Upload 7 files
Browse files- config.json +62 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +945 -0
- trainer_state.json +1234 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50281,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 50281,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"embedding_dropout": 0.0,
|
| 16 |
+
"eos_token_id": 50282,
|
| 17 |
+
"global_attn_every_n_layers": 3,
|
| 18 |
+
"global_rope_theta": 160000.0,
|
| 19 |
+
"gradient_checkpointing": false,
|
| 20 |
+
"hidden_activation": "gelu",
|
| 21 |
+
"hidden_size": 1024,
|
| 22 |
+
"id2label": {
|
| 23 |
+
"0": "LABEL_0",
|
| 24 |
+
"1": "LABEL_1",
|
| 25 |
+
"2": "LABEL_2",
|
| 26 |
+
"3": "LABEL_3",
|
| 27 |
+
"4": "LABEL_4",
|
| 28 |
+
"5": "LABEL_5"
|
| 29 |
+
},
|
| 30 |
+
"initializer_cutoff_factor": 2.0,
|
| 31 |
+
"initializer_range": 0.02,
|
| 32 |
+
"intermediate_size": 2624,
|
| 33 |
+
"label2id": {
|
| 34 |
+
"LABEL_0": 0,
|
| 35 |
+
"LABEL_1": 1,
|
| 36 |
+
"LABEL_2": 2,
|
| 37 |
+
"LABEL_3": 3,
|
| 38 |
+
"LABEL_4": 4,
|
| 39 |
+
"LABEL_5": 5
|
| 40 |
+
},
|
| 41 |
+
"layer_norm_eps": 1e-05,
|
| 42 |
+
"local_attention": 128,
|
| 43 |
+
"local_rope_theta": 10000.0,
|
| 44 |
+
"max_position_embeddings": 8192,
|
| 45 |
+
"mlp_bias": false,
|
| 46 |
+
"mlp_dropout": 0.0,
|
| 47 |
+
"model_type": "modernbert",
|
| 48 |
+
"norm_bias": false,
|
| 49 |
+
"norm_eps": 1e-05,
|
| 50 |
+
"num_attention_heads": 16,
|
| 51 |
+
"num_hidden_layers": 28,
|
| 52 |
+
"pad_token_id": 50283,
|
| 53 |
+
"position_embedding_type": "absolute",
|
| 54 |
+
"problem_type": "single_label_classification",
|
| 55 |
+
"repad_logits_with_grad": false,
|
| 56 |
+
"sep_token_id": 50282,
|
| 57 |
+
"sparse_pred_ignore_index": -100,
|
| 58 |
+
"sparse_prediction": false,
|
| 59 |
+
"torch_dtype": "float32",
|
| 60 |
+
"transformers_version": "4.52.4",
|
| 61 |
+
"vocab_size": 50368
|
| 62 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea6bf910b2ffd2c1146140dd24e258bd05f21acad7ca170ebba968ca6395de5d
|
| 3 |
+
size 1583368040
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,945 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "|||IP_ADDRESS|||",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<|padding|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"50254": {
|
| 20 |
+
"content": " ",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"50255": {
|
| 28 |
+
"content": " ",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"50256": {
|
| 36 |
+
"content": " ",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"50257": {
|
| 44 |
+
"content": " ",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"50258": {
|
| 52 |
+
"content": " ",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"50259": {
|
| 60 |
+
"content": " ",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"50260": {
|
| 68 |
+
"content": " ",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"50261": {
|
| 76 |
+
"content": " ",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"50262": {
|
| 84 |
+
"content": " ",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"50263": {
|
| 92 |
+
"content": " ",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"50264": {
|
| 100 |
+
"content": " ",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"50265": {
|
| 108 |
+
"content": " ",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"50266": {
|
| 116 |
+
"content": " ",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"50267": {
|
| 124 |
+
"content": " ",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"50268": {
|
| 132 |
+
"content": " ",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"50269": {
|
| 140 |
+
"content": " ",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": false
|
| 146 |
+
},
|
| 147 |
+
"50270": {
|
| 148 |
+
"content": " ",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": false
|
| 154 |
+
},
|
| 155 |
+
"50271": {
|
| 156 |
+
"content": " ",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": false
|
| 162 |
+
},
|
| 163 |
+
"50272": {
|
| 164 |
+
"content": " ",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": false
|
| 170 |
+
},
|
| 171 |
+
"50273": {
|
| 172 |
+
"content": " ",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"50274": {
|
| 180 |
+
"content": " ",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"50275": {
|
| 188 |
+
"content": " ",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"50276": {
|
| 196 |
+
"content": " ",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"50277": {
|
| 204 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"50278": {
|
| 212 |
+
"content": "|||PHONE_NUMBER|||",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"50279": {
|
| 220 |
+
"content": "<|endoftext|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"50280": {
|
| 228 |
+
"content": "[UNK]",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"50281": {
|
| 236 |
+
"content": "[CLS]",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"50282": {
|
| 244 |
+
"content": "[SEP]",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"50283": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"50284": {
|
| 260 |
+
"content": "[MASK]",
|
| 261 |
+
"lstrip": true,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"50285": {
|
| 268 |
+
"content": "[unused0]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": true,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"50286": {
|
| 276 |
+
"content": "[unused1]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": true,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"50287": {
|
| 284 |
+
"content": "[unused2]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": true,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
},
|
| 291 |
+
"50288": {
|
| 292 |
+
"content": "[unused3]",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": true,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": false
|
| 298 |
+
},
|
| 299 |
+
"50289": {
|
| 300 |
+
"content": "[unused4]",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": true,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": false
|
| 306 |
+
},
|
| 307 |
+
"50290": {
|
| 308 |
+
"content": "[unused5]",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": true,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": false
|
| 314 |
+
},
|
| 315 |
+
"50291": {
|
| 316 |
+
"content": "[unused6]",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": true,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": false
|
| 322 |
+
},
|
| 323 |
+
"50292": {
|
| 324 |
+
"content": "[unused7]",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": true,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": false
|
| 330 |
+
},
|
| 331 |
+
"50293": {
|
| 332 |
+
"content": "[unused8]",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": true,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": false
|
| 338 |
+
},
|
| 339 |
+
"50294": {
|
| 340 |
+
"content": "[unused9]",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": true,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": false
|
| 346 |
+
},
|
| 347 |
+
"50295": {
|
| 348 |
+
"content": "[unused10]",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": true,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": false
|
| 354 |
+
},
|
| 355 |
+
"50296": {
|
| 356 |
+
"content": "[unused11]",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": true,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": false
|
| 362 |
+
},
|
| 363 |
+
"50297": {
|
| 364 |
+
"content": "[unused12]",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": true,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": false
|
| 370 |
+
},
|
| 371 |
+
"50298": {
|
| 372 |
+
"content": "[unused13]",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": true,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": false
|
| 378 |
+
},
|
| 379 |
+
"50299": {
|
