Training in progress, step 200

.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 +1,28 @@
+{
+  "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": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 48,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba04bb0b54bcb29ee24377d077c463c5f0a20893d1df58f12114cf6e058ccf9
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ad8d4bbf8462b37e4a5bbbceebc4d4667b188dcab65c2a3cd8de8fb41d6f01
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18042fce8d0240324c73fda8c5ffde5975f7cfc61c5e1d90ae58aebeabe1bcf
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:617d0638f738200a2aac4d4de8e390a487b20e25f3cafe9820fe2c4f9c332354
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5feb1b33eb2f9b1f9d17313f4bd683975f14f95c17ad02527e2dc9526a5ecb
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fbb27a6280dd87620766f29afdb069ae4b5a2d5e55fd86f7b1c1a6cd70b1349
+size 4734533160

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.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": "<|im_end|>",
+    "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 +1,209 @@
+{
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,202 @@
+{"current_steps": 1, "total_steps": 246, "loss": 0.7793, "lr": 0.0, "epoch": 0.012060301507537688, "percentage": 0.41, "elapsed_time": "0:03:01", "remaining_time": "12:20:51"}
+{"current_steps": 2, "total_steps": 246, "loss": 0.7167, "lr": 4.0000000000000003e-07, "epoch": 0.024120603015075376, "percentage": 0.81, "elapsed_time": "0:05:50", "remaining_time": "11:51:42"}
+{"current_steps": 3, "total_steps": 246, "loss": 0.7434, "lr": 8.000000000000001e-07, "epoch": 0.036180904522613064, "percentage": 1.22, "elapsed_time": "0:08:31", "remaining_time": "11:30:21"}
+{"current_steps": 4, "total_steps": 246, "loss": 0.6949, "lr": 1.2000000000000002e-06, "epoch": 0.04824120603015075, "percentage": 1.63, "elapsed_time": "0:11:12", "remaining_time": "11:18:33"}
+{"current_steps": 5, "total_steps": 246, "loss": 0.7081, "lr": 1.6000000000000001e-06, "epoch": 0.06030150753768844, "percentage": 2.03, "elapsed_time": "0:13:35", "remaining_time": "10:54:48"}
+{"current_steps": 6, "total_steps": 246, "loss": 0.7598, "lr": 2.0000000000000003e-06, "epoch": 0.07236180904522613, "percentage": 2.44, "elapsed_time": "0:16:20", "remaining_time": "10:53:29"}
+{"current_steps": 7, "total_steps": 246, "loss": 0.6938, "lr": 2.4000000000000003e-06, "epoch": 0.08442211055276382, "percentage": 2.85, "elapsed_time": "0:18:39", "remaining_time": "10:36:50"}
+{"current_steps": 8, "total_steps": 246, "loss": 0.6629, "lr": 2.8000000000000003e-06, "epoch": 0.0964824120603015, "percentage": 3.25, "elapsed_time": "0:21:23", "remaining_time": "10:36:28"}
+{"current_steps": 9, "total_steps": 246, "loss": 0.6612, "lr": 3.2000000000000003e-06, "epoch": 0.10854271356783919, "percentage": 3.66, "elapsed_time": "0:24:05", "remaining_time": "10:34:19"}
+{"current_steps": 10, "total_steps": 246, "loss": 0.6916, "lr": 3.6000000000000003e-06, "epoch": 0.12060301507537688, "percentage": 4.07, "elapsed_time": "0:26:32", "remaining_time": "10:26:21"}
+{"current_steps": 11, "total_steps": 246, "loss": 0.6725, "lr": 4.000000000000001e-06, "epoch": 0.13266331658291458, "percentage": 4.47, "elapsed_time": "0:29:14", "remaining_time": "10:24:35"}
