Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- checkpoint-315/config.json +39 -0
- checkpoint-315/generation_config.json +12 -0
- checkpoint-315/model-00001-of-00004.safetensors +3 -0
- checkpoint-315/model-00002-of-00004.safetensors +3 -0
- checkpoint-315/model-00003-of-00004.safetensors +3 -0
- checkpoint-315/model-00004-of-00004.safetensors +3 -0
- checkpoint-315/model.safetensors.index.json +298 -0
- checkpoint-315/special_tokens_map.json +26 -0
- checkpoint-315/tokenizer.json +3 -0
- checkpoint-315/tokenizer_config.json +2069 -0
- checkpoint-315/training_args.bin +3 -0
- nohup.out +2 -0
- trainer_log.jsonl +315 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-315/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-315/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 128000,
|
| 8 |
+
"eos_token_id": [
|
| 9 |
+
128001,
|
| 10 |
+
128008,
|
| 11 |
+
128009
|
| 12 |
+
],
|
| 13 |
+
"head_dim": 128,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 4096,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 14336,
|
| 18 |
+
"max_position_embeddings": 131072,
|
| 19 |
+
"mlp_bias": false,
|
| 20 |
+
"model_type": "llama",
|
| 21 |
+
"num_attention_heads": 32,
|
| 22 |
+
"num_hidden_layers": 32,
|
| 23 |
+
"num_key_value_heads": 8,
|
| 24 |
+
"pretraining_tp": 1,
|
| 25 |
+
"rms_norm_eps": 1e-05,
|
| 26 |
+
"rope_scaling": {
|
| 27 |
+
"factor": 8.0,
|
| 28 |
+
"high_freq_factor": 4.0,
|
| 29 |
+
"low_freq_factor": 1.0,
|
| 30 |
+
"original_max_position_embeddings": 8192,
|
| 31 |
+
"rope_type": "llama3"
|
| 32 |
+
},
|
| 33 |
+
"rope_theta": 500000.0,
|
| 34 |
+
"tie_word_embeddings": false,
|
| 35 |
+
"torch_dtype": "bfloat16",
|
| 36 |
+
"transformers_version": "4.50.0",
|
| 37 |
+
"use_cache": false,
|
| 38 |
+
"vocab_size": 128256
|
| 39 |
+
}
|
checkpoint-315/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
+
"transformers_version": "4.50.0"
|
| 12 |
+
}
|
checkpoint-315/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81f49c6a754df5f115e7eedd41dc2b7e310b01933caeabbc01e92625b2c3d0d1
|
| 3 |
+
size 4976698672
|
checkpoint-315/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92e027e90d3e3c9d58a127cb20fbea2456f1070b19c585bbbfae08e0911a312f
|
| 3 |
+
size 4999802720
|
checkpoint-315/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10b716a393f6384d4f55e9bc1761a2f5b18d846614725419a074cbb82c53618d
|
| 3 |
+
size 4915916176
|
checkpoint-315/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62c7050e61499a80b102cb9c49ea41c1a98bc72f1d92ee85071392f6a78ff921
|
| 3 |
+
size 1168138808
|
checkpoint-315/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16060522496
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 296 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 297 |
+
}
|
| 298 |
+
}
|
checkpoint-315/special_tokens_map.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|eom_id|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"bos_token": {
|
| 12 |
+
"content": "<|begin_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|eot_id|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"pad_token": "<|eot_id|>"
|
| 26 |
+
}
|
checkpoint-315/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
checkpoint-315/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2069 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"additional_special_tokens": [
|
| 2053 |
+
"<|eom_id|>"
|
| 2054 |
+
],
|
| 2055 |
+
"bos_token": "<|begin_of_text|>",
|
| 2056 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
| 2057 |
+
"clean_up_tokenization_spaces": true,
|
| 2058 |
+
"eos_token": "<|eot_id|>",
|
| 2059 |
+
"extra_special_tokens": {},
|
| 2060 |
+
"model_input_names": [
|
| 2061 |
+
"input_ids",
|
| 2062 |
+
"attention_mask"
|
| 2063 |
+
],
|
| 2064 |
+
"model_max_length": 131072,
|
| 2065 |
+
"pad_token": "<|eot_id|>",
|
| 2066 |
+
"padding_side": "right",
|
| 2067 |
+
"split_special_tokens": false,
|
| 2068 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
| 2069 |
+
}
|
checkpoint-315/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b97d227afa516db35c263c19b2432b0f0b20fc0ffbab9fe6b273dbe91f7f1bfd
|
| 3 |
+
size 8017
|
nohup.out
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Runpod config file not found, please run `runpodctl config` to create it
|
| 2 |
+
pod "5maxhmrny8tjgx" removed
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,315 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 315, "loss": 2.3218, "lr": 4.999875667389858e-05, "epoch": 0.015841584158415842, "percentage": 0.32, "elapsed_time": "0:00:23", "remaining_time": "2:03:29", "throughput": 11109.01, "total_tokens": 262144}
|
| 2 |
+
{"current_steps": 2, "total_steps": 315, "loss": 3.4992, "lr": 4.999502681926309e-05, "epoch": 0.031683168316831684, "percentage": 0.63, "elapsed_time": "0:00:46", "remaining_time": "2:00:41", "throughput": 11330.4, "total_tokens": 524288}
|
| 3 |
+
{"current_steps": 3, "total_steps": 315, "loss": 2.6702, "lr": 4.9988810807087584e-05, "epoch": 0.047524752475247525, "percentage": 0.95, "elapsed_time": "0:01:08", "remaining_time": "1:59:21", "throughput": 11420.79, "total_tokens": 786432}
|
| 4 |
+
{"current_steps": 4, "total_steps": 315, "loss": 2.3942, "lr": 4.998010925565448e-05, "epoch": 0.06336633663366337, "percentage": 1.27, "elapsed_time": "0:01:31", "remaining_time": "1:58:29", "throughput": 11466.64, "total_tokens": 1048576}
|
| 5 |
+
{"current_steps": 5, "total_steps": 315, "loss": 2.4923, "lr": 4.996892303047306e-05, "epoch": 0.07920792079207921, "percentage": 1.59, "elapsed_time": "0:01:54", "remaining_time": "1:57:53", "throughput": 11488.84, "total_tokens": 1310720}
|
| 6 |
+
{"current_steps": 6, "total_steps": 315, "loss": 2.2646, "lr": 4.9955253244193375e-05, "epoch": 0.09504950495049505, "percentage": 1.9, "elapsed_time": "0:02:16", "remaining_time": "1:57:17", "throughput": 11510.89, "total_tokens": 1572864}
|
| 7 |
+
{"current_steps": 7, "total_steps": 315, "loss": 2.0938, "lr": 4.993910125649561e-05, "epoch": 0.11089108910891089, "percentage": 2.22, "elapsed_time": "0:02:39", "remaining_time": "1:56:44", "throughput": 11527.0, "total_tokens": 1835008}
|
| 8 |
+
{"current_steps": 8, "total_steps": 315, "loss": 2.0191, "lr": 4.992046867395478e-05, "epoch": 0.12673267326732673, "percentage": 2.54, "elapsed_time": "0:03:01", "remaining_time": "1:56:14", "throughput": 11538.25, "total_tokens": 2097152}
|
| 9 |
+
{"current_steps": 9, "total_steps": 315, "loss": 2.0952, "lr": 4.989935734988098e-05, "epoch": 0.14257425742574256, "percentage": 2.86, "elapsed_time": "0:03:24", "remaining_time": "1:55:47", "throughput": 11545.75, "total_tokens": 2359296}
|
| 10 |
+
{"current_steps": 10, "total_steps": 315, "loss": 1.9112, "lr": 4.987576938413504e-05, "epoch": 0.15841584158415842, "percentage": 3.17, "elapsed_time": "0:03:46", "remaining_time": "1:55:19", "throughput": 11554.39, "total_tokens": 2621440}
|
| 11 |
+
{"current_steps": 11, "total_steps": 315, "loss": 1.9916, "lr": 4.984970712291963e-05, "epoch": 0.17425742574257425, "percentage": 3.49, "elapsed_time": "0:04:09", "remaining_time": "1:54:52", "throughput": 11561.66, "total_tokens": 2883584}
|
| 12 |
+
{"current_steps": 12, "total_steps": 315, "loss": 1.9434, "lr": 4.9821173158545936e-05, "epoch": 0.1900990099009901, "percentage": 3.81, "elapsed_time": "0:04:31", "remaining_time": "1:54:26", "throughput": 11567.18, "total_tokens": 3145728}
|
| 13 |
+
{"current_steps": 13, "total_steps": 315, "loss": 1.9084, "lr": 4.9790170329175754e-05, "epoch": 0.20594059405940593, "percentage": 4.13, "elapsed_time": "0:04:54", "remaining_time": "1:54:01", "throughput": 11572.39, "total_tokens": 3407872}
|
| 14 |
+
{"current_steps": 14, "total_steps": 315, "loss": 1.887, "lr": 4.975670171853926e-05, "epoch": 0.22178217821782178, "percentage": 4.44, "elapsed_time": "0:05:17", "remaining_time": "1:53:36", "throughput": 11576.46, "total_tokens": 3670016}
|
| 15 |
+
{"current_steps": 15, "total_steps": 315, "loss": 1.8368, "lr": 4.972077065562821e-05, "epoch": 0.2376237623762376, "percentage": 4.76, "elapsed_time": "0:05:39", "remaining_time": "1:53:11", "throughput": 11579.52, "total_tokens": 3932160}
|
| 16 |
+
{"current_steps": 16, "total_steps": 315, "loss": 1.7729, "lr": 4.9682380714364897e-05, "epoch": 0.25346534653465347, "percentage": 5.08, "elapsed_time": "0:06:02", "remaining_time": "1:52:46", "throughput": 11583.22, "total_tokens": 4194304}
|
| 17 |
+
{"current_steps": 17, "total_steps": 315, "loss": 1.8139, "lr": 4.964153571324658e-05, "epoch": 0.2693069306930693, "percentage": 5.4, "elapsed_time": "0:06:24", "remaining_time": "1:52:22", "throughput": 11586.04, "total_tokens": 4456448}
|
| 18 |
+
{"current_steps": 18, "total_steps": 315, "loss": 1.7543, "lr": 4.959823971496574e-05, "epoch": 0.2851485148514851, "percentage": 5.71, "elapsed_time": "0:06:47", "remaining_time": "1:51:58", "throughput": 11588.15, "total_tokens": 4718592}
|
| 19 |
+
{"current_steps": 19, "total_steps": 315, "loss": 1.7287, "lr": 4.9552497026005974e-05, "epoch": 0.300990099009901, "percentage": 6.03, "elapsed_time": "0:07:09", "remaining_time": "1:51:35", "throughput": 11589.87, "total_tokens": 4980736}
|
| 20 |
+
{"current_steps": 20, "total_steps": 315, "loss": 1.7471, "lr": 4.9504312196213596e-05, "epoch": 0.31683168316831684, "percentage": 6.35, "elapsed_time": "0:07:32", "remaining_time": "1:51:10", "throughput": 11592.36, "total_tokens": 5242880}
|
| 21 |
+
{"current_steps": 21, "total_steps": 315, "loss": 1.6805, "lr": 4.9453690018345144e-05, "epoch": 0.3326732673267327, "percentage": 6.67, "elapsed_time": "0:07:54", "remaining_time": "1:50:47", "throughput": 11593.94, "total_tokens": 5505024}
|
| 22 |
+
{"current_steps": 22, "total_steps": 315, "loss": 1.6845, "lr": 4.940063552759061e-05, "epoch": 0.3485148514851485, "percentage": 6.98, "elapsed_time": "0:08:17", "remaining_time": "1:50:23", "throughput": 11595.65, "total_tokens": 5767168}
|
| 23 |
+
{"current_steps": 23, "total_steps": 315, "loss": 1.6713, "lr": 4.934515400107266e-05, "epoch": 0.36435643564356435, "percentage": 7.3, "elapsed_time": "0:08:39", "remaining_time": "1:50:00", "throughput": 11597.22, "total_tokens": 6029312}
|
| 24 |
+
{"current_steps": 24, "total_steps": 315, "loss": 1.681, "lr": 4.928725095732169e-05, "epoch": 0.3801980198019802, "percentage": 7.62, "elapsed_time": "0:09:02", "remaining_time": "1:49:37", "throughput": 11597.51, "total_tokens": 6291456}
|
| 25 |
+
{"current_steps": 25, "total_steps": 315, "loss": 1.6459, "lr": 4.922693215572695e-05, "epoch": 0.39603960396039606, "percentage": 7.94, "elapsed_time": "0:09:25", "remaining_time": "1:49:14", "throughput": 11597.84, "total_tokens": 6553600}
