EfficientRAG bilingual (en+ru) — trained on Necent/efficientrag-*-training-data
Browse files- added_tokens.json +3 -0
- config.json +35 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer_config.json +58 -0
- trainer_state.json +860 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "model_cache/deberta-v3-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaForSequenceTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 1024,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 4096,
|
| 12 |
+
"layer_norm_eps": 1e-07,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta-v2",
|
| 16 |
+
"norm_rel_ebd": "layer_norm",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_dropout": 0,
|
| 21 |
+
"pooler_hidden_act": "gelu",
|
| 22 |
+
"pooler_hidden_size": 1024,
|
| 23 |
+
"pos_att_type": [
|
| 24 |
+
"p2c",
|
| 25 |
+
"c2p"
|
| 26 |
+
],
|
| 27 |
+
"position_biased_input": false,
|
| 28 |
+
"position_buckets": 256,
|
| 29 |
+
"relative_attention": true,
|
| 30 |
+
"share_att_key": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.40.2",
|
| 33 |
+
"type_vocab_size": 0,
|
| 34 |
+
"vocab_size": 128100
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:563cea10ca1be6de72a976eefb337b08005464d4e849fa6deb471adb79b5eca4
|
| 3 |
+
size 1740312872
|
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_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"split_by_punct": false,
|
| 55 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 56 |
+
"unk_token": "[UNK]",
|
| 57 |
+
"vocab_type": "spm"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,860 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4942,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.020234722784297856,
|
| 13 |
+
"grad_norm": 8.72037124633789,
|
| 14 |
+
"learning_rate": 1.25e-06,
|
| 15 |
+
"loss": 1.209,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04046944556859571,
|
| 20 |
+
"grad_norm": 5.450883865356445,
|
| 21 |
+
"learning_rate": 2.5e-06,
|
| 22 |
+
"loss": 0.9725,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.060704168352893564,
|
| 27 |
+
"grad_norm": 9.1498441696167,
|
| 28 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 29 |
+
"loss": 0.6988,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.08093889113719142,
|
| 34 |
+
"grad_norm": 7.334131717681885,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.5294,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.10117361392148927,
|
| 41 |
+
"grad_norm": 9.698792457580566,
|
| 42 |
+
"learning_rate": 4.9472796288485875e-06,
|
| 43 |
+
"loss": 0.4225,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12140833670578713,
|
| 48 |
+
"grad_norm": 4.219217777252197,
|
| 49 |
+
"learning_rate": 4.894559257697175e-06,
|
| 50 |
+
"loss": 0.3813,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.141643059490085,
|
| 55 |
+
"grad_norm": 12.876835823059082,
|
| 56 |
+
"learning_rate": 4.841838886545762e-06,
|
| 57 |
+
"loss": 0.333,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.16187778227438285,
|
| 62 |
+
"grad_norm": 8.669962882995605,
|
| 63 |
+
"learning_rate": 4.789118515394349e-06,
|
| 64 |
+
"loss": 0.3039,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1821125050586807,
|
| 69 |
+
"grad_norm": 13.13197135925293,
|
| 70 |
+
"learning_rate": 4.736398144242936e-06,
|
| 71 |
+
"loss": 0.3216,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.20234722784297854,
|
| 76 |
+
"grad_norm": 10.586642265319824,
|
| 77 |
+
"learning_rate": 4.683677773091523e-06,
|
| 78 |
+
"loss": 0.2824,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.20234722784297854,
|
| 83 |
+
"eval_loss": 0.2994783818721771,
|
| 84 |
+
"eval_runtime": 99.3532,
|
| 85 |
+
"eval_samples_per_second": 41.851,
|
| 86 |
+
"eval_steps_per_second": 0.654,
|
| 87 |
+
