Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccbd89de1f9d6fc57029ed952f4f2dd80dc394655c35757825ab3d765acc3a39
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a414a08cfd1285c5040719f912b6682cc6cf391a6760b20fef1e4360829342c
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:164af978fd3ffc9a41ecad5827bdcdce5eee20925923d5db534f2c5425419fbd
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db66ca7e5c2c79712f1a7a80a27b372db68774f221967b7e86b0972fba0fa9d
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05bfc43747776c3a63d78cbcc1994e4d9dae53b67618b3974a02ba278386b36d
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2235d8e032db30eb1e6bb5e4b0a9c7232b57aac667557e6d0f4d767fce5c5ad3
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6afc672856c6ac47532de62d8987e3f446ebdb58574f8b08d3f24f432a465563
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5734ccdde85c2c0567b99f9bba987c7ec832dc6c969e2bfdeb835724c58ef4f7
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105203b4f738c6ac3b41b9e0324945629d4384650173b5f55a0b2a7bcdd5c82e
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df728b926f690496b5b3e7815679c6faff3a51a45e47625e9c393604679b9407
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a535bb8a37416a4962cfa0b4f9822d6413bc03de029b98963daa11ea20284a
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6b1cc1faef3a03984df585c81d2e905646fe73c847926c295f2d31c315451a
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b19a145fb0fa7c8c9c3af6e54ed111bb162526ddfd8bb83ae84b8c02459eed0
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa45b8da39c3a58af1cf63bcce628bd14635ba6ea5826f1f46e922d3749353a
+size 2123397800

model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 65527752704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,320 @@
+{"current_steps": 1, "total_steps": 1575, "loss": 0.8116, "lr": 5.063291139240507e-07, "epoch": 0.0031733439111463705, "percentage": 0.06, "elapsed_time": "0:06:29", "remaining_time": "7 days, 2:09:35"}
+{"current_steps": 1, "total_steps": 1575, "loss": 0.8116, "lr": 5.063291139240507e-07, "epoch": 0.0031733439111463705, "percentage": 0.06, "elapsed_time": "0:06:22", "remaining_time": "6 days, 23:08:41"}
+{"current_steps": 1, "total_steps": 1575, "loss": 0.8116, "lr": 5.063291139240507e-07, "epoch": 0.0031733439111463705, "percentage": 0.06, "elapsed_time": "0:03:07", "remaining_time": "3 days, 9:52:58"}
+{"current_steps": 2, "total_steps": 1575, "loss": 0.8153, "lr": 1.0126582278481013e-06, "epoch": 0.006346687822292741, "percentage": 0.13, "elapsed_time": "0:06:01", "remaining_time": "3 days, 6:57:14"}
+{"current_steps": 3, "total_steps": 1575, "loss": 0.8057, "lr": 1.518987341772152e-06, "epoch": 0.009520031733439112, "percentage": 0.19, "elapsed_time": "0:08:55", "remaining_time": "3 days, 5:58:04"}
+{"current_steps": 4, "total_steps": 1575, "loss": 0.81, "lr": 2.0253164556962026e-06, "epoch": 0.012693375644585482, "percentage": 0.25, "elapsed_time": "0:11:49", "remaining_time": "3 days, 5:25:54"}
+{"current_steps": 5, "total_steps": 1575, "loss": 0.7939, "lr": 2.5316455696202535e-06, "epoch": 0.01586671955573185, "percentage": 0.32, "elapsed_time": "0:14:43", "remaining_time": "3 days, 5:03:31"}
+{"current_steps": 6, "total_steps": 1575, "loss": 0.7711, "lr": 3.037974683544304e-06, "epoch": 0.019040063466878223, "percentage": 0.38, "elapsed_time": "0:17:36", "remaining_time": "3 days, 4:46:25"}
+{"current_steps": 7, "total_steps": 1575, "loss": 0.7636, "lr": 3.544303797468355e-06, "epoch": 0.022213407378024592, "percentage": 0.44, "elapsed_time": "0:20:30", "remaining_time": "3 days, 4:33:16"}
+{"current_steps": 8, "total_steps": 1575, "loss": 0.7154, "lr": 4.050632911392405e-06, "epoch": 0.025386751289170964, "percentage": 0.51, "elapsed_time": "0:23:23", "remaining_time": "3 days, 4:22:55"}
+{"current_steps": 9, "total_steps": 1575, "loss": 0.7129, "lr": 4.556962025316456e-06, "epoch": 0.028560095200317333, "percentage": 0.57, "elapsed_time": "0:26:18", "remaining_time": "3 days, 4:16:24"}
+{"current_steps": 10, "total_steps": 1575, "loss": 0.6871, "lr": 5.063291139240507e-06, "epoch": 0.0317334391114637, "percentage": 0.63, "elapsed_time": "0:29:12", "remaining_time": "3 days, 4:11:08"}
+{"current_steps": 11, "total_steps": 1575, "loss": 0.6685, "lr": 5.569620253164557e-06, "epoch": 0.03490678302261008, "percentage": 0.7, "elapsed_time": "0:32:06", "remaining_time": "3 days, 4:05:47"}
+{"current_steps": 12, "total_steps": 1575, "loss": 0.6628, "lr": 6.075949367088608e-06, "epoch": 0.038080126933756446, "percentage": 0.76, "elapsed_time": "0:35:00", "remaining_time": "3 days, 3:59:14"}
+{"current_steps": 13, "total_steps": 1575, "loss": 0.6123, "lr": 6.582278481012659e-06, "epoch": 0.041253470844902815, "percentage": 0.83, "elapsed_time": "0:37:54", "remaining_time": "3 days, 3:54:09"}
+{"current_steps": 14, "total_steps": 1575, "loss": 0.607, "lr": 7.08860759493671e-06, "epoch": 0.044426814756049184, "percentage": 0.89, "elapsed_time": "0:40:48", "remaining_time": "3 days, 3:50:55"}
+{"current_steps": 15, "total_steps": 1575, "loss": 0.5893, "lr": 7.5949367088607605e-06, "epoch": 0.04760015866719556, "percentage": 0.95, "elapsed_time": "0:43:43", "remaining_time": "3 days, 3:46:33"}
+{"current_steps": 16, "total_steps": 1575, "loss": 0.5758, "lr": 8.10126582278481e-06, "epoch": 0.05077350257834193, "percentage": 1.02, "elapsed_time": "0:46:37", "remaining_time": "3 days, 3:42:33"}
+{"current_steps": 17, "total_steps": 1575, "loss": 0.5546, "lr": 8.607594936708861e-06, "epoch": 0.0539468464894883, "percentage": 1.08, "elapsed_time": "0:49:32", "remaining_time": "3 days, 3:40:44"}
+{"current_steps": 18, "total_steps": 1575, "loss": 0.5435, "lr": 9.113924050632912e-06, "epoch": 0.057120190400634666, "percentage": 1.14, "elapsed_time": "0:52:28", "remaining_time": "3 days, 3:38:29"}
+{"current_steps": 19, "total_steps": 1575, "loss": 0.5388, "lr": 9.620253164556963e-06, "epoch": 0.06029353431178104, "percentage": 1.21, "elapsed_time": "0:55:22", "remaining_time": "3 days, 3:35:05"}
+{"current_steps": 20, "total_steps": 1575, "loss": 0.5292, "lr": 1.0126582278481014e-05, "epoch": 0.0634668782229274, "percentage": 1.27, "elapsed_time": "0:58:15", "remaining_time": "3 days, 3:30:09"}
+{"current_steps": 21, "total_steps": 1575, "loss": 0.5263, "lr": 1.0632911392405063e-05, "epoch": 0.06664022213407378, "percentage": 1.33, "elapsed_time": "1:01:09", "remaining_time": "3 days, 3:25:12"}
+{"current_steps": 22, "total_steps": 1575, "loss": 0.5136, "lr": 1.1139240506329114e-05, "epoch": 0.06981356604522015, "percentage": 1.4, "elapsed_time": "1:04:02", "remaining_time": "3 days, 3:20:22"}
+{"current_steps": 23, "total_steps": 1575, "loss": 0.5055, "lr": 1.1645569620253165e-05, "epoch": 0.07298690995636652, "percentage": 1.46, "elapsed_time": "1:06:55", "remaining_time": "3 days, 3:15:43"}
+{"current_steps": 24, "total_steps": 1575, "loss": 0.5037, "lr": 1.2151898734177216e-05, "epoch": 0.07616025386751289, "percentage": 1.52, "elapsed_time": "1:09:48", "remaining_time": "3 days, 3:11:43"}
+{"current_steps": 25, "total_steps": 1575, "loss": 0.4961, "lr": 1.2658227848101268e-05, "epoch": 0.07933359777865927, "percentage": 1.59, "elapsed_time": "1:12:43", "remaining_time": "3 days, 3:09:10"}
+{"current_steps": 26, "total_steps": 1575, "loss": 0.4934, "lr": 1.3164556962025317e-05, "epoch": 0.08250694168980563, "percentage": 1.65, "elapsed_time": "1:15:38", "remaining_time": "3 days, 3:06:24"}
+{"current_steps": 27, "total_steps": 1575, "loss": 0.4837, "lr": 1.3670886075949368e-05, "epoch": 0.085680285600952, "percentage": 1.71, "elapsed_time": "1:18:31", "remaining_time": "3 days, 3:02:17"}
+{"current_steps": 28, "total_steps": 1575, "loss": 0.4889, "lr": 1.417721518987342e-05, "epoch": 0.08885362951209837, "percentage": 1.78, "elapsed_time": "1:21:24", "remaining_time": "3 days, 2:58:13"}
+{"current_steps": 29, "total_steps": 1575, "loss": 0.481, "lr": 1.468354430379747e-05, "epoch": 0.09202697342324474, "percentage": 1.84, "elapsed_time": "1:24:18", "remaining_time": "3 days, 2:54:12"}
+{"current_steps": 30, "total_steps": 1575, "loss": 0.4766, "lr": 1.5189873417721521e-05, "epoch": 0.09520031733439112, "percentage": 1.9, "elapsed_time": "1:27:11", "remaining_time": "3 days, 2:50:21"}
+{"current_steps": 31, "total_steps": 1575, "loss": 0.461, "lr": 1.5696202531645572e-05, "epoch": 0.09837366124553748, "percentage": 1.97, "elapsed_time": "1:30:05", "remaining_time": "3 days, 2:47:18"}
