Upload folder using huggingface_hub
Browse files- pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/chat_template.jinja +5 -0
- pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/config.json +52 -0
- pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/model.safetensors +3 -0
- pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/special_tokens_map.json +46 -0
- pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/tokenizer.json +0 -0
- pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/tokenizer_config.json +2163 -0
- pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/trainer_state.json +2554 -0
- pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/training_args.bin +3 -0
pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/chat_template.jinja
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
|
| 2 |
+
|
| 3 |
+
'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>
|
| 4 |
+
|
| 5 |
+
' }}
|
pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_type": "silu",
|
| 3 |
+
"alibi": false,
|
| 4 |
+
"alibi_bias_max": 8.0,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LLaDAModelRouter"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"attention_layer_norm": false,
|
| 10 |
+
"attention_layer_norm_with_affine": true,
|
| 11 |
+
"bias_for_layer_norm": false,
|
| 12 |
+
"block_group_size": 1,
|
| 13 |
+
"block_type": "llama",
|
| 14 |
+
"bos_token_id": 126080,
|
| 15 |
+
"d_model": 1024,
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"embedding_dropout": 0.0,
|
| 18 |
+
"embedding_size": 126464,
|
| 19 |
+
"eos_token_id": 126081,
|
| 20 |
+
"flash_attention": false,
|
| 21 |
+
"include_bias": false,
|
| 22 |
+
"include_qkv_bias": false,
|
| 23 |
+
"init_cutoff_factor": null,
|
| 24 |
+
"init_device": "meta",
|
| 25 |
+
"init_fn": "mitchell",
|
| 26 |
+
"init_std": 0.02,
|
| 27 |
+
"input_emb_norm": false,
|
| 28 |
+
"layer_norm_type": "rms",
|
| 29 |
+
"layer_norm_with_affine": true,
|
| 30 |
+
"mask_token_id": 126336,
|
| 31 |
+
"max_sequence_length": 4096,
|
| 32 |
+
"mlp_hidden_size": 2048,
|
| 33 |
+
"mlp_ratio": 4,
|
| 34 |
+
"model_type": "lladarouter",
|
| 35 |
+
"multi_query_attention": null,
|
| 36 |
+
"n_experts": 4,
|
| 37 |
+
"n_heads": 16,
|
| 38 |
+
"n_kv_heads": 16,
|
| 39 |
+
"n_layers": 12,
|
| 40 |
+
"pad_token_id": 126081,
|
| 41 |
+
"precision": "amp_bf16",
|
| 42 |
+
"residual_dropout": 0.0,
|
| 43 |
+
"rms_norm_eps": 1e-05,
|
| 44 |
+
"rope": true,
|
| 45 |
+
"rope_full_precision": true,
|
| 46 |
+
"rope_theta": 500000.0,
|
| 47 |
+
"scale_logits": false,
|
| 48 |
+
"transformers_version": "4.57.0",
|
| 49 |
+
"use_cache": false,
|
| 50 |
+
"vocab_size": 126464,
|
| 51 |
+
"weight_tying": false
|
| 52 |
+
}
|
pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:891643bd14b7bdf43d9c14948cf3b55e7600eb4c40effc3f2494c982ddfb9b2c
|
| 3 |
+
size 769727144
|
pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/special_tokens_map.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|expert_cls|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"bos_token": {
|
| 12 |
+
"content": "<|startoftext|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"cls_token": {
|
| 19 |
+
"content": "[CLS]",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"eos_token": {
|
| 26 |
+
"content": "<|endoftext|>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
"mask_token": {
|
| 33 |
+
"content": "<|mdm_mask|>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
},
|
| 39 |
+
"pad_token": {
|
| 40 |
+
"content": "<|endoftext|>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
}
|
| 46 |
+
}
|
pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"126080": {
|
| 6 |
+
"content": "<|startoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"126081": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"126082": {
|
| 22 |
+
"content": "[CLS]",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"126083": {
|
| 30 |
+
"content": "[gMASK]",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"126084": {
|
| 38 |
+
"content": "<|reserved_token_0|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"126085": {
|
| 46 |
+
"content": "<|reserved_token_1|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"126086": {
|
| 54 |
+
"content": "<|reserved_token_2|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"126087": {
|
| 62 |
+
"content": "<|reserved_token_3|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"126088": {
|
| 70 |
+
"content": "<|reserved_token_4|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"126089": {
|
| 78 |
+
"content": "<|reserved_token_5|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"126090": {
|
| 86 |
+
"content": "<|reserved_token_6|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"126091": {
|
| 94 |
+
"content": "<|reserved_token_7|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"126092": {
|
| 102 |
+
"content": "<|reserved_token_8|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"126093": {
|
| 110 |
+
"content": "<|reserved_token_9|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"126094": {
|
| 118 |
+
"content": "<|reserved_token_10|>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"126095": {
|
| 126 |
+
"content": "<|reserved_token_11|>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": true
|
| 132 |
+
},
|
| 133 |
+
"126096": {
|
| 134 |
+
"content": "<|reserved_token_12|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
"126097": {
|
| 142 |
+
"content": "<|reserved_token_13|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": true
|
| 148 |
+
},
|
| 149 |
+
"126098": {
|
| 150 |
+
"content": "<|reserved_token_14|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": true
|
| 156 |
+
},
|
| 157 |
+
"126099": {
|
| 158 |
+
"content": "<|reserved_token_15|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": true
|
| 164 |
+
},
|
| 165 |
+
"126100": {
|
| 166 |
+
"content": "<|reserved_token_16|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
"126101": {
|
| 174 |
+
"content": "<|reserved_token_17|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
},
|
| 181 |
+
"126102": {
|
| 182 |
+
"content": "<|reserved_token_18|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"126103": {
|
| 190 |
+
"content": "<|reserved_token_19|>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"126104": {
|
| 198 |
+
"content": "<|reserved_token_20|>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"126105": {
|
| 206 |
+
"content": "<|reserved_token_21|>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
"126106": {
|
| 214 |
+
"content": "<|reserved_token_22|>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"126107": {
|
| 222 |
+
"content": "<|reserved_token_23|>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"126108": {
|
| 230 |
+
"content": "<|reserved_token_24|>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"126109": {
|
| 238 |
+
"content": "<|reserved_token_25|>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
"126110": {
|
| 246 |
+
"content": "<|reserved_token_26|>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": true
|
| 252 |
+
},
|
| 253 |
+
"126111": {
|
| 254 |
+
"content": "<|reserved_token_27|>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": true
|
| 260 |
+
},
|
| 261 |
+
"126112": {
|
| 262 |
+
"content": "<|reserved_token_28|>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": true
|
| 268 |
+
},
|
| 269 |
+
"126113": {
|
| 270 |
+
"content": "<|reserved_token_29|>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": true
|
| 276 |
+
},
|
| 277 |
+
"126114": {
|
| 278 |
+
"content": "<|reserved_token_30|>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": true
|
| 284 |
+
},
|
| 285 |
+
"126115": {
|
| 286 |
+
"content": "<|reserved_token_31|>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": true
|
| 292 |
+
},
|
| 293 |
+
"126116": {
|
| 294 |
+
"content": "<|reserved_token_32|>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": true
|
| 300 |
+
},
|
| 301 |
+
"126117": {
|
| 302 |
+
"content": "<|reserved_token_33|>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": true
|
| 308 |
+
},
|
| 309 |
+
"126118": {
|
| 310 |
+
"content": "<|reserved_token_34|>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": true
|
| 316 |
+
},
|
| 317 |
+
"126119": {
|
| 318 |
+
"content": "<|reserved_token_35|>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": true
|
| 324 |
+
},
|
| 325 |
+
"126120": {
|
| 326 |
+
"content": "<|reserved_token_36|>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": true
|
| 332 |
+
},
|
| 333 |
+
"126121": {
|
| 334 |
+
"content": "<|reserved_token_37|>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": true
|
| 340 |
+
},
|
| 341 |
+
"126122": {
|
| 342 |
+
"content": "<|reserved_token_38|>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": false,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": true
|
| 348 |
+
},
|
| 349 |
+
"126123": {
|
| 350 |
+
"content": "<|reserved_token_39|>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": true
|
| 356 |
+
},
|
| 357 |
+
"126124": {
|
| 358 |
+
"content": "<|reserved_token_40|>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": true
|
| 364 |
+
},
|
| 365 |
+
"126125": {
|
| 366 |
+
"content": "<|reserved_token_41|>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": true
|
| 372 |
+
},
|
| 373 |
+
"126126": {
|
| 374 |
+
"content": "<|reserved_token_42|>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": true
|
| 380 |
+
},
|
| 381 |
+
"126127": {
|
| 382 |
+
"content": "<|reserved_token_43|>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": true
|
| 388 |
+
},
|
| 389 |
+
"126128": {
|
| 390 |
+
"content": "<|reserved_token_44|>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": true
|
| 396 |
+
},
|
| 397 |
+
"126129": {
|
| 398 |
+
"content": "<|reserved_token_45|>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": true
|
| 404 |
+
},
|
| 405 |
+
"126130": {
|
| 406 |
+
"content": "<|reserved_token_46|>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": true
|
| 412 |
+
},
|
| 413 |
+
"126131": {
|
| 414 |
+
"content": "<|reserved_token_47|>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": true
|
| 420 |
+
},
|
| 421 |
+
"126132": {
|
| 422 |
+
"content": "<|reserved_token_48|>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": true
|
| 428 |
+
},
|
| 429 |
+
"126133": {
|
| 430 |
+
"content": "<|reserved_token_49|>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": true
|
| 436 |
+
},
|
| 437 |
+
"126134": {
|
| 438 |
+
"content": "<|reserved_token_50|>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": true
|
| 444 |
+
},
|
| 445 |
+
"126135": {
|
| 446 |
+
"content": "<|reserved_token_51|>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": true
|
| 452 |
+
},
|
| 453 |
+
"126136": {
|
| 454 |
+
"content": "<|reserved_token_52|>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": true
|
| 460 |
+
},
|
| 461 |
+
"126137": {
|
| 462 |
+
"content": "<|reserved_token_53|>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": true
|
| 468 |
+
},
|
| 469 |
+
"126138": {
|
| 470 |
+
"content": "<|reserved_token_54|>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": false,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": true
|
| 476 |
+
},
|
| 477 |
+
"126139": {
|
| 478 |
+
"content": "<|reserved_token_55|>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": true
|
| 484 |
+
},
|
| 485 |
+
"126140": {
|
| 486 |
+
"content": "<|reserved_token_56|>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": false,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": true
|
| 492 |
+
},
|
| 493 |
+
"126141": {
|
| 494 |
+
"content": "<|reserved_token_57|>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": false,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": true
|
| 500 |
+
},
|
| 501 |
+
"126142": {
|
| 502 |
+
"content": "<|reserved_token_58|>",
|
| 503 |
+
"lstrip": false,
|
| 504 |
+
"normalized": false,
|
| 505 |
+
"rstrip": false,
|
| 506 |
+
"single_word": false,
|
| 507 |
+
"special": true
|
| 508 |
+
},
|
| 509 |
+
"126143": {
|
| 510 |
+
"content": "<|reserved_token_59|>",
|
| 511 |
+
"lstrip": false,
|
| 512 |
+
"normalized": false,
|
| 513 |
+
"rstrip": false,
|
| 514 |
+
"single_word": false,
|
| 515 |
+
"special": true
|
| 516 |
+
},
|
| 517 |
+
"126144": {
|
| 518 |
+
"content": "<|reserved_token_60|>",
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"normalized": false,
|
| 521 |
+
"rstrip": false,
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"special": true
|
| 524 |
+
},
|
| 525 |
+
"126145": {
|
| 526 |
+
"content": "<|reserved_token_61|>",
|
| 527 |
+
"lstrip": false,
|
| 528 |
+
"normalized": false,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"single_word": false,
|
| 531 |
+
"special": true
|
| 532 |
+
},
|
| 533 |
+
"126146": {
|
| 534 |
+
"content": "<|reserved_token_62|>",
|
| 535 |
+
"lstrip": false,
|
| 536 |
+
"normalized": false,
|
| 537 |
+
"rstrip": false,
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"special": true
|
| 540 |
+
},
|
| 541 |
+
"126147": {
|
| 542 |
+
"content": "<|reserved_token_63|>",
|
| 543 |
+
"lstrip": false,
|
| 544 |
+
"normalized": false,
|
| 545 |
+
"rstrip": false,
|
| 546 |
+
"single_word": false,
|
| 547 |
+
"special": true
|
| 548 |
+
},
|
| 549 |
+
"126148": {
|
| 550 |
+
"content": "<|reserved_token_64|>",
|
| 551 |
+
"lstrip": false,
|
| 552 |
+
"normalized": false,
|
| 553 |
+
"rstrip": false,
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"special": true
|
| 556 |
+
},
|
| 557 |
+
"126149": {
|
| 558 |
+
"content": "<|reserved_token_65|>",
|
| 559 |
+
"lstrip": false,
|
| 560 |
+
"normalized": false,
|
| 561 |
+
"rstrip": false,
|
| 562 |
+
"single_word": false,
|
| 563 |
+
"special": true
|
| 564 |
+
},
|
| 565 |
+
"126150": {
|
| 566 |
+
"content": "<|reserved_token_66|>",
|
| 567 |
+
"lstrip": false,
|
| 568 |
+
"normalized": false,
|
| 569 |
+
"rstrip": false,
|
| 570 |
+
"single_word": false,
|
| 571 |
+
"special": true
|
| 572 |
+
},
|
| 573 |
+
"126151": {
|
| 574 |
+
"content": "<|reserved_token_67|>",
|
| 575 |
+
"lstrip": false,
|
| 576 |
+
"normalized": false,
|
| 577 |
+
"rstrip": false,
|
| 578 |
+
"single_word": false,
|
| 579 |
+
"special": true
|
| 580 |
+
},
|
| 581 |
+
"126152": {
|
| 582 |
+
"content": "<|reserved_token_68|>",
|
| 583 |
+
"lstrip": false,
|
| 584 |
+
"normalized": false,
|
| 585 |
+
"rstrip": false,
|
| 586 |
+
"single_word": false,
|
| 587 |
+
"special": true
|
| 588 |
+
},
|
| 589 |
+
"126153": {
|
| 590 |
+
"content": "<|reserved_token_69|>",
|
| 591 |
+
"lstrip": false,
|
| 592 |
+
"normalized": false,
|
| 593 |
+
"rstrip": false,
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"special": true
|
| 596 |
+
},
|
| 597 |
+
"126154": {
|
| 598 |
+
"content": "<|reserved_token_70|>",
|
| 599 |
+
"lstrip": false,
|
| 600 |
+
"normalized": false,
|
| 601 |
+
"rstrip": false,
|
| 602 |
+
"single_word": false,
|
| 603 |
+
"special": true
|
| 604 |
+
},
|
| 605 |
+
"126155": {
|
| 606 |
+
"content": "<|reserved_token_71|>",
|
| 607 |
+
"lstrip": false,
|
| 608 |
+
"normalized": false,
|
| 609 |
+
"rstrip": false,
|
| 610 |
+
"single_word": false,
|
| 611 |
+
"special": true
|
| 612 |
+
},
|
| 613 |
+
"126156": {
|
| 614 |
+
"content": "<|reserved_token_72|>",
|
| 615 |
+
"lstrip": false,
|
| 616 |
+
"normalized": false,
|
| 617 |
+
"rstrip": false,
|
| 618 |
+
"single_word": false,
|
| 619 |
+
"special": true
|
| 620 |
+
},
|
| 621 |
+
"126157": {
|
| 622 |
+
"content": "<|reserved_token_73|>",
|
| 623 |
+
"lstrip": false,
|
| 624 |
+
"normalized": false,
|
| 625 |
+
"rstrip": false,
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"special": true
|
| 628 |
+
},
|
| 629 |
+
"126158": {
|
| 630 |
+
"content": "<|reserved_token_74|>",
|
| 631 |
+
"lstrip": false,
|
| 632 |
+
"normalized": false,
|
| 633 |
+
"rstrip": false,
|
| 634 |
+
"single_word": false,
|
| 635 |
+
"special": true
|
| 636 |
+
},
|
| 637 |
+
"126159": {
|
| 638 |
+
"content": "<|reserved_token_75|>",
|
| 639 |
+
"lstrip": false,
|
| 640 |
+
"normalized": false,
|
| 641 |
+
"rstrip": false,
|
| 642 |
+
"single_word": false,
|
| 643 |
+
"special": true
|
| 644 |
+
},
|
| 645 |
+
"126160": {
|
| 646 |
+
"content": "<|reserved_token_76|>",
|
| 647 |
+
"lstrip": false,
|
| 648 |
+
"normalized": false,
|
| 649 |
+
"rstrip": false,
|
| 650 |
+
"single_word": false,
|
| 651 |
+
"special": true
|
| 652 |
+
},
|
| 653 |
+
"126161": {
|
| 654 |
+
"content": "<|reserved_token_77|>",
|
| 655 |
+
"lstrip": false,
|
| 656 |
+
"normalized": false,
|
| 657 |
+
"rstrip": false,
|
| 658 |
+
"single_word": false,