|
| 26 |
+
{"current_steps": 26, "total_steps": 315, "loss": 1.6754, "lr": 4.916420359596368e-05, "epoch": 0.41188118811881186, "percentage": 8.25, "elapsed_time": "0:09:47", "remaining_time": "1:48:51", "throughput": 11598.56, "total_tokens": 6815744}
|
| 27 |
+
{"current_steps": 27, "total_steps": 315, "loss": 1.6168, "lr": 4.909907151739633e-05, "epoch": 0.4277227722772277, "percentage": 8.57, "elapsed_time": "0:10:10", "remaining_time": "1:48:28", "throughput": 11599.44, "total_tokens": 7077888}
|
| 28 |
+
{"current_steps": 28, "total_steps": 315, "loss": 1.6399, "lr": 4.9031542398457974e-05, "epoch": 0.44356435643564357, "percentage": 8.89, "elapsed_time": "0:10:32", "remaining_time": "1:48:05", "throughput": 11600.39, "total_tokens": 7340032}
|
| 29 |
+
{"current_steps": 29, "total_steps": 315, "loss": 1.6318, "lr": 4.896162295600589e-05, "epoch": 0.4594059405940594, "percentage": 9.21, "elapsed_time": "0:10:55", "remaining_time": "1:47:42", "throughput": 11601.42, "total_tokens": 7602176}
|
| 30 |
+
{"current_steps": 30, "total_steps": 315, "loss": 1.6046, "lr": 4.888932014465352e-05, "epoch": 0.4752475247524752, "percentage": 9.52, "elapsed_time": "0:11:17", "remaining_time": "1:47:19", "throughput": 11602.41, "total_tokens": 7864320}
|
| 31 |
+
{"current_steps": 31, "total_steps": 315, "loss": 1.6143, "lr": 4.881464115607865e-05, "epoch": 0.4910891089108911, "percentage": 9.84, "elapsed_time": "0:11:40", "remaining_time": "1:46:56", "throughput": 11603.45, "total_tokens": 8126464}
|
| 32 |
+
{"current_steps": 32, "total_steps": 315, "loss": 1.6118, "lr": 4.8737593418308156e-05, "epoch": 0.5069306930693069, "percentage": 10.16, "elapsed_time": "0:12:02", "remaining_time": "1:46:33", "throughput": 11603.87, "total_tokens": 8388608}
|
| 33 |
+
{"current_steps": 33, "total_steps": 315, "loss": 1.6007, "lr": 4.865818459497911e-05, "epoch": 0.5227722772277228, "percentage": 10.48, "elapsed_time": "0:12:25", "remaining_time": "1:46:10", "throughput": 11604.71, "total_tokens": 8650752}
|
| 34 |
+
{"current_steps": 34, "total_steps": 315, "loss": 1.5592, "lr": 4.8576422584576514e-05, "epoch": 0.5386138613861386, "percentage": 10.79, "elapsed_time": "0:12:47", "remaining_time": "1:45:47", "throughput": 11605.45, "total_tokens": 8912896}
|
| 35 |
+
{"current_steps": 35, "total_steps": 315, "loss": 1.5396, "lr": 4.849231551964771e-05, "epoch": 0.5544554455445545, "percentage": 11.11, "elapsed_time": "0:13:10", "remaining_time": "1:45:24", "throughput": 11606.01, "total_tokens": 9175040}
|
| 36 |
+
{"current_steps": 36, "total_steps": 315, "loss": 1.5477, "lr": 4.8405871765993433e-05, "epoch": 0.5702970297029702, "percentage": 11.43, "elapsed_time": "0:13:33", "remaining_time": "1:45:01", "throughput": 11606.54, "total_tokens": 9437184}
|
| 37 |
+
{"current_steps": 37, "total_steps": 315, "loss": 1.5415, "lr": 4.8317099921835697e-05, "epoch": 0.5861386138613861, "percentage": 11.75, "elapsed_time": "0:13:55", "remaining_time": "1:44:38", "throughput": 11606.88, "total_tokens": 9699328}
|
| 38 |
+
{"current_steps": 38, "total_steps": 315, "loss": 1.5087, "lr": 4.822600881696256e-05, "epoch": 0.601980198019802, "percentage": 12.06, "elapsed_time": "0:14:18", "remaining_time": "1:44:15", "throughput": 11607.26, "total_tokens": 9961472}
|
| 39 |
+
{"current_steps": 39, "total_steps": 315, "loss": 1.5329, "lr": 4.813260751184992e-05, "epoch": 0.6178217821782178, "percentage": 12.38, "elapsed_time": "0:14:40", "remaining_time": "1:43:53", "throughput": 11607.48, "total_tokens": 10223616}
|
| 40 |
+
{"current_steps": 40, "total_steps": 315, "loss": 1.5234, "lr": 4.803690529676019e-05, "epoch": 0.6336633663366337, "percentage": 12.7, "elapsed_time": "0:15:03", "remaining_time": "1:43:30", "throughput": 11607.68, "total_tokens": 10485760}
|
| 41 |
+
{"current_steps": 41, "total_steps": 315, "loss": 1.5128, "lr": 4.7938911690818347e-05, "epoch": 0.6495049504950495, "percentage": 13.02, "elapsed_time": "0:15:25", "remaining_time": "1:43:07", "throughput": 11608.27, "total_tokens": 10747904}
|
| 42 |
+
{"current_steps": 42, "total_steps": 315, "loss": 1.5069, "lr": 4.783863644106502e-05, "epoch": 0.6653465346534654, "percentage": 13.33, "elapsed_time": "0:15:48", "remaining_time": "1:42:44", "throughput": 11608.47, "total_tokens": 11010048}
|
| 43 |
+
{"current_steps": 43, "total_steps": 315, "loss": 1.5214, "lr": 4.773608952148706e-05, "epoch": 0.6811881188118812, "percentage": 13.65, "elapsed_time": "0:16:11", "remaining_time": "1:42:22", "throughput": 11608.72, "total_tokens": 11272192}
|
| 44 |
+
{"current_steps": 44, "total_steps": 315, "loss": 1.503, "lr": 4.763128113202537e-05, "epoch": 0.697029702970297, "percentage": 13.97, "elapsed_time": "0:16:33", "remaining_time": "1:41:59", "throughput": 11609.25, "total_tokens": 11534336}
|
| 45 |
+
{"current_steps": 45, "total_steps": 315, "loss": 1.48, "lr": 4.752422169756048e-05, "epoch": 0.7128712871287128, "percentage": 14.29, "elapsed_time": "0:16:56", "remaining_time": "1:41:36", "throughput": 11609.48, "total_tokens": 11796480}
|
| 46 |
+
{"current_steps": 46, "total_steps": 315, "loss": 1.5072, "lr": 4.7414921866875524e-05, "epoch": 0.7287128712871287, "percentage": 14.6, "elapsed_time": "0:17:18", "remaining_time": "1:41:14", "throughput": 11609.5, "total_tokens": 12058624}
|
| 47 |
+
{"current_steps": 47, "total_steps": 315, "loss": 1.517, "lr": 4.730339251159709e-05, "epoch": 0.7445544554455445, "percentage": 14.92, "elapsed_time": "0:17:41", "remaining_time": "1:40:51", "throughput": 11609.45, "total_tokens": 12320768}
|
| 48 |
+
{"current_steps": 48, "total_steps": 315, "loss": 1.5103, "lr": 4.718964472511386e-05, "epoch": 0.7603960396039604, "percentage": 15.24, "elapsed_time": "0:18:03", "remaining_time": "1:40:28", "throughput": 11609.73, "total_tokens": 12582912}
|
| 49 |
+
{"current_steps": 49, "total_steps": 315, "loss": 1.4858, "lr": 4.707368982147318e-05, "epoch": 0.7762376237623763, "percentage": 15.56, "elapsed_time": "0:18:26", "remaining_time": "1:40:06", "throughput": 11609.6, "total_tokens": 12845056}
|
| 50 |
+
{"current_steps": 50, "total_steps": 315, "loss": 1.4908, "lr": 4.6955539334255716e-05, "epoch": 0.7920792079207921, "percentage": 15.87, "elapsed_time": "0:18:48", "remaining_time": "1:39:43", "throughput": 11609.72, "total_tokens": 13107200}
|
| 51 |
+
{"current_steps": 51, "total_steps": 315, "loss": 1.4893, "lr": 4.6835205015428246e-05, "epoch": 0.807920792079208, "percentage": 16.19, "elapsed_time": "0:19:11", "remaining_time": "1:39:20", "throughput": 11609.98, "total_tokens": 13369344}
|
| 52 |
+
{"current_steps": 52, "total_steps": 315, "loss": 1.4719, "lr": 4.671269883417473e-05, "epoch": 0.8237623762376237, "percentage": 16.51, "elapsed_time": "0:19:34", "remaining_time": "1:38:58", "throughput": 11610.22, "total_tokens": 13631488}
|
| 53 |
+
{"current_steps": 53, "total_steps": 315, "loss": 1.4455, "lr": 4.658803297570577e-05, "epoch": 0.8396039603960396, "percentage": 16.83, "elapsed_time": "0:19:56", "remaining_time": "1:38:35", "throughput": 11610.54, "total_tokens": 13893632}
|
| 54 |
+
{"current_steps": 54, "total_steps": 315, "loss": 1.4374, "lr": 4.6461219840046654e-05, "epoch": 0.8554455445544554, "percentage": 17.14, "elapsed_time": "0:20:19", "remaining_time": "1:38:12", "throughput": 11610.92, "total_tokens": 14155776}
|
| 55 |
+
{"current_steps": 55, "total_steps": 315, "loss": 1.4569, "lr": 4.6332272040803895e-05, "epoch": 0.8712871287128713, "percentage": 17.46, "elapsed_time": "0:20:41", "remaining_time": "1:37:49", "throughput": 11611.25, "total_tokens": 14417920}
|
| 56 |
+
{"current_steps": 56, "total_steps": 315, "loss": 1.461, "lr": 4.620120240391065e-05, "epoch": 0.8871287128712871, "percentage": 17.78, "elapsed_time": "0:21:04", "remaining_time": "1:37:27", "throughput": 11611.59, "total_tokens": 14680064}
|
| 57 |
+
{"current_steps": 57, "total_steps": 315, "loss": 1.4401, "lr": 4.606802396635098e-05, "epoch": 0.902970297029703, "percentage": 18.1, "elapsed_time": "0:21:26", "remaining_time": "1:37:04", "throughput": 11611.77, "total_tokens": 14942208}
|
| 58 |
+
{"current_steps": 58, "total_steps": 315, "loss": 1.4271, "lr": 4.593274997486309e-05, "epoch": 0.9188118811881189, "percentage": 18.41, "elapsed_time": "0:21:49", "remaining_time": "1:36:41", "throughput": 11612.03, "total_tokens": 15204352}
|
| 59 |
+
{"current_steps": 59, "total_steps": 315, "loss": 1.4444, "lr": 4.579539388462173e-05, "epoch": 0.9346534653465347, "percentage": 18.73, "elapsed_time": "0:22:11", "remaining_time": "1:36:19", "throughput": 11612.17, "total_tokens": 15466496}
|
| 60 |
+
{"current_steps": 60, "total_steps": 315, "loss": 1.4349, "lr": 4.5655969357899874e-05, "epoch": 0.9504950495049505, "percentage": 19.05, "elapsed_time": "0:22:34", "remaining_time": "1:35:56", "throughput": 11612.35, "total_tokens": 15728640}
|
| 61 |
+
{"current_steps": 61, "total_steps": 315, "loss": 1.4081, "lr": 4.551449026270979e-05, "epoch": 0.9663366336633663, "percentage": 19.37, "elapsed_time": "0:22:57", "remaining_time": "1:35:33", "throughput": 11612.37, "total_tokens": 15990784}
|
| 62 |
+
{"current_steps": 62, "total_steps": 315, "loss": 1.401, "lr": 4.537097067142363e-05, "epoch": 0.9821782178217822, "percentage": 19.68, "elapsed_time": "0:23:19", "remaining_time": "1:35:11", "throughput": 11612.47, "total_tokens": 16252928}
|
| 63 |
+
{"current_steps": 63, "total_steps": 315, "loss": 1.4383, "lr": 4.522542485937369e-05, "epoch": 0.998019801980198, "percentage": 20.0, "elapsed_time": "0:23:42", "remaining_time": "1:34:48", "throughput": 11612.6, "total_tokens": 16515072}
|
| 64 |
+
{"current_steps": 64, "total_steps": 315, "loss": 1.3665, "lr": 4.5077867303432546e-05, "epoch": 1.0, "percentage": 20.32, "elapsed_time": "0:23:44", "remaining_time": "1:33:08", "throughput": 11612.91, "total_tokens": 16547840}
|
| 65 |
+
{"current_steps": 65, "total_steps": 315, "loss": 1.0116, "lr": 4.4928312680573064e-05, "epoch": 1.0158415841584159, "percentage": 20.63, "elapsed_time": "0:24:07", "remaining_time": "1:32:47", "throughput": 11612.55, "total_tokens": 16809984}
|
| 66 |
+
{"current_steps": 66, "total_steps": 315, "loss": 0.9952, "lr": 4.477677586640854e-05, "epoch": 1.0316831683168317, "percentage": 20.95, "elapsed_time": "0:24:30", "remaining_time": "1:32:26", "throughput": 11612.69, "total_tokens": 17072128}
|
| 67 |
+
