Add fine-tuned ModernBERT model
Browse files- config.json +46 -0
- label_map.json +1 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +945 -0
- trainer_state.json +3172 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50281,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 50281,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"embedding_dropout": 0.0,
|
| 16 |
+
"eos_token_id": 50282,
|
| 17 |
+
"global_attn_every_n_layers": 3,
|
| 18 |
+
"global_rope_theta": 160000.0,
|
| 19 |
+
"gradient_checkpointing": false,
|
| 20 |
+
"hidden_activation": "gelu",
|
| 21 |
+
"hidden_size": 768,
|
| 22 |
+
"initializer_cutoff_factor": 2.0,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 1152,
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"local_attention": 128,
|
| 27 |
+
"local_rope_theta": 10000.0,
|
| 28 |
+
"max_position_embeddings": 8192,
|
| 29 |
+
"mlp_bias": false,
|
| 30 |
+
"mlp_dropout": 0.0,
|
| 31 |
+
"model_type": "modernbert",
|
| 32 |
+
"norm_bias": false,
|
| 33 |
+
"norm_eps": 1e-05,
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_hidden_layers": 22,
|
| 36 |
+
"pad_token_id": 50283,
|
| 37 |
+
"position_embedding_type": "absolute",
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"repad_logits_with_grad": false,
|
| 40 |
+
"sep_token_id": 50282,
|
| 41 |
+
"sparse_pred_ignore_index": -100,
|
| 42 |
+
"sparse_prediction": false,
|
| 43 |
+
"torch_dtype": "float32",
|
| 44 |
+
"transformers_version": "4.52.2",
|
| 45 |
+
"vocab_size": 50368
|
| 46 |
+
}
|
label_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"True": 0, "False": 1}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff682aba27e008f1ef72a422450fe6fd4f0ec796363355ab18d83feadff803e8
|
| 3 |
+
size 598439784
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,945 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "|||IP_ADDRESS|||",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<|padding|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"50254": {
|
| 20 |
+
"content": " ",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"50255": {
|
| 28 |
+
"content": " ",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"50256": {
|
| 36 |
+
"content": " ",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"50257": {
|
| 44 |
+
"content": " ",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"50258": {
|
| 52 |
+
"content": " ",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"50259": {
|
| 60 |
+
"content": " ",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"50260": {
|
| 68 |
+
"content": " ",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"50261": {
|
| 76 |
+
"content": " ",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"50262": {
|
| 84 |
+
"content": " ",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"50263": {
|
| 92 |
+
"content": " ",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"50264": {
|
| 100 |
+
"content": " ",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"50265": {
|
| 108 |
+
"content": " ",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"50266": {
|
| 116 |
+
"content": " ",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"50267": {
|
| 124 |
+
"content": " ",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"50268": {
|
| 132 |
+
"content": " ",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"50269": {
|
| 140 |
+
"content": " ",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": false
|
| 146 |
+
},
|
| 147 |
+
"50270": {
|
| 148 |
+
"content": " ",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": false
|
| 154 |
+
},
|
| 155 |
+
"50271": {
|
| 156 |
+
"content": " ",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": false
|
| 162 |
+
},
|
| 163 |
+
"50272": {
|
| 164 |
+
"content": " ",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": false
|
| 170 |
+
},
|
| 171 |
+
"50273": {
|
| 172 |
+
"content": " ",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"50274": {
|
| 180 |
+
"content": " ",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"50275": {
|
| 188 |
+
"content": " ",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"50276": {
|
| 196 |
+
"content": " ",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"50277": {
|
| 204 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"50278": {
|
| 212 |
+
"content": "|||PHONE_NUMBER|||",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"50279": {
|
| 220 |
+
"content": "<|endoftext|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"50280": {
|
| 228 |
+
"content": "[UNK]",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"50281": {
|
| 236 |
+
"content": "[CLS]",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"50282": {
|
| 244 |
+
"content": "[SEP]",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"50283": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"50284": {
|
| 260 |
+
"content": "[MASK]",
|
| 261 |
+
"lstrip": true,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"50285": {
|
| 268 |
+
"content": "[unused0]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": true,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"50286": {
|
| 276 |
+
"content": "[unused1]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": true,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"50287": {
|
| 284 |
+
"content": "[unused2]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": true,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
},
|
| 291 |
+
"50288": {
|
| 292 |
+
"content": "[unused3]",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": true,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": false
|
| 298 |
+
},
|
| 299 |
+
"50289": {
|
| 300 |
+
"content": "[unused4]",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": true,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": false
|
| 306 |
+
},
|
| 307 |
+
"50290": {
|
| 308 |
+
"content": "[unused5]",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": true,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": false
|
| 314 |
+
},
|
| 315 |
+
"50291": {
|
| 316 |
+
"content": "[unused6]",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": true,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": false
|
| 322 |
+
},
|
| 323 |
+
"50292": {
|
| 324 |
+
"content": "[unused7]",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": true,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": false
|
| 330 |
+
},
|
| 331 |
+
"50293": {
|
| 332 |
+
"content": "[unused8]",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": true,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": false
|
| 338 |
+
},
|
| 339 |
+
"50294": {
|
| 340 |
+
"content": "[unused9]",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": true,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": false
|
| 346 |
+
},
|
| 347 |
+
"50295": {
|
| 348 |
+
"content": "[unused10]",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": true,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": false
|
| 354 |
+
},
|
| 355 |
+
"50296": {
|
| 356 |
+
"content": "[unused11]",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": true,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": false
|
| 362 |
+
},
|
| 363 |
+
"50297": {
|
| 364 |
+
"content": "[unused12]",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": true,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": false
|
| 370 |
+
},
|
| 371 |
+
"50298": {
|
| 372 |
+
"content": "[unused13]",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": true,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": false
|
| 378 |
+
},
|
| 379 |
+
"50299": {
|
| 380 |
+
"content": "[unused14]",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": true,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": false
|
| 386 |
+
},
|
| 387 |
+
"50300": {
|
| 388 |
+
"content": "[unused15]",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": true,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": false
|
| 394 |
+
},
|
| 395 |
+
"50301": {
|
| 396 |
+
"content": "[unused16]",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": true,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": false
|
| 402 |
+
},
|
| 403 |
+
"50302": {
|
| 404 |
+
"content": "[unused17]",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": true,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": false
|
| 410 |
+
},
|
| 411 |
+
"50303": {
|
| 412 |
+
"content": "[unused18]",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": true,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": false
|
| 418 |
+
},
|
| 419 |
+
"50304": {
|
| 420 |
+
"content": "[unused19]",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": true,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": false
|
| 426 |
+
},
|
| 427 |
+
"50305": {
|
| 428 |
+
"content": "[unused20]",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": true,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": false
|
| 434 |
+
},
|
| 435 |
+
"50306": {
|
| 436 |
+
"content": "[unused21]",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": true,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": false
|
| 442 |
+
},
|
| 443 |
+
"50307": {
|
| 444 |
+
"content": "[unused22]",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": true,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": false
|
| 450 |
+
},
|
| 451 |
+
"50308": {
|
| 452 |
+
"content": "[unused23]",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": true,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": false
|
| 458 |
+
},
|
| 459 |
+
"50309": {
|
| 460 |
+
"content": "[unused24]",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": true,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": false
|
| 466 |
+
},
|
| 467 |
+
"50310": {
|
| 468 |
+
"content": "[unused25]",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": true,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": false
|
| 474 |
+
},
|
| 475 |
+
"50311": {
|
| 476 |
+
"content": "[unused26]",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": true,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": false
|
| 482 |
+
},
|
| 483 |
+
"50312": {
|
| 484 |
+
"content": "[unused27]",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": true,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": false
|
| 490 |
+
},
|
| 491 |
+
"50313": {
|
| 492 |
+
"content": "[unused28]",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": true,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": false
|
| 498 |
+
},
|
| 499 |
+
"50314": {
|
| 500 |
+
"content": "[unused29]",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": true,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": false
|
| 506 |
+
},
|
| 507 |
+
"50315": {
|
| 508 |
+
"content": "[unused30]",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": true,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": false
|
| 514 |
+
},
|
| 515 |
+
"50316": {
|
| 516 |
+
"content": "[unused31]",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": true,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": false
|
| 522 |
+
},
|
| 523 |
+
"50317": {
|
| 524 |
+
"content": "[unused32]",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": true,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": false
|
| 530 |
+
},
|
| 531 |
+
"50318": {
|
| 532 |
+
"content": "[unused33]",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": true,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": false
|
| 538 |
+
},
|
| 539 |
+
"50319": {
|
| 540 |
+
"content": "[unused34]",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": true,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": false
|
| 546 |
+
},
|
| 547 |
+
"50320": {
|
| 548 |
+
"content": "[unused35]",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": true,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": false
|
| 554 |
+
},
|
| 555 |
+
"50321": {
|
| 556 |
+
"content": "[unused36]",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": true,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": false
|
| 562 |
+
},
|
| 563 |
+
"50322": {
|
| 564 |
+
"content": "[unused37]",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": true,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": false
|
| 570 |
+
},
|
| 571 |
+
"50323": {
|
| 572 |
+
"content": "[unused38]",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": true,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": false
|
| 578 |
+
},
|
| 579 |
+
"50324": {
|
| 580 |
+
"content": "[unused39]",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": true,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": false
|
| 586 |
+
},
|
| 587 |
+
"50325": {
|
| 588 |
+
"content": "[unused40]",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": true,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": false
|
| 594 |
+
},
|
| 595 |
+
"50326": {
|
| 596 |
+
"content": "[unused41]",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": true,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": false
|
| 602 |
+
},
|
| 603 |
+
"50327": {
|
| 604 |
+
"content": "[unused42]",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": true,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": false
|
| 610 |
+
},
|
| 611 |
+
"50328": {
|
| 612 |
+
"content": "[unused43]",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": true,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": false
|
| 618 |
+
},
|
| 619 |
+
"50329": {
|
| 620 |
+
"content": "[unused44]",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": true,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": false
|
| 626 |
+
},
|
| 627 |
+
"50330": {
|
| 628 |
+
"content": "[unused45]",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": true,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": false
|
| 634 |
+
},
|
| 635 |
+
"50331": {
|
| 636 |
+
"content": "[unused46]",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": true,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": false
|
| 642 |
+
},
|
| 643 |
+
"50332": {
|
| 644 |
+
"content": "[unused47]",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": true,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": false
|
| 650 |
+
},
|
| 651 |
+
"50333": {
|
| 652 |
+
"content": "[unused48]",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": true,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": false
|
| 658 |
+
},
|
| 659 |
+
"50334": {
|
| 660 |
+
"content": "[unused49]",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": true,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": false
|
| 666 |
+
},
|
| 667 |
+
"50335": {
|
| 668 |
+
"content": "[unused50]",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": true,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": false
|
| 674 |
+
},
|
| 675 |
+
"50336": {
|
| 676 |
+
