Upload 12 files
Browse files- config.json +54 -0
- model.onnx +3 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +945 -0
- trainer_state.json +2939 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"dtype": "float32",
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 50282,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"global_rope_theta": 160000.0,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_activation": "gelu",
|
| 22 |
+
"hidden_size": 768,
|
| 23 |
+
"id2label": {
|
| 24 |
+
"0": "LEGITIMATE",
|
| 25 |
+
"1": "INJECTION"
|
| 26 |
+
},
|
| 27 |
+
"initializer_cutoff_factor": 2.0,
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"intermediate_size": 1152,
|
| 30 |
+
"label2id": {
|
| 31 |
+
"INJECTION": 1,
|
| 32 |
+
"LEGITIMATE": 0
|
| 33 |
+
},
|
| 34 |
+
"layer_norm_eps": 1e-05,
|
| 35 |
+
"local_attention": 128,
|
| 36 |
+
"local_rope_theta": 10000.0,
|
| 37 |
+
"max_position_embeddings": 8192,
|
| 38 |
+
"mlp_bias": false,
|
| 39 |
+
"mlp_dropout": 0.0,
|
| 40 |
+
"model_type": "modernbert",
|
| 41 |
+
"norm_bias": false,
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"num_attention_heads": 12,
|
| 44 |
+
"num_hidden_layers": 22,
|
| 45 |
+
"pad_token_id": 50283,
|
| 46 |
+
"position_embedding_type": "absolute",
|
| 47 |
+
"problem_type": "single_label_classification",
|
| 48 |
+
"repad_logits_with_grad": false,
|
| 49 |
+
"sep_token_id": 50282,
|
| 50 |
+
"sparse_pred_ignore_index": -100,
|
| 51 |
+
"sparse_prediction": false,
|
| 52 |
+
"transformers_version": "4.57.1",
|
| 53 |
+
"vocab_size": 50368
|
| 54 |
+
}
|
model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b801332a012c9845d72e837d43da5351434c5bf73ff6ff804bcd1638263441b
|
| 3 |
+
size 599000438
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a277353682b8c52627def3169b8cfea228dd30a9a6cd3334c236aa0fb03dd161
|
| 3 |
+
size 598439784
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f35a251c8b98e87d20f57174913848e699b5065c29e9329fe8cbb81c476adefa
|
| 3 |
+
size 1196969803
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea11996454b5587fcf33ae0ab5cf14b2031bf5f53f8c2ed5a48e87de31e29c84
|
| 3 |
+
size 14645
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56f562c1f6ed0dd67bb21e6f5e439575f7cc893e4616c0c3ff3470db89814cb
|
| 3 |
+
size 1383
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:443205288bec932151a913ebfab3a65ab48faf4f589358aa2a6006cbe62fcace
|
| 3 |
+
size 1465
|
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": "PreTrainedTokenizerFast",
|
| 944 |
+
"unk_token": "[UNK]"
|
| 945 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2939 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 40000,
|
| 3 |
+
"best_metric": 0.983751846381093,
|
| 4 |
+
"best_model_checkpoint": "./outputs/checkpoint-40000",
|
| 5 |
+
"epoch": 2.3806802964021068,
|
| 6 |
+
"eval_steps": 5000,
|
| 7 |
+
"global_step": 40000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.005951849537243699,
|
| 14 |
+
"grad_norm": 14.474434852600098,
|
| 15 |
+
"learning_rate": 4.95e-07,
|
| 16 |
+
"loss": 1.738,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.011903699074487397,
|
| 21 |
+
"grad_norm": 8.228065490722656,
|
| 22 |
+
"learning_rate": 9.950000000000002e-07,
|
| 23 |
+
"loss": 0.9352,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.017855548611731095,
|
| 28 |
+
"grad_norm": 11.45659351348877,
|
| 29 |
+
"learning_rate": 1.495e-06,
|
| 30 |
+
"loss": 0.6597,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.023807398148974795,
|
| 35 |
+
"grad_norm": 14.828703880310059,
|
| 36 |
+
"learning_rate": 1.9950000000000004e-06,
|
| 37 |
+
"loss": 0.5121,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02975924768621849,
|
| 42 |
+
"grad_norm": 3.7912120819091797,
|
| 43 |
+
"learning_rate": 2.4950000000000003e-06,
|
| 44 |
+
"loss": 0.3892,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03571109722346219,
|
| 49 |
+
"grad_norm": 312.57928466796875,
|
| 50 |
+
"learning_rate": 2.995e-06,
|
| 51 |
+
"loss": 0.3349,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.041662946760705886,
|
| 56 |
+
"grad_norm": 10.562920570373535,
|
| 57 |
+
"learning_rate": 3.495e-06,
|
| 58 |
+
"loss": 0.3293,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.04761479629794959,
|
| 63 |
+
"grad_norm": 21.415306091308594,
|
| 64 |
+
"learning_rate": 3.995000000000001e-06,
|
| 65 |
+
"loss": 0.286,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.053566645835193286,
|
| 70 |
+
"grad_norm": 5.152000904083252,
|
| 71 |
+
"learning_rate": 4.495e-06,
|
| 72 |
+
"loss": 0.2326,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.05951849537243698,
|
| 77 |
+
"grad_norm": 12.22340202331543,
|
| 78 |
+
"learning_rate": 4.9950000000000005e-06,
|
| 79 |
+
"loss": 0.2202,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.06547034490968068,
|
| 84 |
+
"grad_norm": 25.30424690246582,
|
| 85 |
+
"learning_rate": 5.495000000000001e-06,
|
| 86 |
+
"loss": 0.245,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.07142219444692438,
|
| 91 |
+
"grad_norm": 15.469476699829102,
|
| 92 |
+
"learning_rate": 5.995000000000001e-06,
|
| 93 |
+
"loss": 0.2306,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.07737404398416808,
|
| 98 |
+
"grad_norm": 7.698344707489014,
|
| 99 |
+
"learning_rate": 6.4950000000000005e-06,
|
| 100 |
+
"loss": 0.1827,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.08332589352141177,
|
| 105 |
+
"grad_norm": 1.8406133651733398,
|
| 106 |
+
"learning_rate": 6.995000000000001e-06,
|
| 107 |
+
"loss": 0.2019,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.08927774305865548,
|
| 112 |
+
"grad_norm": 7.113662242889404,
|
| 113 |
+
"learning_rate": 7.495000000000001e-06,
|
| 114 |
+
"loss": 0.1878,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.09522959259589918,
|
| 119 |
+
"grad_norm": 60.53151321411133,
|
| 120 |
+
"learning_rate": 7.995e-06,
|
| 121 |
+
"loss": 0.2029,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.10118144213314287,
|
| 126 |
+
"grad_norm": 9.212539672851562,
|
| 127 |
+
"learning_rate": 8.495e-06,
|
| 128 |
+
"loss": 0.169,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.10713329167038657,
|
| 133 |
+
"grad_norm": 4.615962028503418,
|
| 134 |
+
"learning_rate": 8.995000000000001e-06,
|
| 135 |
+
"loss": 0.2175,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.11308514120763027,
|
| 140 |
+
"grad_norm": 18.574737548828125,
|
| 141 |
+
"learning_rate": 9.495000000000001e-06,
|
| 142 |
+
"loss": 0.1756,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.11903699074487396,
|
| 147 |
+
"grad_norm": 1.425147294998169,
|
| 148 |
+
"learning_rate": 9.995000000000002e-06,
|
| 149 |
+
"loss": 0.143,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.12498884028211767,
|
| 154 |
+
"grad_norm": 0.27230679988861084,
|
| 155 |
+
"learning_rate": 1.0495000000000002e-05,
|
| 156 |
+
"loss": 0.1585,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.13094068981936136,
|
| 161 |
+
"grad_norm": 1.6913175582885742,
|
| 162 |
+
"learning_rate": 1.0995e-05,
|
| 163 |
+
"loss": 0.1642,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.13689253935660506,
|
| 168 |
+
"grad_norm": 3.160975456237793,
|
| 169 |
+
"learning_rate": 1.1495000000000001e-05,
|
| 170 |
+
"loss": 0.1311,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.14284438889384876,
|
| 175 |
+
"grad_norm": 4.693823337554932,
|
| 176 |
+
"learning_rate": 1.1995000000000001e-05,
|
| 177 |
+
"loss": 0.1641,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.14879623843109246,
|
| 182 |
+
"grad_norm": 0.5840986371040344,
|
| 183 |
+
"learning_rate": 1.2495000000000001e-05,
|
| 184 |
+
"loss": 0.1653,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.15474808796833617,
|
| 189 |
+
"grad_norm": 1.879236102104187,
|
| 190 |
+
"learning_rate": 1.2995000000000002e-05,
|
| 191 |
+
"loss": 0.1382,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.16069993750557987,
|
| 196 |
+
"grad_norm": 0.4364721477031708,
|
| 197 |
+
"learning_rate": 1.3495e-05,
|
| 198 |
+
"loss": 0.1754,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.16665178704282355,
|
| 203 |
+
"grad_norm": 3.1517608165740967,
|
| 204 |
+
"learning_rate": 1.3995e-05,
|
| 205 |
+
"loss": 0.1523,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.17260363658006725,
|
| 210 |
+
"grad_norm": 1.0098434686660767,
|
| 211 |
+
"learning_rate": 1.4495000000000001e-05,
|
| 212 |
+
"loss": 0.158,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.17855548611731095,
|
| 217 |
+
"grad_norm": 11.904523849487305,
|
| 218 |
+
"learning_rate": 1.4995000000000001e-05,
|
| 219 |
+
"loss": 0.1262,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.18450733565455466,
|
| 224 |
+
"grad_norm": 7.423610687255859,
|
| 225 |
+
"learning_rate": 1.5495000000000003e-05,
|
| 226 |
+
"loss": 0.156,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.19045918519179836,
|
| 231 |
+
"grad_norm": 1.702813982963562,
|
| 232 |
+
"learning_rate": 1.5995000000000002e-05,
|
| 233 |
+
"loss": 0.1257,
|
| 234 |
+
"step": 3200
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.19641103472904206,
|
| 238 |
+
"grad_norm": 5.983730316162109,
|
| 239 |
+
"learning_rate": 1.6495e-05,
|
| 240 |
+
"loss": 0.1414,
|
| 241 |
+
"step": 3300
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.20236288426628574,
|
| 245 |
+
"grad_norm": 0.07421358674764633,
|
| 246 |
+
"learning_rate": 1.6995000000000002e-05,
|
| 247 |
+
"loss": 0.1159,
|
| 248 |
+
"step": 3400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.20831473380352944,
|
| 252 |
+
"grad_norm": 9.500596046447754,
|
| 253 |
+
"learning_rate": 1.7495e-05,
|
| 254 |
+
"loss": 0.1362,
|
| 255 |
+
"step": 3500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.21426658334077314,
|
| 259 |
+
"grad_norm": 2.0403008460998535,
|
| 260 |
+
"learning_rate": 1.7995000000000003e-05,
|
| 261 |
+
"loss": 0.1183,
|
| 262 |
+
"step": 3600
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.22021843287801685,
|
| 266 |
+
"grad_norm": 19.424882888793945,
|
| 267 |
+
"learning_rate": 1.8495e-05,
|
| 268 |
+
"loss": 0.1235,
|
| 269 |
+
"step": 3700
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.22617028241526055,
|
| 273 |
+
"grad_norm": 22.792057037353516,
|
| 274 |
+
"learning_rate": 1.8995e-05,
|
| 275 |
+
"loss": 0.154,
|
| 276 |
+
"step": 3800
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.23212213195250425,
|
| 280 |
+
"grad_norm": 7.459188938140869,
|
| 281 |
+
"learning_rate": 1.9495000000000002e-05,
|
| 282 |
+
"loss": 0.1506,
|
| 283 |
+
"step": 3900
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.23807398148974793,
|
| 287 |
+
"grad_norm": 3.574876308441162,
|
| 288 |
+
"learning_rate": 1.9995e-05,
|
| 289 |
+
"loss": 0.1039,
|
| 290 |
+
"step": 4000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.24402583102699163,
|
| 294 |
+
"grad_norm": 14.251306533813477,
|
| 295 |
+
"learning_rate": 1.9975253093363332e-05,
|
| 296 |
+
"loss": 0.1174,
|
| 297 |
+
"step": 4100
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.24997768056423533,
|
| 301 |
+
"grad_norm": 6.622380256652832,
|
| 302 |
+
"learning_rate": 1.9950256217972756e-05,
|
| 303 |
+
"loss": 0.1266,
|
| 304 |
+
"step": 4200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.255929530101479,
|
| 308 |
+
"grad_norm": 56.632022857666016,
|
| 309 |
+
"learning_rate": 1.992525934258218e-05,
|
| 310 |
+
"loss": 0.1186,
|
| 311 |
+
"step": 4300
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.2618813796387227,
|
| 315 |
+
"grad_norm": 29.00509262084961,
|
| 316 |
+
"learning_rate": 1.9900262467191602e-05,
|
| 317 |
+
"loss": 0.1225,
|
| 318 |
+
"step": 4400
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.2678332291759664,
|
| 322 |
+
"grad_norm": 2.0864224433898926,
|
| 323 |
+
"learning_rate": 1.9875265591801026e-05,
|
| 324 |
+
"loss": 0.1123,
|
| 325 |
+
"step": 4500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.2737850787132101,
|
| 329 |
+
"grad_norm": 0.5069118142127991,
|
| 330 |
+
"learning_rate": 1.985026871641045e-05,
|
| 331 |
+
"loss": 0.1047,
|
| 332 |
+
"step": 4600
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.2797369282504538,
|
| 336 |
+