{"current_steps": 67, "total_steps": 315, "loss": 0.9662, "lr": 4.4623271933713065e-05, "epoch": 1.0475247524752476, "percentage": 21.27, "elapsed_time": "0:24:52", "remaining_time": "1:32:05", "throughput": 11612.89, "total_tokens": 17334272}
|
| 68 |
+
{"current_steps": 68, "total_steps": 315, "loss": 0.9799, "lr": 4.446781615092235e-05, "epoch": 1.0633663366336634, "percentage": 21.59, "elapsed_time": "0:25:15", "remaining_time": "1:31:43", "throughput": 11613.01, "total_tokens": 17596416}
|
| 69 |
+
{"current_steps": 69, "total_steps": 315, "loss": 0.9848, "lr": 4.431042398061499e-05, "epoch": 1.0792079207920793, "percentage": 21.9, "elapsed_time": "0:25:37", "remaining_time": "1:31:22", "throughput": 11613.05, "total_tokens": 17858560}
|
| 70 |
+
{"current_steps": 70, "total_steps": 315, "loss": 0.9054, "lr": 4.415111107797445e-05, "epoch": 1.0950495049504951, "percentage": 22.22, "elapsed_time": "0:26:00", "remaining_time": "1:31:01", "throughput": 11613.0, "total_tokens": 18120704}
|
| 71 |
+
{"current_steps": 71, "total_steps": 315, "loss": 0.9266, "lr": 4.3989893289231954e-05, "epoch": 1.110891089108911, "percentage": 22.54, "elapsed_time": "0:26:22", "remaining_time": "1:30:39", "throughput": 11613.18, "total_tokens": 18382848}
|
| 72 |
+
{"current_steps": 72, "total_steps": 315, "loss": 0.923, "lr": 4.382678665009028e-05, "epoch": 1.1267326732673268, "percentage": 22.86, "elapsed_time": "0:26:45", "remaining_time": "1:30:18", "throughput": 11613.34, "total_tokens": 18644992}
|
| 73 |
+
{"current_steps": 73, "total_steps": 315, "loss": 0.9083, "lr": 4.366180738412876e-05, "epoch": 1.1425742574257425, "percentage": 23.17, "elapsed_time": "0:27:08", "remaining_time": "1:29:57", "throughput": 11613.22, "total_tokens": 18907136}
|
| 74 |
+
{"current_steps": 74, "total_steps": 315, "loss": 0.9211, "lr": 4.34949719011896e-05, "epoch": 1.1584158415841583, "percentage": 23.49, "elapsed_time": "0:27:30", "remaining_time": "1:29:35", "throughput": 11613.17, "total_tokens": 19169280}
|
| 75 |
+
{"current_steps": 75, "total_steps": 315, "loss": 0.9228, "lr": 4.332629679574566e-05, "epoch": 1.1742574257425742, "percentage": 23.81, "elapsed_time": "0:27:53", "remaining_time": "1:29:14", "throughput": 11613.14, "total_tokens": 19431424}
|
| 76 |
+
{"current_steps": 76, "total_steps": 315, "loss": 0.8703, "lr": 4.3155798845249827e-05, "epoch": 1.19009900990099, "percentage": 24.13, "elapsed_time": "0:28:15", "remaining_time": "1:28:52", "throughput": 11612.93, "total_tokens": 19693568}
|
| 77 |
+
{"current_steps": 77, "total_steps": 315, "loss": 0.8964, "lr": 4.2983495008466276e-05, "epoch": 1.205940594059406, "percentage": 24.44, "elapsed_time": "0:28:38", "remaining_time": "1:28:31", "throughput": 11612.67, "total_tokens": 19955712}
|
| 78 |
+
{"current_steps": 78, "total_steps": 315, "loss": 0.9076, "lr": 4.2809402423783624e-05, "epoch": 1.2217821782178218, "percentage": 24.76, "elapsed_time": "0:29:01", "remaining_time": "1:28:09", "throughput": 11612.7, "total_tokens": 20217856}
|
| 79 |
+
{"current_steps": 79, "total_steps": 315, "loss": 0.9015, "lr": 4.263353840751022e-05, "epoch": 1.2376237623762376, "percentage": 25.08, "elapsed_time": "0:29:23", "remaining_time": "1:27:48", "throughput": 11612.78, "total_tokens": 20480000}
|
| 80 |
+
{"current_steps": 80, "total_steps": 315, "loss": 0.8966, "lr": 4.245592045215182e-05, "epoch": 1.2534653465346535, "percentage": 25.4, "elapsed_time": "0:29:46", "remaining_time": "1:27:26", "throughput": 11612.79, "total_tokens": 20742144}
|
| 81 |
+
{"current_steps": 81, "total_steps": 315, "loss": 0.8833, "lr": 4.227656622467162e-05, "epoch": 1.2693069306930693, "percentage": 25.71, "elapsed_time": "0:30:08", "remaining_time": "1:27:05", "throughput": 11613.0, "total_tokens": 21004288}
|
| 82 |
+
{"current_steps": 82, "total_steps": 315, "loss": 0.8531, "lr": 4.2095493564733005e-05, "epoch": 1.2851485148514852, "percentage": 26.03, "elapsed_time": "0:30:31", "remaining_time": "1:26:43", "throughput": 11613.01, "total_tokens": 21266432}
|
| 83 |
+
{"current_steps": 83, "total_steps": 315, "loss": 0.8951, "lr": 4.191272048292513e-05, "epoch": 1.300990099009901, "percentage": 26.35, "elapsed_time": "0:30:53", "remaining_time": "1:26:21", "throughput": 11613.01, "total_tokens": 21528576}
|
| 84 |
+
{"current_steps": 84, "total_steps": 315, "loss": 0.909, "lr": 4.172826515897146e-05, "epoch": 1.316831683168317, "percentage": 26.67, "elapsed_time": "0:31:16", "remaining_time": "1:26:00", "throughput": 11612.9, "total_tokens": 21790720}
|
| 85 |
+
{"current_steps": 85, "total_steps": 315, "loss": 0.8722, "lr": 4.154214593992149e-05, "epoch": 1.3326732673267327, "percentage": 26.98, "elapsed_time": "0:31:39", "remaining_time": "1:25:38", "throughput": 11612.82, "total_tokens": 22052864}
|
| 86 |
+
{"current_steps": 86, "total_steps": 315, "loss": 0.8759, "lr": 4.1354381338325864e-05, "epoch": 1.3485148514851484, "percentage": 27.3, "elapsed_time": "0:32:01", "remaining_time": "1:25:16", "throughput": 11612.86, "total_tokens": 22315008}
|
| 87 |
+
{"current_steps": 87, "total_steps": 315, "loss": 0.9013, "lr": 4.116499003039499e-05, "epoch": 1.3643564356435642, "percentage": 27.62, "elapsed_time": "0:32:24", "remaining_time": "1:24:55", "throughput": 11612.83, "total_tokens": 22577152}
|
| 88 |
+
{"current_steps": 88, "total_steps": 315, "loss": 0.8782, "lr": 4.09739908541414e-05, "epoch": 1.38019801980198, "percentage": 27.94, "elapsed_time": "0:32:46", "remaining_time": "1:24:33", "throughput": 11612.89, "total_tokens": 22839296}
|
| 89 |
+
{"current_steps": 89, "total_steps": 315, "loss": 0.8791, "lr": 4.078140280750597e-05, "epoch": 1.396039603960396, "percentage": 28.25, "elapsed_time": "0:33:09", "remaining_time": "1:24:11", "throughput": 11612.95, "total_tokens": 23101440}
|
| 90 |
+
{"current_steps": 90, "total_steps": 315, "loss": 0.8914, "lr": 4.058724504646834e-05, "epoch": 1.4118811881188118, "percentage": 28.57, "elapsed_time": "0:33:31", "remaining_time": "1:23:49", "throughput": 11613.05, "total_tokens": 23363584}
|
| 91 |
+
{"current_steps": 91, "total_steps": 315, "loss": 0.8827, "lr": 4.039153688314145e-05, "epoch": 1.4277227722772277, "percentage": 28.89, "elapsed_time": "0:33:54", "remaining_time": "1:23:27", "throughput": 11613.18, "total_tokens": 23625728}
|
| 92 |
+
{"current_steps": 92, "total_steps": 315, "loss": 0.9108, "lr": 4.0194297783850755e-05, "epoch": 1.4435643564356435, "percentage": 29.21, "elapsed_time": "0:34:16", "remaining_time": "1:23:05", "throughput": 11613.25, "total_tokens": 23887872}
|
| 93 |
+
{"current_steps": 93, "total_steps": 315, "loss": 0.8941, "lr": 3.9995547367197845e-05, "epoch": 1.4594059405940594, "percentage": 29.52, "elapsed_time": "0:34:39", "remaining_time": "1:22:43", "throughput": 11613.31, "total_tokens": 24150016}
|
| 94 |
+
{"current_steps": 94, "total_steps": 315, "loss": 0.8923, "lr": 3.9795305402109195e-05, "epoch": 1.4752475247524752, "percentage": 29.84, "elapsed_time": "0:35:02", "remaining_time": "1:22:22", "throughput": 11613.44, "total_tokens": 24412160}
|
| 95 |
+
{"current_steps": 95, "total_steps": 315, "loss": 0.8704, "lr": 3.959359180586975e-05, "epoch": 1.491089108910891, "percentage": 30.16, "elapsed_time": "0:35:24", "remaining_time": "1:22:00", "throughput": 11613.43, "total_tokens": 24674304}
|
| 96 |
+
{"current_steps": 96, "total_steps": 315, "loss": 0.8993, "lr": 3.939042664214184e-05, "epoch": 1.506930693069307, "percentage": 30.48, "elapsed_time": "0:35:47", "remaining_time": "1:21:38", "throughput": 11613.5, "total_tokens": 24936448}
|
| 97 |
+
{"current_steps": 97, "total_steps": 315, "loss": 0.9145, "lr": 3.918583011896955e-05, "epoch": 1.5227722772277228, "percentage": 30.79, "elapsed_time": "0:36:09", "remaining_time": "1:21:16", "throughput": 11613.54, "total_tokens": 25198592}
|
| 98 |
+
{"current_steps": 98, "total_steps": 315, "loss": 0.8707, "lr": 3.897982258676867e-05, "epoch": 1.5386138613861386, "percentage": 31.11, "elapsed_time": "0:36:32", "remaining_time": "1:20:54", "throughput": 11613.56, "total_tokens": 25460736}
|
| 99 |
+
{"current_steps": 99, "total_steps": 315, "loss": 0.8842, "lr": 3.8772424536302564e-05, "epoch": 1.5544554455445545, "percentage": 31.43, "elapsed_time": "0:36:54", "remaining_time": "1:20:32", "throughput": 11613.63, "total_tokens": 25722880}
|
| 100 |
+
{"current_steps": 100, "total_steps": 315, "loss": 0.9139, "lr": 3.856365659664399e-05, "epoch": 1.5702970297029704, "percentage": 31.75, "elapsed_time": "0:37:17", "remaining_time": "1:20:10", "throughput": 11613.41, "total_tokens": 25985024}
|
| 101 |
+
{"current_steps": 101, "total_steps": 315, "loss": 0.8868, "lr": 3.835353953312322e-05, "epoch": 1.5861386138613862, "percentage": 32.06, "elapsed_time": "0:37:40", "remaining_time": "1:19:48", "throughput": 11613.3, "total_tokens": 26247168}
|
| 102 |
+
{"current_steps": 102, "total_steps": 315, "loss": 0.8928, "lr": 3.814209424526262e-05, "epoch": 1.601980198019802, "percentage": 32.38, "elapsed_time": "0:38:02", "remaining_time": "1:19:26", "throughput": 11613.02, "total_tokens": 26509312}
|
| 103 |
+
{"current_steps": 103, "total_steps": 315, "loss": 0.8843, "lr": 3.7929341764697816e-05, "epoch": 1.617821782178218, "percentage": 32.7, "elapsed_time": "0:38:25", "remaining_time": "1:19:04", "throughput": 11612.89, "total_tokens": 26771456}
|
| 104 |
+
{"current_steps": 104, "total_steps": 315, "loss": 0.9118, "lr": 3.771530325308579e-05, "epoch": 1.6336633663366338, "percentage": 33.02, "elapsed_time": "0:38:47", "remaining_time": "1:18:42", "throughput": 11612.94, "total_tokens": 27033600}
|
| 105 |
+
{"current_steps": 105, "total_steps": 315, "loss": 0.9178, "lr": 3.7500000000000003e-05, "epoch": 1.6495049504950496, "percentage": 33.33, "elapsed_time": "0:39:10", "remaining_time": "1:18:20", "throughput": 11612.98, "total_tokens": 27295744}
|
| 106 |
+
{"current_steps": 106, "total_steps": 315, "loss": 0.9019, "lr": 3.7283453420812786e-05, "epoch": 1.6653465346534655, "percentage": 33.65, "elapsed_time": "0:39:33", "remaining_time": "1:17:58", "throughput": 11613.04, "total_tokens": 27557888}
|
| 107 |
+
{"current_steps": 107, "total_steps": 315, "loss": 0.9223, "lr": 3.706568505456527e-05, "epoch": 1.6811881188118813, "percentage": 33.97, "elapsed_time": "0:39:55", "remaining_time": "1:17:36", "throughput": 11613.15, "total_tokens": 27820032}
|
| 108 |
+
{"current_steps": 108, "total_steps": 315, "loss": 0.9232, "lr": 3.6846716561824965e-05, "epoch": 1.697029702970297, "percentage": 34.29, "elapsed_time": "0:40:18", "remaining_time": "1:17:14", "throughput": 11612.91, "total_tokens": 28082176}