"content": "[unused51]",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": true,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": false
|
| 682 |
+
},
|
| 683 |
+
"50337": {
|
| 684 |
+
"content": "[unused52]",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": true,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": false
|
| 690 |
+
},
|
| 691 |
+
"50338": {
|
| 692 |
+
"content": "[unused53]",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": true,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": false
|
| 698 |
+
},
|
| 699 |
+
"50339": {
|
| 700 |
+
"content": "[unused54]",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": true,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": false
|
| 706 |
+
},
|
| 707 |
+
"50340": {
|
| 708 |
+
"content": "[unused55]",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": true,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": false
|
| 714 |
+
},
|
| 715 |
+
"50341": {
|
| 716 |
+
"content": "[unused56]",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": true,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": false
|
| 722 |
+
},
|
| 723 |
+
"50342": {
|
| 724 |
+
"content": "[unused57]",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": true,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": false
|
| 730 |
+
},
|
| 731 |
+
"50343": {
|
| 732 |
+
"content": "[unused58]",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": true,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": false
|
| 738 |
+
},
|
| 739 |
+
"50344": {
|
| 740 |
+
"content": "[unused59]",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": true,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": false
|
| 746 |
+
},
|
| 747 |
+
"50345": {
|
| 748 |
+
"content": "[unused60]",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": true,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": false
|
| 754 |
+
},
|
| 755 |
+
"50346": {
|
| 756 |
+
"content": "[unused61]",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": true,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": false
|
| 762 |
+
},
|
| 763 |
+
"50347": {
|
| 764 |
+
"content": "[unused62]",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": true,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": false
|
| 770 |
+
},
|
| 771 |
+
"50348": {
|
| 772 |
+
"content": "[unused63]",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": true,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": false
|
| 778 |
+
},
|
| 779 |
+
"50349": {
|
| 780 |
+
"content": "[unused64]",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": true,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": false
|
| 786 |
+
},
|
| 787 |
+
"50350": {
|
| 788 |
+
"content": "[unused65]",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": true,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": false
|
| 794 |
+
},
|
| 795 |
+
"50351": {
|
| 796 |
+
"content": "[unused66]",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": true,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": false
|
| 802 |
+
},
|
| 803 |
+
"50352": {
|
| 804 |
+
"content": "[unused67]",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": true,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": false
|
| 810 |
+
},
|
| 811 |
+
"50353": {
|
| 812 |
+
"content": "[unused68]",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": true,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": false
|
| 818 |
+
},
|
| 819 |
+
"50354": {
|
| 820 |
+
"content": "[unused69]",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": true,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": false
|
| 826 |
+
},
|
| 827 |
+
"50355": {
|
| 828 |
+
"content": "[unused70]",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": true,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": false
|
| 834 |
+
},
|
| 835 |
+
"50356": {
|
| 836 |
+
"content": "[unused71]",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": true,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": false
|
| 842 |
+
},
|
| 843 |
+
"50357": {
|
| 844 |
+
"content": "[unused72]",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": true,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": false
|
| 850 |
+
},
|
| 851 |
+
"50358": {
|
| 852 |
+
"content": "[unused73]",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": true,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": false
|
| 858 |
+
},
|
| 859 |
+
"50359": {
|
| 860 |
+
"content": "[unused74]",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": true,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": false
|
| 866 |
+
},
|
| 867 |
+
"50360": {
|
| 868 |
+
"content": "[unused75]",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": true,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": false
|
| 874 |
+
},
|
| 875 |
+
"50361": {
|
| 876 |
+
"content": "[unused76]",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": true,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": false
|
| 882 |
+
},
|
| 883 |
+
"50362": {
|
| 884 |
+
"content": "[unused77]",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": true,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": false
|
| 890 |
+
},
|
| 891 |
+
"50363": {
|
| 892 |
+
"content": "[unused78]",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": true,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": false
|
| 898 |
+
},
|
| 899 |
+
"50364": {
|
| 900 |
+
"content": "[unused79]",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": true,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": false
|
| 906 |
+
},
|
| 907 |
+
"50365": {
|
| 908 |
+
"content": "[unused80]",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": true,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": false
|
| 914 |
+
},
|
| 915 |
+
"50366": {
|
| 916 |
+
"content": "[unused81]",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": true,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": false
|
| 922 |
+
},
|
| 923 |
+
"50367": {
|
| 924 |
+
"content": "[unused82]",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": true,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": false
|
| 930 |
+
}
|
| 931 |
+
},
|
| 932 |
+
"clean_up_tokenization_spaces": true,
|
| 933 |
+
"cls_token": "[CLS]",
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
+
"mask_token": "[MASK]",
|
| 936 |
+
"model_input_names": [
|
| 937 |
+
"input_ids",
|
| 938 |
+
"attention_mask"
|
| 939 |
+
],
|
| 940 |
+
"model_max_length": 8192,
|
| 941 |
+
"pad_token": "[PAD]",
|
| 942 |
+
"sep_token": "[SEP]",
|
| 943 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
| 944 |
+
"unk_token": "[UNK]"
|
| 945 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4467,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.006715916722632639,
|
| 14 |
+
"grad_norm": 5.630690574645996,
|
| 15 |
+
"learning_rate": 9e-07,
|
| 16 |
+
"loss": 0.7133,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.013431833445265278,
|
| 21 |
+
"grad_norm": 4.237407207489014,
|
| 22 |
+
"learning_rate": 1.9e-06,
|
| 23 |
+
"loss": 0.6472,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.020147750167897917,
|
| 28 |
+
"grad_norm": 6.263025760650635,
|
| 29 |
+
"learning_rate": 2.9e-06,
|
| 30 |
+
"loss": 0.5851,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.026863666890530557,
|
| 35 |
+
"grad_norm": 10.21045207977295,
|
| 36 |
+
"learning_rate": 3.9e-06,
|
| 37 |
+
"loss": 0.5366,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0335795836131632,
|
| 42 |
+
"grad_norm": 3.691526174545288,
|
| 43 |
+
"learning_rate": 4.9000000000000005e-06,
|
| 44 |
+
"loss": 0.4325,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.040295500335795834,
|
| 49 |
+
"grad_norm": 5.201944351196289,
|
| 50 |
+
"learning_rate": 5.9e-06,
|
| 51 |
+
"loss": 0.354,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.04701141705842848,
|
| 56 |
+
"grad_norm": 15.92503547668457,
|
| 57 |
+
"learning_rate": 6.900000000000001e-06,
|
| 58 |
+
"loss": 0.2003,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.053727333781061114,
|
| 63 |
+
"grad_norm": 7.618583679199219,
|
| 64 |
+
"learning_rate": 7.9e-06,
|
| 65 |
+
"loss": 0.2309,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.06044325050369376,
|
| 70 |
+
"grad_norm": 4.151483535766602,
|
| 71 |
+
"learning_rate": 8.9e-06,
|
| 72 |
+
"loss": 0.1384,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0671591672263264,
|
| 77 |
+
"grad_norm": 9.921517372131348,
|
| 78 |
+
"learning_rate": 9.900000000000002e-06,
|
| 79 |
+
"loss": 0.1763,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.07387508394895903,
|
| 84 |
+
"grad_norm": 2.020857810974121,
|
| 85 |
+
"learning_rate": 1.09e-05,
|
| 86 |
+
"loss": 0.1451,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.08059100067159167,
|
| 91 |
+
"grad_norm": 1.8496060371398926,
|
| 92 |
+
"learning_rate": 1.19e-05,
|
| 93 |
+
"loss": 0.1004,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.08730691739422432,
|
| 98 |
+
"grad_norm": 9.236139297485352,
|
| 99 |
+
"learning_rate": 1.29e-05,
|
| 100 |
+
"loss": 0.1879,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.09402283411685695,
|
| 105 |
+
"grad_norm": 10.885250091552734,
|
| 106 |
+
"learning_rate": 1.3900000000000002e-05,
|
| 107 |
+
"loss": 0.1709,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.10073875083948959,
|
| 112 |
+
"grad_norm": 18.184890747070312,
|
| 113 |
+
"learning_rate": 1.49e-05,
|
| 114 |
+
"loss": 0.1324,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.10745466756212223,
|
| 119 |
+
"grad_norm": 6.792922019958496,
|
| 120 |
+
"learning_rate": 1.59e-05,
|
| 121 |
+
"loss": 0.1485,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.11417058428475486,
|
| 126 |
+
"grad_norm": 2.8304738998413086,
|
| 127 |
+
"learning_rate": 1.69e-05,
|
| 128 |
+
"loss": 0.0533,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.12088650100738751,
|
| 133 |
+
"grad_norm": 0.03287811204791069,
|
| 134 |
+
"learning_rate": 1.79e-05,
|
| 135 |
+
"loss": 0.1616,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.12760241773002015,
|
| 140 |
+
"grad_norm": 4.168348789215088,
|
| 141 |
+
"learning_rate": 1.8900000000000002e-05,
|
| 142 |
+
"loss": 0.0667,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.1343183344526528,
|
| 147 |
+
"grad_norm": 0.9931334257125854,
|
| 148 |
+
"learning_rate": 1.9900000000000003e-05,
|
| 149 |
+
"loss": 0.1678,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.14103425117528542,
|
| 154 |
+
"grad_norm": 14.898422241210938,
|
| 155 |
+
"learning_rate": 2.09e-05,
|
| 156 |
+
"loss": 0.1274,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.14775016789791806,
|
| 161 |
+
"grad_norm": 2.7615175247192383,
|
| 162 |
+
"learning_rate": 2.19e-05,
|
| 163 |
+
"loss": 0.1324,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.1544660846205507,
|
| 168 |
+
"grad_norm": 0.19374199211597443,
|
| 169 |
+
"learning_rate": 2.29e-05,
|
| 170 |
+
"loss": 0.2972,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.16118200134318333,
|
| 175 |
+
"grad_norm": 6.9305419921875,
|
| 176 |
+
"learning_rate": 2.39e-05,
|
| 177 |
+
"loss": 0.0863,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.16789791806581597,
|
| 182 |
+
"grad_norm": 8.841792106628418,
|
| 183 |
+
"learning_rate": 2.4900000000000002e-05,
|
| 184 |
+
"loss": 0.1672,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.17461383478844864,
|
| 189 |
+
"grad_norm": 0.10736802220344543,
|
| 190 |
+
"learning_rate": 2.5900000000000003e-05,
|
| 191 |
+
"loss": 0.1535,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.18132975151108127,
|
| 196 |
+
"grad_norm": 9.984793663024902,
|
| 197 |
+
"learning_rate": 2.6900000000000003e-05,
|
| 198 |
+
"loss": 0.0592,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1880456682337139,
|
| 203 |
+
"grad_norm": 17.420595169067383,
|
| 204 |
+
"learning_rate": 2.7900000000000004e-05,
|
| 205 |
+
"loss": 0.2605,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.19476158495634655,
|
| 210 |
+
"grad_norm": 2.0211360454559326,
|
| 211 |
+
"learning_rate": 2.8899999999999998e-05,
|
| 212 |
+
"loss": 0.0581,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.20147750167897918,
|
| 217 |
+
"grad_norm": 4.574538707733154,
|
| 218 |
+
"learning_rate": 2.9900000000000002e-05,
|
| 219 |
+
"loss": 0.1315,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.20819341840161182,
|
| 224 |
+
"grad_norm": 0.37417200207710266,
|
| 225 |
+
"learning_rate": 3.09e-05,
|
| 226 |
+
"loss": 0.0863,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.21490933512424445,
|
| 231 |
+
"grad_norm": 0.08471789956092834,
|
| 232 |
+
"learning_rate": 3.19e-05,
|
| 233 |
+
"loss": 0.0509,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2216252518468771,
|
| 238 |
+
"grad_norm": 2.391404151916504,
|
| 239 |
+
"learning_rate": 3.29e-05,
|
| 240 |
+
"loss": 0.0897,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.22834116856950973,
|
| 245 |
+
"grad_norm": 0.2534968852996826,
|
| 246 |
+
"learning_rate": 3.3900000000000004e-05,
|
| 247 |
+
"loss": 0.1236,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.23505708529214236,
|
| 252 |
+
"grad_norm": 0.9776629209518433,
|
| 253 |
+
"learning_rate": 3.49e-05,
|
| 254 |
+
"loss": 0.1281,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.24177300201477503,
|
| 259 |
+
"grad_norm": 2.469677209854126,
|
| 260 |
+
"learning_rate": 3.59e-05,
|
| 261 |
+
"loss": 0.2372,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.24848891873740767,
|
| 266 |
+
"grad_norm": 0.3327536880970001,
|
| 267 |
+
"learning_rate": 3.69e-05,
|
| 268 |
+
"loss": 0.083,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.2552048354600403,
|
| 273 |
+
"grad_norm": 10.457483291625977,
|
| 274 |
+
"learning_rate": 3.79e-05,
|
| 275 |
+
"loss": 0.1516,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.2619207521826729,
|
| 280 |
+
"grad_norm": 0.4218825697898865,
|
| 281 |
+
"learning_rate": 3.8900000000000004e-05,
|
| 282 |
+
"loss": 0.137,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.2686366689053056,
|
| 287 |
+
"grad_norm": 4.134459495544434,
|
| 288 |
+
"learning_rate": 3.99e-05,
|
| 289 |
+
"loss": 0.1811,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.27535258562793824,
|
| 294 |
+
"grad_norm": 0.6121009588241577,
|
| 295 |
+
"learning_rate": 4.09e-05,
|
| 296 |
+
"loss": 0.0851,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.28206850235057085,
|
| 301 |
+
"grad_norm": 0.04361363872885704,
|
| 302 |
+
"learning_rate": 4.19e-05,
|
| 303 |
+
"loss": 0.0387,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.2887844190732035,
|
| 308 |
+
"grad_norm": 109.2441635131836,
|
| 309 |
+
"learning_rate": 4.29e-05,
|
| 310 |
+
"loss": 0.1153,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.2955003357958361,
|
| 315 |
+
"grad_norm": 0.012662663124501705,
|
| 316 |
+
"learning_rate": 4.39e-05,
|
| 317 |
+
