06,
|
| 1353 |
+
"loss": 0.2152,
|
| 1354 |
+
"step": 9600
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.408285500374345,
|
| 1358 |
+
"grad_norm": 14.718096733093262,
|
| 1359 |
+
"learning_rate": 1.0485518993539557e-06,
|
| 1360 |
+
"loss": 0.1225,
|
| 1361 |
+
"step": 9650
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.42076366358872,
|
| 1365 |
+
"grad_norm": 33.32410430908203,
|
| 1366 |
+
"learning_rate": 1.0063437516001618e-06,
|
| 1367 |
+
"loss": 0.1854,
|
| 1368 |
+
"step": 9700
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.4332418268030946,
|
| 1372 |
+
"grad_norm": 18.032928466796875,
|
| 1373 |
+
"learning_rate": 9.649074369878642e-07,
|
| 1374 |
+
"loss": 0.1911,
|
| 1375 |
+
"step": 9750
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.4457199900174693,
|
| 1379 |
+
"grad_norm": 42.814205169677734,
|
| 1380 |
+
"learning_rate": 9.242509636977587e-07,
|
| 1381 |
+
"loss": 0.1137,
|
| 1382 |
+
"step": 9800
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.4581981532318444,
|
| 1386 |
+
"grad_norm": 19.89804458618164,
|
| 1387 |
+
"learning_rate": 8.843821891946741e-07,
|
| 1388 |
+
"loss": 0.1548,
|
| 1389 |
+
"step": 9850
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.470676316446219,
|
| 1393 |
+
"grad_norm": 20.889028549194336,
|
| 1394 |
+
"learning_rate": 8.453088187089947e-07,
|
| 1395 |
+
"loss": 0.139,
|
| 1396 |
+
"step": 9900
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.4831544796605938,
|
| 1400 |
+
"grad_norm": 12.794198036193848,
|
| 1401 |
+
"learning_rate": 8.070384037475143e-07,
|
| 1402 |
+
"loss": 0.1279,
|
| 1403 |
+
"step": 9950
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.495632642874969,
|
| 1407 |
+
"grad_norm": 11.888481140136719,
|
| 1408 |
+
"learning_rate": 7.695783406339924e-07,
|
| 1409 |
+
"loss": 0.2145,
|
| 1410 |
+
"step": 10000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.5081108060893436,
|
| 1414 |
+
"grad_norm": 14.029563903808594,
|
| 1415 |
+
"learning_rate": 7.329358690797117e-07,
|
| 1416 |
+
"loss": 0.1323,
|
| 1417 |
+
"step": 10050
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.5205889693037182,
|
| 1421 |
+
"grad_norm": 19.522018432617188,
|
| 1422 |
+
"learning_rate": 6.971180707842922e-07,
|
| 1423 |
+
"loss": 0.158,
|
| 1424 |
+
"step": 10100
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.5330671325180933,
|
| 1428 |
+
"grad_norm": 28.709199905395508,
|
| 1429 |
+
"learning_rate": 6.621318680670463e-07,
|
| 1430 |
+
"loss": 0.2427,
|
| 1431 |
+
"step": 10150
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.545545295732468,
|
| 1435 |
+
"grad_norm": 13.266064643859863,
|
| 1436 |
+
"learning_rate": 6.2798402252914e-07,
|
| 1437 |
+
"loss": 0.2196,
|
| 1438 |
+
"step": 10200
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.558023458946843,
|
| 1442 |
+
"grad_norm": 18.30403709411621,
|
| 1443 |
+
"learning_rate": 5.946811337468183e-07,
|
| 1444 |
+
"loss": 0.1252,
|
| 1445 |
+
"step": 10250
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.570501622161218,
|
| 1449 |
+
"grad_norm": 16.022560119628906,
|
| 1450 |
+
"learning_rate": 5.622296379959313e-07,
|
| 1451 |
+
"loss": 0.1611,
|
| 1452 |
+
"step": 10300
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.582979785375593,
|
| 1456 |
+
"grad_norm": 18.459980010986328,
|
| 1457 |
+
"learning_rate": 5.306358070080336e-07,
|
| 1458 |
+
"loss": 0.1977,
|
| 1459 |
+
"step": 10350
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.5954579485899676,
|
| 1463 |
+
"grad_norm": 15.34239387512207,
|
| 1464 |
+
"learning_rate": 4.999057467582774e-07,
|
| 1465 |
+
"loss": 0.0865,
|
| 1466 |
+
"step": 10400
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.6079361118043423,
|
| 1470 |
+
"grad_norm": 17.409448623657227,
|
| 1471 |
+
"learning_rate": 4.7004539628534627e-07,
|
| 1472 |
+
"loss": 0.1527,
|
| 1473 |
+
"step": 10450
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.6204142750187174,
|
| 1477 |
+
"grad_norm": 17.405305862426758,
|
| 1478 |
+
"learning_rate": 4.4106052654364296e-07,
|
| 1479 |
+
"loss": 0.1455,
|
| 1480 |
+
"step": 10500
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.632892438233092,
|
| 1484 |
+
"grad_norm": 16.738950729370117,
|
| 1485 |
+
"learning_rate": 4.1295673928796906e-07,
|
| 1486 |
+
"loss": 0.142,
|
| 1487 |
+
"step": 10550
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.6453706014474667,
|
| 1491 |
+
"grad_norm": 19.793495178222656,
|
| 1492 |
+
"learning_rate": 3.8573946599090417e-07,
|
| 1493 |
+
"loss": 0.0825,
|
| 1494 |
+
"step": 10600
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.657848764661842,
|
| 1498 |
+
"grad_norm": 19.56559181213379,
|
| 1499 |
+
"learning_rate": 3.5941396679309405e-07,
|
| 1500 |
+
"loss": 0.1802,
|
| 1501 |
+
"step": 10650
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.6703269278762165,
|
| 1505 |
+
"grad_norm": 13.598167419433594,
|
| 1506 |
+
"learning_rate": 3.339853294866469e-07,
|
| 1507 |
+
"loss": 0.0642,
|
| 1508 |
+
"step": 10700
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.6828050910905916,
|
| 1512 |
+
"grad_norm": 23.991165161132812,
|
| 1513 |
+
"learning_rate": 3.094584685318458e-07,
|
| 1514 |
+
"loss": 0.1971,
|
| 1515 |
+
"step": 10750
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.6952832543049663,
|
| 1519 |
+
"grad_norm": 17.074853897094727,
|
| 1520 |
+
"learning_rate": 2.858381241073538e-07,
|
| 1521 |
+
"loss": 0.1918,
|
| 1522 |
+
"step": 10800
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.7077614175193414,
|
| 1526 |
+
"grad_norm": 19.827077865600586,
|
| 1527 |
+
"learning_rate": 2.631288611941096e-07,
|
| 1528 |
+
"loss": 0.2273,
|
| 1529 |
+
"step": 10850
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.720239580733716,
|
| 1533 |
+
"grad_norm": 14.52009105682373,
|
| 1534 |
+
"learning_rate": 2.4133506869307043e-07,
|
| 1535 |
+
"loss": 0.1404,
|
| 1536 |
+
"step": 10900
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.7327177439480907,
|
| 1540 |
+
"grad_norm": 12.993230819702148,
|
| 1541 |
+
"learning_rate": 2.2046095857699623e-07,
|
| 1542 |
+
"loss": 0.1339,
|
| 1543 |
+
"step": 10950
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.745195907162466,
|
| 1547 |
+
"grad_norm": 40.58110427856445,
|
| 1548 |
+
"learning_rate": 2.0051056507642164e-07,
|
| 1549 |
+
"loss": 0.1198,
|
| 1550 |
+
"step": 11000
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.7576740703768405,
|
| 1554 |
+
"grad_norm": 24.50381088256836,
|
| 1555 |
+
"learning_rate": 1.8148774389998626e-07,
|
| 1556 |
+
"loss": 0.1825,
|
| 1557 |
+
"step": 11050
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.770152233591215,
|
| 1561 |
+
"grad_norm": 24.359201431274414,