|
| 659 |
+
"special": true
|
| 660 |
+
},
|
| 661 |
+
"126162": {
|
| 662 |
+
"content": "<|reserved_token_78|>",
|
| 663 |
+
"lstrip": false,
|
| 664 |
+
"normalized": false,
|
| 665 |
+
"rstrip": false,
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"special": true
|
| 668 |
+
},
|
| 669 |
+
"126163": {
|
| 670 |
+
"content": "<|reserved_token_79|>",
|
| 671 |
+
"lstrip": false,
|
| 672 |
+
"normalized": false,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"single_word": false,
|
| 675 |
+
"special": true
|
| 676 |
+
},
|
| 677 |
+
"126164": {
|
| 678 |
+
"content": "<|reserved_token_80|>",
|
| 679 |
+
"lstrip": false,
|
| 680 |
+
"normalized": false,
|
| 681 |
+
"rstrip": false,
|
| 682 |
+
"single_word": false,
|
| 683 |
+
"special": true
|
| 684 |
+
},
|
| 685 |
+
"126165": {
|
| 686 |
+
"content": "<|reserved_token_81|>",
|
| 687 |
+
"lstrip": false,
|
| 688 |
+
"normalized": false,
|
| 689 |
+
"rstrip": false,
|
| 690 |
+
"single_word": false,
|
| 691 |
+
"special": true
|
| 692 |
+
},
|
| 693 |
+
"126166": {
|
| 694 |
+
"content": "<|reserved_token_82|>",
|
| 695 |
+
"lstrip": false,
|
| 696 |
+
"normalized": false,
|
| 697 |
+
"rstrip": false,
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"special": true
|
| 700 |
+
},
|
| 701 |
+
"126167": {
|
| 702 |
+
"content": "<|reserved_token_83|>",
|
| 703 |
+
"lstrip": false,
|
| 704 |
+
"normalized": false,
|
| 705 |
+
"rstrip": false,
|
| 706 |
+
"single_word": false,
|
| 707 |
+
"special": true
|
| 708 |
+
},
|
| 709 |
+
"126168": {
|
| 710 |
+
"content": "<|reserved_token_84|>",
|
| 711 |
+
"lstrip": false,
|
| 712 |
+
"normalized": false,
|
| 713 |
+
"rstrip": false,
|
| 714 |
+
"single_word": false,
|
| 715 |
+
"special": true
|
| 716 |
+
},
|
| 717 |
+
"126169": {
|
| 718 |
+
"content": "<|reserved_token_85|>",
|
| 719 |
+
"lstrip": false,
|
| 720 |
+
"normalized": false,
|
| 721 |
+
"rstrip": false,
|
| 722 |
+
"single_word": false,
|
| 723 |
+
"special": true
|
| 724 |
+
},
|
| 725 |
+
"126170": {
|
| 726 |
+
"content": "<|reserved_token_86|>",
|
| 727 |
+
"lstrip": false,
|
| 728 |
+
"normalized": false,
|
| 729 |
+
"rstrip": false,
|
| 730 |
+
"single_word": false,
|
| 731 |
+
"special": true
|
| 732 |
+
},
|
| 733 |
+
"126171": {
|
| 734 |
+
"content": "<|reserved_token_87|>",
|
| 735 |
+
"lstrip": false,
|
| 736 |
+
"normalized": false,
|
| 737 |
+
"rstrip": false,
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"special": true
|
| 740 |
+
},
|
| 741 |
+
"126172": {
|
| 742 |
+
"content": "<|reserved_token_88|>",
|
| 743 |
+
"lstrip": false,
|
| 744 |
+
"normalized": false,
|
| 745 |
+
"rstrip": false,
|
| 746 |
+
"single_word": false,
|
| 747 |
+
"special": true
|
| 748 |
+
},
|
| 749 |
+
"126173": {
|
| 750 |
+
"content": "<|reserved_token_89|>",
|
| 751 |
+
"lstrip": false,
|
| 752 |
+
"normalized": false,
|
| 753 |
+
"rstrip": false,
|
| 754 |
+
"single_word": false,
|
| 755 |
+
"special": true
|
| 756 |
+
},
|
| 757 |
+
"126174": {
|
| 758 |
+
"content": "<|reserved_token_90|>",
|
| 759 |
+
"lstrip": false,
|
| 760 |
+
"normalized": false,
|
| 761 |
+
"rstrip": false,
|
| 762 |
+
"single_word": false,
|
| 763 |
+
"special": true
|
| 764 |
+
},
|
| 765 |
+
"126175": {
|
| 766 |
+
"content": "<|reserved_token_91|>",
|
| 767 |
+
"lstrip": false,
|
| 768 |
+
"normalized": false,
|
| 769 |
+
"rstrip": false,
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"special": true
|
| 772 |
+
},
|
| 773 |
+
"126176": {
|
| 774 |
+
"content": "<|reserved_token_92|>",
|
| 775 |
+
"lstrip": false,
|
| 776 |
+
"normalized": false,
|
| 777 |
+
"rstrip": false,
|
| 778 |
+
"single_word": false,
|
| 779 |
+
"special": true
|
| 780 |
+
},
|
| 781 |
+
"126177": {
|
| 782 |
+
"content": "<|reserved_token_93|>",
|
| 783 |
+
"lstrip": false,
|
| 784 |
+
"normalized": false,
|
| 785 |
+
"rstrip": false,
|
| 786 |
+
"single_word": false,
|
| 787 |
+
"special": true
|
| 788 |
+
},
|
| 789 |
+
"126178": {
|
| 790 |
+
"content": "<|reserved_token_94|>",
|
| 791 |
+
"lstrip": false,
|
| 792 |
+
"normalized": false,
|
| 793 |
+
"rstrip": false,
|
| 794 |
+
"single_word": false,
|
| 795 |
+
"special": true
|
| 796 |
+
},
|
| 797 |
+
"126179": {
|
| 798 |
+
"content": "<|reserved_token_95|>",
|
| 799 |
+
"lstrip": false,
|
| 800 |
+
"normalized": false,
|
| 801 |
+
"rstrip": false,
|
| 802 |
+
"single_word": false,
|
| 803 |
+
"special": true
|
| 804 |
+
},
|
| 805 |
+
"126180": {
|
| 806 |
+
"content": "<|reserved_token_96|>",
|
| 807 |
+
"lstrip": false,
|
| 808 |
+
"normalized": false,
|
| 809 |
+
"rstrip": false,
|
| 810 |
+
"single_word": false,
|
| 811 |
+
"special": true
|
| 812 |
+
},
|
| 813 |
+
"126181": {
|
| 814 |
+
"content": "<|reserved_token_97|>",
|
| 815 |
+
"lstrip": false,
|
| 816 |
+
"normalized": false,
|
| 817 |
+
"rstrip": false,
|
| 818 |
+
"single_word": false,
|
| 819 |
+
"special": true
|
| 820 |
+
},
|
| 821 |
+
"126182": {
|
| 822 |
+
"content": "<|reserved_token_98|>",
|
| 823 |
+
"lstrip": false,
|
| 824 |
+
"normalized": false,
|
| 825 |
+
"rstrip": false,
|
| 826 |
+
"single_word": false,
|
| 827 |
+
"special": true
|
| 828 |
+
},
|
| 829 |
+
"126183": {
|
| 830 |
+
"content": "<|reserved_token_99|>",
|
| 831 |
+
"lstrip": false,
|
| 832 |
+
"normalized": false,
|
| 833 |
+
"rstrip": false,
|
| 834 |
+
"single_word": false,
|
| 835 |
+
"special": true
|
| 836 |
+
},
|
| 837 |
+
"126184": {
|
| 838 |
+
"content": "<|reserved_token_100|>",
|
| 839 |
+
"lstrip": false,
|
| 840 |
+
"normalized": false,
|
| 841 |
+
"rstrip": false,
|
| 842 |
+
"single_word": false,
|
| 843 |
+
"special": true
|
| 844 |
+
},
|
| 845 |
+
"126185": {
|
| 846 |
+
"content": "<|reserved_token_101|>",
|
| 847 |
+
"lstrip": false,
|
| 848 |
+
"normalized": false,
|
| 849 |
+
"rstrip": false,
|
| 850 |
+
"single_word": false,
|
| 851 |
+
"special": true
|
| 852 |
+
},
|
| 853 |
+
"126186": {
|
| 854 |
+
"content": "<|reserved_token_102|>",
|
| 855 |
+
"lstrip": false,
|
| 856 |
+
"normalized": false,
|
| 857 |
+
"rstrip": false,
|
| 858 |
+
"single_word": false,
|
| 859 |
+
"special": true
|
| 860 |
+
},
|
| 861 |
+
"126187": {
|
| 862 |
+
"content": "<|reserved_token_103|>",
|
| 863 |
+
"lstrip": false,
|
| 864 |
+
"normalized": false,
|
| 865 |
+
"rstrip": false,
|
| 866 |
+
"single_word": false,
|
| 867 |
+
"special": true
|
| 868 |
+
},
|
| 869 |
+
"126188": {
|
| 870 |
+
"content": "<|reserved_token_104|>",
|
| 871 |
+
"lstrip": false,
|
| 872 |
+
"normalized": false,
|
| 873 |
+
"rstrip": false,
|
| 874 |
+
"single_word": false,
|
| 875 |
+
"special": true
|
| 876 |
+
},
|
| 877 |
+
"126189": {
|
| 878 |
+
"content": "<|reserved_token_105|>",
|
| 879 |
+
"lstrip": false,
|
| 880 |
+
"normalized": false,
|
| 881 |
+
"rstrip": false,
|
| 882 |
+
"single_word": false,
|
| 883 |
+
"special": true
|
| 884 |
+
},
|
| 885 |
+
"126190": {
|
| 886 |
+
"content": "<|reserved_token_106|>",
|
| 887 |
+
"lstrip": false,
|
| 888 |
+
"normalized": false,
|
| 889 |
+
"rstrip": false,
|
| 890 |
+
"single_word": false,
|
| 891 |
+
"special": true
|
| 892 |
+
},
|
| 893 |
+
"126191": {
|
| 894 |
+
"content": "<|reserved_token_107|>",
|
| 895 |
+
"lstrip": false,
|
| 896 |
+
"normalized": false,
|
| 897 |
+
"rstrip": false,
|
| 898 |
+
"single_word": false,
|
| 899 |
+
"special": true
|
| 900 |
+
},
|
| 901 |
+
"126192": {
|
| 902 |
+
"content": "<|reserved_token_108|>",
|
| 903 |
+
"lstrip": false,
|
| 904 |
+
"normalized": false,
|
| 905 |
+
"rstrip": false,
|
| 906 |
+
"single_word": false,
|
| 907 |
+
"special": true
|
| 908 |
+
},
|
| 909 |
+
"126193": {
|
| 910 |
+
"content": "<|reserved_token_109|>",
|
| 911 |
+
"lstrip": false,
|
| 912 |
+
"normalized": false,
|
| 913 |
+
"rstrip": false,
|
| 914 |
+
"single_word": false,
|
| 915 |
+
"special": true
|
| 916 |
+
},
|
| 917 |
+
"126194": {
|
| 918 |
+
"content": "<|reserved_token_110|>",
|
| 919 |
+
"lstrip": false,
|
| 920 |
+
"normalized": false,
|
| 921 |
+
"rstrip": false,
|
| 922 |
+
"single_word": false,
|
| 923 |
+
"special": true
|
| 924 |
+
},
|
| 925 |
+
"126195": {
|
| 926 |
+
"content": "<|reserved_token_111|>",
|
| 927 |
+
"lstrip": false,
|
| 928 |
+
"normalized": false,
|
| 929 |
+
"rstrip": false,
|
| 930 |
+
"single_word": false,
|
| 931 |
+
"special": true
|
| 932 |
+
},
|
| 933 |
+
"126196": {
|
| 934 |
+
"content": "<|reserved_token_112|>",
|
| 935 |
+
"lstrip": false,
|
| 936 |
+
"normalized": false,
|
| 937 |
+
"rstrip": false,
|
| 938 |
+
"single_word": false,
|
| 939 |
+
"special": true
|
| 940 |
+
},
|
| 941 |
+
"126197": {
|
| 942 |
+
"content": "<|reserved_token_113|>",
|
| 943 |
+
"lstrip": false,
|
| 944 |
+
"normalized": false,
|
| 945 |
+
"rstrip": false,
|
| 946 |
+
"single_word": false,
|
| 947 |
+
"special": true
|
| 948 |
+
},
|
| 949 |
+
"126198": {
|
| 950 |
+
"content": "<|reserved_token_114|>",
|
| 951 |
+
"lstrip": false,
|
| 952 |
+
"normalized": false,
|
| 953 |
+
"rstrip": false,
|
| 954 |
+
"single_word": false,
|
| 955 |
+
"special": true
|
| 956 |
+
},
|
| 957 |
+
"126199": {
|
| 958 |
+
"content": "<|reserved_token_115|>",
|
| 959 |
+
"lstrip": false,
|
| 960 |
+
"normalized": false,
|
| 961 |
+
"rstrip": false,
|
| 962 |
+
"single_word": false,
|
| 963 |
+
"special": true
|
| 964 |
+
},
|
| 965 |
+
"126200": {
|
| 966 |
+
"content": "<|reserved_token_116|>",
|
| 967 |
+
"lstrip": false,
|
| 968 |
+
"normalized": false,
|
| 969 |
+
"rstrip": false,
|
| 970 |
+
"single_word": false,
|
| 971 |
+
"special": true
|
| 972 |
+
},
|
| 973 |
+
"126201": {
|
| 974 |
+
"content": "<|reserved_token_117|>",
|
| 975 |
+
"lstrip": false,
|
| 976 |
+
"normalized": false,
|
| 977 |
+
"rstrip": false,
|
| 978 |
+
"single_word": false,
|
| 979 |
+
"special": true
|
| 980 |
+
},
|
| 981 |
+
"126202": {
|
| 982 |
+
"content": "<|reserved_token_118|>",
|
| 983 |
+
"lstrip": false,
|
| 984 |
+
"normalized": false,
|
| 985 |
+
"rstrip": false,
|
| 986 |
+
"single_word": false,
|
| 987 |
+
"special": true
|
| 988 |
+
},
|
| 989 |
+
"126203": {
|
| 990 |
+
"content": "<|reserved_token_119|>",
|
| 991 |
+
"lstrip": false,
|
| 992 |
+
"normalized": false,
|
| 993 |
+
"rstrip": false,
|
| 994 |
+
"single_word": false,
|
| 995 |
+
"special": true
|
| 996 |
+
},
|
| 997 |
+
"126204": {
|
| 998 |
+
"content": "<|reserved_token_120|>",
|
| 999 |
+
"lstrip": false,
|
| 1000 |
+
"normalized": false,
|
| 1001 |
+
"rstrip": false,
|
| 1002 |
+
"single_word": false,
|
| 1003 |
+
"special": true
|
| 1004 |
+
},
|
| 1005 |
+
"126205": {
|
| 1006 |
+
"content": "<|reserved_token_121|>",
|
| 1007 |
+
"lstrip": false,
|
| 1008 |
+
"normalized": false,
|
| 1009 |
+
"rstrip": false,
|
| 1010 |
+
"single_word": false,
|
| 1011 |
+
"special": true
|
| 1012 |
+
},
|
| 1013 |
+
"126206": {
|
| 1014 |
+
"content": "<|reserved_token_122|>",
|
| 1015 |
+
"lstrip": false,
|
| 1016 |
+
"normalized": false,
|
| 1017 |
+
"rstrip": false,
|
| 1018 |
+
"single_word": false,
|
| 1019 |
+
"special": true
|
| 1020 |
+
},
|
| 1021 |
+
"126207": {
|
| 1022 |
+
"content": "<|reserved_token_123|>",
|
| 1023 |
+
"lstrip": false,
|
| 1024 |
+
"normalized": false,
|
| 1025 |
+
"rstrip": false,
|
| 1026 |
+
"single_word": false,
|
| 1027 |
+
"special": true
|
| 1028 |
+
},
|
| 1029 |
+
"126208": {
|
| 1030 |
+
"content": "<|reserved_token_124|>",
|
| 1031 |
+
"lstrip": false,
|
| 1032 |
+
"normalized": false,
|
| 1033 |
+
"rstrip": false,
|
| 1034 |
+
"single_word": false,
|
| 1035 |
+
"special": true
|
| 1036 |
+
},
|
| 1037 |
+
"126209": {
|
| 1038 |
+
"content": "<|reserved_token_125|>",
|
| 1039 |
+
"lstrip": false,
|
| 1040 |
+
"normalized": false,
|
| 1041 |
+
"rstrip": false,
|
| 1042 |
+
"single_word": false,
|
| 1043 |
+
"special": true
|
| 1044 |
+
},
|
| 1045 |
+
"126210": {
|
| 1046 |
+
"content": "<|reserved_token_126|>",
|
| 1047 |
+
"lstrip": false,
|
| 1048 |
+
"normalized": false,
|
| 1049 |
+
"rstrip": false,
|
| 1050 |
+
"single_word": false,
|
| 1051 |
+
"special": true
|
| 1052 |
+
},
|
| 1053 |
+
"126211": {
|
| 1054 |
+
"content": "<|reserved_token_127|>",
|
| 1055 |
+
"lstrip": false,
|
| 1056 |
+
"normalized": false,
|
| 1057 |
+
"rstrip": false,
|
| 1058 |
+
"single_word": false,
|
| 1059 |
+
"special": true
|
| 1060 |
+
},
|
| 1061 |
+
"126212": {
|
| 1062 |
+
"content": "<|reserved_token_128|>",
|
| 1063 |
+
"lstrip": false,
|
| 1064 |
+
"normalized": false,
|
| 1065 |
+
"rstrip": false,
|
| 1066 |
+
"single_word": false,
|
| 1067 |
+
"special": true
|
| 1068 |
+
},
|
| 1069 |
+
"126213": {
|
| 1070 |
+
"content": "<|reserved_token_129|>",
|
| 1071 |
+
"lstrip": false,
|
| 1072 |
+
"normalized": false,
|
| 1073 |
+
"rstrip": false,
|
| 1074 |
+
"single_word": false,
|
| 1075 |
+
"special": true
|
| 1076 |
+
},
|
| 1077 |
+
"126214": {
|
| 1078 |
+
"content": "<|reserved_token_130|>",
|
| 1079 |
+
"lstrip": false,
|
| 1080 |
+
"normalized": false,
|
| 1081 |
+
"rstrip": false,
|
| 1082 |
+
"single_word": false,
|
| 1083 |
+
"special": true
|
| 1084 |
+
},
|
| 1085 |
+
"126215": {
|
| 1086 |
+
"content": "<|reserved_token_131|>",
|
| 1087 |
+
"lstrip": false,
|
| 1088 |
+
"normalized": false,
|
| 1089 |
+
"rstrip": false,
|
| 1090 |
+
"single_word": false,
|
| 1091 |
+
"special": true
|
| 1092 |
+
},
|
| 1093 |
+
"126216": {
|
| 1094 |
+
"content": "<|reserved_token_132|>",
|
| 1095 |
+
"lstrip": false,
|
| 1096 |
+
"normalized": false,
|
| 1097 |
+
"rstrip": false,
|
| 1098 |
+
"single_word": false,
|
| 1099 |
+
"special": true
|
| 1100 |
+
},
|
| 1101 |
+
"126217": {
|
| 1102 |
+
"content": "<|reserved_token_133|>",
|
| 1103 |
+
"lstrip": false,
|
| 1104 |
+
"normalized": false,
|
| 1105 |
+
"rstrip": false,
|
| 1106 |
+
"single_word": false,
|
| 1107 |
+
"special": true
|
| 1108 |
+
},
|
| 1109 |
+
"126218": {
|
| 1110 |
+
"content": "<|reserved_token_134|>",
|
| 1111 |
+
"lstrip": false,
|
| 1112 |
+
"normalized": false,
|
| 1113 |
+
"rstrip": false,
|
| 1114 |
+
"single_word": false,
|
| 1115 |
+
"special": true
|
| 1116 |
+
},
|
| 1117 |
+
"126219": {
|
| 1118 |
+
"content": "<|reserved_token_135|>",
|
| 1119 |
+
"lstrip": false,
|
| 1120 |
+
"normalized": false,
|
| 1121 |
+
"rstrip": false,
|
| 1122 |
+
"single_word": false,
|
| 1123 |
+
"special": true
|
| 1124 |
+
},
|
| 1125 |
+
"126220": {
|
| 1126 |
+
"content": "<|reserved_token_136|>",
|
| 1127 |
+
"lstrip": false,
|
| 1128 |
+
"normalized": false,
|
| 1129 |
+
"rstrip": false,
|
| 1130 |
+
"single_word": false,
|
| 1131 |
+
"special": true
|
| 1132 |
+
},
|
| 1133 |
+
"126221": {
|
| 1134 |
+
"content": "<|reserved_token_137|>",
|
| 1135 |
+
"lstrip": false,
|
| 1136 |
+
"normalized": false,
|
| 1137 |
+
"rstrip": false,
|
| 1138 |
+
"single_word": false,
|
| 1139 |
+
"special": true
|
| 1140 |
+
},
|
| 1141 |
+
"126222": {
|
| 1142 |
+
"content": "<|reserved_token_138|>",
|
| 1143 |
+
"lstrip": false,
|
| 1144 |
+
"normalized": false,
|
| 1145 |
+
"rstrip": false,
|
| 1146 |
+
"single_word": false,
|
| 1147 |
+
"special": true
|
| 1148 |
+
},
|
| 1149 |
+
"126223": {
|
| 1150 |
+
"content": "<|reserved_token_139|>",
|
| 1151 |
+
"lstrip": false,
|
| 1152 |
+
"normalized": false,
|
| 1153 |
+
"rstrip": false,
|
| 1154 |
+
"single_word": false,
|
| 1155 |
+
"special": true
|
| 1156 |
+
},
|
| 1157 |
+
"126224": {
|
| 1158 |
+
"content": "<|reserved_token_140|>",
|
| 1159 |
+
"lstrip": false,
|
| 1160 |
+
"normalized": false,
|
| 1161 |
+
"rstrip": false,
|
| 1162 |
+
"single_word": false,
|
| 1163 |
+
"special": true
|
| 1164 |
+
},
|
| 1165 |
+
"126225": {
|
| 1166 |
+
"content": "<|reserved_token_141|>",
|
| 1167 |
+
"lstrip": false,
|
| 1168 |
+
"normalized": false,
|
| 1169 |
+
"rstrip": false,
|
| 1170 |
+
"single_word": false,
|
| 1171 |
+
"special": true
|
| 1172 |
+
},
|
| 1173 |
+
"126226": {
|
| 1174 |
+
"content": "<|reserved_token_142|>",
|
| 1175 |
+
"lstrip": false,
|
| 1176 |
+
"normalized": false,
|
| 1177 |
+
"rstrip": false,
|
| 1178 |
+
"single_word": false,
|
| 1179 |
+
"special": true
|
| 1180 |
+
},
|
| 1181 |
+
"126227": {
|
| 1182 |
+
"content": "<|reserved_token_143|>",
|
| 1183 |
+
"lstrip": false,
|
| 1184 |
+
"normalized": false,
|
| 1185 |
+
"rstrip": false,
|
| 1186 |
+
"single_word": false,
|
| 1187 |
+
"special": true
|
| 1188 |
+
},
|
| 1189 |
+
"126228": {
|
| 1190 |
+
"content": "<|reserved_token_144|>",
|
| 1191 |
+
"lstrip": false,
|
| 1192 |
+
"normalized": false,
|
| 1193 |
+
"rstrip": false,
|
| 1194 |
+
"single_word": false,
|
| 1195 |
+
"special": true
|
| 1196 |
+
},
|
| 1197 |
+
"126229": {
|
| 1198 |
+
"content": "<|reserved_token_145|>",
|
| 1199 |
+
"lstrip": false,
|
| 1200 |
+
"normalized": false,
|
| 1201 |
+
"rstrip": false,
|
| 1202 |
+
"single_word": false,
|
| 1203 |
+
"special": true
|
| 1204 |
+
},
|
| 1205 |
+
"126230": {