| 380 |
+
"content": "[unused14]",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": true,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": false
|
| 386 |
+
},
|
| 387 |
+
"50300": {
|
| 388 |
+
"content": "[unused15]",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": true,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": false
|
| 394 |
+
},
|
| 395 |
+
"50301": {
|
| 396 |
+
"content": "[unused16]",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": true,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": false
|
| 402 |
+
},
|
| 403 |
+
"50302": {
|
| 404 |
+
"content": "[unused17]",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": true,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": false
|
| 410 |
+
},
|
| 411 |
+
"50303": {
|
| 412 |
+
"content": "[unused18]",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": true,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": false
|
| 418 |
+
},
|
| 419 |
+
"50304": {
|
| 420 |
+
"content": "[unused19]",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": true,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": false
|
| 426 |
+
},
|
| 427 |
+
"50305": {
|
| 428 |
+
"content": "[unused20]",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": true,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": false
|
| 434 |
+
},
|
| 435 |
+
"50306": {
|
| 436 |
+
"content": "[unused21]",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": true,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": false
|
| 442 |
+
},
|
| 443 |
+
"50307": {
|
| 444 |
+
"content": "[unused22]",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": true,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": false
|
| 450 |
+
},
|
| 451 |
+
"50308": {
|
| 452 |
+
"content": "[unused23]",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": true,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": false
|
| 458 |
+
},
|
| 459 |
+
"50309": {
|
| 460 |
+
"content": "[unused24]",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": true,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": false
|
| 466 |
+
},
|
| 467 |
+
"50310": {
|
| 468 |
+
"content": "[unused25]",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": true,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": false
|
| 474 |
+
},
|
| 475 |
+
"50311": {
|
| 476 |
+
"content": "[unused26]",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": true,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": false
|
| 482 |
+
},
|
| 483 |
+
"50312": {
|
| 484 |
+
"content": "[unused27]",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": true,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": false
|
| 490 |
+
},
|
| 491 |
+
"50313": {
|
| 492 |
+
"content": "[unused28]",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": true,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": false
|
| 498 |
+
},
|
| 499 |
+
"50314": {
|
| 500 |
+
"content": "[unused29]",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": true,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": false
|
| 506 |
+
},
|
| 507 |
+
"50315": {
|
| 508 |
+
"content": "[unused30]",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": true,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": false
|
| 514 |
+
},
|
| 515 |
+
"50316": {
|
| 516 |
+
"content": "[unused31]",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": true,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": false
|
| 522 |
+
},
|
| 523 |
+
"50317": {
|
| 524 |
+
"content": "[unused32]",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": true,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": false
|
| 530 |
+
},
|
| 531 |
+
"50318": {
|
| 532 |
+
"content": "[unused33]",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": true,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": false
|
| 538 |
+
},
|
| 539 |
+
"50319": {
|
| 540 |
+
"content": "[unused34]",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": true,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": false
|
| 546 |
+
},
|
| 547 |
+
"50320": {
|
| 548 |
+
"content": "[unused35]",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": true,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": false
|
| 554 |
+
},
|
| 555 |
+
"50321": {
|
| 556 |
+
"content": "[unused36]",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": true,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": false
|
| 562 |
+
},
|
| 563 |
+
"50322": {
|
| 564 |
+
"content": "[unused37]",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": true,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": false
|
| 570 |
+
},
|
| 571 |
+
"50323": {
|
| 572 |
+
"content": "[unused38]",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": true,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": false
|
| 578 |
+
},
|
| 579 |
+
"50324": {
|
| 580 |
+
"content": "[unused39]",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": true,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": false
|
| 586 |
+
},
|
| 587 |
+
"50325": {
|
| 588 |
+
"content": "[unused40]",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": true,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": false
|
| 594 |
+
},
|
| 595 |
+
"50326": {
|
| 596 |
+
"content": "[unused41]",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": true,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": false
|
| 602 |
+
},
|
| 603 |
+
"50327": {
|
| 604 |
+
"content": "[unused42]",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": true,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": false
|
| 610 |
+
},
|
| 611 |
+
"50328": {
|
| 612 |
+
"content": "[unused43]",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": true,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": false
|
| 618 |
+
},
|
| 619 |
+
"50329": {
|
| 620 |
+
"content": "[unused44]",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": true,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": false
|
| 626 |
+
},
|
| 627 |
+
"50330": {
|
| 628 |
+
"content": "[unused45]",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": true,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": false
|
| 634 |
+
},
|
| 635 |
+
"50331": {
|
| 636 |
+
"content": "[unused46]",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": true,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": false
|
| 642 |
+
},
|
| 643 |
+
"50332": {
|
| 644 |
+
"content": "[unused47]",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": true,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": false
|
| 650 |
+
},
|
| 651 |
+
"50333": {
|
| 652 |
+
"content": "[unused48]",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": true,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": false
|
| 658 |
+
},
|
| 659 |
+
"50334": {
|
| 660 |
+
"content": "[unused49]",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": true,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": false
|
| 666 |
+
},
|
| 667 |
+
"50335": {
|
| 668 |
+
"content": "[unused50]",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": true,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": false
|
| 674 |
+
},
|
| 675 |
+
"50336": {
|
| 676 |
+
"content": "[unused51]",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": true,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": false
|
| 682 |
+
},
|
| 683 |
+
"50337": {
|
| 684 |
+
"content": "[unused52]",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": true,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": false
|
| 690 |
+
},
|
| 691 |
+
"50338": {
|
| 692 |
+
"content": "[unused53]",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": true,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": false
|
| 698 |
+
},
|
| 699 |
+
"50339": {
|
| 700 |
+