"eval_tag_accuracy": 0.9016354016354017,
|
| 88 |
+
"eval_tag_f1": 0.9666317639529918,
|
| 89 |
+
"eval_tag_f1-CONTINUE": 0.9075288265882885,
|
| 90 |
+
"eval_tag_f1-FINISH": 0.9075288265882885,
|
| 91 |
+
"eval_tag_f1-TERMINATE": 0.8949396352427433,
|
| 92 |
+
"eval_token_accuracy": 0.9666317639529918,
|
| 93 |
+
"eval_token_f1": 0.9016354016354017,
|
| 94 |
+
"eval_token_f1_negative": 0.9075288265882885,
|
| 95 |
+
"eval_token_f1_positive": 0.8949396352427433,
|
| 96 |
+
"step": 500
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.2225819506272764,
|
| 100 |
+
"grad_norm": 5.3532562255859375,
|
| 101 |
+
"learning_rate": 4.63095740194011e-06,
|
| 102 |
+
"loss": 0.2726,
|
| 103 |
+
"step": 550
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.24281667341157426,
|
| 107 |
+
"grad_norm": 12.720158576965332,
|
| 108 |
+
"learning_rate": 4.578237030788697e-06,
|
| 109 |
+
"loss": 0.255,
|
| 110 |
+
"step": 600
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.2630513961958721,
|
| 114 |
+
"grad_norm": 6.4184088706970215,
|
| 115 |
+
"learning_rate": 4.525516659637284e-06,
|
| 116 |
+
"loss": 0.254,
|
| 117 |
+
"step": 650
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.28328611898017,
|
| 121 |
+
"grad_norm": 7.8461151123046875,
|
| 122 |
+
"learning_rate": 4.4727962884858715e-06,
|
| 123 |
+
"loss": 0.2647,
|
| 124 |
+
"step": 700
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.3035208417644678,
|
| 128 |
+
"grad_norm": 3.1113088130950928,
|
| 129 |
+
"learning_rate": 4.420075917334458e-06,
|
| 130 |
+
"loss": 0.2442,
|
| 131 |
+
"step": 750
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.3237555645487657,
|
| 135 |
+
"grad_norm": 8.432883262634277,
|
| 136 |
+
"learning_rate": 4.367355546183045e-06,
|
| 137 |
+
"loss": 0.247,
|
| 138 |
+
"step": 800
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.3439902873330635,
|
| 142 |
+
"grad_norm": 4.828508377075195,
|
| 143 |
+
"learning_rate": 4.314635175031632e-06,
|
| 144 |
+
"loss": 0.2359,
|
| 145 |
+
"step": 850
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.3642250101173614,
|
| 149 |
+
"grad_norm": 4.320587635040283,
|
| 150 |
+
"learning_rate": 4.26191480388022e-06,
|
| 151 |
+
"loss": 0.2549,
|
| 152 |
+
"step": 900
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.38445973290165925,
|
| 156 |
+
"grad_norm": 8.660967826843262,
|
| 157 |
+
"learning_rate": 4.209194432728807e-06,
|
| 158 |
+
"loss": 0.2453,
|
| 159 |
+
"step": 950
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.4046944556859571,
|
| 163 |
+
"grad_norm": 6.111636161804199,
|
| 164 |
+
"learning_rate": 4.156474061577394e-06,
|
| 165 |
+
"loss": 0.2447,
|
| 166 |
+
"step": 1000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.4046944556859571,
|
| 170 |
+
"eval_loss": 0.26576703786849976,
|
| 171 |
+
"eval_runtime": 89.7698,
|
| 172 |
+
"eval_samples_per_second": 46.318,
|
| 173 |
+
"eval_steps_per_second": 0.724,
|
| 174 |
+
"eval_tag_accuracy": 0.9086099086099086,
|
| 175 |
+
"eval_tag_f1": 0.9704089737670849,
|
| 176 |
+
"eval_tag_f1-CONTINUE": 0.9146067415730337,
|
| 177 |
+
"eval_tag_f1-FINISH": 0.9146067415730337,
|
| 178 |
+
"eval_tag_f1-TERMINATE": 0.9017071908949819,
|
| 179 |
+
"eval_token_accuracy": 0.9704089737670849,
|
| 180 |
+
"eval_token_f1": 0.9086099086099086,
|
| 181 |
+
"eval_token_f1_negative": 0.9146067415730337,
|
| 182 |
+
"eval_token_f1_positive": 0.9017071908949819,
|
| 183 |
+
"step": 1000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.42492917847025496,
|
| 187 |
+
"grad_norm": 6.170385837554932,
|
| 188 |
+
"learning_rate": 4.103753690425981e-06,
|
| 189 |
+
"loss": 0.2341,
|
| 190 |
+
"step": 1050
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.4451639012545528,
|
| 194 |
+
"grad_norm": 9.265089988708496,
|