|
| 1206 |
+
"content": "<|reserved_token_146|>",
|
| 1207 |
+
"lstrip": false,
|
| 1208 |
+
"normalized": false,
|
| 1209 |
+
"rstrip": false,
|
| 1210 |
+
"single_word": false,
|
| 1211 |
+
"special": true
|
| 1212 |
+
},
|
| 1213 |
+
"126231": {
|
| 1214 |
+
"content": "<|reserved_token_147|>",
|
| 1215 |
+
"lstrip": false,
|
| 1216 |
+
"normalized": false,
|
| 1217 |
+
"rstrip": false,
|
| 1218 |
+
"single_word": false,
|
| 1219 |
+
"special": true
|
| 1220 |
+
},
|
| 1221 |
+
"126232": {
|
| 1222 |
+
"content": "<|reserved_token_148|>",
|
| 1223 |
+
"lstrip": false,
|
| 1224 |
+
"normalized": false,
|
| 1225 |
+
"rstrip": false,
|
| 1226 |
+
"single_word": false,
|
| 1227 |
+
"special": true
|
| 1228 |
+
},
|
| 1229 |
+
"126233": {
|
| 1230 |
+
"content": "<|reserved_token_149|>",
|
| 1231 |
+
"lstrip": false,
|
| 1232 |
+
"normalized": false,
|
| 1233 |
+
"rstrip": false,
|
| 1234 |
+
"single_word": false,
|
| 1235 |
+
"special": true
|
| 1236 |
+
},
|
| 1237 |
+
"126234": {
|
| 1238 |
+
"content": "<|reserved_token_150|>",
|
| 1239 |
+
"lstrip": false,
|
| 1240 |
+
"normalized": false,
|
| 1241 |
+
"rstrip": false,
|
| 1242 |
+
"single_word": false,
|
| 1243 |
+
"special": true
|
| 1244 |
+
},
|
| 1245 |
+
"126235": {
|
| 1246 |
+
"content": "<|reserved_token_151|>",
|
| 1247 |
+
"lstrip": false,
|
| 1248 |
+
"normalized": false,
|
| 1249 |
+
"rstrip": false,
|
| 1250 |
+
"single_word": false,
|
| 1251 |
+
"special": true
|
| 1252 |
+
},
|
| 1253 |
+
"126236": {
|
| 1254 |
+
"content": "<|reserved_token_152|>",
|
| 1255 |
+
"lstrip": false,
|
| 1256 |
+
"normalized": false,
|
| 1257 |
+
"rstrip": false,
|
| 1258 |
+
"single_word": false,
|
| 1259 |
+
"special": true
|
| 1260 |
+
},
|
| 1261 |
+
"126237": {
|
| 1262 |
+
"content": "<|reserved_token_153|>",
|
| 1263 |
+
"lstrip": false,
|
| 1264 |
+
"normalized": false,
|
| 1265 |
+
"rstrip": false,
|
| 1266 |
+
"single_word": false,
|
| 1267 |
+
"special": true
|
| 1268 |
+
},
|
| 1269 |
+
"126238": {
|
| 1270 |
+
"content": "<|reserved_token_154|>",
|
| 1271 |
+
"lstrip": false,
|
| 1272 |
+
"normalized": false,
|
| 1273 |
+
"rstrip": false,
|
| 1274 |
+
"single_word": false,
|
| 1275 |
+
"special": true
|
| 1276 |
+
},
|
| 1277 |
+
"126239": {
|
| 1278 |
+
"content": "<|reserved_token_155|>",
|
| 1279 |
+
"lstrip": false,
|
| 1280 |
+
"normalized": false,
|
| 1281 |
+
"rstrip": false,
|
| 1282 |
+
"single_word": false,
|
| 1283 |
+
"special": true
|
| 1284 |
+
},
|
| 1285 |
+
"126240": {
|
| 1286 |
+
"content": "<|reserved_token_156|>",
|
| 1287 |
+
"lstrip": false,
|
| 1288 |
+
"normalized": false,
|
| 1289 |
+
"rstrip": false,
|
| 1290 |
+
"single_word": false,
|
| 1291 |
+
"special": true
|
| 1292 |
+
},
|
| 1293 |
+
"126241": {
|
| 1294 |
+
"content": "<|reserved_token_157|>",
|
| 1295 |
+
"lstrip": false,
|
| 1296 |
+
"normalized": false,
|
| 1297 |
+
"rstrip": false,
|
| 1298 |
+
"single_word": false,
|
| 1299 |
+
"special": true
|
| 1300 |
+
},
|
| 1301 |
+
"126242": {
|
| 1302 |
+
"content": "<|reserved_token_158|>",
|
| 1303 |
+
"lstrip": false,
|
| 1304 |
+
"normalized": false,
|
| 1305 |
+
"rstrip": false,
|
| 1306 |
+
"single_word": false,
|
| 1307 |
+
"special": true
|
| 1308 |
+
},
|
| 1309 |
+
"126243": {
|
| 1310 |
+
"content": "<|reserved_token_159|>",
|
| 1311 |
+
"lstrip": false,
|
| 1312 |
+
"normalized": false,
|
| 1313 |
+
"rstrip": false,
|
| 1314 |
+
"single_word": false,
|
| 1315 |
+
"special": true
|
| 1316 |
+
},
|
| 1317 |
+
"126244": {
|
| 1318 |
+
"content": "<|reserved_token_160|>",
|
| 1319 |
+
"lstrip": false,
|
| 1320 |
+
"normalized": false,
|
| 1321 |
+
"rstrip": false,
|
| 1322 |
+
"single_word": false,
|
| 1323 |
+
"special": true
|
| 1324 |
+
},
|
| 1325 |
+
"126245": {
|
| 1326 |
+
"content": "<|reserved_token_161|>",
|
| 1327 |
+
"lstrip": false,
|
| 1328 |
+
"normalized": false,
|
| 1329 |
+
"rstrip": false,
|
| 1330 |
+
"single_word": false,
|
| 1331 |
+
"special": true
|
| 1332 |
+
},
|
| 1333 |
+
"126246": {
|
| 1334 |
+
"content": "<|reserved_token_162|>",
|
| 1335 |
+
"lstrip": false,
|
| 1336 |
+
"normalized": false,
|
| 1337 |
+
"rstrip": false,
|
| 1338 |
+
"single_word": false,
|
| 1339 |
+
"special": true
|
| 1340 |
+
},
|
| 1341 |
+
"126247": {
|
| 1342 |
+
"content": "<|reserved_token_163|>",
|
| 1343 |
+
"lstrip": false,
|
| 1344 |
+
"normalized": false,
|
| 1345 |
+
"rstrip": false,
|
| 1346 |
+
"single_word": false,
|
| 1347 |
+
"special": true
|
| 1348 |
+
},
|
| 1349 |
+
"126248": {
|
| 1350 |
+
"content": "<|reserved_token_164|>",
|
| 1351 |
+
"lstrip": false,
|
| 1352 |
+
"normalized": false,
|
| 1353 |
+
"rstrip": false,
|
| 1354 |
+
"single_word": false,
|
| 1355 |
+
"special": true
|
| 1356 |
+
},
|
| 1357 |
+
"126249": {
|
| 1358 |
+
"content": "<|reserved_token_165|>",
|
| 1359 |
+
"lstrip": false,
|
| 1360 |
+
"normalized": false,
|
| 1361 |
+
"rstrip": false,
|
| 1362 |
+
"single_word": false,
|
| 1363 |
+
"special": true
|
| 1364 |
+
},
|
| 1365 |
+
"126250": {
|
| 1366 |
+
"content": "<|reserved_token_166|>",
|
| 1367 |
+
"lstrip": false,
|
| 1368 |
+
"normalized": false,
|
| 1369 |
+
"rstrip": false,
|
| 1370 |
+
"single_word": false,
|
| 1371 |
+
"special": true
|
| 1372 |
+
},
|
| 1373 |
+
"126251": {
|
| 1374 |
+
"content": "<|reserved_token_167|>",
|
| 1375 |
+
"lstrip": false,
|
| 1376 |
+
"normalized": false,
|
| 1377 |
+
"rstrip": false,
|
| 1378 |
+
"single_word": false,
|
| 1379 |
+
"special": true
|
| 1380 |
+
},
|
| 1381 |
+
"126252": {
|
| 1382 |
+
"content": "<|reserved_token_168|>",
|
| 1383 |
+
"lstrip": false,
|
| 1384 |
+
"normalized": false,
|
| 1385 |
+
"rstrip": false,
|
| 1386 |
+
"single_word": false,
|
| 1387 |
+
"special": true
|
| 1388 |
+
},
|
| 1389 |
+
"126253": {
|
| 1390 |
+
"content": "<|reserved_token_169|>",
|
| 1391 |
+
"lstrip": false,
|
| 1392 |
+
"normalized": false,
|
| 1393 |
+
"rstrip": false,
|
| 1394 |
+
"single_word": false,
|
| 1395 |
+
"special": true
|
| 1396 |
+
},
|
| 1397 |
+
"126254": {
|
| 1398 |
+
"content": "<|reserved_token_170|>",
|
| 1399 |
+
"lstrip": false,
|
| 1400 |
+
"normalized": false,
|
| 1401 |
+
"rstrip": false,
|
| 1402 |
+
"single_word": false,
|
| 1403 |
+
"special": true
|
| 1404 |
+
},
|
| 1405 |
+
"126255": {
|
| 1406 |
+
"content": "<|reserved_token_171|>",
|
| 1407 |
+
"lstrip": false,
|
| 1408 |
+
"normalized": false,
|
| 1409 |
+
"rstrip": false,
|
| 1410 |
+
"single_word": false,
|
| 1411 |
+
"special": true
|
| 1412 |
+
},
|
| 1413 |
+
"126256": {
|
| 1414 |
+
"content": "<|reserved_token_172|>",
|
| 1415 |
+
"lstrip": false,
|
| 1416 |
+
"normalized": false,
|
| 1417 |
+
"rstrip": false,
|
| 1418 |
+
"single_word": false,
|
| 1419 |
+
"special": true
|
| 1420 |
+
},
|
| 1421 |
+
"126257": {
|
| 1422 |
+
"content": "<|reserved_token_173|>",
|
| 1423 |
+
"lstrip": false,
|
| 1424 |
+
"normalized": false,
|
| 1425 |
+
"rstrip": false,
|
| 1426 |
+
"single_word": false,
|
| 1427 |
+
"special": true
|
| 1428 |
+
},
|
| 1429 |
+
"126258": {
|
| 1430 |
+
"content": "<|reserved_token_174|>",
|
| 1431 |
+
"lstrip": false,
|
| 1432 |
+
"normalized": false,
|
| 1433 |
+
"rstrip": false,
|
| 1434 |
+
"single_word": false,
|
| 1435 |
+
"special": true
|
| 1436 |
+
},
|
| 1437 |
+
"126259": {
|
| 1438 |
+
"content": "<|reserved_token_175|>",
|
| 1439 |
+
"lstrip": false,
|
| 1440 |
+
"normalized": false,
|
| 1441 |
+
"rstrip": false,
|
| 1442 |
+
"single_word": false,
|
| 1443 |
+
"special": true
|
| 1444 |
+
},
|
| 1445 |
+
"126260": {
|
| 1446 |
+
"content": "<|reserved_token_176|>",
|
| 1447 |
+
"lstrip": false,
|
| 1448 |
+
"normalized": false,
|
| 1449 |
+
"rstrip": false,
|
| 1450 |
+
"single_word": false,
|
| 1451 |
+
"special": true
|
| 1452 |
+
},
|
| 1453 |
+
"126261": {
|
| 1454 |
+
"content": "<|reserved_token_177|>",
|
| 1455 |
+
"lstrip": false,
|
| 1456 |
+
"normalized": false,
|
| 1457 |
+
"rstrip": false,
|
| 1458 |
+
"single_word": false,
|
| 1459 |
+
"special": true
|
| 1460 |
+
},
|
| 1461 |
+
"126262": {
|
| 1462 |
+
"content": "<|reserved_token_178|>",
|
| 1463 |
+
"lstrip": false,
|
| 1464 |
+
"normalized": false,
|
| 1465 |
+
"rstrip": false,
|
| 1466 |
+
"single_word": false,
|
| 1467 |
+
"special": true
|
| 1468 |
+
},
|
| 1469 |
+
"126263": {
|
| 1470 |
+
"content": "<|reserved_token_179|>",
|
| 1471 |
+
"lstrip": false,
|
| 1472 |
+
"normalized": false,
|
| 1473 |
+
"rstrip": false,
|
| 1474 |
+
"single_word": false,
|
| 1475 |
+
"special": true
|
| 1476 |
+
},
|
| 1477 |
+
"126264": {
|
| 1478 |
+
"content": "<|reserved_token_180|>",
|
| 1479 |
+
"lstrip": false,
|
| 1480 |
+
"normalized": false,
|
| 1481 |
+
"rstrip": false,
|
| 1482 |
+
"single_word": false,
|
| 1483 |
+
"special": true
|
| 1484 |
+
},
|
| 1485 |
+
"126265": {
|
| 1486 |
+
"content": "<|reserved_token_181|>",
|
| 1487 |
+
"lstrip": false,
|
| 1488 |
+
"normalized": false,
|
| 1489 |
+
"rstrip": false,
|
| 1490 |
+
"single_word": false,
|
| 1491 |
+
"special": true
|
| 1492 |
+
},
|
| 1493 |
+
"126266": {
|
| 1494 |
+
"content": "<|reserved_token_182|>",
|
| 1495 |
+
"lstrip": false,
|
| 1496 |
+
"normalized": false,
|
| 1497 |
+
"rstrip": false,
|
| 1498 |
+
"single_word": false,
|
| 1499 |
+
"special": true
|
| 1500 |
+
},
|
| 1501 |
+
"126267": {
|
| 1502 |
+
"content": "<|reserved_token_183|>",
|
| 1503 |
+
"lstrip": false,
|
| 1504 |
+
"normalized": false,
|
| 1505 |
+
"rstrip": false,
|
| 1506 |
+
"single_word": false,
|
| 1507 |
+
"special": true
|
| 1508 |
+
},
|
| 1509 |
+
"126268": {
|
| 1510 |
+
"content": "<|reserved_token_184|>",
|
| 1511 |
+
"lstrip": false,
|
| 1512 |
+
"normalized": false,
|
| 1513 |
+
"rstrip": false,
|
| 1514 |
+
"single_word": false,
|
| 1515 |
+
"special": true
|
| 1516 |
+
},
|
| 1517 |
+
"126269": {
|
| 1518 |
+
"content": "<|reserved_token_185|>",
|
| 1519 |
+
"lstrip": false,
|
| 1520 |
+
"normalized": false,
|
| 1521 |
+
"rstrip": false,
|
| 1522 |
+
"single_word": false,
|
| 1523 |
+
"special": true
|
| 1524 |
+
},
|
| 1525 |
+
"126270": {
|
| 1526 |
+
"content": "<|reserved_token_186|>",
|
| 1527 |
+
"lstrip": false,
|
| 1528 |
+
"normalized": false,
|
| 1529 |
+
"rstrip": false,
|
| 1530 |
+
"single_word": false,
|
| 1531 |
+
"special": true
|
| 1532 |
+
},
|
| 1533 |
+
"126271": {
|
| 1534 |
+
"content": "<|reserved_token_187|>",
|
| 1535 |
+
"lstrip": false,
|
| 1536 |
+
"normalized": false,
|
| 1537 |
+
"rstrip": false,
|
| 1538 |
+
"single_word": false,
|
| 1539 |
+
"special": true
|
| 1540 |
+
},
|
| 1541 |
+
"126272": {
|
| 1542 |
+
"content": "<|reserved_token_188|>",
|
| 1543 |
+
"lstrip": false,
|
| 1544 |
+
"normalized": false,
|
| 1545 |
+
"rstrip": false,
|
| 1546 |
+
"single_word": false,
|
| 1547 |
+
"special": true
|
| 1548 |
+
},
|
| 1549 |
+
"126273": {
|
| 1550 |
+
"content": "<|reserved_token_189|>",
|
| 1551 |
+
"lstrip": false,
|
| 1552 |
+
"normalized": false,
|
| 1553 |
+
"rstrip": false,
|
| 1554 |
+
"single_word": false,
|
| 1555 |
+
"special": true
|
| 1556 |
+
},
|
| 1557 |
+
"126274": {
|
| 1558 |
+
"content": "<|reserved_token_190|>",
|
| 1559 |
+
"lstrip": false,
|
| 1560 |
+
"normalized": false,
|
| 1561 |
+
"rstrip": false,
|
| 1562 |
+
"single_word": false,
|
| 1563 |
+
"special": true
|
| 1564 |
+
},
|
| 1565 |
+
"126275": {
|
| 1566 |
+
"content": "<|reserved_token_191|>",
|
| 1567 |
+
"lstrip": false,
|
| 1568 |
+
"normalized": false,
|
| 1569 |
+
"rstrip": false,
|
| 1570 |
+
"single_word": false,
|
| 1571 |
+
"special": true
|
| 1572 |
+
},
|
| 1573 |
+
"126276": {
|
| 1574 |
+
"content": "<|reserved_token_192|>",
|
| 1575 |
+
"lstrip": false,
|
| 1576 |
+
"normalized": false,
|
| 1577 |
+
"rstrip": false,
|
| 1578 |
+
"single_word": false,
|
| 1579 |
+
"special": true
|
| 1580 |
+
},
|
| 1581 |
+
"126277": {
|
| 1582 |
+
"content": "<|reserved_token_193|>",
|
| 1583 |
+
"lstrip": false,
|
| 1584 |
+
"normalized": false,
|
| 1585 |
+
"rstrip": false,
|
| 1586 |
+
"single_word": false,
|
| 1587 |
+
"special": true
|
| 1588 |
+
},
|
| 1589 |
+
"126278": {
|
| 1590 |
+
"content": "<|reserved_token_194|>",
|
| 1591 |
+
"lstrip": false,
|
| 1592 |
+
"normalized": false,
|
| 1593 |
+
"rstrip": false,
|
| 1594 |
+
"single_word": false,
|
| 1595 |
+
"special": true
|
| 1596 |
+
},
|
| 1597 |
+
"126279": {
|
| 1598 |
+
"content": "<|reserved_token_195|>",
|
| 1599 |
+
"lstrip": false,
|
| 1600 |
+
"normalized": false,
|
| 1601 |
+
"rstrip": false,
|
| 1602 |
+
"single_word": false,
|
| 1603 |
+
"special": true
|
| 1604 |
+
},
|
| 1605 |
+
"126280": {
|
| 1606 |
+
"content": "<|reserved_token_196|>",
|
| 1607 |
+
"lstrip": false,
|
| 1608 |
+
"normalized": false,
|
| 1609 |
+
"rstrip": false,
|
| 1610 |
+
"single_word": false,
|
| 1611 |
+
"special": true
|
| 1612 |
+
},
|
| 1613 |
+
"126281": {
|
| 1614 |
+
"content": "<|reserved_token_197|>",
|
| 1615 |
+
"lstrip": false,
|
| 1616 |
+
"normalized": false,
|
| 1617 |
+
"rstrip": false,
|
| 1618 |
+
"single_word": false,
|
| 1619 |
+
"special": true
|
| 1620 |
+
},
|
| 1621 |
+
"126282": {
|
| 1622 |
+
"content": "<|reserved_token_198|>",
|
| 1623 |
+
"lstrip": false,
|
| 1624 |
+
"normalized": false,
|
| 1625 |
+
"rstrip": false,
|
| 1626 |
+
"single_word": false,
|
| 1627 |
+
"special": true
|
| 1628 |
+
},
|
| 1629 |
+
"126283": {
|
| 1630 |
+
"content": "<|reserved_token_199|>",
|
| 1631 |
+
"lstrip": false,
|
| 1632 |
+
"normalized": false,
|
| 1633 |
+
"rstrip": false,
|
| 1634 |
+
"single_word": false,
|
| 1635 |
+
"special": true
|
| 1636 |
+
},
|
| 1637 |
+
"126284": {
|
| 1638 |
+
"content": "<|reserved_token_200|>",
|
| 1639 |
+
"lstrip": false,
|
| 1640 |
+
"normalized": false,
|
| 1641 |
+
"rstrip": false,
|
| 1642 |
+
"single_word": false,
|
| 1643 |
+
"special": true
|
| 1644 |
+
},
|
| 1645 |
+
"126285": {
|
| 1646 |
+
"content": "<|reserved_token_201|>",
|
| 1647 |
+
"lstrip": false,
|
| 1648 |
+
"normalized": false,
|
| 1649 |
+
"rstrip": false,
|
| 1650 |
+
"single_word": false,
|
| 1651 |
+
"special": true
|
| 1652 |
+
},
|
| 1653 |
+
"126286": {
|
| 1654 |
+
"content": "<|reserved_token_202|>",
|
| 1655 |
+
"lstrip": false,
|
| 1656 |
+
"normalized": false,
|
| 1657 |
+
"rstrip": false,
|
| 1658 |
+
"single_word": false,
|
| 1659 |
+
"special": true
|
| 1660 |
+
},
|
| 1661 |
+
"126287": {
|
| 1662 |
+
"content": "<|reserved_token_203|>",
|
| 1663 |
+
"lstrip": false,
|
| 1664 |
+
"normalized": false,
|
| 1665 |
+
"rstrip": false,
|
| 1666 |
+
"single_word": false,
|
| 1667 |
+
"special": true
|
| 1668 |
+
},
|
| 1669 |
+
"126288": {
|
| 1670 |
+
"content": "<|reserved_token_204|>",
|
| 1671 |
+
"lstrip": false,
|
| 1672 |
+
"normalized": false,
|
| 1673 |
+
"rstrip": false,
|
| 1674 |
+
"single_word": false,
|
| 1675 |
+
"special": true
|
| 1676 |
+
},
|
| 1677 |
+
"126289": {
|
| 1678 |
+
"content": "<|reserved_token_205|>",
|
| 1679 |
+
"lstrip": false,
|
| 1680 |
+
"normalized": false,
|
| 1681 |
+
"rstrip": false,
|
| 1682 |
+
"single_word": false,
|
| 1683 |
+
"special": true
|
| 1684 |
+
},
|
| 1685 |
+
"126290": {
|
| 1686 |
+
"content": "<|reserved_token_206|>",
|
| 1687 |
+
"lstrip": false,
|
| 1688 |
+
"normalized": false,
|
| 1689 |
+
"rstrip": false,
|
| 1690 |
+
"single_word": false,
|
| 1691 |
+
"special": true
|
| 1692 |
+
},
|
| 1693 |
+
"126291": {
|
| 1694 |
+
"content": "<|reserved_token_207|>",
|
| 1695 |
+
"lstrip": false,
|
| 1696 |
+
"normalized": false,
|
| 1697 |
+
"rstrip": false,
|
| 1698 |
+
"single_word": false,
|
| 1699 |
+
"special": true
|
| 1700 |
+
},
|
| 1701 |
+
"126292": {
|
| 1702 |
+
"content": "<|reserved_token_208|>",
|
| 1703 |
+
"lstrip": false,
|
| 1704 |
+
"normalized": false,
|
| 1705 |
+
"rstrip": false,
|
| 1706 |
+
"single_word": false,
|
| 1707 |
+
"special": true
|
| 1708 |
+
},
|
| 1709 |
+
"126293": {
|
| 1710 |
+
"content": "<|reserved_token_209|>",
|
| 1711 |
+
"lstrip": false,
|
| 1712 |
+
"normalized": false,
|
| 1713 |
+
"rstrip": false,
|
| 1714 |
+
"single_word": false,
|
| 1715 |
+
"special": true
|
| 1716 |
+
},
|
| 1717 |
+
"126294": {
|
| 1718 |
+
"content": "<|reserved_token_210|>",
|
| 1719 |
+
"lstrip": false,
|
| 1720 |
+
"normalized": false,
|
| 1721 |
+
"rstrip": false,
|
| 1722 |
+
"single_word": false,
|
| 1723 |
+
"special": true
|
| 1724 |
+
},
|
| 1725 |
+
"126295": {
|
| 1726 |
+
"content": "<|reserved_token_211|>",
|
| 1727 |
+
"lstrip": false,
|
| 1728 |
+
"normalized": false,
|
| 1729 |
+
"rstrip": false,
|
| 1730 |
+
"single_word": false,
|
| 1731 |
+
"special": true
|
| 1732 |
+
},
|
| 1733 |
+
"126296": {
|
| 1734 |
+
"content": "<|reserved_token_212|>",
|
| 1735 |
+
"lstrip": false,
|
| 1736 |
+
"normalized": false,
|
| 1737 |
+
"rstrip": false,
|
| 1738 |
+
"single_word": false,
|
| 1739 |
+
"special": true
|
| 1740 |
+
},
|
| 1741 |
+
"126297": {