"content": "[unused54]",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": true,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": false
|
| 706 |
+
},
|
| 707 |
+
"50340": {
|
| 708 |
+
"content": "[unused55]",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": true,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": false
|
| 714 |
+
},
|
| 715 |
+
"50341": {
|
| 716 |
+
"content": "[unused56]",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": true,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": false
|
| 722 |
+
},
|
| 723 |
+
"50342": {
|
| 724 |
+
"content": "[unused57]",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": true,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": false
|
| 730 |
+
},
|
| 731 |
+
"50343": {
|
| 732 |
+
"content": "[unused58]",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": true,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": false
|
| 738 |
+
},
|
| 739 |
+
"50344": {
|
| 740 |
+
"content": "[unused59]",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": true,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": false
|
| 746 |
+
},
|
| 747 |
+
"50345": {
|
| 748 |
+
"content": "[unused60]",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": true,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": false
|
| 754 |
+
},
|
| 755 |
+
"50346": {
|
| 756 |
+
"content": "[unused61]",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": true,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": false
|
| 762 |
+
},
|
| 763 |
+
"50347": {
|
| 764 |
+
"content": "[unused62]",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": true,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": false
|
| 770 |
+
},
|
| 771 |
+
"50348": {
|
| 772 |
+
"content": "[unused63]",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": true,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": false
|
| 778 |
+
},
|
| 779 |
+
"50349": {
|
| 780 |
+
"content": "[unused64]",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": true,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": false
|
| 786 |
+
},
|
| 787 |
+
"50350": {
|
| 788 |
+
"content": "[unused65]",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": true,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": false
|
| 794 |
+
},
|
| 795 |
+
"50351": {
|
| 796 |
+
"content": "[unused66]",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": true,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": false
|
| 802 |
+
},
|
| 803 |
+
"50352": {
|
| 804 |
+
"content": "[unused67]",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": true,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": false
|
| 810 |
+
},
|
| 811 |
+
"50353": {
|
| 812 |
+
"content": "[unused68]",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": true,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": false
|
| 818 |
+
},
|
| 819 |
+
"50354": {
|
| 820 |
+
"content": "[unused69]",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": true,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": false
|
| 826 |
+
},
|
| 827 |
+
"50355": {
|
| 828 |
+
"content": "[unused70]",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": true,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": false
|
| 834 |
+
},
|
| 835 |
+
"50356": {
|
| 836 |
+
"content": "[unused71]",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": true,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": false
|
| 842 |
+
},
|
| 843 |
+
"50357": {
|
| 844 |
+
"content": "[unused72]",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": true,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": false
|
| 850 |
+
},
|
| 851 |
+
"50358": {
|
| 852 |
+
"content": "[unused73]",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": true,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": false
|
| 858 |
+
},
|
| 859 |
+
"50359": {
|
| 860 |
+
"content": "[unused74]",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": true,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": false
|
| 866 |
+
},
|
| 867 |
+
"50360": {
|
| 868 |
+
"content": "[unused75]",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": true,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": false
|
| 874 |
+
},
|
| 875 |
+
"50361": {
|
| 876 |
+
"content": "[unused76]",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": true,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": false
|
| 882 |
+
},
|
| 883 |
+
"50362": {
|
| 884 |
+
"content": "[unused77]",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": true,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": false
|
| 890 |
+
},
|
| 891 |
+
"50363": {
|
| 892 |
+
"content": "[unused78]",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": true,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": false
|
| 898 |
+
},
|
| 899 |
+
"50364": {
|
| 900 |
+
"content": "[unused79]",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": true,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": false
|
| 906 |
+
},
|
| 907 |
+
"50365": {
|
| 908 |
+
"content": "[unused80]",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": true,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": false
|
| 914 |
+
},
|
| 915 |
+
"50366": {
|
| 916 |
+
"content": "[unused81]",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": true,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": false
|
| 922 |
+
},
|
| 923 |
+
"50367": {
|
| 924 |
+
"content": "[unused82]",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": true,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": false
|
| 930 |
+
}
|
| 931 |
+
},
|
| 932 |
+
"clean_up_tokenization_spaces": true,
|
| 933 |
+
"cls_token": "[CLS]",
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
+
"mask_token": "[MASK]",
|
| 936 |
+
"model_input_names": [
|
| 937 |
+
"input_ids",
|
| 938 |
+
"attention_mask"
|
| 939 |
+
],
|
| 940 |
+
"model_max_length": 8192,
|
| 941 |
+
"pad_token": "[PAD]",
|
| 942 |
+
"sep_token": "[SEP]",
|
| 943 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
| 944 |
+
"unk_token": "[UNK]"
|
| 945 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1234 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.6348773841961854,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 6000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.013623978201634877,
|
| 14 |
+
"grad_norm": 3.040151834487915,
|
| 15 |
+
"learning_rate": 4.9786557674841054e-05,
|
| 16 |
+
"loss": 1.5564,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.027247956403269755,
|
| 21 |
+
"grad_norm": 4.2518086433410645,
|
| 22 |
+
"learning_rate": 4.9559491371480476e-05,
|
| 23 |
+
"loss": 1.2807,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04087193460490463,
|
| 28 |
+
"grad_norm": 24.88307762145996,
|
| 29 |
+
"learning_rate": 4.933242506811989e-05,
|
| 30 |
+
"loss": 1.0105,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.05449591280653951,
|
| 35 |
+
"grad_norm": 5.034740447998047,
|
| 36 |
+
"learning_rate": 4.910535876475931e-05,
|
| 37 |
+
"loss": 0.8276,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05449591280653951,
|
| 42 |
+
"eval_accuracy": 0.7211171662125341,
|
| 43 |
+
"eval_f1": 0.6750582112410249,
|
| 44 |
+
"eval_loss": 0.6712220311164856,
|
| 45 |
+
"eval_precision": 0.7004051229737172,
|
| 46 |
+
"eval_recall": 0.7211171662125341,
|
| 47 |
+
"eval_runtime": 38.3333,
|
| 48 |
+
"eval_samples_per_second": 191.478,
|
| 49 |
+
"eval_steps_per_second": 11.974,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.0681198910081744,
|
| 54 |
+
"grad_norm": 16.025089263916016,
|
| 55 |
+
"learning_rate": 4.887829246139873e-05,
|
| 56 |
+
"loss": 0.722,
|
| 57 |
+
"step": 250
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.08174386920980926,
|
| 61 |
+
"grad_norm": 5.8490891456604,
|
| 62 |
+
"learning_rate": 4.865122615803815e-05,
|
| 63 |
+
"loss": 0.8055,