| 195 |
+
"learning_rate": 4.051033319274568e-06,
|
| 196 |
+
"loss": 0.2335,
|
| 197 |
+
"step": 1100
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.4653986240388507,
|
| 201 |
+
"grad_norm": 8.301984786987305,
|
| 202 |
+
"learning_rate": 3.9983129481231555e-06,
|
| 203 |
+
"loss": 0.2176,
|
| 204 |
+
"step": 1150
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.4856333468231485,
|
| 208 |
+
"grad_norm": 2.7331886291503906,
|
| 209 |
+
"learning_rate": 3.945592576971743e-06,
|
| 210 |
+
"loss": 0.2537,
|
| 211 |
+
"step": 1200
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.5058680696074463,
|
| 215 |
+
"grad_norm": 3.475696325302124,
|
| 216 |
+
"learning_rate": 3.89287220582033e-06,
|
| 217 |
+
"loss": 0.2384,
|
| 218 |
+
"step": 1250
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.5261027923917442,
|
| 222 |
+
"grad_norm": 10.670371055603027,
|
| 223 |
+
"learning_rate": 3.840151834668917e-06,
|
| 224 |
+
"loss": 0.2076,
|
| 225 |
+
"step": 1300
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.5463375151760421,
|
| 229 |
+
"grad_norm": 7.286683559417725,
|
| 230 |
+
"learning_rate": 3.7874314635175035e-06,
|
| 231 |
+
"loss": 0.2209,
|
| 232 |
+
"step": 1350
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.56657223796034,
|
| 236 |
+
"grad_norm": 5.6653876304626465,
|
| 237 |
+
"learning_rate": 3.7347110923660906e-06,
|
| 238 |
+
"loss": 0.2277,
|
| 239 |
+
"step": 1400
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.5868069607446378,
|
| 243 |
+
"grad_norm": 8.548470497131348,
|
| 244 |
+
"learning_rate": 3.6819907212146777e-06,
|
| 245 |
+
"loss": 0.2178,
|
| 246 |
+
"step": 1450
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.6070416835289356,
|
| 250 |
+
"grad_norm": 1.2667831182479858,
|
| 251 |
+
"learning_rate": 3.629270350063265e-06,
|
| 252 |
+
"loss": 0.2116,
|
| 253 |
+
"step": 1500
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.6070416835289356,
|
| 257 |
+
"eval_loss": 0.21864494681358337,
|
| 258 |
+
"eval_runtime": 87.99,
|
| 259 |
+
"eval_samples_per_second": 47.255,
|
| 260 |
+
"eval_steps_per_second": 0.739,
|
| 261 |
+
"eval_tag_accuracy": 0.9336219336219336,
|
| 262 |
+
"eval_tag_f1": 0.9717647246654861,
|
| 263 |
+
"eval_tag_f1-CONTINUE": 0.9345351043643264,
|
| 264 |
+
"eval_tag_f1-FINISH": 0.9345351043643264,
|
| 265 |
+
"eval_tag_f1-TERMINATE": 0.9326829268292683,
|
| 266 |
+
"eval_token_accuracy": 0.9717647246654861,
|
| 267 |
+
"eval_token_f1": 0.9336219336219336,
|
| 268 |
+
"eval_token_f1_negative": 0.9345351043643264,
|
| 269 |
+
"eval_token_f1_positive": 0.9326829268292683,
|
| 270 |
+
"step": 1500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.6272764063132336,
|
| 274 |
+
"grad_norm": 12.82320785522461,
|
| 275 |
+
"learning_rate": 3.576549978911852e-06,
|
| 276 |
+
"loss": 0.2244,
|
| 277 |
+
"step": 1550
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.6475111290975314,
|
| 281 |
+
"grad_norm": 5.0135955810546875,
|
| 282 |
+
"learning_rate": 3.523829607760439e-06,
|
| 283 |
+
"loss": 0.1991,
|
| 284 |
+
"step": 1600
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.6677458518818292,
|
| 288 |
+
"grad_norm": 5.661144733428955,
|
| 289 |
+
"learning_rate": 3.471109236609026e-06,
|
| 290 |
+
"loss": 0.2301,
|
| 291 |
+
"step": 1650
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.687980574666127,
|
| 295 |
+
"grad_norm": 4.150299549102783,
|
| 296 |
+
"learning_rate": 3.4183888654576133e-06,
|
| 297 |
+
"loss": 0.215,
|
| 298 |
+
"step": 1700
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.7082152974504249,
|
| 302 |
+
"grad_norm": 1.3773038387298584,
|
| 303 |
+
"learning_rate": 3.3656684943062e-06,
|
| 304 |
+
"loss": 0.2415,
|
| 305 |
+
"step": 1750
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.7284500202347228,