+{"current_steps": 32, "total_steps": 1575, "loss": 0.4666, "lr": 1.620253164556962e-05, "epoch": 0.10154700515668386, "percentage": 2.03, "elapsed_time": "1:33:00", "remaining_time": "3 days, 2:44:54"}
+{"current_steps": 33, "total_steps": 1575, "loss": 0.4623, "lr": 1.6708860759493674e-05, "epoch": 0.10472034906783023, "percentage": 2.1, "elapsed_time": "1:35:54", "remaining_time": "3 days, 2:41:55"}
+{"current_steps": 34, "total_steps": 1575, "loss": 0.4679, "lr": 1.7215189873417723e-05, "epoch": 0.1078936929789766, "percentage": 2.16, "elapsed_time": "1:38:48", "remaining_time": "3 days, 2:38:27"}
+{"current_steps": 35, "total_steps": 1575, "loss": 0.4524, "lr": 1.7721518987341772e-05, "epoch": 0.11106703689012297, "percentage": 2.22, "elapsed_time": "1:41:42", "remaining_time": "3 days, 2:35:13"}
+{"current_steps": 36, "total_steps": 1575, "loss": 0.4555, "lr": 1.8227848101265824e-05, "epoch": 0.11424038080126933, "percentage": 2.29, "elapsed_time": "1:44:37", "remaining_time": "3 days, 2:32:57"}
+{"current_steps": 37, "total_steps": 1575, "loss": 0.4504, "lr": 1.8734177215189874e-05, "epoch": 0.1174137247124157, "percentage": 2.35, "elapsed_time": "1:47:32", "remaining_time": "3 days, 2:30:32"}
+{"current_steps": 38, "total_steps": 1575, "loss": 0.4523, "lr": 1.9240506329113926e-05, "epoch": 0.12058706862356208, "percentage": 2.41, "elapsed_time": "1:50:27", "remaining_time": "3 days, 2:27:56"}
+{"current_steps": 39, "total_steps": 1575, "loss": 0.4455, "lr": 1.974683544303798e-05, "epoch": 0.12376041253470844, "percentage": 2.48, "elapsed_time": "1:53:22", "remaining_time": "3 days, 2:25:11"}
+{"current_steps": 40, "total_steps": 1575, "loss": 0.4468, "lr": 2.0253164556962028e-05, "epoch": 0.1269337564458548, "percentage": 2.54, "elapsed_time": "1:56:17", "remaining_time": "3 days, 2:22:27"}
+{"current_steps": 41, "total_steps": 1575, "loss": 0.4392, "lr": 2.0759493670886077e-05, "epoch": 0.13010710035700118, "percentage": 2.6, "elapsed_time": "1:59:11", "remaining_time": "3 days, 2:19:37"}
+{"current_steps": 42, "total_steps": 1575, "loss": 0.4381, "lr": 2.1265822784810126e-05, "epoch": 0.13328044426814756, "percentage": 2.67, "elapsed_time": "2:02:06", "remaining_time": "3 days, 2:16:48"}
+{"current_steps": 43, "total_steps": 1575, "loss": 0.4387, "lr": 2.177215189873418e-05, "epoch": 0.13645378817929393, "percentage": 2.73, "elapsed_time": "2:04:59", "remaining_time": "3 days, 2:13:06"}
+{"current_steps": 44, "total_steps": 1575, "loss": 0.4336, "lr": 2.2278481012658228e-05, "epoch": 0.1396271320904403, "percentage": 2.79, "elapsed_time": "2:07:52", "remaining_time": "3 days, 2:09:36"}
+{"current_steps": 45, "total_steps": 1575, "loss": 0.4325, "lr": 2.278481012658228e-05, "epoch": 0.14280047600158668, "percentage": 2.86, "elapsed_time": "2:10:45", "remaining_time": "3 days, 2:06:00"}
+{"current_steps": 46, "total_steps": 1575, "loss": 0.4324, "lr": 2.329113924050633e-05, "epoch": 0.14597381991273303, "percentage": 2.92, "elapsed_time": "2:13:39", "remaining_time": "3 days, 2:02:34"}
+{"current_steps": 47, "total_steps": 1575, "loss": 0.4316, "lr": 2.379746835443038e-05, "epoch": 0.1491471638238794, "percentage": 2.98, "elapsed_time": "2:16:33", "remaining_time": "3 days, 1:59:49"}
+{"current_steps": 48, "total_steps": 1575, "loss": 0.4287, "lr": 2.430379746835443e-05, "epoch": 0.15232050773502578, "percentage": 3.05, "elapsed_time": "2:19:29", "remaining_time": "3 days, 1:57:32"}
+{"current_steps": 49, "total_steps": 1575, "loss": 0.4313, "lr": 2.481012658227848e-05, "epoch": 0.15549385164617216, "percentage": 3.11, "elapsed_time": "2:22:22", "remaining_time": "3 days, 1:54:12"}
+{"current_steps": 50, "total_steps": 1575, "loss": 0.4237, "lr": 2.5316455696202537e-05, "epoch": 0.15866719555731854, "percentage": 3.17, "elapsed_time": "2:25:16", "remaining_time": "3 days, 1:50:54"}
+{"current_steps": 51, "total_steps": 1575, "loss": 0.4275, "lr": 2.5822784810126586e-05, "epoch": 0.16184053946846488, "percentage": 3.24, "elapsed_time": "2:28:10", "remaining_time": "3 days, 1:47:47"}
+{"current_steps": 52, "total_steps": 1575, "loss": 0.4183, "lr": 2.6329113924050635e-05, "epoch": 0.16501388337961126, "percentage": 3.3, "elapsed_time": "2:31:03", "remaining_time": "3 days, 1:44:28"}
+{"current_steps": 53, "total_steps": 1575, "loss": 0.4215, "lr": 2.6835443037974687e-05, "epoch": 0.16818722729075763, "percentage": 3.37, "elapsed_time": "2:33:57", "remaining_time": "3 days, 1:41:25"}
+{"current_steps": 54, "total_steps": 1575, "loss": 0.4287, "lr": 2.7341772151898737e-05, "epoch": 0.171360571201904, "percentage": 3.43, "elapsed_time": "2:36:53", "remaining_time": "3 days, 1:39:06"}
+{"current_steps": 55, "total_steps": 1575, "loss": 0.4231, "lr": 2.784810126582279e-05, "epoch": 0.1745339151130504, "percentage": 3.49, "elapsed_time": "2:39:46", "remaining_time": "3 days, 1:35:45"}
+{"current_steps": 56, "total_steps": 1575, "loss": 0.4178, "lr": 2.835443037974684e-05, "epoch": 0.17770725902419673, "percentage": 3.56, "elapsed_time": "2:42:41", "remaining_time": "3 days, 1:32:49"}
+{"current_steps": 57, "total_steps": 1575, "loss": 0.4212, "lr": 2.8860759493670888e-05, "epoch": 0.1808806029353431, "percentage": 3.62, "elapsed_time": "2:45:35", "remaining_time": "3 days, 1:30:00"}
+{"current_steps": 58, "total_steps": 1575, "loss": 0.4233, "lr": 2.936708860759494e-05, "epoch": 0.18405394684648949, "percentage": 3.68, "elapsed_time": "2:48:29", "remaining_time": "3 days, 1:26:51"}
+{"current_steps": 59, "total_steps": 1575, "loss": 0.4141, "lr": 2.987341772151899e-05, "epoch": 0.18722729075763586, "percentage": 3.75, "elapsed_time": "2:51:24", "remaining_time": "3 days, 1:24:10"}
+{"current_steps": 60, "total_steps": 1575, "loss": 0.408, "lr": 3.0379746835443042e-05, "epoch": 0.19040063466878224, "percentage": 3.81, "elapsed_time": "2:54:18", "remaining_time": "3 days, 1:21:09"}
+{"current_steps": 61, "total_steps": 1575, "loss": 0.4233, "lr": 3.088607594936709e-05, "epoch": 0.1935739785799286, "percentage": 3.87, "elapsed_time": "2:57:12", "remaining_time": "3 days, 1:18:24"}
+{"current_steps": 62, "total_steps": 1575, "loss": 0.4259, "lr": 3.1392405063291144e-05, "epoch": 0.19674732249107496, "percentage": 3.94, "elapsed_time": "3:00:07", "remaining_time": "3 days, 1:15:33"}
+{"current_steps": 63, "total_steps": 1575, "loss": 0.4128, "lr": 3.1898734177215196e-05, "epoch": 0.19992066640222134, "percentage": 4.0, "elapsed_time": "3:03:02", "remaining_time": "3 days, 1:12:57"}
+{"current_steps": 64, "total_steps": 1575, "loss": 0.4149, "lr": 3.240506329113924e-05, "epoch": 0.2030940103133677, "percentage": 4.06, "elapsed_time": "3:05:57", "remaining_time": "3 days, 1:10:24"}
+{"current_steps": 65, "total_steps": 1575, "loss": 0.4206, "lr": 3.2911392405063295e-05, "epoch": 0.2062673542245141, "percentage": 4.13, "elapsed_time": "3:08:52", "remaining_time": "3 days, 1:07:50"}
+{"current_steps": 66, "total_steps": 1575, "loss": 0.4149, "lr": 3.341772151898735e-05, "epoch": 0.20944069813566046, "percentage": 4.19, "elapsed_time": "3:11:45", "remaining_time": "3 days, 1:04:28"}
+{"current_steps": 67, "total_steps": 1575, "loss": 0.4158, "lr": 3.392405063291139e-05, "epoch": 0.2126140420468068, "percentage": 4.25, "elapsed_time": "3:14:38", "remaining_time": "3 days, 1:01:03"}
+{"current_steps": 68, "total_steps": 1575, "loss": 0.4122, "lr": 3.4430379746835445e-05, "epoch": 0.2157873859579532, "percentage": 4.32, "elapsed_time": "3:17:32", "remaining_time": "3 days, 0:57:43"}
+{"current_steps": 69, "total_steps": 1575, "loss": 0.4064, "lr": 3.49367088607595e-05, "epoch": 0.21896072986909956, "percentage": 4.38, "elapsed_time": "3:20:26", "remaining_time": "3 days, 0:54:57"}
+{"current_steps": 70, "total_steps": 1575, "loss": 0.4117, "lr": 3.5443037974683544e-05, "epoch": 0.22213407378024594, "percentage": 4.44, "elapsed_time": "3:23:21", "remaining_time": "3 days, 0:52:17"}
+{"current_steps": 71, "total_steps": 1575, "loss": 0.4077, "lr": 3.5949367088607596e-05, "epoch": 0.22530741769139231, "percentage": 4.51, "elapsed_time": "3:26:17", "remaining_time": "3 days, 0:49:58"}
+{"current_steps": 72, "total_steps": 1575, "loss": 0.3973, "lr": 3.645569620253165e-05, "epoch": 0.22848076160253866, "percentage": 4.57, "elapsed_time": "3:29:12", "remaining_time": "3 days, 0:47:13"}