"grad_norm": 9.549971580505371,
|
| 337 |
+
"learning_rate": 1.9825271841019876e-05,
|
| 338 |
+
"loss": 0.104,
|
| 339 |
+
"step": 4700
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.2856887777876975,
|
| 343 |
+
"grad_norm": 9.610527992248535,
|
| 344 |
+
"learning_rate": 1.98002749656293e-05,
|
| 345 |
+
"loss": 0.1267,
|
| 346 |
+
"step": 4800
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.2916406273249412,
|
| 350 |
+
"grad_norm": 1.1918669939041138,
|
| 351 |
+
"learning_rate": 1.977527809023872e-05,
|
| 352 |
+
"loss": 0.1135,
|
| 353 |
+
"step": 4900
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.29759247686218493,
|
| 357 |
+
"grad_norm": 4.561688423156738,
|
| 358 |
+
"learning_rate": 1.9750281214848146e-05,
|
| 359 |
+
"loss": 0.0959,
|
| 360 |
+
"step": 5000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.29759247686218493,
|
| 364 |
+
"eval_accuracy": 0.9856438825798157,
|
| 365 |
+
"eval_f1": 0.9667512130569034,
|
| 366 |
+
"eval_loss": 0.050987500697374344,
|
| 367 |
+
"eval_precision": 0.9792783735478106,
|
| 368 |
+
"eval_recall": 0.9545405052264808,
|
| 369 |
+
"eval_runtime": 716.3292,
|
| 370 |
+
"eval_samples_per_second": 117.273,
|
| 371 |
+
"eval_steps_per_second": 3.666,
|
| 372 |
+
"step": 5000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.30354432639942863,
|
| 376 |
+
"grad_norm": 21.709821701049805,
|
| 377 |
+
"learning_rate": 1.972528433945757e-05,
|
| 378 |
+
"loss": 0.1186,
|
| 379 |
+
"step": 5100
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.30949617593667234,
|
| 383 |
+
"grad_norm": 4.825197219848633,
|
| 384 |
+
"learning_rate": 1.9700287464066993e-05,
|
| 385 |
+
"loss": 0.1197,
|
| 386 |
+
"step": 5200
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.31544802547391604,
|
| 390 |
+
"grad_norm": 0.676392138004303,
|
| 391 |
+
"learning_rate": 1.9675290588676416e-05,
|
| 392 |
+
"loss": 0.1138,
|
| 393 |
+
"step": 5300
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.32139987501115974,
|
| 397 |
+
"grad_norm": 3.394355297088623,
|
| 398 |
+
"learning_rate": 1.9650293713285843e-05,
|
| 399 |
+
"loss": 0.1044,
|
| 400 |
+
"step": 5400
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.3273517245484034,
|
| 404 |
+
"grad_norm": 0.6152952909469604,
|
| 405 |
+
"learning_rate": 1.9625296837895263e-05,
|
| 406 |
+
"loss": 0.0888,
|
| 407 |
+
"step": 5500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.3333035740856471,
|
| 411 |
+
"grad_norm": 3.3491861820220947,
|
| 412 |
+
"learning_rate": 1.9600299962504687e-05,
|
| 413 |
+
"loss": 0.0983,
|
| 414 |
+
"step": 5600
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.3392554236228908,
|
| 418 |
+
"grad_norm": 0.6051576733589172,
|
| 419 |
+
"learning_rate": 1.9575303087114113e-05,
|
| 420 |
+
"loss": 0.1086,
|
| 421 |
+
"step": 5700
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.3452072731601345,
|
| 425 |
+
"grad_norm": 0.05122395604848862,
|
| 426 |
+
"learning_rate": 1.9550306211723537e-05,
|
| 427 |
+
"loss": 0.0887,
|
| 428 |
+
"step": 5800
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.3511591226973782,
|
| 432 |
+
"grad_norm": 1.614094853401184,
|
| 433 |
+
"learning_rate": 1.952530933633296e-05,
|
| 434 |
+
"loss": 0.1085,
|
| 435 |
+
"step": 5900
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.3571109722346219,
|
| 439 |
+
"grad_norm": 0.3445202112197876,
|
| 440 |
+
"learning_rate": 1.9500312460942384e-05,
|
| 441 |
+
"loss": 0.0806,
|
| 442 |
+
"step": 6000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.3630628217718656,
|
| 446 |
+
"grad_norm": 0.30529269576072693,
|
| 447 |
+
"learning_rate": 1.9475315585551807e-05,
|
| 448 |
+
"loss": 0.0717,
|
| 449 |
+
"step": 6100
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.3690146713091093,
|
| 453 |
+
"grad_norm": 6.663509368896484,
|
| 454 |
+
"learning_rate": 1.945031871016123e-05,
|
| 455 |
+
"loss": 0.0943,
|
| 456 |
+
"step": 6200
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.374966520846353,
|
| 460 |
+
"grad_norm": 53.11376953125,
|
| 461 |
+
"learning_rate": 1.9425321834770657e-05,
|
| 462 |
+
"loss": 0.1148,
|
| 463 |
+
"step": 6300
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.3809183703835967,
|
| 467 |
+
"grad_norm": 30.515066146850586,
|
| 468 |
+
"learning_rate": 1.940032495938008e-05,
|
| 469 |
+
"loss": 0.084,
|
| 470 |
+
"step": 6400
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.3868702199208404,
|
| 474 |
+
"grad_norm": 7.43032693862915,
|
| 475 |
+
"learning_rate": 1.93753280839895e-05,
|
| 476 |
+
"loss": 0.0716,
|
| 477 |
+
"step": 6500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.3928220694580841,
|
| 481 |
+
"grad_norm": 0.10134006291627884,
|
| 482 |
+
"learning_rate": 1.9350331208598927e-05,
|
| 483 |
+
"loss": 0.1122,
|
| 484 |
+
"step": 6600
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.3987739189953278,
|
| 488 |
+
"grad_norm": 1.9222484827041626,
|
| 489 |
+
"learning_rate": 1.932533433320835e-05,
|
| 490 |
+
"loss": 0.116,
|
| 491 |
+
"step": 6700
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.4047257685325715,
|
| 495 |
+
"grad_norm": 5.026548385620117,
|
| 496 |
+
"learning_rate": 1.9300337457817774e-05,
|
| 497 |
+
"loss": 0.1087,
|
| 498 |
+
"step": 6800
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.4106776180698152,
|
| 502 |
+
"grad_norm": 5.591833591461182,
|
| 503 |
+
"learning_rate": 1.9275340582427198e-05,
|
| 504 |
+
"loss": 0.1,
|
| 505 |
+
"step": 6900
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.4166294676070589,
|
| 509 |
+
"grad_norm": 4.234807014465332,
|
| 510 |
+
"learning_rate": 1.9250343707036624e-05,
|
| 511 |
+
"loss": 0.08,
|
| 512 |
+
"step": 7000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.4225813171443026,
|
| 516 |
+
"grad_norm": 0.3862815797328949,
|
| 517 |
+
"learning_rate": 1.9225346831646044e-05,
|
| 518 |
+
"loss": 0.1021,
|
| 519 |
+
"step": 7100
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.4285331666815463,
|
| 523 |
+
"grad_norm": 2.0624468326568604,
|
| 524 |
+
"learning_rate": 1.920034995625547e-05,
|
| 525 |
+
"loss": 0.1024,
|
| 526 |
+
"step": 7200
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.43448501621879,
|
| 530 |
+
"grad_norm": 0.02359202690422535,
|
| 531 |
+
"learning_rate": 1.9175353080864895e-05,
|
| 532 |
+
"loss": 0.0734,
|
| 533 |
+
"step": 7300
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.4404368657560337,
|
| 537 |
+
"grad_norm": 3.037367582321167,
|
| 538 |
+
"learning_rate": 1.9150356205474318e-05,
|
| 539 |
+
"loss": 0.0949,
|
| 540 |
+
"step": 7400
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.4463887152932774,
|
| 544 |
+
"grad_norm": 0.7619612812995911,
|
| 545 |
+
"learning_rate": 1.912535933008374e-05,
|
| 546 |
+
"loss": 0.0829,
|
| 547 |
+
"step": 7500
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.4523405648305211,
|
| 551 |
+
"grad_norm": 7.246056079864502,
|
| 552 |
+
"learning_rate": 1.9100362454693165e-05,
|
| 553 |
+
"loss": 0.0865,
|
| 554 |
+
"step": 7600
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.4582924143677648,
|
| 558 |
+
"grad_norm": 0.07375836372375488,
|
| 559 |
+
"learning_rate": 1.9075365579302588e-05,
|
| 560 |
+
"loss": 0.0657,
|
| 561 |
+
"step": 7700
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.4642442639050085,
|
| 565 |
+
"grad_norm": 0.25850656628608704,
|
| 566 |
+
"learning_rate": 1.905036870391201e-05,
|
| 567 |
+
"loss": 0.0958,
|
| 568 |
+
"step": 7800
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.4701961134422522,
|
| 572 |
+
"grad_norm": 6.8354692459106445,
|
| 573 |
+
"learning_rate": 1.902537182852144e-05,
|
| 574 |
+
"loss": 0.1001,
|
| 575 |
+
"step": 7900
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.47614796297949585,
|
| 579 |
+
"grad_norm": 6.075274467468262,
|
| 580 |
+
"learning_rate": 1.900037495313086e-05,
|
| 581 |
+
"loss": 0.0875,
|
| 582 |
+
"step": 8000
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.48209981251673956,
|
| 586 |
+
"grad_norm": 0.09836622327566147,
|
| 587 |
+
"learning_rate": 1.8975378077740282e-05,
|
| 588 |
+
"loss": 0.0638,
|
| 589 |
+
"step": 8100
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.48805166205398326,
|
| 593 |
+
"grad_norm": 4.014862060546875,
|
| 594 |
+
"learning_rate": 1.895038120234971e-05,
|
| 595 |
+
"loss": 0.1102,
|
| 596 |
+
"step": 8200
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.49400351159122696,
|
| 600 |
+
"grad_norm": 1.1304417848587036,
|
| 601 |
+
"learning_rate": 1.8925384326959132e-05,
|
| 602 |
+
"loss": 0.0893,
|
| 603 |
+
"step": 8300
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.49995536112847067,
|
| 607 |
+
"grad_norm": 4.048980712890625,
|
| 608 |
+
"learning_rate": 1.8900387451568555e-05,
|
| 609 |
+
"loss": 0.0771,
|
| 610 |
+
"step": 8400
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.5059072106657144,
|
| 614 |
+
"grad_norm": 0.1943063884973526,
|
| 615 |
+
"learning_rate": 1.887539057617798e-05,
|
| 616 |
+
"loss": 0.0802,
|
| 617 |
+
"step": 8500
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.511859060202958,
|
| 621 |
+
"grad_norm": 3.3784682750701904,
|
| 622 |
+
"learning_rate": 1.8850393700787402e-05,
|
| 623 |
+
"loss": 0.0859,
|
| 624 |
+
"step": 8600
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.5178109097402017,
|
| 628 |
+
"grad_norm": 3.344090700149536,
|
| 629 |
+
"learning_rate": 1.8825396825396826e-05,
|
| 630 |
+
"loss": 0.0816,
|
| 631 |
+
"step": 8700
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.5237627592774454,
|
| 635 |
+
"grad_norm": 0.16063201427459717,
|
| 636 |
+
"learning_rate": 1.8800399950006252e-05,
|
| 637 |
+
"loss": 0.0806,
|
| 638 |
+
"step": 8800
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.5297146088146891,
|
| 642 |
+
"grad_norm": 0.22334939241409302,
|
| 643 |
+
"learning_rate": 1.8775403074615676e-05,
|
| 644 |
+
"loss": 0.0802,
|
| 645 |
+
"step": 8900
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.5356664583519328,
|
| 649 |
+
"grad_norm": 0.22063274681568146,
|
| 650 |
+
"learning_rate": 1.8750406199225096e-05,
|
| 651 |
+
"loss": 0.0934,
|
| 652 |
+
"step": 9000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 0.5416183078891765,
|
| 656 |
+
"grad_norm": 3.237891435623169,
|
| 657 |
+
"learning_rate": 1.8725409323834523e-05,
|
| 658 |
+
"loss": 0.0603,
|
| 659 |
+
"step": 9100
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.5475701574264202,
|
| 663 |
+
"grad_norm": 0.5304477214813232,
|
| 664 |
+
"learning_rate": 1.8700412448443946e-05,
|
| 665 |
+
"loss": 0.0862,
|
| 666 |
+
"step": 9200
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.5535220069636639,
|
| 670 |
+
"grad_norm": 0.03754859045147896,
|
| 671 |
+
"learning_rate": 1.867541557305337e-05,
|
| 672 |
+
"loss": 0.0811,
|
| 673 |
+
"step": 9300
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.5594738565009076,
|
| 677 |
+
"grad_norm": 5.268212795257568,
|
| 678 |
+
"learning_rate": 1.8650418697662793e-05,
|
| 679 |
+
"loss": 0.0613,
|
| 680 |
+
"step": 9400
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.5654257060381513,
|
| 684 |
+
"grad_norm": 0.6994486451148987,
|
| 685 |
+
"learning_rate": 1.862542182227222e-05,
|
| 686 |
+
"loss": 0.0721,
|
| 687 |
+
"step": 9500
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.571377555575395,
|
| 691 |
+
"grad_norm": 7.512162208557129,
|
| 692 |
+
"learning_rate": 1.860042494688164e-05,
|
| 693 |
+
"loss": 0.052,
|
| 694 |
+
"step": 9600
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 0.5773294051126387,
|
| 698 |
+
"grad_norm": 5.643643379211426,
|
| 699 |
+
"learning_rate": 1.8575428071491066e-05,
|
| 700 |
+
"loss": 0.107,
|
| 701 |
+
"step": 9700
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.5832812546498825,
|
| 705 |
+
"grad_norm": 5.92059850692749,
|
| 706 |
+
"learning_rate": 1.855043119610049e-05,
|
| 707 |
+
"loss": 0.0575,
|
| 708 |
+
"step": 9800
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.5892331041871262,
|
| 712 |
+
"grad_norm": 4.476712226867676,
|
| 713 |
+
"learning_rate": 1.8525434320709913e-05,
|
| 714 |
+
"loss": 0.0685,
|
| 715 |
+
"step": 9900
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.5951849537243699,