|
| 64 |
+
"step": 300
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.09536784741144415,
|
| 68 |
+
"grad_norm": 6.563209056854248,
|
| 69 |
+
"learning_rate": 4.842415985467757e-05,
|
| 70 |
+
"loss": 0.6658,
|
| 71 |
+
"step": 350
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.10899182561307902,
|
| 75 |
+
"grad_norm": 5.135402679443359,
|
| 76 |
+
"learning_rate": 4.819709355131699e-05,
|
| 77 |
+
"loss": 0.6751,
|
| 78 |
+
"step": 400
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.10899182561307902,
|
| 82 |
+
"eval_accuracy": 0.7158038147138964,
|
| 83 |
+
"eval_f1": 0.7029378642258501,
|
| 84 |
+
"eval_loss": 0.6223507523536682,
|
| 85 |
+
"eval_precision": 0.7307304008889945,
|
| 86 |
+
"eval_recall": 0.7158038147138964,
|
| 87 |
+
"eval_runtime": 38.9436,
|
| 88 |
+
"eval_samples_per_second": 188.478,
|
| 89 |
+
"eval_steps_per_second": 11.786,
|
| 90 |
+
"step": 400
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.1226158038147139,
|
| 94 |
+
"grad_norm": 4.828739643096924,
|
| 95 |
+
"learning_rate": 4.7970027247956404e-05,
|
| 96 |
+
"loss": 0.6159,
|
| 97 |
+
"step": 450
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.1362397820163488,
|
| 101 |
+
"grad_norm": 7.577467441558838,
|
| 102 |
+
"learning_rate": 4.7742960944595826e-05,
|
| 103 |
+
"loss": 0.71,
|
| 104 |
+
"step": 500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.14986376021798364,
|
| 108 |
+
"grad_norm": 12.106951713562012,
|
| 109 |
+
"learning_rate": 4.751589464123524e-05,
|
| 110 |
+
"loss": 0.6515,
|
| 111 |
+
"step": 550
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.16348773841961853,
|
| 115 |
+
"grad_norm": 4.246662616729736,
|
| 116 |
+
"learning_rate": 4.728882833787466e-05,
|
| 117 |
+
"loss": 0.6159,
|
| 118 |
+
"step": 600
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.16348773841961853,
|
| 122 |
+
"eval_accuracy": 0.7670299727520435,
|
| 123 |
+
"eval_f1": 0.7441405099406139,
|
| 124 |
+
"eval_loss": 0.5788103342056274,
|
| 125 |
+
"eval_precision": 0.7589364817682434,
|
| 126 |
+
"eval_recall": 0.7670299727520435,
|
| 127 |
+
"eval_runtime": 40.7278,
|
| 128 |
+
"eval_samples_per_second": 180.221,
|
| 129 |
+
"eval_steps_per_second": 11.27,
|
| 130 |
+
"step": 600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.1771117166212534,
|
| 134 |
+
"grad_norm": 3.4937551021575928,
|
| 135 |
+
"learning_rate": 4.706176203451408e-05,
|
| 136 |
+
"loss": 0.5875,
|
| 137 |
+
"step": 650
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.1907356948228883,
|
| 141 |
+
"grad_norm": 7.366335868835449,
|
| 142 |
+
"learning_rate": 4.68346957311535e-05,
|
| 143 |
+
"loss": 0.5755,
|
| 144 |
+
"step": 700
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.20435967302452315,
|
| 148 |
+
"grad_norm": 5.80669641494751,
|
| 149 |
+
"learning_rate": 4.660762942779292e-05,
|
| 150 |
+
"loss": 0.6529,
|
| 151 |
+
"step": 750
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.21798365122615804,
|
| 155 |
+
"grad_norm": 5.406530857086182,
|
| 156 |
+
"learning_rate": 4.638056312443234e-05,
|
| 157 |
+
"loss": 0.5457,
|
| 158 |
+
"step": 800
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.21798365122615804,
|
| 162 |
+
"eval_accuracy": 0.8043596730245232,
|
| 163 |
+
"eval_f1": 0.7884436299849555,
|
| 164 |
+
"eval_loss": 0.5009222626686096,
|
| 165 |
+
"eval_precision": 0.7887104187578498,
|
| 166 |
+
"eval_recall": 0.8043596730245232,
|
| 167 |
+
"eval_runtime": 39.3034,
|
| 168 |
+
"eval_samples_per_second": 186.752,
|
| 169 |
+
"eval_steps_per_second": 11.678,
|
| 170 |
+
"step": 800
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.23160762942779292,
|
| 174 |
+
"grad_norm": 5.1995062828063965,
|
| 175 |
+
"learning_rate": 4.6153496821071754e-05,
|
| 176 |
+
"loss": 0.5113,
|
| 177 |
+
"step": 850
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2452316076294278,
|
| 181 |
+
"grad_norm": 7.262979030609131,
|
| 182 |
+
"learning_rate": 4.592643051771117e-05,
|
| 183 |
+
"loss": 0.5886,
|
| 184 |
+
"step": 900
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.25885558583106266,
|
| 188 |
+
"grad_norm": 4.326200485229492,
|
| 189 |
+
"learning_rate": 4.569936421435059e-05,
|
| 190 |
+
"loss": 0.5004,
|
| 191 |
+
"step": 950
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2724795640326976,
|
| 195 |
+
"grad_norm": 4.408982753753662,
|
| 196 |
+
"learning_rate": 4.547229791099001e-05,
|
| 197 |
+
"loss": 0.5958,
|
| 198 |
+
"step": 1000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.2724795640326976,
|
| 202 |
+
"eval_accuracy": 0.8019073569482289,
|
| 203 |
+
"eval_f1": 0.7884210613649448,
|
| 204 |
+
"eval_loss": 0.5075427889823914,
|
| 205 |
+
"eval_precision": 0.7978971957067001,
|
| 206 |
+
"eval_recall": 0.8019073569482289,
|
| 207 |
+
"eval_runtime": 39.1465,
|
| 208 |
+
"eval_samples_per_second": 187.501,
|
| 209 |
+
"eval_steps_per_second": 11.725,
|
| 210 |
+
"step": 1000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.28610354223433243,
|
| 214 |
+
"grad_norm": 4.403244972229004,
|
| 215 |
+
"learning_rate": 4.524523160762943e-05,
|
| 216 |
+
"loss": 0.5382,
|
| 217 |
+
"step": 1050
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.2997275204359673,
|
| 221 |
+
"grad_norm": 3.9688315391540527,
|
| 222 |
+
"learning_rate": 4.501816530426885e-05,
|
| 223 |
+
"loss": 0.626,
|
| 224 |
+
"step": 1100
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.3133514986376022,
|
| 228 |
+
"grad_norm": 5.429931163787842,
|
| 229 |
+
"learning_rate": 4.4791099000908266e-05,
|
| 230 |
+
"loss": 0.5669,
|
| 231 |
+
"step": 1150
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.32697547683923706,
|
| 235 |
+
"grad_norm": 2.1590607166290283,
|
| 236 |
+
"learning_rate": 4.456403269754769e-05,
|
| 237 |
+
"loss": 0.5207,
|
| 238 |
+
"step": 1200
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.32697547683923706,
|
| 242 |
+
"eval_accuracy": 0.8042234332425068,
|
| 243 |
+
"eval_f1": 0.7882201527973293,
|
| 244 |
+
"eval_loss": 0.4852093756198883,
|
| 245 |
+
"eval_precision": 0.7987108830073256,
|
| 246 |
+
"eval_recall": 0.8042234332425068,
|
| 247 |
+
"eval_runtime": 39.4766,
|
| 248 |
+
"eval_samples_per_second": 185.933,
|
| 249 |
+
"eval_steps_per_second": 11.627,
|
| 250 |
+
"step": 1200
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.3405994550408719,
|
| 254 |
+
"grad_norm": 2.970989942550659,
|
| 255 |
+
"learning_rate": 4.433696639418711e-05,
|
| 256 |
+
"loss": 0.5158,
|
| 257 |
+
"step": 1250
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.3542234332425068,
|
| 261 |
+
"grad_norm": 4.843904972076416,
|
| 262 |
+
"learning_rate": 4.4109900090826526e-05,
|
| 263 |
+
"loss": 0.4638,
|
| 264 |
+
"step": 1300
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.3678474114441417,
|
| 268 |
+
"grad_norm": 2.107961654663086,
|
| 269 |
+
"learning_rate": 4.388283378746594e-05,
|
| 270 |
+
"loss": 0.5054,
|
| 271 |
+
"step": 1350
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.3814713896457766,
|
| 275 |
+
"grad_norm": 2.267613410949707,
|
| 276 |
+
"learning_rate": 4.3655767484105356e-05,
|
| 277 |
+
"loss": 0.5511,
|
| 278 |
+
"step": 1400
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.3814713896457766,
|
| 282 |
+
"eval_accuracy": 0.8220708446866485,
|
| 283 |
+
"eval_f1": 0.8151771754853724,
|
| 284 |
+
"eval_loss": 0.44333121180534363,
|
| 285 |
+
"eval_precision": 0.8163392565792945,
|
| 286 |
+
"eval_recall": 0.8220708446866485,
|
| 287 |
+
"eval_runtime": 39.2848,
|
| 288 |
+
"eval_samples_per_second": 186.841,
|
| 289 |
+
"eval_steps_per_second": 11.684,
|
| 290 |
+
"step": 1400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.39509536784741145,
|
| 294 |
+
"grad_norm": 5.881214618682861,
|
| 295 |
+
"learning_rate": 4.342870118074478e-05,
|
| 296 |
+
"loss": 0.5019,
|
| 297 |
+
"step": 1450
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.4087193460490463,