|
| 309 |
+
"grad_norm": 7.56788969039917,
|
| 310 |
+
"learning_rate": 3.312948123154787e-06,
|
| 311 |
+
"loss": 0.215,
|
| 312 |
+
"step": 1800
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.7486847430190207,
|
| 316 |
+
"grad_norm": 9.647685050964355,
|
| 317 |
+
"learning_rate": 3.260227752003374e-06,
|
| 318 |
+
"loss": 0.2187,
|
| 319 |
+
"step": 1850
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.7689194658033185,
|
| 323 |
+
"grad_norm": 3.352022409439087,
|
| 324 |
+
"learning_rate": 3.2075073808519613e-06,
|
| 325 |
+
"loss": 0.232,
|
| 326 |
+
"step": 1900
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.7891541885876163,
|
| 330 |
+
"grad_norm": 6.138416290283203,
|
| 331 |
+
"learning_rate": 3.1547870097005484e-06,
|
| 332 |
+
"loss": 0.2067,
|
| 333 |
+
"step": 1950
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.8093889113719142,
|
| 337 |
+
"grad_norm": 5.341176509857178,
|
| 338 |
+
"learning_rate": 3.1020666385491355e-06,
|
| 339 |
+
"loss": 0.2068,
|
| 340 |
+
"step": 2000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.8093889113719142,
|
| 344 |
+
"eval_loss": 0.202407106757164,
|
| 345 |
+
"eval_runtime": 99.5295,
|
| 346 |
+
"eval_samples_per_second": 41.777,
|
| 347 |
+
"eval_steps_per_second": 0.653,
|
| 348 |
+
"eval_tag_accuracy": 0.9377104377104377,
|
| 349 |
+
"eval_tag_f1": 0.973316054937847,
|
| 350 |
+
"eval_tag_f1-CONTINUE": 0.93849441937782,
|
| 351 |
+
"eval_tag_f1-FINISH": 0.93849441937782,
|
| 352 |
+
"eval_tag_f1-TERMINATE": 0.9369062119366626,
|
| 353 |
+
"eval_token_accuracy": 0.973316054937847,
|
| 354 |
+
"eval_token_f1": 0.9377104377104377,
|
| 355 |
+
"eval_token_f1_negative": 0.93849441937782,
|
| 356 |
+
"eval_token_f1_positive": 0.9369062119366626,
|
| 357 |
+
"step": 2000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.8296236341562121,
|
| 361 |
+
"grad_norm": 3.7065298557281494,
|
| 362 |
+
"learning_rate": 3.0493462673977226e-06,
|
| 363 |
+
"loss": 0.2186,
|
| 364 |
+
"step": 2050
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.8498583569405099,
|
| 368 |
+
"grad_norm": 11.173847198486328,
|
| 369 |
+
"learning_rate": 2.9966258962463097e-06,
|
| 370 |
+
"loss": 0.2298,
|
| 371 |
+
"step": 2100
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.8700930797248078,
|
| 375 |
+
"grad_norm": 7.461451053619385,
|
| 376 |
+
"learning_rate": 2.943905525094897e-06,
|
| 377 |
+
"loss": 0.2171,
|
| 378 |
+
"step": 2150
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.8903278025091056,
|
| 382 |
+
"grad_norm": 5.774527549743652,
|
| 383 |
+
"learning_rate": 2.891185153943484e-06,
|
| 384 |
+
"loss": 0.2008,
|
| 385 |
+
"step": 2200
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.9105625252934035,
|
| 389 |
+
"grad_norm": 13.355608940124512,
|
| 390 |
+
"learning_rate": 2.8384647827920706e-06,
|
| 391 |
+
"loss": 0.1928,
|
| 392 |
+
"step": 2250
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.9307972480777014,
|
| 396 |
+
"grad_norm": 5.512803554534912,
|
| 397 |
+
"learning_rate": 2.7857444116406586e-06,
|
| 398 |
+
"loss": 0.2151,
|
| 399 |
+
"step": 2300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.9510319708619992,
|
| 403 |
+
"grad_norm": 7.355721473693848,
|
| 404 |
+
"learning_rate": 2.7330240404892457e-06,
|
| 405 |
+
"loss": 0.2313,
|
| 406 |
+
"step": 2350
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.971266693646297,
|
| 410 |
+
"grad_norm": 8.145475387573242,
|
| 411 |
+
"learning_rate": 2.680303669337833e-06,
|
| 412 |
+
"loss": 0.206,
|
| 413 |
+
"step": 2400
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.9915014164305949,
|
| 417 |
+
"grad_norm": 3.35742449760437,
|
| 418 |
+
"learning_rate": 2.6275832981864195e-06,
|
| 419 |
+
"loss": 0.2126,
|
| 420 |
+