|
| 719 |
+
"grad_norm": 7.443460941314697,
|
| 720 |
+
"learning_rate": 1.8500437445319337e-05,
|
| 721 |
+
"loss": 0.0972,
|
| 722 |
+
"step": 10000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.5951849537243699,
|
| 726 |
+
"eval_accuracy": 0.9890126895697926,
|
| 727 |
+
"eval_f1": 0.9745751039858965,
|
| 728 |
+
"eval_loss": 0.036706309765577316,
|
| 729 |
+
"eval_precision": 0.9863395595204907,
|
| 730 |
+
"eval_recall": 0.9630879790940766,
|
| 731 |
+
"eval_runtime": 699.1336,
|
| 732 |
+
"eval_samples_per_second": 120.157,
|
| 733 |
+
"eval_steps_per_second": 3.756,
|
| 734 |
+
"step": 10000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.6011368032616136,
|
| 738 |
+
"grad_norm": 1.4378024339675903,
|
| 739 |
+
"learning_rate": 1.847544056992876e-05,
|
| 740 |
+
"loss": 0.0755,
|
| 741 |
+
"step": 10100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.6070886527988573,
|
| 745 |
+
"grad_norm": 3.3750197887420654,
|
| 746 |
+
"learning_rate": 1.8450443694538183e-05,
|
| 747 |
+
"loss": 0.0656,
|
| 748 |
+
"step": 10200
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.613040502336101,
|
| 752 |
+
"grad_norm": 1.403449535369873,
|
| 753 |
+
"learning_rate": 1.8425446819147607e-05,
|
| 754 |
+
"loss": 0.0736,
|
| 755 |
+
"step": 10300
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.6189923518733447,
|
| 759 |
+
"grad_norm": 0.6102975606918335,
|
| 760 |
+
"learning_rate": 1.8400449943757034e-05,
|
| 761 |
+
"loss": 0.0575,
|
| 762 |
+
"step": 10400
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.6249442014105884,
|
| 766 |
+
"grad_norm": 11.931497573852539,
|
| 767 |
+
"learning_rate": 1.8375453068366457e-05,
|
| 768 |
+
"loss": 0.083,
|
| 769 |
+
"step": 10500
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.6308960509478321,
|
| 773 |
+
"grad_norm": 2.4090306758880615,
|
| 774 |
+
"learning_rate": 1.8350456192975877e-05,
|
| 775 |
+
"loss": 0.0939,
|
| 776 |
+
"step": 10600
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.6368479004850758,
|
| 780 |
+
"grad_norm": 9.093697547912598,
|
| 781 |
+
"learning_rate": 1.8325459317585304e-05,
|
| 782 |
+
"loss": 0.0792,
|
| 783 |
+
"step": 10700
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.6427997500223195,
|
| 787 |
+
"grad_norm": 5.047466278076172,
|
| 788 |
+
"learning_rate": 1.8300462442194727e-05,
|
| 789 |
+
"loss": 0.0644,
|
| 790 |
+
"step": 10800
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.6487515995595632,
|
| 794 |
+
"grad_norm": 0.031459350138902664,
|
| 795 |
+
"learning_rate": 1.827546556680415e-05,
|
| 796 |
+
"loss": 0.0853,
|
| 797 |
+
"step": 10900
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.6547034490968068,
|
| 801 |
+
"grad_norm": 4.757169723510742,
|
| 802 |
+
"learning_rate": 1.8250468691413574e-05,
|
| 803 |
+
"loss": 0.0831,
|
| 804 |
+
"step": 11000
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.6606552986340505,
|
| 808 |
+
"grad_norm": 5.49468994140625,
|
| 809 |
+
"learning_rate": 1.8225471816023e-05,
|
| 810 |
+
"loss": 0.0744,
|
| 811 |
+
"step": 11100
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.6666071481712942,
|
| 815 |
+
"grad_norm": 0.1340179443359375,
|
| 816 |
+
"learning_rate": 1.820047494063242e-05,
|
| 817 |
+
"loss": 0.0685,
|
| 818 |
+
"step": 11200
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.6725589977085379,
|
| 822 |
+
"grad_norm": 5.28952693939209,
|
| 823 |
+
"learning_rate": 1.8175478065241848e-05,
|
| 824 |
+
"loss": 0.0676,
|
| 825 |
+
"step": 11300
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.6785108472457816,
|
| 829 |
+
"grad_norm": 0.032111797481775284,
|
| 830 |
+
"learning_rate": 1.815048118985127e-05,
|
| 831 |
+
"loss": 0.0751,
|
| 832 |
+
"step": 11400
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.6844626967830253,
|
| 836 |
+
"grad_norm": 0.06453489512205124,
|
| 837 |
+
"learning_rate": 1.8125484314460694e-05,
|
| 838 |
+
"loss": 0.0696,
|
| 839 |
+
"step": 11500
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.690414546320269,
|
| 843 |
+
"grad_norm": 1.1088204383850098,
|
| 844 |
+
"learning_rate": 1.8100487439070118e-05,
|
| 845 |
+
"loss": 0.0569,
|
| 846 |
+
"step": 11600
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.6963663958575127,
|
| 850 |
+
"grad_norm": 3.420901298522949,
|
| 851 |
+
"learning_rate": 1.807549056367954e-05,
|
| 852 |
+
"loss": 0.0831,
|
| 853 |
+
"step": 11700
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.7023182453947564,
|
| 857 |
+
"grad_norm": 0.044298429042100906,
|
| 858 |
+
"learning_rate": 1.8050493688288965e-05,
|
| 859 |
+
"loss": 0.0811,
|
| 860 |
+
"step": 11800
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.7082700949320001,
|
| 864 |
+
"grad_norm": 0.17848756909370422,
|
| 865 |
+
"learning_rate": 1.8025496812898388e-05,
|
| 866 |
+
"loss": 0.064,
|
| 867 |
+
"step": 11900
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.7142219444692438,
|
| 871 |
+
"grad_norm": 1.6905055046081543,
|
| 872 |
+
"learning_rate": 1.8000499937507815e-05,
|
| 873 |
+
"loss": 0.1141,
|
| 874 |
+
"step": 12000
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.7201737940064875,
|
| 878 |
+
"grad_norm": 0.1147763580083847,
|
| 879 |
+
"learning_rate": 1.7975503062117238e-05,
|
| 880 |
+
"loss": 0.0787,
|
| 881 |
+
"step": 12100
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.7261256435437312,
|
| 885 |
+
"grad_norm": 5.295955181121826,
|
| 886 |
+
"learning_rate": 1.795050618672666e-05,
|
| 887 |
+
"loss": 0.0777,
|
| 888 |
+
"step": 12200
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 0.7320774930809749,
|
| 892 |
+
"grad_norm": 1.885426640510559,
|
| 893 |
+
"learning_rate": 1.7925509311336085e-05,
|
| 894 |
+
"loss": 0.0556,
|
| 895 |
+
"step": 12300
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 0.7380293426182186,
|
| 899 |
+
"grad_norm": 0.2982531785964966,
|
| 900 |
+
"learning_rate": 1.790051243594551e-05,
|
| 901 |
+
"loss": 0.0704,
|
| 902 |
+
"step": 12400
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.7439811921554623,
|
| 906 |
+
"grad_norm": 10.546908378601074,
|
| 907 |
+
"learning_rate": 1.7875515560554932e-05,
|
| 908 |
+
"loss": 0.0505,
|
| 909 |
+
"step": 12500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.749933041692706,
|
| 913 |
+
"grad_norm": 0.013311674818396568,
|
| 914 |
+
"learning_rate": 1.7850518685164355e-05,
|
| 915 |
+
"loss": 0.0622,
|
| 916 |
+
"step": 12600
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.7558848912299497,
|
| 920 |
+
"grad_norm": 20.8616886138916,
|
| 921 |
+
"learning_rate": 1.782552180977378e-05,
|
| 922 |
+
"loss": 0.0588,
|
| 923 |
+
"step": 12700
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.7618367407671934,
|
| 927 |
+
"grad_norm": 0.5590173006057739,
|
| 928 |
+
"learning_rate": 1.7800524934383202e-05,
|
| 929 |
+
"loss": 0.0748,
|
| 930 |
+
"step": 12800
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.7677885903044371,
|
| 934 |
+
"grad_norm": 0.053356532007455826,
|
| 935 |
+
"learning_rate": 1.777552805899263e-05,
|
| 936 |
+
"loss": 0.0866,
|
| 937 |
+
"step": 12900
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.7737404398416808,
|
| 941 |
+
"grad_norm": 8.997873306274414,
|
| 942 |
+
"learning_rate": 1.7750531183602052e-05,
|
| 943 |
+
"loss": 0.0614,
|
| 944 |
+
"step": 13000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.7796922893789245,
|
| 948 |
+
"grad_norm": 0.15272608399391174,
|
| 949 |
+
"learning_rate": 1.7725534308211472e-05,
|
| 950 |
+
"loss": 0.0579,
|
| 951 |
+
"step": 13100
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.7856441389161682,
|
| 955 |
+
"grad_norm": 9.847796440124512,
|
| 956 |
+
"learning_rate": 1.77005374328209e-05,
|
| 957 |
+
"loss": 0.0717,
|
| 958 |
+
"step": 13200
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 0.791595988453412,
|
| 962 |
+
"grad_norm": 0.4942564070224762,
|
| 963 |
+
"learning_rate": 1.7675540557430322e-05,
|
| 964 |
+
"loss": 0.0713,
|
| 965 |
+
"step": 13300
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 0.7975478379906557,
|
| 969 |
+
"grad_norm": 12.623053550720215,
|
| 970 |
+
"learning_rate": 1.7650543682039746e-05,
|
| 971 |
+
"loss": 0.0601,
|
| 972 |
+
"step": 13400
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 0.8034996875278992,
|
| 976 |
+
"grad_norm": 0.47039860486984253,
|
| 977 |
+
"learning_rate": 1.762554680664917e-05,
|
| 978 |
+
"loss": 0.0706,
|
| 979 |
+
"step": 13500
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 0.809451537065143,
|
| 983 |
+
"grad_norm": 0.06241678074002266,
|
| 984 |
+
"learning_rate": 1.7600549931258596e-05,
|
| 985 |
+
"loss": 0.0739,
|
| 986 |
+
"step": 13600
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.8154033866023866,
|
| 990 |
+
"grad_norm": 0.5157163739204407,
|
| 991 |
+
"learning_rate": 1.7575553055868016e-05,
|
| 992 |
+
"loss": 0.0711,
|
| 993 |
+
"step": 13700
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.8213552361396304,
|
| 997 |
+
"grad_norm": 0.684218168258667,
|
| 998 |
+
"learning_rate": 1.7550556180477443e-05,
|
| 999 |
+
"loss": 0.0704,
|
| 1000 |
+
"step": 13800
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 0.827307085676874,
|
| 1004 |
+
"grad_norm": 5.712099075317383,
|
| 1005 |
+
"learning_rate": 1.7525559305086866e-05,
|
| 1006 |
+
"loss": 0.069,
|
| 1007 |
+
"step": 13900
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.8332589352141178,
|
| 1011 |
+
"grad_norm": 10.816957473754883,
|
| 1012 |
+
"learning_rate": 1.750056242969629e-05,
|
| 1013 |
+
"loss": 0.0641,
|
| 1014 |
+
"step": 14000
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.8392107847513615,
|
| 1018 |
+
"grad_norm": 5.686164855957031,
|
| 1019 |
+
"learning_rate": 1.7475565554305713e-05,
|
| 1020 |
+
"loss": 0.068,
|
| 1021 |
+
"step": 14100
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.8451626342886052,
|
| 1025 |
+
"grad_norm": 0.052303824573755264,
|
| 1026 |
+
"learning_rate": 1.7450568678915136e-05,
|
| 1027 |
+
"loss": 0.0861,
|
| 1028 |
+
"step": 14200
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.8511144838258489,
|
| 1032 |
+
"grad_norm": 2.4506478309631348,
|
| 1033 |
+
"learning_rate": 1.742557180352456e-05,
|
| 1034 |
+
"loss": 0.0586,
|
| 1035 |
+
"step": 14300
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.8570663333630926,
|
| 1039 |
+
"grad_norm": 4.940361499786377,
|
| 1040 |
+
"learning_rate": 1.7400574928133983e-05,
|
| 1041 |
+
"loss": 0.058,
|
| 1042 |
+
"step": 14400
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.8630181829003363,
|
| 1046 |
+
"grad_norm": 0.027969790622591972,
|
| 1047 |
+
"learning_rate": 1.737557805274341e-05,
|
| 1048 |
+
"loss": 0.0603,
|
| 1049 |
+
"step": 14500
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.86897003243758,
|
| 1053 |
+
"grad_norm": 7.126792907714844,
|
| 1054 |
+
"learning_rate": 1.7350581177352833e-05,
|
| 1055 |
+
"loss": 0.0718,
|
| 1056 |
+
"step": 14600
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 0.8749218819748237,
|
| 1060 |
+
"grad_norm": 1.7231388092041016,
|
| 1061 |
+
"learning_rate": 1.7325584301962257e-05,
|
| 1062 |
+
"loss": 0.0553,
|
| 1063 |
+
"step": 14700
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 0.8808737315120674,
|
| 1067 |
+
"grad_norm": 2.9911932945251465,
|
| 1068 |
+
"learning_rate": 1.730058742657168e-05,
|
| 1069 |
+
"loss": 0.0671,
|
| 1070 |
+
"step": 14800
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 0.8868255810493111,
|
| 1074 |
+
"grad_norm": 0.11182364076375961,
|
| 1075 |
+
"learning_rate": 1.7275590551181104e-05,
|
| 1076 |
+
"loss": 0.0722,
|
| 1077 |
+
"step": 14900
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.8927774305865548,
|
| 1081 |
+
"grad_norm": 1.7560580968856812,
|
| 1082 |
+
"learning_rate": 1.7250593675790527e-05,
|
| 1083 |
+
"loss": 0.0773,
|
| 1084 |
+
"step": 15000
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.8927774305865548,
|
| 1088 |
+
"eval_accuracy": 0.9907744684903459,
|
| 1089 |
+
"eval_f1": 0.9786730509920472,
|
| 1090 |
+
"eval_loss": 0.030510300770401955,
|
| 1091 |
+
"eval_precision": 0.9894830560347226,
|
| 1092 |
+
"eval_recall": 0.9680966898954704,
|
| 1093 |
+
"eval_runtime": 637.3433,
