Upload 8 files
Browse files- .gitattributes +1 -0
- config.json +37 -0
- model.safetensors +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +61 -0
- trainer_state.json +1038 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "adalbertojunior/distill-bge-retromae",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"finetuning_task": "ner",
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "B-Segmento",
|
| 16 |
+
"1": "I-Segmento"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 4096,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"B-Segmento": 0,
|
| 22 |
+
"I-Segmento": 1
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-05,
|
| 25 |
+
"max_position_embeddings": 8194,
|
| 26 |
+
"model_type": "xlm-roberta",
|
| 27 |
+
"num_attention_heads": 16,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"output_past": true,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"torch_dtype": "bfloat16",
|
| 33 |
+
"transformers_version": "4.46.1",
|
| 34 |
+
"type_vocab_size": 1,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 250002
|
| 37 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9dfb87c1efad6a2ff5360926a9f0e7141f16dfe73d012faf1926d916ecaacb1b
|
| 3 |
+
size 831129388
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95c87c2955c3edd5cce0a9d3ea8d1e49b444b9f75b82ab9e68f7005cd6371142
|
| 3 |
+
size 17082898
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 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": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"max_length": 1024,
|
| 50 |
+
"model_max_length": 8192,
|
| 51 |
+
"pad_to_multiple_of": null,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"pad_token_type_id": 0,
|
| 54 |
+
"padding_side": "right",
|
| 55 |
+
"sep_token": "</s>",
|
| 56 |
+
"stride": 0,
|
| 57 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 58 |
+
"truncation_side": "right",
|
| 59 |
+
"truncation_strategy": "longest_first",
|
| 60 |
+
"unk_token": "<unk>"
|
| 61 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1038 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9118125313435558,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 7500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.012157500417914077,
|
| 13 |
+
"eval_accuracy": 0.9982292163897571,
|
| 14 |
+
"eval_f1": 0.5714285714285715,
|
| 15 |
+
"eval_loss": NaN,
|
| 16 |
+
"eval_precision": 0.5992217898832685,
|
| 17 |
+
"eval_recall": 0.5460992907801419,
|
| 18 |
+
"eval_runtime": 4.2246,
|
| 19 |
+
"eval_samples_per_second": 12.072,
|
| 20 |
+
"eval_steps_per_second": 12.072,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.024315000835828153,
|
| 25 |
+
"eval_accuracy": 0.9979520502594583,
|
| 26 |
+
"eval_f1": 0.561128526645768,
|
| 27 |
+
"eval_loss": NaN,
|
| 28 |
+
"eval_precision": 0.5028089887640449,
|
| 29 |
+
"eval_recall": 0.6347517730496454,
|
| 30 |
+
"eval_runtime": 4.0691,
|
| 31 |
+
"eval_samples_per_second": 12.534,
|
| 32 |
+
"eval_steps_per_second": 12.534,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.03647250125374223,
|
| 37 |
+
"eval_accuracy": 0.9982908088631569,
|
| 38 |
+
"eval_f1": 0.6003401360544217,
|
| 39 |
+
"eval_loss": NaN,
|
| 40 |
+
"eval_precision": 0.576797385620915,
|
| 41 |
+
"eval_recall": 0.625886524822695,
|
| 42 |
+
"eval_runtime": 3.8202,
|
| 43 |
+
"eval_samples_per_second": 13.35,
|
| 44 |
+
"eval_steps_per_second": 13.35,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.048630001671656306,
|
| 49 |
+
"eval_accuracy": 0.9983370032182067,
|
| 50 |
+
"eval_f1": 0.5949579831932772,
|
| 51 |
+
"eval_loss": NaN,
|
| 52 |
+
"eval_precision": 0.5654952076677316,
|
| 53 |
+
"eval_recall": 0.6276595744680851,
|
| 54 |
+
"eval_runtime": 3.892,
|
| 55 |
+
"eval_samples_per_second": 13.104,
|
| 56 |
+
"eval_steps_per_second": 13.104,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.060787502089570386,
|
| 61 |
+
"grad_norm": 0.56640625,
|
| 62 |
+
"learning_rate": 9.39209726443769e-05,
|
| 63 |
+
"loss": 0.0667,
|
| 64 |
+
"step": 500
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.060787502089570386,
|
| 68 |
+
"eval_accuracy": 0.9980906333246077,
|
| 69 |
+
"eval_f1": 0.5690789473684211,
|
| 70 |
+
"eval_loss": NaN,
|
| 71 |
+
"eval_precision": 0.5306748466257669,
|
| 72 |
+
"eval_recall": 0.6134751773049646,
|
| 73 |
+
"eval_runtime": 3.9741,
|
| 74 |
+
"eval_samples_per_second": 12.833,
|
| 75 |
+
"eval_steps_per_second": 12.833,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.07294500250748447,
|
| 80 |
+
"eval_accuracy": 0.9981522257980074,
|
| 81 |
+
"eval_f1": 0.5753646677471637,
|
| 82 |
+
"eval_loss": NaN,
|
| 83 |
+
"eval_precision": 0.5298507462686567,
|
| 84 |
+
"eval_recall": 0.6294326241134752,
|
| 85 |
+
"eval_runtime": 3.9469,
|
| 86 |
+
"eval_samples_per_second": 12.922,
|
| 87 |
+
"eval_steps_per_second": 12.922,
|
| 88 |
+
"step": 600
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.08510250292539853,