|
| 109 |
+
{"current_steps": 109, "total_steps": 315, "loss": 0.8993, "lr": 3.662656972253127e-05, "epoch": 1.7128712871287128, "percentage": 34.6, "elapsed_time": "0:40:40", "remaining_time": "1:16:52", "throughput": 11612.77, "total_tokens": 28344320}
|
| 110 |
+
{"current_steps": 110, "total_steps": 315, "loss": 0.8772, "lr": 3.6405266433829075e-05, "epoch": 1.7287128712871287, "percentage": 34.92, "elapsed_time": "0:41:03", "remaining_time": "1:16:30", "throughput": 11612.65, "total_tokens": 28606464}
|
| 111 |
+
{"current_steps": 111, "total_steps": 315, "loss": 0.8864, "lr": 3.6182828707890816e-05, "epoch": 1.7445544554455445, "percentage": 35.24, "elapsed_time": "0:41:25", "remaining_time": "1:16:08", "throughput": 11612.67, "total_tokens": 28868608}
|
| 112 |
+
{"current_steps": 112, "total_steps": 315, "loss": 0.9053, "lr": 3.5959278669726935e-05, "epoch": 1.7603960396039604, "percentage": 35.56, "elapsed_time": "0:41:48", "remaining_time": "1:15:46", "throughput": 11612.67, "total_tokens": 29130752}
|
| 113 |
+
{"current_steps": 113, "total_steps": 315, "loss": 0.8868, "lr": 3.5734638554985236e-05, "epoch": 1.7762376237623763, "percentage": 35.87, "elapsed_time": "0:42:11", "remaining_time": "1:15:24", "throughput": 11612.57, "total_tokens": 29392896}
|
| 114 |
+
{"current_steps": 114, "total_steps": 315, "loss": 0.9201, "lr": 3.550893070773914e-05, "epoch": 1.7920792079207921, "percentage": 36.19, "elapsed_time": "0:42:33", "remaining_time": "1:15:02", "throughput": 11612.49, "total_tokens": 29655040}
|
| 115 |
+
{"current_steps": 115, "total_steps": 315, "loss": 0.8993, "lr": 3.5282177578265296e-05, "epoch": 1.807920792079208, "percentage": 36.51, "elapsed_time": "0:42:56", "remaining_time": "1:14:40", "throughput": 11612.44, "total_tokens": 29917184}
|
| 116 |
+
{"current_steps": 116, "total_steps": 315, "loss": 0.8602, "lr": 3.505440172081044e-05, "epoch": 1.8237623762376236, "percentage": 36.83, "elapsed_time": "0:43:18", "remaining_time": "1:14:18", "throughput": 11612.48, "total_tokens": 30179328}
|
| 117 |
+
{"current_steps": 117, "total_steps": 315, "loss": 0.8879, "lr": 3.4825625791348096e-05, "epoch": 1.8396039603960395, "percentage": 37.14, "elapsed_time": "0:43:41", "remaining_time": "1:13:56", "throughput": 11612.61, "total_tokens": 30441472}
|
| 118 |
+
{"current_steps": 118, "total_steps": 315, "loss": 0.8879, "lr": 3.459587254532502e-05, "epoch": 1.8554455445544553, "percentage": 37.46, "elapsed_time": "0:44:03", "remaining_time": "1:13:34", "throughput": 11612.58, "total_tokens": 30703616}
|
| 119 |
+
{"current_steps": 119, "total_steps": 315, "loss": 0.9136, "lr": 3.436516483539781e-05, "epoch": 1.8712871287128712, "percentage": 37.78, "elapsed_time": "0:44:26", "remaining_time": "1:13:11", "throughput": 11612.74, "total_tokens": 30965760}
|
| 120 |
+
{"current_steps": 120, "total_steps": 315, "loss": 0.8795, "lr": 3.413352560915988e-05, "epoch": 1.887128712871287, "percentage": 38.1, "elapsed_time": "0:44:49", "remaining_time": "1:12:49", "throughput": 11612.83, "total_tokens": 31227904}
|
| 121 |
+
{"current_steps": 121, "total_steps": 315, "loss": 0.8771, "lr": 3.390097790685892e-05, "epoch": 1.9029702970297029, "percentage": 38.41, "elapsed_time": "0:45:11", "remaining_time": "1:12:27", "throughput": 11612.88, "total_tokens": 31490048}
|
| 122 |
+
{"current_steps": 122, "total_steps": 315, "loss": 0.8743, "lr": 3.366754485910518e-05, "epoch": 1.9188118811881187, "percentage": 38.73, "elapsed_time": "0:45:34", "remaining_time": "1:12:05", "throughput": 11612.98, "total_tokens": 31752192}
|
| 123 |
+
{"current_steps": 123, "total_steps": 315, "loss": 0.8785, "lr": 3.343324968457076e-05, "epoch": 1.9346534653465346, "percentage": 39.05, "elapsed_time": "0:45:56", "remaining_time": "1:11:43", "throughput": 11612.99, "total_tokens": 32014336}
|
| 124 |
+
{"current_steps": 124, "total_steps": 315, "loss": 0.8941, "lr": 3.3198115687680115e-05, "epoch": 1.9504950495049505, "percentage": 39.37, "elapsed_time": "0:46:19", "remaining_time": "1:11:21", "throughput": 11613.12, "total_tokens": 32276480}
|
| 125 |
+
{"current_steps": 125, "total_steps": 315, "loss": 0.9004, "lr": 3.2962166256292113e-05, "epoch": 1.9663366336633663, "percentage": 39.68, "elapsed_time": "0:46:41", "remaining_time": "1:10:58", "throughput": 11613.22, "total_tokens": 32538624}
|
| 126 |
+
{"current_steps": 126, "total_steps": 315, "loss": 0.8775, "lr": 3.272542485937369e-05, "epoch": 1.9821782178217822, "percentage": 40.0, "elapsed_time": "0:47:04", "remaining_time": "1:10:36", "throughput": 11613.3, "total_tokens": 32800768}
|
| 127 |
+
{"current_steps": 127, "total_steps": 315, "loss": 0.9204, "lr": 3.248791504466548e-05, "epoch": 1.998019801980198, "percentage": 40.32, "elapsed_time": "0:47:26", "remaining_time": "1:10:14", "throughput": 11613.44, "total_tokens": 33062912}
|
| 128 |
+
{"current_steps": 128, "total_steps": 315, "loss": 0.8618, "lr": 3.224966043633966e-05, "epoch": 2.0, "percentage": 40.63, "elapsed_time": "0:47:29", "remaining_time": "1:09:23", "throughput": 11613.62, "total_tokens": 33095680}
|
| 129 |
+
{"current_steps": 129, "total_steps": 315, "loss": 0.4193, "lr": 3.201068473265007e-05, "epoch": 2.015841584158416, "percentage": 40.95, "elapsed_time": "0:47:52", "remaining_time": "1:09:01", "throughput": 11613.54, "total_tokens": 33357824}
|
| 130 |
+
{"current_steps": 130, "total_steps": 315, "loss": 0.3973, "lr": 3.177101170357513e-05, "epoch": 2.0316831683168317, "percentage": 41.27, "elapsed_time": "0:48:14", "remaining_time": "1:08:39", "throughput": 11613.63, "total_tokens": 33619968}
|
| 131 |
+
{"current_steps": 131, "total_steps": 315, "loss": 0.3753, "lr": 3.1530665188453464e-05, "epoch": 2.0475247524752476, "percentage": 41.59, "elapsed_time": "0:48:37", "remaining_time": "1:08:17", "throughput": 11613.72, "total_tokens": 33882112}
|
| 132 |
+
{"current_steps": 132, "total_steps": 315, "loss": 0.3861, "lr": 3.1289669093612714e-05, "epoch": 2.0633663366336634, "percentage": 41.9, "elapsed_time": "0:48:59", "remaining_time": "1:07:55", "throughput": 11613.71, "total_tokens": 34144256}
|
| 133 |
+
{"current_steps": 133, "total_steps": 315, "loss": 0.3843, "lr": 3.104804738999169e-05, "epoch": 2.0792079207920793, "percentage": 42.22, "elapsed_time": "0:49:22", "remaining_time": "1:07:34", "throughput": 11613.79, "total_tokens": 34406400}
|
| 134 |
+
{"current_steps": 134, "total_steps": 315, "loss": 0.3644, "lr": 3.0805824110756064e-05, "epoch": 2.095049504950495, "percentage": 42.54, "elapsed_time": "0:49:45", "remaining_time": "1:07:12", "throughput": 11613.84, "total_tokens": 34668544}
|
| 135 |
+
{"current_steps": 135, "total_steps": 315, "loss": 0.3452, "lr": 3.056302334890786e-05, "epoch": 2.110891089108911, "percentage": 42.86, "elapsed_time": "0:50:07", "remaining_time": "1:06:50", "throughput": 11613.91, "total_tokens": 34930688}
|
| 136 |
+
{"current_steps": 136, "total_steps": 315, "loss": 0.3311, "lr": 3.0319669254889055e-05, "epoch": 2.126732673267327, "percentage": 43.17, "elapsed_time": "0:50:30", "remaining_time": "1:06:28", "throughput": 11613.97, "total_tokens": 35192832}
|
| 137 |
+
{"current_steps": 137, "total_steps": 315, "loss": 0.3337, "lr": 3.0075786034179405e-05, "epoch": 2.1425742574257427, "percentage": 43.49, "elapsed_time": "0:50:52", "remaining_time": "1:06:06", "throughput": 11614.08, "total_tokens": 35454976}
|
| 138 |
+
{"current_steps": 138, "total_steps": 315, "loss": 0.3356, "lr": 2.9831397944888833e-05, "epoch": 2.1584158415841586, "percentage": 43.81, "elapsed_time": "0:51:15", "remaining_time": "1:05:44", "throughput": 11614.1, "total_tokens": 35717120}
|
| 139 |
+
{"current_steps": 139, "total_steps": 315, "loss": 0.338, "lr": 2.958652929534456e-05, "epoch": 2.1742574257425744, "percentage": 44.13, "elapsed_time": "0:51:37", "remaining_time": "1:05:22", "throughput": 11614.11, "total_tokens": 35979264}
|
| 140 |
+
{"current_steps": 140, "total_steps": 315, "loss": 0.3364, "lr": 2.9341204441673266e-05, "epoch": 2.1900990099009903, "percentage": 44.44, "elapsed_time": "0:52:00", "remaining_time": "1:05:00", "throughput": 11614.07, "total_tokens": 36241408}
|
| 141 |
+
{"current_steps": 141, "total_steps": 315, "loss": 0.3109, "lr": 2.9095447785378443e-05, "epoch": 2.205940594059406, "percentage": 44.76, "elapsed_time": "0:52:23", "remaining_time": "1:04:38", "throughput": 11614.11, "total_tokens": 36503552}
|
| 142 |
+
{"current_steps": 142, "total_steps": 315, "loss": 0.3099, "lr": 2.8849283770913337e-05, "epoch": 2.221782178217822, "percentage": 45.08, "elapsed_time": "0:52:45", "remaining_time": "1:04:16", "throughput": 11614.24, "total_tokens": 36765696}
|
| 143 |
+
{"current_steps": 143, "total_steps": 315, "loss": 0.312, "lr": 2.8602736883249503e-05, "epoch": 2.237623762376238, "percentage": 45.4, "elapsed_time": "0:53:08", "remaining_time": "1:03:54", "throughput": 11614.31, "total_tokens": 37027840}
|
| 144 |
+
{"current_steps": 144, "total_steps": 315, "loss": 0.3212, "lr": 2.8355831645441388e-05, "epoch": 2.2534653465346537, "percentage": 45.71, "elapsed_time": "0:53:30", "remaining_time": "1:03:32", "throughput": 11614.37, "total_tokens": 37289984}
|
| 145 |
+
{"current_steps": 145, "total_steps": 315, "loss": 0.3264, "lr": 2.8108592616187133e-05, "epoch": 2.2693069306930695, "percentage": 46.03, "elapsed_time": "0:53:53", "remaining_time": "1:03:10", "throughput": 11614.4, "total_tokens": 37552128}
|
| 146 |
+
{"current_steps": 146, "total_steps": 315, "loss": 0.2986, "lr": 2.78610443873858e-05, "epoch": 2.285148514851485, "percentage": 46.35, "elapsed_time": "0:54:15", "remaining_time": "1:02:48", "throughput": 11614.43, "total_tokens": 37814272}
|
| 147 |
+
{"current_steps": 147, "total_steps": 315, "loss": 0.3132, "lr": 2.761321158169134e-05, "epoch": 2.300990099009901, "percentage": 46.67, "elapsed_time": "0:54:38", "remaining_time": "1:02:26", "throughput": 11614.45, "total_tokens": 38076416}
|
| 148 |
+
{"current_steps": 148, "total_steps": 315, "loss": 0.3184, "lr": 2.736511885006343e-05, "epoch": 2.3168316831683167, "percentage": 46.98, "elapsed_time": "0:55:00", "remaining_time": "1:02:04", "throughput": 11614.47, "total_tokens": 38338560}
|
| 149 |
+
{"current_steps": 149, "total_steps": 315, "loss": 0.295, "lr": 2.7116790869315582e-05, "epoch": 2.3326732673267325, "percentage": 47.3, "elapsed_time": "0:55:23", "remaining_time": "1:01:42", "throughput": 11614.54, "total_tokens": 38600704}
|
| 150 |
+