|
| 301 |
+
"grad_norm": 6.367845058441162,
|
| 302 |
+
"learning_rate": 4.32016348773842e-05,
|
| 303 |
+
"loss": 0.4986,
|
| 304 |
+
"step": 1500
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4223433242506812,
|
| 308 |
+
"grad_norm": 3.946660041809082,
|
| 309 |
+
"learning_rate": 4.2974568574023616e-05,
|
| 310 |
+
"loss": 0.5056,
|
| 311 |
+
"step": 1550
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.4359673024523161,
|
| 315 |
+
"grad_norm": 3.114546060562134,
|
| 316 |
+
"learning_rate": 4.274750227066304e-05,
|
| 317 |
+
"loss": 0.5094,
|
| 318 |
+
"step": 1600
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.4359673024523161,
|
| 322 |
+
"eval_accuracy": 0.8198910081743869,
|
| 323 |
+
"eval_f1": 0.8085671594623058,
|
| 324 |
+
"eval_loss": 0.44843149185180664,
|
| 325 |
+
"eval_precision": 0.8199358535824399,
|
| 326 |
+
"eval_recall": 0.8198910081743869,
|
| 327 |
+
"eval_runtime": 39.3837,
|
| 328 |
+
"eval_samples_per_second": 186.371,
|
| 329 |
+
"eval_steps_per_second": 11.655,
|
| 330 |
+
"step": 1600
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.44959128065395093,
|
| 334 |
+
"grad_norm": 5.56833553314209,
|
| 335 |
+
"learning_rate": 4.2520435967302454e-05,
|
| 336 |
+
"loss": 0.49,
|
| 337 |
+
"step": 1650
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.46321525885558584,
|
| 341 |
+
"grad_norm": 1.3245644569396973,
|
| 342 |
+
"learning_rate": 4.2293369663941876e-05,
|
| 343 |
+
"loss": 0.4293,
|
| 344 |
+
"step": 1700
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.4768392370572207,
|
| 348 |
+
"grad_norm": 1.4964958429336548,
|
| 349 |
+
"learning_rate": 4.206630336058129e-05,
|
| 350 |
+
"loss": 0.4674,
|
| 351 |
+
"step": 1750
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.4904632152588556,
|
| 355 |
+
"grad_norm": 6.4207868576049805,
|
| 356 |
+
"learning_rate": 4.1839237057220706e-05,
|
| 357 |
+
"loss": 0.486,
|
| 358 |
+
"step": 1800
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.4904632152588556,
|
| 362 |
+
"eval_accuracy": 0.7931880108991826,
|
| 363 |
+
"eval_f1": 0.7892022337920381,
|
| 364 |
+
"eval_loss": 0.5324758291244507,
|
| 365 |
+
"eval_precision": 0.8152839001650488,
|
| 366 |
+
"eval_recall": 0.7931880108991826,
|
| 367 |
+
"eval_runtime": 39.0794,
|
| 368 |
+
"eval_samples_per_second": 187.823,
|
| 369 |
+
"eval_steps_per_second": 11.745,
|
| 370 |
+
"step": 1800
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.5040871934604905,
|
| 374 |
+
"grad_norm": 3.860630512237549,
|
| 375 |
+
"learning_rate": 4.161217075386013e-05,
|
| 376 |
+
"loss": 0.5087,
|
| 377 |
+
"step": 1850
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.5177111716621253,
|
| 381 |
+
"grad_norm": 4.180031776428223,
|
| 382 |
+
"learning_rate": 4.1385104450499544e-05,
|
| 383 |
+
"loss": 0.4508,
|
| 384 |
+
"step": 1900
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.5313351498637602,
|
| 388 |
+
"grad_norm": 3.8397634029388428,
|
| 389 |
+
"learning_rate": 4.1158038147138966e-05,
|
| 390 |
+
"loss": 0.475,
|
| 391 |
+
"step": 1950
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.5449591280653951,
|
| 395 |
+
"grad_norm": 5.710933208465576,
|
| 396 |
+
"learning_rate": 4.093097184377839e-05,
|
| 397 |
+
"loss": 0.4404,
|
| 398 |
+
"step": 2000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.5449591280653951,
|
| 402 |
+
"eval_accuracy": 0.821117166212534,
|
| 403 |
+
"eval_f1": 0.814914871858581,
|
| 404 |
+
"eval_loss": 0.45968085527420044,
|
| 405 |
+
"eval_precision": 0.8191778311906968,
|
| 406 |
+
"eval_recall": 0.821117166212534,
|
| 407 |
+
"eval_runtime": 39.2262,
|
| 408 |
+
"eval_samples_per_second": 187.12,
|
| 409 |
+
"eval_steps_per_second": 11.701,
|
| 410 |
+
"step": 2000
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.55858310626703,
|
| 414 |
+
"grad_norm": 3.4445128440856934,
|
| 415 |
+
"learning_rate": 4.0703905540417803e-05,
|
| 416 |
+
"loss": 0.485,
|
| 417 |
+
"step": 2050
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.5722070844686649,
|
| 421 |
+
"grad_norm": 2.0595271587371826,
|
| 422 |
+
"learning_rate": 4.0476839237057226e-05,
|
| 423 |
+
"loss": 0.4662,
|
| 424 |
+
"step": 2100
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.5858310626702997,
|
| 428 |
+
"grad_norm": 1.4724421501159668,
|
| 429 |
+
"learning_rate": 4.024977293369664e-05,
|
| 430 |
+
"loss": 0.4597,
|
| 431 |
+
"step": 2150
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.5994550408719346,
|
| 435 |
+
"grad_norm": 3.4617927074432373,
|
| 436 |
+
"learning_rate": 4.002270663033606e-05,
|
| 437 |
+
"loss": 0.5117,
|
| 438 |
+
"step": 2200
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.5994550408719346,
|
| 442 |
+
"eval_accuracy": 0.8012261580381471,
|
| 443 |
+
"eval_f1": 0.7838518874639891,
|
| 444 |
+
"eval_loss": 0.5174744725227356,
|
| 445 |
+
"eval_precision": 0.8073537320499754,
|
| 446 |
+
"eval_recall": 0.8012261580381471,
|
| 447 |
+
"eval_runtime": 39.2852,
|
| 448 |
+
"eval_samples_per_second": 186.839,
|
| 449 |
+
"eval_steps_per_second": 11.684,
|
| 450 |
+
"step": 2200
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.6130790190735694,
|
| 454 |
+
"grad_norm": 5.364044189453125,
|
| 455 |
+
"learning_rate": 3.979564032697548e-05,
|
| 456 |
+
"loss": 0.5748,
|
| 457 |
+
"step": 2250
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.6267029972752044,
|
| 461 |
+
"grad_norm": 6.066217422485352,
|
| 462 |
+
"learning_rate": 3.9568574023614894e-05,
|
| 463 |
+
"loss": 0.5297,
|
| 464 |
+
"step": 2300
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.6403269754768393,
|
| 468 |
+
"grad_norm": 0.9179258346557617,
|
| 469 |
+
"learning_rate": 3.9341507720254316e-05,
|
| 470 |
+
"loss": 0.4056,
|
| 471 |
+
"step": 2350
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.6539509536784741,
|
| 475 |
+
"grad_norm": 5.265466213226318,
|
| 476 |
+
"learning_rate": 3.911444141689373e-05,
|
| 477 |
+
"loss": 0.5134,
|
| 478 |
+
"step": 2400
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.6539509536784741,
|
| 482 |
+
"eval_accuracy": 0.8224795640326975,
|
| 483 |
+
"eval_f1": 0.8176549340592166,
|
| 484 |
+
"eval_loss": 0.43617671728134155,
|
| 485 |
+
"eval_precision": 0.8297416199964833,
|
| 486 |
+
"eval_recall": 0.8224795640326975,
|
| 487 |
+
"eval_runtime": 39.4454,
|
| 488 |
+
"eval_samples_per_second": 186.08,
|
| 489 |
+
"eval_steps_per_second": 11.636,
|
| 490 |
+
"step": 2400
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.667574931880109,
|
| 494 |
+
"grad_norm": 3.929473400115967,
|
| 495 |
+
"learning_rate": 3.8887375113533153e-05,
|
| 496 |
+
"loss": 0.4943,
|
| 497 |
+
"step": 2450
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.6811989100817438,
|
| 501 |
+
"grad_norm": 5.633317947387695,
|
| 502 |
+
"learning_rate": 3.8660308810172576e-05,
|
| 503 |
+
"loss": 0.4633,
|
| 504 |
+
"step": 2500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.6948228882833788,
|
| 508 |
+
"grad_norm": 5.290429592132568,
|
| 509 |
+
"learning_rate": 3.843324250681199e-05,
|
| 510 |
+
"loss": 0.443,
|
| 511 |
+
"step": 2550
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.7084468664850136,
|
| 515 |
+
"grad_norm": 7.304491996765137,
|
| 516 |
+
"learning_rate": 3.820617620345141e-05,
|
| 517 |
+
"loss": 0.5273,
|
| 518 |
+
"step": 2600
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.7084468664850136,
|
| 522 |
+
"eval_accuracy": 0.8346049046321525,
|
| 523 |
+
"eval_f1": 0.8301732046667709,
|
| 524 |
+
"eval_loss": 0.42213955521583557,
|
| 525 |
+
"eval_precision": 0.836033830915573,
|
| 526 |
+
"eval_recall": 0.8346049046321525,
|
| 527 |
+
"eval_runtime": 39.2458,
|
| 528 |
+
"eval_samples_per_second": 187.026,
|
| 529 |
+
"eval_steps_per_second": 11.696,
|
| 530 |
+
"step": 2600
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.7220708446866485,
|
| 534 |
+
"grad_norm": 4.835093975067139,
|
| 535 |
+