"loss": 0.251,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3022162525184688,
|
| 322 |
+
"grad_norm": 0.8022059202194214,
|
| 323 |
+
"learning_rate": 4.49e-05,
|
| 324 |
+
"loss": 0.184,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.3089321692411014,
|
| 329 |
+
"grad_norm": 18.51458740234375,
|
| 330 |
+
"learning_rate": 4.5900000000000004e-05,
|
| 331 |
+
"loss": 0.1241,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.31564808596373406,
|
| 336 |
+
"grad_norm": 2.7725183963775635,
|
| 337 |
+
"learning_rate": 4.69e-05,
|
| 338 |
+
"loss": 0.1641,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.32236400268636667,
|
| 343 |
+
"grad_norm": 0.11448180675506592,
|
| 344 |
+
"learning_rate": 4.79e-05,
|
| 345 |
+
"loss": 0.0613,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.32907991940899933,
|
| 350 |
+
"grad_norm": 0.0008866311982274055,
|
| 351 |
+
"learning_rate": 4.89e-05,
|
| 352 |
+
"loss": 0.0064,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.33579583613163194,
|
| 357 |
+
"grad_norm": 3.4407784938812256,
|
| 358 |
+
"learning_rate": 4.99e-05,
|
| 359 |
+
"loss": 0.1556,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.3425117528542646,
|
| 364 |
+
"grad_norm": 12.447320938110352,
|
| 365 |
+
"learning_rate": 4.988656415427275e-05,
|
| 366 |
+
"loss": 0.2918,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.34922766957689727,
|
| 371 |
+
"grad_norm": 3.2200286388397217,
|
| 372 |
+
"learning_rate": 4.976052432568692e-05,
|
| 373 |
+
"loss": 0.155,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3559435862995299,
|
| 378 |
+
"grad_norm": 0.31001582741737366,
|
| 379 |
+
"learning_rate": 4.963448449710109e-05,
|
| 380 |
+
"loss": 0.0628,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.36265950302216254,
|
| 385 |
+
"grad_norm": 1.2337498664855957,
|
| 386 |
+
"learning_rate": 4.9508444668515254e-05,
|
| 387 |
+
"loss": 0.1069,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.36937541974479515,
|
| 392 |
+
"grad_norm": 0.11717221140861511,
|
| 393 |
+
"learning_rate": 4.938240483992942e-05,
|
| 394 |
+
"loss": 0.0971,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.3760913364674278,
|
| 399 |
+
"grad_norm": 1.2564656734466553,
|
| 400 |
+
"learning_rate": 4.925636501134358e-05,
|
| 401 |
+
"loss": 0.0889,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.3828072531900604,
|
| 406 |
+
"grad_norm": 1.1871436834335327,
|
| 407 |
+
"learning_rate": 4.9130325182757754e-05,
|
| 408 |
+
"loss": 0.2583,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.3895231699126931,
|
| 413 |
+
"grad_norm": 0.31010547280311584,
|
| 414 |
+
"learning_rate": 4.900428535417192e-05,
|
| 415 |
+
"loss": 0.0479,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.3962390866353257,
|
| 420 |
+
"grad_norm": 0.8911293745040894,
|
| 421 |
+
"learning_rate": 4.8878245525586084e-05,
|
| 422 |
+
"loss": 0.1356,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.40295500335795836,
|
| 427 |
+
"grad_norm": 2.5432729721069336,
|
| 428 |
+
"learning_rate": 4.8752205697000255e-05,
|
| 429 |
+
"loss": 0.0841,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.40967092008059103,
|
| 434 |
+
"grad_norm": 0.2870176136493683,
|
| 435 |
+
"learning_rate": 4.862616586841442e-05,
|
| 436 |
+
"loss": 0.0695,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.41638683680322364,
|
| 441 |
+
"grad_norm": 1.6922942399978638,
|
| 442 |
+
"learning_rate": 4.8500126039828585e-05,
|
| 443 |
+
"loss": 0.0721,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.4231027535258563,
|
| 448 |
+
"grad_norm": 0.4180830717086792,
|
| 449 |
+
"learning_rate": 4.8374086211242756e-05,
|
| 450 |
+
"loss": 0.0194,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.4298186702484889,
|
| 455 |
+
"grad_norm": 4.236703872680664,
|
| 456 |
+
"learning_rate": 4.824804638265692e-05,
|
| 457 |
+
"loss": 0.1223,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.4365345869711216,
|
| 462 |
+
"grad_norm": 2.4450433254241943,
|
| 463 |
+
"learning_rate": 4.8122006554071086e-05,
|
| 464 |
+
"loss": 0.0755,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.4432505036937542,
|
| 469 |
+
"grad_norm": 1.0442028045654297,
|
| 470 |
+
"learning_rate": 4.799596672548525e-05,
|
| 471 |
+
"loss": 0.0912,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.44996642041638685,
|
| 476 |
+
"grad_norm": 5.720908164978027,
|
| 477 |
+
"learning_rate": 4.786992689689943e-05,
|
| 478 |
+
"loss": 0.0321,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.45668233713901946,
|
| 483 |
+
"grad_norm": 0.7653585076332092,
|
| 484 |
+
"learning_rate": 4.774388706831359e-05,
|
| 485 |
+
"loss": 0.0998,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.4633982538616521,
|
| 490 |
+
"grad_norm": 0.3201594352722168,
|
| 491 |
+
"learning_rate": 4.761784723972776e-05,
|
| 492 |
+
"loss": 0.0781,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.47011417058428473,
|
| 497 |
+
"grad_norm": 0.001702402252703905,
|
| 498 |
+
"learning_rate": 4.749180741114192e-05,
|
| 499 |
+
"loss": 0.013,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.4768300873069174,
|
| 504 |
+
"grad_norm": 14.604610443115234,
|
| 505 |
+
"learning_rate": 4.7365767582556094e-05,
|
| 506 |
+
"loss": 0.083,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.48354600402955006,
|
| 511 |
+
"grad_norm": 5.529962539672852,
|
| 512 |
+
"learning_rate": 4.723972775397026e-05,
|
| 513 |
+
"loss": 0.182,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.49026192075218267,
|
| 518 |
+
"grad_norm": 1.8030890226364136,
|
| 519 |
+
"learning_rate": 4.7113687925384424e-05,
|
| 520 |
+
"loss": 0.125,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.49697783747481533,
|
| 525 |
+
"grad_norm": 6.454009532928467,
|
| 526 |
+
"learning_rate": 4.6987648096798595e-05,
|
| 527 |
+
"loss": 0.0709,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.503693754197448,
|
| 532 |
+
"grad_norm": 5.522768020629883,
|
| 533 |
+
"learning_rate": 4.686160826821276e-05,
|
| 534 |
+
"loss": 0.1086,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.5104096709200806,
|
| 539 |
+
"grad_norm": 0.5437310338020325,
|
| 540 |
+
"learning_rate": 4.6735568439626924e-05,
|
| 541 |
+
"loss": 0.0835,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.5171255876427132,
|
| 546 |
+
"grad_norm": 1.4233680963516235,
|
| 547 |
+
"learning_rate": 4.660952861104109e-05,
|
| 548 |
+
"loss": 0.15,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.5238415043653458,
|
| 553 |
+
"grad_norm": 2.103144884109497,
|
| 554 |
+
"learning_rate": 4.648348878245526e-05,
|
| 555 |
+
"loss": 0.0615,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.5305574210879785,
|
| 560 |
+
"grad_norm": 4.456714630126953,
|
| 561 |
+
"learning_rate": 4.6357448953869425e-05,
|
| 562 |
+
"loss": 0.117,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.5372733378106112,
|
| 567 |
+
"grad_norm": 2.5074684619903564,
|
| 568 |
+
"learning_rate": 4.623140912528359e-05,
|
| 569 |
+
"loss": 0.1606,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.5439892545332438,
|
| 574 |
+
"grad_norm": 0.8483042120933533,
|
| 575 |
+
"learning_rate": 4.610536929669776e-05,
|
| 576 |
+
"loss": 0.0747,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.5507051712558765,
|
| 581 |
+
"grad_norm": 0.05906325578689575,
|
| 582 |
+
"learning_rate": 4.5979329468111926e-05,
|
| 583 |
+
"loss": 0.1355,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.5574210879785091,
|
| 588 |
+
"grad_norm": 0.8080152273178101,
|
| 589 |
+
"learning_rate": 4.585328963952609e-05,
|
| 590 |
+
"loss": 0.1001,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.5641370047011417,
|
| 595 |
+
"grad_norm": 0.1343095898628235,
|
| 596 |
+
"learning_rate": 4.572724981094026e-05,
|
| 597 |
+
"loss": 0.0376,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.5708529214237743,
|
| 602 |
+
"grad_norm": 1.397542119026184,
|
| 603 |
+
"learning_rate": 4.560120998235443e-05,
|
| 604 |
+
"loss": 0.1431,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.577568838146407,
|
| 609 |
+
"grad_norm": 0.5649687051773071,
|
| 610 |
+
"learning_rate": 4.547517015376859e-05,
|
| 611 |
+
"loss": 0.0864,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.5842847548690396,
|
| 616 |
+
"grad_norm": 1.3697500228881836,
|
| 617 |
+
"learning_rate": 4.5349130325182757e-05,
|
| 618 |
+
"loss": 0.0727,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.5910006715916722,
|
| 623 |
+
"grad_norm": 0.849629819393158,
|
| 624 |
+
"learning_rate": 4.522309049659693e-05,
|
| 625 |
+
"loss": 0.073,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.5977165883143049,
|
| 630 |
+
"grad_norm": 1.3777800798416138,
|
| 631 |
+
"learning_rate": 4.509705066801109e-05,
|
| 632 |
+
"loss": 0.1439,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.6044325050369376,
|
| 637 |
+
"grad_norm": 3.064931869506836,
|
| 638 |
+
"learning_rate": 4.497101083942526e-05,
|
| 639 |
+
"loss": 0.0923,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.6111484217595702,
|
| 644 |
+
"grad_norm": 0.47612619400024414,
|
| 645 |
+
"learning_rate": 4.484497101083943e-05,
|
| 646 |
+
"loss": 0.0279,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.6178643384822028,
|
| 651 |
+
"grad_norm": 0.2581987679004669,
|
| 652 |
+
"learning_rate": 4.4718931182253594e-05,
|
| 653 |
+
"loss": 0.0275,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.6245802552048355,
|
| 658 |
+
"grad_norm": 3.8201942443847656,
|
| 659 |
+
"learning_rate": 4.459289135366776e-05,
|
| 660 |
+
"loss": 0.0821,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.6312961719274681,
|
| 665 |
+
"grad_norm": 5.899015426635742,
|
| 666 |
+
"learning_rate": 4.446685152508192e-05,
|
| 667 |
+
"loss": 0.1238,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.6380120886501007,
|
| 672 |
+
"grad_norm": 0.38817426562309265,
|
| 673 |
+
"learning_rate": 4.4340811696496094e-05,
|
| 674 |
+
"loss": 0.1314,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.6447280053727333,
|
| 679 |
+
"grad_norm": 0.4328228235244751,
|
| 680 |
+
"learning_rate": 4.421477186791026e-05,
|
| 681 |
+
"loss": 0.0884,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.6514439220953661,
|
| 686 |
+
"grad_norm": 0.645894467830658,
|
| 687 |
+
"learning_rate": 4.4088732039324424e-05,
|
| 688 |
+
"loss": 0.0464,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.6581598388179987,
|
| 693 |
+
"grad_norm": 0.25149455666542053,
|
| 694 |
+
"learning_rate": 4.3962692210738595e-05,
|
| 695 |
+
"loss": 0.1324,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.6648757555406313,
|
| 700 |
+
"grad_norm": 3.0216193199157715,
|
| 701 |
+
"learning_rate": 4.383665238215276e-05,
|
| 702 |
+
"loss": 0.1317,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.6715916722632639,
|
| 707 |
+
"grad_norm": 0.4481722116470337,
|
| 708 |
+
"learning_rate": 4.371061255356693e-05,
|
| 709 |
+
"loss": 0.0304,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.6783075889858966,
|
| 714 |
+
"grad_norm": 0.4348456859588623,
|
| 715 |
+
"learning_rate": 4.3584572724981096e-05,
|
| 716 |
+
"loss": 0.1263,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.6850235057085292,
|
| 721 |
+
"grad_norm": 0.7903152108192444,
|
| 722 |
+
"learning_rate": 4.345853289639527e-05,
|
| 723 |
+
"loss": 0.0465,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.6917394224311618,
|
| 728 |
+
"grad_norm": 0.6616799831390381,
|
| 729 |
+
"learning_rate": 4.333249306780943e-05,
|
| 730 |
+
"loss": 0.0438,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.6984553391537945,
|
| 735 |
+
"grad_norm": 0.45970794558525085,
|
| 736 |
+
"learning_rate": 4.32064532392236e-05,
|
| 737 |
+
"loss": 0.0662,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.7051712558764271,
|
| 742 |
+
"grad_norm": 1.471104621887207,
|
| 743 |
+
"learning_rate": 4.308041341063777e-05,
|
| 744 |
+
"loss": 0.0858,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.7118871725990598,
|
| 749 |
+
"grad_norm": 8.536913871765137,
|
| 750 |
+
"learning_rate": 4.295437358205193e-05,
|
| 751 |
+
"loss": 0.0661,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.7186030893216924,
|
| 756 |
+
"grad_norm": 0.17855380475521088,
|
| 757 |
+
"learning_rate": 4.28283337534661e-05,
|
| 758 |
+
"loss": 0.0604,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.7253190060443251,
|
| 763 |
+
"grad_norm": 1.2315560579299927,
|
| 764 |
+
"learning_rate": 4.270229392488026e-05,
|
| 765 |
+
"loss": 0.0738,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.7320349227669577,
|
| 770 |
+
"grad_norm": 2.4337143898010254,
|
| 771 |
+
"learning_rate": 4.2576254096294434e-05,
|
| 772 |
+
"loss": 0.111,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.7387508394895903,
|
| 777 |
+
"grad_norm": 0.5771811604499817,
|
| 778 |
+
"learning_rate": 4.24502142677086e-05,
|
| 779 |
+
"loss": 0.0873,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.7454667562122229,
|
| 784 |
+
"grad_norm": 0.29616767168045044,
|
| 785 |
+
"learning_rate": 4.2324174439122764e-05,
|
| 786 |
+
"loss": 0.1899,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.7521826729348556,
|
| 791 |
+
"grad_norm": 0.005016247741878033,
|
| 792 |
+
"learning_rate": 4.2198134610536935e-05,
|
| 793 |
+
"loss": 0.0512,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.7588985896574882,
|
| 798 |
+
"grad_norm": 0.6726338267326355,
|
| 799 |
+
"learning_rate": 4.20720947819511e-05,
|
| 800 |
+
"loss": 0.0749,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.7656145063801209,
|
| 805 |
+
"grad_norm": 15.482983589172363,
|
| 806 |
+
"learning_rate": 4.1946054953365264e-05,
|
| 807 |
+
"loss": 0.1208,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.7723304231027536,
|
| 812 |
+
"grad_norm": 0.13030461966991425,
|
| 813 |
+
"learning_rate": 4.182001512477943e-05,
|
| 814 |
+
"loss": 0.0716,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.7790463398253862,
|
| 819 |
+
"grad_norm": 0.00033535558031871915,
|
| 820 |
+
"learning_rate": 4.16939752961936e-05,
|
| 821 |
+
"loss": 0.0575,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.7857622565480188,
|
| 826 |
+
"grad_norm": 9.646067337598652e-05,
|
| 827 |
+
"learning_rate": 4.1567935467607765e-05,
|
| 828 |
+
"loss": 0.0491,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.7924781732706514,
|
| 833 |
+
"grad_norm": 0.6216703653335571,
|
| 834 |
+
"learning_rate": 4.144189563902193e-05,
|
| 835 |
+
"loss": 0.1496,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.7991940899932841,
|
| 840 |
+
"grad_norm": 0.1437370628118515,
|
| 841 |
+
"learning_rate": 4.13158558104361e-05,
|
| 842 |
+
"loss": 0.0467,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.8059100067159167,
|
| 847 |
+
"grad_norm": 0.5845384001731873,
|
| 848 |
+
"learning_rate": 4.1189815981850266e-05,
|
| 849 |
+
"loss": 0.0423,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.8126259234385493,
|
| 854 |
+
"grad_norm": 0.006311117671430111,
|
| 855 |
+