+{"current_steps": 12, "total_steps": 246, "loss": 0.6136, "lr": 4.4e-06, "epoch": 0.14472361809045226, "percentage": 4.88, "elapsed_time": "0:31:43", "remaining_time": "10:18:44"}
+{"current_steps": 13, "total_steps": 246, "loss": 0.5935, "lr": 4.800000000000001e-06, "epoch": 0.15678391959798996, "percentage": 5.28, "elapsed_time": "0:34:23", "remaining_time": "10:16:29"}
+{"current_steps": 14, "total_steps": 246, "loss": 0.704, "lr": 5.2e-06, "epoch": 0.16884422110552763, "percentage": 5.69, "elapsed_time": "0:36:59", "remaining_time": "10:13:06"}
+{"current_steps": 15, "total_steps": 246, "loss": 0.6146, "lr": 5.600000000000001e-06, "epoch": 0.18090452261306533, "percentage": 6.1, "elapsed_time": "0:39:29", "remaining_time": "10:08:05"}
+{"current_steps": 16, "total_steps": 246, "loss": 0.6434, "lr": 6e-06, "epoch": 0.192964824120603, "percentage": 6.5, "elapsed_time": "0:42:20", "remaining_time": "10:08:38"}
+{"current_steps": 17, "total_steps": 246, "loss": 0.5955, "lr": 6.4000000000000006e-06, "epoch": 0.2050251256281407, "percentage": 6.91, "elapsed_time": "0:44:47", "remaining_time": "10:03:26"}
+{"current_steps": 18, "total_steps": 246, "loss": 0.6119, "lr": 6.800000000000001e-06, "epoch": 0.21708542713567838, "percentage": 7.32, "elapsed_time": "0:47:39", "remaining_time": "10:03:41"}
+{"current_steps": 19, "total_steps": 246, "loss": 0.5668, "lr": 7.2000000000000005e-06, "epoch": 0.22914572864321608, "percentage": 7.72, "elapsed_time": "0:50:18", "remaining_time": "10:01:07"}
+{"current_steps": 20, "total_steps": 246, "loss": 0.6136, "lr": 7.600000000000001e-06, "epoch": 0.24120603015075376, "percentage": 8.13, "elapsed_time": "0:52:52", "remaining_time": "9:57:24"}
+{"current_steps": 21, "total_steps": 246, "loss": 0.5655, "lr": 8.000000000000001e-06, "epoch": 0.25326633165829143, "percentage": 8.54, "elapsed_time": "0:55:29", "remaining_time": "9:54:37"}
+{"current_steps": 22, "total_steps": 246, "loss": 0.5869, "lr": 8.400000000000001e-06, "epoch": 0.26532663316582916, "percentage": 8.94, "elapsed_time": "0:58:00", "remaining_time": "9:50:37"}
+{"current_steps": 23, "total_steps": 246, "loss": 0.52, "lr": 8.8e-06, "epoch": 0.27738693467336684, "percentage": 9.35, "elapsed_time": "1:00:48", "remaining_time": "9:49:29"}
+{"current_steps": 24, "total_steps": 246, "loss": 0.5961, "lr": 9.200000000000002e-06, "epoch": 0.2894472361809045, "percentage": 9.76, "elapsed_time": "1:03:21", "remaining_time": "9:46:06"}
+{"current_steps": 25, "total_steps": 246, "loss": 0.5569, "lr": 9.600000000000001e-06, "epoch": 0.3015075376884422, "percentage": 10.16, "elapsed_time": "1:06:01", "remaining_time": "9:43:38"}
+{"current_steps": 26, "total_steps": 246, "loss": 0.6162, "lr": 1e-05, "epoch": 0.3135678391959799, "percentage": 10.57, "elapsed_time": "1:08:41", "remaining_time": "9:41:17"}
+{"current_steps": 27, "total_steps": 246, "loss": 0.6361, "lr": 9.999494817970498e-06, "epoch": 0.3256281407035176, "percentage": 10.98, "elapsed_time": "1:11:10", "remaining_time": "9:37:21"}
+{"current_steps": 28, "total_steps": 246, "loss": 0.5519, "lr": 9.997979373965542e-06, "epoch": 0.33768844221105526, "percentage": 11.38, "elapsed_time": "1:13:55", "remaining_time": "9:35:37"}
+{"current_steps": 29, "total_steps": 246, "loss": 0.5622, "lr": 9.995453974215164e-06, "epoch": 0.349748743718593, "percentage": 11.79, "elapsed_time": "1:16:30", "remaining_time": "9:32:27"}