|
| 1742 |
+
"content": "<|reserved_token_213|>",
|
| 1743 |
+
"lstrip": false,
|
| 1744 |
+
"normalized": false,
|
| 1745 |
+
"rstrip": false,
|
| 1746 |
+
"single_word": false,
|
| 1747 |
+
"special": true
|
| 1748 |
+
},
|
| 1749 |
+
"126298": {
|
| 1750 |
+
"content": "<|reserved_token_214|>",
|
| 1751 |
+
"lstrip": false,
|
| 1752 |
+
"normalized": false,
|
| 1753 |
+
"rstrip": false,
|
| 1754 |
+
"single_word": false,
|
| 1755 |
+
"special": true
|
| 1756 |
+
},
|
| 1757 |
+
"126299": {
|
| 1758 |
+
"content": "<|reserved_token_215|>",
|
| 1759 |
+
"lstrip": false,
|
| 1760 |
+
"normalized": false,
|
| 1761 |
+
"rstrip": false,
|
| 1762 |
+
"single_word": false,
|
| 1763 |
+
"special": true
|
| 1764 |
+
},
|
| 1765 |
+
"126300": {
|
| 1766 |
+
"content": "<|reserved_token_216|>",
|
| 1767 |
+
"lstrip": false,
|
| 1768 |
+
"normalized": false,
|
| 1769 |
+
"rstrip": false,
|
| 1770 |
+
"single_word": false,
|
| 1771 |
+
"special": true
|
| 1772 |
+
},
|
| 1773 |
+
"126301": {
|
| 1774 |
+
"content": "<|reserved_token_217|>",
|
| 1775 |
+
"lstrip": false,
|
| 1776 |
+
"normalized": false,
|
| 1777 |
+
"rstrip": false,
|
| 1778 |
+
"single_word": false,
|
| 1779 |
+
"special": true
|
| 1780 |
+
},
|
| 1781 |
+
"126302": {
|
| 1782 |
+
"content": "<|reserved_token_218|>",
|
| 1783 |
+
"lstrip": false,
|
| 1784 |
+
"normalized": false,
|
| 1785 |
+
"rstrip": false,
|
| 1786 |
+
"single_word": false,
|
| 1787 |
+
"special": true
|
| 1788 |
+
},
|
| 1789 |
+
"126303": {
|
| 1790 |
+
"content": "<|reserved_token_219|>",
|
| 1791 |
+
"lstrip": false,
|
| 1792 |
+
"normalized": false,
|
| 1793 |
+
"rstrip": false,
|
| 1794 |
+
"single_word": false,
|
| 1795 |
+
"special": true
|
| 1796 |
+
},
|
| 1797 |
+
"126304": {
|
| 1798 |
+
"content": "<|reserved_token_220|>",
|
| 1799 |
+
"lstrip": false,
|
| 1800 |
+
"normalized": false,
|
| 1801 |
+
"rstrip": false,
|
| 1802 |
+
"single_word": false,
|
| 1803 |
+
"special": true
|
| 1804 |
+
},
|
| 1805 |
+
"126305": {
|
| 1806 |
+
"content": "<|reserved_token_221|>",
|
| 1807 |
+
"lstrip": false,
|
| 1808 |
+
"normalized": false,
|
| 1809 |
+
"rstrip": false,
|
| 1810 |
+
"single_word": false,
|
| 1811 |
+
"special": true
|
| 1812 |
+
},
|
| 1813 |
+
"126306": {
|
| 1814 |
+
"content": "<|reserved_token_222|>",
|
| 1815 |
+
"lstrip": false,
|
| 1816 |
+
"normalized": false,
|
| 1817 |
+
"rstrip": false,
|
| 1818 |
+
"single_word": false,
|
| 1819 |
+
"special": true
|
| 1820 |
+
},
|
| 1821 |
+
"126307": {
|
| 1822 |
+
"content": "<|reserved_token_223|>",
|
| 1823 |
+
"lstrip": false,
|
| 1824 |
+
"normalized": false,
|
| 1825 |
+
"rstrip": false,
|
| 1826 |
+
"single_word": false,
|
| 1827 |
+
"special": true
|
| 1828 |
+
},
|
| 1829 |
+
"126308": {
|
| 1830 |
+
"content": "<|reserved_token_224|>",
|
| 1831 |
+
"lstrip": false,
|
| 1832 |
+
"normalized": false,
|
| 1833 |
+
"rstrip": false,
|
| 1834 |
+
"single_word": false,
|
| 1835 |
+
"special": true
|
| 1836 |
+
},
|
| 1837 |
+
"126309": {
|
| 1838 |
+
"content": "<|reserved_token_225|>",
|
| 1839 |
+
"lstrip": false,
|
| 1840 |
+
"normalized": false,
|
| 1841 |
+
"rstrip": false,
|
| 1842 |
+
"single_word": false,
|
| 1843 |
+
"special": true
|
| 1844 |
+
},
|
| 1845 |
+
"126310": {
|
| 1846 |
+
"content": "<|reserved_token_226|>",
|
| 1847 |
+
"lstrip": false,
|
| 1848 |
+
"normalized": false,
|
| 1849 |
+
"rstrip": false,
|
| 1850 |
+
"single_word": false,
|
| 1851 |
+
"special": true
|
| 1852 |
+
},
|
| 1853 |
+
"126311": {
|
| 1854 |
+
"content": "<|reserved_token_227|>",
|
| 1855 |
+
"lstrip": false,
|
| 1856 |
+
"normalized": false,
|
| 1857 |
+
"rstrip": false,
|
| 1858 |
+
"single_word": false,
|
| 1859 |
+
"special": true
|
| 1860 |
+
},
|
| 1861 |
+
"126312": {
|
| 1862 |
+
"content": "<|reserved_token_228|>",
|
| 1863 |
+
"lstrip": false,
|
| 1864 |
+
"normalized": false,
|
| 1865 |
+
"rstrip": false,
|
| 1866 |
+
"single_word": false,
|
| 1867 |
+
"special": true
|
| 1868 |
+
},
|
| 1869 |
+
"126313": {
|
| 1870 |
+
"content": "<|reserved_token_229|>",
|
| 1871 |
+
"lstrip": false,
|
| 1872 |
+
"normalized": false,
|
| 1873 |
+
"rstrip": false,
|
| 1874 |
+
"single_word": false,
|
| 1875 |
+
"special": true
|
| 1876 |
+
},
|
| 1877 |
+
"126314": {
|
| 1878 |
+
"content": "<|reserved_token_230|>",
|
| 1879 |
+
"lstrip": false,
|
| 1880 |
+
"normalized": false,
|
| 1881 |
+
"rstrip": false,
|
| 1882 |
+
"single_word": false,
|
| 1883 |
+
"special": true
|
| 1884 |
+
},
|
| 1885 |
+
"126315": {
|
| 1886 |
+
"content": "<|reserved_token_231|>",
|
| 1887 |
+
"lstrip": false,
|
| 1888 |
+
"normalized": false,
|
| 1889 |
+
"rstrip": false,
|
| 1890 |
+
"single_word": false,
|
| 1891 |
+
"special": true
|
| 1892 |
+
},
|
| 1893 |
+
"126316": {
|
| 1894 |
+
"content": "<|reserved_token_232|>",
|
| 1895 |
+
"lstrip": false,
|
| 1896 |
+
"normalized": false,
|
| 1897 |
+
"rstrip": false,
|
| 1898 |
+
"single_word": false,
|
| 1899 |
+
"special": true
|
| 1900 |
+
},
|
| 1901 |
+
"126317": {
|
| 1902 |
+
"content": "<|reserved_token_233|>",
|
| 1903 |
+
"lstrip": false,
|
| 1904 |
+
"normalized": false,
|
| 1905 |
+
"rstrip": false,
|
| 1906 |
+
"single_word": false,
|
| 1907 |
+
"special": true
|
| 1908 |
+
},
|
| 1909 |
+
"126318": {
|
| 1910 |
+
"content": "<|reserved_token_234|>",
|
| 1911 |
+
"lstrip": false,
|
| 1912 |
+
"normalized": false,
|
| 1913 |
+
"rstrip": false,
|
| 1914 |
+
"single_word": false,
|
| 1915 |
+
"special": true
|
| 1916 |
+
},
|
| 1917 |
+
"126319": {
|
| 1918 |
+
"content": "<|reserved_token_235|>",
|
| 1919 |
+
"lstrip": false,
|
| 1920 |
+
"normalized": false,
|
| 1921 |
+
"rstrip": false,
|
| 1922 |
+
"single_word": false,
|
| 1923 |
+
"special": true
|
| 1924 |
+
},
|
| 1925 |
+
"126320": {
|
| 1926 |
+
"content": "<|reserved_token_236|>",
|
| 1927 |
+
"lstrip": false,
|
| 1928 |
+
"normalized": false,
|
| 1929 |
+
"rstrip": false,
|
| 1930 |
+
"single_word": false,
|
| 1931 |
+
"special": true
|
| 1932 |
+
},
|
| 1933 |
+
"126321": {
|
| 1934 |
+
"content": "<|reserved_token_237|>",
|
| 1935 |
+
"lstrip": false,
|
| 1936 |
+
"normalized": false,
|
| 1937 |
+
"rstrip": false,
|
| 1938 |
+
"single_word": false,
|
| 1939 |
+
"special": true
|
| 1940 |
+
},
|
| 1941 |
+
"126322": {
|
| 1942 |
+
"content": "<|reserved_token_238|>",
|
| 1943 |
+
"lstrip": false,
|
| 1944 |
+
"normalized": false,
|
| 1945 |
+
"rstrip": false,
|
| 1946 |
+
"single_word": false,
|
| 1947 |
+
"special": true
|
| 1948 |
+
},
|
| 1949 |
+
"126323": {
|
| 1950 |
+
"content": "<|reserved_token_239|>",
|
| 1951 |
+
"lstrip": false,
|
| 1952 |
+
"normalized": false,
|
| 1953 |
+
"rstrip": false,
|
| 1954 |
+
"single_word": false,
|
| 1955 |
+
"special": true
|
| 1956 |
+
},
|
| 1957 |
+
"126324": {
|
| 1958 |
+
"content": "<|reserved_token_240|>",
|
| 1959 |
+
"lstrip": false,
|
| 1960 |
+
"normalized": false,
|
| 1961 |
+
"rstrip": false,
|
| 1962 |
+
"single_word": false,
|
| 1963 |
+
"special": true
|
| 1964 |
+
},
|
| 1965 |
+
"126325": {
|
| 1966 |
+
"content": "<|reserved_token_241|>",
|
| 1967 |
+
"lstrip": false,
|
| 1968 |
+
"normalized": false,
|
| 1969 |
+
"rstrip": false,
|
| 1970 |
+
"single_word": false,
|
| 1971 |
+
"special": true
|
| 1972 |
+
},
|
| 1973 |
+
"126326": {
|
| 1974 |
+
"content": "<|reserved_token_242|>",
|
| 1975 |
+
"lstrip": false,
|
| 1976 |
+
"normalized": false,
|
| 1977 |
+
"rstrip": false,
|
| 1978 |
+
"single_word": false,
|
| 1979 |
+
"special": true
|
| 1980 |
+
},
|
| 1981 |
+
"126327": {
|
| 1982 |
+
"content": "<|reserved_token_243|>",
|
| 1983 |
+
"lstrip": false,
|
| 1984 |
+
"normalized": false,
|
| 1985 |
+
"rstrip": false,
|
| 1986 |
+
"single_word": false,
|
| 1987 |
+
"special": true
|
| 1988 |
+
},
|
| 1989 |
+
"126328": {
|
| 1990 |
+
"content": "<|reserved_token_244|>",
|
| 1991 |
+
"lstrip": false,
|
| 1992 |
+
"normalized": false,
|
| 1993 |
+
"rstrip": false,
|
| 1994 |
+
"single_word": false,
|
| 1995 |
+
"special": true
|
| 1996 |
+
},
|
| 1997 |
+
"126329": {
|
| 1998 |
+
"content": "<|reserved_token_245|>",
|
| 1999 |
+
"lstrip": false,
|
| 2000 |
+
"normalized": false,
|
| 2001 |
+
"rstrip": false,
|
| 2002 |
+
"single_word": false,
|
| 2003 |
+
"special": true
|
| 2004 |
+
},
|
| 2005 |
+
"126330": {
|
| 2006 |
+
"content": "<|reserved_token_246|>",
|
| 2007 |
+
"lstrip": false,
|
| 2008 |
+
"normalized": false,
|
| 2009 |
+
"rstrip": false,
|
| 2010 |
+
"single_word": false,
|
| 2011 |
+
"special": true
|
| 2012 |
+
},
|
| 2013 |
+
"126331": {
|
| 2014 |
+
"content": "<|reserved_token_247|>",
|
| 2015 |
+
"lstrip": false,
|
| 2016 |
+
"normalized": false,
|
| 2017 |
+
"rstrip": false,
|
| 2018 |
+
"single_word": false,
|
| 2019 |
+
"special": true
|
| 2020 |
+
},
|
| 2021 |
+
"126332": {
|
| 2022 |
+
"content": "<|reserved_token_248|>",
|
| 2023 |
+
"lstrip": false,
|
| 2024 |
+
"normalized": false,
|
| 2025 |
+
"rstrip": false,
|
| 2026 |
+
"single_word": false,
|
| 2027 |
+
"special": true
|
| 2028 |
+
},
|
| 2029 |
+
"126333": {
|
| 2030 |
+
"content": "<|reserved_token_249|>",
|
| 2031 |
+
"lstrip": false,
|
| 2032 |
+
"normalized": false,
|
| 2033 |
+
"rstrip": false,
|
| 2034 |
+
"single_word": false,
|
| 2035 |
+
"special": true
|
| 2036 |
+
},
|
| 2037 |
+
"126334": {
|
| 2038 |
+
"content": "<|reserved_token_250|>",
|
| 2039 |
+
"lstrip": false,
|
| 2040 |
+
"normalized": false,
|
| 2041 |
+
"rstrip": false,
|
| 2042 |
+
"single_word": false,
|
| 2043 |
+
"special": true
|
| 2044 |
+
},
|
| 2045 |
+
"126335": {
|
| 2046 |
+
"content": "<|reserved_token_251|>",
|
| 2047 |
+
"lstrip": false,
|
| 2048 |
+
"normalized": false,
|
| 2049 |
+
"rstrip": false,
|
| 2050 |
+
"single_word": false,
|
| 2051 |
+
"special": true
|
| 2052 |
+
},
|
| 2053 |
+
"126336": {
|
| 2054 |
+
"content": "<|mdm_mask|>",
|
| 2055 |
+
"lstrip": false,
|
| 2056 |
+
"normalized": false,
|
| 2057 |
+
"rstrip": false,
|
| 2058 |
+
"single_word": false,
|
| 2059 |
+
"special": true
|
| 2060 |
+
},
|
| 2061 |
+
"126337": {
|
| 2062 |
+
"content": "<|reserved_token_253|>",
|
| 2063 |
+
"lstrip": false,
|
| 2064 |
+
"normalized": false,
|
| 2065 |
+
"rstrip": false,
|
| 2066 |
+
"single_word": false,
|
| 2067 |
+
"special": true
|
| 2068 |
+
},
|
| 2069 |
+
"126338": {
|
| 2070 |
+
"content": "<|reserved_token_254|>",
|
| 2071 |
+
"lstrip": false,
|
| 2072 |
+
"normalized": false,
|
| 2073 |
+
"rstrip": false,
|
| 2074 |
+
"single_word": false,
|
| 2075 |
+
"special": true
|
| 2076 |
+
},
|
| 2077 |
+
"126339": {
|
| 2078 |
+
"content": "<|reserved_token_255|>",
|
| 2079 |
+
"lstrip": false,
|
| 2080 |
+
"normalized": false,
|
| 2081 |
+
"rstrip": false,
|
| 2082 |
+
"single_word": false,
|
| 2083 |
+
"special": true
|
| 2084 |
+
},
|
| 2085 |
+
"126340": {
|
| 2086 |
+
"content": "<role>",
|
| 2087 |
+
"lstrip": false,
|
| 2088 |
+
"normalized": false,
|
| 2089 |
+
"rstrip": false,
|
| 2090 |
+
"single_word": false,
|
| 2091 |
+
"special": true
|
| 2092 |
+
},
|
| 2093 |
+
"126341": {
|
| 2094 |
+
"content": "</role>",
|
| 2095 |
+
"lstrip": false,
|
| 2096 |
+
"normalized": false,
|
| 2097 |
+
"rstrip": false,
|
| 2098 |
+
"single_word": false,
|
| 2099 |
+
"special": true
|
| 2100 |
+
},
|
| 2101 |
+
"126342": {
|
| 2102 |
+
"content": "<|arithmetic_start|>",
|
| 2103 |
+
"lstrip": false,
|
| 2104 |
+
"normalized": false,
|
| 2105 |
+
"rstrip": false,
|
| 2106 |
+
"single_word": false,
|
| 2107 |
+
"special": true
|
| 2108 |
+
},
|
| 2109 |
+
"126343": {
|
| 2110 |
+
"content": "<|arithmetic_end|>",
|
| 2111 |
+
"lstrip": false,
|
| 2112 |
+
"normalized": false,
|
| 2113 |
+
"rstrip": false,
|
| 2114 |
+
"single_word": false,
|
| 2115 |
+
"special": true
|
| 2116 |
+
},
|
| 2117 |
+
"126344": {
|
| 2118 |
+
"content": "<|number_start|>",
|
| 2119 |
+
"lstrip": false,
|
| 2120 |
+
"normalized": false,
|
| 2121 |
+
"rstrip": false,
|
| 2122 |
+
"single_word": false,
|
| 2123 |
+
"special": true
|
| 2124 |
+
},
|
| 2125 |
+
"126345": {
|
| 2126 |
+
"content": "<|number_end|>",
|
| 2127 |
+
"lstrip": false,
|
| 2128 |
+
"normalized": false,
|
| 2129 |
+
"rstrip": false,
|
| 2130 |
+
"single_word": false,
|
| 2131 |
+
"special": true
|
| 2132 |
+
},
|
| 2133 |
+
"126346": {
|
| 2134 |
+
"content": "<|expert_cls|>",
|
| 2135 |
+
"lstrip": false,
|
| 2136 |
+
"normalized": false,
|
| 2137 |
+
"rstrip": false,
|
| 2138 |
+
"single_word": false,
|
| 2139 |
+
"special": true
|
| 2140 |
+
}
|
| 2141 |
+
},
|
| 2142 |
+
"additional_special_tokens": [
|
| 2143 |
+
"<|expert_cls|>"
|
| 2144 |
+
],
|
| 2145 |
+
"bos_token": "<|startoftext|>",
|
| 2146 |
+
"clean_up_tokenization_spaces": false,
|
| 2147 |
+
"cls_token": "[CLS]",
|
| 2148 |
+
"eos_token": "<|endoftext|>",
|
| 2149 |
+
"extra_special_tokens": {},
|
| 2150 |
+
"fast_tokenizer": true,
|
| 2151 |
+
"gmask_token": "[gMASK]",
|
| 2152 |
+
"mask_token": "<|mdm_mask|>",
|
| 2153 |
+
"merges_file": null,
|
| 2154 |
+
"model_input_names": [
|
| 2155 |
+
"input_ids",
|
| 2156 |
+
"attention_mask"
|
| 2157 |
+
],
|
| 2158 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 2159 |
+
"pad_token": "<|endoftext|>",
|
| 2160 |
+
"padding_side": "right",
|
| 2161 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 2162 |
+
"trust_remote_code": true
|
| 2163 |
+
}
|
pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/trainer_state.json
ADDED
|
@@ -0,0 +1,2554 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.04,
|
| 6 |
+
"eval_steps": 9000,
|
| 7 |
+
"global_step": 3600,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00011111111111111112,
|
| 14 |
+
"grad_norm": 25.625,
|
| 15 |
+
"learning_rate": 3e-07,
|
| 16 |
+
"loss": 1.6269,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.00022222222222222223,
|
| 21 |
+
"grad_norm": 39.5,
|
| 22 |
+
"learning_rate": 6.333333333333332e-07,
|
| 23 |
+
"loss": 1.6775,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0003333333333333333,
|
| 28 |
+
"grad_norm": 36.0,
|
| 29 |
+
"learning_rate": 9.666666666666666e-07,
|
| 30 |
+
"loss": 1.587,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.00044444444444444447,
|
| 35 |
+
"grad_norm": 36.75,
|
| 36 |
+
"learning_rate": 1.2999999999999998e-06,
|
| 37 |
+
"loss": 1.6014,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0005555555555555556,
|
| 42 |
+
"grad_norm": 21.875,
|
| 43 |
+
"learning_rate": 1.6333333333333333e-06,
|
| 44 |
+
"loss": 1.5199,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0006666666666666666,
|
| 49 |
+
"grad_norm": 18.375,
|
| 50 |
+
"learning_rate": 1.9666666666666668e-06,
|
| 51 |
+
"loss": 1.4893,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0007777777777777777,
|
| 56 |
+
"grad_norm": 8.0625,
|
| 57 |
+
"learning_rate": 2.2999999999999996e-06,
|
| 58 |
+
"loss": 1.4388,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0008888888888888889,
|
| 63 |
+
"grad_norm": 10.5,
|
| 64 |
+
"learning_rate": 2.6333333333333332e-06,
|
| 65 |
+
"loss": 1.404,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.001,
|
| 70 |
+
"grad_norm": 11.1875,
|
| 71 |
+
"learning_rate": 2.966666666666666e-06,
|
| 72 |
+
"loss": 1.4016,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0011111111111111111,
|
| 77 |
+
"grad_norm": 6.6875,
|
| 78 |
+
"learning_rate": 3.2999999999999993e-06,
|
| 79 |
+
"loss": 1.3865,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0012222222222222222,
|
| 84 |
+
"grad_norm": 14.0625,
|
| 85 |
+
"learning_rate": 3.633333333333333e-06,
|
| 86 |
+
"loss": 1.381,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0013333333333333333,
|
| 91 |
+
"grad_norm": 10.875,
|
| 92 |
+
"learning_rate": 3.966666666666666e-06,
|
| 93 |
+
"loss": 1.3751,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.0014444444444444444,
|
| 98 |
+
"grad_norm": 9.5625,
|
| 99 |
+
"learning_rate": 4.2999999999999995e-06,
|
| 100 |
+
"loss": 1.3597,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.0015555555555555555,
|
| 105 |
+
"grad_norm": 9.25,
|
| 106 |
+
"learning_rate": 4.633333333333333e-06,
|
| 107 |
+
"loss": 1.3594,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.0016666666666666668,
|
| 112 |
+
"grad_norm": 7.625,
|
| 113 |
+
"learning_rate": 4.966666666666666e-06,
|
| 114 |
+
"loss": 1.3554,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.0017777777777777779,
|
| 119 |
+
"grad_norm": 14.25,
|
| 120 |
+
"learning_rate": 5.3e-06,
|
| 121 |
+
"loss": 1.3463,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.001888888888888889,
|
| 126 |
+
"grad_norm": 11.5625,
|
| 127 |
+
"learning_rate": 5.633333333333333e-06,
|
| 128 |
+
"loss": 1.3427,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.002,
|
| 133 |
+
"grad_norm": 10.875,
|
| 134 |
+
"learning_rate": 5.9666666666666666e-06,
|
| 135 |
+