"learning_rate": 4.106377615326443e-05,
|
| 856 |
+
"loss": 0.0434,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.8193418401611821,
|
| 861 |
+
"grad_norm": 0.28811392188072205,
|
| 862 |
+
"learning_rate": 4.09377363246786e-05,
|
| 863 |
+
"loss": 0.0401,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.8260577568838147,
|
| 868 |
+
"grad_norm": 0.00534482067450881,
|
| 869 |
+
"learning_rate": 4.081169649609277e-05,
|
| 870 |
+
"loss": 0.0974,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.8327736736064473,
|
| 875 |
+
"grad_norm": 0.3741544187068939,
|
| 876 |
+
"learning_rate": 4.068565666750693e-05,
|
| 877 |
+
"loss": 0.0457,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.8394895903290799,
|
| 882 |
+
"grad_norm": 0.9101037383079529,
|
| 883 |
+
"learning_rate": 4.0559616838921097e-05,
|
| 884 |
+
"loss": 0.0547,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.8462055070517126,
|
| 889 |
+
"grad_norm": 0.2954216003417969,
|
| 890 |
+
"learning_rate": 4.043357701033527e-05,
|
| 891 |
+
"loss": 0.0656,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.8529214237743452,
|
| 896 |
+
"grad_norm": 1.8236368894577026,
|
| 897 |
+
"learning_rate": 4.030753718174943e-05,
|
| 898 |
+
"loss": 0.0607,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.8596373404969778,
|
| 903 |
+
"grad_norm": 0.17372089624404907,
|
| 904 |
+
"learning_rate": 4.01814973531636e-05,
|
| 905 |
+
"loss": 0.0894,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.8663532572196104,
|
| 910 |
+
"grad_norm": 0.0005210727686062455,
|
| 911 |
+
"learning_rate": 4.005545752457777e-05,
|
| 912 |
+
"loss": 0.0761,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.8730691739422431,
|
| 917 |
+
"grad_norm": 0.29330241680145264,
|
| 918 |
+
"learning_rate": 3.9929417695991934e-05,
|
| 919 |
+
"loss": 0.0626,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.8797850906648758,
|
| 924 |
+
"grad_norm": 0.7308351397514343,
|
| 925 |
+
"learning_rate": 3.98033778674061e-05,
|
| 926 |
+
"loss": 0.0754,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.8865010073875084,
|
| 931 |
+
"grad_norm": 0.0010205712169408798,
|
| 932 |
+
"learning_rate": 3.967733803882027e-05,
|
| 933 |
+
"loss": 0.0991,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.8932169241101411,
|
| 938 |
+
"grad_norm": 0.26492127776145935,
|
| 939 |
+
"learning_rate": 3.955129821023444e-05,
|
| 940 |
+
"loss": 0.0371,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.8999328408327737,
|
| 945 |
+
"grad_norm": 0.3958211839199066,
|
| 946 |
+
"learning_rate": 3.9425258381648606e-05,
|
| 947 |
+
"loss": 0.1793,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.9066487575554063,
|
| 952 |
+
"grad_norm": 0.006723370868712664,
|
| 953 |
+
"learning_rate": 3.929921855306277e-05,
|
| 954 |
+
"loss": 0.0385,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.9133646742780389,
|
| 959 |
+
"grad_norm": 16.94601821899414,
|
| 960 |
+
"learning_rate": 3.917317872447694e-05,
|
| 961 |
+
"loss": 0.0664,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.9200805910006716,
|
| 966 |
+
"grad_norm": 0.3626093864440918,
|
| 967 |
+
"learning_rate": 3.904713889589111e-05,
|
| 968 |
+
"loss": 0.0424,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.9267965077233042,
|
| 973 |
+
"grad_norm": 0.347401887178421,
|
| 974 |
+
"learning_rate": 3.892109906730527e-05,
|
| 975 |
+
"loss": 0.0558,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.9335124244459369,
|
| 980 |
+
"grad_norm": 0.5849874019622803,
|
| 981 |
+
"learning_rate": 3.8795059238719436e-05,
|
| 982 |
+
"loss": 0.0543,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.9402283411685695,
|
| 987 |
+
"grad_norm": 0.0007323077879846096,
|
| 988 |
+
"learning_rate": 3.866901941013361e-05,
|
| 989 |
+
"loss": 0.065,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.9469442578912022,
|
| 994 |
+
"grad_norm": 0.29866859316825867,
|
| 995 |
+
"learning_rate": 3.854297958154777e-05,
|
| 996 |
+
"loss": 0.083,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.9536601746138348,
|
| 1001 |
+
"grad_norm": 1.046910047531128,
|
| 1002 |
+
"learning_rate": 3.841693975296194e-05,
|
| 1003 |
+
"loss": 0.0795,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.9603760913364674,
|
| 1008 |
+
"grad_norm": 0.28778284788131714,
|
| 1009 |
+
"learning_rate": 3.829089992437611e-05,
|
| 1010 |
+
"loss": 0.121,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.9670920080591001,
|
| 1015 |
+
"grad_norm": 0.6510307192802429,
|
| 1016 |
+
"learning_rate": 3.816486009579027e-05,
|
| 1017 |
+
"loss": 0.0976,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.9738079247817327,
|
| 1022 |
+
"grad_norm": 0.7349569797515869,
|
| 1023 |
+
"learning_rate": 3.803882026720444e-05,
|
| 1024 |
+
"loss": 0.027,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.9805238415043653,
|
| 1029 |
+
"grad_norm": 0.41969776153564453,
|
| 1030 |
+
"learning_rate": 3.79127804386186e-05,
|
| 1031 |
+
"loss": 0.0609,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.9872397582269979,
|
| 1036 |
+
"grad_norm": 0.765001118183136,
|
| 1037 |
+
"learning_rate": 3.7786740610032774e-05,
|
| 1038 |
+
"loss": 0.0823,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.9939556749496307,
|
| 1043 |
+
"grad_norm": 0.5332460999488831,
|
| 1044 |
+
"learning_rate": 3.766070078144694e-05,
|
| 1045 |
+
"loss": 0.063,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.0,
|
| 1050 |
+
"eval_loss": 0.05031801387667656,
|
| 1051 |
+
"eval_runtime": 16.4028,
|
| 1052 |
+
"eval_samples_per_second": 362.988,
|
| 1053 |
+
"eval_steps_per_second": 5.731,
|
| 1054 |
+
"step": 1489
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 1.0006715916722633,
|
| 1058 |
+
"grad_norm": 1.0223584175109863,
|
| 1059 |
+
"learning_rate": 3.7534660952861104e-05,
|
| 1060 |
+
"loss": 0.0612,
|
| 1061 |
+
"step": 1490
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 1.007387508394896,
|
| 1065 |
+
"grad_norm": 0.2597563862800598,
|
| 1066 |
+
"learning_rate": 3.7408621124275275e-05,
|
| 1067 |
+
"loss": 0.0986,
|
| 1068 |
+
"step": 1500
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 1.0141034251175285,
|
| 1072 |
+
"grad_norm": 0.4414527714252472,
|
| 1073 |
+
"learning_rate": 3.728258129568944e-05,
|
| 1074 |
+
"loss": 0.0544,
|
| 1075 |
+
"step": 1510
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 1.0208193418401612,
|
| 1079 |
+
"grad_norm": 0.5101744532585144,
|
| 1080 |
+
"learning_rate": 3.7156541467103605e-05,
|
| 1081 |
+
"loss": 0.0549,
|
| 1082 |
+
"step": 1520
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 1.027535258562794,
|
| 1086 |
+
"grad_norm": 0.695880651473999,
|
| 1087 |
+
"learning_rate": 3.7030501638517776e-05,
|
| 1088 |
+
"loss": 0.0429,
|
| 1089 |
+
"step": 1530
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.0342511752854264,
|
| 1093 |
+
"grad_norm": 0.0017918674275279045,
|
| 1094 |
+
"learning_rate": 3.690446180993194e-05,
|
| 1095 |
+
"loss": 0.057,
|
| 1096 |
+
"step": 1540
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 1.0409670920080591,
|
| 1100 |
+
"grad_norm": 5.918661117553711,
|
| 1101 |
+
"learning_rate": 3.6778421981346105e-05,
|
| 1102 |
+
"loss": 0.0428,
|
| 1103 |
+
"step": 1550
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 1.0476830087306916,
|
| 1107 |
+
"grad_norm": 0.017390791326761246,
|
| 1108 |
+
"learning_rate": 3.665238215276027e-05,
|
| 1109 |
+
"loss": 0.107,
|
| 1110 |
+
"step": 1560
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.0543989254533244,
|
| 1114 |
+
"grad_norm": 0.022303210571408272,
|
| 1115 |
+
"learning_rate": 3.652634232417444e-05,
|
| 1116 |
+
"loss": 0.0683,
|
| 1117 |
+
"step": 1570
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 1.061114842175957,
|
| 1121 |
+
"grad_norm": 0.003013026202097535,
|
| 1122 |
+
"learning_rate": 3.6400302495588606e-05,
|
| 1123 |
+
"loss": 0.0675,
|
| 1124 |
+
"step": 1580
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 1.0678307588985896,
|
| 1128 |
+
"grad_norm": 0.0006217322661541402,
|
| 1129 |
+
"learning_rate": 3.627426266700277e-05,
|
| 1130 |
+
"loss": 0.0552,
|
| 1131 |
+
"step": 1590
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 1.0745466756212223,
|
| 1135 |
+
"grad_norm": 0.2726440131664276,
|
| 1136 |
+
"learning_rate": 3.614822283841694e-05,
|
| 1137 |
+
"loss": 0.0427,
|
| 1138 |
+
"step": 1600
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 1.081262592343855,
|
| 1142 |
+
"grad_norm": 0.29946306347846985,
|
| 1143 |
+
"learning_rate": 3.602218300983111e-05,
|
| 1144 |
+
"loss": 0.0866,
|
| 1145 |
+
"step": 1610
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.0879785090664875,
|
| 1149 |
+
"grad_norm": 0.0426226370036602,
|
| 1150 |
+
"learning_rate": 3.589614318124527e-05,
|
| 1151 |
+
"loss": 0.0447,
|
| 1152 |
+
"step": 1620
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 1.0946944257891202,
|
| 1156 |
+
"grad_norm": 0.6733192801475525,
|
| 1157 |
+
"learning_rate": 3.5770103352659437e-05,
|
| 1158 |
+
"loss": 0.1095,
|
| 1159 |
+
"step": 1630
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 1.1014103425117527,
|
| 1163 |
+
"grad_norm": 0.2110043466091156,
|
| 1164 |
+
"learning_rate": 3.564406352407361e-05,
|
| 1165 |
+
"loss": 0.0213,
|
| 1166 |
+
"step": 1640
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 1.1081262592343855,
|
| 1170 |
+
"grad_norm": 0.0002463633718434721,
|
| 1171 |
+
"learning_rate": 3.551802369548777e-05,
|
| 1172 |
+
"loss": 0.0531,
|
| 1173 |
+
"step": 1650
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 1.1148421759570182,
|
| 1177 |
+
"grad_norm": 0.660849392414093,
|
| 1178 |
+
"learning_rate": 3.5391983866901944e-05,
|
| 1179 |
+
"loss": 0.0565,
|
| 1180 |
+
"step": 1660
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 1.1215580926796507,
|
| 1184 |
+
"grad_norm": 0.0015531358076259494,
|
| 1185 |
+
"learning_rate": 3.526594403831611e-05,
|
| 1186 |
+
"loss": 0.0355,
|
| 1187 |
+
"step": 1670
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 1.1282740094022834,
|
| 1191 |
+
"grad_norm": 0.5349295735359192,
|
| 1192 |
+
"learning_rate": 3.513990420973028e-05,
|
| 1193 |
+
"loss": 0.0461,
|
| 1194 |
+
"step": 1680
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 1.1349899261249161,
|
| 1198 |
+
"grad_norm": 0.0036038027610629797,
|
| 1199 |
+
"learning_rate": 3.5013864381144445e-05,
|
| 1200 |
+
"loss": 0.0672,
|
| 1201 |
+
"step": 1690
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 1.1417058428475486,
|
| 1205 |
+
"grad_norm": 0.0011060705874115229,
|
| 1206 |
+
"learning_rate": 3.488782455255861e-05,
|
| 1207 |
+
"loss": 0.0501,
|
| 1208 |
+
"step": 1700
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 1.1484217595701813,
|
| 1212 |
+
"grad_norm": 3.7792551517486572,
|
| 1213 |
+
"learning_rate": 3.476178472397278e-05,
|
| 1214 |
+
"loss": 0.0436,
|
| 1215 |
+
"step": 1710
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 1.155137676292814,
|
| 1219 |
+
"grad_norm": 8.058547019958496,
|
| 1220 |
+
"learning_rate": 3.4635744895386946e-05,
|
| 1221 |
+
"loss": 0.0752,
|
| 1222 |
+
"step": 1720
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 1.1618535930154466,
|
| 1226 |
+
"grad_norm": 0.0012638597982004285,
|
| 1227 |
+
"learning_rate": 3.450970506680111e-05,
|
| 1228 |
+
"loss": 0.0591,
|
| 1229 |
+
"step": 1730
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 1.1685695097380793,
|
| 1233 |
+
"grad_norm": 0.0024126614443957806,
|
| 1234 |
+
"learning_rate": 3.438366523821528e-05,
|
| 1235 |
+
"loss": 0.0399,
|
| 1236 |
+
"step": 1740
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 1.1752854264607118,
|
| 1240 |
+
"grad_norm": 3.4204914569854736,
|
| 1241 |
+
"learning_rate": 3.425762540962945e-05,
|
| 1242 |
+
"loss": 0.0456,
|
| 1243 |
+
"step": 1750
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 1.1820013431833445,
|
| 1247 |
+
"grad_norm": 0.6280553340911865,
|
| 1248 |
+
"learning_rate": 3.413158558104361e-05,
|
| 1249 |
+
"loss": 0.0623,
|
| 1250 |
+
"step": 1760
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.1887172599059772,
|
| 1254 |
+
"grad_norm": 0.0001932340528583154,
|
| 1255 |
+
"learning_rate": 3.4005545752457776e-05,
|
| 1256 |
+
"loss": 0.015,
|
| 1257 |
+
"step": 1770
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.19543317662861,
|
| 1261 |
+
"grad_norm": 3.976154088973999,
|
| 1262 |
+
"learning_rate": 3.387950592387195e-05,
|
| 1263 |
+
"loss": 0.0464,
|
| 1264 |
+
"step": 1780
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 1.2021490933512424,
|
| 1268 |
+
"grad_norm": 0.632788360118866,
|
| 1269 |
+
"learning_rate": 3.375346609528611e-05,
|
| 1270 |
+
"loss": 0.1215,
|
| 1271 |
+
"step": 1790
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 1.2088650100738751,
|
| 1275 |
+
"grad_norm": 0.24529287219047546,
|
| 1276 |
+
"learning_rate": 3.362742626670028e-05,
|
| 1277 |
+
"loss": 0.0582,
|
| 1278 |
+
"step": 1800
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 1.2155809267965076,
|
| 1282 |
+
"grad_norm": 0.42675378918647766,
|
| 1283 |
+
"learning_rate": 3.350138643811445e-05,
|
| 1284 |
+
"loss": 0.0812,
|
| 1285 |
+
"step": 1810
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 1.2222968435191404,
|
| 1289 |
+
"grad_norm": 0.0022362687159329653,
|
| 1290 |
+
"learning_rate": 3.337534660952861e-05,
|
| 1291 |
+
"loss": 0.047,
|
| 1292 |
+
"step": 1820
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 1.229012760241773,
|
| 1296 |
+
"grad_norm": 0.45256197452545166,
|
| 1297 |
+
"learning_rate": 3.324930678094278e-05,
|
| 1298 |
+
"loss": 0.0664,
|
| 1299 |
+
"step": 1830
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.2357286769644056,
|
| 1303 |
+
"grad_norm": 0.8793488144874573,
|
| 1304 |
+
"learning_rate": 3.312326695235694e-05,
|
| 1305 |
+
"loss": 0.0452,
|
| 1306 |
+
"step": 1840
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.2424445936870383,
|
| 1310 |
+
"grad_norm": 0.0005373602034524083,
|
| 1311 |
+
"learning_rate": 3.2997227123771114e-05,
|
| 1312 |
+
"loss": 0.0289,
|
| 1313 |
+
"step": 1850
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.2491605104096708,
|
| 1317 |
+
"grad_norm": 1.7183722257614136,
|
| 1318 |
+
"learning_rate": 3.287118729518528e-05,
|
| 1319 |
+
"loss": 0.0455,
|
| 1320 |
+
"step": 1860
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.2558764271323035,
|
| 1324 |
+
"grad_norm": 0.005168843548744917,
|
| 1325 |
+
"learning_rate": 3.2745147466599444e-05,
|
| 1326 |
+
"loss": 0.0554,
|
| 1327 |
+
"step": 1870
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.2625923438549362,
|
| 1331 |
+
"grad_norm": 0.0013626981526613235,
|
| 1332 |
+
"learning_rate": 3.2619107638013615e-05,
|
| 1333 |
+
"loss": 0.0344,
|
| 1334 |
+
"step": 1880
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.269308260577569,
|
| 1338 |
+
"grad_norm": 0.42641666531562805,
|
| 1339 |
+
"learning_rate": 3.249306780942778e-05,
|
| 1340 |
+
"loss": 0.0683,