+{"current_steps": 30, "total_steps": 246, "loss": 0.5429, "lr": 9.991919129033994e-06, "epoch": 0.36180904522613067, "percentage": 12.2, "elapsed_time": "1:19:07", "remaining_time": "9:29:39"}
+{"current_steps": 31, "total_steps": 246, "loss": 0.5649, "lr": 9.987375552718133e-06, "epoch": 0.37386934673366834, "percentage": 12.6, "elapsed_time": "1:21:22", "remaining_time": "9:24:20"}
+{"current_steps": 32, "total_steps": 246, "loss": 0.5269, "lr": 9.981824163400827e-06, "epoch": 0.385929648241206, "percentage": 13.01, "elapsed_time": "1:23:36", "remaining_time": "9:19:10"}
+{"current_steps": 33, "total_steps": 246, "loss": 0.5233, "lr": 9.975266082866923e-06, "epoch": 0.39798994974874374, "percentage": 13.41, "elapsed_time": "1:25:55", "remaining_time": "9:14:35"}
+{"current_steps": 34, "total_steps": 246, "loss": 0.4995, "lr": 9.967702636326195e-06, "epoch": 0.4100502512562814, "percentage": 13.82, "elapsed_time": "1:28:09", "remaining_time": "9:09:39"}
+{"current_steps": 35, "total_steps": 246, "loss": 0.5158, "lr": 9.959135352145552e-06, "epoch": 0.4221105527638191, "percentage": 14.23, "elapsed_time": "1:30:24", "remaining_time": "9:05:02"}
+{"current_steps": 36, "total_steps": 246, "loss": 0.5075, "lr": 9.9495659615402e-06, "epoch": 0.43417085427135677, "percentage": 14.63, "elapsed_time": "1:32:37", "remaining_time": "9:00:17"}
+{"current_steps": 37, "total_steps": 246, "loss": 0.5744, "lr": 9.938996398223802e-06, "epoch": 0.4462311557788945, "percentage": 15.04, "elapsed_time": "1:34:58", "remaining_time": "8:56:27"}
+{"current_steps": 38, "total_steps": 246, "loss": 0.5649, "lr": 9.927428798017738e-06, "epoch": 0.45829145728643217, "percentage": 15.45, "elapsed_time": "1:37:12", "remaining_time": "8:52:06"}
+{"current_steps": 39, "total_steps": 246, "loss": 0.5042, "lr": 9.91486549841951e-06, "epoch": 0.47035175879396984, "percentage": 15.85, "elapsed_time": "1:39:34", "remaining_time": "8:48:30"}
+{"current_steps": 40, "total_steps": 246, "loss": 0.4814, "lr": 9.901309038130392e-06, "epoch": 0.4824120603015075, "percentage": 16.26, "elapsed_time": "1:41:54", "remaining_time": "8:44:48"}
+{"current_steps": 41, "total_steps": 246, "loss": 0.5319, "lr": 9.886762156542428e-06, "epoch": 0.49447236180904525, "percentage": 16.67, "elapsed_time": "1:44:19", "remaining_time": "8:41:36"}
+{"current_steps": 42, "total_steps": 246, "loss": 0.4963, "lr": 9.871227793184893e-06, "epoch": 0.5065326633165829, "percentage": 17.07, "elapsed_time": "1:46:33", "remaining_time": "8:37:32"}
+{"current_steps": 43, "total_steps": 246, "loss": 0.5569, "lr": 9.854709087130261e-06, "epoch": 0.5185929648241207, "percentage": 17.48, "elapsed_time": "1:48:59", "remaining_time": "8:34:32"}
+{"current_steps": 44, "total_steps": 246, "loss": 0.5426, "lr": 9.837209376359918e-06, "epoch": 0.5306532663316583, "percentage": 17.89, "elapsed_time": "1:51:16", "remaining_time": "8:30:50"}
+{"current_steps": 45, "total_steps": 246, "loss": 0.4224, "lr": 9.81873219708962e-06, "epoch": 0.542713567839196, "percentage": 18.29, "elapsed_time": "1:53:40", "remaining_time": "8:27:46"}
+{"current_steps": 46, "total_steps": 246, "loss": 0.5157, "lr": 9.79928128305494e-06, "epoch": 0.5547738693467337, "percentage": 18.7, "elapsed_time": "1:56:01", "remaining_time": "8:24:27"}
+{"current_steps": 47, "total_steps": 246, "loss": 0.6073, "lr": 9.778860564756769e-06, "epoch": 0.5668341708542713, "percentage": 19.11, "elapsed_time": "1:58:15", "remaining_time": "8:20:44"}