"step": 2450
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.0117361392148927,
|
| 424 |
+
"grad_norm": 4.693106651306152,
|
| 425 |
+
"learning_rate": 2.5748629270350066e-06,
|
| 426 |
+
"loss": 0.1958,
|
| 427 |
+
"step": 2500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.0117361392148927,
|
| 431 |
+
"eval_loss": 0.20388753712177277,
|
| 432 |
+
"eval_runtime": 90.2103,
|
| 433 |
+
"eval_samples_per_second": 46.092,
|
| 434 |
+
"eval_steps_per_second": 0.721,
|
| 435 |
+
"eval_tag_accuracy": 0.9321789321789322,
|
| 436 |
+
"eval_tag_f1": 0.9744642522149032,
|
| 437 |
+
"eval_tag_f1-CONTINUE": 0.9338338808071328,
|
| 438 |
+
"eval_tag_f1-FINISH": 0.9338338808071328,
|
| 439 |
+
"eval_tag_f1-TERMINATE": 0.9304390725209669,
|
| 440 |
+
"eval_token_accuracy": 0.9744642522149032,
|
| 441 |
+
"eval_token_f1": 0.9321789321789322,
|
| 442 |
+
"eval_token_f1_negative": 0.9338338808071328,
|
| 443 |
+
"eval_token_f1_positive": 0.9304390725209669,
|
| 444 |
+
"step": 2500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.0319708619991905,
|
| 448 |
+
"grad_norm": 4.066263675689697,
|
| 449 |
+
"learning_rate": 2.5221425558835937e-06,
|
| 450 |
+
"loss": 0.1705,
|
| 451 |
+
"step": 2550
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.0522055847834886,
|
| 455 |
+
"grad_norm": 1.981619954109192,
|
| 456 |
+
"learning_rate": 2.4694221847321804e-06,
|
| 457 |
+
"loss": 0.2019,
|
| 458 |
+
"step": 2600
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.0724403075677864,
|
| 462 |
+
"grad_norm": 17.264829635620117,
|
| 463 |
+
"learning_rate": 2.416701813580768e-06,
|
| 464 |
+
"loss": 0.1502,
|
| 465 |
+
"step": 2650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.0926750303520842,
|
| 469 |
+
"grad_norm": 8.771439552307129,
|
| 470 |
+
"learning_rate": 2.363981442429355e-06,
|
| 471 |
+
"loss": 0.1552,
|
| 472 |
+
"step": 2700
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.112909753136382,
|
| 476 |
+
"grad_norm": 11.144837379455566,
|
| 477 |
+
"learning_rate": 2.311261071277942e-06,
|
| 478 |
+
"loss": 0.1537,
|
| 479 |
+
"step": 2750
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.13314447592068,
|
| 483 |
+
"grad_norm": 3.879704475402832,
|
| 484 |
+
"learning_rate": 2.2585407001265293e-06,
|
| 485 |
+
"loss": 0.1816,
|
| 486 |
+
"step": 2800
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.1533791987049777,
|
| 490 |
+
"grad_norm": 4.202072620391846,
|
| 491 |
+
"learning_rate": 2.2058203289751164e-06,
|
| 492 |
+
"loss": 0.1522,
|
| 493 |
+
"step": 2850
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.1736139214892756,
|
| 497 |
+
"grad_norm": 19.130678176879883,
|
| 498 |
+
"learning_rate": 2.1530999578237035e-06,
|
| 499 |
+
"loss": 0.1646,
|
| 500 |
+
"step": 2900
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.1938486442735734,
|
| 504 |
+
"grad_norm": 1.3073982000350952,
|
| 505 |
+
"learning_rate": 2.10037958667229e-06,
|
| 506 |
+
"loss": 0.1594,
|
| 507 |
+
"step": 2950
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.2140833670578712,
|
| 511 |
+
"grad_norm": 6.3615851402282715,
|
| 512 |
+
"learning_rate": 2.0476592155208773e-06,
|
| 513 |
+
"loss": 0.1616,
|
| 514 |
+
"step": 3000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.2140833670578712,
|
| 518 |
+
"eval_loss": 0.21922506392002106,
|
| 519 |
+
"eval_runtime": 90.428,
|
| 520 |
+
"eval_samples_per_second": 45.981,
|
| 521 |
+
"eval_steps_per_second": 0.719,
|
| 522 |
+
"eval_tag_accuracy": 0.9391534391534392,
|
| 523 |
+
"eval_tag_f1": 0.974827471052257,
|
| 524 |
+
"eval_tag_f1-CONTINUE": 0.9403161122906346,
|
| 525 |
+
"eval_tag_f1-FINISH": 0.9403161122906346,
|
| 526 |
+
"eval_tag_f1-TERMINATE": 0.9379445670836399,
|
| 527 |
+
"eval_token_accuracy": 0.974827471052257,
|
| 528 |
+