+{"current_steps": 73, "total_steps": 1575, "loss": 0.4033, "lr": 3.69620253164557e-05, "epoch": 0.23165410551368504, "percentage": 4.63, "elapsed_time": "3:32:06", "remaining_time": "3 days, 0:44:15"}
+{"current_steps": 74, "total_steps": 1575, "loss": 0.4035, "lr": 3.746835443037975e-05, "epoch": 0.2348274494248314, "percentage": 4.7, "elapsed_time": "3:34:59", "remaining_time": "3 days, 0:40:56"}
+{"current_steps": 75, "total_steps": 1575, "loss": 0.402, "lr": 3.79746835443038e-05, "epoch": 0.2380007933359778, "percentage": 4.76, "elapsed_time": "3:37:53", "remaining_time": "3 days, 0:37:47"}
+{"current_steps": 76, "total_steps": 1575, "loss": 0.4048, "lr": 3.848101265822785e-05, "epoch": 0.24117413724712417, "percentage": 4.83, "elapsed_time": "3:40:48", "remaining_time": "3 days, 0:34:59"}
+{"current_steps": 77, "total_steps": 1575, "loss": 0.3987, "lr": 3.89873417721519e-05, "epoch": 0.24434748115827054, "percentage": 4.89, "elapsed_time": "3:43:43", "remaining_time": "3 days, 0:32:18"}
+{"current_steps": 78, "total_steps": 1575, "loss": 0.4058, "lr": 3.949367088607596e-05, "epoch": 0.2475208250694169, "percentage": 4.95, "elapsed_time": "3:46:37", "remaining_time": "3 days, 0:29:18"}
+{"current_steps": 79, "total_steps": 1575, "loss": 0.4025, "lr": 4e-05, "epoch": 0.2506941689805633, "percentage": 5.02, "elapsed_time": "3:49:32", "remaining_time": "3 days, 0:26:50"}
+{"current_steps": 80, "total_steps": 1575, "loss": 0.403, "lr": 4.0506329113924056e-05, "epoch": 0.2538675128917096, "percentage": 5.08, "elapsed_time": "3:52:30", "remaining_time": "3 days, 0:25:01"}
+{"current_steps": 81, "total_steps": 1575, "loss": 0.4021, "lr": 4.10126582278481e-05, "epoch": 0.257040856802856, "percentage": 5.14, "elapsed_time": "3:55:26", "remaining_time": "3 days, 0:22:35"}
+{"current_steps": 82, "total_steps": 1575, "loss": 0.401, "lr": 4.1518987341772154e-05, "epoch": 0.26021420071400236, "percentage": 5.21, "elapsed_time": "3:58:22", "remaining_time": "3 days, 0:20:03"}
+{"current_steps": 83, "total_steps": 1575, "loss": 0.3999, "lr": 4.202531645569621e-05, "epoch": 0.26338754462514874, "percentage": 5.27, "elapsed_time": "4:01:19", "remaining_time": "3 days, 0:18:02"}
+{"current_steps": 84, "total_steps": 1575, "loss": 0.3984, "lr": 4.253164556962025e-05, "epoch": 0.2665608885362951, "percentage": 5.33, "elapsed_time": "4:04:12", "remaining_time": "3 days, 0:14:45"}
+{"current_steps": 85, "total_steps": 1575, "loss": 0.3984, "lr": 4.3037974683544305e-05, "epoch": 0.2697342324474415, "percentage": 5.4, "elapsed_time": "4:07:08", "remaining_time": "3 days, 0:12:06"}
+{"current_steps": 86, "total_steps": 1575, "loss": 0.3939, "lr": 4.354430379746836e-05, "epoch": 0.27290757635858787, "percentage": 5.46, "elapsed_time": "4:10:02", "remaining_time": "3 days, 0:09:20"}
+{"current_steps": 87, "total_steps": 1575, "loss": 0.4037, "lr": 4.405063291139241e-05, "epoch": 0.27608092026973424, "percentage": 5.52, "elapsed_time": "4:12:57", "remaining_time": "3 days, 0:06:33"}
+{"current_steps": 88, "total_steps": 1575, "loss": 0.3962, "lr": 4.4556962025316456e-05, "epoch": 0.2792542641808806, "percentage": 5.59, "elapsed_time": "4:15:52", "remaining_time": "3 days, 0:03:35"}
+{"current_steps": 89, "total_steps": 1575, "loss": 0.4019, "lr": 4.506329113924051e-05, "epoch": 0.282427608092027, "percentage": 5.65, "elapsed_time": "4:18:45", "remaining_time": "3 days, 0:00:20"}
+{"current_steps": 90, "total_steps": 1575, "loss": 0.3998, "lr": 4.556962025316456e-05, "epoch": 0.28560095200317337, "percentage": 5.71, "elapsed_time": "4:21:38", "remaining_time": "2 days, 23:57:04"}
+{"current_steps": 91, "total_steps": 1575, "loss": 0.4078, "lr": 4.607594936708861e-05, "epoch": 0.2887742959143197, "percentage": 5.78, "elapsed_time": "4:24:33", "remaining_time": "2 days, 23:54:20"}
+{"current_steps": 92, "total_steps": 1575, "loss": 0.3953, "lr": 4.658227848101266e-05, "epoch": 0.29194763982546607, "percentage": 5.84, "elapsed_time": "4:27:28", "remaining_time": "2 days, 23:51:36"}
+{"current_steps": 93, "total_steps": 1575, "loss": 0.4012, "lr": 4.708860759493671e-05, "epoch": 0.29512098373661244, "percentage": 5.9, "elapsed_time": "4:30:24", "remaining_time": "2 days, 23:49:01"}
+{"current_steps": 94, "total_steps": 1575, "loss": 0.3989, "lr": 4.759493670886076e-05, "epoch": 0.2982943276477588, "percentage": 5.97, "elapsed_time": "4:33:19", "remaining_time": "2 days, 23:46:22"}
+{"current_steps": 95, "total_steps": 1575, "loss": 0.3983, "lr": 4.810126582278481e-05, "epoch": 0.3014676715589052, "percentage": 6.03, "elapsed_time": "4:36:14", "remaining_time": "2 days, 23:43:31"}
+{"current_steps": 96, "total_steps": 1575, "loss": 0.3981, "lr": 4.860759493670886e-05, "epoch": 0.30464101547005157, "percentage": 6.1, "elapsed_time": "4:39:09", "remaining_time": "2 days, 23:40:43"}
+{"current_steps": 97, "total_steps": 1575, "loss": 0.3974, "lr": 4.911392405063292e-05, "epoch": 0.30781435938119794, "percentage": 6.16, "elapsed_time": "4:42:02", "remaining_time": "2 days, 23:37:37"}
+{"current_steps": 98, "total_steps": 1575, "loss": 0.3944, "lr": 4.962025316455696e-05, "epoch": 0.3109877032923443, "percentage": 6.22, "elapsed_time": "4:44:56", "remaining_time": "2 days, 23:34:34"}
+{"current_steps": 99, "total_steps": 1575, "loss": 0.3946, "lr": 5.012658227848102e-05, "epoch": 0.3141610472034907, "percentage": 6.29, "elapsed_time": "4:47:50", "remaining_time": "2 days, 23:31:29"}
+{"current_steps": 100, "total_steps": 1575, "loss": 0.4048, "lr": 5.063291139240507e-05, "epoch": 0.31733439111463707, "percentage": 6.35, "elapsed_time": "4:50:44", "remaining_time": "2 days, 23:28:31"}
+{"current_steps": 101, "total_steps": 1575, "loss": 0.3918, "lr": 5.113924050632911e-05, "epoch": 0.32050773502578345, "percentage": 6.41, "elapsed_time": "4:53:38", "remaining_time": "2 days, 23:25:25"}
+{"current_steps": 102, "total_steps": 1575, "loss": 0.3924, "lr": 5.164556962025317e-05, "epoch": 0.32368107893692977, "percentage": 6.48, "elapsed_time": "4:56:32", "remaining_time": "2 days, 23:22:19"}
+{"current_steps": 103, "total_steps": 1575, "loss": 0.3991, "lr": 5.2151898734177224e-05, "epoch": 0.32685442284807614, "percentage": 6.54, "elapsed_time": "4:59:28", "remaining_time": "2 days, 23:19:49"}
+{"current_steps": 104, "total_steps": 1575, "loss": 0.3937, "lr": 5.265822784810127e-05, "epoch": 0.3300277667592225, "percentage": 6.6, "elapsed_time": "5:02:23", "remaining_time": "2 days, 23:17:08"}
+{"current_steps": 105, "total_steps": 1575, "loss": 0.3945, "lr": 5.316455696202532e-05, "epoch": 0.3332011106703689, "percentage": 6.67, "elapsed_time": "5:05:19", "remaining_time": "2 days, 23:14:33"}
+{"current_steps": 106, "total_steps": 1575, "loss": 0.395, "lr": 5.3670886075949375e-05, "epoch": 0.33637445458151527, "percentage": 6.73, "elapsed_time": "5:08:14", "remaining_time": "2 days, 23:11:51"}
+{"current_steps": 107, "total_steps": 1575, "loss": 0.395, "lr": 5.417721518987342e-05, "epoch": 0.33954779849266165, "percentage": 6.79, "elapsed_time": "5:11:09", "remaining_time": "2 days, 23:08:55"}
+{"current_steps": 108, "total_steps": 1575, "loss": 0.3941, "lr": 5.468354430379747e-05, "epoch": 0.342721142403808, "percentage": 6.86, "elapsed_time": "5:14:04", "remaining_time": "2 days, 23:06:08"}
+{"current_steps": 109, "total_steps": 1575, "loss": 0.387, "lr": 5.5189873417721526e-05, "epoch": 0.3458944863149544, "percentage": 6.92, "elapsed_time": "5:16:59", "remaining_time": "2 days, 23:03:17"}
+{"current_steps": 110, "total_steps": 1575, "loss": 0.3839, "lr": 5.569620253164558e-05, "epoch": 0.3490678302261008, "percentage": 6.98, "elapsed_time": "5:19:54", "remaining_time": "2 days, 23:00:29"}
+{"current_steps": 111, "total_steps": 1575, "loss": 0.3876, "lr": 5.6202531645569624e-05, "epoch": 0.35224117413724715, "percentage": 7.05, "elapsed_time": "5:22:49", "remaining_time": "2 days, 22:57:42"}
+{"current_steps": 112, "total_steps": 1575, "loss": 0.3876, "lr": 5.670886075949368e-05, "epoch": 0.35541451804839347, "percentage": 7.11, "elapsed_time": "5:25:42", "remaining_time": "2 days, 22:54:31"}
+{"current_steps": 113, "total_steps": 1575, "loss": 0.3849, "lr": 5.721518987341773e-05, "epoch": 0.35858786195953984, "percentage": 7.17, "elapsed_time": "5:28:35", "remaining_time": "2 days, 22:51:19"}