|
| 92 |
+
"eval_accuracy": 0.9983524013365567,
|
| 93 |
+
"eval_f1": 0.608108108108108,
|
| 94 |
+
"eval_loss": NaN,
|
| 95 |
+
"eval_precision": 0.5806451612903226,
|
| 96 |
+
"eval_recall": 0.6382978723404256,
|
| 97 |
+
"eval_runtime": 4.9419,
|
| 98 |
+
"eval_samples_per_second": 10.32,
|
| 99 |
+
"eval_steps_per_second": 10.32,
|
| 100 |
+
"step": 700
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.09726000334331261,
|
| 104 |
+
"eval_accuracy": 0.9978904577860586,
|
| 105 |
+
"eval_f1": 0.5460317460317461,
|
| 106 |
+
"eval_loss": NaN,
|
| 107 |
+
"eval_precision": 0.4942528735632184,
|
| 108 |
+
"eval_recall": 0.6099290780141844,
|
| 109 |
+
"eval_runtime": 3.9464,
|
| 110 |
+
"eval_samples_per_second": 12.923,
|
| 111 |
+
"eval_steps_per_second": 12.923,
|
| 112 |
+
"step": 800
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.10941750376122669,
|
| 116 |
+
"eval_accuracy": 0.9981984201530573,
|
| 117 |
+
"eval_f1": 0.5831960461285007,
|
| 118 |
+
"eval_loss": NaN,
|
| 119 |
+
"eval_precision": 0.5446153846153846,
|
| 120 |
+
"eval_recall": 0.6276595744680851,
|
| 121 |
+
"eval_runtime": 3.9207,
|
| 122 |
+
"eval_samples_per_second": 13.008,
|
| 123 |
+
"eval_steps_per_second": 13.008,
|
| 124 |
+
"step": 900
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.12157500417914077,
|
| 128 |
+
"grad_norm": 0.49609375,
|
| 129 |
+
"learning_rate": 8.78419452887538e-05,
|
| 130 |
+
"loss": 0.0273,
|
| 131 |
+
"step": 1000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.12157500417914077,
|
| 135 |
+
"eval_accuracy": 0.9981368276796575,
|
| 136 |
+
"eval_f1": 0.5692821368948245,
|
| 137 |
+
"eval_loss": NaN,
|
| 138 |
+
"eval_precision": 0.5378548895899053,
|
| 139 |
+
"eval_recall": 0.6046099290780141,
|
| 140 |
+
"eval_runtime": 3.9151,
|
| 141 |
+
"eval_samples_per_second": 13.026,
|
| 142 |
+
"eval_steps_per_second": 13.026,
|
| 143 |
+
"step": 1000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.13373250459705485,
|
| 147 |
+
"eval_accuracy": 0.9985679749934558,
|
| 148 |
+
"eval_f1": 0.6378091872791519,
|
| 149 |
+
"eval_loss": NaN,
|
| 150 |
+
"eval_precision": 0.6355633802816901,
|
| 151 |
+
"eval_recall": 0.6400709219858156,
|
| 152 |
+
"eval_runtime": 3.9167,
|
| 153 |
+
"eval_samples_per_second": 13.021,
|
| 154 |
+
"eval_steps_per_second": 13.021,
|
| 155 |
+
"step": 1100
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.14589000501496893,
|
| 159 |
+
"eval_accuracy": 0.9982446145081071,
|
| 160 |
+
"eval_f1": 0.5888324873096447,
|
| 161 |
+
"eval_loss": NaN,
|
| 162 |
+
"eval_precision": 0.5631067961165048,
|
| 163 |
+
"eval_recall": 0.6170212765957447,
|
| 164 |
+
"eval_runtime": 3.9347,
|
| 165 |
+
"eval_samples_per_second": 12.962,
|
| 166 |
+
"eval_steps_per_second": 12.962,
|
| 167 |
+
"step": 1200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.158047505432883,
|
| 171 |
+
"eval_accuracy": 0.9982908088631569,
|
| 172 |
+
"eval_f1": 0.6126418152350082,
|
| 173 |
+
"eval_loss": NaN,
|
| 174 |
+
"eval_precision": 0.564179104477612,
|
| 175 |
+
"eval_recall": 0.6702127659574468,
|
| 176 |
+
"eval_runtime": 3.9694,
|
| 177 |
+
"eval_samples_per_second": 12.848,
|
| 178 |
+
"eval_steps_per_second": 12.848,
|
| 179 |
+
"step": 1300
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.17020500585079706,
|
| 183 |
+
"eval_accuracy": 0.9983524013365567,
|
| 184 |
+
"eval_f1": 0.6128500823723229,
|
| 185 |
+
"eval_loss": NaN,
|
| 186 |
+
"eval_precision": 0.5723076923076923,
|
| 187 |
+
"eval_recall": 0.6595744680851063,
|
| 188 |
+
"eval_runtime": 3.9587,
|
| 189 |
+
"eval_samples_per_second": 12.883,
|
| 190 |
+
"eval_steps_per_second": 12.883,
|
| 191 |
+
"step": 1400
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.18236250626871114,
|
| 195 |
+
"grad_norm": 1.453125,
|
| 196 |
+
"learning_rate": 8.17629179331307e-05,
|
| 197 |
+
"loss": 0.0198,
|
| 198 |
+
"step": 1500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.18236250626871114,
|
| 202 |
+
"eval_accuracy": 0.9984139938099564,
|
| 203 |
+
"eval_f1": 0.6216216216216217,
|
| 204 |
+
"eval_loss": NaN,
|
| 205 |
+
"eval_precision": 0.5935483870967742,
|
| 206 |
+
"eval_recall": 0.6524822695035462,
|
| 207 |
+
"eval_runtime": 3.9699,
|
| 208 |
+
"eval_samples_per_second": 12.847,
|
| 209 |
+
"eval_steps_per_second": 12.847,
|
| 210 |
+
"step": 1500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.19452000668662522,
|
| 214 |
+
"eval_accuracy": 0.9983985956916065,
|
| 215 |
+
"eval_f1": 0.6113013698630136,
|
| 216 |
+
"eval_loss": NaN,
|
| 217 |
+
"eval_precision": 0.5910596026490066,
|
| 218 |
+
"eval_recall": 0.6329787234042553,
|
| 219 |
+
"eval_runtime": 3.9634,
|
| 220 |
+
"eval_samples_per_second": 12.868,
|
| 221 |
+
"eval_steps_per_second": 12.868,
|
| 222 |
+
"step": 1600
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.2066775071045393,
|
| 226 |
+
"eval_accuracy": 0.998537178756756,