+{"current_steps": 48, "total_steps": 246, "loss": 0.5141, "lr": 9.757474168667072e-06, "epoch": 0.578894472361809, "percentage": 19.51, "elapsed_time": "2:00:27", "remaining_time": "8:16:55"}
+{"current_steps": 49, "total_steps": 246, "loss": 0.4712, "lr": 9.73512641639504e-06, "epoch": 0.5909547738693467, "percentage": 19.92, "elapsed_time": "2:02:44", "remaining_time": "8:13:26"}
+{"current_steps": 50, "total_steps": 246, "loss": 0.4844, "lr": 9.711821823813812e-06, "epoch": 0.6030150753768844, "percentage": 20.33, "elapsed_time": "2:04:57", "remaining_time": "8:09:51"}
+{"current_steps": 51, "total_steps": 246, "loss": 0.5009, "lr": 9.68756510014794e-06, "epoch": 0.6150753768844222, "percentage": 20.73, "elapsed_time": "2:07:13", "remaining_time": "8:06:26"}
+{"current_steps": 52, "total_steps": 246, "loss": 0.5003, "lr": 9.66236114702178e-06, "epoch": 0.6271356783919598, "percentage": 21.14, "elapsed_time": "2:09:28", "remaining_time": "8:03:02"}
+{"current_steps": 53, "total_steps": 246, "loss": 0.5092, "lr": 9.636215057469009e-06, "epoch": 0.6391959798994975, "percentage": 21.54, "elapsed_time": "2:12:34", "remaining_time": "8:02:45"}
+{"current_steps": 54, "total_steps": 246, "loss": 0.5529, "lr": 9.609132114903458e-06, "epoch": 0.6512562814070352, "percentage": 21.95, "elapsed_time": "2:15:21", "remaining_time": "8:01:17"}
+{"current_steps": 55, "total_steps": 246, "loss": 0.5637, "lr": 9.581117792051487e-06, "epoch": 0.6633165829145728, "percentage": 22.36, "elapsed_time": "2:18:00", "remaining_time": "7:59:17"}
+{"current_steps": 56, "total_steps": 246, "loss": 0.5119, "lr": 9.552177749846083e-06, "epoch": 0.6753768844221105, "percentage": 22.76, "elapsed_time": "2:20:31", "remaining_time": "7:56:46"}
+{"current_steps": 57, "total_steps": 246, "loss": 0.5025, "lr": 9.522317836282949e-06, "epoch": 0.6874371859296482, "percentage": 23.17, "elapsed_time": "2:22:57", "remaining_time": "7:54:02"}
+{"current_steps": 58, "total_steps": 246, "loss": 0.5005, "lr": 9.491544085238778e-06, "epoch": 0.699497487437186, "percentage": 23.58, "elapsed_time": "2:25:12", "remaining_time": "7:50:38"}
+{"current_steps": 59, "total_steps": 246, "loss": 0.5244, "lr": 9.459862715251973e-06, "epoch": 0.7115577889447237, "percentage": 23.98, "elapsed_time": "2:27:29", "remaining_time": "7:47:28"}
+{"current_steps": 60, "total_steps": 246, "loss": 0.5427, "lr": 9.427280128266049e-06, "epoch": 0.7236180904522613, "percentage": 24.39, "elapsed_time": "2:29:47", "remaining_time": "7:44:19"}
+{"current_steps": 61, "total_steps": 246, "loss": 0.5277, "lr": 9.393802908335978e-06, "epoch": 0.735678391959799, "percentage": 24.8, "elapsed_time": "2:32:06", "remaining_time": "7:41:18"}
+{"current_steps": 62, "total_steps": 246, "loss": 0.4353, "lr": 9.359437820297716e-06, "epoch": 0.7477386934673367, "percentage": 25.2, "elapsed_time": "2:34:21", "remaining_time": "7:38:04"}
+{"current_steps": 63, "total_steps": 246, "loss": 0.5307, "lr": 9.324191808401235e-06, "epoch": 0.7597989949748744, "percentage": 25.61, "elapsed_time": "2:36:41", "remaining_time": "7:35:08"}
+{"current_steps": 64, "total_steps": 246, "loss": 0.5196, "lr": 9.288071994907262e-06, "epoch": 0.771859296482412, "percentage": 26.02, "elapsed_time": "2:39:03", "remaining_time": "7:32:18"}