"loss": 1.337,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.002111111111111111,
|
| 140 |
+
"grad_norm": 10.625,
|
| 141 |
+
"learning_rate": 6.3e-06,
|
| 142 |
+
"loss": 1.3184,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.0022222222222222222,
|
| 147 |
+
"grad_norm": 9.5,
|
| 148 |
+
"learning_rate": 6.633333333333333e-06,
|
| 149 |
+
"loss": 1.3289,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.0023333333333333335,
|
| 154 |
+
"grad_norm": 8.0,
|
| 155 |
+
"learning_rate": 6.9666666666666655e-06,
|
| 156 |
+
"loss": 1.3101,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.0024444444444444444,
|
| 161 |
+
"grad_norm": 8.375,
|
| 162 |
+
"learning_rate": 7.299999999999999e-06,
|
| 163 |
+
"loss": 1.3113,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.0025555555555555557,
|
| 168 |
+
"grad_norm": 16.25,
|
| 169 |
+
"learning_rate": 7.633333333333332e-06,
|
| 170 |
+
"loss": 1.3096,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.0026666666666666666,
|
| 175 |
+
"grad_norm": 11.1875,
|
| 176 |
+
"learning_rate": 7.966666666666666e-06,
|
| 177 |
+
"loss": 1.2804,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.002777777777777778,
|
| 182 |
+
"grad_norm": 8.5625,
|
| 183 |
+
"learning_rate": 8.299999999999998e-06,
|
| 184 |
+
"loss": 1.2911,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.0028888888888888888,
|
| 189 |
+
"grad_norm": 7.71875,
|
| 190 |
+
"learning_rate": 8.633333333333333e-06,
|
| 191 |
+
"loss": 1.2868,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.003,
|
| 196 |
+
"grad_norm": 9.1875,
|
| 197 |
+
"learning_rate": 8.966666666666665e-06,
|
| 198 |
+
"loss": 1.296,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.003111111111111111,
|
| 203 |
+
"grad_norm": 11.3125,
|
| 204 |
+
"learning_rate": 9.299999999999999e-06,
|
| 205 |
+
"loss": 1.2714,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.0032222222222222222,
|
| 210 |
+
"grad_norm": 11.75,
|
| 211 |
+
"learning_rate": 9.633333333333333e-06,
|
| 212 |
+
"loss": 1.2572,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.0033333333333333335,
|
| 217 |
+
"grad_norm": 15.5625,
|
| 218 |
+
"learning_rate": 9.966666666666666e-06,
|
| 219 |
+
"loss": 1.2655,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.0034444444444444444,
|
| 224 |
+
"grad_norm": 13.875,
|
| 225 |
+
"learning_rate": 1.03e-05,
|
| 226 |
+
"loss": 1.2668,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.0035555555555555557,
|
| 231 |
+
"grad_norm": 24.375,
|
| 232 |
+
"learning_rate": 1.0633333333333332e-05,
|
| 233 |
+
"loss": 1.265,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.0036666666666666666,
|
| 238 |
+
"grad_norm": 8.125,
|
| 239 |
+
"learning_rate": 1.0966666666666666e-05,
|
| 240 |
+
"loss": 1.2435,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.003777777777777778,
|
| 245 |
+
"grad_norm": 9.5625,
|
| 246 |
+
"learning_rate": 1.1299999999999999e-05,
|
| 247 |
+
"loss": 1.2272,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.0038888888888888888,
|
| 252 |
+
"grad_norm": 19.25,
|
| 253 |
+
"learning_rate": 1.1633333333333333e-05,
|
| 254 |
+
"loss": 1.2072,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.004,
|
| 259 |
+
"grad_norm": 10.0,
|
| 260 |
+
"learning_rate": 1.1966666666666667e-05,
|
| 261 |
+
"loss": 1.2086,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.004111111111111111,
|
| 266 |
+
"grad_norm": 8.0,
|
| 267 |
+
"learning_rate": 1.2299999999999999e-05,
|
| 268 |
+
"loss": 1.2023,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.004222222222222222,
|
| 273 |
+
"grad_norm": 20.75,
|
| 274 |
+
"learning_rate": 1.2633333333333333e-05,
|
| 275 |
+
"loss": 1.1886,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.004333333333333333,
|
| 280 |
+
"grad_norm": 20.75,
|
| 281 |
+
"learning_rate": 1.2966666666666666e-05,
|
| 282 |
+
"loss": 1.1868,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.0044444444444444444,
|
| 287 |
+
"grad_norm": 17.5,
|
| 288 |
+
"learning_rate": 1.33e-05,
|
| 289 |
+
"loss": 1.1956,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.004555555555555556,
|
| 294 |
+
"grad_norm": 18.875,
|
| 295 |
+
"learning_rate": 1.3633333333333332e-05,
|
| 296 |
+
"loss": 1.1915,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.004666666666666667,
|
| 301 |
+
"grad_norm": 30.375,
|
| 302 |
+
"learning_rate": 1.3966666666666666e-05,
|
| 303 |
+
"loss": 1.1606,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.0047777777777777775,
|
| 308 |
+
"grad_norm": 34.25,
|
| 309 |
+
"learning_rate": 1.43e-05,
|
| 310 |
+
"loss": 1.1721,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.004888888888888889,
|
| 315 |
+
"grad_norm": 14.5,
|
| 316 |
+
"learning_rate": 1.4633333333333333e-05,
|
| 317 |
+
"loss": 1.1453,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.005,
|
| 322 |
+
"grad_norm": 15.5,
|
| 323 |
+
"learning_rate": 1.4966666666666667e-05,
|
| 324 |
+
"loss": 1.1354,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.005111111111111111,
|
| 329 |
+
"grad_norm": 20.5,
|
| 330 |
+
"learning_rate": 1.53e-05,
|
| 331 |
+
"loss": 1.1412,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.005222222222222222,
|
| 336 |
+
"grad_norm": 26.5,
|
| 337 |
+
"learning_rate": 1.563333333333333e-05,
|
| 338 |
+
"loss": 1.1316,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.005333333333333333,
|
| 343 |
+
"grad_norm": 37.75,
|
| 344 |
+
"learning_rate": 1.5966666666666664e-05,
|
| 345 |
+
"loss": 1.1416,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.0054444444444444445,
|
| 350 |
+
"grad_norm": 9.125,
|
| 351 |
+
"learning_rate": 1.6299999999999996e-05,
|
| 352 |
+
"loss": 1.1542,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.005555555555555556,
|
| 357 |
+
"grad_norm": 17.75,
|
| 358 |
+
"learning_rate": 1.6633333333333332e-05,
|
| 359 |
+
"loss": 1.1284,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.005666666666666667,
|
| 364 |
+
"grad_norm": 20.625,
|
| 365 |
+
"learning_rate": 1.6966666666666665e-05,
|
| 366 |
+
"loss": 1.1576,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.0057777777777777775,
|
| 371 |
+
"grad_norm": 17.25,
|
| 372 |
+
"learning_rate": 1.7299999999999997e-05,
|
| 373 |
+
"loss": 1.1076,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.005888888888888889,
|
| 378 |
+
"grad_norm": 54.5,
|
| 379 |
+
"learning_rate": 1.7633333333333333e-05,
|
| 380 |
+
"loss": 1.1281,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.006,
|
| 385 |
+
"grad_norm": 49.25,
|
| 386 |
+
"learning_rate": 1.7966666666666665e-05,
|
| 387 |
+
"loss": 1.0892,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.006111111111111111,
|
| 392 |
+
"grad_norm": 36.5,
|
| 393 |
+
"learning_rate": 1.8299999999999998e-05,
|
| 394 |
+
"loss": 1.1067,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.006222222222222222,
|
| 399 |
+
"grad_norm": 21.5,
|
| 400 |
+
"learning_rate": 1.863333333333333e-05,
|
| 401 |
+
"loss": 1.1111,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.006333333333333333,
|
| 406 |
+
"grad_norm": 56.25,
|
| 407 |
+
"learning_rate": 1.8966666666666666e-05,
|
| 408 |
+
"loss": 1.1049,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.0064444444444444445,
|
| 413 |
+
"grad_norm": 37.75,
|
| 414 |
+
"learning_rate": 1.93e-05,
|
| 415 |
+
"loss": 1.1011,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.006555555555555556,
|
| 420 |
+
"grad_norm": 55.25,
|
| 421 |
+
"learning_rate": 1.963333333333333e-05,
|
| 422 |
+
"loss": 1.1063,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.006666666666666667,
|
| 427 |
+
"grad_norm": 93.0,
|
| 428 |
+
"learning_rate": 1.9966666666666666e-05,
|
| 429 |
+
"loss": 1.1096,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.0067777777777777775,
|
| 434 |
+
"grad_norm": 33.5,
|
| 435 |
+
"learning_rate": 2.03e-05,
|
| 436 |
+
"loss": 1.093,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.006888888888888889,
|
| 441 |
+
"grad_norm": 25.5,
|
| 442 |
+
"learning_rate": 2.063333333333333e-05,
|
| 443 |
+
"loss": 1.0844,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.007,
|
| 448 |
+
"grad_norm": 70.0,
|
| 449 |
+
"learning_rate": 2.0966666666666664e-05,
|
| 450 |
+
"loss": 1.0816,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.0071111111111111115,
|
| 455 |
+
"grad_norm": 43.5,
|
| 456 |
+
"learning_rate": 2.1299999999999996e-05,
|
| 457 |
+
"loss": 1.0537,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.007222222222222222,
|
| 462 |
+
"grad_norm": 29.375,
|
| 463 |
+
"learning_rate": 2.1633333333333332e-05,
|
| 464 |
+
"loss": 1.0998,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.007333333333333333,
|
| 469 |
+
"grad_norm": 109.5,
|
| 470 |
+
"learning_rate": 2.1966666666666664e-05,
|
| 471 |
+
"loss": 1.0622,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.0074444444444444445,
|
| 476 |
+
"grad_norm": 26.0,
|
| 477 |
+
"learning_rate": 2.23e-05,
|
| 478 |
+
"loss": 1.0704,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.007555555555555556,
|
| 483 |
+
"grad_norm": 72.5,
|
| 484 |
+
"learning_rate": 2.263333333333333e-05,
|
| 485 |
+
"loss": 1.0564,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.007666666666666666,
|
| 490 |
+
"grad_norm": 114.5,
|
| 491 |
+
"learning_rate": 2.2966666666666665e-05,
|
| 492 |
+
"loss": 1.1096,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.0077777777777777776,
|
| 497 |
+
"grad_norm": 73.0,
|
| 498 |
+
"learning_rate": 2.3299999999999997e-05,
|
| 499 |
+
"loss": 1.0886,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.00788888888888889,
|
| 504 |
+
"grad_norm": 29.375,
|
| 505 |
+
"learning_rate": 2.3633333333333333e-05,
|
| 506 |
+
"loss": 1.1203,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.008,
|
| 511 |
+
"grad_norm": 46.75,
|
| 512 |
+
"learning_rate": 2.3966666666666662e-05,
|
| 513 |
+
"loss": 1.0413,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.00811111111111111,
|
| 518 |
+
"grad_norm": 34.25,
|
| 519 |
+
"learning_rate": 2.4299999999999998e-05,
|
| 520 |
+
"loss": 1.0317,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.008222222222222223,
|
| 525 |
+
"grad_norm": 52.0,
|
| 526 |
+
"learning_rate": 2.463333333333333e-05,
|
| 527 |
+
"loss": 1.0521,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.008333333333333333,
|
| 532 |
+
"grad_norm": 29.25,
|
| 533 |
+
"learning_rate": 2.4966666666666666e-05,
|
| 534 |
+
"loss": 1.0433,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.008444444444444444,
|
| 539 |
+
"grad_norm": 33.25,
|
| 540 |
+
"learning_rate": 2.53e-05,
|
| 541 |
+
"loss": 1.0429,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.008555555555555556,
|
| 546 |
+
"grad_norm": 90.0,
|
| 547 |
+
"learning_rate": 2.563333333333333e-05,
|
| 548 |
+
"loss": 1.0678,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.008666666666666666,
|
| 553 |
+
"grad_norm": 36.0,
|
| 554 |
+
"learning_rate": 2.5966666666666663e-05,
|
| 555 |
+
"loss": 1.0956,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.008777777777777778,
|
| 560 |
+
"grad_norm": 41.5,
|
| 561 |
+
"learning_rate": 2.63e-05,
|
| 562 |
+
"loss": 1.0266,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.008888888888888889,
|
| 567 |
+
"grad_norm": 24.125,
|
| 568 |
+
"learning_rate": 2.663333333333333e-05,
|
| 569 |
+
"loss": 1.006,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.009,
|
| 574 |
+
"grad_norm": 63.0,
|
| 575 |
+
"learning_rate": 2.6966666666666667e-05,
|
| 576 |
+
"loss": 1.0309,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.009111111111111111,
|
| 581 |
+
"grad_norm": 78.5,
|
| 582 |
+
"learning_rate": 2.7299999999999996e-05,
|
| 583 |
+
"loss": 1.0492,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.009222222222222222,
|
| 588 |
+
"grad_norm": 61.75,
|
| 589 |
+
"learning_rate": 2.7633333333333332e-05,
|
| 590 |
+
"loss": 1.0139,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.009333333333333334,
|
| 595 |
+
"grad_norm": 26.25,
|
| 596 |
+
"learning_rate": 2.7966666666666664e-05,
|
| 597 |
+
"loss": 1.0908,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.009444444444444445,
|
| 602 |
+
"grad_norm": 78.0,
|
| 603 |
+
"learning_rate": 2.83e-05,
|
| 604 |
+
"loss": 1.1256,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.009555555555555555,
|
| 609 |
+
"grad_norm": 16.875,
|
| 610 |
+
"learning_rate": 2.863333333333333e-05,
|
| 611 |
+
"loss": 1.0275,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.009666666666666667,
|
| 616 |
+
"grad_norm": 72.5,
|
| 617 |
+
"learning_rate": 2.8966666666666665e-05,
|
| 618 |
+
"loss": 1.1138,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.009777777777777778,
|
| 623 |
+
"grad_norm": 63.5,
|
| 624 |
+
"learning_rate": 2.9299999999999997e-05,
|
| 625 |
+
"loss": 1.0754,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.009888888888888888,
|
| 630 |
+
"grad_norm": 54.25,
|
| 631 |
+
"learning_rate": 2.9633333333333333e-05,
|
| 632 |
+
"loss": 1.0312,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.01,
|
| 637 |
+
"grad_norm": 40.0,
|
| 638 |
+
"learning_rate": 2.9966666666666665e-05,
|
| 639 |
+
"loss": 1.0032,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.01011111111111111,
|
| 644 |
+
"grad_norm": 61.75,
|
| 645 |
+
"learning_rate": 3.0299999999999998e-05,
|
| 646 |
+
"loss": 1.0668,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.010222222222222223,
|
| 651 |
+
"grad_norm": 39.0,
|
| 652 |
+
"learning_rate": 3.063333333333333e-05,
|
| 653 |
+
"loss": 0.9896,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.010333333333333333,
|
| 658 |
+
"grad_norm": 125.0,
|
| 659 |
+
"learning_rate": 3.096666666666666e-05,
|
| 660 |
+
"loss": 1.0181,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.010444444444444444,
|
| 665 |
+
"grad_norm": 77.5,
|
| 666 |
+
"learning_rate": 3.1299999999999995e-05,
|
| 667 |
+
"loss": 1.0347,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.010555555555555556,
|
| 672 |
+
"grad_norm": 103.5,
|
| 673 |
+
"learning_rate": 3.163333333333333e-05,
|
| 674 |
+
"loss": 1.0609,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.010666666666666666,
|
| 679 |
+
"grad_norm": 29.5,
|
| 680 |
+
"learning_rate": 3.196666666666667e-05,
|
| 681 |
+
"loss": 1.0042,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.010777777777777778,
|
| 686 |
+
"grad_norm": 70.5,
|
| 687 |
+
"learning_rate": 3.229999999999999e-05,
|
| 688 |
+
"loss": 1.0119,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.010888888888888889,
|
| 693 |
+
"grad_norm": 60.75,
|
| 694 |
+
"learning_rate": 3.263333333333333e-05,
|
| 695 |
+
"loss": 1.0056,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.011,
|
| 700 |
+
"grad_norm": 56.5,
|
| 701 |
+
"learning_rate": 3.2966666666666664e-05,
|
| 702 |
+
"loss": 1.0239,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.011111111111111112,
|
| 707 |
+
"grad_norm": 64.0,
|
| 708 |
+
"learning_rate": 3.3299999999999996e-05,
|
| 709 |
+
"loss": 0.9812,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.011222222222222222,
|
| 714 |
+
"grad_norm": 110.5,
|
| 715 |
+
"learning_rate": 3.363333333333333e-05,
|
| 716 |
+
"loss": 0.9701,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.011333333333333334,
|
| 721 |
+
"grad_norm": 51.75,
|
| 722 |
+
"learning_rate": 3.396666666666666e-05,
|
| 723 |
+
"loss": 0.9663,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.011444444444444445,
|
| 728 |
+
"grad_norm": 55.5,
|
| 729 |
+
"learning_rate": 3.4299999999999993e-05,
|
| 730 |
+
"loss": 0.9947,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.011555555555555555,
|
| 735 |
+
"grad_norm": 74.5,
|
| 736 |
+
"learning_rate": 3.463333333333333e-05,
|
| 737 |
+
"loss": 0.958,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.011666666666666667,
|
| 742 |
+
"grad_norm": 101.5,
|
| 743 |
+
"learning_rate": 3.4966666666666665e-05,
|
| 744 |
+
"loss": 1.0788,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.011777777777777778,
|
| 749 |
+
"grad_norm": 40.25,
|
| 750 |
+
"learning_rate": 3.53e-05,
|
| 751 |
+
"loss": 0.9559,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.011888888888888888,
|
| 756 |
+
"grad_norm": 67.5,
|
| 757 |
+
"learning_rate": 3.563333333333333e-05,
|
| 758 |
+
"loss": 1.0126,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.012,
|
| 763 |
+
"grad_norm": 61.0,
|
| 764 |
+
"learning_rate": 3.596666666666666e-05,
|
| 765 |
+
"loss": 1.0124,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.01211111111111111,
|
| 770 |
+
"grad_norm": 33.5,
|
| 771 |
+
"learning_rate": 3.6299999999999995e-05,
|
| 772 |
+
"loss": 1.0403,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.012222222222222223,
|
| 777 |
+
"grad_norm": 67.5,
|
| 778 |
+