|
| 1094 |
+
"eval_samples_per_second": 131.807,
|
| 1095 |
+
"eval_steps_per_second": 4.12,
|
| 1096 |
+
"step": 15000
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.8987292801237985,
|
| 1100 |
+
"grad_norm": 24.16592025756836,
|
| 1101 |
+
"learning_rate": 1.722559680039995e-05,
|
| 1102 |
+
"loss": 0.0547,
|
| 1103 |
+
"step": 15100
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 0.9046811296610422,
|
| 1107 |
+
"grad_norm": 0.27272409200668335,
|
| 1108 |
+
"learning_rate": 1.7200599925009377e-05,
|
| 1109 |
+
"loss": 0.0766,
|
| 1110 |
+
"step": 15200
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 0.9106329791982859,
|
| 1114 |
+
"grad_norm": 0.11689332127571106,
|
| 1115 |
+
"learning_rate": 1.7175603049618797e-05,
|
| 1116 |
+
"loss": 0.0585,
|
| 1117 |
+
"step": 15300
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 0.9165848287355296,
|
| 1121 |
+
"grad_norm": 0.033309925347566605,
|
| 1122 |
+
"learning_rate": 1.7150606174228224e-05,
|
| 1123 |
+
"loss": 0.0508,
|
| 1124 |
+
"step": 15400
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 0.9225366782727733,
|
| 1128 |
+
"grad_norm": 0.1792755424976349,
|
| 1129 |
+
"learning_rate": 1.7125609298837647e-05,
|
| 1130 |
+
"loss": 0.0676,
|
| 1131 |
+
"step": 15500
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.928488527810017,
|
| 1135 |
+
"grad_norm": 0.009599496610462666,
|
| 1136 |
+
"learning_rate": 1.710061242344707e-05,
|
| 1137 |
+
"loss": 0.0582,
|
| 1138 |
+
"step": 15600
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.9344403773472607,
|
| 1142 |
+
"grad_norm": 5.908741474151611,
|
| 1143 |
+
"learning_rate": 1.7075615548056494e-05,
|
| 1144 |
+
"loss": 0.0531,
|
| 1145 |
+
"step": 15700
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 0.9403922268845044,
|
| 1149 |
+
"grad_norm": 0.12097036838531494,
|
| 1150 |
+
"learning_rate": 1.7050618672665918e-05,
|
| 1151 |
+
"loss": 0.0701,
|
| 1152 |
+
"step": 15800
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 0.946344076421748,
|
| 1156 |
+
"grad_norm": 0.04996073991060257,
|
| 1157 |
+
"learning_rate": 1.702562179727534e-05,
|
| 1158 |
+
"loss": 0.0797,
|
| 1159 |
+
"step": 15900
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 0.9522959259589917,
|
| 1163 |
+
"grad_norm": 3.689929485321045,
|
| 1164 |
+
"learning_rate": 1.7000624921884764e-05,
|
| 1165 |
+
"loss": 0.0783,
|
| 1166 |
+
"step": 16000
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 0.9582477754962354,
|
| 1170 |
+
"grad_norm": 3.7698171138763428,
|
| 1171 |
+
"learning_rate": 1.697562804649419e-05,
|
| 1172 |
+
"loss": 0.0608,
|
| 1173 |
+
"step": 16100
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.9641996250334791,
|
| 1177 |
+
"grad_norm": 0.3943725824356079,
|
| 1178 |
+
"learning_rate": 1.6950631171103615e-05,
|
| 1179 |
+
"loss": 0.068,
|
| 1180 |
+
"step": 16200
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.9701514745707228,
|
| 1184 |
+
"grad_norm": 0.24215468764305115,
|
| 1185 |
+
"learning_rate": 1.6925634295713038e-05,
|
| 1186 |
+
"loss": 0.0588,
|
| 1187 |
+
"step": 16300
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.9761033241079665,
|
| 1191 |
+
"grad_norm": 1.7841726541519165,
|
| 1192 |
+
"learning_rate": 1.690063742032246e-05,
|
| 1193 |
+
"loss": 0.0621,
|
| 1194 |
+
"step": 16400
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.9820551736452102,
|
| 1198 |
+
"grad_norm": 0.02200796641409397,
|
| 1199 |
+
"learning_rate": 1.6875640544931885e-05,
|
| 1200 |
+
"loss": 0.0658,
|
| 1201 |
+
"step": 16500
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.9880070231824539,
|
| 1205 |
+
"grad_norm": 5.905091762542725,
|
| 1206 |
+
"learning_rate": 1.6850643669541308e-05,
|
| 1207 |
+
"loss": 0.0477,
|
| 1208 |
+
"step": 16600
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.9939588727196976,
|
| 1212 |
+
"grad_norm": 6.53129243850708,
|
| 1213 |
+
"learning_rate": 1.682564679415073e-05,
|
| 1214 |
+
"loss": 0.0612,
|
| 1215 |
+
"step": 16700
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.9999107222569413,
|
| 1219 |
+
"grad_norm": 8.548293113708496,
|
| 1220 |
+
"learning_rate": 1.680064991876016e-05,
|
| 1221 |
+
"loss": 0.0594,
|
| 1222 |
+
"step": 16800
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 1.0058328125464988,
|
| 1226 |
+
"grad_norm": 0.3448663353919983,
|
| 1227 |
+
"learning_rate": 1.677565304336958e-05,
|
| 1228 |
+
"loss": 0.0327,
|
| 1229 |
+
"step": 16900
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 1.0117846620837425,
|
| 1233 |
+
"grad_norm": 0.6257154941558838,
|
| 1234 |
+
"learning_rate": 1.6750656167979005e-05,
|
| 1235 |
+
"loss": 0.0306,
|
| 1236 |
+
"step": 17000
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 1.0177365116209862,
|
| 1240 |
+
"grad_norm": 4.9479193687438965,
|
| 1241 |
+
"learning_rate": 1.672565929258843e-05,
|
| 1242 |
+
"loss": 0.0346,
|
| 1243 |
+
"step": 17100
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 1.02368836115823,
|
| 1247 |
+
"grad_norm": 0.009480413980782032,
|
| 1248 |
+
"learning_rate": 1.6700662417197852e-05,
|
| 1249 |
+
"loss": 0.0268,
|
| 1250 |
+
"step": 17200
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.0296402106954736,
|
| 1254 |
+
"grad_norm": 0.9463269114494324,
|
| 1255 |
+
"learning_rate": 1.6675665541807275e-05,
|
| 1256 |
+
"loss": 0.0586,
|
| 1257 |
+
"step": 17300
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.0355920602327173,
|
| 1261 |
+
"grad_norm": 0.07529614865779877,
|
| 1262 |
+
"learning_rate": 1.66506686664167e-05,
|
| 1263 |
+
"loss": 0.0294,
|
| 1264 |
+
"step": 17400
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 1.041543909769961,
|
| 1268 |
+
"grad_norm": 0.006725461222231388,
|
| 1269 |
+
"learning_rate": 1.6625671791026122e-05,
|
| 1270 |
+
"loss": 0.0387,
|
| 1271 |
+
"step": 17500
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 1.0474957593072047,
|
| 1275 |
+
"grad_norm": 0.6210471987724304,
|
| 1276 |
+
"learning_rate": 1.6600674915635546e-05,
|
| 1277 |
+
"loss": 0.0422,
|
| 1278 |
+
"step": 17600
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 1.0534476088444484,
|
| 1282 |
+
"grad_norm": 0.21577982604503632,
|
| 1283 |
+
"learning_rate": 1.6575678040244972e-05,
|
| 1284 |
+
"loss": 0.0241,
|
| 1285 |
+
"step": 17700
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 1.0593994583816921,
|
| 1289 |
+
"grad_norm": 13.052763938903809,
|
| 1290 |
+
"learning_rate": 1.6550681164854392e-05,
|
| 1291 |
+
"loss": 0.0321,
|
| 1292 |
+
"step": 17800
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 1.0653513079189358,
|
| 1296 |
+
"grad_norm": 0.019462615251541138,
|
| 1297 |
+
"learning_rate": 1.652568428946382e-05,
|
| 1298 |
+
"loss": 0.0374,
|
| 1299 |
+
"step": 17900
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.0713031574561795,
|
| 1303 |
+
"grad_norm": 0.008586418814957142,
|
| 1304 |
+
"learning_rate": 1.6500687414073243e-05,
|
| 1305 |
+
"loss": 0.0441,
|
| 1306 |
+
"step": 18000
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.0772550069934232,
|
| 1310 |
+
"grad_norm": 0.0021827963646501303,
|
| 1311 |
+
"learning_rate": 1.6475690538682666e-05,
|
| 1312 |
+
"loss": 0.0219,
|
| 1313 |
+
"step": 18100
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.083206856530667,
|
| 1317 |
+
"grad_norm": 0.019988901913166046,
|
| 1318 |
+
"learning_rate": 1.645069366329209e-05,
|
| 1319 |
+
"loss": 0.0363,
|
| 1320 |
+
"step": 18200
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.0891587060679107,
|
| 1324 |
+
"grad_norm": 0.3322964012622833,
|
| 1325 |
+
"learning_rate": 1.6425696787901513e-05,
|
| 1326 |
+
"loss": 0.041,
|
| 1327 |
+
"step": 18300
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.0951105556051544,
|
| 1331 |
+
"grad_norm": 3.1195592880249023,
|
| 1332 |
+
"learning_rate": 1.6400699912510936e-05,
|
| 1333 |
+
"loss": 0.0349,
|
| 1334 |
+
"step": 18400
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.101062405142398,
|
| 1338 |
+
"grad_norm": 0.020526066422462463,
|
| 1339 |
+
"learning_rate": 1.637570303712036e-05,
|
| 1340 |
+
"loss": 0.0583,
|
| 1341 |
+
"step": 18500
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 1.1070142546796418,
|
| 1345 |
+
"grad_norm": 0.026518339291214943,
|
| 1346 |
+
"learning_rate": 1.6350706161729786e-05,
|
| 1347 |
+
"loss": 0.0328,
|
| 1348 |
+
"step": 18600
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 1.1129661042168855,
|
| 1352 |
+
"grad_norm": 0.02615894377231598,
|
| 1353 |
+
"learning_rate": 1.632570928633921e-05,
|
| 1354 |
+
"loss": 0.0233,
|
| 1355 |
+
"step": 18700
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 1.1189179537541292,
|
| 1359 |
+
"grad_norm": 0.036855828016996384,
|
| 1360 |
+
"learning_rate": 1.6300712410948633e-05,
|
| 1361 |
+
"loss": 0.025,
|
| 1362 |
+
"step": 18800
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 1.1248698032913729,
|
| 1366 |
+
"grad_norm": 0.07263686507940292,
|
| 1367 |
+
"learning_rate": 1.6275715535558057e-05,
|
| 1368 |
+
"loss": 0.0318,
|
| 1369 |
+
"step": 18900
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 1.1308216528286166,
|
| 1373 |
+
"grad_norm": 0.12782253324985504,
|
| 1374 |
+
"learning_rate": 1.625071866016748e-05,
|
| 1375 |
+
"loss": 0.0588,
|
| 1376 |
+
"step": 19000
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 1.1367735023658603,
|
| 1380 |
+
"grad_norm": 0.012232950888574123,
|
| 1381 |
+
"learning_rate": 1.6225721784776903e-05,
|
| 1382 |
+
"loss": 0.0283,
|
| 1383 |
+
"step": 19100
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 1.142725351903104,
|
| 1387 |
+
"grad_norm": 0.22422778606414795,
|
| 1388 |
+
"learning_rate": 1.6200724909386327e-05,
|
| 1389 |
+
"loss": 0.0454,
|
| 1390 |
+
"step": 19200
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 1.1486772014403477,
|
| 1394 |
+
"grad_norm": 0.37581029534339905,
|
| 1395 |
+
"learning_rate": 1.6175728033995754e-05,
|
| 1396 |
+
"loss": 0.0475,
|
| 1397 |
+
"step": 19300
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 1.1546290509775914,
|
| 1401 |
+
"grad_norm": 0.06439394503831863,
|
| 1402 |
+
"learning_rate": 1.6150731158605174e-05,
|
| 1403 |
+
"loss": 0.0484,
|
| 1404 |
+
"step": 19400
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 1.160580900514835,
|
| 1408 |
+
"grad_norm": 0.09931550920009613,
|
| 1409 |
+
"learning_rate": 1.61257342832146e-05,
|
| 1410 |
+
"loss": 0.0386,
|
| 1411 |
+
"step": 19500
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 1.1665327500520788,
|
| 1415 |
+
"grad_norm": 4.9056291580200195,
|
| 1416 |
+
"learning_rate": 1.6100737407824024e-05,
|
| 1417 |
+
"loss": 0.0499,
|
| 1418 |
+
"step": 19600
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.1724845995893225,
|
| 1422 |
+
"grad_norm": 0.15619812905788422,
|
| 1423 |
+
"learning_rate": 1.6075740532433447e-05,
|
| 1424 |
+
"loss": 0.0324,
|
| 1425 |
+
"step": 19700
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 1.1784364491265662,
|
| 1429 |
+
"grad_norm": 0.42920124530792236,
|
| 1430 |
+
"learning_rate": 1.605074365704287e-05,
|
| 1431 |
+
"loss": 0.0321,
|
| 1432 |
+
"step": 19800
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 1.18438829866381,
|
| 1436 |
+
"grad_norm": 0.014962832443416119,
|
| 1437 |
+
"learning_rate": 1.6025746781652294e-05,
|
| 1438 |
+
"loss": 0.0256,
|
| 1439 |
+
"step": 19900
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.1903401482010534,
|
| 1443 |
+
"grad_norm": 1.7344650030136108,
|
| 1444 |
+
"learning_rate": 1.6000749906261717e-05,
|
| 1445 |
+
"loss": 0.0416,
|
| 1446 |
+
"step": 20000
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 1.1903401482010534,
|
| 1450 |
+
"eval_accuracy": 0.9913934718948646,
|
| 1451 |
+
"eval_f1": 0.9800788030749731,
|
| 1452 |
+
"eval_loss": 0.03799758478999138,
|
| 1453 |
+
"eval_precision": 0.992189679218968,
|
| 1454 |
+
"eval_recall": 0.9682600174216028,
|
| 1455 |
+
"eval_runtime": 634.1459,
|
| 1456 |
+
"eval_samples_per_second": 132.471,
|
| 1457 |
+
"eval_steps_per_second": 4.141,
|
| 1458 |
+
"step": 20000
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.196291997738297,
|
| 1462 |
+
"grad_norm": 0.008463047444820404,
|
| 1463 |
+