+{"current_steps": 65, "total_steps": 246, "loss": 0.5412, "lr": 9.251085678648072e-06, "epoch": 0.7839195979899497, "percentage": 26.42, "elapsed_time": "2:41:15", "remaining_time": "7:29:02"}
+{"current_steps": 66, "total_steps": 246, "loss": 0.506, "lr": 9.213240333552589e-06, "epoch": 0.7959798994974875, "percentage": 26.83, "elapsed_time": "2:43:31", "remaining_time": "7:25:59"}
+{"current_steps": 67, "total_steps": 246, "loss": 0.4566, "lr": 9.174543607136111e-06, "epoch": 0.8080402010050252, "percentage": 27.24, "elapsed_time": "2:46:04", "remaining_time": "7:23:41"}
+{"current_steps": 68, "total_steps": 246, "loss": 0.4965, "lr": 9.135003318954954e-06, "epoch": 0.8201005025125628, "percentage": 27.64, "elapsed_time": "2:48:32", "remaining_time": "7:21:09"}
+{"current_steps": 69, "total_steps": 246, "loss": 0.4126, "lr": 9.094627459026326e-06, "epoch": 0.8321608040201005, "percentage": 28.05, "elapsed_time": "2:50:51", "remaining_time": "7:18:18"}
+{"current_steps": 70, "total_steps": 246, "loss": 0.4746, "lr": 9.053424186213776e-06, "epoch": 0.8442211055276382, "percentage": 28.46, "elapsed_time": "2:53:12", "remaining_time": "7:15:30"}
+{"current_steps": 71, "total_steps": 246, "loss": 0.4936, "lr": 9.011401826578492e-06, "epoch": 0.8562814070351759, "percentage": 28.86, "elapsed_time": "2:55:27", "remaining_time": "7:12:28"}
+{"current_steps": 72, "total_steps": 246, "loss": 0.4718, "lr": 8.968568871696847e-06, "epoch": 0.8683417085427135, "percentage": 29.27, "elapsed_time": "2:57:41", "remaining_time": "7:09:24"}
+{"current_steps": 73, "total_steps": 246, "loss": 0.5179, "lr": 8.924933976944474e-06, "epoch": 0.8804020100502512, "percentage": 29.67, "elapsed_time": "2:59:45", "remaining_time": "7:06:00"}
+{"current_steps": 74, "total_steps": 246, "loss": 0.5252, "lr": 8.880505959747245e-06, "epoch": 0.892462311557789, "percentage": 30.08, "elapsed_time": "3:01:48", "remaining_time": "7:02:35"}
+{"current_steps": 75, "total_steps": 246, "loss": 0.5661, "lr": 8.835293797799517e-06, "epoch": 0.9045226130653267, "percentage": 30.49, "elapsed_time": "3:04:04", "remaining_time": "6:59:41"}
+{"current_steps": 76, "total_steps": 246, "loss": 0.4611, "lr": 8.789306627249985e-06, "epoch": 0.9165829145728643, "percentage": 30.89, "elapsed_time": "3:06:29", "remaining_time": "6:57:09"}
+{"current_steps": 77, "total_steps": 246, "loss": 0.5003, "lr": 8.742553740855507e-06, "epoch": 0.928643216080402, "percentage": 31.3, "elapsed_time": "3:08:40", "remaining_time": "6:54:05"}
+{"current_steps": 78, "total_steps": 246, "loss": 0.504, "lr": 8.695044586103297e-06, "epoch": 0.9407035175879397, "percentage": 31.71, "elapsed_time": "3:10:45", "remaining_time": "6:50:51"}
+{"current_steps": 79, "total_steps": 246, "loss": 0.54, "lr": 8.646788763301842e-06, "epoch": 0.9527638190954774, "percentage": 32.11, "elapsed_time": "3:12:48", "remaining_time": "6:47:35"}
+{"current_steps": 80, "total_steps": 246, "loss": 0.478, "lr": 8.59779602364094e-06, "epoch": 0.964824120603015, "percentage": 32.52, "elapsed_time": "3:15:04", "remaining_time": "6:44:47"}
+{"current_steps": 81, "total_steps": 246, "loss": 0.4788, "lr": 8.548076267221258e-06, "epoch": 0.9768844221105528, "percentage": 32.93, "elapsed_time": "3:17:22", "remaining_time": "6:42:02"}
+{"current_steps": 82, "total_steps": 246, "loss": 0.4821, "lr": 8.497639541053769e-06, "epoch": 0.9889447236180905, "percentage": 33.33, "elapsed_time": "3:19:43", "remaining_time": "6:39:27"}