"learning_rate": 3.6633333333333334e-05,
|
| 779 |
+
"loss": 0.9884,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.012333333333333333,
|
| 784 |
+
"grad_norm": 23.125,
|
| 785 |
+
"learning_rate": 3.696666666666666e-05,
|
| 786 |
+
"loss": 0.9952,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.012444444444444444,
|
| 791 |
+
"grad_norm": 145.0,
|
| 792 |
+
"learning_rate": 3.73e-05,
|
| 793 |
+
"loss": 1.0333,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.012555555555555556,
|
| 798 |
+
"grad_norm": 46.0,
|
| 799 |
+
"learning_rate": 3.763333333333333e-05,
|
| 800 |
+
"loss": 1.0542,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.012666666666666666,
|
| 805 |
+
"grad_norm": 25.375,
|
| 806 |
+
"learning_rate": 3.7966666666666663e-05,
|
| 807 |
+
"loss": 0.9828,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.012777777777777779,
|
| 812 |
+
"grad_norm": 30.25,
|
| 813 |
+
"learning_rate": 3.83e-05,
|
| 814 |
+
"loss": 1.0306,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.012888888888888889,
|
| 819 |
+
"grad_norm": 16.875,
|
| 820 |
+
"learning_rate": 3.863333333333333e-05,
|
| 821 |
+
"loss": 0.9167,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.013,
|
| 826 |
+
"grad_norm": 92.0,
|
| 827 |
+
"learning_rate": 3.896666666666666e-05,
|
| 828 |
+
"loss": 1.011,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.013111111111111112,
|
| 833 |
+
"grad_norm": 45.25,
|
| 834 |
+
"learning_rate": 3.93e-05,
|
| 835 |
+
"loss": 1.01,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.013222222222222222,
|
| 840 |
+
"grad_norm": 53.5,
|
| 841 |
+
"learning_rate": 3.963333333333333e-05,
|
| 842 |
+
"loss": 0.934,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.013333333333333334,
|
| 847 |
+
"grad_norm": 58.0,
|
| 848 |
+
"learning_rate": 3.996666666666666e-05,
|
| 849 |
+
"loss": 0.966,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.013444444444444445,
|
| 854 |
+
"grad_norm": 59.0,
|
| 855 |
+
"learning_rate": 4.03e-05,
|
| 856 |
+
"loss": 0.938,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.013555555555555555,
|
| 861 |
+
"grad_norm": 51.75,
|
| 862 |
+
"learning_rate": 4.063333333333333e-05,
|
| 863 |
+
"loss": 0.9357,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.013666666666666667,
|
| 868 |
+
"grad_norm": 30.875,
|
| 869 |
+
"learning_rate": 4.096666666666667e-05,
|
| 870 |
+
"loss": 0.9175,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.013777777777777778,
|
| 875 |
+
"grad_norm": 22.875,
|
| 876 |
+
"learning_rate": 4.1299999999999994e-05,
|
| 877 |
+
"loss": 0.8468,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.013888888888888888,
|
| 882 |
+
"grad_norm": 22.875,
|
| 883 |
+
"learning_rate": 4.163333333333333e-05,
|
| 884 |
+
"loss": 0.8916,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.014,
|
| 889 |
+
"grad_norm": 44.5,
|
| 890 |
+
"learning_rate": 4.1966666666666666e-05,
|
| 891 |
+
"loss": 0.9066,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.01411111111111111,
|
| 896 |
+
"grad_norm": 58.75,
|
| 897 |
+
"learning_rate": 4.229999999999999e-05,
|
| 898 |
+
"loss": 0.8707,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.014222222222222223,
|
| 903 |
+
"grad_norm": 39.0,
|
| 904 |
+
"learning_rate": 4.263333333333333e-05,
|
| 905 |
+
"loss": 0.8821,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.014333333333333333,
|
| 910 |
+
"grad_norm": 32.25,
|
| 911 |
+
"learning_rate": 4.296666666666666e-05,
|
| 912 |
+
"loss": 0.8132,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.014444444444444444,
|
| 917 |
+
"grad_norm": 28.25,
|
| 918 |
+
"learning_rate": 4.3299999999999995e-05,
|
| 919 |
+
"loss": 0.7782,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.014555555555555556,
|
| 924 |
+
"grad_norm": 35.75,
|
| 925 |
+
"learning_rate": 4.363333333333333e-05,
|
| 926 |
+
"loss": 0.8004,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.014666666666666666,
|
| 931 |
+
"grad_norm": 49.5,
|
| 932 |
+
"learning_rate": 4.396666666666666e-05,
|
| 933 |
+
"loss": 0.8025,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.014777777777777779,
|
| 938 |
+
"grad_norm": 36.0,
|
| 939 |
+
"learning_rate": 4.43e-05,
|
| 940 |
+
"loss": 0.8144,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.014888888888888889,
|
| 945 |
+
"grad_norm": 15.8125,
|
| 946 |
+
"learning_rate": 4.463333333333333e-05,
|
| 947 |
+
"loss": 0.7734,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.015,
|
| 952 |
+
"grad_norm": 37.5,
|
| 953 |
+
"learning_rate": 4.496666666666666e-05,
|
| 954 |
+
"loss": 0.8131,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.015111111111111112,
|
| 959 |
+
"grad_norm": 14.75,
|
| 960 |
+
"learning_rate": 4.5299999999999997e-05,
|
| 961 |
+
"loss": 0.7909,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.015222222222222222,
|
| 966 |
+
"grad_norm": 43.75,
|
| 967 |
+
"learning_rate": 4.563333333333333e-05,
|
| 968 |
+
"loss": 0.8024,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.015333333333333332,
|
| 973 |
+
"grad_norm": 22.875,
|
| 974 |
+
"learning_rate": 4.596666666666667e-05,
|
| 975 |
+
"loss": 0.7408,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.015444444444444445,
|
| 980 |
+
"grad_norm": 16.125,
|
| 981 |
+
"learning_rate": 4.6299999999999994e-05,
|
| 982 |
+
"loss": 0.763,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.015555555555555555,
|
| 987 |
+
"grad_norm": 16.0,
|
| 988 |
+
"learning_rate": 4.6633333333333326e-05,
|
| 989 |
+
"loss": 0.7198,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.015666666666666666,
|
| 994 |
+
"grad_norm": 29.75,
|
| 995 |
+
"learning_rate": 4.6966666666666665e-05,
|
| 996 |
+
"loss": 0.7312,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.01577777777777778,
|
| 1001 |
+
"grad_norm": 18.125,
|
| 1002 |
+
"learning_rate": 4.73e-05,
|
| 1003 |
+
"loss": 0.6853,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.01588888888888889,
|
| 1008 |
+
"grad_norm": 8.375,
|
| 1009 |
+
"learning_rate": 4.763333333333332e-05,
|
| 1010 |
+
"loss": 0.7067,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.016,
|
| 1015 |
+
"grad_norm": 16.75,
|
| 1016 |
+
"learning_rate": 4.796666666666666e-05,
|
| 1017 |
+
"loss": 0.6398,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.01611111111111111,
|
| 1022 |
+
"grad_norm": 12.75,
|
| 1023 |
+
"learning_rate": 4.8299999999999995e-05,
|
| 1024 |
+
"loss": 0.6991,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.01622222222222222,
|
| 1029 |
+
"grad_norm": 9.3125,
|
| 1030 |
+
"learning_rate": 4.8633333333333334e-05,
|
| 1031 |
+
"loss": 0.7016,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.01633333333333333,
|
| 1036 |
+
"grad_norm": 21.25,
|
| 1037 |
+
"learning_rate": 4.896666666666666e-05,
|
| 1038 |
+
"loss": 0.7055,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.016444444444444446,
|
| 1043 |
+
"grad_norm": 27.375,
|
| 1044 |
+
"learning_rate": 4.929999999999999e-05,
|
| 1045 |
+
"loss": 0.7067,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.016555555555555556,
|
| 1050 |
+
"grad_norm": 15.0625,
|
| 1051 |
+
"learning_rate": 4.963333333333333e-05,
|
| 1052 |
+
"loss": 0.6778,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.016666666666666666,
|
| 1057 |
+
"grad_norm": 9.3125,
|
| 1058 |
+
"learning_rate": 4.9966666666666664e-05,
|
| 1059 |
+
"loss": 0.6304,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.016777777777777777,
|
| 1064 |
+
"grad_norm": 12.125,
|
| 1065 |
+
"learning_rate": 5.0299999999999996e-05,
|
| 1066 |
+
"loss": 0.6127,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.016888888888888887,
|
| 1071 |
+
"grad_norm": 17.0,
|
| 1072 |
+
"learning_rate": 5.063333333333333e-05,
|
| 1073 |
+
"loss": 0.7338,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.017,
|
| 1078 |
+
"grad_norm": 23.0,
|
| 1079 |
+
"learning_rate": 5.096666666666666e-05,
|
| 1080 |
+
"loss": 0.688,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.01711111111111111,
|
| 1085 |
+
"grad_norm": 12.5,
|
| 1086 |
+
"learning_rate": 5.13e-05,
|
| 1087 |
+
"loss": 0.6855,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.017222222222222222,
|
| 1092 |
+
"grad_norm": 10.0,
|
| 1093 |
+
"learning_rate": 5.1633333333333326e-05,
|
| 1094 |
+
"loss": 0.6238,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.017333333333333333,
|
| 1099 |
+
"grad_norm": 9.0625,
|
| 1100 |
+
"learning_rate": 5.1966666666666665e-05,
|
| 1101 |
+
"loss": 0.6624,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.017444444444444443,
|
| 1106 |
+
"grad_norm": 11.125,
|
| 1107 |
+
"learning_rate": 5.23e-05,
|
| 1108 |
+
"loss": 0.6544,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.017555555555555557,
|
| 1113 |
+
"grad_norm": 13.8125,
|
| 1114 |
+
"learning_rate": 5.263333333333332e-05,
|
| 1115 |
+
"loss": 0.6489,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.017666666666666667,
|
| 1120 |
+
"grad_norm": 12.5625,
|
| 1121 |
+
"learning_rate": 5.296666666666666e-05,
|
| 1122 |
+
"loss": 0.6204,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.017777777777777778,
|
| 1127 |
+
"grad_norm": 10.5625,
|
| 1128 |
+
"learning_rate": 5.3299999999999995e-05,
|
| 1129 |
+
"loss": 0.6095,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.017888888888888888,
|
| 1134 |
+
"grad_norm": 16.0,
|
| 1135 |
+
"learning_rate": 5.3633333333333334e-05,
|
| 1136 |
+
"loss": 0.6667,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.018,
|
| 1141 |
+
"grad_norm": 13.1875,
|
| 1142 |
+
"learning_rate": 5.396666666666666e-05,
|
| 1143 |
+
"loss": 0.6194,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.018111111111111113,
|
| 1148 |
+
"grad_norm": 15.125,
|
| 1149 |
+
"learning_rate": 5.429999999999999e-05,
|
| 1150 |
+
"loss": 0.6473,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.018222222222222223,
|
| 1155 |
+
"grad_norm": 13.375,
|
| 1156 |
+
"learning_rate": 5.463333333333333e-05,
|
| 1157 |
+
"loss": 0.5924,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.018333333333333333,
|
| 1162 |
+
"grad_norm": 9.5,
|
| 1163 |
+
"learning_rate": 5.496666666666666e-05,
|
| 1164 |
+
"loss": 0.625,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.018444444444444444,
|
| 1169 |
+
"grad_norm": 10.4375,
|
| 1170 |
+
"learning_rate": 5.529999999999999e-05,
|
| 1171 |
+
"loss": 0.5987,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.018555555555555554,
|
| 1176 |
+
"grad_norm": 7.90625,
|
| 1177 |
+
"learning_rate": 5.563333333333333e-05,
|
| 1178 |
+
"loss": 0.5764,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.018666666666666668,
|
| 1183 |
+
"grad_norm": 6.40625,
|
| 1184 |
+
"learning_rate": 5.596666666666666e-05,
|
| 1185 |
+
"loss": 0.5754,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.01877777777777778,
|
| 1190 |
+
"grad_norm": 5.59375,
|
| 1191 |
+
"learning_rate": 5.63e-05,
|
| 1192 |
+
"loss": 0.5995,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.01888888888888889,
|
| 1197 |
+
"grad_norm": 9.9375,
|
| 1198 |
+
"learning_rate": 5.6633333333333325e-05,
|
| 1199 |
+
"loss": 0.5614,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.019,
|
| 1204 |
+
"grad_norm": 5.3125,
|
| 1205 |
+
"learning_rate": 5.696666666666666e-05,
|
| 1206 |
+
"loss": 0.5429,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.01911111111111111,
|
| 1211 |
+
"grad_norm": 6.15625,
|
| 1212 |
+
"learning_rate": 5.73e-05,
|
| 1213 |
+
"loss": 0.5681,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.019222222222222224,
|
| 1218 |
+
"grad_norm": 9.625,
|
| 1219 |
+
"learning_rate": 5.763333333333333e-05,
|
| 1220 |
+
"loss": 0.55,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.019333333333333334,
|
| 1225 |
+
"grad_norm": 7.40625,
|
| 1226 |
+
"learning_rate": 5.796666666666666e-05,
|
| 1227 |
+
"loss": 0.5089,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.019444444444444445,
|
| 1232 |
+
"grad_norm": 8.125,
|
| 1233 |
+
"learning_rate": 5.8299999999999994e-05,
|
| 1234 |
+
"loss": 0.575,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.019555555555555555,
|
| 1239 |
+
"grad_norm": 6.59375,
|
| 1240 |
+
"learning_rate": 5.8633333333333326e-05,
|
| 1241 |
+
"loss": 0.5887,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.019666666666666666,
|
| 1246 |
+
"grad_norm": 6.8125,
|
| 1247 |
+
"learning_rate": 5.8966666666666666e-05,
|
| 1248 |
+
"loss": 0.5966,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.019777777777777776,
|
| 1253 |
+
"grad_norm": 4.75,
|
| 1254 |
+
"learning_rate": 5.929999999999999e-05,
|
| 1255 |
+
"loss": 0.5728,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.01988888888888889,
|
| 1260 |
+
"grad_norm": 4.4375,
|
| 1261 |
+
"learning_rate": 5.963333333333333e-05,
|
| 1262 |
+
"loss": 0.5167,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.02,
|
| 1267 |
+
"grad_norm": 6.75,
|
| 1268 |
+
"learning_rate": 5.996666666666666e-05,
|
| 1269 |
+
"loss": 0.4957,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.02011111111111111,
|
| 1274 |
+
"grad_norm": 7.15625,
|
| 1275 |
+
"learning_rate": 6.0299999999999995e-05,
|
| 1276 |
+
"loss": 0.5384,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.02022222222222222,
|
| 1281 |
+
"grad_norm": 5.4375,
|
| 1282 |
+
"learning_rate": 6.063333333333333e-05,
|
| 1283 |
+
"loss": 0.5669,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.02033333333333333,
|
| 1288 |
+
"grad_norm": 5.59375,
|
| 1289 |
+
"learning_rate": 6.096666666666666e-05,
|
| 1290 |
+
"loss": 0.5503,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.020444444444444446,
|
| 1295 |
+
"grad_norm": 4.9375,
|
| 1296 |
+
"learning_rate": 6.13e-05,
|
| 1297 |
+
"loss": 0.5444,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.020555555555555556,
|
| 1302 |
+
"grad_norm": 6.46875,
|
| 1303 |
+
"learning_rate": 6.163333333333333e-05,
|
| 1304 |
+
"loss": 0.55,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.020666666666666667,
|
| 1309 |
+
"grad_norm": 5.6875,
|
| 1310 |
+
"learning_rate": 6.196666666666666e-05,
|
| 1311 |
+
"loss": 0.5482,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.020777777777777777,
|
| 1316 |
+
"grad_norm": 6.84375,
|
| 1317 |
+
"learning_rate": 6.23e-05,
|
| 1318 |
+
"loss": 0.5808,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.020888888888888887,
|
| 1323 |
+
"grad_norm": 4.46875,
|
| 1324 |
+
"learning_rate": 6.263333333333333e-05,
|
| 1325 |
+
"loss": 0.548,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.021,
|
| 1330 |
+
"grad_norm": 4.375,
|
| 1331 |
+
"learning_rate": 6.296666666666666e-05,
|
| 1332 |
+
"loss": 0.5725,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.021111111111111112,
|
| 1337 |
+
"grad_norm": 3.859375,
|
| 1338 |
+
"learning_rate": 6.33e-05,
|
| 1339 |
+
"loss": 0.5176,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.021222222222222222,
|
| 1344 |
+
"grad_norm": 5.84375,
|
| 1345 |
+
"learning_rate": 6.363333333333333e-05,
|
| 1346 |
+
"loss": 0.5197,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.021333333333333333,
|
| 1351 |
+
"grad_norm": 4.6875,
|
| 1352 |
+
"learning_rate": 6.396666666666666e-05,
|
| 1353 |
+
"loss": 0.566,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.021444444444444443,
|
| 1358 |
+
"grad_norm": 5.625,
|
| 1359 |
+
"learning_rate": 6.429999999999999e-05,
|
| 1360 |
+
"loss": 0.5202,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.021555555555555557,
|
| 1365 |
+
"grad_norm": 4.0625,
|
| 1366 |
+
"learning_rate": 6.463333333333332e-05,
|
| 1367 |
+
"loss": 0.5185,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.021666666666666667,
|
| 1372 |
+
"grad_norm": 7.21875,
|
| 1373 |
+
"learning_rate": 6.496666666666666e-05,
|
| 1374 |
+
"loss": 0.5465,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.021777777777777778,
|
| 1379 |
+
"grad_norm": 4.15625,
|
| 1380 |
+
"learning_rate": 6.53e-05,
|
| 1381 |
+
"loss": 0.5223,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.02188888888888889,
|
| 1386 |
+
"grad_norm": 4.25,
|
| 1387 |
+
"learning_rate": 6.563333333333332e-05,
|
| 1388 |
+
"loss": 0.6037,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.022,
|
| 1393 |
+
"grad_norm": 5.53125,
|
| 1394 |
+
"learning_rate": 6.596666666666665e-05,
|
| 1395 |
+
"loss": 0.5452,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.022111111111111113,
|
| 1400 |
+
"grad_norm": 3.890625,
|
| 1401 |
+
"learning_rate": 6.63e-05,
|
| 1402 |
+
"loss": 0.5751,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.022222222222222223,
|
| 1407 |
+
"grad_norm": 3.5625,
|
| 1408 |
+
"learning_rate": 6.663333333333333e-05,
|
| 1409 |
+
"loss": 0.5589,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.022333333333333334,
|
| 1414 |
+
"grad_norm": 3.953125,