"learning_rate": 1.597575303087114e-05,
|
| 1464 |
+
"loss": 0.0374,
|
| 1465 |
+
"step": 20100
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.2022438472755408,
|
| 1469 |
+
"grad_norm": 0.055202700197696686,
|
| 1470 |
+
"learning_rate": 1.5950756155480568e-05,
|
| 1471 |
+
"loss": 0.0376,
|
| 1472 |
+
"step": 20200
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.2081956968127845,
|
| 1476 |
+
"grad_norm": 0.8383081555366516,
|
| 1477 |
+
"learning_rate": 1.592575928008999e-05,
|
| 1478 |
+
"loss": 0.0391,
|
| 1479 |
+
"step": 20300
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.2141475463500282,
|
| 1483 |
+
"grad_norm": 4.7434868812561035,
|
| 1484 |
+
"learning_rate": 1.5900762404699414e-05,
|
| 1485 |
+
"loss": 0.0561,
|
| 1486 |
+
"step": 20400
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 1.220099395887272,
|
| 1490 |
+
"grad_norm": 0.18934893608093262,
|
| 1491 |
+
"learning_rate": 1.5875765529308838e-05,
|
| 1492 |
+
"loss": 0.0323,
|
| 1493 |
+
"step": 20500
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.2260512454245156,
|
| 1497 |
+
"grad_norm": 0.02613821066915989,
|
| 1498 |
+
"learning_rate": 1.585076865391826e-05,
|
| 1499 |
+
"loss": 0.0425,
|
| 1500 |
+
"step": 20600
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 1.2320030949617593,
|
| 1504 |
+
"grad_norm": 0.04844895005226135,
|
| 1505 |
+
"learning_rate": 1.5825771778527685e-05,
|
| 1506 |
+
"loss": 0.0315,
|
| 1507 |
+
"step": 20700
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.237954944499003,
|
| 1511 |
+
"grad_norm": 0.2447776347398758,
|
| 1512 |
+
"learning_rate": 1.5800774903137108e-05,
|
| 1513 |
+
"loss": 0.0205,
|
| 1514 |
+
"step": 20800
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.2439067940362467,
|
| 1518 |
+
"grad_norm": 6.23702335357666,
|
| 1519 |
+
"learning_rate": 1.5775778027746535e-05,
|
| 1520 |
+
"loss": 0.046,
|
| 1521 |
+
"step": 20900
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.2498586435734904,
|
| 1525 |
+
"grad_norm": 9.4482421875,
|
| 1526 |
+
"learning_rate": 1.5750781152355955e-05,
|
| 1527 |
+
"loss": 0.0252,
|
| 1528 |
+
"step": 21000
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.2558104931107341,
|
| 1532 |
+
"grad_norm": 5.085052013397217,
|
| 1533 |
+
"learning_rate": 1.572578427696538e-05,
|
| 1534 |
+
"loss": 0.0391,
|
| 1535 |
+
"step": 21100
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.2617623426479778,
|
| 1539 |
+
"grad_norm": 6.614001274108887,
|
| 1540 |
+
"learning_rate": 1.5700787401574805e-05,
|
| 1541 |
+
"loss": 0.0312,
|
| 1542 |
+
"step": 21200
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.2677141921852215,
|
| 1546 |
+
"grad_norm": 0.14532746374607086,
|
| 1547 |
+
"learning_rate": 1.567579052618423e-05,
|
| 1548 |
+
"loss": 0.0416,
|
| 1549 |
+
"step": 21300
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.2736660417224652,
|
| 1553 |
+
"grad_norm": 0.16996897757053375,
|
| 1554 |
+
"learning_rate": 1.5650793650793652e-05,
|
| 1555 |
+
"loss": 0.0409,
|
| 1556 |
+
"step": 21400
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.279617891259709,
|
| 1560 |
+
"grad_norm": 21.97540283203125,
|
| 1561 |
+
"learning_rate": 1.5625796775403075e-05,
|
| 1562 |
+
"loss": 0.0279,
|
| 1563 |
+
"step": 21500
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.2855697407969526,
|
| 1567 |
+
"grad_norm": 0.021660545840859413,
|
| 1568 |
+
"learning_rate": 1.56007999000125e-05,
|
| 1569 |
+
"loss": 0.0387,
|
| 1570 |
+
"step": 21600
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.2915215903341963,
|
| 1574 |
+
"grad_norm": 4.85373592376709,
|
| 1575 |
+
"learning_rate": 1.5575803024621922e-05,
|
| 1576 |
+
"loss": 0.0438,
|
| 1577 |
+
"step": 21700
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.29747343987144,
|
| 1581 |
+
"grad_norm": 0.12195076793432236,
|
| 1582 |
+
"learning_rate": 1.555080614923135e-05,
|
| 1583 |
+
"loss": 0.0397,
|
| 1584 |
+
"step": 21800
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.3034252894086837,
|
| 1588 |
+
"grad_norm": 0.004497983027249575,
|
| 1589 |
+
"learning_rate": 1.5525809273840772e-05,
|
| 1590 |
+
"loss": 0.0357,
|
| 1591 |
+
"step": 21900
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.3093771389459274,
|
| 1595 |
+
"grad_norm": 0.6372514367103577,
|
| 1596 |
+
"learning_rate": 1.5500812398450196e-05,
|
| 1597 |
+
"loss": 0.0341,
|
| 1598 |
+
"step": 22000
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 1.3153289884831711,
|
| 1602 |
+
"grad_norm": 0.04463673010468483,
|
| 1603 |
+
"learning_rate": 1.547581552305962e-05,
|
| 1604 |
+
"loss": 0.0339,
|
| 1605 |
+
"step": 22100
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.3212808380204148,
|
| 1609 |
+
"grad_norm": 0.5814944505691528,
|
| 1610 |
+
"learning_rate": 1.5450818647669042e-05,
|
| 1611 |
+
"loss": 0.0417,
|
| 1612 |
+
"step": 22200
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 1.3272326875576586,
|
| 1616 |
+
"grad_norm": 16.33363151550293,
|
| 1617 |
+
"learning_rate": 1.5425821772278466e-05,
|
| 1618 |
+
"loss": 0.0514,
|
| 1619 |
+
"step": 22300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.3331845370949023,
|
| 1623 |
+
"grad_norm": 6.866737365722656,
|
| 1624 |
+
"learning_rate": 1.540082489688789e-05,
|
| 1625 |
+
"loss": 0.0261,
|
| 1626 |
+
"step": 22400
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.339136386632146,
|
| 1630 |
+
"grad_norm": 0.016487309709191322,
|
| 1631 |
+
"learning_rate": 1.5375828021497313e-05,
|
| 1632 |
+
"loss": 0.032,
|
| 1633 |
+
"step": 22500
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.3450882361693897,
|
| 1637 |
+
"grad_norm": 0.08337634056806564,
|
| 1638 |
+
"learning_rate": 1.5350831146106736e-05,
|
| 1639 |
+
"loss": 0.0493,
|
| 1640 |
+
"step": 22600
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.3510400857066334,
|
| 1644 |
+
"grad_norm": 0.01637539267539978,
|
| 1645 |
+
"learning_rate": 1.5325834270716163e-05,
|
| 1646 |
+
"loss": 0.0405,
|
| 1647 |
+
"step": 22700
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.356991935243877,
|
| 1651 |
+
"grad_norm": 0.48449915647506714,
|
| 1652 |
+
"learning_rate": 1.5300837395325586e-05,
|
| 1653 |
+
"loss": 0.0408,
|
| 1654 |
+
"step": 22800
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.3629437847811208,
|
| 1658 |
+
"grad_norm": 0.05106478929519653,
|
| 1659 |
+
"learning_rate": 1.527584051993501e-05,
|
| 1660 |
+
"loss": 0.0393,
|
| 1661 |
+
"step": 22900
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.3688956343183645,
|
| 1665 |
+
"grad_norm": 0.01775064878165722,
|
| 1666 |
+
"learning_rate": 1.5250843644544433e-05,
|
| 1667 |
+
"loss": 0.0507,
|
| 1668 |
+
"step": 23000
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.3748474838556082,
|
| 1672 |
+
"grad_norm": 0.027698859572410583,
|
| 1673 |
+
"learning_rate": 1.5225846769153858e-05,
|
| 1674 |
+
"loss": 0.0227,
|
| 1675 |
+
"step": 23100
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.3807993333928519,
|
| 1679 |
+
"grad_norm": 0.004283764399588108,
|
| 1680 |
+
"learning_rate": 1.5200849893763282e-05,
|
| 1681 |
+
"loss": 0.0381,
|
| 1682 |
+
"step": 23200
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.3867511829300956,
|
| 1686 |
+
"grad_norm": 0.008574152365326881,
|
| 1687 |
+
"learning_rate": 1.5175853018372703e-05,
|
| 1688 |
+
"loss": 0.0505,
|
| 1689 |
+
"step": 23300
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.3927030324673393,
|
| 1693 |
+
"grad_norm": 0.3766544759273529,
|
| 1694 |
+
"learning_rate": 1.5150856142982128e-05,
|
| 1695 |
+
"loss": 0.0245,
|
| 1696 |
+
"step": 23400
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.398654882004583,
|
| 1700 |
+
"grad_norm": 0.003701981622725725,
|
| 1701 |
+
"learning_rate": 1.5125859267591552e-05,
|
| 1702 |
+
"loss": 0.0315,
|
| 1703 |
+
"step": 23500
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.4046067315418267,
|
| 1707 |
+
"grad_norm": 0.049905925989151,
|
| 1708 |
+
"learning_rate": 1.5100862392200977e-05,
|
| 1709 |
+
"loss": 0.0494,
|
| 1710 |
+
"step": 23600
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.4105585810790704,
|
| 1714 |
+
"grad_norm": 0.01804766058921814,
|
| 1715 |
+
"learning_rate": 1.50758655168104e-05,
|
| 1716 |
+
"loss": 0.0425,
|
| 1717 |
+
"step": 23700
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.416510430616314,
|
| 1721 |
+
"grad_norm": 7.34988260269165,
|
| 1722 |
+
"learning_rate": 1.5050868641419825e-05,
|
| 1723 |
+
"loss": 0.0519,
|
| 1724 |
+
"step": 23800
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.4224622801535578,
|
| 1728 |
+
"grad_norm": 27.711393356323242,
|
| 1729 |
+
"learning_rate": 1.5025871766029247e-05,
|
| 1730 |
+
"loss": 0.0351,
|
| 1731 |
+
"step": 23900
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.4284141296908013,
|
| 1735 |
+
"grad_norm": 6.535654544830322,
|
| 1736 |
+
"learning_rate": 1.500087489063867e-05,
|
| 1737 |
+
"loss": 0.0398,
|
| 1738 |
+
"step": 24000
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.434365979228045,
|
| 1742 |
+
"grad_norm": 0.5379288196563721,
|
| 1743 |
+
"learning_rate": 1.4975878015248096e-05,
|
| 1744 |
+
"loss": 0.0263,
|
| 1745 |
+
"step": 24100
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.4403178287652887,
|
| 1749 |
+
"grad_norm": 2.396723747253418,
|
| 1750 |
+
"learning_rate": 1.4950881139857519e-05,
|
| 1751 |
+
"loss": 0.0355,
|
| 1752 |
+
"step": 24200
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.4462696783025324,
|
| 1756 |
+
"grad_norm": 0.052881885319948196,
|
| 1757 |
+
"learning_rate": 1.4925884264466944e-05,
|
| 1758 |
+
"loss": 0.0381,
|
| 1759 |
+
"step": 24300
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.452221527839776,
|
| 1763 |
+
"grad_norm": 0.042416125535964966,
|
| 1764 |
+
"learning_rate": 1.4900887389076366e-05,
|
| 1765 |
+
"loss": 0.0268,
|
| 1766 |
+
"step": 24400
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 1.4581733773770198,
|
| 1770 |
+
"grad_norm": 0.05842834711074829,
|
| 1771 |
+
"learning_rate": 1.4875890513685791e-05,
|
| 1772 |
+
"loss": 0.0508,
|
| 1773 |
+
"step": 24500
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.4641252269142635,
|
| 1777 |
+
"grad_norm": 0.1875191628932953,
|
| 1778 |
+
"learning_rate": 1.4850893638295214e-05,
|
| 1779 |
+
"loss": 0.0578,
|
| 1780 |
+
"step": 24600
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.4700770764515072,
|
| 1784 |
+
"grad_norm": 2.026597499847412,
|
| 1785 |
+
"learning_rate": 1.482589676290464e-05,
|
| 1786 |
+
"loss": 0.0272,
|
| 1787 |
+
"step": 24700
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.476028925988751,
|
| 1791 |
+
"grad_norm": 0.9349521398544312,
|
| 1792 |
+
"learning_rate": 1.4800899887514063e-05,
|
| 1793 |
+
"loss": 0.0338,
|
| 1794 |
+
"step": 24800
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.4819807755259946,
|
| 1798 |
+
"grad_norm": 7.7040791511535645,
|
| 1799 |
+
"learning_rate": 1.4775903012123484e-05,
|
| 1800 |
+
"loss": 0.0288,
|
| 1801 |
+
"step": 24900
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.4879326250632383,
|
| 1805 |
+
"grad_norm": 0.027851175516843796,
|
| 1806 |
+
"learning_rate": 1.475090613673291e-05,
|
| 1807 |
+
"loss": 0.0412,
|
| 1808 |
+
"step": 25000
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.4879326250632383,
|
| 1812 |
+
"eval_accuracy": 0.9921910339737637,
|
| 1813 |
+
"eval_f1": 0.982066703116457,
|
| 1814 |
+
"eval_loss": 0.031415630131959915,
|
| 1815 |
+
"eval_precision": 0.9862727871732924,
|
| 1816 |
+
"eval_recall": 0.9778963414634146,
|
| 1817 |
+
"eval_runtime": 634.7831,
|
| 1818 |
+
"eval_samples_per_second": 132.338,
|
| 1819 |
+
"eval_steps_per_second": 4.137,
|
| 1820 |
+
"step": 25000
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 1.493884474600482,
|
| 1824 |
+
"grad_norm": 0.005522654391825199,
|
| 1825 |
+
"learning_rate": 1.4725909261342333e-05,
|
| 1826 |
+
"loss": 0.0185,
|
| 1827 |
+
"step": 25100
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 1.4998363241377257,
|
| 1831 |
+
"grad_norm": 5.522494316101074,
|
| 1832 |
+
"learning_rate": 1.4700912385951758e-05,
|
| 1833 |
+
"loss": 0.0452,
|
| 1834 |
+
"step": 25200