+{"current_steps": 114, "total_steps": 1575, "loss": 0.3896, "lr": 5.7721518987341775e-05, "epoch": 0.3617612058706862, "percentage": 7.24, "elapsed_time": "5:31:28", "remaining_time": "2 days, 22:48:09"}
+{"current_steps": 115, "total_steps": 1575, "loss": 0.3876, "lr": 5.822784810126583e-05, "epoch": 0.3649345497818326, "percentage": 7.3, "elapsed_time": "5:34:23", "remaining_time": "2 days, 22:45:17"}
+{"current_steps": 116, "total_steps": 1575, "loss": 0.3874, "lr": 5.873417721518988e-05, "epoch": 0.36810789369297897, "percentage": 7.37, "elapsed_time": "5:37:17", "remaining_time": "2 days, 22:42:23"}
+{"current_steps": 117, "total_steps": 1575, "loss": 0.3917, "lr": 5.9240506329113926e-05, "epoch": 0.37128123760412535, "percentage": 7.43, "elapsed_time": "5:40:12", "remaining_time": "2 days, 22:39:29"}
+{"current_steps": 118, "total_steps": 1575, "loss": 0.3878, "lr": 5.974683544303798e-05, "epoch": 0.3744545815152717, "percentage": 7.49, "elapsed_time": "5:43:06", "remaining_time": "2 days, 22:36:33"}
+{"current_steps": 119, "total_steps": 1575, "loss": 0.3878, "lr": 6.025316455696203e-05, "epoch": 0.3776279254264181, "percentage": 7.56, "elapsed_time": "5:46:01", "remaining_time": "2 days, 22:33:46"}
+{"current_steps": 120, "total_steps": 1575, "loss": 0.3911, "lr": 6.0759493670886084e-05, "epoch": 0.3808012693375645, "percentage": 7.62, "elapsed_time": "5:48:55", "remaining_time": "2 days, 22:30:45"}
+{"current_steps": 121, "total_steps": 1575, "loss": 0.3974, "lr": 6.126582278481012e-05, "epoch": 0.38397461324871085, "percentage": 7.68, "elapsed_time": "5:51:48", "remaining_time": "2 days, 22:27:36"}
+{"current_steps": 122, "total_steps": 1575, "loss": 0.3962, "lr": 6.177215189873418e-05, "epoch": 0.3871479571598572, "percentage": 7.75, "elapsed_time": "5:54:42", "remaining_time": "2 days, 22:24:31"}
+{"current_steps": 123, "total_steps": 1575, "loss": 0.3883, "lr": 6.227848101265824e-05, "epoch": 0.39032130107100355, "percentage": 7.81, "elapsed_time": "5:57:37", "remaining_time": "2 days, 22:21:40"}
+{"current_steps": 124, "total_steps": 1575, "loss": 0.3892, "lr": 6.278481012658229e-05, "epoch": 0.3934946449821499, "percentage": 7.87, "elapsed_time": "6:00:30", "remaining_time": "2 days, 22:18:33"}
+{"current_steps": 125, "total_steps": 1575, "loss": 0.3905, "lr": 6.329113924050633e-05, "epoch": 0.3966679888932963, "percentage": 7.94, "elapsed_time": "6:03:24", "remaining_time": "2 days, 22:15:31"}
+{"current_steps": 126, "total_steps": 1575, "loss": 0.3954, "lr": 6.379746835443039e-05, "epoch": 0.3998413328044427, "percentage": 8.0, "elapsed_time": "6:06:18", "remaining_time": "2 days, 22:12:33"}
+{"current_steps": 127, "total_steps": 1575, "loss": 0.3977, "lr": 6.430379746835444e-05, "epoch": 0.40301467671558905, "percentage": 8.06, "elapsed_time": "6:09:12", "remaining_time": "2 days, 22:09:32"}
+{"current_steps": 128, "total_steps": 1575, "loss": 0.3919, "lr": 6.481012658227848e-05, "epoch": 0.4061880206267354, "percentage": 8.13, "elapsed_time": "6:12:06", "remaining_time": "2 days, 22:06:39"}
+{"current_steps": 129, "total_steps": 1575, "loss": 0.3882, "lr": 6.531645569620254e-05, "epoch": 0.4093613645378818, "percentage": 8.19, "elapsed_time": "6:15:01", "remaining_time": "2 days, 22:03:45"}
+{"current_steps": 130, "total_steps": 1575, "loss": 0.3916, "lr": 6.582278481012659e-05, "epoch": 0.4125347084490282, "percentage": 8.25, "elapsed_time": "6:17:54", "remaining_time": "2 days, 22:00:39"}
+{"current_steps": 131, "total_steps": 1575, "loss": 0.3889, "lr": 6.632911392405063e-05, "epoch": 0.41570805236017455, "percentage": 8.32, "elapsed_time": "6:20:49", "remaining_time": "2 days, 21:57:48"}
+{"current_steps": 132, "total_steps": 1575, "loss": 0.3915, "lr": 6.68354430379747e-05, "epoch": 0.4188813962713209, "percentage": 8.38, "elapsed_time": "6:23:44", "remaining_time": "2 days, 21:54:56"}
+{"current_steps": 133, "total_steps": 1575, "loss": 0.3841, "lr": 6.734177215189874e-05, "epoch": 0.42205474018246725, "percentage": 8.44, "elapsed_time": "6:26:39", "remaining_time": "2 days, 21:52:08"}
+{"current_steps": 134, "total_steps": 1575, "loss": 0.3809, "lr": 6.784810126582279e-05, "epoch": 0.4252280840936136, "percentage": 8.51, "elapsed_time": "6:29:33", "remaining_time": "2 days, 21:49:12"}
+{"current_steps": 135, "total_steps": 1575, "loss": 0.3838, "lr": 6.835443037974685e-05, "epoch": 0.42840142800476, "percentage": 8.57, "elapsed_time": "6:32:26", "remaining_time": "2 days, 21:46:07"}
+{"current_steps": 136, "total_steps": 1575, "loss": 0.386, "lr": 6.886075949367089e-05, "epoch": 0.4315747719159064, "percentage": 8.63, "elapsed_time": "6:35:20", "remaining_time": "2 days, 21:43:03"}
+{"current_steps": 137, "total_steps": 1575, "loss": 0.3824, "lr": 6.936708860759494e-05, "epoch": 0.43474811582705275, "percentage": 8.7, "elapsed_time": "6:38:14", "remaining_time": "2 days, 21:40:02"}
+{"current_steps": 138, "total_steps": 1575, "loss": 0.3864, "lr": 6.9873417721519e-05, "epoch": 0.4379214597381991, "percentage": 8.76, "elapsed_time": "6:41:09", "remaining_time": "2 days, 21:37:14"}
+{"current_steps": 139, "total_steps": 1575, "loss": 0.3884, "lr": 7.037974683544304e-05, "epoch": 0.4410948036493455, "percentage": 8.83, "elapsed_time": "6:44:04", "remaining_time": "2 days, 21:34:23"}
+{"current_steps": 140, "total_steps": 1575, "loss": 0.3977, "lr": 7.088607594936709e-05, "epoch": 0.4442681475604919, "percentage": 8.89, "elapsed_time": "6:46:59", "remaining_time": "2 days, 21:31:38"}
+{"current_steps": 141, "total_steps": 1575, "loss": 0.4034, "lr": 7.139240506329115e-05, "epoch": 0.44744149147163825, "percentage": 8.95, "elapsed_time": "6:49:53", "remaining_time": "2 days, 21:28:42"}
+{"current_steps": 142, "total_steps": 1575, "loss": 0.3897, "lr": 7.189873417721519e-05, "epoch": 0.45061483538278463, "percentage": 9.02, "elapsed_time": "6:52:47", "remaining_time": "2 days, 21:25:38"}
+{"current_steps": 143, "total_steps": 1575, "loss": 0.4007, "lr": 7.240506329113925e-05, "epoch": 0.453788179293931, "percentage": 9.08, "elapsed_time": "6:55:40", "remaining_time": "2 days, 21:22:31"}
+{"current_steps": 144, "total_steps": 1575, "loss": 0.3858, "lr": 7.29113924050633e-05, "epoch": 0.4569615232050773, "percentage": 9.14, "elapsed_time": "6:58:33", "remaining_time": "2 days, 21:19:25"}
+{"current_steps": 145, "total_steps": 1575, "loss": 0.3921, "lr": 7.341772151898734e-05, "epoch": 0.4601348671162237, "percentage": 9.21, "elapsed_time": "7:01:27", "remaining_time": "2 days, 21:16:30"}
+{"current_steps": 146, "total_steps": 1575, "loss": 0.3899, "lr": 7.39240506329114e-05, "epoch": 0.4633082110273701, "percentage": 9.27, "elapsed_time": "7:04:22", "remaining_time": "2 days, 21:13:38"}
+{"current_steps": 147, "total_steps": 1575, "loss": 0.3871, "lr": 7.443037974683545e-05, "epoch": 0.46648155493851645, "percentage": 9.33, "elapsed_time": "7:07:15", "remaining_time": "2 days, 21:10:35"}
+{"current_steps": 148, "total_steps": 1575, "loss": 0.3853, "lr": 7.49367088607595e-05, "epoch": 0.4696548988496628, "percentage": 9.4, "elapsed_time": "7:10:09", "remaining_time": "2 days, 21:07:35"}
+{"current_steps": 149, "total_steps": 1575, "loss": 0.3846, "lr": 7.544303797468355e-05, "epoch": 0.4728282427608092, "percentage": 9.46, "elapsed_time": "7:13:13", "remaining_time": "2 days, 21:06:10"}
+{"current_steps": 150, "total_steps": 1575, "loss": 0.3875, "lr": 7.59493670886076e-05, "epoch": 0.4760015866719556, "percentage": 9.52, "elapsed_time": "7:16:07", "remaining_time": "2 days, 21:03:11"}
+{"current_steps": 151, "total_steps": 1575, "loss": 0.3775, "lr": 7.645569620253165e-05, "epoch": 0.47917493058310195, "percentage": 9.59, "elapsed_time": "7:19:01", "remaining_time": "2 days, 21:00:16"}
+{"current_steps": 152, "total_steps": 1575, "loss": 0.3837, "lr": 7.69620253164557e-05, "epoch": 0.48234827449424833, "percentage": 9.65, "elapsed_time": "7:21:55", "remaining_time": "2 days, 20:57:14"}
+{"current_steps": 153, "total_steps": 1575, "loss": 0.3811, "lr": 7.746835443037976e-05, "epoch": 0.4855216184053947, "percentage": 9.71, "elapsed_time": "7:24:50", "remaining_time": "2 days, 20:54:21"}
+{"current_steps": 154, "total_steps": 1575, "loss": 0.385, "lr": 7.79746835443038e-05, "epoch": 0.4886949623165411, "percentage": 9.78, "elapsed_time": "7:27:44", "remaining_time": "2 days, 20:51:26"}
+{"current_steps": 155, "total_steps": 1575, "loss": 0.3817, "lr": 7.848101265822786e-05, "epoch": 0.4918683062276874, "percentage": 9.84, "elapsed_time": "7:30:39", "remaining_time": "2 days, 20:48:32"}