|
| 227 |
+
"eval_f1": 0.6450511945392491,
|
| 228 |
+
"eval_loss": NaN,
|
| 229 |
+
"eval_precision": 0.6217105263157895,
|
| 230 |
+
"eval_recall": 0.6702127659574468,
|
| 231 |
+
"eval_runtime": 3.9348,
|
| 232 |
+
"eval_samples_per_second": 12.961,
|
| 233 |
+
"eval_steps_per_second": 12.961,
|
| 234 |
+
"step": 1700
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.21883500752245338,
|
| 238 |
+
"eval_accuracy": 0.9985063825200561,
|
| 239 |
+
"eval_f1": 0.61101243339254,
|
| 240 |
+
"eval_loss": NaN,
|
| 241 |
+
"eval_precision": 0.6120996441281139,
|
| 242 |
+
"eval_recall": 0.6099290780141844,
|
| 243 |
+
"eval_runtime": 3.9403,
|
| 244 |
+
"eval_samples_per_second": 12.943,
|
| 245 |
+
"eval_steps_per_second": 12.943,
|
| 246 |
+
"step": 1800
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.23099250794036746,
|
| 250 |
+
"eval_accuracy": 0.9985987712301557,
|
| 251 |
+
"eval_f1": 0.638888888888889,
|
| 252 |
+
"eval_loss": NaN,
|
| 253 |
+
"eval_precision": 0.6258503401360545,
|
| 254 |
+
"eval_recall": 0.6524822695035462,
|
| 255 |
+
"eval_runtime": 3.8792,
|
| 256 |
+
"eval_samples_per_second": 13.147,
|
| 257 |
+
"eval_steps_per_second": 13.147,
|
| 258 |
+
"step": 1900
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.24315000835828154,
|
| 262 |
+
"grad_norm": 0.337890625,
|
| 263 |
+
"learning_rate": 7.56838905775076e-05,
|
| 264 |
+
"loss": 0.015,
|
| 265 |
+
"step": 2000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.24315000835828154,
|
| 269 |
+
"eval_accuracy": 0.9983677994549066,
|
| 270 |
+
"eval_f1": 0.6179966044142615,
|
| 271 |
+
"eval_loss": NaN,
|
| 272 |
+
"eval_precision": 0.5928338762214984,
|
| 273 |
+
"eval_recall": 0.6453900709219859,
|
| 274 |
+
"eval_runtime": 3.8941,
|
| 275 |
+
"eval_samples_per_second": 13.097,
|
| 276 |
+
"eval_steps_per_second": 13.097,
|
| 277 |
+
"step": 2000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.2553075087761956,
|
| 281 |
+
"eval_accuracy": 0.998521780638406,
|
| 282 |
+
"eval_f1": 0.6296928327645053,
|
| 283 |
+
"eval_loss": NaN,
|
| 284 |
+
"eval_precision": 0.6069078947368421,
|
| 285 |
+
"eval_recall": 0.6542553191489362,
|
| 286 |
+
"eval_runtime": 3.8421,
|
| 287 |
+
"eval_samples_per_second": 13.274,
|
| 288 |
+
"eval_steps_per_second": 13.274,
|
| 289 |
+
"step": 2100
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.2674650091941097,
|
| 293 |
+
"eval_accuracy": 0.9984755862833562,
|
| 294 |
+
"eval_f1": 0.6352739726027398,
|
| 295 |
+
"eval_loss": NaN,
|
| 296 |
+
"eval_precision": 0.6142384105960265,
|
| 297 |
+
"eval_recall": 0.6578014184397163,
|
| 298 |
+
"eval_runtime": 3.8929,
|
| 299 |
+
"eval_samples_per_second": 13.101,
|
| 300 |
+
"eval_steps_per_second": 13.101,
|
| 301 |
+
"step": 2200
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.2796225096120238,
|
| 305 |
+
"eval_accuracy": 0.9985679749934558,
|
| 306 |
+
"eval_f1": 0.6507666098807496,
|
| 307 |
+
"eval_loss": NaN,
|
| 308 |
+
"eval_precision": 0.6262295081967213,
|
| 309 |
+
"eval_recall": 0.6773049645390071,
|
| 310 |
+
"eval_runtime": 4.0354,
|
| 311 |
+
"eval_samples_per_second": 12.638,
|
| 312 |
+
"eval_steps_per_second": 12.638,
|
| 313 |
+
"step": 2300
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.29178001002993786,
|
| 317 |
+
"eval_accuracy": 0.998275410744807,
|
| 318 |
+
"eval_f1": 0.5949152542372882,
|
| 319 |
+
"eval_loss": NaN,
|
| 320 |
+
"eval_precision": 0.5698051948051948,
|
| 321 |
+
"eval_recall": 0.6223404255319149,
|
| 322 |
+
"eval_runtime": 3.9548,
|
| 323 |
+
"eval_samples_per_second": 12.896,
|
| 324 |
+
"eval_steps_per_second": 12.896,
|
| 325 |
+
"step": 2400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.30393751044785194,
|
| 329 |
+
"grad_norm": 0.5,
|
| 330 |
+
"learning_rate": 6.96048632218845e-05,
|
| 331 |
+
"loss": 0.0122,
|
| 332 |
+
"step": 2500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.30393751044785194,
|
| 336 |
+
"eval_accuracy": 0.9983677994549066,
|
| 337 |
+
"eval_f1": 0.6200657894736843,
|
| 338 |
+
"eval_loss": NaN,
|
| 339 |
+
"eval_precision": 0.5782208588957055,
|
| 340 |
+
"eval_recall": 0.6684397163120568,
|
| 341 |
+
"eval_runtime": 3.9191,
|
| 342 |
+
"eval_samples_per_second": 13.013,
|
| 343 |
+
"eval_steps_per_second": 13.013,
|
| 344 |
+
"step": 2500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.316095010865766,
|
| 348 |
+
"eval_accuracy": 0.998537178756756,
|
| 349 |
+
"eval_f1": 0.6379310344827586,
|
| 350 |
+
"eval_loss": NaN,
|
| 351 |
+
"eval_precision": 0.6208053691275168,
|
| 352 |
+
"eval_recall": 0.6560283687943262,
|
| 353 |
+
"eval_runtime": 3.9133,
|
| 354 |
+
"eval_samples_per_second": 13.033,
|
| 355 |
+
"eval_steps_per_second": 13.033,
|
| 356 |
+
"step": 2600
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.32825251128368005,
|
| 360 |
+
"eval_accuracy": 0.9984293919283064,
|
| 361 |
+
"eval_f1": 0.6284722222222222,