"learning_rate": 3.797910990009083e-05,
|
| 536 |
+
"loss": 0.4684,
|
| 537 |
+
"step": 2650
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.7356948228882834,
|
| 541 |
+
"grad_norm": 2.2180492877960205,
|
| 542 |
+
"learning_rate": 3.7752043596730244e-05,
|
| 543 |
+
"loss": 0.4262,
|
| 544 |
+
"step": 2700
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.7493188010899182,
|
| 548 |
+
"grad_norm": 2.7012526988983154,
|
| 549 |
+
"learning_rate": 3.7524977293369666e-05,
|
| 550 |
+
"loss": 0.4145,
|
| 551 |
+
"step": 2750
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.7629427792915532,
|
| 555 |
+
"grad_norm": 6.204261779785156,
|
| 556 |
+
"learning_rate": 3.729791099000908e-05,
|
| 557 |
+
"loss": 0.4236,
|
| 558 |
+
"step": 2800
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.7629427792915532,
|
| 562 |
+
"eval_accuracy": 0.8416893732970028,
|
| 563 |
+
"eval_f1": 0.8376095906779634,
|
| 564 |
+
"eval_loss": 0.4056047201156616,
|
| 565 |
+
"eval_precision": 0.8385532518248264,
|
| 566 |
+
"eval_recall": 0.8416893732970028,
|
| 567 |
+
"eval_runtime": 39.2548,
|
| 568 |
+
"eval_samples_per_second": 186.984,
|
| 569 |
+
"eval_steps_per_second": 11.693,
|
| 570 |
+
"step": 2800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.776566757493188,
|
| 574 |
+
"grad_norm": 5.149259090423584,
|
| 575 |
+
"learning_rate": 3.7070844686648503e-05,
|
| 576 |
+
"loss": 0.463,
|
| 577 |
+
"step": 2850
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.7901907356948229,
|
| 581 |
+
"grad_norm": 3.473318576812744,
|
| 582 |
+
"learning_rate": 3.684377838328792e-05,
|
| 583 |
+
"loss": 0.3832,
|
| 584 |
+
"step": 2900
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.8038147138964578,
|
| 588 |
+
"grad_norm": 4.627190589904785,
|
| 589 |
+
"learning_rate": 3.661671207992734e-05,
|
| 590 |
+
"loss": 0.349,
|
| 591 |
+
"step": 2950
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.8174386920980926,
|
| 595 |
+
"grad_norm": 6.506262302398682,
|
| 596 |
+
"learning_rate": 3.638964577656676e-05,
|
| 597 |
+
"loss": 0.4429,
|
| 598 |
+
"step": 3000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.8174386920980926,
|
| 602 |
+
"eval_accuracy": 0.8209809264305177,
|
| 603 |
+
"eval_f1": 0.8212439998778114,
|
| 604 |
+
"eval_loss": 0.48423996567726135,
|
| 605 |
+
"eval_precision": 0.8278178165511351,
|
| 606 |
+
"eval_recall": 0.8209809264305177,
|
| 607 |
+
"eval_runtime": 39.376,
|
| 608 |
+
"eval_samples_per_second": 186.408,
|
| 609 |
+
"eval_steps_per_second": 11.657,
|
| 610 |
+
"step": 3000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.8310626702997275,
|
| 614 |
+
"grad_norm": 4.5560383796691895,
|
| 615 |
+
"learning_rate": 3.616257947320618e-05,
|
| 616 |
+
"loss": 0.4988,
|
| 617 |
+
"step": 3050
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.8446866485013624,
|
| 621 |
+
"grad_norm": 4.5877156257629395,
|
| 622 |
+
"learning_rate": 3.59355131698456e-05,
|
| 623 |
+
"loss": 0.3699,
|
| 624 |
+
"step": 3100
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.8583106267029973,
|
| 628 |
+
"grad_norm": 5.670323371887207,
|
| 629 |
+
"learning_rate": 3.5708446866485016e-05,
|
| 630 |
+
"loss": 0.4385,
|
| 631 |
+
"step": 3150
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.8719346049046321,
|
| 635 |
+
"grad_norm": 2.6689882278442383,
|
| 636 |
+
"learning_rate": 3.548138056312443e-05,
|
| 637 |
+
"loss": 0.4039,
|
| 638 |
+
"step": 3200
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.8719346049046321,
|
| 642 |
+
"eval_accuracy": 0.8485013623978201,
|
| 643 |
+
"eval_f1": 0.843592674785316,
|
| 644 |
+
"eval_loss": 0.39310726523399353,
|
| 645 |
+
"eval_precision": 0.847405927098554,
|
| 646 |
+
"eval_recall": 0.8485013623978201,
|
| 647 |
+
"eval_runtime": 39.4436,
|
| 648 |
+
"eval_samples_per_second": 186.089,
|
| 649 |
+
"eval_steps_per_second": 11.637,
|
| 650 |
+
"step": 3200
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.885558583106267,
|
| 654 |
+
"grad_norm": 1.9075839519500732,
|
| 655 |
+
"learning_rate": 3.525431425976385e-05,
|
| 656 |
+
"loss": 0.411,
|
| 657 |
+
"step": 3250
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.8991825613079019,
|
| 661 |
+
"grad_norm": 4.115935802459717,
|
| 662 |
+
"learning_rate": 3.502724795640327e-05,
|
| 663 |
+
"loss": 0.4112,
|
| 664 |
+
"step": 3300
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.9128065395095368,
|
| 668 |
+
"grad_norm": 2.8845183849334717,
|
| 669 |
+
"learning_rate": 3.480018165304269e-05,
|
| 670 |
+
"loss": 0.3931,
|
| 671 |
+
"step": 3350
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.9264305177111717,
|
| 675 |
+
"grad_norm": 5.959798336029053,
|
| 676 |
+
"learning_rate": 3.457311534968211e-05,
|
| 677 |
+
"loss": 0.4499,
|
| 678 |
+
"step": 3400
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.9264305177111717,
|
| 682 |
+
"eval_accuracy": 0.8366485013623978,
|
| 683 |
+
"eval_f1": 0.8371173604861236,
|
| 684 |
+
"eval_loss": 0.43168991804122925,
|
| 685 |
+
"eval_precision": 0.8493978099646374,
|
| 686 |
+
"eval_recall": 0.8366485013623978,
|
| 687 |
+
"eval_runtime": 40.9976,
|
| 688 |
+
"eval_samples_per_second": 179.035,
|
| 689 |
+
"eval_steps_per_second": 11.196,
|
| 690 |
+
"step": 3400
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.9400544959128065,
|
| 694 |
+
"grad_norm": 7.796460151672363,
|
| 695 |
+
"learning_rate": 3.434604904632153e-05,
|
| 696 |
+
"loss": 0.487,
|
| 697 |
+
"step": 3450
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.9536784741144414,
|
| 701 |
+
"grad_norm": 5.747544288635254,
|
| 702 |
+
"learning_rate": 3.411898274296095e-05,
|
| 703 |
+
"loss": 0.4197,
|
| 704 |
+
"step": 3500
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.9673024523160763,
|
| 708 |
+
"grad_norm": 2.902282953262329,
|
| 709 |
+
"learning_rate": 3.3891916439600366e-05,
|
| 710 |
+
"loss": 0.4066,
|
| 711 |
+
"step": 3550
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.9809264305177112,
|
| 715 |
+
"grad_norm": 7.779834747314453,
|
| 716 |
+
"learning_rate": 3.366485013623978e-05,
|
| 717 |
+
"loss": 0.3876,
|
| 718 |
+
"step": 3600
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.9809264305177112,
|
| 722 |
+
"eval_accuracy": 0.8555858310626703,
|
| 723 |
+
"eval_f1": 0.8510007395096015,
|
| 724 |
+
"eval_loss": 0.3871959149837494,
|
| 725 |
+
"eval_precision": 0.8520110874749584,
|
| 726 |
+
"eval_recall": 0.8555858310626703,
|
| 727 |
+
"eval_runtime": 39.3945,
|
| 728 |
+
"eval_samples_per_second": 186.32,
|
| 729 |
+
"eval_steps_per_second": 11.651,
|
| 730 |
+
"step": 3600
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.9945504087193461,
|
| 734 |
+
"grad_norm": 6.112946033477783,
|
| 735 |
+
"learning_rate": 3.34377838328792e-05,
|
| 736 |
+
"loss": 0.394,
|
| 737 |
+
"step": 3650
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.008174386920981,
|
| 741 |
+
"grad_norm": 2.9620373249053955,
|
| 742 |
+
"learning_rate": 3.321071752951862e-05,
|
| 743 |
+
"loss": 0.3563,
|
| 744 |
+
"step": 3700
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.021798365122616,
|
| 748 |
+
"grad_norm": 4.225318908691406,
|
| 749 |
+
"learning_rate": 3.298365122615804e-05,
|
| 750 |
+
"loss": 0.3394,
|
| 751 |
+
"step": 3750
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.0354223433242506,
|
| 755 |
+
"grad_norm": 4.271127223968506,
|
| 756 |
+
"learning_rate": 3.2756584922797456e-05,
|
| 757 |
+
"loss": 0.3265,
|
| 758 |
+
"step": 3800
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.0354223433242506,
|
| 762 |
+
"eval_accuracy": 0.8442779291553133,
|
| 763 |
+
"eval_f1": 0.8423344722305859,
|
| 764 |
+
"eval_loss": 0.4092128872871399,
|
| 765 |
+
"eval_precision": 0.844819730861473,
|
| 766 |
+
"eval_recall": 0.8442779291553133,
|
| 767 |
+
"eval_runtime": 39.2791,
|
| 768 |
+
"eval_samples_per_second": 186.868,
|
| 769 |
+
"eval_steps_per_second": 11.686,
|
| 770 |
+