+{"current_steps": 156, "total_steps": 1575, "loss": 0.3837, "lr": 7.898734177215191e-05, "epoch": 0.4950416501388338, "percentage": 9.9, "elapsed_time": "7:33:33", "remaining_time": "2 days, 20:45:35"}
+{"current_steps": 157, "total_steps": 1575, "loss": 0.3833, "lr": 7.949367088607595e-05, "epoch": 0.49821499404998015, "percentage": 9.97, "elapsed_time": "7:36:27", "remaining_time": "2 days, 20:42:36"}
+{"current_steps": 158, "total_steps": 1575, "loss": 0.3773, "lr": 8e-05, "epoch": 0.5013883379611266, "percentage": 10.03, "elapsed_time": "7:39:20", "remaining_time": "2 days, 20:39:31"}
+{"current_steps": 159, "total_steps": 1575, "loss": 0.3872, "lr": 7.999990169177323e-05, "epoch": 0.5045616818722729, "percentage": 10.1, "elapsed_time": "7:42:13", "remaining_time": "2 days, 20:36:25"}
+{"current_steps": 160, "total_steps": 1575, "loss": 0.3792, "lr": 7.99996067675761e-05, "epoch": 0.5077350257834192, "percentage": 10.16, "elapsed_time": "7:45:08", "remaining_time": "2 days, 20:33:32"}
+{"current_steps": 161, "total_steps": 1575, "loss": 0.3845, "lr": 7.99991152288583e-05, "epoch": 0.5109083696945657, "percentage": 10.22, "elapsed_time": "7:48:02", "remaining_time": "2 days, 20:30:40"}
+{"current_steps": 162, "total_steps": 1575, "loss": 0.3798, "lr": 7.999842707803597e-05, "epoch": 0.514081713605712, "percentage": 10.29, "elapsed_time": "7:50:56", "remaining_time": "2 days, 20:27:43"}
+{"current_steps": 163, "total_steps": 1575, "loss": 0.3938, "lr": 7.999754231849163e-05, "epoch": 0.5172550575168584, "percentage": 10.35, "elapsed_time": "7:53:51", "remaining_time": "2 days, 20:24:47"}
+{"current_steps": 164, "total_steps": 1575, "loss": 0.3907, "lr": 7.999646095457422e-05, "epoch": 0.5204284014280047, "percentage": 10.41, "elapsed_time": "7:56:44", "remaining_time": "2 days, 20:21:47"}
+{"current_steps": 165, "total_steps": 1575, "loss": 0.3792, "lr": 7.999518299159912e-05, "epoch": 0.5236017453391512, "percentage": 10.48, "elapsed_time": "7:59:38", "remaining_time": "2 days, 20:18:43"}
+{"current_steps": 166, "total_steps": 1575, "loss": 0.38, "lr": 7.999370843584805e-05, "epoch": 0.5267750892502975, "percentage": 10.54, "elapsed_time": "8:02:31", "remaining_time": "2 days, 20:15:37"}
+{"current_steps": 167, "total_steps": 1575, "loss": 0.3809, "lr": 7.999203729456902e-05, "epoch": 0.5299484331614439, "percentage": 10.6, "elapsed_time": "8:05:25", "remaining_time": "2 days, 20:12:40"}
+{"current_steps": 168, "total_steps": 1575, "loss": 0.3838, "lr": 7.99901695759764e-05, "epoch": 0.5331217770725902, "percentage": 10.67, "elapsed_time": "8:08:19", "remaining_time": "2 days, 20:09:39"}
+{"current_steps": 169, "total_steps": 1575, "loss": 0.3788, "lr": 7.99881052892508e-05, "epoch": 0.5362951209837367, "percentage": 10.73, "elapsed_time": "8:11:12", "remaining_time": "2 days, 20:06:39"}
+{"current_steps": 170, "total_steps": 1575, "loss": 0.3766, "lr": 7.998584444453901e-05, "epoch": 0.539468464894883, "percentage": 10.79, "elapsed_time": "8:14:07", "remaining_time": "2 days, 20:03:44"}
+{"current_steps": 171, "total_steps": 1575, "loss": 0.3795, "lr": 7.998338705295406e-05, "epoch": 0.5426418088060293, "percentage": 10.86, "elapsed_time": "8:17:02", "remaining_time": "2 days, 20:00:54"}
+{"current_steps": 172, "total_steps": 1575, "loss": 0.3741, "lr": 7.9980733126575e-05, "epoch": 0.5458151527171757, "percentage": 10.92, "elapsed_time": "8:19:57", "remaining_time": "2 days, 19:58:08"}
+{"current_steps": 173, "total_steps": 1575, "loss": 0.3805, "lr": 7.997788267844699e-05, "epoch": 0.548988496628322, "percentage": 10.98, "elapsed_time": "8:22:52", "remaining_time": "2 days, 19:55:16"}
+{"current_steps": 174, "total_steps": 1575, "loss": 0.3811, "lr": 7.997483572258112e-05, "epoch": 0.5521618405394685, "percentage": 11.05, "elapsed_time": "8:25:46", "remaining_time": "2 days, 19:52:24"}
+{"current_steps": 175, "total_steps": 1575, "loss": 0.3712, "lr": 7.997159227395449e-05, "epoch": 0.5553351844506148, "percentage": 11.11, "elapsed_time": "8:28:40", "remaining_time": "2 days, 19:49:26"}
+{"current_steps": 176, "total_steps": 1575, "loss": 0.371, "lr": 7.996815234850994e-05, "epoch": 0.5585085283617612, "percentage": 11.17, "elapsed_time": "8:31:35", "remaining_time": "2 days, 19:46:37"}
+{"current_steps": 177, "total_steps": 1575, "loss": 0.3715, "lr": 7.996451596315613e-05, "epoch": 0.5616818722729076, "percentage": 11.24, "elapsed_time": "8:34:30", "remaining_time": "2 days, 19:43:41"}
+{"current_steps": 178, "total_steps": 1575, "loss": 0.3753, "lr": 7.99606831357674e-05, "epoch": 0.564855216184054, "percentage": 11.3, "elapsed_time": "8:37:23", "remaining_time": "2 days, 19:40:42"}
+{"current_steps": 179, "total_steps": 1575, "loss": 0.3728, "lr": 7.995665388518366e-05, "epoch": 0.5680285600952003, "percentage": 11.37, "elapsed_time": "8:40:18", "remaining_time": "2 days, 19:37:52"}
+{"current_steps": 180, "total_steps": 1575, "loss": 0.3764, "lr": 7.995242823121035e-05, "epoch": 0.5712019040063467, "percentage": 11.43, "elapsed_time": "8:43:12", "remaining_time": "2 days, 19:34:51"}
+{"current_steps": 181, "total_steps": 1575, "loss": 0.3737, "lr": 7.994800619461826e-05, "epoch": 0.5743752479174931, "percentage": 11.49, "elapsed_time": "8:46:05", "remaining_time": "2 days, 19:31:49"}
+{"current_steps": 182, "total_steps": 1575, "loss": 0.3735, "lr": 7.994338779714356e-05, "epoch": 0.5775485918286394, "percentage": 11.56, "elapsed_time": "8:48:59", "remaining_time": "2 days, 19:28:50"}
+{"current_steps": 183, "total_steps": 1575, "loss": 0.3666, "lr": 7.993857306148757e-05, "epoch": 0.5807219357397858, "percentage": 11.62, "elapsed_time": "8:51:53", "remaining_time": "2 days, 19:25:55"}
+{"current_steps": 184, "total_steps": 1575, "loss": 0.3763, "lr": 7.993356201131667e-05, "epoch": 0.5838952796509321, "percentage": 11.68, "elapsed_time": "8:54:48", "remaining_time": "2 days, 19:23:03"}
+{"current_steps": 185, "total_steps": 1575, "loss": 0.3789, "lr": 7.992835467126226e-05, "epoch": 0.5870686235620786, "percentage": 11.75, "elapsed_time": "8:57:43", "remaining_time": "2 days, 19:20:14"}
+{"current_steps": 186, "total_steps": 1575, "loss": 0.3718, "lr": 7.992295106692053e-05, "epoch": 0.5902419674732249, "percentage": 11.81, "elapsed_time": "9:00:37", "remaining_time": "2 days, 19:17:14"}
+{"current_steps": 187, "total_steps": 1575, "loss": 0.3738, "lr": 7.991735122485244e-05, "epoch": 0.5934153113843713, "percentage": 11.87, "elapsed_time": "9:03:30", "remaining_time": "2 days, 19:14:11"}
+{"current_steps": 188, "total_steps": 1575, "loss": 0.3749, "lr": 7.991155517258351e-05, "epoch": 0.5965886552955176, "percentage": 11.94, "elapsed_time": "9:06:24", "remaining_time": "2 days, 19:11:10"}
+{"current_steps": 189, "total_steps": 1575, "loss": 0.3738, "lr": 7.990556293860373e-05, "epoch": 0.5997619992066641, "percentage": 12.0, "elapsed_time": "9:09:17", "remaining_time": "2 days, 19:08:11"}
+{"current_steps": 190, "total_steps": 1575, "loss": 0.3767, "lr": 7.989937455236738e-05, "epoch": 0.6029353431178104, "percentage": 12.06, "elapsed_time": "9:12:12", "remaining_time": "2 days, 19:05:17"}
+{"current_steps": 191, "total_steps": 1575, "loss": 0.3775, "lr": 7.989299004429294e-05, "epoch": 0.6061086870289568, "percentage": 12.13, "elapsed_time": "9:15:06", "remaining_time": "2 days, 19:02:22"}
+{"current_steps": 192, "total_steps": 1575, "loss": 0.3801, "lr": 7.988640944576287e-05, "epoch": 0.6092820309401031, "percentage": 12.19, "elapsed_time": "9:18:00", "remaining_time": "2 days, 18:59:21"}
+{"current_steps": 193, "total_steps": 1575, "loss": 0.3754, "lr": 7.987963278912353e-05, "epoch": 0.6124553748512495, "percentage": 12.25, "elapsed_time": "9:20:54", "remaining_time": "2 days, 18:56:24"}
+{"current_steps": 194, "total_steps": 1575, "loss": 0.3744, "lr": 7.9872660107685e-05, "epoch": 0.6156287187623959, "percentage": 12.32, "elapsed_time": "9:23:48", "remaining_time": "2 days, 18:53:31"}
+{"current_steps": 195, "total_steps": 1575, "loss": 0.3722, "lr": 7.986549143572085e-05, "epoch": 0.6188020626735422, "percentage": 12.38, "elapsed_time": "9:26:43", "remaining_time": "2 days, 18:50:42"}
+{"current_steps": 196, "total_steps": 1575, "loss": 0.3721, "lr": 7.985812680846804e-05, "epoch": 0.6219754065846886, "percentage": 12.44, "elapsed_time": "9:29:38", "remaining_time": "2 days, 18:47:48"}