+{"current_steps": 83, "total_steps": 246, "loss": 0.9163, "lr": 8.446496037029555e-06, "epoch": 1.0120603015075378, "percentage": 33.74, "elapsed_time": "3:23:37", "remaining_time": "6:39:54"}
+{"current_steps": 84, "total_steps": 246, "loss": 0.4151, "lr": 8.394656089860274e-06, "epoch": 1.0241206030150753, "percentage": 34.15, "elapsed_time": "3:25:59", "remaining_time": "6:37:17"}
+{"current_steps": 85, "total_steps": 246, "loss": 0.4027, "lr": 8.342130174989819e-06, "epoch": 1.0361809045226131, "percentage": 34.55, "elapsed_time": "3:28:22", "remaining_time": "6:34:40"}
+{"current_steps": 86, "total_steps": 246, "loss": 0.3566, "lr": 8.288928906477497e-06, "epoch": 1.0482412060301507, "percentage": 34.96, "elapsed_time": "3:30:43", "remaining_time": "6:32:01"}
+{"current_steps": 87, "total_steps": 246, "loss": 0.412, "lr": 8.235063034853228e-06, "epoch": 1.0603015075376885, "percentage": 35.37, "elapsed_time": "3:33:04", "remaining_time": "6:29:25"}
+{"current_steps": 88, "total_steps": 246, "loss": 0.3899, "lr": 8.180543444945154e-06, "epoch": 1.072361809045226, "percentage": 35.77, "elapsed_time": "3:35:08", "remaining_time": "6:26:15"}
+{"current_steps": 89, "total_steps": 246, "loss": 0.3873, "lr": 8.125381153680103e-06, "epoch": 1.0844221105527638, "percentage": 36.18, "elapsed_time": "3:37:17", "remaining_time": "6:23:18"}
+{"current_steps": 90, "total_steps": 246, "loss": 0.3368, "lr": 8.069587307857377e-06, "epoch": 1.0964824120603014, "percentage": 36.59, "elapsed_time": "3:39:20", "remaining_time": "6:20:10"}
+{"current_steps": 91, "total_steps": 246, "loss": 0.4321, "lr": 8.013173181896283e-06, "epoch": 1.1085427135678392, "percentage": 36.99, "elapsed_time": "3:41:24", "remaining_time": "6:17:07"}
+{"current_steps": 92, "total_steps": 246, "loss": 0.3744, "lr": 7.95615017555788e-06, "epoch": 1.120603015075377, "percentage": 37.4, "elapsed_time": "3:43:35", "remaining_time": "6:14:16"}
+{"current_steps": 93, "total_steps": 246, "loss": 0.3951, "lr": 7.898529811641393e-06, "epoch": 1.1326633165829145, "percentage": 37.8, "elapsed_time": "3:45:38", "remaining_time": "6:11:13"}
+{"current_steps": 94, "total_steps": 246, "loss": 0.3973, "lr": 7.84032373365578e-06, "epoch": 1.1447236180904523, "percentage": 38.21, "elapsed_time": "3:47:40", "remaining_time": "6:08:09"}
+{"current_steps": 95, "total_steps": 246, "loss": 0.381, "lr": 7.781543703466881e-06, "epoch": 1.1567839195979899, "percentage": 38.62, "elapsed_time": "3:49:42", "remaining_time": "6:05:06"}
+{"current_steps": 96, "total_steps": 246, "loss": 0.3773, "lr": 7.722201598920673e-06, "epoch": 1.1688442211055277, "percentage": 39.02, "elapsed_time": "3:51:51", "remaining_time": "6:02:16"}
+{"current_steps": 97, "total_steps": 246, "loss": 0.4552, "lr": 7.662309411443084e-06, "epoch": 1.1809045226130652, "percentage": 39.43, "elapsed_time": "3:53:54", "remaining_time": "5:59:18"}
+{"current_steps": 98, "total_steps": 246, "loss": 0.374, "lr": 7.601879243616838e-06, "epoch": 1.192964824120603, "percentage": 39.84, "elapsed_time": "3:56:02", "remaining_time": "5:56:28"}
+{"current_steps": 99, "total_steps": 246, "loss": 0.396, "lr": 7.540923306735868e-06, "epoch": 1.2050251256281408, "percentage": 40.24, "elapsed_time": "3:58:16", "remaining_time": "5:53:48"}