"step": 3800
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.0490463215258856,
|
| 774 |
+
"grad_norm": 5.944393634796143,
|
| 775 |
+
"learning_rate": 3.252951861943688e-05,
|
| 776 |
+
"loss": 0.3015,
|
| 777 |
+
"step": 3850
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.0626702997275204,
|
| 781 |
+
"grad_norm": 4.36716890335083,
|
| 782 |
+
"learning_rate": 3.23024523160763e-05,
|
| 783 |
+
"loss": 0.3369,
|
| 784 |
+
"step": 3900
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.0762942779291553,
|
| 788 |
+
"grad_norm": 6.840479850769043,
|
| 789 |
+
"learning_rate": 3.207992733878293e-05,
|
| 790 |
+
"loss": 0.3459,
|
| 791 |
+
"step": 3950
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.0899182561307903,
|
| 795 |
+
"grad_norm": 2.2635903358459473,
|
| 796 |
+
"learning_rate": 3.185286103542234e-05,
|
| 797 |
+
"loss": 0.369,
|
| 798 |
+
"step": 4000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.0899182561307903,
|
| 802 |
+
"eval_accuracy": 0.8351498637602179,
|
| 803 |
+
"eval_f1": 0.8345444526814599,
|
| 804 |
+
"eval_loss": 0.44853049516677856,
|
| 805 |
+
"eval_precision": 0.8451624069805984,
|
| 806 |
+
"eval_recall": 0.8351498637602179,
|
| 807 |
+
"eval_runtime": 39.2298,
|
| 808 |
+
"eval_samples_per_second": 187.103,
|
| 809 |
+
"eval_steps_per_second": 11.7,
|
| 810 |
+
"step": 4000
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.103542234332425,
|
| 814 |
+
"grad_norm": 10.20390510559082,
|
| 815 |
+
"learning_rate": 3.1625794732061765e-05,
|
| 816 |
+
"loss": 0.3449,
|
| 817 |
+
"step": 4050
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 1.11716621253406,
|
| 821 |
+
"grad_norm": 0.1351608783006668,
|
| 822 |
+
"learning_rate": 3.139872842870118e-05,
|
| 823 |
+
"loss": 0.3357,
|
| 824 |
+
"step": 4100
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.1307901907356948,
|
| 828 |
+
"grad_norm": 2.0290515422821045,
|
| 829 |
+
"learning_rate": 3.11716621253406e-05,
|
| 830 |
+
"loss": 0.3782,
|
| 831 |
+
"step": 4150
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.1444141689373297,
|
| 835 |
+
"grad_norm": 2.227574586868286,
|
| 836 |
+
"learning_rate": 3.094459582198002e-05,
|
| 837 |
+
"loss": 0.3383,
|
| 838 |
+
"step": 4200
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.1444141689373297,
|
| 842 |
+
"eval_accuracy": 0.8622615803814714,
|
| 843 |
+
"eval_f1": 0.8598094201224885,
|
| 844 |
+
"eval_loss": 0.3893040716648102,
|
| 845 |
+
"eval_precision": 0.8592251940540689,
|
| 846 |
+
"eval_recall": 0.8622615803814714,
|
| 847 |
+
"eval_runtime": 39.4522,
|
| 848 |
+
"eval_samples_per_second": 186.048,
|
| 849 |
+
"eval_steps_per_second": 11.634,
|
| 850 |
+
"step": 4200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.1580381471389645,
|
| 854 |
+
"grad_norm": 2.8619637489318848,
|
| 855 |
+
"learning_rate": 3.0717529518619433e-05,
|
| 856 |
+
"loss": 0.4244,
|
| 857 |
+
"step": 4250
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.1716621253405994,
|
| 861 |
+
"grad_norm": 2.4978890419006348,
|
| 862 |
+
"learning_rate": 3.049046321525886e-05,
|
| 863 |
+
"loss": 0.3951,
|
| 864 |
+
"step": 4300
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.1852861035422344,
|
| 868 |
+
"grad_norm": 2.387751579284668,
|
| 869 |
+
"learning_rate": 3.0263396911898274e-05,
|
| 870 |
+
"loss": 0.3153,
|
| 871 |
+
"step": 4350
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.1989100817438691,
|
| 875 |
+
"grad_norm": 7.264976978302002,
|
| 876 |
+
"learning_rate": 3.0036330608537693e-05,
|
| 877 |
+
"loss": 0.3985,
|
| 878 |
+
"step": 4400
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.1989100817438691,
|
| 882 |
+
"eval_accuracy": 0.8493188010899183,
|
| 883 |
+
"eval_f1": 0.850019326075464,
|
| 884 |
+
"eval_loss": 0.44555896520614624,
|
| 885 |
+
"eval_precision": 0.8541605321280626,
|
| 886 |
+
"eval_recall": 0.8493188010899183,
|
| 887 |
+
"eval_runtime": 39.3959,
|
| 888 |
+
"eval_samples_per_second": 186.314,
|
| 889 |
+
"eval_steps_per_second": 11.651,
|
| 890 |
+
"step": 4400
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.2125340599455041,
|
| 894 |
+
"grad_norm": 2.748687505722046,
|
| 895 |
+
"learning_rate": 2.9809264305177115e-05,
|
| 896 |
+
"loss": 0.3217,
|
| 897 |
+
"step": 4450
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.226158038147139,
|
| 901 |
+
"grad_norm": 7.619766712188721,
|
| 902 |
+
"learning_rate": 2.958219800181653e-05,
|
| 903 |
+
"loss": 0.4105,
|
| 904 |
+
"step": 4500
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.2397820163487738,
|
| 908 |
+
"grad_norm": 5.104996204376221,
|
| 909 |
+
"learning_rate": 2.935513169845595e-05,
|
| 910 |
+
"loss": 0.3711,
|
| 911 |
+
"step": 4550
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 1.2534059945504088,
|
| 915 |
+
"grad_norm": 4.894058704376221,
|
| 916 |
+
"learning_rate": 2.912806539509537e-05,
|
| 917 |
+
"loss": 0.3878,
|
| 918 |
+
"step": 4600
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 1.2534059945504088,
|
| 922 |
+
"eval_accuracy": 0.8566757493188011,
|
| 923 |
+
"eval_f1": 0.8522483893823563,
|
| 924 |
+
"eval_loss": 0.3841998875141144,
|
| 925 |
+
"eval_precision": 0.8541643709440505,
|
| 926 |
+
"eval_recall": 0.8566757493188011,
|
| 927 |
+
"eval_runtime": 39.394,
|
| 928 |
+
"eval_samples_per_second": 186.323,
|
| 929 |
+
"eval_steps_per_second": 11.652,
|
| 930 |
+
"step": 4600
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.2670299727520435,
|
| 934 |
+
"grad_norm": 2.4597229957580566,
|
| 935 |
+
"learning_rate": 2.8900999091734787e-05,
|
| 936 |
+
"loss": 0.406,
|
| 937 |
+
"step": 4650
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.2806539509536785,
|
| 941 |
+
"grad_norm": 5.7981343269348145,
|
| 942 |
+
"learning_rate": 2.867393278837421e-05,
|
| 943 |
+
"loss": 0.3517,
|
| 944 |
+
"step": 4700
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 1.2942779291553133,
|
| 948 |
+
"grad_norm": 4.284982681274414,
|
| 949 |
+
"learning_rate": 2.8446866485013624e-05,
|
| 950 |
+
"loss": 0.3071,
|
| 951 |
+
"step": 4750
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 1.3079019073569482,
|
| 955 |
+
"grad_norm": 8.857301712036133,
|
| 956 |
+
"learning_rate": 2.8219800181653043e-05,
|
| 957 |
+
"loss": 0.3578,
|
| 958 |
+
"step": 4800
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.3079019073569482,
|
| 962 |
+
"eval_accuracy": 0.8568119891008175,
|
| 963 |
+
"eval_f1": 0.8532818648850209,
|
| 964 |
+
"eval_loss": 0.40182751417160034,
|
| 965 |
+
"eval_precision": 0.8533652780848004,
|
| 966 |
+
"eval_recall": 0.8568119891008175,
|
| 967 |
+
"eval_runtime": 39.2999,
|
| 968 |
+
"eval_samples_per_second": 186.769,
|
| 969 |
+
"eval_steps_per_second": 11.679,
|
| 970 |
+
"step": 4800
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.3215258855585832,
|
| 974 |
+
"grad_norm": 3.8386123180389404,
|
| 975 |
+
"learning_rate": 2.7992733878292465e-05,
|
| 976 |
+
"loss": 0.295,
|
| 977 |
+
"step": 4850
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.335149863760218,
|
| 981 |
+
"grad_norm": 6.5531463623046875,
|
| 982 |
+
"learning_rate": 2.776566757493188e-05,
|
| 983 |
+
"loss": 0.3963,
|
| 984 |
+
"step": 4900
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.348773841961853,
|
| 988 |
+
"grad_norm": 7.941685199737549,
|
| 989 |
+
"learning_rate": 2.7538601271571303e-05,
|
| 990 |
+
"loss": 0.3396,
|
| 991 |
+
"step": 4950
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 1.3623978201634879,
|
| 995 |
+
"grad_norm": 5.075099468231201,
|
| 996 |
+
"learning_rate": 2.7311534968210718e-05,
|
| 997 |
+
"loss": 0.3962,
|
| 998 |
+
"step": 5000
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.3623978201634879,
|
| 1002 |
+
"eval_accuracy": 0.8622615803814714,
|
| 1003 |
+
"eval_f1": 0.8595333600713432,
|
| 1004 |
+
"eval_loss": 0.37939050793647766,
|
| 1005 |
+
"eval_precision": 0.8596955747598374,
|
| 1006 |
+