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 1.5057881736749694,
|
| 1838 |
+
"grad_norm": 18.661855697631836,
|
| 1839 |
+
"learning_rate": 1.467591551056118e-05,
|
| 1840 |
+
"loss": 0.031,
|
| 1841 |
+
"step": 25300
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 1.5117400232122131,
|
| 1845 |
+
"grad_norm": 0.14226514101028442,
|
| 1846 |
+
"learning_rate": 1.4650918635170605e-05,
|
| 1847 |
+
"loss": 0.0354,
|
| 1848 |
+
"step": 25400
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 1.5176918727494568,
|
| 1852 |
+
"grad_norm": 0.0307607501745224,
|
| 1853 |
+
"learning_rate": 1.4625921759780028e-05,
|
| 1854 |
+
"loss": 0.0351,
|
| 1855 |
+
"step": 25500
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 1.5236437222867005,
|
| 1859 |
+
"grad_norm": 0.018097123131155968,
|
| 1860 |
+
"learning_rate": 1.4600924884389453e-05,
|
| 1861 |
+
"loss": 0.0463,
|
| 1862 |
+
"step": 25600
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 1.5295955718239442,
|
| 1866 |
+
"grad_norm": 0.016355447471141815,
|
| 1867 |
+
"learning_rate": 1.4575928008998877e-05,
|
| 1868 |
+
"loss": 0.0275,
|
| 1869 |
+
"step": 25700
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 1.535547421361188,
|
| 1873 |
+
"grad_norm": 0.03597331792116165,
|
| 1874 |
+
"learning_rate": 1.4550931133608298e-05,
|
| 1875 |
+
"loss": 0.0231,
|
| 1876 |
+
"step": 25800
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 1.5414992708984316,
|
| 1880 |
+
"grad_norm": 0.02727796509861946,
|
| 1881 |
+
"learning_rate": 1.4525934258217724e-05,
|
| 1882 |
+
"loss": 0.0346,
|
| 1883 |
+
"step": 25900
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 1.5474511204356753,
|
| 1887 |
+
"grad_norm": 20.804296493530273,
|
| 1888 |
+
"learning_rate": 1.4500937382827147e-05,
|
| 1889 |
+
"loss": 0.0397,
|
| 1890 |
+
"step": 26000
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 1.553402969972919,
|
| 1894 |
+
"grad_norm": 0.07538951188325882,
|
| 1895 |
+
"learning_rate": 1.4475940507436572e-05,
|
| 1896 |
+
"loss": 0.049,
|
| 1897 |
+
"step": 26100
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 1.5593548195101627,
|
| 1901 |
+
"grad_norm": 5.466484546661377,
|
| 1902 |
+
"learning_rate": 1.4450943632045995e-05,
|
| 1903 |
+
"loss": 0.0454,
|
| 1904 |
+
"step": 26200
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 1.5653066690474065,
|
| 1908 |
+
"grad_norm": 5.512643814086914,
|
| 1909 |
+
"learning_rate": 1.442594675665542e-05,
|
| 1910 |
+
"loss": 0.0464,
|
| 1911 |
+
"step": 26300
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 1.5712585185846502,
|
| 1915 |
+
"grad_norm": 0.0186602845788002,
|
| 1916 |
+
"learning_rate": 1.4400949881264842e-05,
|
| 1917 |
+
"loss": 0.0301,
|
| 1918 |
+
"step": 26400
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 1.5772103681218939,
|
| 1922 |
+
"grad_norm": 0.031637031584978104,
|
| 1923 |
+
"learning_rate": 1.4375953005874266e-05,
|
| 1924 |
+
"loss": 0.0349,
|
| 1925 |
+
"step": 26500
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 1.5831622176591376,
|
| 1929 |
+
"grad_norm": 0.016410792246460915,
|
| 1930 |
+
"learning_rate": 1.435095613048369e-05,
|
| 1931 |
+
"loss": 0.0468,
|
| 1932 |
+
"step": 26600
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 1.5891140671963813,
|
| 1936 |
+
"grad_norm": 0.05681620165705681,
|
| 1937 |
+
"learning_rate": 1.4325959255093114e-05,
|
| 1938 |
+
"loss": 0.0251,
|
| 1939 |
+
"step": 26700
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 1.595065916733625,
|
| 1943 |
+
"grad_norm": 0.594913125038147,
|
| 1944 |
+
"learning_rate": 1.430096237970254e-05,
|
| 1945 |
+
"loss": 0.0334,
|
| 1946 |
+
"step": 26800
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.6010177662708687,
|
| 1950 |
+
"grad_norm": 1.608115553855896,
|
| 1951 |
+
"learning_rate": 1.4275965504311961e-05,
|
| 1952 |
+
"loss": 0.0366,
|
| 1953 |
+
"step": 26900
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 1.6069696158081124,
|
| 1957 |
+
"grad_norm": 6.881460189819336,
|
| 1958 |
+
"learning_rate": 1.4250968628921386e-05,
|
| 1959 |
+
"loss": 0.04,
|
| 1960 |
+
"step": 27000
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 1.612921465345356,
|
| 1964 |
+
"grad_norm": 0.032269809395074844,
|
| 1965 |
+
"learning_rate": 1.422597175353081e-05,
|
| 1966 |
+
"loss": 0.0332,
|
| 1967 |
+
"step": 27100
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 1.6188733148825998,
|
| 1971 |
+
"grad_norm": 1.2177642583847046,
|
| 1972 |
+
"learning_rate": 1.4200974878140235e-05,
|
| 1973 |
+
"loss": 0.0265,
|
| 1974 |
+
"step": 27200
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 1.6248251644198435,
|
| 1978 |
+
"grad_norm": 0.016585221514105797,
|
| 1979 |
+
"learning_rate": 1.4175978002749658e-05,
|
| 1980 |
+
"loss": 0.0275,
|
| 1981 |
+
"step": 27300
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 1.6307770139570872,
|
| 1985 |
+
"grad_norm": 7.614233493804932,
|
| 1986 |
+
"learning_rate": 1.415098112735908e-05,
|
| 1987 |
+
"loss": 0.0411,
|
| 1988 |
+
"step": 27400
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 1.6367288634943309,
|
| 1992 |
+
"grad_norm": 0.0856470912694931,
|
| 1993 |
+
"learning_rate": 1.4125984251968505e-05,
|
| 1994 |
+
"loss": 0.0569,
|
| 1995 |
+
"step": 27500
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 1.6426807130315746,
|
| 1999 |
+
"grad_norm": 0.03266504406929016,
|
| 2000 |
+
"learning_rate": 1.4100987376577928e-05,
|
| 2001 |
+
"loss": 0.0253,
|
| 2002 |
+
"step": 27600
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 1.6486325625688183,
|
| 2006 |
+
"grad_norm": 0.08693056553602219,
|
| 2007 |
+
"learning_rate": 1.4075990501187353e-05,
|
| 2008 |
+
"loss": 0.0375,
|
| 2009 |
+
"step": 27700
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 1.654584412106062,
|
| 2013 |
+
"grad_norm": 0.016319314017891884,
|
| 2014 |
+
"learning_rate": 1.4050993625796777e-05,
|
| 2015 |
+
"loss": 0.0442,
|
| 2016 |
+
"step": 27800
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 1.6605362616433057,
|
| 2020 |
+
"grad_norm": 0.11942635476589203,
|
| 2021 |
+
"learning_rate": 1.4025996750406202e-05,
|
| 2022 |
+
"loss": 0.0372,
|
| 2023 |
+
"step": 27900
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 1.6664881111805494,
|
| 2027 |
+
"grad_norm": 5.282145977020264,
|
| 2028 |
+
"learning_rate": 1.4000999875015623e-05,
|
| 2029 |
+
"loss": 0.053,
|
| 2030 |
+
"step": 28000
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 1.672439960717793,
|
| 2034 |
+
"grad_norm": 0.020808018743991852,
|
| 2035 |
+
"learning_rate": 1.3976002999625049e-05,
|
| 2036 |
+
"loss": 0.0336,
|
| 2037 |
+
"step": 28100
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 1.6783918102550368,
|
| 2041 |
+
"grad_norm": 3.7852814197540283,
|
| 2042 |
+
"learning_rate": 1.3951006124234472e-05,
|
| 2043 |
+
"loss": 0.0457,
|
| 2044 |
+
"step": 28200
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 1.6843436597922805,
|
| 2048 |
+
"grad_norm": 0.013235555961728096,
|
| 2049 |
+
"learning_rate": 1.3926009248843895e-05,
|
| 2050 |
+
"loss": 0.0386,
|
| 2051 |
+
"step": 28300
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 1.6902955093295242,
|
| 2055 |
+
"grad_norm": 0.05768481642007828,
|
| 2056 |
+
"learning_rate": 1.390101237345332e-05,
|
| 2057 |
+
"loss": 0.0493,
|
| 2058 |
+
"step": 28400
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 1.696247358866768,
|
| 2062 |
+
"grad_norm": 2.631303548812866,
|
| 2063 |
+
"learning_rate": 1.3876015498062742e-05,
|
| 2064 |
+
"loss": 0.0439,
|
| 2065 |
+
"step": 28500
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 1.7021992084040116,
|
| 2069 |
+
"grad_norm": 0.5090872645378113,
|
| 2070 |
+
"learning_rate": 1.3851018622672167e-05,
|
| 2071 |
+
"loss": 0.0282,
|
| 2072 |
+
"step": 28600
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 1.7081510579412553,
|
| 2076 |
+
"grad_norm": 0.014639855362474918,
|
| 2077 |
+
"learning_rate": 1.382602174728159e-05,
|
| 2078 |
+
"loss": 0.0451,
|
| 2079 |
+
"step": 28700
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 1.714102907478499,
|
| 2083 |
+
"grad_norm": 0.010227348655462265,
|
| 2084 |
+
"learning_rate": 1.3801024871891016e-05,
|
| 2085 |
+
"loss": 0.0304,
|
| 2086 |
+
"step": 28800
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 1.7200547570157427,
|
| 2090 |
+
"grad_norm": 0.06359577178955078,
|
| 2091 |
+
"learning_rate": 1.377602799650044e-05,
|
| 2092 |
+
"loss": 0.0531,
|
| 2093 |
+
"step": 28900
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 1.7260066065529864,
|
| 2097 |
+
"grad_norm": 0.1433858424425125,
|
| 2098 |
+
"learning_rate": 1.3751031121109864e-05,
|
| 2099 |
+
"loss": 0.0407,
|
| 2100 |
+
"step": 29000
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 1.7319584560902301,
|
| 2104 |
+
"grad_norm": 0.5865179896354675,
|
| 2105 |
+
"learning_rate": 1.3726034245719286e-05,
|
| 2106 |
+
"loss": 0.0351,
|
| 2107 |
+
"step": 29100
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 1.7379103056274738,
|
| 2111 |
+
"grad_norm": 0.008081269450485706,
|
| 2112 |
+
"learning_rate": 1.370103737032871e-05,
|
| 2113 |
+
"loss": 0.0359,
|
| 2114 |
+
"step": 29200
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 1.7438621551647175,
|
| 2118 |
+
"grad_norm": 0.0038693081587553024,
|
| 2119 |
+
"learning_rate": 1.3676040494938134e-05,
|
| 2120 |
+
"loss": 0.029,
|
| 2121 |
+
"step": 29300
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 1.7498140047019612,
|
| 2125 |
+
"grad_norm": 0.011708752252161503,
|
| 2126 |
+
"learning_rate": 1.3651043619547558e-05,
|
| 2127 |
+
"loss": 0.02,
|
| 2128 |
+
"step": 29400
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 1.755765854239205,
|
| 2132 |
+
"grad_norm": 13.56950569152832,
|
| 2133 |
+
"learning_rate": 1.3626046744156983e-05,
|
| 2134 |
+
"loss": 0.0261,
|
| 2135 |
+
"step": 29500
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 1.7617177037764487,
|
| 2139 |
+
"grad_norm": 0.07075086236000061,
|
| 2140 |
+
"learning_rate": 1.3601049868766405e-05,
|
| 2141 |
+
"loss": 0.0336,
|
| 2142 |
+
"step": 29600
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 1.7676695533136924,
|
| 2146 |
+
"grad_norm": 0.03655830770730972,
|
| 2147 |
+
"learning_rate": 1.357605299337583e-05,
|
| 2148 |
+
"loss": 0.0383,
|
| 2149 |
+
"step": 29700
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 1.773621402850936,
|
| 2153 |
+
"grad_norm": 0.29130032658576965,
|
| 2154 |
+
"learning_rate": 1.3551056117985253e-05,
|
| 2155 |
+
"loss": 0.0324,
|
| 2156 |
+
"step": 29800
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 1.7795732523881798,
|
| 2160 |
+
"grad_norm": 0.023573417216539383,
|
| 2161 |
+
"learning_rate": 1.3526059242594677e-05,
|
| 2162 |
+
"loss": 0.0366,
|
| 2163 |
+
"step": 29900
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 1.7855251019254235,
|
| 2167 |
+
"grad_norm": 3.8324155807495117,
|
| 2168 |
+
"learning_rate": 1.35010623672041e-05,
|
| 2169 |
+
"loss": 0.0391,
|
| 2170 |
+
"step": 30000
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 1.7855251019254235,
|
| 2174 |
+
"eval_accuracy": 0.9919529557412565,
|
| 2175 |
+
"eval_f1": 0.9815602836879432,
|
| 2176 |
+
"eval_loss": 0.031384389847517014,
|
| 2177 |
+
"eval_precision": 0.9835993877104745,
|
| 2178 |
+
"eval_recall": 0.9795296167247387,
|
| 2179 |
+
"eval_runtime": 634.8585,
|
| 2180 |
+
"eval_samples_per_second": 132.322,
|
| 2181 |
+
"eval_steps_per_second": 4.136,
|
| 2182 |
+
"step": 30000
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 1.7914769514626672,
|
| 2186 |
+
"grad_norm": 3.4548158645629883,
|
| 2187 |
+
"learning_rate": 1.3476065491813523e-05,
|
| 2188 |
+
"loss": 0.0359,
|
| 2189 |
+
"step": 30100
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 1.7974288009999109,
|
| 2193 |
+
"grad_norm": 0.14029207825660706,
|
| 2194 |
+
"learning_rate": 1.3451068616422948e-05,
|
| 2195 |
+
"loss": 0.0263,
|
| 2196 |
+
"step": 30200
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 1.8033806505371546,
|
| 2200 |
+
"grad_norm": 0.004503784701228142,
|
| 2201 |
+
"learning_rate": 1.3426071741032372e-05,
|
| 2202 |
+
"loss": 0.0393,
|
| 2203 |
+
"step": 30300
|
| 2204 |
+
},
|
| 2205 |