|
| 362 |
+
"eval_loss": NaN,
|
| 363 |
+
"eval_precision": 0.6156462585034014,
|
| 364 |
+
"eval_recall": 0.6418439716312057,
|
| 365 |
+
"eval_runtime": 3.9458,
|
| 366 |
+
"eval_samples_per_second": 12.925,
|
| 367 |
+
"eval_steps_per_second": 12.925,
|
| 368 |
+
"step": 2700
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.34041001170159413,
|
| 372 |
+
"eval_accuracy": 0.9984293919283064,
|
| 373 |
+
"eval_f1": 0.6254295532646049,
|
| 374 |
+
"eval_loss": NaN,
|
| 375 |
+
"eval_precision": 0.6066666666666667,
|
| 376 |
+
"eval_recall": 0.6453900709219859,
|
| 377 |
+
"eval_runtime": 5.0134,
|
| 378 |
+
"eval_samples_per_second": 10.173,
|
| 379 |
+
"eval_steps_per_second": 10.173,
|
| 380 |
+
"step": 2800
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.3525675121195082,
|
| 384 |
+
"eval_accuracy": 0.9984601881650063,
|
| 385 |
+
"eval_f1": 0.6185567010309279,
|
| 386 |
+
"eval_loss": NaN,
|
| 387 |
+
"eval_precision": 0.6,
|
| 388 |
+
"eval_recall": 0.6382978723404256,
|
| 389 |
+
"eval_runtime": 3.9121,
|
| 390 |
+
"eval_samples_per_second": 13.037,
|
| 391 |
+
"eval_steps_per_second": 13.037,
|
| 392 |
+
"step": 2900
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.3647250125374223,
|
| 396 |
+
"grad_norm": 0.47265625,
|
| 397 |
+
"learning_rate": 6.352583586626139e-05,
|
| 398 |
+
"loss": 0.0102,
|
| 399 |
+
"step": 3000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.3647250125374223,
|
| 403 |
+
"eval_accuracy": 0.9984601881650063,
|
| 404 |
+
"eval_f1": 0.6175438596491228,
|
| 405 |
+
"eval_loss": NaN,
|
| 406 |
+
"eval_precision": 0.6111111111111112,
|
| 407 |
+
"eval_recall": 0.624113475177305,
|
| 408 |
+
"eval_runtime": 3.9032,
|
| 409 |
+
"eval_samples_per_second": 13.066,
|
| 410 |
+
"eval_steps_per_second": 13.066,
|
| 411 |
+
"step": 3000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.37688251295533637,
|
| 415 |
+
"eval_accuracy": 0.9983985956916065,
|
| 416 |
+
"eval_f1": 0.6067615658362988,
|
| 417 |
+
"eval_loss": NaN,
|
| 418 |
+
"eval_precision": 0.6089285714285714,
|
| 419 |
+
"eval_recall": 0.6046099290780141,
|
| 420 |
+
"eval_runtime": 3.9167,
|
| 421 |
+
"eval_samples_per_second": 13.021,
|
| 422 |
+
"eval_steps_per_second": 13.021,
|
| 423 |
+
"step": 3100
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.38904001337325045,
|
| 427 |
+
"eval_accuracy": 0.9981984201530573,
|
| 428 |
+
"eval_f1": 0.5792163543441226,
|
| 429 |
+
"eval_loss": NaN,
|
| 430 |
+
"eval_precision": 0.5573770491803278,
|
| 431 |
+
"eval_recall": 0.6028368794326241,
|
| 432 |
+
"eval_runtime": 3.9349,
|
| 433 |
+
"eval_samples_per_second": 12.961,
|
| 434 |
+
"eval_steps_per_second": 12.961,
|
| 435 |
+
"step": 3200
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.40119751379116453,
|
| 439 |
+
"eval_accuracy": 0.998275410744807,
|
| 440 |
+
"eval_f1": 0.6016528925619835,
|
| 441 |
+
"eval_loss": NaN,
|
| 442 |
+
"eval_precision": 0.5634674922600619,
|
| 443 |
+
"eval_recall": 0.6453900709219859,
|
| 444 |
+
"eval_runtime": 5.1154,
|
| 445 |
+
"eval_samples_per_second": 9.97,
|
| 446 |
+
"eval_steps_per_second": 9.97,
|
| 447 |
+
"step": 3300
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.4133550142090786,
|
| 451 |
+
"eval_accuracy": 0.9983985956916065,
|
| 452 |
+
"eval_f1": 0.6064735945485519,
|
| 453 |
+
"eval_loss": NaN,
|
| 454 |
+
"eval_precision": 0.5836065573770491,
|
| 455 |
+
"eval_recall": 0.6312056737588653,
|
| 456 |
+
"eval_runtime": 3.9386,
|
| 457 |
+
"eval_samples_per_second": 12.949,
|
| 458 |
+
"eval_steps_per_second": 12.949,
|
| 459 |
+
"step": 3400
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.4255125146269927,
|
| 463 |
+
"grad_norm": 0.63671875,
|
| 464 |
+
"learning_rate": 5.744680851063831e-05,
|
| 465 |
+
"loss": 0.0087,
|
| 466 |
+
"step": 3500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.4255125146269927,
|
| 470 |
+
"eval_accuracy": 0.9984601881650063,
|
| 471 |
+
"eval_f1": 0.6166950596252129,
|
| 472 |
+
"eval_loss": NaN,
|
| 473 |
+
"eval_precision": 0.5934426229508196,
|
| 474 |
+
"eval_recall": 0.6418439716312057,
|
| 475 |
+
"eval_runtime": 3.9507,
|
| 476 |
+
"eval_samples_per_second": 12.909,
|
| 477 |
+
"eval_steps_per_second": 12.909,
|
| 478 |
+
"step": 3500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.43767001504490677,
|
| 482 |
+
"eval_accuracy": 0.9985525768751059,
|
| 483 |
+
"eval_f1": 0.6412859560067682,
|
| 484 |
+
"eval_loss": NaN,
|
| 485 |
+
"eval_precision": 0.6132686084142395,
|
| 486 |
+
"eval_recall": 0.6719858156028369,
|
| 487 |
+
"eval_runtime": 3.9696,
|
| 488 |
+
"eval_samples_per_second": 12.848,
|
| 489 |
+
"eval_steps_per_second": 12.848,
|
| 490 |
+
"step": 3600
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.44982751546282085,
|
| 494 |
+
"eval_accuracy": 0.998521780638406,
|
| 495 |
+
"eval_f1": 0.638655462184874,
|
| 496 |
+
"eval_loss": NaN,
|
| 497 |
+
"eval_precision": 0.6070287539936102,