"eval_recall": 0.8622615803814714,
|
| 1007 |
+
"eval_runtime": 39.294,
|
| 1008 |
+
"eval_samples_per_second": 186.797,
|
| 1009 |
+
"eval_steps_per_second": 11.681,
|
| 1010 |
+
"step": 5000
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.3760217983651226,
|
| 1014 |
+
"grad_norm": 2.8509788513183594,
|
| 1015 |
+
"learning_rate": 2.7084468664850137e-05,
|
| 1016 |
+
"loss": 0.3855,
|
| 1017 |
+
"step": 5050
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.3896457765667574,
|
| 1021 |
+
"grad_norm": 5.918415546417236,
|
| 1022 |
+
"learning_rate": 2.685740236148956e-05,
|
| 1023 |
+
"loss": 0.3238,
|
| 1024 |
+
"step": 5100
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.4032697547683923,
|
| 1028 |
+
"grad_norm": 4.571900844573975,
|
| 1029 |
+
"learning_rate": 2.6630336058128974e-05,
|
| 1030 |
+
"loss": 0.3277,
|
| 1031 |
+
"step": 5150
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.4168937329700273,
|
| 1035 |
+
"grad_norm": 5.005604267120361,
|
| 1036 |
+
"learning_rate": 2.6403269754768396e-05,
|
| 1037 |
+
"loss": 0.3979,
|
| 1038 |
+
"step": 5200
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.4168937329700273,
|
| 1042 |
+
"eval_accuracy": 0.8600817438692098,
|
| 1043 |
+
"eval_f1": 0.8570639571936529,
|
| 1044 |
+
"eval_loss": 0.3867308795452118,
|
| 1045 |
+
"eval_precision": 0.858591149569358,
|
| 1046 |
+
"eval_recall": 0.8600817438692098,
|
| 1047 |
+
"eval_runtime": 39.3968,
|
| 1048 |
+
"eval_samples_per_second": 186.31,
|
| 1049 |
+
"eval_steps_per_second": 11.651,
|
| 1050 |
+
"step": 5200
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.430517711171662,
|
| 1054 |
+
"grad_norm": 3.3436524868011475,
|
| 1055 |
+
"learning_rate": 2.6176203451407812e-05,
|
| 1056 |
+
"loss": 0.3755,
|
| 1057 |
+
"step": 5250
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 1.444141689373297,
|
| 1061 |
+
"grad_norm": 2.1698825359344482,
|
| 1062 |
+
"learning_rate": 2.594913714804723e-05,
|
| 1063 |
+
"loss": 0.2778,
|
| 1064 |
+
"step": 5300
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.457765667574932,
|
| 1068 |
+
"grad_norm": 4.432777404785156,
|
| 1069 |
+
"learning_rate": 2.5722070844686653e-05,
|
| 1070 |
+
"loss": 0.3833,
|
| 1071 |
+
"step": 5350
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 1.4713896457765667,
|
| 1075 |
+
"grad_norm": 4.060556411743164,
|
| 1076 |
+
"learning_rate": 2.5495004541326068e-05,
|
| 1077 |
+
"loss": 0.393,
|
| 1078 |
+
"step": 5400
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 1.4713896457765667,
|
| 1082 |
+
"eval_accuracy": 0.8645776566757494,
|
| 1083 |
+
"eval_f1": 0.859894933118512,
|
| 1084 |
+
"eval_loss": 0.3773682415485382,
|
| 1085 |
+
"eval_precision": 0.8635251166375231,
|
| 1086 |
+
"eval_recall": 0.8645776566757494,
|
| 1087 |
+
"eval_runtime": 39.4823,
|
| 1088 |
+
"eval_samples_per_second": 185.906,
|
| 1089 |
+
"eval_steps_per_second": 11.625,
|
| 1090 |
+
"step": 5400
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.4850136239782017,
|
| 1094 |
+
"grad_norm": 2.296135425567627,
|
| 1095 |
+
"learning_rate": 2.5267938237965487e-05,
|
| 1096 |
+
"loss": 0.2596,
|
| 1097 |
+
"step": 5450
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 1.4986376021798364,
|
| 1101 |
+
"grad_norm": 3.110579013824463,
|
| 1102 |
+
"learning_rate": 2.5040871934604902e-05,
|
| 1103 |
+
"loss": 0.3188,
|
| 1104 |
+
"step": 5500
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 1.5122615803814714,
|
| 1108 |
+
"grad_norm": 0.38325050473213196,
|
| 1109 |
+
"learning_rate": 2.4813805631244324e-05,
|
| 1110 |
+
"loss": 0.3707,
|
| 1111 |
+
"step": 5550
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 1.5258855585831061,
|
| 1115 |
+
"grad_norm": 1.0077499151229858,
|
| 1116 |
+
"learning_rate": 2.4586739327883743e-05,
|
| 1117 |
+
"loss": 0.2461,
|
| 1118 |
+
"step": 5600
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 1.5258855585831061,
|
| 1122 |
+
"eval_accuracy": 0.8677111716621253,
|
| 1123 |
+
"eval_f1": 0.8647432485320001,
|
| 1124 |
+
"eval_loss": 0.40655508637428284,
|
| 1125 |
+
"eval_precision": 0.866115043606446,
|
| 1126 |
+
"eval_recall": 0.8677111716621253,
|
| 1127 |
+
"eval_runtime": 39.421,
|
| 1128 |
+
"eval_samples_per_second": 186.195,
|
| 1129 |
+
"eval_steps_per_second": 11.644,
|
| 1130 |
+
"step": 5600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.5395095367847411,
|
| 1134 |
+
"grad_norm": 4.395697116851807,
|
| 1135 |
+
"learning_rate": 2.4359673024523162e-05,
|
| 1136 |
+
"loss": 0.3078,
|
| 1137 |
+
"step": 5650
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.553133514986376,
|
| 1141 |
+
"grad_norm": 4.02500581741333,
|
| 1142 |
+
"learning_rate": 2.413260672116258e-05,
|
| 1143 |
+
"loss": 0.4794,
|
| 1144 |
+
"step": 5700
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.5667574931880108,
|
| 1148 |
+
"grad_norm": 3.775764226913452,
|
| 1149 |
+
"learning_rate": 2.3905540417802e-05,
|
| 1150 |
+
"loss": 0.2948,
|
| 1151 |
+
"step": 5750
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.5803814713896458,
|
| 1155 |
+
"grad_norm": 1.1017502546310425,
|
| 1156 |
+
"learning_rate": 2.3678474114441418e-05,
|
| 1157 |
+
"loss": 0.322,
|
| 1158 |
+
"step": 5800
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.5803814713896458,
|
| 1162 |
+
"eval_accuracy": 0.8683923705722071,
|
| 1163 |
+
"eval_f1": 0.8666679607870518,
|
| 1164 |
+
"eval_loss": 0.3748830556869507,
|
| 1165 |
+
"eval_precision": 0.8666797382883451,
|
| 1166 |
+
"eval_recall": 0.8683923705722071,
|
| 1167 |
+
"eval_runtime": 39.4374,
|
| 1168 |
+
"eval_samples_per_second": 186.118,
|
| 1169 |
+
"eval_steps_per_second": 11.639,
|
| 1170 |
+
"step": 5800
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.5940054495912808,
|
| 1174 |
+
"grad_norm": 24.16415786743164,
|
| 1175 |
+
"learning_rate": 2.3451407811080837e-05,
|
| 1176 |
+
"loss": 0.3231,
|
| 1177 |
+
"step": 5850
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.6076294277929155,
|
| 1181 |
+
"grad_norm": 5.224663734436035,
|
| 1182 |
+
"learning_rate": 2.3224341507720255e-05,
|
| 1183 |
+
"loss": 0.3528,
|
| 1184 |
+
"step": 5900
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.6212534059945503,
|
| 1188 |
+
"grad_norm": 4.033137321472168,
|
| 1189 |
+
"learning_rate": 2.2997275204359674e-05,
|
| 1190 |
+
"loss": 0.362,
|
| 1191 |
+
"step": 5950
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.6348773841961854,
|
| 1195 |
+
"grad_norm": 3.7657642364501953,
|
| 1196 |
+
"learning_rate": 2.2770208900999093e-05,
|
| 1197 |
+
"loss": 0.3104,
|
| 1198 |
+
"step": 6000
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 1.6348773841961854,
|
| 1202 |
+
"eval_accuracy": 0.8681198910081744,
|
| 1203 |
+
"eval_f1": 0.8658248505222946,
|
| 1204 |
+
"eval_loss": 0.35615479946136475,
|
| 1205 |
+
"eval_precision": 0.8666734700848255,
|
| 1206 |
+
"eval_recall": 0.8681198910081744,
|
| 1207 |
+
"eval_runtime": 39.4899,
|
| 1208 |
+
"eval_samples_per_second": 185.87,
|
| 1209 |
+
"eval_steps_per_second": 11.623,
|
| 1210 |
+
"step": 6000
|
| 1211 |
+
}
|
| 1212 |
+
],
|
| 1213 |
+
"logging_steps": 50,
|
| 1214 |
+
"max_steps": 11010,
|
| 1215 |
+
"num_input_tokens_seen": 0,
|
| 1216 |
+
"num_train_epochs": 3,
|
| 1217 |
+
"save_steps": 200,
|
| 1218 |
+
"stateful_callbacks": {
|
| 1219 |
+
"TrainerControl": {
|
| 1220 |
+
"args": {
|
| 1221 |
+
"should_epoch_stop": false,
|
| 1222 |
+
"should_evaluate": false,
|
| 1223 |
+
"should_log": false,
|
| 1224 |
+
"should_save": true,
|
| 1225 |
+
"should_training_stop": false
|
| 1226 |
+
},
|
| 1227 |
+
"attributes": {}
|
| 1228 |
+
}
|
| 1229 |
+
},
|
| 1230 |
+
"total_flos": 2.5379531411779584e+16,
|
| 1231 |
+
"train_batch_size": 8,
|
| 1232 |
+
"trial_name": null,
|
| 1233 |
+
"trial_params": null
|
| 1234 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cc6228e27c24968ef2516fdcb9dda847eade57f0b34b3a289a6b89e12df06d1
|
| 3 |
+
size 5176
|