+
{
|
| 2206 |
+
"epoch": 1.8093325000743983,
|
| 2207 |
+
"grad_norm": 1.7882189750671387,
|
| 2208 |
+
"learning_rate": 1.3401074865641797e-05,
|
| 2209 |
+
"loss": 0.0489,
|
| 2210 |
+
"step": 30400
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 1.815284349611642,
|
| 2214 |
+
"grad_norm": 1.591253399848938,
|
| 2215 |
+
"learning_rate": 1.3376077990251219e-05,
|
| 2216 |
+
"loss": 0.0433,
|
| 2217 |
+
"step": 30500
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 1.8212361991488857,
|
| 2221 |
+
"grad_norm": 0.012020041234791279,
|
| 2222 |
+
"learning_rate": 1.3351081114860644e-05,
|
| 2223 |
+
"loss": 0.0304,
|
| 2224 |
+
"step": 30600
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 1.8271880486861292,
|
| 2228 |
+
"grad_norm": 1.5531669855117798,
|
| 2229 |
+
"learning_rate": 1.3326084239470067e-05,
|
| 2230 |
+
"loss": 0.0335,
|
| 2231 |
+
"step": 30700
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 1.8331398982233729,
|
| 2235 |
+
"grad_norm": 3.4099249839782715,
|
| 2236 |
+
"learning_rate": 1.330108736407949e-05,
|
| 2237 |
+
"loss": 0.0513,
|
| 2238 |
+
"step": 30800
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 1.8390917477606166,
|
| 2242 |
+
"grad_norm": 0.0514712817966938,
|
| 2243 |
+
"learning_rate": 1.3276090488688916e-05,
|
| 2244 |
+
"loss": 0.0492,
|
| 2245 |
+
"step": 30900
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 1.8450435972978603,
|
| 2249 |
+
"grad_norm": 0.018144380301237106,
|
| 2250 |
+
"learning_rate": 1.3251093613298337e-05,
|
| 2251 |
+
"loss": 0.0348,
|
| 2252 |
+
"step": 31000
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 1.850995446835104,
|
| 2256 |
+
"grad_norm": 0.016865933313965797,
|
| 2257 |
+
"learning_rate": 1.3226096737907762e-05,
|
| 2258 |
+
"loss": 0.0387,
|
| 2259 |
+
"step": 31100
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 1.8569472963723477,
|
| 2263 |
+
"grad_norm": 1.086006760597229,
|
| 2264 |
+
"learning_rate": 1.3201099862517186e-05,
|
| 2265 |
+
"loss": 0.0531,
|
| 2266 |
+
"step": 31200
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 1.8628991459095914,
|
| 2270 |
+
"grad_norm": 0.2081891894340515,
|
| 2271 |
+
"learning_rate": 1.3176102987126611e-05,
|
| 2272 |
+
"loss": 0.0541,
|
| 2273 |
+
"step": 31300
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 1.868850995446835,
|
| 2277 |
+
"grad_norm": 0.14017155766487122,
|
| 2278 |
+
"learning_rate": 1.3151106111736034e-05,
|
| 2279 |
+
"loss": 0.0425,
|
| 2280 |
+
"step": 31400
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 1.8748028449840788,
|
| 2284 |
+
"grad_norm": 0.3818506598472595,
|
| 2285 |
+
"learning_rate": 1.312610923634546e-05,
|
| 2286 |
+
"loss": 0.0418,
|
| 2287 |
+
"step": 31500
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 1.8807546945213225,
|
| 2291 |
+
"grad_norm": 0.06837693601846695,
|
| 2292 |
+
"learning_rate": 1.3101112360954881e-05,
|
| 2293 |
+
"loss": 0.0346,
|
| 2294 |
+
"step": 31600
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 1.8867065440585662,
|
| 2298 |
+
"grad_norm": 9.042508125305176,
|
| 2299 |
+
"learning_rate": 1.3076115485564305e-05,
|
| 2300 |
+
"loss": 0.0395,
|
| 2301 |
+
"step": 31700
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 1.89265839359581,
|
| 2305 |
+
"grad_norm": 2.3299245834350586,
|
| 2306 |
+
"learning_rate": 1.305111861017373e-05,
|
| 2307 |
+
"loss": 0.036,
|
| 2308 |
+
"step": 31800
|
| 2309 |
+
},
|
| 2310 |
+
{
|
| 2311 |
+
"epoch": 1.8986102431330536,
|
| 2312 |
+
"grad_norm": 0.08258947730064392,
|
| 2313 |
+
"learning_rate": 1.3026121734783153e-05,
|
| 2314 |
+
"loss": 0.0509,
|
| 2315 |
+
"step": 31900
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 1.9045620926702973,
|
| 2319 |
+
"grad_norm": 0.054314155131578445,
|
| 2320 |
+
"learning_rate": 1.3001124859392578e-05,
|
| 2321 |
+
"loss": 0.036,
|
| 2322 |
+
"step": 32000
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 1.910513942207541,
|
| 2326 |
+
"grad_norm": 0.047836799174547195,
|
| 2327 |
+
"learning_rate": 1.2976127984002e-05,
|
| 2328 |
+
"loss": 0.0353,
|
| 2329 |
+
"step": 32100
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 1.9164657917447847,
|
| 2333 |
+
"grad_norm": 0.2258683145046234,
|
| 2334 |
+
"learning_rate": 1.2951131108611425e-05,
|
| 2335 |
+
"loss": 0.0344,
|
| 2336 |
+
"step": 32200
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 1.9224176412820284,
|
| 2340 |
+
"grad_norm": 2.757575273513794,
|
| 2341 |
+
"learning_rate": 1.2926134233220848e-05,
|
| 2342 |
+
"loss": 0.0295,
|
| 2343 |
+
"step": 32300
|
| 2344 |
+
},
|
| 2345 |
+
{
|
| 2346 |
+
"epoch": 1.9283694908192721,
|
| 2347 |
+
"grad_norm": 0.5833088159561157,
|
| 2348 |
+
"learning_rate": 1.2901137357830272e-05,
|
| 2349 |
+
"loss": 0.037,
|
| 2350 |
+
"step": 32400
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 1.9343213403565158,
|
| 2354 |
+
"grad_norm": 0.00616218289360404,
|
| 2355 |
+
"learning_rate": 1.2876140482439697e-05,
|
| 2356 |
+
"loss": 0.0335,
|
| 2357 |
+
"step": 32500
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 1.9402731898937595,
|
| 2361 |
+
"grad_norm": 0.11325003206729889,
|
| 2362 |
+
"learning_rate": 1.2851143607049119e-05,
|
| 2363 |
+
"loss": 0.0405,
|
| 2364 |
+
"step": 32600
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 1.9462250394310032,
|
| 2368 |
+
"grad_norm": 13.159346580505371,
|
| 2369 |
+
"learning_rate": 1.2826146731658544e-05,
|
| 2370 |
+
"loss": 0.0299,
|
| 2371 |
+
"step": 32700
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 1.952176888968247,
|
| 2375 |
+
"grad_norm": 0.03671230375766754,
|
| 2376 |
+
"learning_rate": 1.2801149856267967e-05,
|
| 2377 |
+
"loss": 0.0479,
|
| 2378 |
+
"step": 32800
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 1.9581287385054906,
|
| 2382 |
+
"grad_norm": 0.011833186261355877,
|
| 2383 |
+
"learning_rate": 1.2776152980877392e-05,
|
| 2384 |
+
"loss": 0.0293,
|
| 2385 |
+
"step": 32900
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 1.9640805880427343,
|
| 2389 |
+
"grad_norm": 0.021998632699251175,
|
| 2390 |
+
"learning_rate": 1.2751156105486816e-05,
|
| 2391 |
+
"loss": 0.0355,
|
| 2392 |
+
"step": 33000
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 1.9700324375799778,
|
| 2396 |
+
"grad_norm": 0.020362643525004387,
|
| 2397 |
+
"learning_rate": 1.272615923009624e-05,
|
| 2398 |
+
"loss": 0.046,
|
| 2399 |
+
"step": 33100
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 1.9759842871172215,
|
| 2403 |
+
"grad_norm": 3.637277603149414,
|
| 2404 |
+
"learning_rate": 1.2701162354705662e-05,
|
| 2405 |
+
"loss": 0.0314,
|
| 2406 |
+
"step": 33200
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 1.9819361366544652,
|
| 2410 |
+
"grad_norm": 0.03707759082317352,
|
| 2411 |
+
"learning_rate": 1.2676165479315086e-05,
|
| 2412 |
+
"loss": 0.03,
|
| 2413 |
+
"step": 33300
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 1.987887986191709,
|
| 2417 |
+
"grad_norm": 0.071082204580307,
|
| 2418 |
+
"learning_rate": 1.2651168603924511e-05,
|
| 2419 |
+
"loss": 0.0311,
|
| 2420 |
+
"step": 33400
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 1.9938398357289526,
|
| 2424 |
+
"grad_norm": 1.5680729150772095,
|
| 2425 |
+
"learning_rate": 1.2626171728533934e-05,
|
| 2426 |
+
"loss": 0.0405,
|
| 2427 |
+
"step": 33500
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 1.9997916852661963,
|
| 2431 |
+
"grad_norm": 0.09194811433553696,
|
| 2432 |
+
"learning_rate": 1.260117485314336e-05,
|
| 2433 |
+
"loss": 0.0528,
|
| 2434 |
+
"step": 33600
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 2.005713775555754,
|
| 2438 |
+
"grad_norm": 0.04092830792069435,
|
| 2439 |
+
"learning_rate": 1.2576177977752781e-05,
|
| 2440 |
+
"loss": 0.0103,
|
| 2441 |
+
"step": 33700
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 2.0116656250929976,
|
| 2445 |
+
"grad_norm": 0.017966441810131073,
|
| 2446 |
+
"learning_rate": 1.2551181102362206e-05,
|
| 2447 |
+
"loss": 0.0045,
|
| 2448 |
+
"step": 33800
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 2.0176174746302413,
|
| 2452 |
+
"grad_norm": 0.002570417709648609,
|
| 2453 |
+
"learning_rate": 1.252618422697163e-05,
|
| 2454 |
+
"loss": 0.0185,
|
| 2455 |
+
"step": 33900
|
| 2456 |
+
},
|
| 2457 |
+
{
|
| 2458 |
+
"epoch": 2.023569324167485,
|
| 2459 |
+
"grad_norm": 9.743237495422363,
|
| 2460 |
+
"learning_rate": 1.2501187351581055e-05,
|
| 2461 |
+
"loss": 0.0095,
|
| 2462 |
+
"step": 34000
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 2.0295211737047287,
|
| 2466 |
+
"grad_norm": 0.00426062848418951,
|
| 2467 |
+
"learning_rate": 1.2476190476190478e-05,
|
| 2468 |
+
"loss": 0.0206,
|
| 2469 |
+
"step": 34100
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 2.0354730232419724,
|
| 2473 |
+
"grad_norm": 0.010534725151956081,
|
| 2474 |
+
"learning_rate": 1.24511936007999e-05,
|
| 2475 |
+
"loss": 0.0112,
|
| 2476 |
+
"step": 34200
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 2.041424872779216,
|
| 2480 |
+
"grad_norm": 0.0059084463864564896,
|
| 2481 |
+
"learning_rate": 1.2426196725409325e-05,
|
| 2482 |
+
"loss": 0.0136,
|
| 2483 |
+
"step": 34300
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 2.04737672231646,
|
| 2487 |
+
"grad_norm": 0.02636191062629223,
|
| 2488 |
+
"learning_rate": 1.2401199850018748e-05,
|
| 2489 |
+
"loss": 0.0173,
|
| 2490 |
+
"step": 34400
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 2.0533285718537035,
|
| 2494 |
+
"grad_norm": 0.010172510519623756,
|
| 2495 |
+
"learning_rate": 1.2376202974628173e-05,
|
| 2496 |
+
"loss": 0.0158,
|
| 2497 |
+
"step": 34500
|
| 2498 |
+
},
|
| 2499 |
+
{
|
| 2500 |
+
"epoch": 2.0592804213909472,
|
| 2501 |
+
"grad_norm": 0.04961102828383446,
|
| 2502 |
+
"learning_rate": 1.2351206099237597e-05,
|
| 2503 |
+
"loss": 0.0243,
|
| 2504 |
+
"step": 34600
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 2.065232270928191,
|
| 2508 |
+
"grad_norm": 0.0027994669508188963,
|
| 2509 |
+
"learning_rate": 1.232620922384702e-05,
|
| 2510 |
+
"loss": 0.0152,
|
| 2511 |
+
"step": 34700
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 2.0711841204654347,
|
| 2515 |
+
"grad_norm": 0.0040953196585178375,
|
| 2516 |
+
"learning_rate": 1.2301212348456444e-05,
|
| 2517 |
+
"loss": 0.0076,
|
| 2518 |
+
"step": 34800
|
| 2519 |
+
},
|
| 2520 |
+
{
|
| 2521 |
+
"epoch": 2.0771359700026784,
|
| 2522 |
+
"grad_norm": 0.019047342240810394,
|
| 2523 |
+
"learning_rate": 1.2276215473065867e-05,
|
| 2524 |
+
"loss": 0.0089,
|
| 2525 |
+
"step": 34900
|
| 2526 |
+
},
|
| 2527 |
+
{
|
| 2528 |
+
"epoch": 2.083087819539922,
|
| 2529 |
+
"grad_norm": 0.0023104604333639145,
|
| 2530 |
+
"learning_rate": 1.2251218597675292e-05,
|
| 2531 |
+
"loss": 0.0119,
|
| 2532 |
+
"step": 35000
|
| 2533 |
+
},
|
| 2534 |
+
{
|
| 2535 |
+
"epoch": 2.083087819539922,
|
| 2536 |
+
"eval_accuracy": 0.9928933647596601,
|
| 2537 |
+
"eval_f1": 0.9836666575469891,
|
| 2538 |
+
"eval_loss": 0.04034886509180069,
|
| 2539 |
+
"eval_precision": 0.9886707364021339,
|
| 2540 |
+
"eval_recall": 0.9787129790940766,
|
| 2541 |
+
"eval_runtime": 633.4633,
|
| 2542 |
+
"eval_samples_per_second": 132.614,
|
| 2543 |
+
"eval_steps_per_second": 4.145,
|
| 2544 |
+
"step": 35000
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 2.0890396690771658,
|
| 2548 |
+
"grad_norm": 0.04810173809528351,
|
| 2549 |
+
"learning_rate": 1.2226221722284714e-05,
|
| 2550 |
+
"loss": 0.0185,
|
| 2551 |
+
"step": 35100
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 2.0949915186144095,
|
| 2555 |
+
"grad_norm": 0.013579961843788624,
|
| 2556 |
+
"learning_rate": 1.2201224846894139e-05,
|
| 2557 |
+
"loss": 0.0147,
|
| 2558 |
+
"step": 35200
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 2.100943368151653,
|
| 2562 |
+
"grad_norm": 0.001705506001599133,
|
| 2563 |
+
"learning_rate": 1.2176227971503562e-05,
|
| 2564 |
+
"loss": 0.014,
|
| 2565 |
+
"step": 35300
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 2.106895217688897,
|
| 2569 |
+
"grad_norm": 0.12017501890659332,
|
| 2570 |
+
"learning_rate": 1.2151231096112987e-05,
|
| 2571 |
+
"loss": 0.0258,
|
| 2572 |
+
"step": 35400