|
| 498 |
+
"eval_recall": 0.6737588652482269,
|
| 499 |
+
"eval_runtime": 3.9563,
|
| 500 |
+
"eval_samples_per_second": 12.891,
|
| 501 |
+
"eval_steps_per_second": 12.891,
|
| 502 |
+
"step": 3700
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.46198501588073493,
|
| 506 |
+
"eval_accuracy": 0.9984909844017061,
|
| 507 |
+
"eval_f1": 0.6237288135593221,
|
| 508 |
+
"eval_loss": NaN,
|
| 509 |
+
"eval_precision": 0.5974025974025974,
|
| 510 |
+
"eval_recall": 0.6524822695035462,
|
| 511 |
+
"eval_runtime": 3.9225,
|
| 512 |
+
"eval_samples_per_second": 13.002,
|
| 513 |
+
"eval_steps_per_second": 13.002,
|
| 514 |
+
"step": 3800
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.474142516298649,
|
| 518 |
+
"eval_accuracy": 0.9984601881650063,
|
| 519 |
+
"eval_f1": 0.6193656093489149,
|
| 520 |
+
"eval_loss": NaN,
|
| 521 |
+
"eval_precision": 0.5851735015772871,
|
| 522 |
+
"eval_recall": 0.6578014184397163,
|
| 523 |
+
"eval_runtime": 3.8167,
|
| 524 |
+
"eval_samples_per_second": 13.362,
|
| 525 |
+
"eval_steps_per_second": 13.362,
|
| 526 |
+
"step": 3900
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.4863000167165631,
|
| 530 |
+
"grad_norm": 0.2578125,
|
| 531 |
+
"learning_rate": 5.13677811550152e-05,
|
| 532 |
+
"loss": 0.0074,
|
| 533 |
+
"step": 4000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.4863000167165631,
|
| 537 |
+
"eval_accuracy": 0.9984293919283064,
|
| 538 |
+
"eval_f1": 0.6102564102564102,
|
| 539 |
+
"eval_loss": NaN,
|
| 540 |
+
"eval_precision": 0.5891089108910891,
|
| 541 |
+
"eval_recall": 0.6329787234042553,
|
| 542 |
+
"eval_runtime": 3.9064,
|
| 543 |
+
"eval_samples_per_second": 13.055,
|
| 544 |
+
"eval_steps_per_second": 13.055,
|
| 545 |
+
"step": 4000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.49845751713447717,
|
| 549 |
+
"eval_accuracy": 0.9983677994549066,
|
| 550 |
+
"eval_f1": 0.5982905982905984,
|
| 551 |
+
"eval_loss": NaN,
|
| 552 |
+
"eval_precision": 0.5775577557755776,
|
| 553 |
+
"eval_recall": 0.6205673758865248,
|
| 554 |
+
"eval_runtime": 3.8733,
|
| 555 |
+
"eval_samples_per_second": 13.167,
|
| 556 |
+
"eval_steps_per_second": 13.167,
|
| 557 |
+
"step": 4100
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.5106150175523912,
|
| 561 |
+
"eval_accuracy": 0.9985525768751059,
|
| 562 |
+
"eval_f1": 0.6456558773424191,
|
| 563 |
+
"eval_loss": NaN,
|
| 564 |
+
"eval_precision": 0.6213114754098361,
|
| 565 |
+
"eval_recall": 0.6719858156028369,
|
| 566 |
+
"eval_runtime": 3.9945,
|
| 567 |
+
"eval_samples_per_second": 12.767,
|
| 568 |
+
"eval_steps_per_second": 12.767,
|
| 569 |
+
"step": 4200
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.5227725179703053,
|
| 573 |
+
"eval_accuracy": 0.9984755862833562,
|
| 574 |
+
"eval_f1": 0.6348408710217756,
|
| 575 |
+
"eval_loss": NaN,
|
| 576 |
+
"eval_precision": 0.6015873015873016,
|
| 577 |
+
"eval_recall": 0.6719858156028369,
|
| 578 |
+
"eval_runtime": 3.9449,
|
| 579 |
+
"eval_samples_per_second": 12.928,
|
| 580 |
+
"eval_steps_per_second": 12.928,
|
| 581 |
+
"step": 4300
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.5349300183882194,
|
| 585 |
+
"eval_accuracy": 0.9984447900466563,
|
| 586 |
+
"eval_f1": 0.6231155778894472,
|
| 587 |
+
"eval_loss": NaN,
|
| 588 |
+
"eval_precision": 0.5904761904761905,
|
| 589 |
+
"eval_recall": 0.6595744680851063,
|
| 590 |
+
"eval_runtime": 3.9223,
|
| 591 |
+
"eval_samples_per_second": 13.003,
|
| 592 |
+
"eval_steps_per_second": 13.003,
|
| 593 |
+
"step": 4400
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.5470875188061335,
|
| 597 |
+
"grad_norm": 0.796875,
|
| 598 |
+
"learning_rate": 4.52887537993921e-05,
|
| 599 |
+
"loss": 0.0069,
|
| 600 |
+
"step": 4500
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.5470875188061335,
|
| 604 |
+
"eval_accuracy": 0.9983985956916065,
|
| 605 |
+
"eval_f1": 0.6139767054908487,
|
| 606 |
+
"eval_loss": NaN,
|
| 607 |
+
"eval_precision": 0.5783699059561128,
|
| 608 |
+
"eval_recall": 0.6542553191489362,
|
| 609 |
+
"eval_runtime": 3.8802,
|
| 610 |
+
"eval_samples_per_second": 13.144,
|
| 611 |
+
"eval_steps_per_second": 13.144,
|
| 612 |
+
"step": 4500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.5592450192240476,
|
| 616 |
+
"eval_accuracy": 0.9983216050998568,
|
| 617 |
+
"eval_f1": 0.5902192242833052,
|
| 618 |
+
"eval_loss": NaN,
|
| 619 |
+
"eval_precision": 0.5627009646302251,
|
| 620 |
+
"eval_recall": 0.6205673758865248,
|
| 621 |
+
"eval_runtime": 3.8007,
|
| 622 |
+
"eval_samples_per_second": 13.418,
|
| 623 |
+
"eval_steps_per_second": 13.418,
|
| 624 |
+
"step": 4600
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.5714025196419616,
|
| 628 |
+
"eval_accuracy": 0.9984755862833562,
|
| 629 |
+
"eval_f1": 0.6243739565943239,
|
| 630 |
+
"eval_loss": NaN,
|
| 631 |
+
"eval_precision": 0.5899053627760252,
|
| 632 |
+
"eval_recall": 0.6631205673758865,