{"current_steps": 150, "total_steps": 315, "loss": 0.3218, "lr": 2.686825233966061e-05, "epoch": 2.3485148514851484, "percentage": 47.62, "elapsed_time": "0:55:46", "remaining_time": "1:01:20", "throughput": 11614.61, "total_tokens": 38862848}
|
| 151 |
+
{"current_steps": 151, "total_steps": 315, "loss": 0.3033, "lr": 2.6619527982253794e-05, "epoch": 2.3643564356435642, "percentage": 47.94, "elapsed_time": "0:56:08", "remaining_time": "1:00:58", "throughput": 11614.58, "total_tokens": 39124992}
|
| 152 |
+
{"current_steps": 152, "total_steps": 315, "loss": 0.31, "lr": 2.6370642536734004e-05, "epoch": 2.38019801980198, "percentage": 48.25, "elapsed_time": "0:56:31", "remaining_time": "1:00:36", "throughput": 11614.62, "total_tokens": 39387136}
|
| 153 |
+
{"current_steps": 153, "total_steps": 315, "loss": 0.2966, "lr": 2.6121620758762877e-05, "epoch": 2.396039603960396, "percentage": 48.57, "elapsed_time": "0:56:53", "remaining_time": "1:00:14", "throughput": 11614.59, "total_tokens": 39649280}
|
| 154 |
+
{"current_steps": 154, "total_steps": 315, "loss": 0.3146, "lr": 2.587248741756253e-05, "epoch": 2.411881188118812, "percentage": 48.89, "elapsed_time": "0:57:16", "remaining_time": "0:59:52", "throughput": 11614.65, "total_tokens": 39911424}
|
| 155 |
+
{"current_steps": 155, "total_steps": 315, "loss": 0.3063, "lr": 2.5623267293451826e-05, "epoch": 2.4277227722772277, "percentage": 49.21, "elapsed_time": "0:57:38", "remaining_time": "0:59:30", "throughput": 11614.67, "total_tokens": 40173568}
|
| 156 |
+
{"current_steps": 156, "total_steps": 315, "loss": 0.2858, "lr": 2.5373985175381594e-05, "epoch": 2.4435643564356435, "percentage": 49.52, "elapsed_time": "0:58:01", "remaining_time": "0:59:08", "throughput": 11614.63, "total_tokens": 40435712}
|
| 157 |
+
{"current_steps": 157, "total_steps": 315, "loss": 0.3047, "lr": 2.5124665858468954e-05, "epoch": 2.4594059405940594, "percentage": 49.84, "elapsed_time": "0:58:24", "remaining_time": "0:58:46", "throughput": 11614.56, "total_tokens": 40697856}
|
| 158 |
+
{"current_steps": 158, "total_steps": 315, "loss": 0.2995, "lr": 2.4875334141531052e-05, "epoch": 2.4752475247524752, "percentage": 50.16, "elapsed_time": "0:58:46", "remaining_time": "0:58:24", "throughput": 11614.58, "total_tokens": 40960000}
|
| 159 |
+
{"current_steps": 159, "total_steps": 315, "loss": 0.3007, "lr": 2.4626014824618415e-05, "epoch": 2.491089108910891, "percentage": 50.48, "elapsed_time": "0:59:09", "remaining_time": "0:58:02", "throughput": 11614.6, "total_tokens": 41222144}
|
| 160 |
+
{"current_steps": 160, "total_steps": 315, "loss": 0.3126, "lr": 2.4376732706548183e-05, "epoch": 2.506930693069307, "percentage": 50.79, "elapsed_time": "0:59:31", "remaining_time": "0:57:40", "throughput": 11614.68, "total_tokens": 41484288}
|
| 161 |
+
{"current_steps": 161, "total_steps": 315, "loss": 0.3149, "lr": 2.4127512582437485e-05, "epoch": 2.522772277227723, "percentage": 51.11, "elapsed_time": "0:59:54", "remaining_time": "0:57:18", "throughput": 11614.63, "total_tokens": 41746432}
|
| 162 |
+
{"current_steps": 162, "total_steps": 315, "loss": 0.3178, "lr": 2.3878379241237136e-05, "epoch": 2.5386138613861386, "percentage": 51.43, "elapsed_time": "1:00:16", "remaining_time": "0:56:55", "throughput": 11614.72, "total_tokens": 42008576}
|
| 163 |
+
{"current_steps": 163, "total_steps": 315, "loss": 0.3153, "lr": 2.3629357463265995e-05, "epoch": 2.5544554455445545, "percentage": 51.75, "elapsed_time": "1:00:39", "remaining_time": "0:56:33", "throughput": 11614.75, "total_tokens": 42270720}
|
| 164 |
+
{"current_steps": 164, "total_steps": 315, "loss": 0.314, "lr": 2.3380472017746202e-05, "epoch": 2.5702970297029704, "percentage": 52.06, "elapsed_time": "1:01:01", "remaining_time": "0:56:11", "throughput": 11614.73, "total_tokens": 42532864}
|
| 165 |
+
{"current_steps": 165, "total_steps": 315, "loss": 0.3121, "lr": 2.3131747660339394e-05, "epoch": 2.586138613861386, "percentage": 52.38, "elapsed_time": "1:01:24", "remaining_time": "0:55:49", "throughput": 11614.7, "total_tokens": 42795008}
|
| 166 |
+
{"current_steps": 166, "total_steps": 315, "loss": 0.3112, "lr": 2.288320913068442e-05, "epoch": 2.601980198019802, "percentage": 52.7, "elapsed_time": "1:01:47", "remaining_time": "0:55:27", "throughput": 11614.66, "total_tokens": 43057152}
|
| 167 |
+
{"current_steps": 167, "total_steps": 315, "loss": 0.3114, "lr": 2.2634881149936575e-05, "epoch": 2.617821782178218, "percentage": 53.02, "elapsed_time": "1:02:09", "remaining_time": "0:55:05", "throughput": 11614.6, "total_tokens": 43319296}
|
| 168 |
+
{"current_steps": 168, "total_steps": 315, "loss": 0.3092, "lr": 2.238678841830867e-05, "epoch": 2.633663366336634, "percentage": 53.33, "elapsed_time": "1:02:32", "remaining_time": "0:54:43", "throughput": 11614.62, "total_tokens": 43581440}
|
| 169 |
+
{"current_steps": 169, "total_steps": 315, "loss": 0.3114, "lr": 2.2138955612614207e-05, "epoch": 2.6495049504950496, "percentage": 53.65, "elapsed_time": "1:02:54", "remaining_time": "0:54:21", "throughput": 11614.76, "total_tokens": 43843584}
|
| 170 |
+
{"current_steps": 170, "total_steps": 315, "loss": 0.3053, "lr": 2.189140738381288e-05, "epoch": 2.6653465346534655, "percentage": 53.97, "elapsed_time": "1:03:17", "remaining_time": "0:53:58", "throughput": 11614.85, "total_tokens": 44105728}
|
| 171 |
+
{"current_steps": 171, "total_steps": 315, "loss": 0.2993, "lr": 2.164416835455862e-05, "epoch": 2.6811881188118813, "percentage": 54.29, "elapsed_time": "1:03:39", "remaining_time": "0:53:36", "throughput": 11614.96, "total_tokens": 44367872}
|
| 172 |
+
{"current_steps": 172, "total_steps": 315, "loss": 0.3082, "lr": 2.1397263116750503e-05, "epoch": 2.6970297029702968, "percentage": 54.6, "elapsed_time": "1:04:02", "remaining_time": "0:53:14", "throughput": 11615.02, "total_tokens": 44630016}
|
| 173 |
+
{"current_steps": 173, "total_steps": 315, "loss": 0.3042, "lr": 2.115071622908666e-05, "epoch": 2.7128712871287126, "percentage": 54.92, "elapsed_time": "1:04:24", "remaining_time": "0:52:52", "throughput": 11615.1, "total_tokens": 44892160}
|
| 174 |
+
{"current_steps": 174, "total_steps": 315, "loss": 0.3083, "lr": 2.090455221462156e-05, "epoch": 2.7287128712871285, "percentage": 55.24, "elapsed_time": "1:04:47", "remaining_time": "0:52:30", "throughput": 11615.1, "total_tokens": 45154304}
|
| 175 |
+
{"current_steps": 175, "total_steps": 315, "loss": 0.3202, "lr": 2.0658795558326743e-05, "epoch": 2.7445544554455443, "percentage": 55.56, "elapsed_time": "1:05:10", "remaining_time": "0:52:08", "throughput": 11615.14, "total_tokens": 45416448}
|
| 176 |
+
{"current_steps": 176, "total_steps": 315, "loss": 0.3099, "lr": 2.0413470704655445e-05, "epoch": 2.76039603960396, "percentage": 55.87, "elapsed_time": "1:05:32", "remaining_time": "0:51:45", "throughput": 11615.12, "total_tokens": 45678592}
|
| 177 |
+
{"current_steps": 177, "total_steps": 315, "loss": 0.3225, "lr": 2.0168602055111173e-05, "epoch": 2.776237623762376, "percentage": 56.19, "elapsed_time": "1:05:55", "remaining_time": "0:51:23", "throughput": 11615.1, "total_tokens": 45940736}
|
| 178 |
+
{"current_steps": 178, "total_steps": 315, "loss": 0.3149, "lr": 1.99242139658206e-05, "epoch": 2.792079207920792, "percentage": 56.51, "elapsed_time": "1:06:17", "remaining_time": "0:51:01", "throughput": 11615.15, "total_tokens": 46202880}
|
| 179 |
+
{"current_steps": 179, "total_steps": 315, "loss": 0.2952, "lr": 1.9680330745110954e-05, "epoch": 2.8079207920792078, "percentage": 56.83, "elapsed_time": "1:06:40", "remaining_time": "0:50:39", "throughput": 11615.21, "total_tokens": 46465024}
|
| 180 |
+
{"current_steps": 180, "total_steps": 315, "loss": 0.3035, "lr": 1.9436976651092144e-05, "epoch": 2.8237623762376236, "percentage": 57.14, "elapsed_time": "1:07:02", "remaining_time": "0:50:17", "throughput": 11615.27, "total_tokens": 46727168}
|
| 181 |
+
{"current_steps": 181, "total_steps": 315, "loss": 0.303, "lr": 1.919417588924394e-05, "epoch": 2.8396039603960395, "percentage": 57.46, "elapsed_time": "1:07:25", "remaining_time": "0:49:54", "throughput": 11615.3, "total_tokens": 46989312}
|
| 182 |
+
{"current_steps": 182, "total_steps": 315, "loss": 0.3057, "lr": 1.895195261000831e-05, "epoch": 2.8554455445544553, "percentage": 57.78, "elapsed_time": "1:07:48", "remaining_time": "0:49:32", "throughput": 11615.31, "total_tokens": 47251456}
|
| 183 |
+
{"current_steps": 183, "total_steps": 315, "loss": 0.3138, "lr": 1.871033090638729e-05, "epoch": 2.871287128712871, "percentage": 58.1, "elapsed_time": "1:08:10", "remaining_time": "0:49:10", "throughput": 11615.17, "total_tokens": 47513600}
|
| 184 |
+
{"current_steps": 184, "total_steps": 315, "loss": 0.3164, "lr": 1.8469334811546542e-05, "epoch": 2.887128712871287, "percentage": 58.41, "elapsed_time": "1:08:33", "remaining_time": "0:48:48", "throughput": 11615.2, "total_tokens": 47775744}
|
| 185 |
+
{"current_steps": 185, "total_steps": 315, "loss": 0.3178, "lr": 1.8228988296424877e-05, "epoch": 2.902970297029703, "percentage": 58.73, "elapsed_time": "1:08:55", "remaining_time": "0:48:26", "throughput": 11615.19, "total_tokens": 48037888}
|
| 186 |
+
{"current_steps": 186, "total_steps": 315, "loss": 0.3135, "lr": 1.7989315267349936e-05, "epoch": 2.9188118811881187, "percentage": 59.05, "elapsed_time": "1:09:18", "remaining_time": "0:48:04", "throughput": 11615.12, "total_tokens": 48300032}
|
| 187 |
+
{"current_steps": 187, "total_steps": 315, "loss": 0.3068, "lr": 1.7750339563660347e-05, "epoch": 2.9346534653465346, "percentage": 59.37, "elapsed_time": "1:09:40", "remaining_time": "0:47:41", "throughput": 11615.13, "total_tokens": 48562176}
|
| 188 |
+
{"current_steps": 188, "total_steps": 315, "loss": 0.3052, "lr": 1.751208495533452e-05, "epoch": 2.9504950495049505, "percentage": 59.68, "elapsed_time": "1:10:03", "remaining_time": "0:47:19", "throughput": 11615.19, "total_tokens": 48824320}
|
| 189 |
+
{"current_steps": 189, "total_steps": 315, "loss": 0.3192, "lr": 1.7274575140626318e-05, "epoch": 2.9663366336633663, "percentage": 60.0, "elapsed_time": "1:10:26", "remaining_time": "0:46:57", "throughput": 11615.23, "total_tokens": 49086464}
|
| 190 |
+
{"current_steps": 190, "total_steps": 315, "loss": 0.313, "lr": 1.7037833743707892e-05, "epoch": 2.982178217821782, "percentage": 60.32, "elapsed_time": "1:10:48", "remaining_time": "0:46:35", "throughput": 11615.23, "total_tokens": 49348608}
|
| 191 |
+
{"current_steps": 191, "total_steps": 315, "loss": 0.31, "lr": 1.6801884312319895e-05, "epoch": 2.998019801980198, "percentage": 60.63, "elapsed_time": "1:11:11", "remaining_time": "0:46:12", "throughput": 11615.25, "total_tokens": 49610752}