"eval_token_f1": 0.9391534391534392,
|
| 529 |
+
"eval_token_f1_negative": 0.9403161122906346,
|
| 530 |
+
"eval_token_f1_positive": 0.9379445670836399,
|
| 531 |
+
"step": 3000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.2343180898421693,
|
| 535 |
+
"grad_norm": 5.983785152435303,
|
| 536 |
+
"learning_rate": 1.9949388443694644e-06,
|
| 537 |
+
"loss": 0.1884,
|
| 538 |
+
"step": 3050
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.254552812626467,
|
| 542 |
+
"grad_norm": 7.194103717803955,
|
| 543 |
+
"learning_rate": 1.9422184732180515e-06,
|
| 544 |
+
"loss": 0.1682,
|
| 545 |
+
"step": 3100
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.274787535410765,
|
| 549 |
+
"grad_norm": 8.178751945495605,
|
| 550 |
+
"learning_rate": 1.8894981020666386e-06,
|
| 551 |
+
"loss": 0.1621,
|
| 552 |
+
"step": 3150
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.2950222581950628,
|
| 556 |
+
"grad_norm": 9.569229125976562,
|
| 557 |
+
"learning_rate": 1.8367777309152257e-06,
|
| 558 |
+
"loss": 0.162,
|
| 559 |
+
"step": 3200
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.3152569809793606,
|
| 563 |
+
"grad_norm": 10.708954811096191,
|
| 564 |
+
"learning_rate": 1.7840573597638128e-06,
|
| 565 |
+
"loss": 0.1437,
|
| 566 |
+
"step": 3250
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.3354917037636584,
|
| 570 |
+
"grad_norm": 8.722265243530273,
|
| 571 |
+
"learning_rate": 1.7313369886124e-06,
|
| 572 |
+
"loss": 0.163,
|
| 573 |
+
"step": 3300
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.3557264265479563,
|
| 577 |
+
"grad_norm": 1.2432576417922974,
|
| 578 |
+
"learning_rate": 1.6786166174609872e-06,
|
| 579 |
+
"loss": 0.1529,
|
| 580 |
+
"step": 3350
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.375961149332254,
|
| 584 |
+
"grad_norm": 8.486040115356445,
|
| 585 |
+
"learning_rate": 1.6258962463095744e-06,
|
| 586 |
+
"loss": 0.1509,
|
| 587 |
+
"step": 3400
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.396195872116552,
|
| 591 |
+
"grad_norm": 7.521843910217285,
|
| 592 |
+
"learning_rate": 1.5731758751581612e-06,
|
| 593 |
+
"loss": 0.176,
|
| 594 |
+
"step": 3450
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.41643059490085,
|
| 598 |
+
"grad_norm": 5.913136959075928,
|
| 599 |
+
"learning_rate": 1.5204555040067484e-06,
|
| 600 |
+
"loss": 0.1635,
|
| 601 |
+
"step": 3500
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.41643059490085,
|
| 605 |
+
"eval_loss": 0.21361203491687775,
|
| 606 |
+
"eval_runtime": 99.2858,
|
| 607 |
+
"eval_samples_per_second": 41.879,
|
| 608 |
+
"eval_steps_per_second": 0.655,
|
| 609 |
+
"eval_tag_accuracy": 0.9389129389129389,
|
| 610 |
+
"eval_tag_f1": 0.9748354538838472,
|
| 611 |
+
"eval_tag_f1-CONTINUE": 0.9399243140964996,
|
| 612 |
+
"eval_tag_f1-FINISH": 0.9399243140964996,
|
| 613 |
+
"eval_tag_f1-TERMINATE": 0.937866927592955,
|
| 614 |
+
"eval_token_accuracy": 0.9748354538838472,
|
| 615 |
+
"eval_token_f1": 0.9389129389129389,
|
| 616 |
+
"eval_token_f1_negative": 0.9399243140964996,
|
| 617 |
+
"eval_token_f1_positive": 0.937866927592955,
|
| 618 |
+
"step": 3500
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.4366653176851476,
|
| 622 |
+
"grad_norm": 3.9816882610321045,
|
| 623 |
+
"learning_rate": 1.4677351328553355e-06,
|
| 624 |
+
"loss": 0.1598,
|
| 625 |
+
"step": 3550
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.4569000404694457,
|
| 629 |
+
"grad_norm": 11.924986839294434,
|
| 630 |
+
"learning_rate": 1.4150147617039226e-06,
|
| 631 |
+
"loss": 0.1722,
|
| 632 |
+
"step": 3600
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.4771347632537435,
|
| 636 |
+
"grad_norm": 4.420969009399414,
|
| 637 |
+
"learning_rate": 1.3622943905525097e-06,
|
| 638 |
+
"loss": 0.1408,
|
| 639 |