|
| 1415 |
+
"learning_rate": 6.696666666666666e-05,
|
| 1416 |
+
"loss": 0.5742,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.022444444444444444,
|
| 1421 |
+
"grad_norm": 4.125,
|
| 1422 |
+
"learning_rate": 6.73e-05,
|
| 1423 |
+
"loss": 0.539,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.022555555555555554,
|
| 1428 |
+
"grad_norm": 5.75,
|
| 1429 |
+
"learning_rate": 6.763333333333333e-05,
|
| 1430 |
+
"loss": 0.5682,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.02266666666666667,
|
| 1435 |
+
"grad_norm": 3.5625,
|
| 1436 |
+
"learning_rate": 6.796666666666666e-05,
|
| 1437 |
+
"loss": 0.5637,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.02277777777777778,
|
| 1442 |
+
"grad_norm": 7.0625,
|
| 1443 |
+
"learning_rate": 6.829999999999999e-05,
|
| 1444 |
+
"loss": 0.5896,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.02288888888888889,
|
| 1449 |
+
"grad_norm": 3.953125,
|
| 1450 |
+
"learning_rate": 6.863333333333333e-05,
|
| 1451 |
+
"loss": 0.5521,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.023,
|
| 1456 |
+
"grad_norm": 6.9375,
|
| 1457 |
+
"learning_rate": 6.896666666666666e-05,
|
| 1458 |
+
"loss": 0.55,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.02311111111111111,
|
| 1463 |
+
"grad_norm": 3.46875,
|
| 1464 |
+
"learning_rate": 6.93e-05,
|
| 1465 |
+
"loss": 0.5617,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.02322222222222222,
|
| 1470 |
+
"grad_norm": 6.5,
|
| 1471 |
+
"learning_rate": 6.963333333333332e-05,
|
| 1472 |
+
"loss": 0.5708,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.023333333333333334,
|
| 1477 |
+
"grad_norm": 5.0625,
|
| 1478 |
+
"learning_rate": 6.996666666666666e-05,
|
| 1479 |
+
"loss": 0.5241,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.023444444444444445,
|
| 1484 |
+
"grad_norm": 7.125,
|
| 1485 |
+
"learning_rate": 7.03e-05,
|
| 1486 |
+
"loss": 0.5633,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.023555555555555555,
|
| 1491 |
+
"grad_norm": 3.078125,
|
| 1492 |
+
"learning_rate": 7.063333333333333e-05,
|
| 1493 |
+
"loss": 0.573,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.023666666666666666,
|
| 1498 |
+
"grad_norm": 4.09375,
|
| 1499 |
+
"learning_rate": 7.096666666666665e-05,
|
| 1500 |
+
"loss": 0.5531,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.023777777777777776,
|
| 1505 |
+
"grad_norm": 4.5,
|
| 1506 |
+
"learning_rate": 7.13e-05,
|
| 1507 |
+
"loss": 0.5203,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.02388888888888889,
|
| 1512 |
+
"grad_norm": 4.78125,
|
| 1513 |
+
"learning_rate": 7.163333333333333e-05,
|
| 1514 |
+
"loss": 0.5045,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.024,
|
| 1519 |
+
"grad_norm": 3.875,
|
| 1520 |
+
"learning_rate": 7.196666666666666e-05,
|
| 1521 |
+
"loss": 0.4908,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.02411111111111111,
|
| 1526 |
+
"grad_norm": 6.53125,
|
| 1527 |
+
"learning_rate": 7.23e-05,
|
| 1528 |
+
"loss": 0.5529,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.02422222222222222,
|
| 1533 |
+
"grad_norm": 4.84375,
|
| 1534 |
+
"learning_rate": 7.263333333333333e-05,
|
| 1535 |
+
"loss": 0.5192,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.024333333333333332,
|
| 1540 |
+
"grad_norm": 3.140625,
|
| 1541 |
+
"learning_rate": 7.296666666666666e-05,
|
| 1542 |
+
"loss": 0.5088,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.024444444444444446,
|
| 1547 |
+
"grad_norm": 5.09375,
|
| 1548 |
+
"learning_rate": 7.329999999999999e-05,
|
| 1549 |
+
"loss": 0.4941,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.024555555555555556,
|
| 1554 |
+
"grad_norm": 4.90625,
|
| 1555 |
+
"learning_rate": 7.363333333333333e-05,
|
| 1556 |
+
"loss": 0.5166,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.024666666666666667,
|
| 1561 |
+
"grad_norm": 3.75,
|
| 1562 |
+
"learning_rate": 7.396666666666666e-05,
|
| 1563 |
+
"loss": 0.5204,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.024777777777777777,
|
| 1568 |
+
"grad_norm": 3.921875,
|
| 1569 |
+
"learning_rate": 7.429999999999999e-05,
|
| 1570 |
+
"loss": 0.496,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.024888888888888887,
|
| 1575 |
+
"grad_norm": 3.609375,
|
| 1576 |
+
"learning_rate": 7.463333333333332e-05,
|
| 1577 |
+
"loss": 0.5035,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.025,
|
| 1582 |
+
"grad_norm": 2.9375,
|
| 1583 |
+
"learning_rate": 7.496666666666665e-05,
|
| 1584 |
+
"loss": 0.5095,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.025111111111111112,
|
| 1589 |
+
"grad_norm": 3.421875,
|
| 1590 |
+
"learning_rate": 7.529999999999999e-05,
|
| 1591 |
+
"loss": 0.5163,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.025222222222222222,
|
| 1596 |
+
"grad_norm": 4.1875,
|
| 1597 |
+
"learning_rate": 7.563333333333333e-05,
|
| 1598 |
+
"loss": 0.5412,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.025333333333333333,
|
| 1603 |
+
"grad_norm": 3.734375,
|
| 1604 |
+
"learning_rate": 7.596666666666667e-05,
|
| 1605 |
+
"loss": 0.5029,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.025444444444444443,
|
| 1610 |
+
"grad_norm": 2.984375,
|
| 1611 |
+
"learning_rate": 7.63e-05,
|
| 1612 |
+
"loss": 0.5206,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.025555555555555557,
|
| 1617 |
+
"grad_norm": 4.0625,
|
| 1618 |
+
"learning_rate": 7.663333333333332e-05,
|
| 1619 |
+
"loss": 0.5263,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.025666666666666667,
|
| 1624 |
+
"grad_norm": 5.78125,
|
| 1625 |
+
"learning_rate": 7.696666666666665e-05,
|
| 1626 |
+
"loss": 0.5031,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.025777777777777778,
|
| 1631 |
+
"grad_norm": 3.890625,
|
| 1632 |
+
"learning_rate": 7.73e-05,
|
| 1633 |
+
"loss": 0.5037,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.02588888888888889,
|
| 1638 |
+
"grad_norm": 4.125,
|
| 1639 |
+
"learning_rate": 7.763333333333333e-05,
|
| 1640 |
+
"loss": 0.4609,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.026,
|
| 1645 |
+
"grad_norm": 4.625,
|
| 1646 |
+
"learning_rate": 7.796666666666666e-05,
|
| 1647 |
+
"loss": 0.4941,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.026111111111111113,
|
| 1652 |
+
"grad_norm": 3.546875,
|
| 1653 |
+
"learning_rate": 7.829999999999999e-05,
|
| 1654 |
+
"loss": 0.5153,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.026222222222222223,
|
| 1659 |
+
"grad_norm": 3.421875,
|
| 1660 |
+
"learning_rate": 7.863333333333334e-05,
|
| 1661 |
+
"loss": 0.4923,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.026333333333333334,
|
| 1666 |
+
"grad_norm": 4.46875,
|
| 1667 |
+
"learning_rate": 7.896666666666667e-05,
|
| 1668 |
+
"loss": 0.5217,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.026444444444444444,
|
| 1673 |
+
"grad_norm": 4.1875,
|
| 1674 |
+
"learning_rate": 7.929999999999999e-05,
|
| 1675 |
+
"loss": 0.5412,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.026555555555555554,
|
| 1680 |
+
"grad_norm": 5.875,
|
| 1681 |
+
"learning_rate": 7.963333333333332e-05,
|
| 1682 |
+
"loss": 0.5329,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.02666666666666667,
|
| 1687 |
+
"grad_norm": 4.5,
|
| 1688 |
+
"learning_rate": 7.996666666666665e-05,
|
| 1689 |
+
"loss": 0.5247,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.02677777777777778,
|
| 1694 |
+
"grad_norm": 4.3125,
|
| 1695 |
+
"learning_rate": 8.029999999999999e-05,
|
| 1696 |
+
"loss": 0.4787,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.02688888888888889,
|
| 1701 |
+
"grad_norm": 3.859375,
|
| 1702 |
+
"learning_rate": 8.063333333333333e-05,
|
| 1703 |
+
"loss": 0.4061,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.027,
|
| 1708 |
+
"grad_norm": 7.625,
|
| 1709 |
+
"learning_rate": 8.096666666666667e-05,
|
| 1710 |
+
"loss": 0.4978,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.02711111111111111,
|
| 1715 |
+
"grad_norm": 5.03125,
|
| 1716 |
+
"learning_rate": 8.13e-05,
|
| 1717 |
+
"loss": 0.5139,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.02722222222222222,
|
| 1722 |
+
"grad_norm": 3.515625,
|
| 1723 |
+
"learning_rate": 8.163333333333333e-05,
|
| 1724 |
+
"loss": 0.5051,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.027333333333333334,
|
| 1729 |
+
"grad_norm": 3.71875,
|
| 1730 |
+
"learning_rate": 8.196666666666665e-05,
|
| 1731 |
+
"loss": 0.4972,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.027444444444444445,
|
| 1736 |
+
"grad_norm": 3.1875,
|
| 1737 |
+
"learning_rate": 8.23e-05,
|
| 1738 |
+
"loss": 0.5039,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.027555555555555555,
|
| 1743 |
+
"grad_norm": 2.625,
|
| 1744 |
+
"learning_rate": 8.263333333333333e-05,
|
| 1745 |
+
"loss": 0.4746,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.027666666666666666,
|
| 1750 |
+
"grad_norm": 4.71875,
|
| 1751 |
+
"learning_rate": 8.296666666666666e-05,
|
| 1752 |
+
"loss": 0.5106,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.027777777777777776,
|
| 1757 |
+
"grad_norm": 3.671875,
|
| 1758 |
+
"learning_rate": 8.329999999999999e-05,
|
| 1759 |
+
"loss": 0.4807,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.02788888888888889,
|
| 1764 |
+
"grad_norm": 4.5625,
|
| 1765 |
+
"learning_rate": 8.363333333333332e-05,
|
| 1766 |
+
"loss": 0.5224,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.028,
|
| 1771 |
+
"grad_norm": 3.28125,
|
| 1772 |
+
"learning_rate": 8.396666666666667e-05,
|
| 1773 |
+
"loss": 0.4969,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.02811111111111111,
|
| 1778 |
+
"grad_norm": 4.25,
|
| 1779 |
+
"learning_rate": 8.43e-05,
|
| 1780 |
+
"loss": 0.4979,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.02822222222222222,
|
| 1785 |
+
"grad_norm": 3.46875,
|
| 1786 |
+
"learning_rate": 8.463333333333332e-05,
|
| 1787 |
+
"loss": 0.5123,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.028333333333333332,
|
| 1792 |
+
"grad_norm": 2.890625,
|
| 1793 |
+
"learning_rate": 8.496666666666665e-05,
|
| 1794 |
+
"loss": 0.5076,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.028444444444444446,
|
| 1799 |
+
"grad_norm": 4.46875,
|
| 1800 |
+
"learning_rate": 8.529999999999999e-05,
|
| 1801 |
+
"loss": 0.4811,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.028555555555555556,
|
| 1806 |
+
"grad_norm": 3.515625,
|
| 1807 |
+
"learning_rate": 8.563333333333333e-05,
|
| 1808 |
+
"loss": 0.4557,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.028666666666666667,
|
| 1813 |
+
"grad_norm": 3.75,
|
| 1814 |
+
"learning_rate": 8.596666666666666e-05,
|
| 1815 |
+
"loss": 0.4741,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.028777777777777777,
|
| 1820 |
+
"grad_norm": 3.546875,
|
| 1821 |
+
"learning_rate": 8.63e-05,
|
| 1822 |
+
"loss": 0.4776,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.028888888888888888,
|
| 1827 |
+
"grad_norm": 3.546875,
|
| 1828 |
+
"learning_rate": 8.663333333333333e-05,
|
| 1829 |
+
"loss": 0.4393,
|
| 1830 |
+
"step": 2600
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.029,
|
| 1834 |
+
"grad_norm": 3.734375,
|
| 1835 |
+
"learning_rate": 8.696666666666665e-05,
|
| 1836 |
+
"loss": 0.4638,
|
| 1837 |
+
"step": 2610
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.029111111111111112,
|
| 1841 |
+
"grad_norm": 3.875,
|
| 1842 |
+
"learning_rate": 8.729999999999998e-05,
|
| 1843 |
+
"loss": 0.4602,
|
| 1844 |
+
"step": 2620
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.029222222222222222,
|
| 1848 |
+
"grad_norm": 3.65625,
|
| 1849 |
+
"learning_rate": 8.763333333333333e-05,
|
| 1850 |
+
"loss": 0.4903,
|
| 1851 |
+
"step": 2630
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.029333333333333333,
|
| 1855 |
+
"grad_norm": 3.125,
|
| 1856 |
+
"learning_rate": 8.796666666666666e-05,
|
| 1857 |
+
"loss": 0.4953,
|
| 1858 |
+
"step": 2640
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.029444444444444443,
|
| 1862 |
+
"grad_norm": 4.21875,
|
| 1863 |
+
"learning_rate": 8.829999999999999e-05,
|
| 1864 |
+
"loss": 0.4572,
|
| 1865 |
+
"step": 2650
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.029555555555555557,
|
| 1869 |
+
"grad_norm": 3.34375,
|
| 1870 |
+
"learning_rate": 8.863333333333332e-05,
|
| 1871 |
+
"loss": 0.5045,
|
| 1872 |
+
"step": 2660
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.029666666666666668,
|
| 1876 |
+
"grad_norm": 4.53125,
|
| 1877 |
+
"learning_rate": 8.896666666666667e-05,
|
| 1878 |
+
"loss": 0.4624,
|
| 1879 |
+
"step": 2670
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.029777777777777778,
|
| 1883 |
+
"grad_norm": 2.140625,
|
| 1884 |
+
"learning_rate": 8.93e-05,
|
| 1885 |
+
"loss": 0.4473,
|
| 1886 |
+
"step": 2680
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.02988888888888889,
|
| 1890 |
+
"grad_norm": 2.640625,
|
| 1891 |
+
"learning_rate": 8.963333333333332e-05,
|
| 1892 |
+
"loss": 0.5067,
|
| 1893 |
+
"step": 2690
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.03,
|
| 1897 |
+
"grad_norm": 3.15625,
|
| 1898 |
+
"learning_rate": 8.996666666666665e-05,
|
| 1899 |
+
"loss": 0.467,
|
| 1900 |
+
"step": 2700
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.030111111111111113,
|
| 1904 |
+
"grad_norm": 4.5,
|
| 1905 |
+
"learning_rate": 9.029999999999999e-05,
|
| 1906 |
+
"loss": 0.5335,
|
| 1907 |
+
"step": 2710
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.030222222222222223,
|
| 1911 |
+
"grad_norm": 2.546875,
|
| 1912 |
+
"learning_rate": 9.063333333333332e-05,
|
| 1913 |
+
"loss": 0.4391,
|
| 1914 |
+
"step": 2720
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.030333333333333334,
|
| 1918 |
+
"grad_norm": 4.75,
|
| 1919 |
+
"learning_rate": 9.096666666666666e-05,
|
| 1920 |
+
"loss": 0.4425,
|
| 1921 |
+
"step": 2730
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.030444444444444444,
|
| 1925 |
+
"grad_norm": 2.4375,
|
| 1926 |
+
"learning_rate": 9.13e-05,
|
| 1927 |
+
"loss": 0.526,
|
| 1928 |
+
"step": 2740
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.030555555555555555,
|
| 1932 |
+
"grad_norm": 4.375,
|
| 1933 |
+
"learning_rate": 9.163333333333333e-05,
|
| 1934 |
+
"loss": 0.5044,
|
| 1935 |
+
"step": 2750
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.030666666666666665,
|
| 1939 |
+
"grad_norm": 3.3125,
|
| 1940 |
+
"learning_rate": 9.196666666666666e-05,
|
| 1941 |
+
"loss": 0.5066,
|
| 1942 |
+
"step": 2760
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.03077777777777778,
|
| 1946 |
+
"grad_norm": 2.71875,
|
| 1947 |
+
"learning_rate": 9.229999999999998e-05,
|
| 1948 |
+
"loss": 0.4502,
|
| 1949 |
+
"step": 2770
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.03088888888888889,
|
| 1953 |
+
"grad_norm": 3.125,
|
| 1954 |
+
"learning_rate": 9.263333333333333e-05,
|
| 1955 |
+
"loss": 0.4847,
|
| 1956 |
+
"step": 2780
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.031,
|
| 1960 |
+
"grad_norm": 3.515625,
|
| 1961 |
+
"learning_rate": 9.296666666666666e-05,
|
| 1962 |
+
"loss": 0.5151,
|
| 1963 |
+
"step": 2790
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.03111111111111111,
|
| 1967 |
+
"grad_norm": 3.40625,
|
| 1968 |
+
"learning_rate": 9.329999999999999e-05,
|
| 1969 |
+
"loss": 0.497,
|
| 1970 |
+
"step": 2800
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.03122222222222222,
|
| 1974 |
+
"grad_norm": 3.109375,
|
| 1975 |
+
"learning_rate": 9.363333333333332e-05,
|
| 1976 |
+
"loss": 0.4864,
|
| 1977 |
+
"step": 2810
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.03133333333333333,
|
| 1981 |
+
"grad_norm": 2.71875,
|
| 1982 |
+
"learning_rate": 9.396666666666666e-05,
|
| 1983 |
+
"loss": 0.4869,
|
| 1984 |
+
"step": 2820
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.03144444444444444,
|
| 1988 |
+
"grad_norm": 2.296875,
|
| 1989 |
+
"learning_rate": 9.43e-05,
|
| 1990 |
+
"loss": 0.4417,
|
| 1991 |
+
"step": 2830
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.03155555555555556,
|
| 1995 |
+
"grad_norm": 2.5,
|
| 1996 |
+
"learning_rate": 9.463333333333333e-05,
|
| 1997 |
+
"loss": 0.4582,
|
| 1998 |
+
"step": 2840
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.03166666666666667,
|
| 2002 |
+
"grad_norm": 3.03125,
|
| 2003 |
+
"learning_rate": 9.496666666666665e-05,
|
| 2004 |
+
"loss": 0.4582,
|
| 2005 |
+
"step": 2850
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.03177777777777778,
|
| 2009 |
+
"grad_norm": 3.140625,
|
| 2010 |
+
"learning_rate": 9.529999999999999e-05,
|
| 2011 |
+
"loss": 0.4409,
|
| 2012 |
+
"step": 2860
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.03188888888888889,
|
| 2016 |
+
"grad_norm": 2.734375,
|