+{"current_steps": 197, "total_steps": 1575, "loss": 0.377, "lr": 7.985056626212678e-05, "epoch": 0.625148750495835, "percentage": 12.51, "elapsed_time": "9:32:32", "remaining_time": "2 days, 18:44:56"}
+{"current_steps": 198, "total_steps": 1575, "loss": 0.3733, "lr": 7.984280983386022e-05, "epoch": 0.6283220944069814, "percentage": 12.57, "elapsed_time": "9:35:27", "remaining_time": "2 days, 18:42:05"}
+{"current_steps": 199, "total_steps": 1575, "loss": 0.3724, "lr": 7.983485756179443e-05, "epoch": 0.6314954383181277, "percentage": 12.63, "elapsed_time": "9:38:23", "remaining_time": "2 days, 18:39:17"}
+{"current_steps": 200, "total_steps": 1575, "loss": 0.376, "lr": 7.98267094850181e-05, "epoch": 0.6346687822292741, "percentage": 12.7, "elapsed_time": "9:41:18", "remaining_time": "2 days, 18:36:31"}
+{"current_steps": 201, "total_steps": 1575, "loss": 0.375, "lr": 7.981836564358235e-05, "epoch": 0.6378421261404205, "percentage": 12.76, "elapsed_time": "9:44:13", "remaining_time": "2 days, 18:33:40"}
+{"current_steps": 202, "total_steps": 1575, "loss": 0.3715, "lr": 7.980982607850062e-05, "epoch": 0.6410154700515669, "percentage": 12.83, "elapsed_time": "9:47:07", "remaining_time": "2 days, 18:30:44"}
+{"current_steps": 203, "total_steps": 1575, "loss": 0.3747, "lr": 7.980109083174838e-05, "epoch": 0.6441888139627132, "percentage": 12.89, "elapsed_time": "9:50:01", "remaining_time": "2 days, 18:27:45"}
+{"current_steps": 204, "total_steps": 1575, "loss": 0.3688, "lr": 7.979215994626295e-05, "epoch": 0.6473621578738595, "percentage": 12.95, "elapsed_time": "9:52:54", "remaining_time": "2 days, 18:24:42"}
+{"current_steps": 205, "total_steps": 1575, "loss": 0.3678, "lr": 7.97830334659433e-05, "epoch": 0.650535501785006, "percentage": 13.02, "elapsed_time": "9:55:48", "remaining_time": "2 days, 18:21:42"}
+{"current_steps": 206, "total_steps": 1575, "loss": 0.3748, "lr": 7.977371143564986e-05, "epoch": 0.6537088456961523, "percentage": 13.08, "elapsed_time": "9:58:42", "remaining_time": "2 days, 18:18:46"}
+{"current_steps": 207, "total_steps": 1575, "loss": 0.3697, "lr": 7.976419390120422e-05, "epoch": 0.6568821896072987, "percentage": 13.14, "elapsed_time": "10:01:36", "remaining_time": "2 days, 18:15:53"}
+{"current_steps": 208, "total_steps": 1575, "loss": 0.3753, "lr": 7.9754480909389e-05, "epoch": 0.660055533518445, "percentage": 13.21, "elapsed_time": "10:04:31", "remaining_time": "2 days, 18:13:02"}
+{"current_steps": 209, "total_steps": 1575, "loss": 0.3738, "lr": 7.974457250794752e-05, "epoch": 0.6632288774295915, "percentage": 13.27, "elapsed_time": "10:07:25", "remaining_time": "2 days, 18:10:06"}
+{"current_steps": 210, "total_steps": 1575, "loss": 0.3715, "lr": 7.973446874558367e-05, "epoch": 0.6664022213407378, "percentage": 13.33, "elapsed_time": "10:10:21", "remaining_time": "2 days, 18:07:20"}
+{"current_steps": 211, "total_steps": 1575, "loss": 0.3747, "lr": 7.97241696719616e-05, "epoch": 0.6695755652518842, "percentage": 13.4, "elapsed_time": "10:13:15", "remaining_time": "2 days, 18:04:22"}
+{"current_steps": 212, "total_steps": 1575, "loss": 0.3706, "lr": 7.971367533770548e-05, "epoch": 0.6727489091630305, "percentage": 13.46, "elapsed_time": "10:16:11", "remaining_time": "2 days, 18:01:37"}
+{"current_steps": 213, "total_steps": 1575, "loss": 0.3741, "lr": 7.97029857943993e-05, "epoch": 0.6759222530741769, "percentage": 13.52, "elapsed_time": "10:19:06", "remaining_time": "2 days, 17:58:49"}
+{"current_steps": 214, "total_steps": 1575, "loss": 0.3719, "lr": 7.969210109458653e-05, "epoch": 0.6790955969853233, "percentage": 13.59, "elapsed_time": "10:22:02", "remaining_time": "2 days, 17:56:06"}
+{"current_steps": 215, "total_steps": 1575, "loss": 0.3702, "lr": 7.968102129176998e-05, "epoch": 0.6822689408964696, "percentage": 13.65, "elapsed_time": "10:24:58", "remaining_time": "2 days, 17:53:22"}
+{"current_steps": 216, "total_steps": 1575, "loss": 0.3749, "lr": 7.966974644041142e-05, "epoch": 0.685442284807616, "percentage": 13.71, "elapsed_time": "10:27:53", "remaining_time": "2 days, 17:50:29"}
+{"current_steps": 217, "total_steps": 1575, "loss": 0.3688, "lr": 7.965827659593138e-05, "epoch": 0.6886156287187624, "percentage": 13.78, "elapsed_time": "10:30:48", "remaining_time": "2 days, 17:47:40"}
+{"current_steps": 218, "total_steps": 1575, "loss": 0.3678, "lr": 7.964661181470887e-05, "epoch": 0.6917889726299088, "percentage": 13.84, "elapsed_time": "10:33:44", "remaining_time": "2 days, 17:44:50"}
+{"current_steps": 219, "total_steps": 1575, "loss": 0.3641, "lr": 7.96347521540811e-05, "epoch": 0.6949623165410551, "percentage": 13.9, "elapsed_time": "10:36:39", "remaining_time": "2 days, 17:42:04"}
+{"current_steps": 220, "total_steps": 1575, "loss": 0.3725, "lr": 7.962269767234315e-05, "epoch": 0.6981356604522015, "percentage": 13.97, "elapsed_time": "10:39:33", "remaining_time": "2 days, 17:39:07"}
+{"current_steps": 221, "total_steps": 1575, "loss": 0.3729, "lr": 7.96104484287478e-05, "epoch": 0.7013090043633479, "percentage": 14.03, "elapsed_time": "10:42:28", "remaining_time": "2 days, 17:36:15"}
+{"current_steps": 222, "total_steps": 1575, "loss": 0.3681, "lr": 7.959800448350507e-05, "epoch": 0.7044823482744943, "percentage": 14.1, "elapsed_time": "10:45:23", "remaining_time": "2 days, 17:33:23"}
+{"current_steps": 223, "total_steps": 1575, "loss": 0.3664, "lr": 7.95853658977821e-05, "epoch": 0.7076556921856406, "percentage": 14.16, "elapsed_time": "10:48:18", "remaining_time": "2 days, 17:30:35"}
+{"current_steps": 224, "total_steps": 1575, "loss": 0.3649, "lr": 7.957253273370275e-05, "epoch": 0.7108290360967869, "percentage": 14.22, "elapsed_time": "10:51:14", "remaining_time": "2 days, 17:27:45"}
+{"current_steps": 225, "total_steps": 1575, "loss": 0.3654, "lr": 7.955950505434725e-05, "epoch": 0.7140023800079334, "percentage": 14.29, "elapsed_time": "10:54:07", "remaining_time": "2 days, 17:24:45"}
+{"current_steps": 226, "total_steps": 1575, "loss": 0.3723, "lr": 7.954628292375207e-05, "epoch": 0.7171757239190797, "percentage": 14.35, "elapsed_time": "10:57:01", "remaining_time": "2 days, 17:21:49"}
+{"current_steps": 227, "total_steps": 1575, "loss": 0.3682, "lr": 7.953286640690936e-05, "epoch": 0.7203490678302261, "percentage": 14.41, "elapsed_time": "10:59:54", "remaining_time": "2 days, 17:18:47"}
+{"current_steps": 228, "total_steps": 1575, "loss": 0.3719, "lr": 7.951925556976686e-05, "epoch": 0.7235224117413724, "percentage": 14.48, "elapsed_time": "11:02:48", "remaining_time": "2 days, 17:15:50"}
+{"current_steps": 229, "total_steps": 1575, "loss": 0.3697, "lr": 7.950545047922741e-05, "epoch": 0.7266957556525189, "percentage": 14.54, "elapsed_time": "11:05:43", "remaining_time": "2 days, 17:12:56"}
+{"current_steps": 230, "total_steps": 1575, "loss": 0.3672, "lr": 7.949145120314871e-05, "epoch": 0.7298690995636652, "percentage": 14.6, "elapsed_time": "11:08:38", "remaining_time": "2 days, 17:10:04"}
+{"current_steps": 231, "total_steps": 1575, "loss": 0.3642, "lr": 7.947725781034299e-05, "epoch": 0.7330424434748116, "percentage": 14.67, "elapsed_time": "11:11:31", "remaining_time": "2 days, 17:07:05"}
+{"current_steps": 232, "total_steps": 1575, "loss": 0.3663, "lr": 7.946287037057657e-05, "epoch": 0.7362157873859579, "percentage": 14.73, "elapsed_time": "11:14:25", "remaining_time": "2 days, 17:04:04"}
+{"current_steps": 233, "total_steps": 1575, "loss": 0.3655, "lr": 7.944828895456968e-05, "epoch": 0.7393891312971044, "percentage": 14.79, "elapsed_time": "11:17:18", "remaining_time": "2 days, 17:01:04"}
+{"current_steps": 234, "total_steps": 1575, "loss": 0.3743, "lr": 7.943351363399593e-05, "epoch": 0.7425624752082507, "percentage": 14.86, "elapsed_time": "11:20:11", "remaining_time": "2 days, 16:58:03"}
+{"current_steps": 235, "total_steps": 1575, "loss": 0.3683, "lr": 7.941854448148212e-05, "epoch": 0.745735819119397, "percentage": 14.92, "elapsed_time": "11:23:06", "remaining_time": "2 days, 16:55:07"}
+{"current_steps": 236, "total_steps": 1575, "loss": 0.3653, "lr": 7.94033815706078e-05, "epoch": 0.7489091630305434, "percentage": 14.98, "elapsed_time": "11:26:00", "remaining_time": "2 days, 16:52:13"}
+{"current_steps": 237, "total_steps": 1575, "loss": 0.3648, "lr": 7.938802497590491e-05, "epoch": 0.7520825069416898, "percentage": 15.05, "elapsed_time": "11:28:55", "remaining_time": "2 days, 16:49:19"}