|
| 1341 |
+
"step": 1890
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 1.2760241773002015,
|
| 1345 |
+
"grad_norm": 0.005407288204878569,
|
| 1346 |
+
"learning_rate": 3.2367027980841945e-05,
|
| 1347 |
+
"loss": 0.0167,
|
| 1348 |
+
"step": 1900
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 1.2827400940228342,
|
| 1352 |
+
"grad_norm": 0.00033558416180312634,
|
| 1353 |
+
"learning_rate": 3.2240988152256116e-05,
|
| 1354 |
+
"loss": 0.0603,
|
| 1355 |
+
"step": 1910
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 1.2894560107454667,
|
| 1359 |
+
"grad_norm": 0.10696588456630707,
|
| 1360 |
+
"learning_rate": 3.211494832367028e-05,
|
| 1361 |
+
"loss": 0.0787,
|
| 1362 |
+
"step": 1920
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 1.2961719274680994,
|
| 1366 |
+
"grad_norm": 0.7402423620223999,
|
| 1367 |
+
"learning_rate": 3.1988908495084445e-05,
|
| 1368 |
+
"loss": 0.1398,
|
| 1369 |
+
"step": 1930
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 1.3028878441907321,
|
| 1373 |
+
"grad_norm": 0.8248059749603271,
|
| 1374 |
+
"learning_rate": 3.186286866649861e-05,
|
| 1375 |
+
"loss": 0.0925,
|
| 1376 |
+
"step": 1940
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 1.3096037609133646,
|
| 1380 |
+
"grad_norm": 0.0007926832186058164,
|
| 1381 |
+
"learning_rate": 3.173682883791278e-05,
|
| 1382 |
+
"loss": 0.0942,
|
| 1383 |
+
"step": 1950
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 1.3163196776359973,
|
| 1387 |
+
"grad_norm": 0.47744426131248474,
|
| 1388 |
+
"learning_rate": 3.1610789009326946e-05,
|
| 1389 |
+
"loss": 0.0348,
|
| 1390 |
+
"step": 1960
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 1.3230355943586298,
|
| 1394 |
+
"grad_norm": 0.2431195080280304,
|
| 1395 |
+
"learning_rate": 3.148474918074111e-05,
|
| 1396 |
+
"loss": 0.0533,
|
| 1397 |
+
"step": 1970
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 1.3297515110812625,
|
| 1401 |
+
"grad_norm": 3.9710357189178467,
|
| 1402 |
+
"learning_rate": 3.135870935215528e-05,
|
| 1403 |
+
"loss": 0.0338,
|
| 1404 |
+
"step": 1980
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 1.3364674278038953,
|
| 1408 |
+
"grad_norm": 0.6269270181655884,
|
| 1409 |
+
"learning_rate": 3.1232669523569454e-05,
|
| 1410 |
+
"loss": 0.0741,
|
| 1411 |
+
"step": 1990
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 1.343183344526528,
|
| 1415 |
+
"grad_norm": 0.004900393076241016,
|
| 1416 |
+
"learning_rate": 3.110662969498362e-05,
|
| 1417 |
+
"loss": 0.0309,
|
| 1418 |
+
"step": 2000
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.3498992612491605,
|
| 1422 |
+
"grad_norm": 1.1476103067398071,
|
| 1423 |
+
"learning_rate": 3.098058986639778e-05,
|
| 1424 |
+
"loss": 0.047,
|
| 1425 |
+
"step": 2010
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 1.3566151779717932,
|
| 1429 |
+
"grad_norm": 0.30575576424598694,
|
| 1430 |
+
"learning_rate": 3.0854550037811955e-05,
|
| 1431 |
+
"loss": 0.0541,
|
| 1432 |
+
"step": 2020
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 1.3633310946944257,
|
| 1436 |
+
"grad_norm": 0.0030384438578039408,
|
| 1437 |
+
"learning_rate": 3.072851020922612e-05,
|
| 1438 |
+
"loss": 0.0721,
|
| 1439 |
+
"step": 2030
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.3700470114170584,
|
| 1443 |
+
"grad_norm": 0.3193557560443878,
|
| 1444 |
+
"learning_rate": 3.0602470380640284e-05,
|
| 1445 |
+
"loss": 0.0818,
|
| 1446 |
+
"step": 2040
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 1.3767629281396911,
|
| 1450 |
+
"grad_norm": 0.09504958987236023,
|
| 1451 |
+
"learning_rate": 3.0476430552054452e-05,
|
| 1452 |
+
"loss": 0.0238,
|
| 1453 |
+
"step": 2050
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 1.3834788448623236,
|
| 1457 |
+
"grad_norm": 0.40825656056404114,
|
| 1458 |
+
"learning_rate": 3.035039072346862e-05,
|
| 1459 |
+
"loss": 0.0558,
|
| 1460 |
+
"step": 2060
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 1.3901947615849564,
|
| 1464 |
+
"grad_norm": 0.08500930666923523,
|
| 1465 |
+
"learning_rate": 3.0224350894882785e-05,
|
| 1466 |
+
"loss": 0.0854,
|
| 1467 |
+
"step": 2070
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 1.3969106783075889,
|
| 1471 |
+
"grad_norm": 0.9645543098449707,
|
| 1472 |
+
"learning_rate": 3.0098311066296953e-05,
|
| 1473 |
+
"loss": 0.0704,
|
| 1474 |
+
"step": 2080
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 1.4036265950302216,
|
| 1478 |
+
"grad_norm": 0.5297892093658447,
|
| 1479 |
+
"learning_rate": 2.9972271237711118e-05,
|
| 1480 |
+
"loss": 0.0528,
|
| 1481 |
+
"step": 2090
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 1.4103425117528543,
|
| 1485 |
+
"grad_norm": 0.002040713559836149,
|
| 1486 |
+
"learning_rate": 2.9846231409125286e-05,
|
| 1487 |
+
"loss": 0.064,
|
| 1488 |
+
"step": 2100
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 1.417058428475487,
|
| 1492 |
+
"grad_norm": 0.0018752739997580647,
|
| 1493 |
+
"learning_rate": 2.9720191580539454e-05,
|
| 1494 |
+
"loss": 0.0442,
|
| 1495 |
+
"step": 2110
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 1.4237743451981195,
|
| 1499 |
+
"grad_norm": 0.012829877436161041,
|
| 1500 |
+
"learning_rate": 2.959415175195362e-05,
|
| 1501 |
+
"loss": 0.0457,
|
| 1502 |
+
"step": 2120
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 1.4304902619207522,
|
| 1506 |
+
"grad_norm": 0.7869836688041687,
|
| 1507 |
+
"learning_rate": 2.9468111923367787e-05,
|
| 1508 |
+
"loss": 0.0562,
|
| 1509 |
+
"step": 2130
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 1.4372061786433847,
|
| 1513 |
+
"grad_norm": 0.3505788743495941,
|
| 1514 |
+
"learning_rate": 2.934207209478195e-05,
|
| 1515 |
+
"loss": 0.0734,
|
| 1516 |
+
"step": 2140
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 1.4439220953660175,
|
| 1520 |
+
"grad_norm": 0.35704436898231506,
|
| 1521 |
+
"learning_rate": 2.921603226619612e-05,
|
| 1522 |
+
"loss": 0.055,
|
| 1523 |
+
"step": 2150
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 1.4506380120886502,
|
| 1527 |
+
"grad_norm": 0.45379963517189026,
|
| 1528 |
+
"learning_rate": 2.9089992437610288e-05,
|
| 1529 |
+
"loss": 0.0495,
|
| 1530 |
+
"step": 2160
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.4573539288112827,
|
| 1534 |
+
"grad_norm": 0.7454732656478882,
|
| 1535 |
+
"learning_rate": 2.8963952609024453e-05,
|
| 1536 |
+
"loss": 0.085,
|
| 1537 |
+
"step": 2170
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 1.4640698455339154,
|
| 1541 |
+
"grad_norm": 0.04314453899860382,
|
| 1542 |
+
"learning_rate": 2.883791278043862e-05,
|
| 1543 |
+
"loss": 0.0336,
|
| 1544 |
+
"step": 2180
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.470785762256548,
|
| 1548 |
+
"grad_norm": 0.306495726108551,
|
| 1549 |
+
"learning_rate": 2.8711872951852785e-05,
|
| 1550 |
+
"loss": 0.0458,
|
| 1551 |
+
"step": 2190
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 1.4775016789791806,
|
| 1555 |
+
"grad_norm": 0.3177057206630707,
|
| 1556 |
+
"learning_rate": 2.8585833123266953e-05,
|
| 1557 |
+
"loss": 0.09,
|
| 1558 |
+
"step": 2200
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 1.4842175957018133,
|
| 1562 |
+
"grad_norm": 0.4207700192928314,
|
| 1563 |
+
"learning_rate": 2.8459793294681118e-05,
|
| 1564 |
+
"loss": 0.0506,
|
| 1565 |
+
"step": 2210
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 1.490933512424446,
|
| 1569 |
+
"grad_norm": 0.43287593126296997,
|
| 1570 |
+
"learning_rate": 2.8333753466095286e-05,
|
| 1571 |
+
"loss": 0.042,
|
| 1572 |
+
"step": 2220
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 1.4976494291470785,
|
| 1576 |
+
"grad_norm": 0.6717241406440735,
|
| 1577 |
+
"learning_rate": 2.8207713637509454e-05,
|
| 1578 |
+
"loss": 0.0523,
|
| 1579 |
+
"step": 2230
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 1.5043653458697113,
|
| 1583 |
+
"grad_norm": 0.00016471787239424884,
|
| 1584 |
+
"learning_rate": 2.808167380892362e-05,
|
| 1585 |
+
"loss": 0.0308,
|
| 1586 |
+
"step": 2240
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.5110812625923438,
|
| 1590 |
+
"grad_norm": 0.32060420513153076,
|
| 1591 |
+
"learning_rate": 2.7955633980337787e-05,
|
| 1592 |
+
"loss": 0.0945,
|
| 1593 |
+
"step": 2250
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.5177971793149765,
|
| 1597 |
+
"grad_norm": 0.399581640958786,
|
| 1598 |
+
"learning_rate": 2.7829594151751952e-05,
|
| 1599 |
+
"loss": 0.0374,
|
| 1600 |
+
"step": 2260
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.5245130960376092,
|
| 1604 |
+
"grad_norm": 0.6255159378051758,
|
| 1605 |
+
"learning_rate": 2.770355432316612e-05,
|
| 1606 |
+
"loss": 0.049,
|
| 1607 |
+
"step": 2270
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.531229012760242,
|
| 1611 |
+
"grad_norm": 0.005870606750249863,
|
| 1612 |
+
"learning_rate": 2.7577514494580288e-05,
|
| 1613 |
+
"loss": 0.0183,
|
| 1614 |
+
"step": 2280
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.5379449294828744,
|
| 1618 |
+
"grad_norm": 9.138748282566667e-05,
|
| 1619 |
+
"learning_rate": 2.7451474665994453e-05,
|
| 1620 |
+
"loss": 0.0429,
|
| 1621 |
+
"step": 2290
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.544660846205507,
|
| 1625 |
+
"grad_norm": 0.780626654624939,
|
| 1626 |
+
"learning_rate": 2.732543483740862e-05,
|
| 1627 |
+
"loss": 0.0528,
|
| 1628 |
+
"step": 2300
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.5513767629281396,
|
| 1632 |
+
"grad_norm": 0.28625041246414185,
|
| 1633 |
+
"learning_rate": 2.7199395008822785e-05,
|
| 1634 |
+
"loss": 0.0555,
|
| 1635 |
+
"step": 2310
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.5580926796507724,
|
| 1639 |
+
"grad_norm": 0.6077707409858704,
|
| 1640 |
+
"learning_rate": 2.707335518023696e-05,
|
| 1641 |
+
"loss": 0.0651,
|
| 1642 |
+
"step": 2320
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.564808596373405,
|
| 1646 |
+
"grad_norm": 0.005245072301477194,
|
| 1647 |
+
"learning_rate": 2.6947315351651125e-05,
|
| 1648 |
+
"loss": 0.0269,
|
| 1649 |
+
"step": 2330
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 1.5715245130960376,
|
| 1653 |
+
"grad_norm": 0.3782106935977936,
|
| 1654 |
+
"learning_rate": 2.6821275523065293e-05,
|
| 1655 |
+
"loss": 0.0622,
|
| 1656 |
+
"step": 2340
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 1.5782404298186703,
|
| 1660 |
+
"grad_norm": 1.065748929977417,
|
| 1661 |
+
"learning_rate": 2.6695235694479458e-05,
|
| 1662 |
+
"loss": 0.0855,
|
| 1663 |
+
"step": 2350
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 1.5849563465413028,
|
| 1667 |
+
"grad_norm": 0.4613993763923645,
|
| 1668 |
+
"learning_rate": 2.6569195865893626e-05,
|
| 1669 |
+
"loss": 0.0365,
|
| 1670 |
+
"step": 2360
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 1.5916722632639355,
|
| 1674 |
+
"grad_norm": 0.3238326907157898,
|
| 1675 |
+
"learning_rate": 2.6443156037307794e-05,
|
| 1676 |
+
"loss": 0.0357,
|
| 1677 |
+
"step": 2370
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 1.5983881799865682,
|
| 1681 |
+
"grad_norm": 0.0309292059391737,
|
| 1682 |
+
"learning_rate": 2.631711620872196e-05,
|
| 1683 |
+
"loss": 0.228,
|
| 1684 |
+
"step": 2380
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 1.605104096709201,
|
| 1688 |
+
"grad_norm": 13.997108459472656,
|
| 1689 |
+
"learning_rate": 2.6191076380136127e-05,
|
| 1690 |
+
"loss": 0.0675,
|
| 1691 |
+
"step": 2390
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 1.6118200134318335,
|
| 1695 |
+
"grad_norm": 0.4026775658130646,
|
| 1696 |
+
"learning_rate": 2.606503655155029e-05,
|
| 1697 |
+
"loss": 0.1093,
|
| 1698 |
+
"step": 2400
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 1.618535930154466,
|
| 1702 |
+
"grad_norm": 0.29253387451171875,
|
| 1703 |
+
"learning_rate": 2.593899672296446e-05,
|
| 1704 |
+
"loss": 0.0617,
|
| 1705 |
+
"step": 2410
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 1.6252518468770987,
|
| 1709 |
+
"grad_norm": 0.017194174230098724,
|
| 1710 |
+
"learning_rate": 2.5812956894378624e-05,
|
| 1711 |
+
"loss": 0.0371,
|
| 1712 |
+
"step": 2420
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 1.6319677635997314,
|
| 1716 |
+
"grad_norm": 0.2723110020160675,
|
| 1717 |
+
"learning_rate": 2.5686917065792792e-05,
|
| 1718 |
+
"loss": 0.0377,
|
| 1719 |
+
"step": 2430
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 1.6386836803223641,
|
| 1723 |
+
"grad_norm": 1.9029347896575928,
|
| 1724 |
+
"learning_rate": 2.556087723720696e-05,
|
| 1725 |
+
"loss": 0.062,
|
| 1726 |
+
"step": 2440
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 1.6453995970449966,
|
| 1730 |
+
"grad_norm": 0.6120497584342957,
|
| 1731 |
+
"learning_rate": 2.5434837408621125e-05,
|
| 1732 |
+
"loss": 0.0396,
|
| 1733 |
+
"step": 2450
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 1.6521155137676293,
|
| 1737 |
+
"grad_norm": 0.012274952605366707,
|
| 1738 |
+
"learning_rate": 2.5308797580035293e-05,
|
| 1739 |
+
"loss": 0.1047,
|
| 1740 |
+
"step": 2460
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 1.6588314304902618,
|
| 1744 |
+
"grad_norm": 0.0005646342178806663,
|
| 1745 |
+
"learning_rate": 2.5182757751449458e-05,
|
| 1746 |
+
"loss": 0.0295,
|
| 1747 |
+
"step": 2470
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 1.6655473472128945,
|
| 1751 |
+
"grad_norm": 0.2949657738208771,
|
| 1752 |
+
"learning_rate": 2.5056717922863626e-05,
|
| 1753 |
+
"loss": 0.0687,
|
| 1754 |
+
"step": 2480
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 1.6722632639355273,
|
| 1758 |
+
"grad_norm": 0.0009046673658303916,
|
| 1759 |
+
"learning_rate": 2.4930678094277794e-05,
|
| 1760 |
+
"loss": 0.0363,
|
| 1761 |
+
"step": 2490
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 1.67897918065816,
|
| 1765 |
+
"grad_norm": 0.666671633720398,
|
| 1766 |
+
"learning_rate": 2.480463826569196e-05,
|
| 1767 |
+
"loss": 0.0456,
|
| 1768 |
+
"step": 2500
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 1.6856950973807925,
|
| 1772 |
+
"grad_norm": 0.40098175406455994,
|
| 1773 |
+
"learning_rate": 2.4678598437106127e-05,
|
| 1774 |
+
"loss": 0.046,
|
| 1775 |
+
"step": 2510
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 1.692411014103425,
|
| 1779 |
+
"grad_norm": 0.43292441964149475,
|
| 1780 |
+
"learning_rate": 2.455255860852029e-05,
|
| 1781 |
+
"loss": 0.0506,
|
| 1782 |
+
"step": 2520
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 1.6991269308260577,
|
| 1786 |
+
"grad_norm": 0.9216532707214355,
|
| 1787 |
+
"learning_rate": 2.442651877993446e-05,
|
| 1788 |
+
"loss": 0.0481,
|
| 1789 |
+
"step": 2530
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 1.7058428475486904,
|
| 1793 |
+
"grad_norm": 46.244651794433594,
|
| 1794 |
+
"learning_rate": 2.4300478951348628e-05,
|
| 1795 |
+
"loss": 0.0886,
|
| 1796 |
+
"step": 2540
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 1.7125587642713231,
|
| 1800 |
+