|
| 192 |
+
{"current_steps": 192, "total_steps": 315, "loss": 0.2615, "lr": 1.6566750315429254e-05, "epoch": 3.0, "percentage": 60.95, "elapsed_time": "1:11:13", "remaining_time": "0:45:37", "throughput": 11615.38, "total_tokens": 49643520}
|
| 193 |
+
{"current_steps": 193, "total_steps": 315, "loss": 0.0973, "lr": 1.633245514089482e-05, "epoch": 3.015841584158416, "percentage": 61.27, "elapsed_time": "1:11:36", "remaining_time": "0:45:15", "throughput": 11615.37, "total_tokens": 49905664}
|
| 194 |
+
{"current_steps": 194, "total_steps": 315, "loss": 0.0962, "lr": 1.609902209314108e-05, "epoch": 3.0316831683168317, "percentage": 61.59, "elapsed_time": "1:11:59", "remaining_time": "0:44:53", "throughput": 11615.41, "total_tokens": 50167808}
|
| 195 |
+
{"current_steps": 195, "total_steps": 315, "loss": 0.0855, "lr": 1.5866474390840125e-05, "epoch": 3.0475247524752476, "percentage": 61.9, "elapsed_time": "1:12:21", "remaining_time": "0:44:31", "throughput": 11615.43, "total_tokens": 50429952}
|
| 196 |
+
{"current_steps": 196, "total_steps": 315, "loss": 0.077, "lr": 1.56348351646022e-05, "epoch": 3.0633663366336634, "percentage": 62.22, "elapsed_time": "1:12:44", "remaining_time": "0:44:09", "throughput": 11615.5, "total_tokens": 50692096}
|
| 197 |
+
{"current_steps": 197, "total_steps": 315, "loss": 0.0784, "lr": 1.5404127454674995e-05, "epoch": 3.0792079207920793, "percentage": 62.54, "elapsed_time": "1:13:06", "remaining_time": "0:43:47", "throughput": 11615.61, "total_tokens": 50954240}
|
| 198 |
+
{"current_steps": 198, "total_steps": 315, "loss": 0.0791, "lr": 1.5174374208651912e-05, "epoch": 3.095049504950495, "percentage": 62.86, "elapsed_time": "1:13:29", "remaining_time": "0:43:25", "throughput": 11615.64, "total_tokens": 51216384}
|
| 199 |
+
{"current_steps": 199, "total_steps": 315, "loss": 0.0757, "lr": 1.4945598279189565e-05, "epoch": 3.110891089108911, "percentage": 63.17, "elapsed_time": "1:13:51", "remaining_time": "0:43:03", "throughput": 11615.65, "total_tokens": 51478528}
|
| 200 |
+
{"current_steps": 200, "total_steps": 315, "loss": 0.0871, "lr": 1.4717822421734718e-05, "epoch": 3.126732673267327, "percentage": 63.49, "elapsed_time": "1:14:14", "remaining_time": "0:42:41", "throughput": 11615.65, "total_tokens": 51740672}
|
| 201 |
+
{"current_steps": 201, "total_steps": 315, "loss": 0.0765, "lr": 1.4491069292260868e-05, "epoch": 3.1425742574257427, "percentage": 63.81, "elapsed_time": "1:14:36", "remaining_time": "0:42:19", "throughput": 11615.59, "total_tokens": 52002816}
|
| 202 |
+
{"current_steps": 202, "total_steps": 315, "loss": 0.0735, "lr": 1.4265361445014768e-05, "epoch": 3.1584158415841586, "percentage": 64.13, "elapsed_time": "1:14:59", "remaining_time": "0:41:57", "throughput": 11615.58, "total_tokens": 52264960}
|
| 203 |
+
{"current_steps": 203, "total_steps": 315, "loss": 0.0745, "lr": 1.4040721330273062e-05, "epoch": 3.1742574257425744, "percentage": 64.44, "elapsed_time": "1:15:22", "remaining_time": "0:41:35", "throughput": 11614.87, "total_tokens": 52527104}
|
| 204 |
+
{"current_steps": 204, "total_steps": 315, "loss": 0.0821, "lr": 1.3817171292109183e-05, "epoch": 3.1900990099009903, "percentage": 64.76, "elapsed_time": "1:15:45", "remaining_time": "0:41:13", "throughput": 11614.19, "total_tokens": 52789248}
|
| 205 |
+
{"current_steps": 205, "total_steps": 315, "loss": 0.0754, "lr": 1.3594733566170926e-05, "epoch": 3.205940594059406, "percentage": 65.08, "elapsed_time": "1:16:07", "remaining_time": "0:40:51", "throughput": 11614.17, "total_tokens": 53051392}
|
| 206 |
+
{"current_steps": 206, "total_steps": 315, "loss": 0.0709, "lr": 1.337343027746874e-05, "epoch": 3.221782178217822, "percentage": 65.4, "elapsed_time": "1:16:30", "remaining_time": "0:40:28", "throughput": 11614.2, "total_tokens": 53313536}
|
| 207 |
+
{"current_steps": 207, "total_steps": 315, "loss": 0.0681, "lr": 1.3153283438175034e-05, "epoch": 3.237623762376238, "percentage": 65.71, "elapsed_time": "1:16:53", "remaining_time": "0:40:06", "throughput": 11613.11, "total_tokens": 53575680}
|
| 208 |
+
{"current_steps": 208, "total_steps": 315, "loss": 0.0754, "lr": 1.2934314945434734e-05, "epoch": 3.2534653465346537, "percentage": 66.03, "elapsed_time": "1:17:15", "remaining_time": "0:39:44", "throughput": 11613.2, "total_tokens": 53837824}
|
| 209 |
+
{"current_steps": 209, "total_steps": 315, "loss": 0.0675, "lr": 1.271654657918722e-05, "epoch": 3.2693069306930695, "percentage": 66.35, "elapsed_time": "1:17:38", "remaining_time": "0:39:22", "throughput": 11613.21, "total_tokens": 54099968}
|
| 210 |
+
{"current_steps": 210, "total_steps": 315, "loss": 0.0683, "lr": 1.2500000000000006e-05, "epoch": 3.285148514851485, "percentage": 66.67, "elapsed_time": "1:18:01", "remaining_time": "0:39:00", "throughput": 11613.26, "total_tokens": 54362112}
|
| 211 |
+
{"current_steps": 211, "total_steps": 315, "loss": 0.0734, "lr": 1.2284696746914216e-05, "epoch": 3.300990099009901, "percentage": 66.98, "elapsed_time": "1:18:23", "remaining_time": "0:38:38", "throughput": 11613.31, "total_tokens": 54624256}
|
| 212 |
+
{"current_steps": 212, "total_steps": 315, "loss": 0.0678, "lr": 1.2070658235302181e-05, "epoch": 3.3168316831683167, "percentage": 67.3, "elapsed_time": "1:18:46", "remaining_time": "0:38:16", "throughput": 11613.37, "total_tokens": 54886400}
|
| 213 |
+
{"current_steps": 213, "total_steps": 315, "loss": 0.0662, "lr": 1.185790575473738e-05, "epoch": 3.3326732673267325, "percentage": 67.62, "elapsed_time": "1:19:08", "remaining_time": "0:37:54", "throughput": 11613.47, "total_tokens": 55148544}
|
| 214 |
+
{"current_steps": 214, "total_steps": 315, "loss": 0.0746, "lr": 1.1646460466876783e-05, "epoch": 3.3485148514851484, "percentage": 67.94, "elapsed_time": "1:19:31", "remaining_time": "0:37:31", "throughput": 11613.55, "total_tokens": 55410688}
|
| 215 |
+
{"current_steps": 215, "total_steps": 315, "loss": 0.0747, "lr": 1.1436343403356017e-05, "epoch": 3.3643564356435642, "percentage": 68.25, "elapsed_time": "1:19:53", "remaining_time": "0:37:09", "throughput": 11613.6, "total_tokens": 55672832}
|
| 216 |
+
{"current_steps": 216, "total_steps": 315, "loss": 0.0647, "lr": 1.122757546369744e-05, "epoch": 3.38019801980198, "percentage": 68.57, "elapsed_time": "1:20:16", "remaining_time": "0:36:47", "throughput": 11613.59, "total_tokens": 55934976}
|
| 217 |
+
{"current_steps": 217, "total_steps": 315, "loss": 0.0666, "lr": 1.1020177413231334e-05, "epoch": 3.396039603960396, "percentage": 68.89, "elapsed_time": "1:20:38", "remaining_time": "0:36:25", "throughput": 11613.63, "total_tokens": 56197120}
|
| 218 |
+
{"current_steps": 218, "total_steps": 315, "loss": 0.0678, "lr": 1.0814169881030459e-05, "epoch": 3.411881188118812, "percentage": 69.21, "elapsed_time": "1:21:01", "remaining_time": "0:36:03", "throughput": 11613.67, "total_tokens": 56459264}
|
| 219 |
+
{"current_steps": 219, "total_steps": 315, "loss": 0.068, "lr": 1.0609573357858166e-05, "epoch": 3.4277227722772277, "percentage": 69.52, "elapsed_time": "1:21:24", "remaining_time": "0:35:40", "throughput": 11613.68, "total_tokens": 56721408}
|
| 220 |
+
{"current_steps": 220, "total_steps": 315, "loss": 0.069, "lr": 1.0406408194130259e-05, "epoch": 3.4435643564356435, "percentage": 69.84, "elapsed_time": "1:21:46", "remaining_time": "0:35:18", "throughput": 11613.59, "total_tokens": 56983552}
|
| 221 |
+
{"current_steps": 221, "total_steps": 315, "loss": 0.0602, "lr": 1.0204694597890812e-05, "epoch": 3.4594059405940594, "percentage": 70.16, "elapsed_time": "1:22:09", "remaining_time": "0:34:56", "throughput": 11613.6, "total_tokens": 57245696}
|
| 222 |
+
{"current_steps": 222, "total_steps": 315, "loss": 0.0698, "lr": 1.0004452632802158e-05, "epoch": 3.4752475247524752, "percentage": 70.48, "elapsed_time": "1:22:31", "remaining_time": "0:34:34", "throughput": 11613.54, "total_tokens": 57507840}
|
| 223 |
+
{"current_steps": 223, "total_steps": 315, "loss": 0.065, "lr": 9.805702216149251e-06, "epoch": 3.491089108910891, "percentage": 70.79, "elapsed_time": "1:22:54", "remaining_time": "0:34:12", "throughput": 11613.51, "total_tokens": 57769984}
|
| 224 |
+
{"current_steps": 224, "total_steps": 315, "loss": 0.0582, "lr": 9.608463116858542e-06, "epoch": 3.506930693069307, "percentage": 71.11, "elapsed_time": "1:23:16", "remaining_time": "0:33:50", "throughput": 11613.52, "total_tokens": 58032128}
|
| 225 |
+
{"current_steps": 225, "total_steps": 315, "loss": 0.063, "lr": 9.412754953531663e-06, "epoch": 3.522772277227723, "percentage": 71.43, "elapsed_time": "1:23:39", "remaining_time": "0:33:27", "throughput": 11613.54, "total_tokens": 58294272}
|
| 226 |
+
{"current_steps": 226, "total_steps": 315, "loss": 0.0686, "lr": 9.21859719249403e-06, "epoch": 3.5386138613861386, "percentage": 71.75, "elapsed_time": "1:24:02", "remaining_time": "0:33:05", "throughput": 11613.56, "total_tokens": 58556416}
|
| 227 |
+
{"current_steps": 227, "total_steps": 315, "loss": 0.0616, "lr": 9.026009145858607e-06, "epoch": 3.5544554455445545, "percentage": 72.06, "elapsed_time": "1:24:24", "remaining_time": "0:32:43", "throughput": 11613.53, "total_tokens": 58818560}
|
| 228 |
+
{"current_steps": 228, "total_steps": 315, "loss": 0.06, "lr": 8.835009969605012e-06, "epoch": 3.5702970297029704, "percentage": 72.38, "elapsed_time": "1:24:47", "remaining_time": "0:32:21", "throughput": 11613.55, "total_tokens": 59080704}
|
| 229 |
+
{"current_steps": 229, "total_steps": 315, "loss": 0.0613, "lr": 8.645618661674142e-06, "epoch": 3.586138613861386, "percentage": 72.7, "elapsed_time": "1:25:09", "remaining_time": "0:31:58", "throughput": 11613.55, "total_tokens": 59342848}
|
| 230 |
+
{"current_steps": 230, "total_steps": 315, "loss": 0.0616, "lr": 8.45785406007852e-06, "epoch": 3.601980198019802, "percentage": 73.02, "elapsed_time": "1:25:32", "remaining_time": "0:31:36", "throughput": 11613.49, "total_tokens": 59604992}
|
| 231 |
+
{"current_steps": 231, "total_steps": 315, "loss": 0.0644, "lr": 8.271734841028553e-06, "epoch": 3.617821782178218, "percentage": 73.33, "elapsed_time": "1:25:54", "remaining_time": "0:31:14", "throughput": 11613.45, "total_tokens": 59867136}
|
| 232 |
+
{"current_steps": 232, "total_steps": 315, "loss": 0.0637, "lr": 8.08727951707487e-06, "epoch": 3.633663366336634, "percentage": 73.65, "elapsed_time": "1:26:17", "remaining_time": "0:30:52", "throughput": 11613.45, "total_tokens": 60129280}
|
| 233 |
+