+{"current_steps": 238, "total_steps": 1575, "loss": 0.3676, "lr": 7.937247477285743e-05, "epoch": 0.7552558508528362, "percentage": 15.11, "elapsed_time": "11:31:49", "remaining_time": "2 days, 16:46:23"}
+{"current_steps": 239, "total_steps": 1575, "loss": 0.3704, "lr": 7.935673103790101e-05, "epoch": 0.7584291947639825, "percentage": 15.17, "elapsed_time": "11:34:43", "remaining_time": "2 days, 16:43:26"}
+{"current_steps": 240, "total_steps": 1575, "loss": 0.3685, "lr": 7.934079384842255e-05, "epoch": 0.761602538675129, "percentage": 15.24, "elapsed_time": "11:37:38", "remaining_time": "2 days, 16:40:36"}
+{"current_steps": 241, "total_steps": 1575, "loss": 0.3687, "lr": 7.932466328275994e-05, "epoch": 0.7647758825862753, "percentage": 15.3, "elapsed_time": "11:40:33", "remaining_time": "2 days, 16:37:46"}
+{"current_steps": 242, "total_steps": 1575, "loss": 0.3702, "lr": 7.93083394202015e-05, "epoch": 0.7679492264974217, "percentage": 15.37, "elapsed_time": "11:43:28", "remaining_time": "2 days, 16:34:53"}
+{"current_steps": 243, "total_steps": 1575, "loss": 0.3656, "lr": 7.929182234098576e-05, "epoch": 0.771122570408568, "percentage": 15.43, "elapsed_time": "11:46:22", "remaining_time": "2 days, 16:31:57"}
+{"current_steps": 244, "total_steps": 1575, "loss": 0.3673, "lr": 7.927511212630096e-05, "epoch": 0.7742959143197145, "percentage": 15.49, "elapsed_time": "11:49:16", "remaining_time": "2 days, 16:29:01"}
+{"current_steps": 245, "total_steps": 1575, "loss": 0.3702, "lr": 7.925820885828468e-05, "epoch": 0.7774692582308608, "percentage": 15.56, "elapsed_time": "11:52:10", "remaining_time": "2 days, 16:26:05"}
+{"current_steps": 246, "total_steps": 1575, "loss": 0.3719, "lr": 7.924111262002338e-05, "epoch": 0.7806426021420071, "percentage": 15.62, "elapsed_time": "11:55:05", "remaining_time": "2 days, 16:23:13"}
+{"current_steps": 247, "total_steps": 1575, "loss": 0.3702, "lr": 7.922382349555218e-05, "epoch": 0.7838159460531535, "percentage": 15.68, "elapsed_time": "11:57:59", "remaining_time": "2 days, 16:20:16"}
+{"current_steps": 248, "total_steps": 1575, "loss": 0.3653, "lr": 7.92063415698542e-05, "epoch": 0.7869892899642998, "percentage": 15.75, "elapsed_time": "12:00:52", "remaining_time": "2 days, 16:17:15"}
+{"current_steps": 249, "total_steps": 1575, "loss": 0.3751, "lr": 7.918866692886031e-05, "epoch": 0.7901626338754463, "percentage": 15.81, "elapsed_time": "12:03:45", "remaining_time": "2 days, 16:14:14"}
+{"current_steps": 250, "total_steps": 1575, "loss": 0.3713, "lr": 7.917079965944862e-05, "epoch": 0.7933359777865926, "percentage": 15.87, "elapsed_time": "12:06:39", "remaining_time": "2 days, 16:11:15"}
+{"current_steps": 251, "total_steps": 1575, "loss": 0.37, "lr": 7.915273984944412e-05, "epoch": 0.796509321697739, "percentage": 15.94, "elapsed_time": "12:09:32", "remaining_time": "2 days, 16:08:17"}
+{"current_steps": 252, "total_steps": 1575, "loss": 0.3649, "lr": 7.913448758761821e-05, "epoch": 0.7996826656088853, "percentage": 16.0, "elapsed_time": "12:12:26", "remaining_time": "2 days, 16:05:19"}
+{"current_steps": 253, "total_steps": 1575, "loss": 0.3677, "lr": 7.911604296368826e-05, "epoch": 0.8028560095200318, "percentage": 16.06, "elapsed_time": "12:15:20", "remaining_time": "2 days, 16:02:21"}
+{"current_steps": 254, "total_steps": 1575, "loss": 0.3676, "lr": 7.909740606831719e-05, "epoch": 0.8060293534311781, "percentage": 16.13, "elapsed_time": "12:18:13", "remaining_time": "2 days, 15:59:21"}
+{"current_steps": 255, "total_steps": 1575, "loss": 0.367, "lr": 7.907857699311299e-05, "epoch": 0.8092026973423245, "percentage": 16.19, "elapsed_time": "12:21:06", "remaining_time": "2 days, 15:56:22"}
+{"current_steps": 256, "total_steps": 1575, "loss": 0.3721, "lr": 7.905955583062833e-05, "epoch": 0.8123760412534708, "percentage": 16.25, "elapsed_time": "12:24:00", "remaining_time": "2 days, 15:53:21"}
+{"current_steps": 257, "total_steps": 1575, "loss": 0.3618, "lr": 7.904034267436004e-05, "epoch": 0.8155493851646172, "percentage": 16.32, "elapsed_time": "12:26:53", "remaining_time": "2 days, 15:50:21"}
+{"current_steps": 258, "total_steps": 1575, "loss": 0.3709, "lr": 7.902093761874867e-05, "epoch": 0.8187227290757636, "percentage": 16.38, "elapsed_time": "12:29:46", "remaining_time": "2 days, 15:47:22"}
+{"current_steps": 259, "total_steps": 1575, "loss": 0.3705, "lr": 7.900134075917807e-05, "epoch": 0.8218960729869099, "percentage": 16.44, "elapsed_time": "12:32:40", "remaining_time": "2 days, 15:44:23"}
+{"current_steps": 260, "total_steps": 1575, "loss": 0.3613, "lr": 7.898155219197488e-05, "epoch": 0.8250694168980564, "percentage": 16.51, "elapsed_time": "12:35:33", "remaining_time": "2 days, 15:41:25"}
+{"current_steps": 261, "total_steps": 1575, "loss": 0.3639, "lr": 7.896157201440801e-05, "epoch": 0.8282427608092027, "percentage": 16.57, "elapsed_time": "12:38:27", "remaining_time": "2 days, 15:38:27"}
+{"current_steps": 262, "total_steps": 1575, "loss": 0.3648, "lr": 7.894140032468828e-05, "epoch": 0.8314161047203491, "percentage": 16.63, "elapsed_time": "12:41:21", "remaining_time": "2 days, 15:35:31"}
+{"current_steps": 263, "total_steps": 1575, "loss": 0.3652, "lr": 7.892103722196782e-05, "epoch": 0.8345894486314954, "percentage": 16.7, "elapsed_time": "12:44:16", "remaining_time": "2 days, 15:32:40"}
+{"current_steps": 264, "total_steps": 1575, "loss": 0.3615, "lr": 7.890048280633967e-05, "epoch": 0.8377627925426419, "percentage": 16.76, "elapsed_time": "12:47:10", "remaining_time": "2 days, 15:29:44"}
+{"current_steps": 265, "total_steps": 1575, "loss": 0.3624, "lr": 7.887973717883725e-05, "epoch": 0.8409361364537882, "percentage": 16.83, "elapsed_time": "12:50:04", "remaining_time": "2 days, 15:26:45"}
+{"current_steps": 266, "total_steps": 1575, "loss": 0.3661, "lr": 7.885880044143382e-05, "epoch": 0.8441094803649345, "percentage": 16.89, "elapsed_time": "12:52:57", "remaining_time": "2 days, 15:23:46"}
+{"current_steps": 267, "total_steps": 1575, "loss": 0.3651, "lr": 7.883767269704209e-05, "epoch": 0.8472828242760809, "percentage": 16.95, "elapsed_time": "12:55:51", "remaining_time": "2 days, 15:20:47"}
+{"current_steps": 268, "total_steps": 1575, "loss": 0.3677, "lr": 7.88163540495136e-05, "epoch": 0.8504561681872272, "percentage": 17.02, "elapsed_time": "12:58:45", "remaining_time": "2 days, 15:17:53"}
+{"current_steps": 269, "total_steps": 1575, "loss": 0.3679, "lr": 7.879484460363825e-05, "epoch": 0.8536295120983737, "percentage": 17.08, "elapsed_time": "13:01:38", "remaining_time": "2 days, 15:14:53"}
+{"current_steps": 270, "total_steps": 1575, "loss": 0.3627, "lr": 7.877314446514385e-05, "epoch": 0.85680285600952, "percentage": 17.14, "elapsed_time": "13:04:31", "remaining_time": "2 days, 15:11:54"}
+{"current_steps": 271, "total_steps": 1575, "loss": 0.3668, "lr": 7.87512537406955e-05, "epoch": 0.8599761999206664, "percentage": 17.21, "elapsed_time": "13:07:25", "remaining_time": "2 days, 15:08:54"}
+{"current_steps": 272, "total_steps": 1575, "loss": 0.3688, "lr": 7.87291725378951e-05, "epoch": 0.8631495438318127, "percentage": 17.27, "elapsed_time": "13:10:18", "remaining_time": "2 days, 15:05:54"}
+{"current_steps": 273, "total_steps": 1575, "loss": 0.3593, "lr": 7.870690096528084e-05, "epoch": 0.8663228877429592, "percentage": 17.33, "elapsed_time": "13:13:11", "remaining_time": "2 days, 15:02:54"}
+{"current_steps": 274, "total_steps": 1575, "loss": 0.3628, "lr": 7.868443913232669e-05, "epoch": 0.8694962316541055, "percentage": 17.4, "elapsed_time": "13:16:05", "remaining_time": "2 days, 14:59:58"}
+{"current_steps": 275, "total_steps": 1575, "loss": 0.3614, "lr": 7.866178714944178e-05, "epoch": 0.8726695755652519, "percentage": 17.46, "elapsed_time": "13:18:58", "remaining_time": "2 days, 14:56:59"}
+{"current_steps": 276, "total_steps": 1575, "loss": 0.3612, "lr": 7.863894512796992e-05, "epoch": 0.8758429194763983, "percentage": 17.52, "elapsed_time": "13:21:52", "remaining_time": "2 days, 14:54:00"}
+{"current_steps": 277, "total_steps": 1575, "loss": 0.3643, "lr": 7.861591318018904e-05, "epoch": 0.8790162633875446, "percentage": 17.59, "elapsed_time": "13:24:45", "remaining_time": "2 days, 14:51:03"}
+{"current_steps": 278, "total_steps": 1575, "loss": 0.362, "lr": 7.859269141931065e-05, "epoch": 0.882189607298691, "percentage": 17.65, "elapsed_time": "13:27:39", "remaining_time": "2 days, 14:48:04"}