|
| 1562 |
+
"learning_rate": 1.633961714892529e-07,
|
| 1563 |
+
"loss": 0.1136,
|
| 1564 |
+
"step": 11100
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.7826303968055903,
|
| 1568 |
+
"grad_norm": 36.12211227416992,
|
| 1569 |
+
"learning_rate": 1.462393443081894e-07,
|
| 1570 |
+
"loss": 0.1704,
|
| 1571 |
+
"step": 11150
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.795108560019965,
|
| 1575 |
+
"grad_norm": 39.766082763671875,
|
| 1576 |
+
"learning_rate": 1.300205781674202e-07,
|
| 1577 |
+
"loss": 0.2094,
|
| 1578 |
+
"step": 11200
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.8075867232343397,
|
| 1582 |
+
"grad_norm": 22.819293975830078,
|
| 1583 |
+
"learning_rate": 1.1474300758340052e-07,
|
| 1584 |
+
"loss": 0.0836,
|
| 1585 |
+
"step": 11250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.820064886448715,
|
| 1589 |
+
"grad_norm": 13.354026794433594,
|
| 1590 |
+
"learning_rate": 1.0040958517261945e-07,
|
| 1591 |
+
"loss": 0.146,
|
| 1592 |
+
"step": 11300
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.8325430496630895,
|
| 1596 |
+
"grad_norm": 33.82267379760742,
|
| 1597 |
+
"learning_rate": 8.702308108097024e-08,
|
| 1598 |
+
"loss": 0.1747,
|
| 1599 |
+
"step": 11350
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.8450212128774646,
|
| 1603 |
+
"grad_norm": 26.619991302490234,
|
| 1604 |
+
"learning_rate": 7.458608244837073e-08,
|
| 1605 |
+
"loss": 0.1173,
|
| 1606 |
+
"step": 11400
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.8574993760918392,
|
| 1610 |
+
"grad_norm": 18.810808181762695,
|
| 1611 |
+
"learning_rate": 6.31009929087678e-08,
|
| 1612 |
+
"loss": 0.1694,
|
| 1613 |
+
"step": 11450
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.8699775393062144,
|
| 1617 |
+
"grad_norm": 15.145133972167969,
|
| 1618 |
+
"learning_rate": 5.257003212559453e-08,
|
| 1619 |
+
"loss": 0.1515,
|
| 1620 |
+
"step": 11500
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.882455702520589,
|
| 1624 |
+
"grad_norm": 36.28367233276367,
|
| 1625 |
+
"learning_rate": 4.299523536278938e-08,
|
| 1626 |
+
"loss": 0.0779,
|
| 1627 |
+
"step": 11550
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.8949338657349637,
|
| 1631 |
+
"grad_norm": 21.905363082885742,
|
| 1632 |
+
"learning_rate": 3.437845309144983e-08,
|
| 1633 |
+
"loss": 0.0904,
|
| 1634 |
+
"step": 11600
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.907412028949339,
|
| 1638 |
+
"grad_norm": 23.147872924804688,
|
| 1639 |
+
"learning_rate": 2.6721350632205044e-08,
|
| 1640 |
+
"loss": 0.2007,
|
| 1641 |
+
"step": 11650
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.9198901921637135,
|
| 1645 |
+
"grad_norm": 33.980567932128906,
|
| 1646 |
+
"learning_rate": 2.0025407833362265e-08,
|
| 1647 |
+
"loss": 0.1442,
|
| 1648 |
+
"step": 11700
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.932368355378088,
|
| 1652 |
+
"grad_norm": 33.668724060058594,
|
| 1653 |
+
"learning_rate": 1.4291918784910542e-08,
|
| 1654 |
+
"loss": 0.1689,
|
| 1655 |
+
"step": 11750
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.9448465185924633,
|
| 1659 |
+
"grad_norm": 41.63605499267578,
|
| 1660 |
+
"learning_rate": 9.521991568414158e-09,
|
| 1661 |
+
"loss": 0.1675,
|
| 1662 |
+
"step": 11800
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.957324681806838,
|
| 1666 |
+
"grad_norm": 27.84828758239746,
|
| 1667 |
+
"learning_rate": 5.7165480428611475e-09,
|
| 1668 |
+
"loss": 0.201,
|
| 1669 |
+
"step": 11850
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.9698028450212126,
|
| 1673 |
+
"grad_norm": 20.36393165588379,
|
| 1674 |
+
"learning_rate": 2.8763236665002582e-09,
|
| 1675 |
+
"loss": 0.195,
|
| 1676 |
+
"step": 11900
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.9822810082355877,
|
| 1680 |
+
"grad_norm": 10.760637283325195,
|
| 1681 |
+
"learning_rate": 1.001867354702979e-09,
|
| 1682 |
+
"loss": 0.1057,
|
| 1683 |
+
"step": 11950
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.994759171449963,
|
| 1687 |
+
"grad_norm": 24.99573516845703,
|
| 1688 |
+
"learning_rate": 9.354137387729278e-11,
|
| 1689 |
+
"loss": 0.1154,
|
| 1690 |
+
"step": 12000
|
| 1691 |
+
}
|
| 1692 |
+
],
|
| 1693 |
+
"logging_steps": 50,
|
| 1694 |
+
"max_steps": 12021,
|
| 1695 |
+
"num_input_tokens_seen": 0,
|
| 1696 |
+
"num_train_epochs": 3,
|
| 1697 |
+
"save_steps": 500,
|
| 1698 |
+
"stateful_callbacks": {
|
| 1699 |
+
"TrainerControl": {
|
| 1700 |
+
"args": {
|
| 1701 |
+
"should_epoch_stop": false,
|
| 1702 |
+
"should_evaluate": false,
|
| 1703 |
+
"should_log": false,
|
| 1704 |
+
"should_save": true,
|
| 1705 |
+
"should_training_stop": true
|
| 1706 |
+
},
|
| 1707 |
+
"attributes": {}
|
| 1708 |
+
}
|
| 1709 |
+
},
|
| 1710 |
+
"total_flos": 8.960860132044595e+16,
|
| 1711 |
+
"train_batch_size": 8,
|
| 1712 |
+
"trial_name": null,
|
| 1713 |
+
"trial_params": null
|
| 1714 |
+
}
|
checkpoint-12021/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df7c9cf011f4f9400f1f5cf3c4a7a647c7ffb48e8cc7f55519ab028b9e1751ba
|
| 3 |
+
size 5841
|
checkpoint-8014/added_tokens.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000,
|
| 3 |
+
"[YEAR=2017]": 128001,
|
| 4 |
+
"[YEAR=2018]": 128002,
|
| 5 |
+
"[YEAR=2019]": 128003,
|
| 6 |
+
"[YEAR=2020]": 128004,
|
| 7 |
+
"[YEAR=2021]": 128005,
|
| 8 |
+
"[YEAR=2022]": 128006,
|
| 9 |
+
"[YEAR=2023]": 128007,
|
| 10 |
+
"[YEAR=2024]": 128008,
|
| 11 |
+
"[YEAR=2025]": 128009
|
| 12 |
+
}
|
checkpoint-8014/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4096,
|
| 14 |
+
"layer_norm_eps": 1e-07,
|
| 15 |
+
"legacy": true,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"max_relative_positions": -1,
|
| 18 |
+
"model_type": "deberta-v2",
|
| 19 |
+
"norm_rel_ebd": "layer_norm",
|
| 20 |
+
"num_attention_heads": 16,
|
| 21 |
+
"num_hidden_layers": 24,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pooler_dropout": 0,
|
| 24 |
+
"pooler_hidden_act": "gelu",
|
| 25 |
+
"pooler_hidden_size": 1024,
|
| 26 |
+
"pos_att_type": [
|
| 27 |
+
"p2c",
|
| 28 |
+
"c2p"
|
| 29 |
+
],
|
| 30 |
+
"position_biased_input": false,
|
| 31 |
+
"position_buckets": 256,
|
| 32 |
+
"problem_type": "regression",
|
| 33 |
+
"relative_attention": true,
|
| 34 |
+
"share_att_key": true,
|
| 35 |
+
"transformers_version": "4.57.1",
|
| 36 |
+
"type_vocab_size": 0,
|
| 37 |
+
"use_cache": false,
|
| 38 |
+
"vocab_size": 128010
|
| 39 |
+
}
|
checkpoint-8014/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de9fb7bb0da7340d508f2bc21f6f38b52bd84be56635842e3d8db65a16279689
|
| 3 |
+
size 1739935800
|
checkpoint-8014/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96fda0da9019e1a2c356b6e687a88f725d6df062f1455f1019639d76aaec1bfa
|
| 3 |