"grad_norm": 0.6050248742103577,
|
| 1801 |
+
"learning_rate": 2.4174439122762793e-05,
|
| 1802 |
+
"loss": 0.0557,
|
| 1803 |
+
"step": 2550
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 1.7192746809939556,
|
| 1807 |
+
"grad_norm": 1.492427110671997,
|
| 1808 |
+
"learning_rate": 2.404839929417696e-05,
|
| 1809 |
+
"loss": 0.0499,
|
| 1810 |
+
"step": 2560
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 1.7259905977165884,
|
| 1814 |
+
"grad_norm": 2.4528143405914307,
|
| 1815 |
+
"learning_rate": 2.392235946559113e-05,
|
| 1816 |
+
"loss": 0.0938,
|
| 1817 |
+
"step": 2570
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 1.7327065144392209,
|
| 1821 |
+
"grad_norm": 0.029096094891428947,
|
| 1822 |
+
"learning_rate": 2.3796319637005297e-05,
|
| 1823 |
+
"loss": 0.0313,
|
| 1824 |
+
"step": 2580
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 1.7394224311618536,
|
| 1828 |
+
"grad_norm": 0.3839016556739807,
|
| 1829 |
+
"learning_rate": 2.367027980841946e-05,
|
| 1830 |
+
"loss": 0.0503,
|
| 1831 |
+
"step": 2590
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 1.7461383478844863,
|
| 1835 |
+
"grad_norm": 1.5034056901931763,
|
| 1836 |
+
"learning_rate": 2.354423997983363e-05,
|
| 1837 |
+
"loss": 0.0269,
|
| 1838 |
+
"step": 2600
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 1.752854264607119,
|
| 1842 |
+
"grad_norm": 0.0012208319967612624,
|
| 1843 |
+
"learning_rate": 2.3418200151247798e-05,
|
| 1844 |
+
"loss": 0.0609,
|
| 1845 |
+
"step": 2610
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 1.7595701813297515,
|
| 1849 |
+
"grad_norm": 0.9314192533493042,
|
| 1850 |
+
"learning_rate": 2.3292160322661962e-05,
|
| 1851 |
+
"loss": 0.0475,
|
| 1852 |
+
"step": 2620
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 1.766286098052384,
|
| 1856 |
+
"grad_norm": 0.16898050904273987,
|
| 1857 |
+
"learning_rate": 2.316612049407613e-05,
|
| 1858 |
+
"loss": 0.078,
|
| 1859 |
+
"step": 2630
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 1.7730020147750167,
|
| 1863 |
+
"grad_norm": 0.6302085518836975,
|
| 1864 |
+
"learning_rate": 2.3040080665490295e-05,
|
| 1865 |
+
"loss": 0.173,
|
| 1866 |
+
"step": 2640
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 1.7797179314976495,
|
| 1870 |
+
"grad_norm": 0.01881493628025055,
|
| 1871 |
+
"learning_rate": 2.2914040836904463e-05,
|
| 1872 |
+
"loss": 0.0291,
|
| 1873 |
+
"step": 2650
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 1.7864338482202822,
|
| 1877 |
+
"grad_norm": 0.1634562611579895,
|
| 1878 |
+
"learning_rate": 2.2788001008318628e-05,
|
| 1879 |
+
"loss": 0.0672,
|
| 1880 |
+
"step": 2660
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 1.7931497649429147,
|
| 1884 |
+
"grad_norm": 0.2767401933670044,
|
| 1885 |
+
"learning_rate": 2.2661961179732796e-05,
|
| 1886 |
+
"loss": 0.052,
|
| 1887 |
+
"step": 2670
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 1.7998656816655474,
|
| 1891 |
+
"grad_norm": 0.5256266593933105,
|
| 1892 |
+
"learning_rate": 2.2535921351146964e-05,
|
| 1893 |
+
"loss": 0.0783,
|
| 1894 |
+
"step": 2680
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 1.8065815983881799,
|
| 1898 |
+
"grad_norm": 0.006557038053870201,
|
| 1899 |
+
"learning_rate": 2.240988152256113e-05,
|
| 1900 |
+
"loss": 0.0281,
|
| 1901 |
+
"step": 2690
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 1.8132975151108126,
|
| 1905 |
+
"grad_norm": 0.5430310368537903,
|
| 1906 |
+
"learning_rate": 2.2283841693975297e-05,
|
| 1907 |
+
"loss": 0.0274,
|
| 1908 |
+
"step": 2700
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 1.8200134318334453,
|
| 1912 |
+
"grad_norm": 0.0013151871971786022,
|
| 1913 |
+
"learning_rate": 2.215780186538946e-05,
|
| 1914 |
+
"loss": 0.0453,
|
| 1915 |
+
"step": 2710
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 1.826729348556078,
|
| 1919 |
+
"grad_norm": 3.120368480682373,
|
| 1920 |
+
"learning_rate": 2.203176203680363e-05,
|
| 1921 |
+
"loss": 0.06,
|
| 1922 |
+
"step": 2720
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 1.8334452652787105,
|
| 1926 |
+
"grad_norm": 0.46205762028694153,
|
| 1927 |
+
"learning_rate": 2.1905722208217798e-05,
|
| 1928 |
+
"loss": 0.1034,
|
| 1929 |
+
"step": 2730
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 1.840161182001343,
|
| 1933 |
+
"grad_norm": 0.6960582137107849,
|
| 1934 |
+
"learning_rate": 2.1779682379631966e-05,
|
| 1935 |
+
"loss": 0.0706,
|
| 1936 |
+
"step": 2740
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 1.8468770987239758,
|
| 1940 |
+
"grad_norm": 0.552689254283905,
|
| 1941 |
+
"learning_rate": 2.1653642551046134e-05,
|
| 1942 |
+
"loss": 0.0281,
|
| 1943 |
+
"step": 2750
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 1.8535930154466085,
|
| 1947 |
+
"grad_norm": 0.37117066979408264,
|
| 1948 |
+
"learning_rate": 2.15276027224603e-05,
|
| 1949 |
+
"loss": 0.0655,
|
| 1950 |
+
"step": 2760
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 1.8603089321692412,
|
| 1954 |
+
"grad_norm": 0.3859846293926239,
|
| 1955 |
+
"learning_rate": 2.1401562893874467e-05,
|
| 1956 |
+
"loss": 0.0769,
|
| 1957 |
+
"step": 2770
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"epoch": 1.8670248488918737,
|
| 1961 |
+
"grad_norm": 0.47629514336586,
|
| 1962 |
+
"learning_rate": 2.127552306528863e-05,
|
| 1963 |
+
"loss": 0.0398,
|
| 1964 |
+
"step": 2780
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 1.8737407656145064,
|
| 1968 |
+
"grad_norm": 0.5712143182754517,
|
| 1969 |
+
"learning_rate": 2.11494832367028e-05,
|
| 1970 |
+
"loss": 0.0549,
|
| 1971 |
+
"step": 2790
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 1.880456682337139,
|
| 1975 |
+
"grad_norm": 1.7003332376480103,
|
| 1976 |
+
"learning_rate": 2.1023443408116968e-05,
|
| 1977 |
+
"loss": 0.0624,
|
| 1978 |
+
"step": 2800
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 1.8871725990597716,
|
| 1982 |
+
"grad_norm": 0.46252167224884033,
|
| 1983 |
+
"learning_rate": 2.0897403579531132e-05,
|
| 1984 |
+
"loss": 0.0584,
|
| 1985 |
+
"step": 2810
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 1.8938885157824044,
|
| 1989 |
+
"grad_norm": 4.596211910247803,
|
| 1990 |
+
"learning_rate": 2.07713637509453e-05,
|
| 1991 |
+
"loss": 0.1001,
|
| 1992 |
+
"step": 2820
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"epoch": 1.900604432505037,
|
| 1996 |
+
"grad_norm": 0.0004219062684569508,
|
| 1997 |
+
"learning_rate": 2.0645323922359465e-05,
|
| 1998 |
+
"loss": 0.0698,
|
| 1999 |
+
"step": 2830
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 1.9073203492276696,
|
| 2003 |
+
"grad_norm": 0.5564634799957275,
|
| 2004 |
+
"learning_rate": 2.0519284093773633e-05,
|
| 2005 |
+
"loss": 0.0587,
|
| 2006 |
+
"step": 2840
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 1.914036265950302,
|
| 2010 |
+
"grad_norm": 0.3310578763484955,
|
| 2011 |
+
"learning_rate": 2.03932442651878e-05,
|
| 2012 |
+
"loss": 0.0921,
|
| 2013 |
+
"step": 2850
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 1.9207521826729348,
|
| 2017 |
+
"grad_norm": 0.4154551327228546,
|
| 2018 |
+
"learning_rate": 2.0267204436601966e-05,
|
| 2019 |
+
"loss": 0.0653,
|
| 2020 |
+
"step": 2860
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 1.9274680993955675,
|
| 2024 |
+
"grad_norm": 0.30634987354278564,
|
| 2025 |
+
"learning_rate": 2.0141164608016134e-05,
|
| 2026 |
+
"loss": 0.0439,
|
| 2027 |
+
"step": 2870
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 1.9341840161182002,
|
| 2031 |
+
"grad_norm": 0.353935569524765,
|
| 2032 |
+
"learning_rate": 2.00151247794303e-05,
|
| 2033 |
+
"loss": 0.0453,
|
| 2034 |
+
"step": 2880
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 1.9408999328408327,
|
| 2038 |
+
"grad_norm": 0.009207702241837978,
|
| 2039 |
+
"learning_rate": 1.9889084950844467e-05,
|
| 2040 |
+
"loss": 0.019,
|
| 2041 |
+
"step": 2890
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 1.9476158495634655,
|
| 2045 |
+
"grad_norm": 0.5521604418754578,
|
| 2046 |
+
"learning_rate": 1.9763045122258635e-05,
|
| 2047 |
+
"loss": 0.1271,
|
| 2048 |
+
"step": 2900
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 1.954331766286098,
|
| 2052 |
+
"grad_norm": 4.1649088859558105,
|
| 2053 |
+
"learning_rate": 1.9637005293672803e-05,
|
| 2054 |
+
"loss": 0.0635,
|
| 2055 |
+
"step": 2910
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 1.9610476830087307,
|
| 2059 |
+
"grad_norm": 0.36337295174598694,
|
| 2060 |
+
"learning_rate": 1.9510965465086968e-05,
|
| 2061 |
+
"loss": 0.0704,
|
| 2062 |
+
"step": 2920
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 1.9677635997313634,
|
| 2066 |
+
"grad_norm": 0.1291392743587494,
|
| 2067 |
+
"learning_rate": 1.9384925636501136e-05,
|
| 2068 |
+
"loss": 0.046,
|
| 2069 |
+
"step": 2930
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 1.974479516453996,
|
| 2073 |
+
"grad_norm": 0.011192429810762405,
|
| 2074 |
+
"learning_rate": 1.9258885807915304e-05,
|
| 2075 |
+
"loss": 0.0733,
|
| 2076 |
+
"step": 2940
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 1.9811954331766286,
|
| 2080 |
+
"grad_norm": 0.048028428107500076,
|
| 2081 |
+
"learning_rate": 1.913284597932947e-05,
|
| 2082 |
+
"loss": 0.0419,
|
| 2083 |
+
"step": 2950
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 1.987911349899261,
|
| 2087 |
+
"grad_norm": 0.3492966890335083,
|
| 2088 |
+
"learning_rate": 1.9006806150743637e-05,
|
| 2089 |
+
"loss": 0.0585,
|
| 2090 |
+
"step": 2960
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 1.9946272666218938,
|
| 2094 |
+
"grad_norm": 0.00014002685202285647,
|
| 2095 |
+
"learning_rate": 1.88807663221578e-05,
|
| 2096 |
+
"loss": 0.0612,
|
| 2097 |
+
"step": 2970
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 2.0,
|
| 2101 |
+
"eval_loss": 0.05646410211920738,
|
| 2102 |
+
"eval_runtime": 13.5636,
|
| 2103 |
+
"eval_samples_per_second": 438.969,
|
| 2104 |
+
"eval_steps_per_second": 6.93,
|
| 2105 |
+
"step": 2978
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 2.0013431833445265,
|
| 2109 |
+
"grad_norm": 0.3761807680130005,
|
| 2110 |
+
"learning_rate": 1.875472649357197e-05,
|
| 2111 |
+
"loss": 0.0616,
|
| 2112 |
+
"step": 2980
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 2.0080591000671593,
|
| 2116 |
+
"grad_norm": 0.015631867572665215,
|
| 2117 |
+
"learning_rate": 1.8628686664986138e-05,
|
| 2118 |
+
"loss": 0.0211,
|
| 2119 |
+
"step": 2990
|
| 2120 |
+
},
|
| 2121 |
+
{
|
| 2122 |
+
"epoch": 2.014775016789792,
|
| 2123 |
+
"grad_norm": 0.02187258005142212,
|
| 2124 |
+
"learning_rate": 1.8502646836400302e-05,
|
| 2125 |
+
"loss": 0.0486,
|
| 2126 |
+
"step": 3000
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 2.0214909335124243,
|
| 2130 |
+
"grad_norm": 0.28977006673812866,
|
| 2131 |
+
"learning_rate": 1.837660700781447e-05,
|
| 2132 |
+
"loss": 0.0663,
|
| 2133 |
+
"step": 3010
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 2.028206850235057,
|
| 2137 |
+
"grad_norm": 0.006137068383395672,
|
| 2138 |
+
"learning_rate": 1.8250567179228635e-05,
|
| 2139 |
+
"loss": 0.034,
|
| 2140 |
+
"step": 3020
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 2.0349227669576897,
|
| 2144 |
+
"grad_norm": 0.022373627871274948,
|
| 2145 |
+
"learning_rate": 1.8124527350642803e-05,
|
| 2146 |
+
"loss": 0.0503,
|
| 2147 |
+
"step": 3030
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 2.0416386836803224,
|
| 2151 |
+
"grad_norm": 0.017447108402848244,
|
| 2152 |
+
"learning_rate": 1.799848752205697e-05,
|
| 2153 |
+
"loss": 0.0307,
|
| 2154 |
+
"step": 3040
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 2.048354600402955,
|
| 2158 |
+
"grad_norm": 0.09448742121458054,
|
| 2159 |
+
"learning_rate": 1.7872447693471136e-05,
|
| 2160 |
+
"loss": 0.0401,
|
| 2161 |
+
"step": 3050
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 2.055070517125588,
|
| 2165 |
+
"grad_norm": 0.5452361702919006,
|
| 2166 |
+
"learning_rate": 1.7746407864885304e-05,
|
| 2167 |
+
"loss": 0.0496,
|
| 2168 |
+
"step": 3060
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 2.06178643384822,
|
| 2172 |
+
"grad_norm": 0.5851243138313293,
|
| 2173 |
+
"learning_rate": 1.7620368036299472e-05,
|
| 2174 |
+
"loss": 0.0307,
|
| 2175 |
+
"step": 3070
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 2.068502350570853,
|
| 2179 |
+
"grad_norm": 0.1558593511581421,
|
| 2180 |
+
"learning_rate": 1.749432820771364e-05,
|
| 2181 |
+
"loss": 0.0437,
|
| 2182 |
+
"step": 3080
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 2.0752182672934856,
|
| 2186 |
+
"grad_norm": 0.4523046612739563,
|
| 2187 |
+
"learning_rate": 1.7368288379127805e-05,
|
| 2188 |
+
"loss": 0.0318,
|
| 2189 |
+
"step": 3090
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 2.0819341840161183,
|
| 2193 |
+
"grad_norm": 0.0008133721421472728,
|
| 2194 |
+
"learning_rate": 1.7242248550541973e-05,
|
| 2195 |
+
"loss": 0.0968,
|
| 2196 |
+
"step": 3100
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 2.088650100738751,
|
| 2200 |
+
"grad_norm": 0.28596845269203186,
|
| 2201 |
+
"learning_rate": 1.7116208721956138e-05,
|
| 2202 |
+
"loss": 0.0308,
|
| 2203 |
+
"step": 3110
|
| 2204 |
+
},
|
| 2205 |
+
{
|
| 2206 |
+
"epoch": 2.0953660174613833,
|
| 2207 |
+
"grad_norm": 0.0006714498158544302,
|
| 2208 |
+
"learning_rate": 1.6990168893370306e-05,
|
| 2209 |
+
"loss": 0.0451,
|
| 2210 |
+
"step": 3120
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 2.102081934184016,
|
| 2214 |
+
"grad_norm": 0.3977266550064087,
|
| 2215 |
+
"learning_rate": 1.6864129064784474e-05,
|
| 2216 |
+
"loss": 0.0308,
|
| 2217 |
+
"step": 3130
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 2.1087978509066487,
|
| 2221 |
+
"grad_norm": 1.4212539196014404,
|
| 2222 |
+
"learning_rate": 1.673808923619864e-05,
|
| 2223 |
+
"loss": 0.0518,
|
| 2224 |
+
"step": 3140
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 2.1155137676292814,
|
| 2228 |
+
"grad_norm": 11.565996170043945,
|
| 2229 |
+
"learning_rate": 1.6612049407612807e-05,
|
| 2230 |
+
"loss": 0.0819,
|
| 2231 |
+
"step": 3150
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 2.122229684351914,
|
| 2235 |
+
"grad_norm": 2.776099920272827,
|
| 2236 |
+
"learning_rate": 1.648600957902697e-05,
|
| 2237 |
+
"loss": 0.055,
|
| 2238 |
+
"step": 3160
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 2.1289456010745464,
|
| 2242 |
+
"grad_norm": 0.0052488865330815315,
|
| 2243 |
+
"learning_rate": 1.635996975044114e-05,
|
| 2244 |
+
"loss": 0.0485,
|
| 2245 |
+
"step": 3170
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 2.135661517797179,
|
| 2249 |
+
"grad_norm": 0.7042301893234253,
|
| 2250 |
+
"learning_rate": 1.6233929921855308e-05,
|
| 2251 |
+
"loss": 0.0454,
|
| 2252 |
+
"step": 3180
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 2.142377434519812,
|
| 2256 |
+
"grad_norm": 0.3006635308265686,
|
| 2257 |
+
"learning_rate": 1.6107890093269472e-05,