+{"current_steps": 279, "total_steps": 1575, "loss": 0.3604, "lr": 7.856927995947925e-05, "epoch": 0.8853629512098373, "percentage": 17.71, "elapsed_time": "13:30:32", "remaining_time": "2 days, 14:45:05"}
+{"current_steps": 280, "total_steps": 1575, "loss": 0.3682, "lr": 7.854567891577179e-05, "epoch": 0.8885362951209838, "percentage": 17.78, "elapsed_time": "13:33:25", "remaining_time": "2 days, 14:42:05"}
+{"current_steps": 281, "total_steps": 1575, "loss": 0.3609, "lr": 7.852188840419711e-05, "epoch": 0.8917096390321301, "percentage": 17.84, "elapsed_time": "13:36:19", "remaining_time": "2 days, 14:39:08"}
+{"current_steps": 282, "total_steps": 1575, "loss": 0.3621, "lr": 7.849790854169536e-05, "epoch": 0.8948829829432765, "percentage": 17.9, "elapsed_time": "13:39:12", "remaining_time": "2 days, 14:36:09"}
+{"current_steps": 283, "total_steps": 1575, "loss": 0.3588, "lr": 7.847373944613745e-05, "epoch": 0.8980563268544228, "percentage": 17.97, "elapsed_time": "13:42:05", "remaining_time": "2 days, 14:33:11"}
+{"current_steps": 284, "total_steps": 1575, "loss": 0.3622, "lr": 7.844938123632439e-05, "epoch": 0.9012296707655693, "percentage": 18.03, "elapsed_time": "13:44:59", "remaining_time": "2 days, 14:30:14"}
+{"current_steps": 285, "total_steps": 1575, "loss": 0.3631, "lr": 7.842483403198683e-05, "epoch": 0.9044030146767156, "percentage": 18.1, "elapsed_time": "13:47:52", "remaining_time": "2 days, 14:27:15"}
+{"current_steps": 286, "total_steps": 1575, "loss": 0.3688, "lr": 7.840009795378436e-05, "epoch": 0.907576358587862, "percentage": 18.16, "elapsed_time": "13:50:47", "remaining_time": "2 days, 14:24:21"}
+{"current_steps": 287, "total_steps": 1575, "loss": 0.3671, "lr": 7.837517312330498e-05, "epoch": 0.9107497024990083, "percentage": 18.22, "elapsed_time": "13:53:42", "remaining_time": "2 days, 14:21:29"}
+{"current_steps": 288, "total_steps": 1575, "loss": 0.3681, "lr": 7.83500596630645e-05, "epoch": 0.9139230464101546, "percentage": 18.29, "elapsed_time": "13:56:35", "remaining_time": "2 days, 14:18:31"}
+{"current_steps": 289, "total_steps": 1575, "loss": 0.3665, "lr": 7.832475769650588e-05, "epoch": 0.9170963903213011, "percentage": 18.35, "elapsed_time": "13:59:29", "remaining_time": "2 days, 14:15:35"}
+{"current_steps": 290, "total_steps": 1575, "loss": 0.3628, "lr": 7.829926734799872e-05, "epoch": 0.9202697342324474, "percentage": 18.41, "elapsed_time": "14:02:23", "remaining_time": "2 days, 14:12:41"}
+{"current_steps": 291, "total_steps": 1575, "loss": 0.3665, "lr": 7.827358874283855e-05, "epoch": 0.9234430781435938, "percentage": 18.48, "elapsed_time": "14:05:17", "remaining_time": "2 days, 14:09:45"}
+{"current_steps": 292, "total_steps": 1575, "loss": 0.3635, "lr": 7.824772200724629e-05, "epoch": 0.9266164220547402, "percentage": 18.54, "elapsed_time": "14:08:11", "remaining_time": "2 days, 14:06:50"}
+{"current_steps": 293, "total_steps": 1575, "loss": 0.36, "lr": 7.822166726836758e-05, "epoch": 0.9297897659658866, "percentage": 18.6, "elapsed_time": "14:11:05", "remaining_time": "2 days, 14:03:54"}
+{"current_steps": 294, "total_steps": 1575, "loss": 0.3607, "lr": 7.819542465427217e-05, "epoch": 0.9329631098770329, "percentage": 18.67, "elapsed_time": "14:13:59", "remaining_time": "2 days, 14:00:59"}
+{"current_steps": 295, "total_steps": 1575, "loss": 0.3639, "lr": 7.816899429395332e-05, "epoch": 0.9361364537881793, "percentage": 18.73, "elapsed_time": "14:16:53", "remaining_time": "2 days, 13:58:02"}
+{"current_steps": 296, "total_steps": 1575, "loss": 0.3629, "lr": 7.814237631732711e-05, "epoch": 0.9393097976993257, "percentage": 18.79, "elapsed_time": "14:19:46", "remaining_time": "2 days, 13:55:04"}
+{"current_steps": 297, "total_steps": 1575, "loss": 0.3649, "lr": 7.811557085523187e-05, "epoch": 0.9424831416104721, "percentage": 18.86, "elapsed_time": "14:22:40", "remaining_time": "2 days, 13:52:06"}
+{"current_steps": 298, "total_steps": 1575, "loss": 0.3594, "lr": 7.808857803942741e-05, "epoch": 0.9456564855216184, "percentage": 18.92, "elapsed_time": "14:25:33", "remaining_time": "2 days, 13:49:08"}
+{"current_steps": 299, "total_steps": 1575, "loss": 0.355, "lr": 7.80613980025946e-05, "epoch": 0.9488298294327647, "percentage": 18.98, "elapsed_time": "14:28:27", "remaining_time": "2 days, 13:46:10"}
+{"current_steps": 300, "total_steps": 1575, "loss": 0.3566, "lr": 7.803403087833444e-05, "epoch": 0.9520031733439112, "percentage": 19.05, "elapsed_time": "14:31:20", "remaining_time": "2 days, 13:43:12"}
+{"current_steps": 301, "total_steps": 1575, "loss": 0.3586, "lr": 7.800647680116764e-05, "epoch": 0.9551765172550575, "percentage": 19.11, "elapsed_time": "14:34:13", "remaining_time": "2 days, 13:40:14"}
+{"current_steps": 302, "total_steps": 1575, "loss": 0.3551, "lr": 7.797873590653381e-05, "epoch": 0.9583498611662039, "percentage": 19.17, "elapsed_time": "14:37:07", "remaining_time": "2 days, 13:37:15"}
+{"current_steps": 303, "total_steps": 1575, "loss": 0.3613, "lr": 7.795080833079084e-05, "epoch": 0.9615232050773502, "percentage": 19.24, "elapsed_time": "14:40:00", "remaining_time": "2 days, 13:34:18"}
+{"current_steps": 304, "total_steps": 1575, "loss": 0.3607, "lr": 7.792269421121429e-05, "epoch": 0.9646965489884967, "percentage": 19.3, "elapsed_time": "14:42:54", "remaining_time": "2 days, 13:31:20"}
+{"current_steps": 305, "total_steps": 1575, "loss": 0.3606, "lr": 7.78943936859966e-05, "epoch": 0.967869892899643, "percentage": 19.37, "elapsed_time": "14:45:47", "remaining_time": "2 days, 13:28:22"}
+{"current_steps": 306, "total_steps": 1575, "loss": 0.3633, "lr": 7.78659068942465e-05, "epoch": 0.9710432368107894, "percentage": 19.43, "elapsed_time": "14:48:41", "remaining_time": "2 days, 13:25:26"}
+{"current_steps": 307, "total_steps": 1575, "loss": 0.3682, "lr": 7.783723397598829e-05, "epoch": 0.9742165807219357, "percentage": 19.49, "elapsed_time": "14:51:34", "remaining_time": "2 days, 13:22:28"}
+{"current_steps": 308, "total_steps": 1575, "loss": 0.3594, "lr": 7.780837507216114e-05, "epoch": 0.9773899246330822, "percentage": 19.56, "elapsed_time": "14:54:28", "remaining_time": "2 days, 13:19:30"}
+{"current_steps": 309, "total_steps": 1575, "loss": 0.3628, "lr": 7.777933032461845e-05, "epoch": 0.9805632685442285, "percentage": 19.62, "elapsed_time": "14:57:23", "remaining_time": "2 days, 13:16:41"}
+{"current_steps": 310, "total_steps": 1575, "loss": 0.3604, "lr": 7.775009987612711e-05, "epoch": 0.9837366124553748, "percentage": 19.68, "elapsed_time": "15:00:17", "remaining_time": "2 days, 13:13:44"}
+{"current_steps": 311, "total_steps": 1575, "loss": 0.3592, "lr": 7.772068387036677e-05, "epoch": 0.9869099563665212, "percentage": 19.75, "elapsed_time": "15:03:10", "remaining_time": "2 days, 13:10:48"}
+{"current_steps": 312, "total_steps": 1575, "loss": 0.3662, "lr": 7.769108245192922e-05, "epoch": 0.9900833002776676, "percentage": 19.81, "elapsed_time": "15:06:04", "remaining_time": "2 days, 13:07:52"}
+{"current_steps": 313, "total_steps": 1575, "loss": 0.3624, "lr": 7.766129576631759e-05, "epoch": 0.993256644188814, "percentage": 19.87, "elapsed_time": "15:08:58", "remaining_time": "2 days, 13:04:55"}
+{"current_steps": 314, "total_steps": 1575, "loss": 0.3559, "lr": 7.763132395994572e-05, "epoch": 0.9964299880999603, "percentage": 19.94, "elapsed_time": "15:11:51", "remaining_time": "2 days, 13:01:58"}
+{"current_steps": 315, "total_steps": 1575, "loss": 0.3612, "lr": 7.760116718013735e-05, "epoch": 0.9996033320111067, "percentage": 20.0, "elapsed_time": "15:14:45", "remaining_time": "2 days, 12:59:02"}
+{"current_steps": 316, "total_steps": 1575, "loss": 0.3469, "lr": 7.757082557512545e-05, "epoch": 1.0027766759222532, "percentage": 20.06, "elapsed_time": "15:27:46", "remaining_time": "2 days, 13:36:26"}
+{"current_steps": 317, "total_steps": 1575, "loss": 0.3462, "lr": 7.75402992940515e-05, "epoch": 1.0059500198333995, "percentage": 20.13, "elapsed_time": "15:30:40", "remaining_time": "2 days, 13:33:19"}
+{"current_steps": 318, "total_steps": 1575, "loss": 0.35, "lr": 7.750958848696473e-05, "epoch": 1.0091233637445458, "percentage": 20.19, "elapsed_time": "15:33:33", "remaining_time": "2 days, 13:30:11"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8540c1c4b808a05ae16ad89f6f80ae87fc32f37258e44e07414882e632378a5b
+size 7288