+
size 3480108865
|
checkpoint-8014/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be3ddd4753459d14a6a78e1c4babdae7da0ece0ad67b8ff122dd208aed442ace
|
| 3 |
+
size 1465
|
checkpoint-8014/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
checkpoint-8014/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-8014/tokenizer_config.json
ADDED
|
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128001": {
|
| 44 |
+
"content": "[YEAR=2017]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"128002": {
|
| 52 |
+
"content": "[YEAR=2018]",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"128003": {
|
| 60 |
+
"content": "[YEAR=2019]",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"128004": {
|
| 68 |
+
"content": "[YEAR=2020]",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"128005": {
|
| 76 |
+
"content": "[YEAR=2021]",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"128006": {
|
| 84 |
+
"content": "[YEAR=2022]",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"128007": {
|
| 92 |
+
"content": "[YEAR=2023]",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"128008": {
|
| 100 |
+
"content": "[YEAR=2024]",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"128009": {
|
| 108 |
+
"content": "[YEAR=2025]",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
}
|
| 115 |
+
},
|
| 116 |
+
"bos_token": "[CLS]",
|
| 117 |
+
"clean_up_tokenization_spaces": false,
|
| 118 |
+
"cls_token": "[CLS]",
|
| 119 |
+
"do_lower_case": false,
|
| 120 |
+
"eos_token": "[SEP]",
|
| 121 |
+
"extra_special_tokens": {},
|
| 122 |
+
"mask_token": "[MASK]",
|
| 123 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 124 |
+
"pad_token": "[PAD]",
|
| 125 |
+
"sep_token": "[SEP]",
|
| 126 |
+
"sp_model_kwargs": {},
|
| 127 |
+
"split_by_punct": false,
|
| 128 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 129 |
+
"unk_token": "[UNK]",
|
| 130 |
+
"vocab_type": "spm"
|
| 131 |
+
}
|
checkpoint-8014/trainer_state.json
ADDED
|
@@ -0,0 +1,1154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 8014,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.012478163214374845,
|
| 14 |
+
"grad_norm": 4.458792209625244,
|
| 15 |
+
"learning_rate": 6.786703601108035e-07,
|
| 16 |
+
"loss": 0.5794,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02495632642874969,
|
| 21 |
+
"grad_norm": 3.041719436645508,
|
| 22 |
+
"learning_rate": 1.371191135734072e-06,
|
| 23 |
+
"loss": 0.5188,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.037434489643124534,
|
| 28 |
+
"grad_norm": 10.141822814941406,
|
| 29 |
+
"learning_rate": 2.0637119113573407e-06,
|
| 30 |
+
"loss": 0.5702,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04991265285749938,
|
| 35 |
+
"grad_norm": 4.34501838684082,
|
| 36 |
+
"learning_rate": 2.7562326869806094e-06,
|
| 37 |
+
"loss": 0.5027,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.062390816071874224,
|
| 42 |
+
"grad_norm": 6.478577613830566,
|
| 43 |
+
"learning_rate": 3.448753462603878e-06,
|
| 44 |
+
"loss": 0.5349,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07486897928624907,
|
| 49 |
+
"grad_norm": 4.510005950927734,
|
| 50 |
+
"learning_rate": 4.141274238227147e-06,
|
| 51 |
+
"loss": 0.5024,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0873471425006239,
|
| 56 |
+
"grad_norm": 4.612236976623535,
|
| 57 |
+
"learning_rate": 4.833795013850416e-06,
|
| 58 |
+
"loss": 0.4693,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.09982530571499876,
|
| 63 |
+
"grad_norm": 12.051955223083496,
|
| 64 |
+
"learning_rate": 5.526315789473685e-06,
|
| 65 |
+
"loss": 0.5274,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1123034689293736,
|
| 70 |
+
"grad_norm": 11.082642555236816,
|
| 71 |
+
"learning_rate": 6.218836565096953e-06,
|
| 72 |
+
"loss": 0.4646,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.12478163214374845,
|
| 77 |
+
"grad_norm": 5.821896553039551,
|
| 78 |
+
"learning_rate": 6.911357340720221e-06,
|
| 79 |
+
"loss": 0.4762,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.13725979535812327,
|
| 84 |
+
"grad_norm": 10.287369728088379,
|
| 85 |
+
"learning_rate": 7.6038781163434905e-06,
|
| 86 |
+
"loss": 0.5373,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.14973795857249814,
|
| 91 |
+
"grad_norm": 6.837547779083252,
|
| 92 |
+
"learning_rate": 8.29639889196676e-06,
|
| 93 |
+
"loss": 0.4746,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.16221612178687297,
|
| 98 |
+
"grad_norm": 5.090405464172363,
|
| 99 |
+
"learning_rate": 8.988919667590029e-06,
|
| 100 |
+
"loss": 0.4974,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1746942850012478,
|
| 105 |
+
"grad_norm": 7.571693420410156,
|
| 106 |
+
"learning_rate": 9.681440443213298e-06,
|
| 107 |
+
"loss": 0.4859,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.18717244821562265,
|
| 112 |
+
"grad_norm": 5.327805042266846,
|
| 113 |
+
"learning_rate": 9.999859108359658e-06,
|
| 114 |
+
"loss": 0.4728,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.19965061142999752,
|
| 119 |
+
"grad_norm": 8.96234130859375,
|
| 120 |
+
"learning_rate": 9.998854158364854e-06,
|
| 121 |
+
"loss": 0.4707,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.21212877464437235,
|
| 126 |
+
"grad_norm": 6.393317222595215,
|
| 127 |
+
"learning_rate": 9.996883105864235e-06,
|
| 128 |
+
"loss": 0.4647,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2246069378587472,
|
| 133 |
+
"grad_norm": 6.38814115524292,
|
| 134 |
+
"learning_rate": 9.993946331792856e-06,
|
| 135 |
+
"loss": 0.4589,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.23708510107312203,
|
| 140 |
+
"grad_norm": 16.268198013305664,
|
| 141 |
+
"learning_rate": 9.990044403725743e-06,
|
| 142 |
+
"loss": 0.4048,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2495632642874969,
|
| 147 |
+
"grad_norm": 3.3333048820495605,
|
| 148 |
+
"learning_rate": 9.985178075768209e-06,
|
| 149 |
+
"loss": 0.5081,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2620414275018717,
|
| 154 |
+
"grad_norm": 10.300507545471191,
|
| 155 |
+
"learning_rate": 9.979348288410111e-06,
|
| 156 |
+
"loss": 0.4608,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.27451959071624654,
|
| 161 |
+
"grad_norm": 6.351011276245117,
|
| 162 |
+
"learning_rate": 9.97255616834409e-06,
|
| 163 |
+
"loss": 0.4638,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.28699775393062144,
|
| 168 |
+
"grad_norm": 7.574777603149414,
|
| 169 |
+
"learning_rate": 9.964803028247807e-06,
|
| 170 |
+
"loss": 0.427,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.2994759171449963,
|
| 175 |
+
"grad_norm": 12.513327598571777,
|
| 176 |
+
"learning_rate": 9.95609036653027e-06,
|
| 177 |
+