{"current_steps": 233, "total_steps": 315, "loss": 0.0604, "lr": 7.904506435266998e-06, "epoch": 3.6495049504950496, "percentage": 73.97, "elapsed_time": "1:26:40", "remaining_time": "0:30:30", "throughput": 11613.36, "total_tokens": 60391424}
|
| 234 |
+
{"current_steps": 234, "total_steps": 315, "loss": 0.0623, "lr": 7.723433775328384e-06, "epoch": 3.6653465346534655, "percentage": 74.29, "elapsed_time": "1:27:02", "remaining_time": "0:30:07", "throughput": 11613.39, "total_tokens": 60653568}
|
| 235 |
+
{"current_steps": 235, "total_steps": 315, "loss": 0.0621, "lr": 7.5440795478481815e-06, "epoch": 3.6811881188118813, "percentage": 74.6, "elapsed_time": "1:27:25", "remaining_time": "0:29:45", "throughput": 11613.34, "total_tokens": 60915712}
|
| 236 |
+
{"current_steps": 236, "total_steps": 315, "loss": 0.0599, "lr": 7.366461592489782e-06, "epoch": 3.6970297029702968, "percentage": 74.92, "elapsed_time": "1:27:47", "remaining_time": "0:29:23", "throughput": 11613.37, "total_tokens": 61177856}
|
| 237 |
+
{"current_steps": 237, "total_steps": 315, "loss": 0.0616, "lr": 7.190597576216385e-06, "epoch": 3.7128712871287126, "percentage": 75.24, "elapsed_time": "1:28:10", "remaining_time": "0:29:01", "throughput": 11613.4, "total_tokens": 61440000}
|
| 238 |
+
{"current_steps": 238, "total_steps": 315, "loss": 0.0569, "lr": 7.016504991533726e-06, "epoch": 3.7287128712871285, "percentage": 75.56, "elapsed_time": "1:28:32", "remaining_time": "0:28:38", "throughput": 11613.44, "total_tokens": 61702144}
|
| 239 |
+
{"current_steps": 239, "total_steps": 315, "loss": 0.0601, "lr": 6.844201154750177e-06, "epoch": 3.7445544554455443, "percentage": 75.87, "elapsed_time": "1:28:55", "remaining_time": "0:28:16", "throughput": 11613.48, "total_tokens": 61964288}
|
| 240 |
+
{"current_steps": 240, "total_steps": 315, "loss": 0.0524, "lr": 6.673703204254347e-06, "epoch": 3.76039603960396, "percentage": 76.19, "elapsed_time": "1:29:18", "remaining_time": "0:27:54", "throughput": 11613.35, "total_tokens": 62226432}
|
| 241 |
+
{"current_steps": 241, "total_steps": 315, "loss": 0.0583, "lr": 6.505028098810406e-06, "epoch": 3.776237623762376, "percentage": 76.51, "elapsed_time": "1:29:40", "remaining_time": "0:27:32", "throughput": 11613.39, "total_tokens": 62488576}
|
| 242 |
+
{"current_steps": 242, "total_steps": 315, "loss": 0.0553, "lr": 6.338192615871247e-06, "epoch": 3.792079207920792, "percentage": 76.83, "elapsed_time": "1:30:03", "remaining_time": "0:27:09", "throughput": 11613.35, "total_tokens": 62750720}
|
| 243 |
+
{"current_steps": 243, "total_steps": 315, "loss": 0.0599, "lr": 6.173213349909729e-06, "epoch": 3.8079207920792078, "percentage": 77.14, "elapsed_time": "1:30:25", "remaining_time": "0:26:47", "throughput": 11613.38, "total_tokens": 63012864}
|
| 244 |
+
{"current_steps": 244, "total_steps": 315, "loss": 0.0614, "lr": 6.010106710768052e-06, "epoch": 3.8237623762376236, "percentage": 77.46, "elapsed_time": "1:30:48", "remaining_time": "0:26:25", "throughput": 11613.31, "total_tokens": 63275008}
|
| 245 |
+
{"current_steps": 245, "total_steps": 315, "loss": 0.0562, "lr": 5.848888922025553e-06, "epoch": 3.8396039603960395, "percentage": 77.78, "elapsed_time": "1:31:11", "remaining_time": "0:26:03", "throughput": 11613.3, "total_tokens": 63537152}
|
| 246 |
+
{"current_steps": 246, "total_steps": 315, "loss": 0.0565, "lr": 5.689576019385015e-06, "epoch": 3.8554455445544553, "percentage": 78.1, "elapsed_time": "1:31:33", "remaining_time": "0:25:40", "throughput": 11613.35, "total_tokens": 63799296}
|
| 247 |
+
{"current_steps": 247, "total_steps": 315, "loss": 0.0671, "lr": 5.532183849077652e-06, "epoch": 3.871287128712871, "percentage": 78.41, "elapsed_time": "1:31:56", "remaining_time": "0:25:18", "throughput": 11613.4, "total_tokens": 64061440}
|
| 248 |
+
{"current_steps": 248, "total_steps": 315, "loss": 0.0581, "lr": 5.376728066286943e-06, "epoch": 3.887128712871287, "percentage": 78.73, "elapsed_time": "1:32:18", "remaining_time": "0:24:56", "throughput": 11613.42, "total_tokens": 64323584}
|
| 249 |
+
{"current_steps": 249, "total_steps": 315, "loss": 0.0584, "lr": 5.223224133591476e-06, "epoch": 3.902970297029703, "percentage": 79.05, "elapsed_time": "1:32:41", "remaining_time": "0:24:34", "throughput": 11613.45, "total_tokens": 64585728}
|
| 250 |
+
{"current_steps": 250, "total_steps": 315, "loss": 0.0563, "lr": 5.071687319426946e-06, "epoch": 3.9188118811881187, "percentage": 79.37, "elapsed_time": "1:33:03", "remaining_time": "0:24:11", "throughput": 11613.48, "total_tokens": 64847872}
|
| 251 |
+
{"current_steps": 251, "total_steps": 315, "loss": 0.0601, "lr": 4.922132696567464e-06, "epoch": 3.9346534653465346, "percentage": 79.68, "elapsed_time": "1:33:26", "remaining_time": "0:23:49", "throughput": 11613.44, "total_tokens": 65110016}
|
| 252 |
+
{"current_steps": 252, "total_steps": 315, "loss": 0.0538, "lr": 4.7745751406263165e-06, "epoch": 3.9504950495049505, "percentage": 80.0, "elapsed_time": "1:33:49", "remaining_time": "0:23:27", "throughput": 11613.43, "total_tokens": 65372160}
|
| 253 |
+
{"current_steps": 253, "total_steps": 315, "loss": 0.0587, "lr": 4.629029328576381e-06, "epoch": 3.9663366336633663, "percentage": 80.32, "elapsed_time": "1:34:11", "remaining_time": "0:23:04", "throughput": 11613.45, "total_tokens": 65634304}
|
| 254 |
+
{"current_steps": 254, "total_steps": 315, "loss": 0.0531, "lr": 4.4855097372902135e-06, "epoch": 3.982178217821782, "percentage": 80.63, "elapsed_time": "1:34:34", "remaining_time": "0:22:42", "throughput": 11613.47, "total_tokens": 65896448}
|
| 255 |
+
{"current_steps": 255, "total_steps": 315, "loss": 0.0605, "lr": 4.344030642100133e-06, "epoch": 3.998019801980198, "percentage": 80.95, "elapsed_time": "1:34:56", "remaining_time": "0:22:20", "throughput": 11613.46, "total_tokens": 66158592}
|
| 256 |
+
{"current_steps": 256, "total_steps": 315, "loss": 0.0431, "lr": 4.204606115378282e-06, "epoch": 4.0, "percentage": 81.27, "elapsed_time": "1:34:59", "remaining_time": "0:21:53", "throughput": 11613.55, "total_tokens": 66191360}
|
| 257 |
+
{"current_steps": 257, "total_steps": 315, "loss": 0.0167, "lr": 4.067250025136921e-06, "epoch": 4.015841584158416, "percentage": 81.59, "elapsed_time": "1:35:22", "remaining_time": "0:21:31", "throughput": 11613.52, "total_tokens": 66453504}
|
| 258 |
+
{"current_steps": 258, "total_steps": 315, "loss": 0.0163, "lr": 3.931976033649021e-06, "epoch": 4.031683168316832, "percentage": 81.9, "elapsed_time": "1:35:44", "remaining_time": "0:21:09", "throughput": 11613.45, "total_tokens": 66715648}
|
| 259 |
+
{"current_steps": 259, "total_steps": 315, "loss": 0.0142, "lr": 3.798797596089351e-06, "epoch": 4.047524752475248, "percentage": 82.22, "elapsed_time": "1:36:07", "remaining_time": "0:20:46", "throughput": 11613.44, "total_tokens": 66977792}
|
| 260 |
+
{"current_steps": 260, "total_steps": 315, "loss": 0.0156, "lr": 3.66772795919611e-06, "epoch": 4.063366336633663, "percentage": 82.54, "elapsed_time": "1:36:29", "remaining_time": "0:20:24", "throughput": 11613.39, "total_tokens": 67239936}
|
| 261 |
+
{"current_steps": 261, "total_steps": 315, "loss": 0.0143, "lr": 3.5387801599533475e-06, "epoch": 4.079207920792079, "percentage": 82.86, "elapsed_time": "1:36:52", "remaining_time": "0:20:02", "throughput": 11613.37, "total_tokens": 67502080}
|
| 262 |
+
{"current_steps": 262, "total_steps": 315, "loss": 0.014, "lr": 3.41196702429423e-06, "epoch": 4.095049504950495, "percentage": 83.17, "elapsed_time": "1:37:15", "remaining_time": "0:19:40", "throughput": 11613.34, "total_tokens": 67764224}
|
| 263 |
+
{"current_steps": 263, "total_steps": 315, "loss": 0.0131, "lr": 3.2873011658252796e-06, "epoch": 4.110891089108911, "percentage": 83.49, "elapsed_time": "1:37:37", "remaining_time": "0:19:18", "throughput": 11613.3, "total_tokens": 68026368}
|
| 264 |
+
{"current_steps": 264, "total_steps": 315, "loss": 0.012, "lr": 3.164794984571759e-06, "epoch": 4.126732673267327, "percentage": 83.81, "elapsed_time": "1:38:00", "remaining_time": "0:18:55", "throughput": 11613.3, "total_tokens": 68288512}
|
| 265 |
+
{"current_steps": 265, "total_steps": 315, "loss": 0.0126, "lr": 3.044460665744284e-06, "epoch": 4.142574257425743, "percentage": 84.13, "elapsed_time": "1:38:22", "remaining_time": "0:18:33", "throughput": 11613.29, "total_tokens": 68550656}
|
| 266 |
+
{"current_steps": 266, "total_steps": 315, "loss": 0.0129, "lr": 2.9263101785268254e-06, "epoch": 4.158415841584159, "percentage": 84.44, "elapsed_time": "1:38:45", "remaining_time": "0:18:11", "throughput": 11613.31, "total_tokens": 68812800}
|
| 267 |
+
{"current_steps": 267, "total_steps": 315, "loss": 0.0132, "lr": 2.8103552748861476e-06, "epoch": 4.174257425742574, "percentage": 84.76, "elapsed_time": "1:39:07", "remaining_time": "0:17:49", "throughput": 11613.35, "total_tokens": 69074944}
|
| 268 |
+
{"current_steps": 268, "total_steps": 315, "loss": 0.0107, "lr": 2.6966074884029164e-06, "epoch": 4.19009900990099, "percentage": 85.08, "elapsed_time": "1:39:30", "remaining_time": "0:17:27", "throughput": 11613.38, "total_tokens": 69337088}
|
| 269 |
+
{"current_steps": 269, "total_steps": 315, "loss": 0.0113, "lr": 2.58507813312448e-06, "epoch": 4.205940594059406, "percentage": 85.4, "elapsed_time": "1:39:52", "remaining_time": "0:17:04", "throughput": 11613.42, "total_tokens": 69599232}
|
| 270 |
+
{"current_steps": 270, "total_steps": 315, "loss": 0.0109, "lr": 2.475778302439524e-06, "epoch": 4.221782178217822, "percentage": 85.71, "elapsed_time": "1:40:15", "remaining_time": "0:16:42", "throughput": 11613.47, "total_tokens": 69861376}
|
| 271 |
+
{"current_steps": 271, "total_steps": 315, "loss": 0.0112, "lr": 2.3687188679746315e-06, "epoch": 4.237623762376238, "percentage": 86.03, "elapsed_time": "1:40:38", "remaining_time": "0:16:20", "throughput": 11613.49, "total_tokens": 70123520}
|
| 272 |
+
{"current_steps": 272, "total_steps": 315, "loss": 0.0113, "lr": 2.2639104785129455e-06, "epoch": 4.253465346534654, "percentage": 86.35, "elapsed_time": "1:41:00", "remaining_time": "0:15:58", "throughput": 11613.4, "total_tokens": 70385664}
|
| 273 |
+
{"current_steps": 273, "total_steps": 315, "loss": 0.0108, "lr": 2.1613635589349756e-06, "epoch": 4.2693069306930695, "percentage": 86.67, "elapsed_time": "1:41:23", "remaining_time": "0:15:35", "throughput": 11613.42, "total_tokens": 70647808}
|
| 274 |
+