|
| 633 |
+
"eval_runtime": 5.2589,
|
| 634 |
+
"eval_samples_per_second": 9.698,
|
| 635 |
+
"eval_steps_per_second": 9.698,
|
| 636 |
+
"step": 4700
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.5835600200598757,
|
| 640 |
+
"eval_accuracy": 0.9984755862833562,
|
| 641 |
+
"eval_f1": 0.6231155778894472,
|
| 642 |
+
"eval_loss": NaN,
|
| 643 |
+
"eval_precision": 0.5904761904761905,
|
| 644 |
+
"eval_recall": 0.6595744680851063,
|
| 645 |
+
"eval_runtime": 3.9226,
|
| 646 |
+
"eval_samples_per_second": 13.001,
|
| 647 |
+
"eval_steps_per_second": 13.001,
|
| 648 |
+
"step": 4800
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.5957175204777898,
|
| 652 |
+
"eval_accuracy": 0.9984755862833562,
|
| 653 |
+
"eval_f1": 0.6298157453936348,
|
| 654 |
+
"eval_loss": NaN,
|
| 655 |
+
"eval_precision": 0.5968253968253968,
|
| 656 |
+
"eval_recall": 0.6666666666666666,
|
| 657 |
+
"eval_runtime": 3.9435,
|
| 658 |
+
"eval_samples_per_second": 12.933,
|
| 659 |
+
"eval_steps_per_second": 12.933,
|
| 660 |
+
"step": 4900
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.6078750208957039,
|
| 664 |
+
"grad_norm": 0.298828125,
|
| 665 |
+
"learning_rate": 3.9209726443769e-05,
|
| 666 |
+
"loss": 0.0065,
|
| 667 |
+
"step": 5000
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.6078750208957039,
|
| 671 |
+
"eval_accuracy": 0.9984293919283064,
|
| 672 |
+
"eval_f1": 0.6074450084602369,
|
| 673 |
+
"eval_loss": NaN,
|
| 674 |
+
"eval_precision": 0.580906148867314,
|
| 675 |
+
"eval_recall": 0.6365248226950354,
|
| 676 |
+
"eval_runtime": 3.9158,
|
| 677 |
+
"eval_samples_per_second": 13.024,
|
| 678 |
+
"eval_steps_per_second": 13.024,
|
| 679 |
+
"step": 5000
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.620032521313618,
|
| 683 |
+
"eval_accuracy": 0.9984909844017061,
|
| 684 |
+
"eval_f1": 0.6282271944922547,
|
| 685 |
+
"eval_loss": NaN,
|
| 686 |
+
"eval_precision": 0.6103678929765887,
|
| 687 |
+
"eval_recall": 0.6471631205673759,
|
| 688 |
+
"eval_runtime": 3.9051,
|
| 689 |
+
"eval_samples_per_second": 13.06,
|
| 690 |
+
"eval_steps_per_second": 13.06,
|
| 691 |
+
"step": 5100
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.632190021731532,
|
| 695 |
+
"eval_accuracy": 0.9984139938099564,
|
| 696 |
+
"eval_f1": 0.6184873949579831,
|
| 697 |
+
"eval_loss": NaN,
|
| 698 |
+
"eval_precision": 0.5878594249201278,
|
| 699 |
+
"eval_recall": 0.6524822695035462,
|
| 700 |
+
"eval_runtime": 3.9165,
|
| 701 |
+
"eval_samples_per_second": 13.022,
|
| 702 |
+
"eval_steps_per_second": 13.022,
|
| 703 |
+
"step": 5200
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.6443475221494461,
|
| 707 |
+
"eval_accuracy": 0.9984139938099564,
|
| 708 |
+
"eval_f1": 0.6115843270868824,
|
| 709 |
+
"eval_loss": NaN,
|
| 710 |
+
"eval_precision": 0.5885245901639344,
|
| 711 |
+
"eval_recall": 0.6365248226950354,
|
| 712 |
+
"eval_runtime": 3.9234,
|
| 713 |
+
"eval_samples_per_second": 12.999,
|
| 714 |
+
"eval_steps_per_second": 12.999,
|
| 715 |
+
"step": 5300
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.6565050225673601,
|
| 719 |
+
"eval_accuracy": 0.9985063825200561,
|
| 720 |
+
"eval_f1": 0.6408094435075886,
|
| 721 |
+
"eval_loss": NaN,
|
| 722 |
+
"eval_precision": 0.6109324758842444,
|
| 723 |
+
"eval_recall": 0.6737588652482269,
|
| 724 |
+
"eval_runtime": 3.9194,
|
| 725 |
+
"eval_samples_per_second": 13.012,
|
| 726 |
+
"eval_steps_per_second": 13.012,
|
| 727 |
+
"step": 5400
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.6686625229852742,
|
| 731 |
+
"grad_norm": 0.40625,
|
| 732 |
+
"learning_rate": 3.31306990881459e-05,
|
| 733 |
+
"loss": 0.0059,
|
| 734 |
+
"step": 5500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.6686625229852742,
|
| 738 |
+
"eval_accuracy": 0.998537178756756,
|
| 739 |
+
"eval_f1": 0.6480541455160745,
|
| 740 |
+
"eval_loss": NaN,
|
| 741 |
+
"eval_precision": 0.6197411003236246,
|
| 742 |
+
"eval_recall": 0.6790780141843972,
|
| 743 |
+
"eval_runtime": 3.9129,
|
| 744 |
+
"eval_samples_per_second": 13.034,
|
| 745 |
+
"eval_steps_per_second": 13.034,
|
| 746 |
+
"step": 5500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.6808200234031883,
|
| 750 |
+
"eval_accuracy": 0.9984601881650063,
|
| 751 |
+
"eval_f1": 0.6254295532646049,
|
| 752 |
+
"eval_loss": NaN,
|
| 753 |
+
"eval_precision": 0.6066666666666667,
|
| 754 |
+
"eval_recall": 0.6453900709219859,
|
| 755 |
+
"eval_runtime": 5.213,
|
| 756 |
+
"eval_samples_per_second": 9.783,
|
| 757 |
+
"eval_steps_per_second": 9.783,
|
| 758 |
+
"step": 5600
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.6929775238211023,
|
| 762 |
+
"eval_accuracy": 0.9984909844017061,
|
| 763 |
+
"eval_f1": 0.626465661641541,
|
| 764 |
+
"eval_loss": NaN,
|
| 765 |
+
"eval_precision": 0.5936507936507937,
|
| 766 |
+
"eval_recall": 0.6631205673758865,
|
| 767 |
+
"eval_runtime": 3.9034,
|
| 768 |
+