"loss": 0.451,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.3119540803593711,
|
| 182 |
+
"grad_norm": 7.875536918640137,
|
| 183 |
+
"learning_rate": 9.946419867042226e-06,
|
| 184 |
+
"loss": 0.4535,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.32443224357374595,
|
| 189 |
+
"grad_norm": 3.6338303089141846,
|
| 190 |
+
"learning_rate": 9.935793398750741e-06,
|
| 191 |
+
"loss": 0.4618,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.3369104067881208,
|
| 196 |
+
"grad_norm": 122.68341827392578,
|
| 197 |
+
"learning_rate": 9.924213015377991e-06,
|
| 198 |
+
"loss": 0.4842,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.3493885700024956,
|
| 203 |
+
"grad_norm": 14.782501220703125,
|
| 204 |
+
"learning_rate": 9.911680955004353e-06,
|
| 205 |
+
"loss": 0.4984,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.36186673321687046,
|
| 210 |
+
"grad_norm": 8.127388000488281,
|
| 211 |
+
"learning_rate": 9.89819963963586e-06,
|
| 212 |
+
"loss": 0.5211,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3743448964312453,
|
| 217 |
+
"grad_norm": 9.87590503692627,
|
| 218 |
+
"learning_rate": 9.883771674736113e-06,
|
| 219 |
+
"loss": 0.4535,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.38682305964562014,
|
| 224 |
+
"grad_norm": 9.47072696685791,
|
| 225 |
+
"learning_rate": 9.868399848722738e-06,
|
| 226 |
+
"loss": 0.4273,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.39930122285999503,
|
| 231 |
+
"grad_norm": 7.544781684875488,
|
| 232 |
+
"learning_rate": 9.852087132428483e-06,
|
| 233 |
+
"loss": 0.4068,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.41177938607436987,
|
| 238 |
+
"grad_norm": 8.554336547851562,
|
| 239 |
+
"learning_rate": 9.834836678527055e-06,
|
| 240 |
+
"loss": 0.4562,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.4242575492887447,
|
| 245 |
+
"grad_norm": 11.270395278930664,
|
| 246 |
+
"learning_rate": 9.816651820923832e-06,
|
| 247 |
+
"loss": 0.4057,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.43673571250311954,
|
| 252 |
+
"grad_norm": 4.841072082519531,
|
| 253 |
+
"learning_rate": 9.797536074111523e-06,
|
| 254 |
+
"loss": 0.5079,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.4492138757174944,
|
| 259 |
+
"grad_norm": 10.340139389038086,
|
| 260 |
+
"learning_rate": 9.777493132490945e-06,
|
| 261 |
+
"loss": 0.4431,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.4616920389318692,
|
| 266 |
+
"grad_norm": 4.847078800201416,
|
| 267 |
+
"learning_rate": 9.75652686965703e-06,
|
| 268 |
+
"loss": 0.4961,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.47417020214624406,
|
| 273 |
+
"grad_norm": 3.77082896232605,
|
| 274 |
+
"learning_rate": 9.734641337650186e-06,
|
| 275 |
+
"loss": 0.3592,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.4866483653606189,
|
| 280 |
+
"grad_norm": 11.575835227966309,
|
| 281 |
+
"learning_rate": 9.711840766173195e-06,
|
| 282 |
+
"loss": 0.493,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4991265285749938,
|
| 287 |
+
"grad_norm": 8.841684341430664,
|
| 288 |
+
"learning_rate": 9.688129561773742e-06,
|
| 289 |
+
"loss": 0.4283,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5116046917893686,
|
| 294 |
+
"grad_norm": 14.447687149047852,
|
| 295 |
+
"learning_rate": 9.663512306992797e-06,
|
| 296 |
+
"loss": 0.4683,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5240828550037434,
|
| 301 |
+
"grad_norm": 5.287663459777832,
|
| 302 |
+
"learning_rate": 9.637993759478972e-06,
|
| 303 |
+
"loss": 0.4147,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.5365610182181183,
|
| 308 |
+
"grad_norm": 5.344033718109131,
|
| 309 |
+
"learning_rate": 9.611578851069023e-06,
|
| 310 |
+
"loss": 0.4346,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.5490391814324931,
|
| 315 |
+
"grad_norm": 12.01088809967041,
|
| 316 |
+
"learning_rate": 9.584272686834716e-06,
|
| 317 |
+
"loss": 0.364,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.561517344646868,
|
| 322 |
+
"grad_norm": 4.283223628997803,
|
| 323 |
+
"learning_rate": 9.55608054409618e-06,
|
| 324 |
+
"loss": 0.4039,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.5739955078612429,
|
| 329 |
+
"grad_norm": 5.19553804397583,
|
| 330 |
+
"learning_rate": 9.527007871402002e-06,
|
| 331 |
+
"loss": 0.4427,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5864736710756177,
|
| 336 |
+
"grad_norm": 13.137829780578613,
|
| 337 |
+
"learning_rate": 9.4970602874762e-06,
|
| 338 |
+
"loss": 0.515,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5989518342899925,
|
| 343 |
+
"grad_norm": 9.434691429138184,
|
| 344 |
+
"learning_rate": 9.466243580132336e-06,
|
| 345 |
+
"loss": 0.3969,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6114299975043673,
|
| 350 |
+
"grad_norm": 6.398521423339844,
|
| 351 |
+
"learning_rate": 9.434563705154922e-06,
|
| 352 |
+
"loss": 0.4726,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6239081607187422,
|
| 357 |
+
"grad_norm": 11.770699501037598,
|
| 358 |
+
"learning_rate": 9.402026785148385e-06,
|
| 359 |
+
"loss": 0.4433,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.636386323933117,
|
| 364 |
+
"grad_norm": 3.9562103748321533,
|
| 365 |
+
"learning_rate": 9.368639108353781e-06,
|
| 366 |
+
"loss": 0.3859,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6488644871474919,
|
| 371 |
+
"grad_norm": 8.58365535736084,
|
| 372 |
+
"learning_rate": 9.3344071274335e-06,
|
| 373 |
+
"loss": 0.5342,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6613426503618667,
|
| 378 |
+
"grad_norm": 5.637104511260986,
|
| 379 |
+
"learning_rate": 9.29933745822419e-06,
|
| 380 |
+
"loss": 0.3778,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6738208135762416,
|
| 385 |
+
"grad_norm": 7.481651306152344,
|
| 386 |
+
"learning_rate": 9.263436878458151e-06,
|
| 387 |
+
"loss": 0.4751,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6862989767906165,
|
| 392 |
+
"grad_norm": 5.351173400878906,
|
| 393 |
+
"learning_rate": 9.226712326453446e-06,
|
| 394 |
+
"loss": 0.4493,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.6987771400049912,
|
| 399 |
+
"grad_norm": 7.108247756958008,
|
| 400 |
+
"learning_rate": 9.189170899772949e-06,
|
| 401 |
+
"loss": 0.4515,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.7112553032193661,
|
| 406 |
+
"grad_norm": 8.506830215454102,
|
| 407 |
+
"learning_rate": 9.150819853852656e-06,
|
| 408 |
+
"loss": 0.3848,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.7237334664337409,
|
| 413 |
+
"grad_norm": 5.16771936416626,
|
| 414 |
+
"learning_rate": 9.111666600599455e-06,
|
| 415 |
+
"loss": 0.4331,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.7362116296481158,
|
| 420 |
+
"grad_norm": 6.397897243499756,
|
| 421 |
+