+
"step": 3650
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.4973694860380413,
|
| 643 |
+
"grad_norm": 11.450356483459473,
|
| 644 |
+
"learning_rate": 1.3095740194010966e-06,
|
| 645 |
+
"loss": 0.167,
|
| 646 |
+
"step": 3700
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.5176042088223392,
|
| 650 |
+
"grad_norm": 8.506190299987793,
|
| 651 |
+
"learning_rate": 1.2568536482496837e-06,
|
| 652 |
+
"loss": 0.1547,
|
| 653 |
+
"step": 3750
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.537838931606637,
|
| 657 |
+
"grad_norm": 2.8181309700012207,
|
| 658 |
+
"learning_rate": 1.2041332770982708e-06,
|
| 659 |
+
"loss": 0.1425,
|
| 660 |
+
"step": 3800
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.5580736543909348,
|
| 664 |
+
"grad_norm": 2.5935609340667725,
|
| 665 |
+
"learning_rate": 1.151412905946858e-06,
|
| 666 |
+
"loss": 0.1547,
|
| 667 |
+
"step": 3850
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.5783083771752326,
|
| 671 |
+
"grad_norm": 10.59027099609375,
|
| 672 |
+
"learning_rate": 1.098692534795445e-06,
|
| 673 |
+
"loss": 0.1495,
|
| 674 |
+
"step": 3900
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.5985430999595307,
|
| 678 |
+
"grad_norm": 2.5813493728637695,
|
| 679 |
+
"learning_rate": 1.0459721636440321e-06,
|
| 680 |
+
"loss": 0.1305,
|
| 681 |
+
"step": 3950
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.6187778227438283,
|
| 685 |
+
"grad_norm": 1.844016671180725,
|
| 686 |
+
"learning_rate": 9.932517924926192e-07,
|
| 687 |
+
"loss": 0.1566,
|
| 688 |
+
"step": 4000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.6187778227438283,
|
| 692 |
+
"eval_loss": 0.22482524812221527,
|
| 693 |
+
"eval_runtime": 87.0812,
|
| 694 |
+
"eval_samples_per_second": 47.749,
|
| 695 |
+
"eval_steps_per_second": 0.746,
|
| 696 |
+
"eval_tag_accuracy": 0.9377104377104377,
|
| 697 |
+
"eval_tag_f1": 0.9749232650313393,
|
| 698 |
+
"eval_tag_f1-CONTINUE": 0.9394718392147698,
|
| 699 |
+
"eval_tag_f1-FINISH": 0.9394718392147698,
|
| 700 |
+
"eval_tag_f1-TERMINATE": 0.9358434481050285,
|
| 701 |
+
"eval_token_accuracy": 0.9749232650313393,
|
| 702 |
+
"eval_token_f1": 0.9377104377104377,
|
| 703 |
+
"eval_token_f1_negative": 0.9394718392147698,
|
| 704 |
+
"eval_token_f1_positive": 0.9358434481050285,
|
| 705 |
+
"step": 4000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.6390125455281264,
|
| 709 |
+
"grad_norm": 9.678681373596191,
|
| 710 |
+
"learning_rate": 9.405314213412063e-07,
|
| 711 |
+
"loss": 0.1682,
|
| 712 |
+
"step": 4050
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.659247268312424,
|
| 716 |
+
"grad_norm": 11.279572486877441,
|
| 717 |
+
"learning_rate": 8.878110501897934e-07,
|
| 718 |
+
"loss": 0.1655,
|
| 719 |
+
"step": 4100
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 1.679481991096722,
|
| 723 |
+
"grad_norm": 6.408283710479736,
|
| 724 |
+
"learning_rate": 8.350906790383805e-07,
|
| 725 |
+
"loss": 0.1375,
|
| 726 |
+
"step": 4150
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 1.6997167138810199,
|
| 730 |
+
"grad_norm": 8.360751152038574,
|
| 731 |
+
"learning_rate": 7.823703078869676e-07,
|
| 732 |
+
"loss": 0.148,
|
| 733 |
+
"step": 4200
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.7199514366653177,
|
| 737 |
+
"grad_norm": 9.093498229980469,
|
| 738 |
+
"learning_rate": 7.296499367355547e-07,
|
| 739 |
+
"loss": 0.1511,
|
| 740 |
+
"step": 4250
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.7401861594496155,
|
| 744 |
+
"grad_norm": 8.47696304321289,
|
| 745 |
+
"learning_rate": 6.769295655841418e-07,
|
| 746 |
+
"loss": 0.183,
|
| 747 |
+
"step": 4300
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.7604208822339134,
|
| 751 |
+
"grad_norm": 5.258668422698975,
|
| 752 |
+