|
| 2258 |
+
"loss": 0.0377,
|
| 2259 |
+
"step": 3190
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 2.1490933512424446,
|
| 2263 |
+
"grad_norm": 1.699796199798584,
|
| 2264 |
+
"learning_rate": 1.598185026468364e-05,
|
| 2265 |
+
"loss": 0.0731,
|
| 2266 |
+
"step": 3200
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 2.1558092679650773,
|
| 2270 |
+
"grad_norm": 0.20682166516780853,
|
| 2271 |
+
"learning_rate": 1.5855810436097805e-05,
|
| 2272 |
+
"loss": 0.0413,
|
| 2273 |
+
"step": 3210
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 2.16252518468771,
|
| 2277 |
+
"grad_norm": 0.0004898414481431246,
|
| 2278 |
+
"learning_rate": 1.5729770607511973e-05,
|
| 2279 |
+
"loss": 0.1173,
|
| 2280 |
+
"step": 3220
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 2.1692411014103423,
|
| 2284 |
+
"grad_norm": 0.0038841627538204193,
|
| 2285 |
+
"learning_rate": 1.560373077892614e-05,
|
| 2286 |
+
"loss": 0.0435,
|
| 2287 |
+
"step": 3230
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 2.175957018132975,
|
| 2291 |
+
"grad_norm": 0.014045453630387783,
|
| 2292 |
+
"learning_rate": 1.547769095034031e-05,
|
| 2293 |
+
"loss": 0.0457,
|
| 2294 |
+
"step": 3240
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 2.1826729348556078,
|
| 2298 |
+
"grad_norm": 0.010443809442222118,
|
| 2299 |
+
"learning_rate": 1.5351651121754478e-05,
|
| 2300 |
+
"loss": 0.0456,
|
| 2301 |
+
"step": 3250
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 2.1893888515782405,
|
| 2305 |
+
"grad_norm": 0.0003762775450013578,
|
| 2306 |
+
"learning_rate": 1.5225611293168642e-05,
|
| 2307 |
+
"loss": 0.0493,
|
| 2308 |
+
"step": 3260
|
| 2309 |
+
},
|
| 2310 |
+
{
|
| 2311 |
+
"epoch": 2.196104768300873,
|
| 2312 |
+
"grad_norm": 0.3689648509025574,
|
| 2313 |
+
"learning_rate": 1.509957146458281e-05,
|
| 2314 |
+
"loss": 0.0494,
|
| 2315 |
+
"step": 3270
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 2.2028206850235055,
|
| 2319 |
+
"grad_norm": 5.371860243030824e-05,
|
| 2320 |
+
"learning_rate": 1.4973531635996977e-05,
|
| 2321 |
+
"loss": 0.0415,
|
| 2322 |
+
"step": 3280
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 2.209536601746138,
|
| 2326 |
+
"grad_norm": 0.3309116065502167,
|
| 2327 |
+
"learning_rate": 1.4847491807411143e-05,
|
| 2328 |
+
"loss": 0.0428,
|
| 2329 |
+
"step": 3290
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 2.216252518468771,
|
| 2333 |
+
"grad_norm": 0.4156160056591034,
|
| 2334 |
+
"learning_rate": 1.472145197882531e-05,
|
| 2335 |
+
"loss": 0.0647,
|
| 2336 |
+
"step": 3300
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 2.2229684351914036,
|
| 2340 |
+
"grad_norm": 0.44069477915763855,
|
| 2341 |
+
"learning_rate": 1.4595412150239476e-05,
|
| 2342 |
+
"loss": 0.0266,
|
| 2343 |
+
"step": 3310
|
| 2344 |
+
},
|
| 2345 |
+
{
|
| 2346 |
+
"epoch": 2.2296843519140364,
|
| 2347 |
+
"grad_norm": 4.7501349449157715,
|
| 2348 |
+
"learning_rate": 1.4469372321653642e-05,
|
| 2349 |
+
"loss": 0.0934,
|
| 2350 |
+
"step": 3320
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 2.236400268636669,
|
| 2354 |
+
"grad_norm": 4.7144985728664324e-05,
|
| 2355 |
+
"learning_rate": 1.434333249306781e-05,
|
| 2356 |
+
"loss": 0.0488,
|
| 2357 |
+
"step": 3330
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 2.2431161853593014,
|
| 2361 |
+
"grad_norm": 0.0005517873796634376,
|
| 2362 |
+
"learning_rate": 1.4217292664481977e-05,
|
| 2363 |
+
"loss": 0.1232,
|
| 2364 |
+
"step": 3340
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 2.249832102081934,
|
| 2368 |
+
"grad_norm": 0.046205148100852966,
|
| 2369 |
+
"learning_rate": 1.4091252835896143e-05,
|
| 2370 |
+
"loss": 0.1431,
|
| 2371 |
+
"step": 3350
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 2.256548018804567,
|
| 2375 |
+
"grad_norm": 0.06340274959802628,
|
| 2376 |
+
"learning_rate": 1.396521300731031e-05,
|
| 2377 |
+
"loss": 0.0771,
|
| 2378 |
+
"step": 3360
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 2.2632639355271995,
|
| 2382 |
+
"grad_norm": 0.38464516401290894,
|
| 2383 |
+
"learning_rate": 1.3839173178724476e-05,
|
| 2384 |
+
"loss": 0.0383,
|
| 2385 |
+
"step": 3370
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 2.2699798522498322,
|
| 2389 |
+
"grad_norm": 1.4843387603759766,
|
| 2390 |
+
"learning_rate": 1.3713133350138642e-05,
|
| 2391 |
+
"loss": 0.0477,
|
| 2392 |
+
"step": 3380
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 2.2766957689724645,
|
| 2396 |
+
"grad_norm": 0.006335641257464886,
|
| 2397 |
+
"learning_rate": 1.358709352155281e-05,
|
| 2398 |
+
"loss": 0.0583,
|
| 2399 |
+
"step": 3390
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 2.2834116856950972,
|
| 2403 |
+
"grad_norm": 0.009423257783055305,
|
| 2404 |
+
"learning_rate": 1.3461053692966979e-05,
|
| 2405 |
+
"loss": 0.0493,
|
| 2406 |
+
"step": 3400
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 2.29012760241773,
|
| 2410 |
+
"grad_norm": 0.7405962347984314,
|
| 2411 |
+
"learning_rate": 1.3335013864381147e-05,
|
| 2412 |
+
"loss": 0.0444,
|
| 2413 |
+
"step": 3410
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 2.2968435191403627,
|
| 2417 |
+
"grad_norm": 0.13406887650489807,
|
| 2418 |
+
"learning_rate": 1.3208974035795313e-05,
|
| 2419 |
+
"loss": 0.0185,
|
| 2420 |
+
"step": 3420
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 2.3035594358629954,
|
| 2424 |
+
"grad_norm": 1.9850287437438965,
|
| 2425 |
+
"learning_rate": 1.308293420720948e-05,
|
| 2426 |
+
"loss": 0.0305,
|
| 2427 |
+
"step": 3430
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 2.310275352585628,
|
| 2431 |
+
"grad_norm": 0.35775044560432434,
|
| 2432 |
+
"learning_rate": 1.2956894378623646e-05,
|
| 2433 |
+
"loss": 0.0604,
|
| 2434 |
+
"step": 3440
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 2.316991269308261,
|
| 2438 |
+
"grad_norm": 0.46501487493515015,
|
| 2439 |
+
"learning_rate": 1.2830854550037812e-05,
|
| 2440 |
+
"loss": 0.0569,
|
| 2441 |
+
"step": 3450
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 2.323707186030893,
|
| 2445 |
+
"grad_norm": 0.0007875201408751309,
|
| 2446 |
+
"learning_rate": 1.270481472145198e-05,
|
| 2447 |
+
"loss": 0.0305,
|
| 2448 |
+
"step": 3460
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 2.330423102753526,
|
| 2452 |
+
"grad_norm": 0.0034116168972104788,
|
| 2453 |
+
"learning_rate": 1.2578774892866147e-05,
|
| 2454 |
+
"loss": 0.0443,
|
| 2455 |
+
"step": 3470
|
| 2456 |
+
},
|
| 2457 |
+
{
|
| 2458 |
+
"epoch": 2.3371390194761585,
|
| 2459 |
+
"grad_norm": 0.4020250141620636,
|
| 2460 |
+
"learning_rate": 1.2452735064280313e-05,
|
| 2461 |
+
"loss": 0.0364,
|
| 2462 |
+
"step": 3480
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 2.3438549361987913,
|
| 2466 |
+
"grad_norm": 0.6396084427833557,
|
| 2467 |
+
"learning_rate": 1.232669523569448e-05,
|
| 2468 |
+
"loss": 0.0335,
|
| 2469 |
+
"step": 3490
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 2.3505708529214235,
|
| 2473 |
+
"grad_norm": 0.002272074343636632,
|
| 2474 |
+
"learning_rate": 1.2200655407108646e-05,
|
| 2475 |
+
"loss": 0.0348,
|
| 2476 |
+
"step": 3500
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 2.3572867696440563,
|
| 2480 |
+
"grad_norm": 0.36031338572502136,
|
| 2481 |
+
"learning_rate": 1.2074615578522812e-05,
|
| 2482 |
+
"loss": 0.0211,
|
| 2483 |
+
"step": 3510
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 2.364002686366689,
|
| 2487 |
+
"grad_norm": 1.6808172464370728,
|
| 2488 |
+
"learning_rate": 1.194857574993698e-05,
|
| 2489 |
+
"loss": 0.0838,
|
| 2490 |
+
"step": 3520
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 2.3707186030893217,
|
| 2494 |
+
"grad_norm": 0.00011936118971789256,
|
| 2495 |
+
"learning_rate": 1.1822535921351149e-05,
|
| 2496 |
+
"loss": 0.0281,
|
| 2497 |
+
"step": 3530
|
| 2498 |
+
},
|
| 2499 |
+
{
|
| 2500 |
+
"epoch": 2.3774345198119544,
|
| 2501 |
+
"grad_norm": 0.0034045290667563677,
|
| 2502 |
+
"learning_rate": 1.1696496092765315e-05,
|
| 2503 |
+
"loss": 0.0384,
|
| 2504 |
+
"step": 3540
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 2.384150436534587,
|
| 2508 |
+
"grad_norm": 3.1306815799325705e-05,
|
| 2509 |
+
"learning_rate": 1.1570456264179481e-05,
|
| 2510 |
+
"loss": 0.026,
|
| 2511 |
+
"step": 3550
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 2.39086635325722,
|
| 2515 |
+
"grad_norm": 0.03722585365176201,
|
| 2516 |
+
"learning_rate": 1.1444416435593648e-05,
|
| 2517 |
+
"loss": 0.055,
|
| 2518 |
+
"step": 3560
|
| 2519 |
+
},
|
| 2520 |
+
{
|
| 2521 |
+
"epoch": 2.397582269979852,
|
| 2522 |
+
"grad_norm": 0.00011495844955788925,
|
| 2523 |
+
"learning_rate": 1.1318376607007814e-05,
|
| 2524 |
+
"loss": 0.0821,
|
| 2525 |
+
"step": 3570
|
| 2526 |
+
},
|
| 2527 |
+
{
|
| 2528 |
+
"epoch": 2.404298186702485,
|
| 2529 |
+
"grad_norm": 0.21863265335559845,
|
| 2530 |
+
"learning_rate": 1.1192336778421982e-05,
|
| 2531 |
+
"loss": 0.0207,
|
| 2532 |
+
"step": 3580
|
| 2533 |
+
},
|
| 2534 |
+
{
|
| 2535 |
+
"epoch": 2.4110141034251176,
|
| 2536 |
+
"grad_norm": 0.3169233798980713,
|
| 2537 |
+
"learning_rate": 1.1066296949836149e-05,
|
| 2538 |
+
"loss": 0.0398,
|
| 2539 |
+
"step": 3590
|
| 2540 |
+
},
|
| 2541 |
+
{
|
| 2542 |
+
"epoch": 2.4177300201477503,
|
| 2543 |
+
"grad_norm": 0.39215508103370667,
|
| 2544 |
+
"learning_rate": 1.0940257121250315e-05,
|
| 2545 |
+
"loss": 0.0436,
|
| 2546 |
+
"step": 3600
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 2.4244459368703826,
|
| 2550 |
+
"grad_norm": 0.9112158417701721,
|
| 2551 |
+
"learning_rate": 1.0814217292664483e-05,
|
| 2552 |
+
"loss": 0.059,
|
| 2553 |
+
"step": 3610
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 2.4311618535930153,
|
| 2557 |
+
"grad_norm": 0.2396714836359024,
|
| 2558 |
+
"learning_rate": 1.068817746407865e-05,
|
| 2559 |
+
"loss": 0.1052,
|
| 2560 |
+
"step": 3620
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 2.437877770315648,
|
| 2564 |
+
"grad_norm": 0.48746079206466675,
|
| 2565 |
+
"learning_rate": 1.0562137635492816e-05,
|
| 2566 |
+
"loss": 0.1301,
|
| 2567 |
+
"step": 3630
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 2.4445936870382807,
|
| 2571 |
+
"grad_norm": 0.2512687146663666,
|
| 2572 |
+
"learning_rate": 1.0436097806906982e-05,
|
| 2573 |
+
"loss": 0.0395,
|
| 2574 |
+
"step": 3640
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 2.4513096037609134,
|
| 2578 |
+
"grad_norm": 0.0035686984192579985,
|
| 2579 |
+
"learning_rate": 1.031005797832115e-05,
|
| 2580 |
+
"loss": 0.0353,
|
| 2581 |
+
"step": 3650
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 2.458025520483546,
|
| 2585 |
+
"grad_norm": 0.5211601257324219,
|
| 2586 |
+
"learning_rate": 1.0184018149735317e-05,
|
| 2587 |
+
"loss": 0.0351,
|
| 2588 |
+
"step": 3660
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 2.464741437206179,
|
| 2592 |
+
"grad_norm": 0.0005140244611538947,
|
| 2593 |
+
"learning_rate": 1.0057978321149483e-05,
|
| 2594 |
+
"loss": 0.024,
|
| 2595 |
+
"step": 3670
|
| 2596 |
+
},
|
| 2597 |
+
{
|
| 2598 |
+
"epoch": 2.471457353928811,
|
| 2599 |
+
"grad_norm": 0.6637148261070251,
|
| 2600 |
+
"learning_rate": 9.93193849256365e-06,
|
| 2601 |
+
"loss": 0.0451,
|
| 2602 |
+
"step": 3680
|
| 2603 |
+
},
|
| 2604 |
+
{
|
| 2605 |
+
"epoch": 2.478173270651444,
|
| 2606 |
+
"grad_norm": 1.191238522529602,
|
| 2607 |
+
"learning_rate": 9.805898663977818e-06,
|
| 2608 |
+
"loss": 0.0392,
|
| 2609 |
+
"step": 3690
|
| 2610 |
+
},
|
| 2611 |
+
{
|
| 2612 |
+
"epoch": 2.4848891873740766,
|
| 2613 |
+
"grad_norm": 0.48035892844200134,
|
| 2614 |
+
"learning_rate": 9.679858835391984e-06,
|
| 2615 |
+
"loss": 0.071,
|
| 2616 |
+
"step": 3700
|
| 2617 |
+
},
|
| 2618 |
+
{
|
| 2619 |
+
"epoch": 2.4916051040967093,
|
| 2620 |
+
"grad_norm": 0.0007876435411162674,
|
| 2621 |
+
"learning_rate": 9.553819006806152e-06,
|
| 2622 |
+
"loss": 0.0841,
|
| 2623 |
+
"step": 3710
|
| 2624 |
+
},
|
| 2625 |
+
{
|
| 2626 |
+
"epoch": 2.4983210208193416,
|
| 2627 |
+
"grad_norm": 7.469072341918945,
|
| 2628 |
+
"learning_rate": 9.427779178220319e-06,
|
| 2629 |
+
"loss": 0.0629,
|
| 2630 |
+
"step": 3720
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 2.5050369375419743,
|
| 2634 |
+
"grad_norm": 0.004849706310778856,
|
| 2635 |
+
"learning_rate": 9.301739349634485e-06,
|
| 2636 |
+
"loss": 0.0444,
|
| 2637 |
+
"step": 3730
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 2.511752854264607,
|
| 2641 |
+
"grad_norm": 0.26340028643608093,
|
| 2642 |
+
"learning_rate": 9.175699521048651e-06,
|
| 2643 |
+
"loss": 0.0256,
|
| 2644 |
+
"step": 3740
|
| 2645 |
+
},
|
| 2646 |
+
{
|
| 2647 |
+
"epoch": 2.5184687709872398,
|
| 2648 |
+
"grad_norm": 0.5283430218696594,
|
| 2649 |
+
"learning_rate": 9.049659692462818e-06,
|
| 2650 |
+
"loss": 0.0177,
|
| 2651 |
+
"step": 3750
|
| 2652 |
+
},
|
| 2653 |
+
{
|
| 2654 |
+
"epoch": 2.5251846877098725,
|
| 2655 |
+
"grad_norm": 2.114301605615765e-05,
|
| 2656 |
+
"learning_rate": 8.923619863876984e-06,
|
| 2657 |
+
"loss": 0.0215,
|
| 2658 |
+
"step": 3760
|
| 2659 |
+
},
|
| 2660 |
+
{
|
| 2661 |
+
"epoch": 2.531900604432505,
|
| 2662 |
+
"grad_norm": 0.432597279548645,
|
| 2663 |
+
"learning_rate": 8.797580035291152e-06,
|
| 2664 |
+
"loss": 0.0784,
|
| 2665 |
+
"step": 3770
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 2.538616521155138,
|
| 2669 |
+
"grad_norm": 0.00014320577611215413,
|
| 2670 |
+
"learning_rate": 8.67154020670532e-06,
|
| 2671 |
+
"loss": 0.0582,
|
| 2672 |
+
"step": 3780
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 2.54533243787777,
|
| 2676 |
+
"grad_norm": 0.00046885263873264194,
|
| 2677 |
+
"learning_rate": 8.545500378119487e-06,
|
| 2678 |
+
"loss": 0.0253,
|
| 2679 |
+
"step": 3790
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 2.552048354600403,
|
| 2683 |
+
"grad_norm": 0.0021923587191849947,
|
| 2684 |
+
"learning_rate": 8.419460549533653e-06,
|
| 2685 |
+
"loss": 0.0598,
|
| 2686 |
+
"step": 3800
|
| 2687 |
+
},
|
| 2688 |
+
{
|
| 2689 |
+
"epoch": 2.5587642713230356,
|
| 2690 |
+
"grad_norm": 0.3422527015209198,
|
| 2691 |
+
"learning_rate": 8.29342072094782e-06,
|
| 2692 |
+
"loss": 0.0442,
|
| 2693 |
+
"step": 3810
|
| 2694 |
+
},
|
| 2695 |
+
{
|
| 2696 |
+
"epoch": 2.5654801880456684,
|
| 2697 |
+
"grad_norm": 0.006465827114880085,
|
| 2698 |
+
"learning_rate": 8.167380892361986e-06,
|
| 2699 |
+
"loss": 0.0194,
|
| 2700 |
+
"step": 3820
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"epoch": 2.5721961047683006,
|
| 2704 |
+
"grad_norm": 9.287328430218622e-05,
|
| 2705 |
+
"learning_rate": 8.041341063776154e-06,
|
| 2706 |
+
"loss": 0.0813,
|
| 2707 |
+
"step": 3830
|
| 2708 |
+
},
|
| 2709 |
+
{
|
| 2710 |
+
"epoch": 2.5789120214909333,
|
| 2711 |
+
"grad_norm": 1.295121669769287,
|
| 2712 |
+
"learning_rate": 7.91530123519032e-06,
|
| 2713 |
+
"loss": 0.0261,
|
| 2714 |
+
"step": 3840
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 2.585627938213566,