| 2017 |
+
"learning_rate": 9.563333333333332e-05,
|
| 2018 |
+
"loss": 0.4184,
|
| 2019 |
+
"step": 2870
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.032,
|
| 2023 |
+
"grad_norm": 1.9296875,
|
| 2024 |
+
"learning_rate": 9.596666666666666e-05,
|
| 2025 |
+
"loss": 0.4542,
|
| 2026 |
+
"step": 2880
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.03211111111111111,
|
| 2030 |
+
"grad_norm": 3.171875,
|
| 2031 |
+
"learning_rate": 9.63e-05,
|
| 2032 |
+
"loss": 0.4919,
|
| 2033 |
+
"step": 2890
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.03222222222222222,
|
| 2037 |
+
"grad_norm": 3.46875,
|
| 2038 |
+
"learning_rate": 9.663333333333333e-05,
|
| 2039 |
+
"loss": 0.4185,
|
| 2040 |
+
"step": 2900
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.03233333333333333,
|
| 2044 |
+
"grad_norm": 2.453125,
|
| 2045 |
+
"learning_rate": 9.696666666666666e-05,
|
| 2046 |
+
"loss": 0.5011,
|
| 2047 |
+
"step": 2910
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.03244444444444444,
|
| 2051 |
+
"grad_norm": 2.921875,
|
| 2052 |
+
"learning_rate": 9.729999999999998e-05,
|
| 2053 |
+
"loss": 0.4642,
|
| 2054 |
+
"step": 2920
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.03255555555555555,
|
| 2058 |
+
"grad_norm": 2.828125,
|
| 2059 |
+
"learning_rate": 9.763333333333331e-05,
|
| 2060 |
+
"loss": 0.4147,
|
| 2061 |
+
"step": 2930
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.03266666666666666,
|
| 2065 |
+
"grad_norm": 3.1875,
|
| 2066 |
+
"learning_rate": 9.796666666666666e-05,
|
| 2067 |
+
"loss": 0.4494,
|
| 2068 |
+
"step": 2940
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.03277777777777778,
|
| 2072 |
+
"grad_norm": 2.8125,
|
| 2073 |
+
"learning_rate": 9.829999999999999e-05,
|
| 2074 |
+
"loss": 0.4327,
|
| 2075 |
+
"step": 2950
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.03288888888888889,
|
| 2079 |
+
"grad_norm": 2.5,
|
| 2080 |
+
"learning_rate": 9.863333333333332e-05,
|
| 2081 |
+
"loss": 0.3892,
|
| 2082 |
+
"step": 2960
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.033,
|
| 2086 |
+
"grad_norm": 3.5,
|
| 2087 |
+
"learning_rate": 9.896666666666666e-05,
|
| 2088 |
+
"loss": 0.4336,
|
| 2089 |
+
"step": 2970
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.03311111111111111,
|
| 2093 |
+
"grad_norm": 2.75,
|
| 2094 |
+
"learning_rate": 9.93e-05,
|
| 2095 |
+
"loss": 0.4157,
|
| 2096 |
+
"step": 2980
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.03322222222222222,
|
| 2100 |
+
"grad_norm": 2.75,
|
| 2101 |
+
"learning_rate": 9.963333333333333e-05,
|
| 2102 |
+
"loss": 0.4559,
|
| 2103 |
+
"step": 2990
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.03333333333333333,
|
| 2107 |
+
"grad_norm": 2.171875,
|
| 2108 |
+
"learning_rate": 9.996666666666665e-05,
|
| 2109 |
+
"loss": 0.4436,
|
| 2110 |
+
"step": 3000
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.03344444444444444,
|
| 2114 |
+
"grad_norm": 3.875,
|
| 2115 |
+
"learning_rate": 0.00010029999999999998,
|
| 2116 |
+
"loss": 0.454,
|
| 2117 |
+
"step": 3010
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.033555555555555554,
|
| 2121 |
+
"grad_norm": 2.703125,
|
| 2122 |
+
"learning_rate": 0.00010063333333333332,
|
| 2123 |
+
"loss": 0.4623,
|
| 2124 |
+
"step": 3020
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.033666666666666664,
|
| 2128 |
+
"grad_norm": 3.421875,
|
| 2129 |
+
"learning_rate": 0.00010096666666666666,
|
| 2130 |
+
"loss": 0.4503,
|
| 2131 |
+
"step": 3030
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.033777777777777775,
|
| 2135 |
+
"grad_norm": 2.59375,
|
| 2136 |
+
"learning_rate": 0.0001013,
|
| 2137 |
+
"loss": 0.4265,
|
| 2138 |
+
"step": 3040
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.03388888888888889,
|
| 2142 |
+
"grad_norm": 3.484375,
|
| 2143 |
+
"learning_rate": 0.00010163333333333333,
|
| 2144 |
+
"loss": 0.4593,
|
| 2145 |
+
"step": 3050
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.034,
|
| 2149 |
+
"grad_norm": 3.640625,
|
| 2150 |
+
"learning_rate": 0.00010196666666666666,
|
| 2151 |
+
"loss": 0.4418,
|
| 2152 |
+
"step": 3060
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.03411111111111111,
|
| 2156 |
+
"grad_norm": 4.21875,
|
| 2157 |
+
"learning_rate": 0.00010229999999999999,
|
| 2158 |
+
"loss": 0.4592,
|
| 2159 |
+
"step": 3070
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.03422222222222222,
|
| 2163 |
+
"grad_norm": 2.15625,
|
| 2164 |
+
"learning_rate": 0.00010263333333333331,
|
| 2165 |
+
"loss": 0.4317,
|
| 2166 |
+
"step": 3080
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.034333333333333334,
|
| 2170 |
+
"grad_norm": 2.71875,
|
| 2171 |
+
"learning_rate": 0.00010296666666666666,
|
| 2172 |
+
"loss": 0.4194,
|
| 2173 |
+
"step": 3090
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.034444444444444444,
|
| 2177 |
+
"grad_norm": 3.109375,
|
| 2178 |
+
"learning_rate": 0.00010329999999999999,
|
| 2179 |
+
"loss": 0.4041,
|
| 2180 |
+
"step": 3100
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.034555555555555555,
|
| 2184 |
+
"grad_norm": 2.75,
|
| 2185 |
+
"learning_rate": 0.00010363333333333332,
|
| 2186 |
+
"loss": 0.4533,
|
| 2187 |
+
"step": 3110
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.034666666666666665,
|
| 2191 |
+
"grad_norm": 2.921875,
|
| 2192 |
+
"learning_rate": 0.00010396666666666665,
|
| 2193 |
+
"loss": 0.4373,
|
| 2194 |
+
"step": 3120
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.034777777777777776,
|
| 2198 |
+
"grad_norm": 4.15625,
|
| 2199 |
+
"learning_rate": 0.0001043,
|
| 2200 |
+
"loss": 0.4325,
|
| 2201 |
+
"step": 3130
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.034888888888888886,
|
| 2205 |
+
"grad_norm": 2.46875,
|
| 2206 |
+
"learning_rate": 0.00010463333333333333,
|
| 2207 |
+
"loss": 0.4601,
|
| 2208 |
+
"step": 3140
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.035,
|
| 2212 |
+
"grad_norm": 2.875,
|
| 2213 |
+
"learning_rate": 0.00010496666666666667,
|
| 2214 |
+
"loss": 0.4523,
|
| 2215 |
+
"step": 3150
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.035111111111111114,
|
| 2219 |
+
"grad_norm": 2.796875,
|
| 2220 |
+
"learning_rate": 0.00010529999999999998,
|
| 2221 |
+
"loss": 0.432,
|
| 2222 |
+
"step": 3160
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.035222222222222224,
|
| 2226 |
+
"grad_norm": 3.28125,
|
| 2227 |
+
"learning_rate": 0.00010563333333333332,
|
| 2228 |
+
"loss": 0.4423,
|
| 2229 |
+
"step": 3170
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.035333333333333335,
|
| 2233 |
+
"grad_norm": 3.5,
|
| 2234 |
+
"learning_rate": 0.00010596666666666665,
|
| 2235 |
+
"loss": 0.4262,
|
| 2236 |
+
"step": 3180
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.035444444444444445,
|
| 2240 |
+
"grad_norm": 2.78125,
|
| 2241 |
+
"learning_rate": 0.0001063,
|
| 2242 |
+
"loss": 0.4211,
|
| 2243 |
+
"step": 3190
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.035555555555555556,
|
| 2247 |
+
"grad_norm": 3.765625,
|
| 2248 |
+
"learning_rate": 0.00010663333333333333,
|
| 2249 |
+
"loss": 0.489,
|
| 2250 |
+
"step": 3200
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.035666666666666666,
|
| 2254 |
+
"grad_norm": 2.984375,
|
| 2255 |
+
"learning_rate": 0.00010696666666666666,
|
| 2256 |
+
"loss": 0.46,
|
| 2257 |
+
"step": 3210
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.035777777777777776,
|
| 2261 |
+
"grad_norm": 3.15625,
|
| 2262 |
+
"learning_rate": 0.00010729999999999999,
|
| 2263 |
+
"loss": 0.4536,
|
| 2264 |
+
"step": 3220
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.03588888888888889,
|
| 2268 |
+
"grad_norm": 2.3125,
|
| 2269 |
+
"learning_rate": 0.00010763333333333331,
|
| 2270 |
+
"loss": 0.4764,
|
| 2271 |
+
"step": 3230
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.036,
|
| 2275 |
+
"grad_norm": 3.171875,
|
| 2276 |
+
"learning_rate": 0.00010796666666666666,
|
| 2277 |
+
"loss": 0.4262,
|
| 2278 |
+
"step": 3240
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.03611111111111111,
|
| 2282 |
+
"grad_norm": 2.40625,
|
| 2283 |
+
"learning_rate": 0.00010829999999999999,
|
| 2284 |
+
"loss": 0.4402,
|
| 2285 |
+
"step": 3250
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 0.036222222222222225,
|
| 2289 |
+
"grad_norm": 3.71875,
|
| 2290 |
+
"learning_rate": 0.00010863333333333332,
|
| 2291 |
+
"loss": 0.4269,
|
| 2292 |
+
"step": 3260
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 0.036333333333333336,
|
| 2296 |
+
"grad_norm": 3.0,
|
| 2297 |
+
"learning_rate": 0.00010896666666666665,
|
| 2298 |
+
"loss": 0.4828,
|
| 2299 |
+
"step": 3270
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 0.036444444444444446,
|
| 2303 |
+
"grad_norm": 2.796875,
|
| 2304 |
+
"learning_rate": 0.00010929999999999999,
|
| 2305 |
+
"loss": 0.4634,
|
| 2306 |
+
"step": 3280
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.036555555555555556,
|
| 2310 |
+
"grad_norm": 1.90625,
|
| 2311 |
+
"learning_rate": 0.00010963333333333333,
|
| 2312 |
+
"loss": 0.4246,
|
| 2313 |
+
"step": 3290
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.03666666666666667,
|
| 2317 |
+
"grad_norm": 2.25,
|
| 2318 |
+
"learning_rate": 0.00010996666666666667,
|
| 2319 |
+
"loss": 0.4753,
|
| 2320 |
+
"step": 3300
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.03677777777777778,
|
| 2324 |
+
"grad_norm": 2.53125,
|
| 2325 |
+
"learning_rate": 0.00011029999999999998,
|
| 2326 |
+
"loss": 0.4409,
|
| 2327 |
+
"step": 3310
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.03688888888888889,
|
| 2331 |
+
"grad_norm": 3.265625,
|
| 2332 |
+
"learning_rate": 0.00011063333333333332,
|
| 2333 |
+
"loss": 0.4434,
|
| 2334 |
+
"step": 3320
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.037,
|
| 2338 |
+
"grad_norm": 2.875,
|
| 2339 |
+
"learning_rate": 0.00011096666666666665,
|
| 2340 |
+
"loss": 0.4453,
|
| 2341 |
+
"step": 3330
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.03711111111111111,
|
| 2345 |
+
"grad_norm": 1.828125,
|
| 2346 |
+
"learning_rate": 0.0001113,
|
| 2347 |
+
"loss": 0.4237,
|
| 2348 |
+
"step": 3340
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.03722222222222222,
|
| 2352 |
+
"grad_norm": 2.203125,
|
| 2353 |
+
"learning_rate": 0.00011163333333333333,
|
| 2354 |
+
"loss": 0.432,
|
| 2355 |
+
"step": 3350
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.037333333333333336,
|
| 2359 |
+
"grad_norm": 3.0,
|
| 2360 |
+
"learning_rate": 0.00011196666666666666,
|
| 2361 |
+
"loss": 0.4681,
|
| 2362 |
+
"step": 3360
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.03744444444444445,
|
| 2366 |
+
"grad_norm": 3.140625,
|
| 2367 |
+
"learning_rate": 0.00011229999999999999,
|
| 2368 |
+
"loss": 0.4333,
|
| 2369 |
+
"step": 3370
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.03755555555555556,
|
| 2373 |
+
"grad_norm": 2.71875,
|
| 2374 |
+
"learning_rate": 0.00011263333333333332,
|
| 2375 |
+
"loss": 0.4415,
|
| 2376 |
+
"step": 3380
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.03766666666666667,
|
| 2380 |
+
"grad_norm": 3.90625,
|
| 2381 |
+
"learning_rate": 0.00011296666666666664,
|
| 2382 |
+
"loss": 0.457,
|
| 2383 |
+
"step": 3390
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.03777777777777778,
|
| 2387 |
+
"grad_norm": 2.25,
|
| 2388 |
+
"learning_rate": 0.00011329999999999999,
|
| 2389 |
+
"loss": 0.4225,
|
| 2390 |
+
"step": 3400
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.03788888888888889,
|
| 2394 |
+
"grad_norm": 2.875,
|
| 2395 |
+
"learning_rate": 0.00011363333333333332,
|
| 2396 |
+
"loss": 0.3935,
|
| 2397 |
+
"step": 3410
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.038,
|
| 2401 |
+
"grad_norm": 3.390625,
|
| 2402 |
+
"learning_rate": 0.00011396666666666665,
|
| 2403 |
+
"loss": 0.4559,
|
| 2404 |
+
"step": 3420
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.03811111111111111,
|
| 2408 |
+
"grad_norm": 2.5625,
|
| 2409 |
+
"learning_rate": 0.00011429999999999999,
|
| 2410 |
+
"loss": 0.4471,
|
| 2411 |
+
"step": 3430
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.03822222222222222,
|
| 2415 |
+
"grad_norm": 2.40625,
|
| 2416 |
+
"learning_rate": 0.00011463333333333333,
|
| 2417 |
+
"loss": 0.4276,
|
| 2418 |
+
"step": 3440
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.03833333333333333,
|
| 2422 |
+
"grad_norm": 2.109375,
|
| 2423 |
+
"learning_rate": 0.00011496666666666666,
|
| 2424 |
+
"loss": 0.4431,
|
| 2425 |
+
"step": 3450
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.03844444444444445,
|
| 2429 |
+
"grad_norm": 2.890625,
|
| 2430 |
+
"learning_rate": 0.0001153,
|
| 2431 |
+
"loss": 0.4208,
|
| 2432 |
+
"step": 3460
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.03855555555555556,
|
| 2436 |
+
"grad_norm": 2.890625,
|
| 2437 |
+
"learning_rate": 0.00011563333333333332,
|
| 2438 |
+
"loss": 0.4508,
|
| 2439 |
+
"step": 3470
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.03866666666666667,
|
| 2443 |
+
"grad_norm": 2.609375,
|
| 2444 |
+
"learning_rate": 0.00011596666666666665,
|
| 2445 |
+
"loss": 0.444,
|
| 2446 |
+
"step": 3480
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.03877777777777778,
|
| 2450 |
+
"grad_norm": 2.296875,
|
| 2451 |
+
"learning_rate": 0.00011629999999999998,
|
| 2452 |
+
"loss": 0.4209,
|
| 2453 |
+
"step": 3490
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.03888888888888889,
|
| 2457 |
+
"grad_norm": 2.28125,
|
| 2458 |
+
"learning_rate": 0.00011663333333333333,
|
| 2459 |
+
"loss": 0.4227,
|
| 2460 |
+
"step": 3500
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.039,
|
| 2464 |
+
"grad_norm": 2.28125,
|
| 2465 |
+
"learning_rate": 0.00011696666666666666,
|
| 2466 |
+
"loss": 0.419,
|
| 2467 |
+
"step": 3510
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.03911111111111111,
|
| 2471 |
+
"grad_norm": 4.03125,
|
| 2472 |
+
"learning_rate": 0.00011729999999999999,
|
| 2473 |
+
"loss": 0.4519,
|
| 2474 |
+
"step": 3520
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.03922222222222222,
|
| 2478 |
+
"grad_norm": 2.265625,
|
| 2479 |
+
"learning_rate": 0.00011763333333333332,
|
| 2480 |
+
"loss": 0.3913,
|
| 2481 |
+
"step": 3530
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.03933333333333333,
|
| 2485 |
+
"grad_norm": 3.515625,
|
| 2486 |
+
"learning_rate": 0.00011796666666666664,
|
| 2487 |
+
"loss": 0.4594,
|
| 2488 |
+
"step": 3540
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.03944444444444444,
|
| 2492 |
+
"grad_norm": 2.328125,
|
| 2493 |
+
"learning_rate": 0.00011829999999999999,
|
| 2494 |
+
"loss": 0.4555,
|
| 2495 |
+
"step": 3550
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.03955555555555555,
|
| 2499 |
+
"grad_norm": 2.796875,
|
| 2500 |
+
"learning_rate": 0.00011863333333333332,
|
| 2501 |
+
"loss": 0.4405,
|
| 2502 |
+
"step": 3560
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.03966666666666667,
|
| 2506 |
+
"grad_norm": 1.96875,
|
| 2507 |
+
"learning_rate": 0.00011896666666666665,
|
| 2508 |
+
"loss": 0.372,
|
| 2509 |
+
"step": 3570
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.03977777777777778,
|
| 2513 |
+
"grad_norm": 2.078125,
|
| 2514 |
+
"learning_rate": 0.00011929999999999999,
|
| 2515 |
+
"loss": 0.4217,
|
| 2516 |
+
"step": 3580
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.03988888888888889,
|
| 2520 |
+
"grad_norm": 2.734375,
|
| 2521 |
+
"learning_rate": 0.00011963333333333333,
|
| 2522 |
+
"loss": 0.419,
|
| 2523 |
+
"step": 3590
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.04,
|
| 2527 |
+
"grad_norm": 2.328125,
|
| 2528 |
+
"learning_rate": 0.00011996666666666666,
|
| 2529 |
+
"loss": 0.4318,
|
| 2530 |
+
"step": 3600
|
| 2531 |
+
}
|
| 2532 |
+
],
|
| 2533 |
+
"logging_steps": 10,
|
| 2534 |
+
"max_steps": 90000,
|
| 2535 |
+
"num_input_tokens_seen": 0,
|
| 2536 |
+
"num_train_epochs": 9223372036854775807,
|
| 2537 |
+
"save_steps": 3600,
|
| 2538 |
+
"stateful_callbacks": {
|
| 2539 |
+
"TrainerControl": {
|
| 2540 |
+
"args": {
|
| 2541 |
+
"should_epoch_stop": false,
|
| 2542 |
+
"should_evaluate": false,
|
| 2543 |
+
"should_log": false,
|
| 2544 |
+
"should_save": true,
|
| 2545 |
+
"should_training_stop": false
|
| 2546 |
+
},
|
| 2547 |
+
"attributes": {}
|
| 2548 |
+
}
|
| 2549 |
+
},
|
| 2550 |
+
"total_flos": 1.2310110527207506e+18,
|
| 2551 |
+
"train_batch_size": 8,
|
| 2552 |
+
"trial_name": null,
|
| 2553 |
+
"trial_params": null
|
| 2554 |
+
}
|
pt-d-llada-250M_fineweb-20B-4clusters_24h/router/checkpoint-3600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e508821fa75ec77f2c09d6b42e3d5253552126bff92a8e89b434ab044c2275fb
|
| 3 |
+
size 6161
|