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 2.1128470672261406,
|
| 2576 |
+
"grad_norm": 0.017923153936862946,
|
| 2577 |
+
"learning_rate": 1.212623422072241e-05,
|
| 2578 |
+
"loss": 0.0043,
|
| 2579 |
+
"step": 35500
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 2.1187989167633843,
|
| 2583 |
+
"grad_norm": 0.026006320491433144,
|
| 2584 |
+
"learning_rate": 1.2101237345331836e-05,
|
| 2585 |
+
"loss": 0.0113,
|
| 2586 |
+
"step": 35600
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 2.124750766300628,
|
| 2590 |
+
"grad_norm": 0.009411540813744068,
|
| 2591 |
+
"learning_rate": 1.2076240469941258e-05,
|
| 2592 |
+
"loss": 0.0191,
|
| 2593 |
+
"step": 35700
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 2.1307026158378717,
|
| 2597 |
+
"grad_norm": 0.037772323936223984,
|
| 2598 |
+
"learning_rate": 1.2051243594550681e-05,
|
| 2599 |
+
"loss": 0.0106,
|
| 2600 |
+
"step": 35800
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 2.1366544653751154,
|
| 2604 |
+
"grad_norm": 0.0031770714558660984,
|
| 2605 |
+
"learning_rate": 1.2026246719160106e-05,
|
| 2606 |
+
"loss": 0.0178,
|
| 2607 |
+
"step": 35900
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 2.142606314912359,
|
| 2611 |
+
"grad_norm": 0.0042376103810966015,
|
| 2612 |
+
"learning_rate": 1.200124984376953e-05,
|
| 2613 |
+
"loss": 0.0204,
|
| 2614 |
+
"step": 36000
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 2.148558164449603,
|
| 2618 |
+
"grad_norm": 0.0013943923404440284,
|
| 2619 |
+
"learning_rate": 1.1976252968378955e-05,
|
| 2620 |
+
"loss": 0.0148,
|
| 2621 |
+
"step": 36100
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 2.1545100139868465,
|
| 2625 |
+
"grad_norm": 0.0036634367424994707,
|
| 2626 |
+
"learning_rate": 1.1951256092988376e-05,
|
| 2627 |
+
"loss": 0.0203,
|
| 2628 |
+
"step": 36200
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 2.16046186352409,
|
| 2632 |
+
"grad_norm": 0.015139013528823853,
|
| 2633 |
+
"learning_rate": 1.1926259217597801e-05,
|
| 2634 |
+
"loss": 0.0143,
|
| 2635 |
+
"step": 36300
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 2.166413713061334,
|
| 2639 |
+
"grad_norm": 0.0035298485308885574,
|
| 2640 |
+
"learning_rate": 1.1901262342207225e-05,
|
| 2641 |
+
"loss": 0.0071,
|
| 2642 |
+
"step": 36400
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 2.1723655625985776,
|
| 2646 |
+
"grad_norm": 0.007681310176849365,
|
| 2647 |
+
"learning_rate": 1.187626546681665e-05,
|
| 2648 |
+
"loss": 0.0211,
|
| 2649 |
+
"step": 36500
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 2.1783174121358213,
|
| 2653 |
+
"grad_norm": 1.1557055711746216,
|
| 2654 |
+
"learning_rate": 1.1851268591426073e-05,
|
| 2655 |
+
"loss": 0.0111,
|
| 2656 |
+
"step": 36600
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 2.184269261673065,
|
| 2660 |
+
"grad_norm": 0.7144343256950378,
|
| 2661 |
+
"learning_rate": 1.1826271716035495e-05,
|
| 2662 |
+
"loss": 0.0136,
|
| 2663 |
+
"step": 36700
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 2.1902211112103087,
|
| 2667 |
+
"grad_norm": 0.021098671481013298,
|
| 2668 |
+
"learning_rate": 1.180127484064492e-05,
|
| 2669 |
+
"loss": 0.0241,
|
| 2670 |
+
"step": 36800
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 2.1961729607475524,
|
| 2674 |
+
"grad_norm": 0.0722559317946434,
|
| 2675 |
+
"learning_rate": 1.1776277965254343e-05,
|
| 2676 |
+
"loss": 0.027,
|
| 2677 |
+
"step": 36900
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 2.202124810284796,
|
| 2681 |
+
"grad_norm": 0.0044738114811480045,
|
| 2682 |
+
"learning_rate": 1.1751281089863769e-05,
|
| 2683 |
+
"loss": 0.0142,
|
| 2684 |
+
"step": 37000
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 2.20807665982204,
|
| 2688 |
+
"grad_norm": 0.0008085681474767625,
|
| 2689 |
+
"learning_rate": 1.1726284214473192e-05,
|
| 2690 |
+
"loss": 0.0206,
|
| 2691 |
+
"step": 37100
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 2.2140285093592835,
|
| 2695 |
+
"grad_norm": 0.0013074972666800022,
|
| 2696 |
+
"learning_rate": 1.1701287339082617e-05,
|
| 2697 |
+
"loss": 0.0104,
|
| 2698 |
+
"step": 37200
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 2.2199803588965272,
|
| 2702 |
+
"grad_norm": 0.006557020358741283,
|
| 2703 |
+
"learning_rate": 1.1676290463692039e-05,
|
| 2704 |
+
"loss": 0.0208,
|
| 2705 |
+
"step": 37300
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 2.225932208433771,
|
| 2709 |
+
"grad_norm": 0.007766306400299072,
|
| 2710 |
+
"learning_rate": 1.1651293588301462e-05,
|
| 2711 |
+
"loss": 0.0314,
|
| 2712 |
+
"step": 37400
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 2.2318840579710146,
|
| 2716 |
+
"grad_norm": 0.05710221454501152,
|
| 2717 |
+
"learning_rate": 1.1626296712910887e-05,
|
| 2718 |
+
"loss": 0.0184,
|
| 2719 |
+
"step": 37500
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 2.2378359075082583,
|
| 2723 |
+
"grad_norm": 0.00156008405610919,
|
| 2724 |
+
"learning_rate": 1.160129983752031e-05,
|
| 2725 |
+
"loss": 0.0127,
|
| 2726 |
+
"step": 37600
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 2.243787757045502,
|
| 2730 |
+
"grad_norm": 0.022134894505143166,
|
| 2731 |
+
"learning_rate": 1.1576302962129736e-05,
|
| 2732 |
+
"loss": 0.0268,
|
| 2733 |
+
"step": 37700
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 2.2497396065827457,
|
| 2737 |
+
"grad_norm": 0.4784717559814453,
|
| 2738 |
+
"learning_rate": 1.1551306086739157e-05,
|
| 2739 |
+
"loss": 0.0169,
|
| 2740 |
+
"step": 37800
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 2.2556914561199894,
|
| 2744 |
+
"grad_norm": 0.02040729857981205,
|
| 2745 |
+
"learning_rate": 1.1526309211348583e-05,
|
| 2746 |
+
"loss": 0.0235,
|
| 2747 |
+
"step": 37900
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 2.261643305657233,
|
| 2751 |
+
"grad_norm": 0.006299525499343872,
|
| 2752 |
+
"learning_rate": 1.1501312335958006e-05,
|
| 2753 |
+
"loss": 0.0251,
|
| 2754 |
+
"step": 38000
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 2.267595155194477,
|
| 2758 |
+
"grad_norm": 0.017164984717965126,
|
| 2759 |
+
"learning_rate": 1.1476315460567431e-05,
|
| 2760 |
+
"loss": 0.0161,
|
| 2761 |
+
"step": 38100
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 2.2735470047317206,
|
| 2765 |
+
"grad_norm": 0.006945526693016291,
|
| 2766 |
+
"learning_rate": 1.1451318585176854e-05,
|
| 2767 |
+
"loss": 0.0141,
|
| 2768 |
+
"step": 38200
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 2.2794988542689643,
|
| 2772 |
+
"grad_norm": 0.012456955388188362,
|
| 2773 |
+
"learning_rate": 1.1426321709786276e-05,
|
| 2774 |
+
"loss": 0.02,
|
| 2775 |
+
"step": 38300
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 2.285450703806208,
|
| 2779 |
+
"grad_norm": 0.2582660913467407,
|
| 2780 |
+
"learning_rate": 1.1401324834395701e-05,
|
| 2781 |
+
"loss": 0.0118,
|
| 2782 |
+
"step": 38400
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 2.2914025533434517,
|
| 2786 |
+
"grad_norm": 0.008593305014073849,
|
| 2787 |
+
"learning_rate": 1.1376327959005125e-05,
|
| 2788 |
+
"loss": 0.0172,
|
| 2789 |
+
"step": 38500
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 2.2973544028806954,
|
| 2793 |
+
"grad_norm": 0.3093462884426117,
|
| 2794 |
+
"learning_rate": 1.135133108361455e-05,
|
| 2795 |
+
"loss": 0.0177,
|
| 2796 |
+
"step": 38600
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 2.303306252417939,
|
| 2800 |
+
"grad_norm": 0.03443511947989464,
|
| 2801 |
+
"learning_rate": 1.1326334208223973e-05,
|
| 2802 |
+
"loss": 0.0288,
|
| 2803 |
+
"step": 38700
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 2.3092581019551828,
|
| 2807 |
+
"grad_norm": 0.002232662169262767,
|
| 2808 |
+
"learning_rate": 1.1301337332833398e-05,
|
| 2809 |
+
"loss": 0.0129,
|
| 2810 |
+
"step": 38800
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 2.3152099514924265,
|
| 2814 |
+
"grad_norm": 0.08788257837295532,
|
| 2815 |
+
"learning_rate": 1.127634045744282e-05,
|
| 2816 |
+
"loss": 0.0298,
|
| 2817 |
+
"step": 38900
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 2.32116180102967,
|
| 2821 |
+
"grad_norm": 0.06080511957406998,
|
| 2822 |
+
"learning_rate": 1.1251343582052245e-05,
|
| 2823 |
+
"loss": 0.0193,
|
| 2824 |
+
"step": 39000
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 2.327113650566914,
|
| 2828 |
+
"grad_norm": 0.03741913661360741,
|
| 2829 |
+
"learning_rate": 1.1226346706661668e-05,
|
| 2830 |
+
"loss": 0.0065,
|
| 2831 |
+
"step": 39100
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 2.3330655001041576,
|
| 2835 |
+
"grad_norm": 4.331652641296387,
|
| 2836 |
+
"learning_rate": 1.1201349831271092e-05,
|
| 2837 |
+
"loss": 0.0087,
|
| 2838 |
+
"step": 39200
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 2.3390173496414013,
|
| 2842 |
+
"grad_norm": 7.526216983795166,
|
| 2843 |
+
"learning_rate": 1.1176352955880517e-05,
|
| 2844 |
+
"loss": 0.0157,
|
| 2845 |
+
"step": 39300
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 2.344969199178645,
|
| 2849 |
+
"grad_norm": 0.0066286916844546795,
|
| 2850 |
+
"learning_rate": 1.1151356080489939e-05,
|
| 2851 |
+
"loss": 0.012,
|
| 2852 |
+
"step": 39400
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 2.3509210487158887,
|
| 2856 |
+
"grad_norm": 0.03812452405691147,
|
| 2857 |
+
"learning_rate": 1.1126359205099364e-05,
|
| 2858 |
+
"loss": 0.0265,
|
| 2859 |
+
"step": 39500
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 2.3568728982531324,
|
| 2863 |
+
"grad_norm": 0.063834048807621,
|
| 2864 |
+
"learning_rate": 1.1101362329708787e-05,
|
| 2865 |
+
"loss": 0.0212,
|
| 2866 |
+
"step": 39600
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 2.362824747790376,
|
| 2870 |
+
"grad_norm": 0.0014151857467368245,
|
| 2871 |
+
"learning_rate": 1.1076365454318212e-05,
|
| 2872 |
+
"loss": 0.0141,
|
| 2873 |
+
"step": 39700
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 2.36877659732762,
|
| 2877 |
+
"grad_norm": 10.587772369384766,
|
| 2878 |
+
"learning_rate": 1.1051368578927634e-05,
|
| 2879 |
+
"loss": 0.0297,
|
| 2880 |
+
"step": 39800
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 2.374728446864863,
|
| 2884 |
+
"grad_norm": 0.0303042009472847,
|
| 2885 |
+
"learning_rate": 1.1026371703537059e-05,
|
| 2886 |
+
"loss": 0.0132,
|
| 2887 |
+
"step": 39900
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 2.3806802964021068,
|
| 2891 |
+
"grad_norm": 0.008887387812137604,
|
| 2892 |
+
"learning_rate": 1.1001374828146482e-05,
|
| 2893 |
+
"loss": 0.0195,
|
| 2894 |
+
"step": 40000
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 2.3806802964021068,
|
| 2898 |
+
"eval_accuracy": 0.9929290764945361,
|
| 2899 |
+
"eval_f1": 0.983751846381093,
|
| 2900 |
+
"eval_loss": 0.0369524210691452,
|
| 2901 |
+
"eval_precision": 0.988565145684442,
|
| 2902 |
+
"eval_recall": 0.9789851916376306,
|
| 2903 |
+
"eval_runtime": 635.2271,
|
| 2904 |
+
"eval_samples_per_second": 132.246,
|
| 2905 |
+
"eval_steps_per_second": 4.134,
|
| 2906 |
+
"step": 40000
|
| 2907 |
+
}
|
| 2908 |
+
],
|
| 2909 |
+
"logging_steps": 100,
|
| 2910 |
+
"max_steps": 84010,
|
| 2911 |
+
"num_input_tokens_seen": 0,
|
| 2912 |
+
"num_train_epochs": 5,
|
| 2913 |
+
"save_steps": 5000,
|
| 2914 |
+
"stateful_callbacks": {
|
| 2915 |
+
"EarlyStoppingCallback": {
|
| 2916 |
+
"args": {
|
| 2917 |
+
"early_stopping_patience": 3,
|
| 2918 |
+
"early_stopping_threshold": 0.0
|
| 2919 |
+
},
|
| 2920 |
+
"attributes": {
|
| 2921 |
+
"early_stopping_patience_counter": 0
|
| 2922 |
+
}
|
| 2923 |
+
},
|
| 2924 |
+
"TrainerControl": {
|
| 2925 |
+
"args": {
|
| 2926 |
+
"should_epoch_stop": false,
|
| 2927 |
+
"should_evaluate": false,
|
| 2928 |
+
"should_log": false,
|
| 2929 |
+
"should_save": true,
|
| 2930 |
+
"should_training_stop": false
|
| 2931 |
+
},
|
| 2932 |
+
"attributes": {}
|
| 2933 |
+
}
|
| 2934 |
+
},
|
| 2935 |
+
"total_flos": 1.0903801272155259e+18,
|
| 2936 |
+
"train_batch_size": 20,
|
| 2937 |
+
"trial_name": null,
|
| 2938 |
+
"trial_params": null
|
| 2939 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf18ebd0b6fae6621807dc55422e62ada74d6744e19663b48835f1ec2a9e7148
|
| 3 |
+
size 5777
|