"learning_rate": 9.071718706958662e-06,
|
| 422 |
+
"loss": 0.374,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.7486897928624906,
|
| 427 |
+
"grad_norm": 11.78195571899414,
|
| 428 |
+
"learning_rate": 9.030983893451612e-06,
|
| 429 |
+
"loss": 0.415,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.7611679560768655,
|
| 434 |
+
"grad_norm": 16.80957794189453,
|
| 435 |
+
"learning_rate": 8.989470032683534e-06,
|
| 436 |
+
"loss": 0.3573,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.7736461192912403,
|
| 441 |
+
"grad_norm": 7.505095958709717,
|
| 442 |
+
"learning_rate": 8.947185147822064e-06,
|
| 443 |
+
"loss": 0.4102,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.7861242825056152,
|
| 448 |
+
"grad_norm": 8.942618370056152,
|
| 449 |
+
"learning_rate": 8.904137411046656e-06,
|
| 450 |
+
"loss": 0.385,
|
| 451 |
+
"step": 3150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.7986024457199901,
|
| 455 |
+
"grad_norm": 12.872928619384766,
|
| 456 |
+
"learning_rate": 8.860335141969173e-06,
|
| 457 |
+
"loss": 0.4918,
|
| 458 |
+
"step": 3200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.8110806089343648,
|
| 462 |
+
"grad_norm": 7.009009838104248,
|
| 463 |
+
"learning_rate": 8.815786806026008e-06,
|
| 464 |
+
"loss": 0.3944,
|
| 465 |
+
"step": 3250
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.8235587721487397,
|
| 469 |
+
"grad_norm": 9.012943267822266,
|
| 470 |
+
"learning_rate": 8.77050101284201e-06,
|
| 471 |
+
"loss": 0.4019,
|
| 472 |
+
"step": 3300
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.8360369353631145,
|
| 476 |
+
"grad_norm": 4.293410301208496,
|
| 477 |
+
"learning_rate": 8.72448651456655e-06,
|
| 478 |
+
"loss": 0.4727,
|
| 479 |
+
"step": 3350
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.8485150985774894,
|
| 483 |
+
"grad_norm": 6.573951721191406,
|
| 484 |
+
"learning_rate": 8.677752204182038e-06,
|
| 485 |
+
"loss": 0.3932,
|
| 486 |
+
"step": 3400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.8609932617918642,
|
| 490 |
+
"grad_norm": 7.871060848236084,
|
| 491 |
+
"learning_rate": 8.630307113785214e-06,
|
| 492 |
+
"loss": 0.4232,
|
| 493 |
+
"step": 3450
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.8734714250062391,
|
| 497 |
+
"grad_norm": 6.599925994873047,
|
| 498 |
+
"learning_rate": 8.582160412841578e-06,
|
| 499 |
+
"loss": 0.4354,
|
| 500 |
+
"step": 3500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.8859495882206139,
|
| 504 |
+
"grad_norm": 8.174042701721191,
|
| 505 |
+
"learning_rate": 8.533321406413238e-06,
|
| 506 |
+
"loss": 0.4637,
|
| 507 |
+
"step": 3550
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.8984277514349888,
|
| 511 |
+
"grad_norm": 11.967002868652344,
|
| 512 |
+
"learning_rate": 8.48379953336058e-06,
|
| 513 |
+
"loss": 0.3552,
|
| 514 |
+
"step": 3600
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.9109059146493637,
|
| 518 |
+
"grad_norm": 21.131765365600586,
|
| 519 |
+
"learning_rate": 8.433604364518067e-06,
|
| 520 |
+
"loss": 0.3665,
|
| 521 |
+
"step": 3650
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.9233840778637384,
|
| 525 |
+
"grad_norm": 7.3277907371521,
|
| 526 |
+
"learning_rate": 8.38274560084453e-06,
|
| 527 |
+
"loss": 0.4076,
|
| 528 |
+
"step": 3700
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.9358622410781133,
|
| 532 |
+
"grad_norm": 6.7681732177734375,
|
| 533 |
+
"learning_rate": 8.331233071548318e-06,
|
| 534 |
+
"loss": 0.4331,
|
| 535 |
+
"step": 3750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.9483404042924881,
|
| 539 |
+
"grad_norm": 5.008552551269531,
|
| 540 |
+
"learning_rate": 8.27907673218766e-06,
|
| 541 |
+
"loss": 0.4162,
|
| 542 |
+
"step": 3800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.960818567506863,
|
| 546 |
+
"grad_norm": 11.283330917358398,
|
| 547 |
+
"learning_rate": 8.226286662746594e-06,
|
| 548 |
+
"loss": 0.3277,
|
| 549 |
+
"step": 3850
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.9732967307212378,
|
| 553 |
+
"grad_norm": 7.3569746017456055,
|
| 554 |
+
"learning_rate": 8.172873065686877e-06,
|
| 555 |
+
"loss": 0.4533,
|
| 556 |
+
"step": 3900
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.9857748939356127,
|
| 560 |
+
"grad_norm": 15.550161361694336,
|
| 561 |
+
"learning_rate": 8.1188462639762e-06,
|
| 562 |
+
"loss": 0.4304,
|
| 563 |
+
"step": 3950
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.9982530571499876,
|
| 567 |
+
"grad_norm": 9.424723625183105,
|
| 568 |
+
"learning_rate": 8.06421669909312e-06,
|
| 569 |
+
"loss": 0.4069,
|
| 570 |
+
"step": 4000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.0107312203643624,
|
| 574 |
+
"grad_norm": 5.943562030792236,
|
| 575 |
+
"learning_rate": 8.008994929009097e-06,
|
| 576 |
+
"loss": 0.3779,
|
| 577 |
+
"step": 4050
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.0232093835787373,
|
| 581 |
+
"grad_norm": 13.873172760009766,
|
| 582 |
+
"learning_rate": 7.953191626148002e-06,
|
| 583 |
+
"loss": 0.3955,
|
| 584 |
+
"step": 4100
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.0356875467931121,
|
| 588 |
+
"grad_norm": 6.041378974914551,
|
| 589 |
+
"learning_rate": 7.896817575323516e-06,
|
| 590 |
+
"loss": 0.3335,
|
| 591 |
+
"step": 4150
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.0481657100074868,
|
| 595 |
+
"grad_norm": 9.297985076904297,
|
| 596 |
+
"learning_rate": 7.839883671654814e-06,
|
| 597 |
+
"loss": 0.3622,
|
| 598 |
+
"step": 4200
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.0606438732218617,
|
| 602 |
+
"grad_norm": 4.703738689422607,
|
| 603 |
+
"learning_rate": 7.7824009184609e-06,
|
| 604 |
+
"loss": 0.3698,
|
| 605 |
+
"step": 4250
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.0731220364362366,
|
| 609 |
+
"grad_norm": 8.91132926940918,
|
| 610 |
+
"learning_rate": 7.724380425134082e-06,
|
| 611 |
+
"loss": 0.2974,
|
| 612 |
+
"step": 4300
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.0856001996506115,
|
| 616 |
+
"grad_norm": 9.209162712097168,
|
| 617 |
+
"learning_rate": 7.66583340499289e-06,
|
| 618 |
+
"loss": 0.4056,
|
| 619 |
+
"step": 4350
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.0980783628649862,
|
| 623 |
+
"grad_norm": 6.217947959899902,
|
| 624 |
+
"learning_rate": 7.606771173114962e-06,
|
| 625 |
+
"loss": 0.4447,
|
| 626 |
+
"step": 4400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.110556526079361,
|
| 630 |
+
"grad_norm": 7.217406272888184,
|
| 631 |
+
"learning_rate": 7.547205144150211e-06,
|
| 632 |
+
"loss": 0.3444,
|
| 633 |
+
"step": 4450
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.123034689293736,
|
| 637 |
+
"grad_norm": 9.686402320861816,
|
| 638 |
+
"learning_rate": 7.487146830114797e-06,