|
| 2718 |
+
"grad_norm": 1.8356350660324097,
|
| 2719 |
+
"learning_rate": 7.789261406604489e-06,
|
| 2720 |
+
"loss": 0.0862,
|
| 2721 |
+
"step": 3850
|
| 2722 |
+
},
|
| 2723 |
+
{
|
| 2724 |
+
"epoch": 2.592343854936199,
|
| 2725 |
+
"grad_norm": 0.40983912348747253,
|
| 2726 |
+
"learning_rate": 7.663221578018655e-06,
|
| 2727 |
+
"loss": 0.0302,
|
| 2728 |
+
"step": 3860
|
| 2729 |
+
},
|
| 2730 |
+
{
|
| 2731 |
+
"epoch": 2.5990597716588315,
|
| 2732 |
+
"grad_norm": 0.001640897593460977,
|
| 2733 |
+
"learning_rate": 7.537181749432821e-06,
|
| 2734 |
+
"loss": 0.0264,
|
| 2735 |
+
"step": 3870
|
| 2736 |
+
},
|
| 2737 |
+
{
|
| 2738 |
+
"epoch": 2.6057756883814642,
|
| 2739 |
+
"grad_norm": 2.8107948310207576e-05,
|
| 2740 |
+
"learning_rate": 7.4111419208469886e-06,
|
| 2741 |
+
"loss": 0.0615,
|
| 2742 |
+
"step": 3880
|
| 2743 |
+
},
|
| 2744 |
+
{
|
| 2745 |
+
"epoch": 2.612491605104097,
|
| 2746 |
+
"grad_norm": 3.114527862635441e-05,
|
| 2747 |
+
"learning_rate": 7.285102092261155e-06,
|
| 2748 |
+
"loss": 0.0594,
|
| 2749 |
+
"step": 3890
|
| 2750 |
+
},
|
| 2751 |
+
{
|
| 2752 |
+
"epoch": 2.6192075218267292,
|
| 2753 |
+
"grad_norm": 0.10608917474746704,
|
| 2754 |
+
"learning_rate": 7.159062263675321e-06,
|
| 2755 |
+
"loss": 0.0329,
|
| 2756 |
+
"step": 3900
|
| 2757 |
+
},
|
| 2758 |
+
{
|
| 2759 |
+
"epoch": 2.625923438549362,
|
| 2760 |
+
"grad_norm": 0.0014250510139390826,
|
| 2761 |
+
"learning_rate": 7.033022435089489e-06,
|
| 2762 |
+
"loss": 0.0758,
|
| 2763 |
+
"step": 3910
|
| 2764 |
+
},
|
| 2765 |
+
{
|
| 2766 |
+
"epoch": 2.6326393552719947,
|
| 2767 |
+
"grad_norm": 0.3084910213947296,
|
| 2768 |
+
"learning_rate": 6.906982606503655e-06,
|
| 2769 |
+
"loss": 0.0241,
|
| 2770 |
+
"step": 3920
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 2.6393552719946274,
|
| 2774 |
+
"grad_norm": 2.416365168755874e-05,
|
| 2775 |
+
"learning_rate": 6.780942777917821e-06,
|
| 2776 |
+
"loss": 0.0247,
|
| 2777 |
+
"step": 3930
|
| 2778 |
+
},
|
| 2779 |
+
{
|
| 2780 |
+
"epoch": 2.6460711887172597,
|
| 2781 |
+
"grad_norm": 0.45002567768096924,
|
| 2782 |
+
"learning_rate": 6.6549029493319895e-06,
|
| 2783 |
+
"loss": 0.0558,
|
| 2784 |
+
"step": 3940
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 2.6527871054398924,
|
| 2788 |
+
"grad_norm": 2.132117986679077,
|
| 2789 |
+
"learning_rate": 6.528863120746157e-06,
|
| 2790 |
+
"loss": 0.0902,
|
| 2791 |
+
"step": 3950
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 2.659503022162525,
|
| 2795 |
+
"grad_norm": 0.6513732075691223,
|
| 2796 |
+
"learning_rate": 6.402823292160323e-06,
|
| 2797 |
+
"loss": 0.0566,
|
| 2798 |
+
"step": 3960
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 2.666218938885158,
|
| 2802 |
+
"grad_norm": 0.0017292428528890014,
|
| 2803 |
+
"learning_rate": 6.2767834635744895e-06,
|
| 2804 |
+
"loss": 0.0324,
|
| 2805 |
+
"step": 3970
|
| 2806 |
+
},
|
| 2807 |
+
{
|
| 2808 |
+
"epoch": 2.6729348556077905,
|
| 2809 |
+
"grad_norm": 0.3677961826324463,
|
| 2810 |
+
"learning_rate": 6.150743634988657e-06,
|
| 2811 |
+
"loss": 0.0529,
|
| 2812 |
+
"step": 3980
|
| 2813 |
+
},
|
| 2814 |
+
{
|
| 2815 |
+
"epoch": 2.6796507723304233,
|
| 2816 |
+
"grad_norm": 0.43927228450775146,
|
| 2817 |
+
"learning_rate": 6.024703806402823e-06,
|
| 2818 |
+
"loss": 0.0385,
|
| 2819 |
+
"step": 3990
|
| 2820 |
+
},
|
| 2821 |
+
{
|
| 2822 |
+
"epoch": 2.686366689053056,
|
| 2823 |
+
"grad_norm": 0.47322943806648254,
|
| 2824 |
+
"learning_rate": 5.89866397781699e-06,
|
| 2825 |
+
"loss": 0.0735,
|
| 2826 |
+
"step": 4000
|
| 2827 |
+
},
|
| 2828 |
+
{
|
| 2829 |
+
"epoch": 2.6930826057756883,
|
| 2830 |
+
"grad_norm": 0.00010313421807950363,
|
| 2831 |
+
"learning_rate": 5.772624149231158e-06,
|
| 2832 |
+
"loss": 0.062,
|
| 2833 |
+
"step": 4010
|
| 2834 |
+
},
|
| 2835 |
+
{
|
| 2836 |
+
"epoch": 2.699798522498321,
|
| 2837 |
+
"grad_norm": 2.2094976902008057,
|
| 2838 |
+
"learning_rate": 5.646584320645324e-06,
|
| 2839 |
+
"loss": 0.0495,
|
| 2840 |
+
"step": 4020
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"epoch": 2.7065144392209537,
|
| 2844 |
+
"grad_norm": 5.995333776809275e-05,
|
| 2845 |
+
"learning_rate": 5.5205444920594905e-06,
|
| 2846 |
+
"loss": 0.0336,
|
| 2847 |
+
"step": 4030
|
| 2848 |
+
},
|
| 2849 |
+
{
|
| 2850 |
+
"epoch": 2.7132303559435864,
|
| 2851 |
+
"grad_norm": 0.1308954805135727,
|
| 2852 |
+
"learning_rate": 5.3945046634736586e-06,
|
| 2853 |
+
"loss": 0.0457,
|
| 2854 |
+
"step": 4040
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 2.7199462726662187,
|
| 2858 |
+
"grad_norm": 0.10739518702030182,
|
| 2859 |
+
"learning_rate": 5.268464834887825e-06,
|
| 2860 |
+
"loss": 0.0205,
|
| 2861 |
+
"step": 4050
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 2.7266621893888514,
|
| 2865 |
+
"grad_norm": 0.45175987482070923,
|
| 2866 |
+
"learning_rate": 5.142425006301991e-06,
|
| 2867 |
+
"loss": 0.0293,
|
| 2868 |
+
"step": 4060
|
| 2869 |
+
},
|
| 2870 |
+
{
|
| 2871 |
+
"epoch": 2.733378106111484,
|
| 2872 |
+
"grad_norm": 0.4527464210987091,
|
| 2873 |
+
"learning_rate": 5.016385177716159e-06,
|
| 2874 |
+
"loss": 0.049,
|
| 2875 |
+
"step": 4070
|
| 2876 |
+
},
|
| 2877 |
+
{
|
| 2878 |
+
"epoch": 2.740094022834117,
|
| 2879 |
+
"grad_norm": 0.9216799736022949,
|
| 2880 |
+
"learning_rate": 4.890345349130326e-06,
|
| 2881 |
+
"loss": 0.0472,
|
| 2882 |
+
"step": 4080
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 2.7468099395567496,
|
| 2886 |
+
"grad_norm": 0.4577857553958893,
|
| 2887 |
+
"learning_rate": 4.764305520544492e-06,
|
| 2888 |
+
"loss": 0.0317,
|
| 2889 |
+
"step": 4090
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 2.7535258562793823,
|
| 2893 |
+
"grad_norm": 0.2905367910861969,
|
| 2894 |
+
"learning_rate": 4.6382656919586595e-06,
|
| 2895 |
+
"loss": 0.0304,
|
| 2896 |
+
"step": 4100
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 2.760241773002015,
|
| 2900 |
+
"grad_norm": 2.5396127700805664,
|
| 2901 |
+
"learning_rate": 4.512225863372826e-06,
|
| 2902 |
+
"loss": 0.0583,
|
| 2903 |
+
"step": 4110
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 2.7669576897246473,
|
| 2907 |
+
"grad_norm": 0.0009265750413760543,
|
| 2908 |
+
"learning_rate": 4.386186034786993e-06,
|
| 2909 |
+
"loss": 0.0323,
|
| 2910 |
+
"step": 4120
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"epoch": 2.77367360644728,
|
| 2914 |
+
"grad_norm": 0.8636244535446167,
|
| 2915 |
+
"learning_rate": 4.2601462062011595e-06,
|
| 2916 |
+
"loss": 0.074,
|
| 2917 |
+
"step": 4130
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 2.7803895231699127,
|
| 2921 |
+
"grad_norm": 0.0012430851347744465,
|
| 2922 |
+
"learning_rate": 4.134106377615327e-06,
|
| 2923 |
+
"loss": 0.03,
|
| 2924 |
+
"step": 4140
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 2.7871054398925454,
|
| 2928 |
+
"grad_norm": 0.567550778388977,
|
| 2929 |
+
"learning_rate": 4.008066549029493e-06,
|
| 2930 |
+
"loss": 0.0888,
|
| 2931 |
+
"step": 4150
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 2.7938213566151777,
|
| 2935 |
+
"grad_norm": 0.0012551085092127323,
|
| 2936 |
+
"learning_rate": 3.88202672044366e-06,
|
| 2937 |
+
"loss": 0.078,
|
| 2938 |
+
"step": 4160
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 2.8005372733378104,
|
| 2942 |
+
"grad_norm": 0.6136677265167236,
|
| 2943 |
+
"learning_rate": 3.7559868918578272e-06,
|
| 2944 |
+
"loss": 0.0619,
|
| 2945 |
+
"step": 4170
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 2.807253190060443,
|
| 2949 |
+
"grad_norm": 0.34767717123031616,
|
| 2950 |
+
"learning_rate": 3.629947063271994e-06,
|
| 2951 |
+
"loss": 0.0572,
|
| 2952 |
+
"step": 4180
|
| 2953 |
+
},
|
| 2954 |
+
{
|
| 2955 |
+
"epoch": 2.813969106783076,
|
| 2956 |
+
"grad_norm": 0.26787152886390686,
|
| 2957 |
+
"learning_rate": 3.503907234686161e-06,
|
| 2958 |
+
"loss": 0.0449,
|
| 2959 |
+
"step": 4190
|
| 2960 |
+
},
|
| 2961 |
+
{
|
| 2962 |
+
"epoch": 2.8206850235057086,
|
| 2963 |
+
"grad_norm": 0.8297312259674072,
|
| 2964 |
+
"learning_rate": 3.377867406100328e-06,
|
| 2965 |
+
"loss": 0.0545,
|
| 2966 |
+
"step": 4200
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 2.8274009402283413,
|
| 2970 |
+
"grad_norm": 8.094152144622058e-05,
|
| 2971 |
+
"learning_rate": 3.251827577514495e-06,
|
| 2972 |
+
"loss": 0.0491,
|
| 2973 |
+
"step": 4210
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 2.834116856950974,
|
| 2977 |
+
"grad_norm": 2.410463571548462,
|
| 2978 |
+
"learning_rate": 3.1257877489286617e-06,
|
| 2979 |
+
"loss": 0.0564,
|
| 2980 |
+
"step": 4220
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 2.8408327736736063,
|
| 2984 |
+
"grad_norm": 0.9952247142791748,
|
| 2985 |
+
"learning_rate": 2.999747920342828e-06,
|
| 2986 |
+
"loss": 0.0714,
|
| 2987 |
+
"step": 4230
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 2.847548690396239,
|
| 2991 |
+
"grad_norm": 0.4516734480857849,
|
| 2992 |
+
"learning_rate": 2.8737080917569954e-06,
|
| 2993 |
+
"loss": 0.047,
|
| 2994 |
+
"step": 4240
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 2.8542646071188718,
|
| 2998 |
+
"grad_norm": 0.3798590898513794,
|
| 2999 |
+
"learning_rate": 2.747668263171162e-06,
|
| 3000 |
+
"loss": 0.0654,
|
| 3001 |
+
"step": 4250
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 2.8609805238415045,
|
| 3005 |
+
"grad_norm": 1.9686492681503296,
|
| 3006 |
+
"learning_rate": 2.621628434585329e-06,
|
| 3007 |
+
"loss": 0.0626,
|
| 3008 |
+
"step": 4260
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 2.8676964405641368,
|
| 3012 |
+
"grad_norm": 0.4292641580104828,
|
| 3013 |
+
"learning_rate": 2.495588605999496e-06,
|
| 3014 |
+
"loss": 0.0485,
|
| 3015 |
+
"step": 4270
|
| 3016 |
+
},
|
| 3017 |
+
{
|
| 3018 |
+
"epoch": 2.8744123572867695,
|
| 3019 |
+
"grad_norm": 5.976020111120306e-05,
|
| 3020 |
+
"learning_rate": 2.3695487774136627e-06,
|
| 3021 |
+
"loss": 0.0338,
|
| 3022 |
+
"step": 4280
|
| 3023 |
+
},
|
| 3024 |
+
{
|
| 3025 |
+
"epoch": 2.881128274009402,
|
| 3026 |
+
"grad_norm": 0.027319636195898056,
|
| 3027 |
+
"learning_rate": 2.2435089488278295e-06,
|
| 3028 |
+
"loss": 0.0465,
|
| 3029 |
+
"step": 4290
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 2.887844190732035,
|
| 3033 |
+
"grad_norm": 0.37028828263282776,
|
| 3034 |
+
"learning_rate": 2.1174691202419967e-06,
|
| 3035 |
+
"loss": 0.0311,
|
| 3036 |
+
"step": 4300
|
| 3037 |
+
},
|
| 3038 |
+
{
|
| 3039 |
+
"epoch": 2.8945601074546676,
|
| 3040 |
+
"grad_norm": 0.44889381527900696,
|
| 3041 |
+
"learning_rate": 1.991429291656163e-06,
|
| 3042 |
+
"loss": 0.0414,
|
| 3043 |
+
"step": 4310
|
| 3044 |
+
},
|
| 3045 |
+
{
|
| 3046 |
+
"epoch": 2.9012760241773004,
|
| 3047 |
+
"grad_norm": 0.5002055168151855,
|
| 3048 |
+
"learning_rate": 1.8653894630703304e-06,
|
| 3049 |
+
"loss": 0.07,
|
| 3050 |
+
"step": 4320
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 2.907991940899933,
|
| 3054 |
+
"grad_norm": 0.003884148085489869,
|
| 3055 |
+
"learning_rate": 1.739349634484497e-06,
|
| 3056 |
+
"loss": 0.0356,
|
| 3057 |
+
"step": 4330
|
| 3058 |
+
},
|
| 3059 |
+
{
|
| 3060 |
+
"epoch": 2.9147078576225653,
|
| 3061 |
+
"grad_norm": 0.35928064584732056,
|
| 3062 |
+
"learning_rate": 1.613309805898664e-06,
|
| 3063 |
+
"loss": 0.0508,
|
| 3064 |
+
"step": 4340
|
| 3065 |
+
},
|
| 3066 |
+
{
|
| 3067 |
+
"epoch": 2.921423774345198,
|
| 3068 |
+
"grad_norm": 1.2552955150604248,
|
| 3069 |
+
"learning_rate": 1.487269977312831e-06,
|
| 3070 |
+
"loss": 0.0427,
|
| 3071 |
+
"step": 4350
|
| 3072 |
+
},
|
| 3073 |
+
{
|
| 3074 |
+
"epoch": 2.928139691067831,
|
| 3075 |
+
"grad_norm": 0.007359993644058704,
|
| 3076 |
+
"learning_rate": 1.3612301487269979e-06,
|
| 3077 |
+
"loss": 0.0253,
|
| 3078 |
+
"step": 4360
|
| 3079 |
+
},
|
| 3080 |
+
{
|
| 3081 |
+
"epoch": 2.9348556077904635,
|
| 3082 |
+
"grad_norm": 1.1389840841293335,
|
| 3083 |
+
"learning_rate": 1.2351903201411647e-06,
|
| 3084 |
+
"loss": 0.0632,
|
| 3085 |
+
"step": 4370
|
| 3086 |
+
},
|
| 3087 |
+
{
|
| 3088 |
+
"epoch": 2.941571524513096,
|
| 3089 |
+
"grad_norm": 0.8267861008644104,
|
| 3090 |
+
"learning_rate": 1.1091504915553315e-06,
|
| 3091 |
+
"loss": 0.0396,
|
| 3092 |
+
"step": 4380
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 2.9482874412357285,
|
| 3096 |
+
"grad_norm": 3.601860284805298,
|
| 3097 |
+
"learning_rate": 9.831106629694983e-07,
|
| 3098 |
+
"loss": 0.0484,
|
| 3099 |
+
"step": 4390
|
| 3100 |
+
},
|
| 3101 |
+
{
|
| 3102 |
+
"epoch": 2.955003357958361,
|
| 3103 |
+
"grad_norm": 0.8058955073356628,
|
| 3104 |
+
"learning_rate": 8.570708343836652e-07,
|
| 3105 |
+
"loss": 0.0346,
|
| 3106 |
+
"step": 4400
|
| 3107 |
+
},
|
| 3108 |
+
{
|
| 3109 |
+
"epoch": 2.961719274680994,
|
| 3110 |
+
"grad_norm": 0.0007326535996980965,
|
| 3111 |
+
"learning_rate": 7.310310057978322e-07,
|
| 3112 |
+
"loss": 0.0317,
|
| 3113 |
+
"step": 4410
|
| 3114 |
+
},
|
| 3115 |
+
{
|
| 3116 |
+
"epoch": 2.9684351914036267,
|
| 3117 |
+
"grad_norm": 0.9190682768821716,
|
| 3118 |
+
"learning_rate": 6.04991177211999e-07,
|
| 3119 |
+
"loss": 0.0232,
|
| 3120 |
+
"step": 4420
|
| 3121 |
+
},
|
| 3122 |
+
{
|
| 3123 |
+
"epoch": 2.9751511081262594,
|
| 3124 |
+
"grad_norm": 0.0039444975554943085,
|
| 3125 |
+
"learning_rate": 4.789513486261659e-07,
|
| 3126 |
+
"loss": 0.0685,
|
| 3127 |
+
"step": 4430
|
| 3128 |
+
},
|
| 3129 |
+
{
|
| 3130 |
+
"epoch": 2.981867024848892,
|
| 3131 |
+
"grad_norm": 0.9105575680732727,
|
| 3132 |
+
"learning_rate": 3.5291152004033275e-07,
|
| 3133 |
+
"loss": 0.0481,
|
| 3134 |
+
"step": 4440
|
| 3135 |
+
},
|
| 3136 |
+
{
|
| 3137 |
+
"epoch": 2.9885829415715244,
|
| 3138 |
+
"grad_norm": 0.0033778748475015163,
|
| 3139 |
+
"learning_rate": 2.2687169145449963e-07,
|
| 3140 |
+
"loss": 0.0524,
|
| 3141 |
+
"step": 4450
|
| 3142 |
+
},
|
| 3143 |
+
{
|
| 3144 |
+
"epoch": 2.995298858294157,
|
| 3145 |
+
"grad_norm": 0.5608463287353516,
|
| 3146 |
+
"learning_rate": 1.008318628686665e-07,
|
| 3147 |
+
"loss": 0.0465,
|
| 3148 |
+
"step": 4460
|
| 3149 |
+
}
|
| 3150 |
+
],
|
| 3151 |
+
"logging_steps": 10,
|
| 3152 |
+
"max_steps": 4467,
|
| 3153 |
+
"num_input_tokens_seen": 0,
|
| 3154 |
+
"num_train_epochs": 3,
|
| 3155 |
+
"save_steps": 500,
|
| 3156 |
+
"stateful_callbacks": {
|
| 3157 |
+
"TrainerControl": {
|
| 3158 |
+
"args": {
|
| 3159 |
+
"should_epoch_stop": false,
|
| 3160 |
+
"should_evaluate": false,
|
| 3161 |
+
"should_log": false,
|
| 3162 |
+
"should_save": true,
|
| 3163 |
+
"should_training_stop": true
|
| 3164 |
+
},
|
| 3165 |
+
"attributes": {}
|
| 3166 |
+
}
|
| 3167 |
+
},
|
| 3168 |
+
"total_flos": 1521654161384448.0,
|
| 3169 |
+
"train_batch_size": 16,
|
| 3170 |
+
"trial_name": null,
|
| 3171 |
+
"trial_params": null
|
| 3172 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df6632f661d869839bc14ef06c696f5dab5d77a3b176911b28248e1701a422a9
|
| 3 |
+
size 5240
|