{"current_steps": 274, "total_steps": 315, "loss": 0.0103, "lr": 2.0610883091816525e-06, "epoch": 4.285148514851485, "percentage": 86.98, "elapsed_time": "1:41:45", "remaining_time": "0:15:13", "throughput": 11613.46, "total_tokens": 70909952}
|
| 275 |
+
{"current_steps": 275, "total_steps": 315, "loss": 0.0115, "lr": 1.9630947032398067e-06, "epoch": 4.300990099009901, "percentage": 87.3, "elapsed_time": "1:42:08", "remaining_time": "0:14:51", "throughput": 11613.46, "total_tokens": 71172096}
|
| 276 |
+
{"current_steps": 276, "total_steps": 315, "loss": 0.012, "lr": 1.8673924881500826e-06, "epoch": 4.316831683168317, "percentage": 87.62, "elapsed_time": "1:42:31", "remaining_time": "0:14:29", "throughput": 11613.42, "total_tokens": 71434240}
|
| 277 |
+
{"current_steps": 277, "total_steps": 315, "loss": 0.0106, "lr": 1.773991183037435e-06, "epoch": 4.332673267326733, "percentage": 87.94, "elapsed_time": "1:42:53", "remaining_time": "0:14:06", "throughput": 11613.45, "total_tokens": 71696384}
|
| 278 |
+
{"current_steps": 278, "total_steps": 315, "loss": 0.0125, "lr": 1.6829000781643094e-06, "epoch": 4.348514851485149, "percentage": 88.25, "elapsed_time": "1:43:16", "remaining_time": "0:13:44", "throughput": 11613.48, "total_tokens": 71958528}
|
| 279 |
+
{"current_steps": 279, "total_steps": 315, "loss": 0.0109, "lr": 1.59412823400657e-06, "epoch": 4.364356435643565, "percentage": 88.57, "elapsed_time": "1:43:38", "remaining_time": "0:13:22", "throughput": 11613.48, "total_tokens": 72220672}
|
| 280 |
+
{"current_steps": 280, "total_steps": 315, "loss": 0.0114, "lr": 1.5076844803522922e-06, "epoch": 4.3801980198019805, "percentage": 88.89, "elapsed_time": "1:44:01", "remaining_time": "0:13:00", "throughput": 11613.57, "total_tokens": 72482816}
|
| 281 |
+
{"current_steps": 281, "total_steps": 315, "loss": 0.0104, "lr": 1.4235774154234855e-06, "epoch": 4.396039603960396, "percentage": 89.21, "elapsed_time": "1:44:23", "remaining_time": "0:12:37", "throughput": 11613.59, "total_tokens": 72744960}
|
| 282 |
+
{"current_steps": 282, "total_steps": 315, "loss": 0.0109, "lr": 1.3418154050208936e-06, "epoch": 4.411881188118812, "percentage": 89.52, "elapsed_time": "1:44:46", "remaining_time": "0:12:15", "throughput": 11613.66, "total_tokens": 73007104}
|
| 283 |
+
{"current_steps": 283, "total_steps": 315, "loss": 0.0115, "lr": 1.2624065816918413e-06, "epoch": 4.427722772277228, "percentage": 89.84, "elapsed_time": "1:45:08", "remaining_time": "0:11:53", "throughput": 11613.72, "total_tokens": 73269248}
|
| 284 |
+
{"current_steps": 284, "total_steps": 315, "loss": 0.0108, "lr": 1.1853588439213442e-06, "epoch": 4.443564356435644, "percentage": 90.16, "elapsed_time": "1:45:31", "remaining_time": "0:11:31", "throughput": 11613.78, "total_tokens": 73531392}
|
| 285 |
+
{"current_steps": 285, "total_steps": 315, "loss": 0.0103, "lr": 1.1106798553464804e-06, "epoch": 4.45940594059406, "percentage": 90.48, "elapsed_time": "1:45:53", "remaining_time": "0:11:08", "throughput": 11613.81, "total_tokens": 73793536}
|
| 286 |
+
{"current_steps": 286, "total_steps": 315, "loss": 0.0107, "lr": 1.038377043994107e-06, "epoch": 4.475247524752476, "percentage": 90.79, "elapsed_time": "1:46:16", "remaining_time": "0:10:46", "throughput": 11613.82, "total_tokens": 74055680}
|
| 287 |
+
{"current_steps": 287, "total_steps": 315, "loss": 0.0122, "lr": 9.684576015420278e-07, "epoch": 4.4910891089108915, "percentage": 91.11, "elapsed_time": "1:46:39", "remaining_time": "0:10:24", "throughput": 11613.87, "total_tokens": 74317824}
|
| 288 |
+
{"current_steps": 288, "total_steps": 315, "loss": 0.0109, "lr": 9.009284826036691e-07, "epoch": 4.506930693069307, "percentage": 91.43, "elapsed_time": "1:47:01", "remaining_time": "0:10:02", "throughput": 11613.88, "total_tokens": 74579968}
|
| 289 |
+
{"current_steps": 289, "total_steps": 315, "loss": 0.0103, "lr": 8.357964040363209e-07, "epoch": 4.522772277227723, "percentage": 91.75, "elapsed_time": "1:47:24", "remaining_time": "0:09:39", "throughput": 11613.87, "total_tokens": 74842112}
|
| 290 |
+
{"current_steps": 290, "total_steps": 315, "loss": 0.011, "lr": 7.730678442730538e-07, "epoch": 4.538613861386139, "percentage": 92.06, "elapsed_time": "1:47:46", "remaining_time": "0:09:17", "throughput": 11613.88, "total_tokens": 75104256}
|
| 291 |
+
{"current_steps": 291, "total_steps": 315, "loss": 0.0103, "lr": 7.127490426783123e-07, "epoch": 4.554455445544555, "percentage": 92.38, "elapsed_time": "1:48:09", "remaining_time": "0:08:55", "throughput": 11613.92, "total_tokens": 75366400}
|
| 292 |
+
{"current_steps": 292, "total_steps": 315, "loss": 0.0104, "lr": 6.54845998927342e-07, "epoch": 4.57029702970297, "percentage": 92.7, "elapsed_time": "1:48:31", "remaining_time": "0:08:32", "throughput": 11613.91, "total_tokens": 75628544}
|
| 293 |
+
{"current_steps": 293, "total_steps": 315, "loss": 0.0097, "lr": 5.993644724093888e-07, "epoch": 4.586138613861386, "percentage": 93.02, "elapsed_time": "1:48:54", "remaining_time": "0:08:10", "throughput": 11613.94, "total_tokens": 75890688}
|
| 294 |
+
{"current_steps": 294, "total_steps": 315, "loss": 0.0105, "lr": 5.463099816548579e-07, "epoch": 4.601980198019802, "percentage": 93.33, "elapsed_time": "1:49:17", "remaining_time": "0:07:48", "throughput": 11613.94, "total_tokens": 76152832}
|
| 295 |
+
{"current_steps": 295, "total_steps": 315, "loss": 0.0096, "lr": 4.956878037864043e-07, "epoch": 4.6178217821782175, "percentage": 93.65, "elapsed_time": "1:49:39", "remaining_time": "0:07:26", "throughput": 11613.96, "total_tokens": 76414976}
|
| 296 |
+
{"current_steps": 296, "total_steps": 315, "loss": 0.0113, "lr": 4.475029739940295e-07, "epoch": 4.633663366336633, "percentage": 93.97, "elapsed_time": "1:50:02", "remaining_time": "0:07:03", "throughput": 11613.91, "total_tokens": 76677120}
|
| 297 |
+
{"current_steps": 297, "total_steps": 315, "loss": 0.0113, "lr": 4.0176028503425835e-07, "epoch": 4.649504950495049, "percentage": 94.29, "elapsed_time": "1:50:24", "remaining_time": "0:06:41", "throughput": 11613.86, "total_tokens": 76939264}
|
| 298 |
+
{"current_steps": 298, "total_steps": 315, "loss": 0.0115, "lr": 3.5846428675342657e-07, "epoch": 4.665346534653465, "percentage": 94.6, "elapsed_time": "1:50:47", "remaining_time": "0:06:19", "throughput": 11613.84, "total_tokens": 77201408}
|
| 299 |
+
{"current_steps": 299, "total_steps": 315, "loss": 0.0097, "lr": 3.1761928563510955e-07, "epoch": 4.681188118811881, "percentage": 94.92, "elapsed_time": "1:51:09", "remaining_time": "0:05:56", "throughput": 11613.83, "total_tokens": 77463552}
|
| 300 |
+
{"current_steps": 300, "total_steps": 315, "loss": 0.0104, "lr": 2.7922934437178695e-07, "epoch": 4.697029702970297, "percentage": 95.24, "elapsed_time": "1:51:32", "remaining_time": "0:05:34", "throughput": 11613.83, "total_tokens": 77725696}
|
| 301 |
+
{"current_steps": 301, "total_steps": 315, "loss": 0.011, "lr": 2.4329828146074095e-07, "epoch": 4.712871287128713, "percentage": 95.56, "elapsed_time": "1:51:55", "remaining_time": "0:05:12", "throughput": 11613.83, "total_tokens": 77987840}
|
| 302 |
+
{"current_steps": 302, "total_steps": 315, "loss": 0.0095, "lr": 2.0982967082424365e-07, "epoch": 4.7287128712871285, "percentage": 95.87, "elapsed_time": "1:52:17", "remaining_time": "0:04:50", "throughput": 11613.83, "total_tokens": 78249984}
|
| 303 |
+
{"current_steps": 303, "total_steps": 315, "loss": 0.0105, "lr": 1.7882684145406614e-07, "epoch": 4.744554455445544, "percentage": 96.19, "elapsed_time": "1:52:40", "remaining_time": "0:04:27", "throughput": 11613.89, "total_tokens": 78512128}
|
| 304 |
+
{"current_steps": 304, "total_steps": 315, "loss": 0.0099, "lr": 1.5029287708036854e-07, "epoch": 4.76039603960396, "percentage": 96.51, "elapsed_time": "1:53:02", "remaining_time": "0:04:05", "throughput": 11613.93, "total_tokens": 78774272}
|
| 305 |
+
{"current_steps": 305, "total_steps": 315, "loss": 0.0106, "lr": 1.2423061586496477e-07, "epoch": 4.776237623762376, "percentage": 96.83, "elapsed_time": "1:53:25", "remaining_time": "0:03:43", "throughput": 11613.96, "total_tokens": 79036416}
|
| 306 |
+
{"current_steps": 306, "total_steps": 315, "loss": 0.0103, "lr": 1.006426501190233e-07, "epoch": 4.792079207920792, "percentage": 97.14, "elapsed_time": "1:53:47", "remaining_time": "0:03:20", "throughput": 11613.99, "total_tokens": 79298560}
|
| 307 |
+
{"current_steps": 307, "total_steps": 315, "loss": 0.0107, "lr": 7.953132604522628e-08, "epoch": 4.807920792079208, "percentage": 97.46, "elapsed_time": "1:54:10", "remaining_time": "0:02:58", "throughput": 11614.02, "total_tokens": 79560704}
|
| 308 |
+
{"current_steps": 308, "total_steps": 315, "loss": 0.0098, "lr": 6.089874350439506e-08, "epoch": 4.823762376237624, "percentage": 97.78, "elapsed_time": "1:54:32", "remaining_time": "0:02:36", "throughput": 11614.02, "total_tokens": 79822848}
|
| 309 |
+
{"current_steps": 309, "total_steps": 315, "loss": 0.0101, "lr": 4.474675580662113e-08, "epoch": 4.8396039603960395, "percentage": 98.1, "elapsed_time": "1:54:55", "remaining_time": "0:02:13", "throughput": 11614.02, "total_tokens": 80084992}
|
| 310 |
+
{"current_steps": 310, "total_steps": 315, "loss": 0.0102, "lr": 3.107696952694139e-08, "epoch": 4.855445544554455, "percentage": 98.41, "elapsed_time": "1:55:18", "remaining_time": "0:01:51", "throughput": 11614.04, "total_tokens": 80347136}
|
| 311 |
+
{"current_steps": 311, "total_steps": 315, "loss": 0.0102, "lr": 1.9890744345518742e-08, "epoch": 4.871287128712871, "percentage": 98.73, "elapsed_time": "1:55:40", "remaining_time": "0:01:29", "throughput": 11614.08, "total_tokens": 80609280}
|
| 312 |
+
{"current_steps": 312, "total_steps": 315, "loss": 0.01, "lr": 1.1189192912416934e-08, "epoch": 4.887128712871287, "percentage": 99.05, "elapsed_time": "1:56:03", "remaining_time": "0:01:06", "throughput": 11614.12, "total_tokens": 80871424}
|
| 313 |
+
{"current_steps": 313, "total_steps": 315, "loss": 0.0102, "lr": 4.9731807369113316e-09, "epoch": 4.902970297029703, "percentage": 99.37, "elapsed_time": "1:56:25", "remaining_time": "0:00:44", "throughput": 11614.13, "total_tokens": 81133568}
|
| 314 |
+
{"current_steps": 314, "total_steps": 315, "loss": 0.0101, "lr": 1.2433261014244136e-09, "epoch": 4.918811881188119, "percentage": 99.68, "elapsed_time": "1:56:48", "remaining_time": "0:00:22", "throughput": 11614.14, "total_tokens": 81395712}
|
| 315 |
+
{"current_steps": 315, "total_steps": 315, "loss": 0.01, "lr": 0.0, "epoch": 4.934653465346535, "percentage": 100.0, "elapsed_time": "1:57:10", "remaining_time": "0:00:00", "throughput": 11614.12, "total_tokens": 81657856}
|