|
| 639 |
+
"loss": 0.39,
|
| 640 |
+
"step": 4500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.1355128525081108,
|
| 644 |
+
"grad_norm": 7.340874671936035,
|
| 645 |
+
"learning_rate": 7.426607838166252e-06,
|
| 646 |
+
"loss": 0.3825,
|
| 647 |
+
"step": 4550
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.1479910157224857,
|
| 651 |
+
"grad_norm": 24.946033477783203,
|
| 652 |
+
"learning_rate": 7.36559986836022e-06,
|
| 653 |
+
"loss": 0.3891,
|
| 654 |
+
"step": 4600
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.1604691789368604,
|
| 658 |
+
"grad_norm": 9.491501808166504,
|
| 659 |
+
"learning_rate": 7.304134711389256e-06,
|
| 660 |
+
"loss": 0.3215,
|
| 661 |
+
"step": 4650
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1729473421512353,
|
| 665 |
+
"grad_norm": 7.190339088439941,
|
| 666 |
+
"learning_rate": 7.242224246304095e-06,
|
| 667 |
+
"loss": 0.3614,
|
| 668 |
+
"step": 4700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.1854255053656102,
|
| 672 |
+
"grad_norm": 32.30070877075195,
|
| 673 |
+
"learning_rate": 7.179880438217854e-06,
|
| 674 |
+
"loss": 0.3325,
|
| 675 |
+
"step": 4750
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.197903668579985,
|
| 679 |
+
"grad_norm": 8.440774917602539,
|
| 680 |
+
"learning_rate": 7.1171153359935945e-06,
|
| 681 |
+
"loss": 0.3708,
|
| 682 |
+
"step": 4800
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.21038183179436,
|
| 686 |
+
"grad_norm": 7.894869804382324,
|
| 687 |
+
"learning_rate": 7.0539410699156995e-06,
|
| 688 |
+
"loss": 0.3683,
|
| 689 |
+
"step": 4850
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2228599950087347,
|
| 693 |
+
"grad_norm": 10.961115837097168,
|
| 694 |
+
"learning_rate": 6.990369849345519e-06,
|
| 695 |
+
"loss": 0.3572,
|
| 696 |
+
"step": 4900
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.2353381582231096,
|
| 700 |
+
"grad_norm": 7.400118350982666,
|
| 701 |
+
"learning_rate": 6.926413960361734e-06,
|
| 702 |
+
"loss": 0.2907,
|
| 703 |
+
"step": 4950
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.2478163214374844,
|
| 707 |
+
"grad_norm": 7.078188419342041,
|
| 708 |
+
"learning_rate": 6.862085763385882e-06,
|
| 709 |
+
"loss": 0.3524,
|
| 710 |
+
"step": 5000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.2602944846518591,
|
| 714 |
+
"grad_norm": 7.620141983032227,
|
| 715 |
+
"learning_rate": 6.797397690793528e-06,
|
| 716 |
+
"loss": 0.3271,
|
| 717 |
+
"step": 5050
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.272772647866234,
|
| 721 |
+
"grad_norm": 7.046457290649414,
|
| 722 |
+
"learning_rate": 6.732362244511523e-06,
|
| 723 |
+
"loss": 0.4414,
|
| 724 |
+
"step": 5100
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.285250811080609,
|
| 728 |
+
"grad_norm": 15.27204704284668,
|
| 729 |
+
"learning_rate": 6.666991993601821e-06,
|
| 730 |
+
"loss": 0.297,
|
| 731 |
+
"step": 5150
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.2977289742949838,
|
| 735 |
+
"grad_norm": 10.220624923706055,
|
| 736 |
+
"learning_rate": 6.601299571832325e-06,
|
| 737 |
+
"loss": 0.3015,
|
| 738 |
+
"step": 5200
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.3102071375093587,
|
| 742 |
+
"grad_norm": 12.588732719421387,
|
| 743 |
+
"learning_rate": 6.535297675235221e-06,
|
| 744 |
+
"loss": 0.3472,
|
| 745 |
+
"step": 5250
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.3226853007237334,
|
| 749 |
+
"grad_norm": 10.140027046203613,
|
| 750 |
+
"learning_rate": 6.46899905965328e-06,
|
| 751 |
+
"loss": 0.3691,
|
| 752 |
+
"step": 5300
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.3351634639381083,
|
| 756 |
+
"grad_norm": 7.856444358825684,
|
| 757 |
+
"learning_rate": 6.402416538274609e-06,
|
| 758 |
+
"loss": 0.3839,
|
| 759 |
+
"step": 5350
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.3476416271524831,
|
| 763 |
+
"grad_norm": 7.6511712074279785,
|
| 764 |
+
"learning_rate": 6.3355629791563085e-06,
|
| 765 |
+
"loss": 0.361,
|
| 766 |
+
"step": 5400
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.360119790366858,
|
| 770 |
+
"grad_norm": 4.789505481719971,
|
| 771 |
+
"learning_rate": 6.2684513027375336e-06,
|
| 772 |
+
"loss": 0.4478,
|
| 773 |
+
"step": 5450
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.372597953581233,
|
| 777 |
+
"grad_norm": 7.044528007507324,
|
| 778 |
+
"learning_rate": 6.201094479342419e-06,
|
| 779 |
+
"loss": 0.3199,
|
| 780 |
+
"step": 5500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.3850761167956076,
|
| 784 |
+
"grad_norm": 8.48816967010498,
|
| 785 |
+
"learning_rate": 6.133505526673387e-06,
|
| 786 |
+
"loss": 0.3087,
|
| 787 |
+
"step": 5550
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.3975542800099825,
|
| 791 |
+
"grad_norm": 11.27566146850586,
|
| 792 |
+
"learning_rate": 6.065697507295267e-06,
|
| 793 |
+
"loss": 0.3392,
|
| 794 |
+
"step": 5600
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.4100324432243574,
|
| 798 |
+
"grad_norm": 8.946170806884766,
|
| 799 |
+
"learning_rate": 5.997683526110779e-06,
|
| 800 |
+
"loss": 0.3173,
|
| 801 |
+
"step": 5650
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.4225106064387323,
|
| 805 |
+
"grad_norm": 14.0136137008667,
|
| 806 |
+
"learning_rate": 5.929476727827801e-06,
|
| 807 |
+
"loss": 0.3957,
|
| 808 |
+
"step": 5700
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.4349887696531072,
|
| 812 |
+
"grad_norm": 8.724675178527832,
|
| 813 |
+
"learning_rate": 5.861090294418973e-06,
|
| 814 |
+
"loss": 0.4072,
|
| 815 |
+
"step": 5750
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.4474669328674818,
|
| 819 |
+
"grad_norm": 7.454153537750244,
|
| 820 |
+
"learning_rate": 5.792537442574076e-06,
|
| 821 |
+
"loss": 0.3562,
|
| 822 |
+
"step": 5800
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.4599450960818567,
|
| 826 |
+
"grad_norm": 8.835644721984863,
|
| 827 |
+
"learning_rate": 5.723831421145718e-06,
|
| 828 |
+
"loss": 0.3093,
|
| 829 |
+
"step": 5850
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.4724232592962316,
|
| 833 |
+
"grad_norm": 26.4691219329834,
|
| 834 |
+
"learning_rate": 5.6549855085887925e-06,
|
| 835 |
+
"loss": 0.3797,
|
| 836 |
+
"step": 5900
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.4849014225106063,
|
| 840 |
+
"grad_norm": 7.992363452911377,
|
| 841 |
+
"learning_rate": 5.586013010394226e-06,
|
| 842 |
+
"loss": 0.2999,
|
| 843 |
+
"step": 5950
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.4973795857249814,
|
| 847 |
+
"grad_norm": 8.84736156463623,
|
| 848 |
+
"learning_rate": 5.5169272565174866e-06,
|
| 849 |
+
"loss": 0.3515,
|
| 850 |
+
"step": 6000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.509857748939356,