"learning_rate": 6.242091944327289e-07,
|
| 753 |
+
"loss": 0.1583,
|
| 754 |
+
"step": 4350
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.7806556050182114,
|
| 758 |
+
"grad_norm": 2.8200266361236572,
|
| 759 |
+
"learning_rate": 5.714888232813159e-07,
|
| 760 |
+
"loss": 0.1392,
|
| 761 |
+
"step": 4400
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.800890327802509,
|
| 765 |
+
"grad_norm": 1.5096231698989868,
|
| 766 |
+
"learning_rate": 5.18768452129903e-07,
|
| 767 |
+
"loss": 0.1252,
|
| 768 |
+
"step": 4450
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.821125050586807,
|
| 772 |
+
"grad_norm": 7.513113975524902,
|
| 773 |
+
"learning_rate": 4.660480809784902e-07,
|
| 774 |
+
"loss": 0.165,
|
| 775 |
+
"step": 4500
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.821125050586807,
|
| 779 |
+
"eval_loss": 0.21320512890815735,
|
| 780 |
+
"eval_runtime": 90.0868,
|
| 781 |
+
"eval_samples_per_second": 46.156,
|
| 782 |
+
"eval_steps_per_second": 0.722,
|
| 783 |
+
"eval_tag_accuracy": 0.9403559403559404,
|
| 784 |
+
"eval_tag_f1": 0.9753503465214146,
|
| 785 |
+
"eval_tag_f1-CONTINUE": 0.9416470588235294,
|
| 786 |
+
"eval_tag_f1-FINISH": 0.9416470588235294,
|
| 787 |
+
"eval_tag_f1-TERMINATE": 0.9390063944909002,
|
| 788 |
+
"eval_token_accuracy": 0.9753503465214146,
|
| 789 |
+
"eval_token_f1": 0.9403559403559404,
|
| 790 |
+
"eval_token_f1_negative": 0.9416470588235294,
|
| 791 |
+
"eval_token_f1_positive": 0.9390063944909002,
|
| 792 |
+
"step": 4500
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 1.8413597733711047,
|
| 796 |
+
"grad_norm": 3.344792604446411,
|
| 797 |
+
"learning_rate": 4.1332770982707723e-07,
|
| 798 |
+
"loss": 0.1645,
|
| 799 |
+
"step": 4550
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 1.8615944961554027,
|
| 803 |
+
"grad_norm": 1.2586418390274048,
|
| 804 |
+
"learning_rate": 3.606073386756643e-07,
|
| 805 |
+
"loss": 0.1497,
|
| 806 |
+
"step": 4600
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 1.8818292189397006,
|
| 810 |
+
"grad_norm": 5.412999629974365,
|
| 811 |
+
"learning_rate": 3.078869675242514e-07,
|
| 812 |
+
"loss": 0.1586,
|
| 813 |
+
"step": 4650
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.9020639417239984,
|
| 817 |
+
"grad_norm": 4.021740436553955,
|
| 818 |
+
"learning_rate": 2.551665963728385e-07,
|
| 819 |
+
"loss": 0.1804,
|
| 820 |
+
"step": 4700
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 1.9222986645082962,
|
| 824 |
+
"grad_norm": 5.421517372131348,
|
| 825 |
+
"learning_rate": 2.0244622522142556e-07,
|
| 826 |
+
"loss": 0.1426,
|
| 827 |
+
"step": 4750
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 1.942533387292594,
|
| 831 |
+
"grad_norm": 13.003674507141113,
|
| 832 |
+
"learning_rate": 1.4972585407001267e-07,
|
| 833 |
+
"loss": 0.1798,
|
| 834 |
+
"step": 4800
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.962768110076892,
|
| 838 |
+
"grad_norm": 2.8676435947418213,
|
| 839 |
+
"learning_rate": 9.700548291859976e-08,
|
| 840 |
+
"loss": 0.1675,
|
| 841 |
+
"step": 4850
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.9830028328611897,
|
| 845 |
+
"grad_norm": 5.923835277557373,
|
| 846 |
+
"learning_rate": 4.4285111767186845e-08,
|
| 847 |
+
"loss": 0.1406,
|
| 848 |
+
"step": 4900
|
| 849 |
+
}
|
| 850 |
+
],
|
| 851 |
+
"logging_steps": 50,
|
| 852 |
+
"max_steps": 4942,
|
| 853 |
+
"num_input_tokens_seen": 0,
|
| 854 |
+
"num_train_epochs": 2,
|
| 855 |
+
"save_steps": 500,
|
| 856 |
+
"total_flos": 1.105108458176471e+17,
|
| 857 |
+
"train_batch_size": 32,
|
| 858 |
+
"trial_name": null,
|
| 859 |
+
"trial_params": null
|
| 860 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bd33e113054e6a02b7681ef7c87c0c9876fa65c564778f18edb6ec01be05c9a
|
| 3 |
+
size 5048
|