"eval_samples_per_second": 13.066,
|
| 769 |
+
"eval_steps_per_second": 13.066,
|
| 770 |
+
"step": 5700
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.7051350242390164,
|
| 774 |
+
"eval_accuracy": 0.9984601881650063,
|
| 775 |
+
"eval_f1": 0.6192893401015229,
|
| 776 |
+
"eval_loss": NaN,
|
| 777 |
+
"eval_precision": 0.5922330097087378,
|
| 778 |
+
"eval_recall": 0.648936170212766,
|
| 779 |
+
"eval_runtime": 3.9098,
|
| 780 |
+
"eval_samples_per_second": 13.044,
|
| 781 |
+
"eval_steps_per_second": 13.044,
|
| 782 |
+
"step": 5800
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.7172925246569305,
|
| 786 |
+
"eval_accuracy": 0.9984909844017061,
|
| 787 |
+
"eval_f1": 0.6323777403035413,
|
| 788 |
+
"eval_loss": NaN,
|
| 789 |
+
"eval_precision": 0.6028938906752411,
|
| 790 |
+
"eval_recall": 0.6648936170212766,
|
| 791 |
+
"eval_runtime": 3.9284,
|
| 792 |
+
"eval_samples_per_second": 12.982,
|
| 793 |
+
"eval_steps_per_second": 12.982,
|
| 794 |
+
"step": 5900
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.7294500250748446,
|
| 798 |
+
"grad_norm": 0.41796875,
|
| 799 |
+
"learning_rate": 2.7051671732522798e-05,
|
| 800 |
+
"loss": 0.0058,
|
| 801 |
+
"step": 6000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.7294500250748446,
|
| 805 |
+
"eval_accuracy": 0.9984293919283064,
|
| 806 |
+
"eval_f1": 0.6126279863481229,
|
| 807 |
+
"eval_loss": NaN,
|
| 808 |
+
"eval_precision": 0.5904605263157895,
|
| 809 |
+
"eval_recall": 0.6365248226950354,
|
| 810 |
+
"eval_runtime": 5.2952,
|
| 811 |
+
"eval_samples_per_second": 9.631,
|
| 812 |
+
"eval_steps_per_second": 9.631,
|
| 813 |
+
"step": 6000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.7416075254927587,
|
| 817 |
+
"eval_accuracy": 0.9984755862833562,
|
| 818 |
+
"eval_f1": 0.6201022146507666,
|
| 819 |
+
"eval_loss": NaN,
|
| 820 |
+
"eval_precision": 0.5967213114754099,
|
| 821 |
+
"eval_recall": 0.6453900709219859,
|
| 822 |
+
"eval_runtime": 5.2342,
|
| 823 |
+
"eval_samples_per_second": 9.744,
|
| 824 |
+
"eval_steps_per_second": 9.744,
|
| 825 |
+
"step": 6100
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.7537650259106727,
|
| 829 |
+
"eval_accuracy": 0.9984909844017061,
|
| 830 |
+
"eval_f1": 0.6306913996627319,
|
| 831 |
+
"eval_loss": NaN,
|
| 832 |
+
"eval_precision": 0.6012861736334405,
|
| 833 |
+
"eval_recall": 0.6631205673758865,
|
| 834 |
+
"eval_runtime": 3.8769,
|
| 835 |
+
"eval_samples_per_second": 13.155,
|
| 836 |
+
"eval_steps_per_second": 13.155,
|
| 837 |
+
"step": 6200
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.7659225263285868,
|
| 841 |
+
"eval_accuracy": 0.9984909844017061,
|
| 842 |
+
"eval_f1": 0.6281833616298812,
|
| 843 |
+
"eval_loss": NaN,
|
| 844 |
+
"eval_precision": 0.6026058631921825,
|
| 845 |
+
"eval_recall": 0.6560283687943262,
|
| 846 |
+
"eval_runtime": 3.8104,
|
| 847 |
+
"eval_samples_per_second": 13.384,
|
| 848 |
+
"eval_steps_per_second": 13.384,
|
| 849 |
+
"step": 6300
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.7780800267465009,
|
| 853 |
+
"eval_accuracy": 0.9984601881650063,
|
| 854 |
+
"eval_f1": 0.6302521008403361,
|
| 855 |
+
"eval_loss": NaN,
|
| 856 |
+
"eval_precision": 0.5990415335463258,
|
| 857 |
+
"eval_recall": 0.6648936170212766,
|
| 858 |
+
"eval_runtime": 3.9796,
|
| 859 |
+
"eval_samples_per_second": 12.815,
|
| 860 |
+
"eval_steps_per_second": 12.815,
|
| 861 |
+
"step": 6400
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.790237527164415,
|
| 865 |
+
"grad_norm": 0.5390625,
|
| 866 |
+
"learning_rate": 2.0972644376899697e-05,
|
| 867 |
+
"loss": 0.0055,
|
| 868 |
+
"step": 6500
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.790237527164415,
|
| 872 |
+
"eval_accuracy": 0.9984601881650063,
|
| 873 |
+
"eval_f1": 0.6302521008403361,
|
| 874 |
+
"eval_loss": NaN,
|
| 875 |
+
"eval_precision": 0.5990415335463258,
|
| 876 |
+
"eval_recall": 0.6648936170212766,
|
| 877 |
+
"eval_runtime": 3.9236,
|
| 878 |
+
"eval_samples_per_second": 12.998,
|
| 879 |
+
"eval_steps_per_second": 12.998,
|
| 880 |
+
"step": 6500
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.8023950275823291,
|
| 884 |
+
"eval_accuracy": 0.9985063825200561,
|
| 885 |
+
"eval_f1": 0.6256410256410256,
|
| 886 |
+
"eval_loss": NaN,
|
| 887 |
+
"eval_precision": 0.6039603960396039,
|
| 888 |
+
"eval_recall": 0.648936170212766,
|
| 889 |
+
"eval_runtime": 3.9065,
|
| 890 |
+
"eval_samples_per_second": 13.055,
|
| 891 |
+
"eval_steps_per_second": 13.055,
|
| 892 |
+
"step": 6600
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.8145525280002431,
|
| 896 |
+
"eval_accuracy": 0.9984755862833562,
|
| 897 |
+
"eval_f1": 0.6209262435677531,
|
| 898 |
+
"eval_loss": NaN,
|
| 899 |
+
"eval_precision": 0.6013289036544851,
|
| 900 |
+
"eval_recall": 0.6418439716312057,
|
| 901 |
+
"eval_runtime": 3.883,
|
| 902 |
+
"eval_samples_per_second": 13.134,
|
| 903 |
+