|
| 854 |
+
"grad_norm": 14.053621292114258,
|
| 855 |
+
"learning_rate": 5.447741598802384e-06,
|
| 856 |
+
"loss": 0.3372,
|
| 857 |
+
"step": 6050
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.522335912153731,
|
| 861 |
+
"grad_norm": 12.153364181518555,
|
| 862 |
+
"learning_rate": 5.378469408400618e-06,
|
| 863 |
+
"loss": 0.3291,
|
| 864 |
+
"step": 6100
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.5348140753681059,
|
| 868 |
+
"grad_norm": 8.285240173339844,
|
| 869 |
+
"learning_rate": 5.309124073187613e-06,
|
| 870 |
+
"loss": 0.3676,
|
| 871 |
+
"step": 6150
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.5472922385824806,
|
| 875 |
+
"grad_norm": 11.175989151000977,
|
| 876 |
+
"learning_rate": 5.239718995175107e-06,
|
| 877 |
+
"loss": 0.3833,
|
| 878 |
+
"step": 6200
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.5597704017968557,
|
| 882 |
+
"grad_norm": 7.0034003257751465,
|
| 883 |
+
"learning_rate": 5.170267587921021e-06,
|
| 884 |
+
"loss": 0.3275,
|
| 885 |
+
"step": 6250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.5722485650112303,
|
| 889 |
+
"grad_norm": 14.088438987731934,
|
| 890 |
+
"learning_rate": 5.100783273937084e-06,
|
| 891 |
+
"loss": 0.3754,
|
| 892 |
+
"step": 6300
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.5847267282256052,
|
| 896 |
+
"grad_norm": 7.637153625488281,
|
| 897 |
+
"learning_rate": 5.031279482094741e-06,
|
| 898 |
+
"loss": 0.2582,
|
| 899 |
+
"step": 6350
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.5972048914399801,
|
| 903 |
+
"grad_norm": 16.597148895263672,
|
| 904 |
+
"learning_rate": 4.961769645029815e-06,
|
| 905 |
+
"loss": 0.3279,
|
| 906 |
+
"step": 6400
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.6096830546543548,
|
| 910 |
+
"grad_norm": 5.401224613189697,
|
| 911 |
+
"learning_rate": 4.892267196546468e-06,
|
| 912 |
+
"loss": 0.3662,
|
| 913 |
+
"step": 6450
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.6221612178687297,
|
| 917 |
+
"grad_norm": 17.39789390563965,
|
| 918 |
+
"learning_rate": 4.822785569020898e-06,
|
| 919 |
+
"loss": 0.3882,
|
| 920 |
+
"step": 6500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.6346393810831046,
|
| 924 |
+
"grad_norm": 7.322461128234863,
|
| 925 |
+
"learning_rate": 4.753338190805354e-06,
|
| 926 |
+
"loss": 0.3656,
|
| 927 |
+
"step": 6550
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.6471175442974793,
|
| 931 |
+
"grad_norm": 11.221035957336426,
|
| 932 |
+
"learning_rate": 4.683938483632893e-06,
|
| 933 |
+
"loss": 0.3346,
|
| 934 |
+
"step": 6600
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.6595957075118544,
|
| 938 |
+
"grad_norm": 12.337651252746582,
|
| 939 |
+
"learning_rate": 4.6145998600234405e-06,
|
| 940 |
+
"loss": 0.2959,
|
| 941 |
+
"step": 6650
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.672073870726229,
|
| 945 |
+
"grad_norm": 9.140985488891602,
|
| 946 |
+
"learning_rate": 4.545335720691619e-06,
|
| 947 |
+
"loss": 0.2888,
|
| 948 |
+
"step": 6700
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.684552033940604,
|
| 952 |
+
"grad_norm": 12.107025146484375,
|
| 953 |
+
"learning_rate": 4.476159451956864e-06,
|
| 954 |
+
"loss": 0.3458,
|
| 955 |
+
"step": 6750
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.6970301971549788,
|
| 959 |
+
"grad_norm": 12.792327880859375,
|
| 960 |
+
"learning_rate": 4.407084423156318e-06,
|
| 961 |
+
"loss": 0.3031,
|
| 962 |
+
"step": 6800
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.7095083603693535,
|
| 966 |
+
"grad_norm": 7.57142448425293,
|
| 967 |
+
"learning_rate": 4.338123984061008e-06,
|
| 968 |
+
"loss": 0.3177,
|
| 969 |
+
"step": 6850
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.7219865235837286,
|
| 973 |
+
"grad_norm": 13.280131340026855,
|
| 974 |
+
"learning_rate": 4.269291462295805e-06,
|
| 975 |
+
"loss": 0.3068,
|
| 976 |
+
"step": 6900
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.7344646867981033,
|
| 980 |
+
"grad_norm": 19.578649520874023,
|
| 981 |
+
"learning_rate": 4.200600160763666e-06,
|
| 982 |
+
"loss": 0.2977,
|
| 983 |
+
"step": 6950
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.7469428500124782,
|
| 987 |
+
"grad_norm": 13.223540306091309,
|
| 988 |
+
"learning_rate": 4.1320633550746464e-06,
|
| 989 |
+
"loss": 0.3542,
|
| 990 |
+
"step": 7000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.759421013226853,
|
| 994 |
+
"grad_norm": 13.519241333007812,
|
| 995 |
+
"learning_rate": 4.063694290980198e-06,
|
| 996 |
+
"loss": 0.2883,
|
| 997 |
+
"step": 7050
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.7718991764412277,
|
| 1001 |
+
"grad_norm": 14.22149658203125,
|
| 1002 |
+
"learning_rate": 3.995506181813225e-06,
|
| 1003 |
+
"loss": 0.2897,
|
| 1004 |
+
"step": 7100
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.7843773396556029,
|
| 1008 |
+
"grad_norm": 15.721160888671875,
|
| 1009 |
+
"learning_rate": 3.927512205934419e-06,
|
| 1010 |
+
"loss": 0.383,
|
| 1011 |
+
"step": 7150
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.7968555028699775,
|
| 1015 |
+
"grad_norm": 8.207934379577637,
|
| 1016 |
+
"learning_rate": 3.859725504185337e-06,
|
| 1017 |
+
"loss": 0.2854,
|
| 1018 |
+
"step": 7200
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.8093336660843524,
|
| 1022 |
+
"grad_norm": 13.97625732421875,
|
| 1023 |
+
"learning_rate": 3.7921591773487496e-06,
|
| 1024 |
+
"loss": 0.296,
|
| 1025 |
+
"step": 7250
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.8218118292987273,
|
| 1029 |
+
"grad_norm": 12.828845024108887,
|
| 1030 |
+
"learning_rate": 3.7248262836167133e-06,
|
| 1031 |
+
"loss": 0.2767,
|
| 1032 |
+
"step": 7300
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.834289992513102,
|
| 1036 |
+
"grad_norm": 12.510878562927246,
|
| 1037 |
+
"learning_rate": 3.6577398360668858e-06,
|
| 1038 |
+
"loss": 0.3011,
|
| 1039 |
+
"step": 7350
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.8467681557274769,
|
| 1043 |
+
"grad_norm": 9.349883079528809,
|
| 1044 |
+
"learning_rate": 3.5909128001475523e-06,
|
| 1045 |
+
"loss": 0.4221,
|
| 1046 |
+
"step": 7400
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.8592463189418518,
|
| 1050 |
+
"grad_norm": 6.913302898406982,
|
| 1051 |
+
"learning_rate": 3.5243580911718666e-06,
|
| 1052 |
+
"loss": 0.3221,
|
| 1053 |
+
"step": 7450
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.8717244821562264,
|
| 1057 |
+
"grad_norm": 7.532046318054199,
|
| 1058 |
+
"learning_rate": 3.45808857182177e-06,
|
| 1059 |
+
"loss": 0.2691,
|
| 1060 |
+
"step": 7500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.8842026453706016,
|
| 1064 |
+
"grad_norm": 6.2996296882629395,