"eval_steps_per_second": 13.134,
|
| 904 |
+
"step": 6700
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.8267100284181572,
|
| 908 |
+
"eval_accuracy": 0.9984293919283064,
|
| 909 |
+
"eval_f1": 0.6214405360134003,
|
| 910 |
+
"eval_loss": NaN,
|
| 911 |
+
"eval_precision": 0.5888888888888889,
|
| 912 |
+
"eval_recall": 0.6578014184397163,
|
| 913 |
+
"eval_runtime": 3.8972,
|
| 914 |
+
"eval_samples_per_second": 13.086,
|
| 915 |
+
"eval_steps_per_second": 13.086,
|
| 916 |
+
"step": 6800
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.8388675288360713,
|
| 920 |
+
"eval_accuracy": 0.9984293919283064,
|
| 921 |
+
"eval_f1": 0.6121416526138279,
|
| 922 |
+
"eval_loss": NaN,
|
| 923 |
+
"eval_precision": 0.5836012861736335,
|
| 924 |
+
"eval_recall": 0.6436170212765957,
|
| 925 |
+
"eval_runtime": 3.9065,
|
| 926 |
+
"eval_samples_per_second": 13.055,
|
| 927 |
+
"eval_steps_per_second": 13.055,
|
| 928 |
+
"step": 6900
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.8510250292539854,
|
| 932 |
+
"grad_norm": 0.5234375,
|
| 933 |
+
"learning_rate": 1.4893617021276596e-05,
|
| 934 |
+
"loss": 0.0052,
|
| 935 |
+
"step": 7000
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.8510250292539854,
|
| 939 |
+
"eval_accuracy": 0.9984601881650063,
|
| 940 |
+
"eval_f1": 0.6235294117647059,
|
| 941 |
+
"eval_loss": NaN,
|
| 942 |
+
"eval_precision": 0.5926517571884984,
|
| 943 |
+
"eval_recall": 0.6578014184397163,
|
| 944 |
+
"eval_runtime": 4.6336,
|
| 945 |
+
"eval_samples_per_second": 11.007,
|
| 946 |
+
"eval_steps_per_second": 11.007,
|
| 947 |
+
"step": 7000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.8631825296718995,
|
| 951 |
+
"eval_accuracy": 0.9984601881650063,
|
| 952 |
+
"eval_f1": 0.6302521008403361,
|
| 953 |
+
"eval_loss": NaN,
|
| 954 |
+
"eval_precision": 0.5990415335463258,
|
| 955 |
+
"eval_recall": 0.6648936170212766,
|
| 956 |
+
"eval_runtime": 3.9703,
|
| 957 |
+
"eval_samples_per_second": 12.845,
|
| 958 |
+
"eval_steps_per_second": 12.845,
|
| 959 |
+
"step": 7100
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.8753400300898135,
|
| 963 |
+
"eval_accuracy": 0.9984293919283064,
|
| 964 |
+
"eval_f1": 0.6214405360134003,
|
| 965 |
+
"eval_loss": NaN,
|
| 966 |
+
"eval_precision": 0.5888888888888889,
|
| 967 |
+
"eval_recall": 0.6578014184397163,
|
| 968 |
+
"eval_runtime": 3.9965,
|
| 969 |
+
"eval_samples_per_second": 12.761,
|
| 970 |
+
"eval_steps_per_second": 12.761,
|
| 971 |
+
"step": 7200
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.8874975305077276,
|
| 975 |
+
"eval_accuracy": 0.998537178756756,
|
| 976 |
+
"eval_f1": 0.637137989778535,
|
| 977 |
+
"eval_loss": NaN,
|
| 978 |
+
"eval_precision": 0.6131147540983607,
|
| 979 |
+
"eval_recall": 0.6631205673758865,
|
| 980 |
+
"eval_runtime": 4.0553,
|
| 981 |
+
"eval_samples_per_second": 12.576,
|
| 982 |
+
"eval_steps_per_second": 12.576,
|
| 983 |
+
"step": 7300
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.8996550309256417,
|
| 987 |
+
"eval_accuracy": 0.9985525768751059,
|
| 988 |
+
"eval_f1": 0.6417657045840408,
|
| 989 |
+
"eval_loss": NaN,
|
| 990 |
+
"eval_precision": 0.6156351791530945,
|
| 991 |
+
"eval_recall": 0.6702127659574468,
|
| 992 |
+
"eval_runtime": 4.0275,
|
| 993 |
+
"eval_samples_per_second": 12.663,
|
| 994 |
+
"eval_steps_per_second": 12.663,
|
| 995 |
+
"step": 7400
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.9118125313435558,
|
| 999 |
+
"grad_norm": 0.2412109375,
|
| 1000 |
+
"learning_rate": 8.814589665653496e-06,
|
| 1001 |
+
"loss": 0.0052,
|
| 1002 |
+
"step": 7500
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.9118125313435558,
|
| 1006 |
+
"eval_accuracy": 0.9985525768751059,
|
| 1007 |
+
"eval_f1": 0.6417657045840408,
|
| 1008 |
+
"eval_loss": NaN,
|
| 1009 |
+
"eval_precision": 0.6156351791530945,
|
| 1010 |
+
"eval_recall": 0.6702127659574468,
|
| 1011 |
+
"eval_runtime": 4.1063,
|
| 1012 |
+
"eval_samples_per_second": 12.42,
|
| 1013 |
+
"eval_steps_per_second": 12.42,
|
| 1014 |
+
"step": 7500
|
| 1015 |
+
}
|
| 1016 |
+
],
|
| 1017 |
+
"logging_steps": 500,
|
| 1018 |
+
"max_steps": 8225,
|
| 1019 |
+
"num_input_tokens_seen": 0,
|
| 1020 |
+
"num_train_epochs": 1,
|
| 1021 |
+
"save_steps": 500,
|
| 1022 |
+
"stateful_callbacks": {
|
| 1023 |
+
"TrainerControl": {
|
| 1024 |
+
"args": {
|
| 1025 |
+
"should_epoch_stop": false,
|
| 1026 |
+
"should_evaluate": false,
|
| 1027 |
+
"should_log": false,
|
| 1028 |
+
"should_save": true,
|
| 1029 |
+
"should_training_stop": false
|
| 1030 |
+
},
|
| 1031 |
+
"attributes": {}
|
| 1032 |
+
}
|
| 1033 |
+
},
|
| 1034 |
+
"total_flos": 6.941757589813818e+16,
|
| 1035 |
+
"train_batch_size": 1,
|
| 1036 |
+
"trial_name": null,
|
| 1037 |
+
"trial_params": null
|
| 1038 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c11918fc93cdd5b1d48fbaa6f39e87e39fb16810854310c513e8c4296922bc5e
|
| 3 |
+
size 5216
|