|
| 1065 |
+
"learning_rate": 3.3921170496620926e-06,
|
| 1066 |
+
"loss": 0.3504,
|
| 1067 |
+
"step": 7550
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.8966808085849762,
|
| 1071 |
+
"grad_norm": 13.062787055969238,
|
| 1072 |
+
"learning_rate": 3.3264562746652963e-06,
|
| 1073 |
+
"loss": 0.2446,
|
| 1074 |
+
"step": 7600
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.9091589717993511,
|
| 1078 |
+
"grad_norm": 16.110904693603516,
|
| 1079 |
+
"learning_rate": 3.261118936747362e-06,
|
| 1080 |
+
"loss": 0.3326,
|
| 1081 |
+
"step": 7650
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.921637135013726,
|
| 1085 |
+
"grad_norm": 13.394048690795898,
|
| 1086 |
+
"learning_rate": 3.1961176633152657e-06,
|
| 1087 |
+
"loss": 0.3525,
|
| 1088 |
+
"step": 7700
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.9341152982281007,
|
| 1092 |
+
"grad_norm": 9.24908447265625,
|
| 1093 |
+
"learning_rate": 3.131465016826556e-06,
|
| 1094 |
+
"loss": 0.3851,
|
| 1095 |
+
"step": 7750
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.9465934614424758,
|
| 1099 |
+
"grad_norm": 6.787208080291748,
|
| 1100 |
+
"learning_rate": 3.067173492361465e-06,
|
| 1101 |
+
"loss": 0.3336,
|
| 1102 |
+
"step": 7800
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.9590716246568505,
|
| 1106 |
+
"grad_norm": 7.182611465454102,
|
| 1107 |
+
"learning_rate": 3.003255515208052e-06,
|
| 1108 |
+
"loss": 0.332,
|
| 1109 |
+
"step": 7850
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.9715497878712254,
|
| 1113 |
+
"grad_norm": 12.668556213378906,
|
| 1114 |
+
"learning_rate": 2.9397234384608347e-06,
|
| 1115 |
+
"loss": 0.3065,
|
| 1116 |
+
"step": 7900
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.9840279510856003,
|
| 1120 |
+
"grad_norm": 8.110651969909668,
|
| 1121 |
+
"learning_rate": 2.8765895406333688e-06,
|
| 1122 |
+
"loss": 0.3478,
|
| 1123 |
+
"step": 7950
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.996506114299975,
|
| 1127 |
+
"grad_norm": 7.546565532684326,
|
| 1128 |
+
"learning_rate": 2.8138660232852413e-06,
|
| 1129 |
+
"loss": 0.2889,
|
| 1130 |
+
"step": 8000
|
| 1131 |
+
}
|
| 1132 |
+
],
|
| 1133 |
+
"logging_steps": 50,
|
| 1134 |
+
"max_steps": 12021,
|
| 1135 |
+
"num_input_tokens_seen": 0,
|
| 1136 |
+
"num_train_epochs": 3,
|
| 1137 |
+
"save_steps": 500,
|
| 1138 |
+
"stateful_callbacks": {
|
| 1139 |
+
"TrainerControl": {
|
| 1140 |
+
"args": {
|
| 1141 |
+
"should_epoch_stop": false,
|
| 1142 |
+
"should_evaluate": false,
|
| 1143 |
+
"should_log": false,
|
| 1144 |
+
"should_save": true,
|
| 1145 |
+
"should_training_stop": false
|
| 1146 |
+
},
|
| 1147 |
+
"attributes": {}
|
| 1148 |
+
}
|
| 1149 |
+
},
|
| 1150 |
+
"total_flos": 5.973906754696397e+16,
|
| 1151 |
+
"train_batch_size": 8,
|
| 1152 |
+
"trial_name": null,
|
| 1153 |
+
"trial_params": null
|
| 1154 |
+
}
|
checkpoint-8014/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df7c9cf011f4f9400f1f5cf3c4a7a647c7ffb48e8cc7f55519ab028b9e1751ba
|
| 3 |
+
size 5841
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4096,
|
| 14 |
+
"layer_norm_eps": 1e-07,
|
| 15 |
+
"legacy": true,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"max_relative_positions": -1,
|
| 18 |
+
"model_type": "deberta-v2",
|
| 19 |
+
"norm_rel_ebd": "layer_norm",
|
| 20 |
+
"num_attention_heads": 16,
|
| 21 |
+
"num_hidden_layers": 24,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pooler_dropout": 0,
|
| 24 |
+
"pooler_hidden_act": "gelu",
|
| 25 |
+
"pooler_hidden_size": 1024,
|
| 26 |
+
"pos_att_type": [
|
| 27 |
+
"p2c",
|
| 28 |
+
"c2p"
|
| 29 |
+
],
|
| 30 |
+
"position_biased_input": false,
|
| 31 |
+
"position_buckets": 256,
|
| 32 |
+
"problem_type": "regression",
|
| 33 |
+
"relative_attention": true,
|
| 34 |
+
"share_att_key": true,
|
| 35 |
+
"transformers_version": "4.57.1",
|
| 36 |
+
"type_vocab_size": 0,
|
| 37 |
+
"use_cache": false,
|
| 38 |
+
"vocab_size": 128010
|
| 39 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d86a3010e49a8679374ce449892b0a9e1d2aa6ba56a7b03394df30bd9a755a13
|
| 3 |
+
size 1739935800
|
reward_iso.joblib
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a41e9d2523010c22eba2d5cca7ecb9245c7f415411e2f0fc57354c0bb1611f25
|
| 3 |
+
size 20919
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128001": {
|
| 44 |
+
"content": "[YEAR=2017]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"128002": {
|
| 52 |
+
"content": "[YEAR=2018]",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"128003": {
|
| 60 |
+
"content": "[YEAR=2019]",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"128004": {
|
| 68 |
+
"content": "[YEAR=2020]",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"128005": {
|
| 76 |
+
"content": "[YEAR=2021]",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"128006": {
|
| 84 |
+
"content": "[YEAR=2022]",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"128007": {
|
| 92 |
+
"content": "[YEAR=2023]",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"128008": {
|
| 100 |
+
"content": "[YEAR=2024]",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"128009": {
|
| 108 |
+
"content": "[YEAR=2025]",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
}
|
| 115 |
+
},
|
| 116 |
+
"bos_token": "[CLS]",
|
| 117 |
+
"clean_up_tokenization_spaces": false,
|
| 118 |
+
"cls_token": "[CLS]",
|
| 119 |
+
"do_lower_case": false,
|
| 120 |
+
"eos_token": "[SEP]",
|
| 121 |
+
"extra_special_tokens": {},
|
| 122 |
+
"mask_token": "[MASK]",
|
| 123 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 124 |
+
"pad_token": "[PAD]",
|
| 125 |
+
"sep_token": "[SEP]",
|
| 126 |
+
"sp_model_kwargs": {},
|
| 127 |
+
"split_by_punct": false,
|
| 128 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 129 |
+
"unk_token": "[UNK]",
|
| 130 |
+
"vocab_type": "spm"
|
| 131 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df7c9cf011f4f9400f1f5cf3c4a7a647c7ffb48e8cc7f55519ab028b9e1751ba
|
| 3 |
+
size 5841
|
year_z_stats.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"year_stats": {"2017": {"mean": 5.734393939393939, "std": 1.335890119159626}, "2018": {"mean": 5.348607888631091, "std": 1.2111420919734752}, "2019": {"mean": 5.328988603988604, "std": 1.2028410718217644}, "2020": {"mean": 4.193639117265253, "std": 1.7097622239948587}, "2021": {"mean": 5.351257744733582, "std": 1.040507616912965}, "2022": {"mean": 5.191849211594751, "std": 1.342382572148313}, "2023": {"mean": 5.160679239993098, "std": 1.3342913113252441}, "2024": {"mean": 5.135218738196927, "std": 1.261966881292129}, "2025": {"mean": 5.155482795283201, "std": 1.2534368441910395}}, "default": {"mean": 5.123307570820908, "std": 1.3241330929194113}, "target_type": "year_z"}
|