+{"current_steps": 100, "total_steps": 246, "loss": 0.405, "lr": 7.479453918337733e-06, "epoch": 1.2170854271356784, "percentage": 40.65, "elapsed_time": "4:00:34", "remaining_time": "5:51:14"}
+{"current_steps": 101, "total_steps": 246, "loss": 0.3875, "lr": 7.417483499714589e-06, "epoch": 1.2291457286432161, "percentage": 41.06, "elapsed_time": "4:02:50", "remaining_time": "5:48:37"}
+{"current_steps": 102, "total_steps": 246, "loss": 0.4169, "lr": 7.355024573403174e-06, "epoch": 1.2412060301507537, "percentage": 41.46, "elapsed_time": "4:04:56", "remaining_time": "5:45:48"}
+{"current_steps": 103, "total_steps": 246, "loss": 0.3653, "lr": 7.292089760654352e-06, "epoch": 1.2532663316582915, "percentage": 41.87, "elapsed_time": "4:07:08", "remaining_time": "5:43:07"}
+{"current_steps": 104, "total_steps": 246, "loss": 0.3753, "lr": 7.2286917788826926e-06, "epoch": 1.265326633165829, "percentage": 42.28, "elapsed_time": "4:09:34", "remaining_time": "5:40:45"}
+{"current_steps": 105, "total_steps": 246, "loss": 0.4224, "lr": 7.1648434390966356e-06, "epoch": 1.2773869346733668, "percentage": 42.68, "elapsed_time": "4:12:14", "remaining_time": "5:38:42"}
+{"current_steps": 106, "total_steps": 246, "loss": 0.3392, "lr": 7.100557643309732e-06, "epoch": 1.2894472361809046, "percentage": 43.09, "elapsed_time": "4:14:44", "remaining_time": "5:36:26"}
+{"current_steps": 107, "total_steps": 246, "loss": 0.3895, "lr": 7.035847381933494e-06, "epoch": 1.3015075376884422, "percentage": 43.5, "elapsed_time": "4:17:13", "remaining_time": "5:34:08"}
+{"current_steps": 108, "total_steps": 246, "loss": 0.3768, "lr": 6.970725731152389e-06, "epoch": 1.31356783919598, "percentage": 43.9, "elapsed_time": "4:19:36", "remaining_time": "5:31:42"}
+{"current_steps": 109, "total_steps": 246, "loss": 0.377, "lr": 6.905205850281502e-06, "epoch": 1.3256281407035175, "percentage": 44.31, "elapsed_time": "4:21:48", "remaining_time": "5:29:04"}
+{"current_steps": 110, "total_steps": 246, "loss": 0.3778, "lr": 6.8393009791073895e-06, "epoch": 1.3376884422110553, "percentage": 44.72, "elapsed_time": "4:23:55", "remaining_time": "5:26:18"}
+{"current_steps": 111, "total_steps": 246, "loss": 0.3756, "lr": 6.773024435212678e-06, "epoch": 1.3497487437185929, "percentage": 45.12, "elapsed_time": "4:25:59", "remaining_time": "5:23:30"}
+{"current_steps": 112, "total_steps": 246, "loss": 0.3293, "lr": 6.706389611284953e-06, "epoch": 1.3618090452261307, "percentage": 45.53, "elapsed_time": "4:28:13", "remaining_time": "5:20:55"}
+{"current_steps": 113, "total_steps": 246, "loss": 0.3802, "lr": 6.639409972410446e-06, "epoch": 1.3738693467336685, "percentage": 45.93, "elapsed_time": "4:30:22", "remaining_time": "5:18:13"}
+{"current_steps": 114, "total_steps": 246, "loss": 0.4086, "lr": 6.57209905335312e-06, "epoch": 1.385929648241206, "percentage": 46.34, "elapsed_time": "4:33:00", "remaining_time": "5:16:07"}
+{"current_steps": 115, "total_steps": 246, "loss": 0.3663, "lr": 6.504470455819651e-06, "epoch": 1.3979899497487438, "percentage": 46.75, "elapsed_time": "4:36:44", "remaining_time": "5:15:14"}
+{"current_steps": 116, "total_steps": 246, "loss": 0.3733, "lr": 6.436537845710904e-06, "epoch": 1.4100502512562814, "percentage": 47.15, "elapsed_time": "4:39:23", "remaining_time": "5:13:06"}
+{"current_steps": 117, "total_steps": 246, "loss": 0.3619, "lr": 6.368314950360416e-06, "epoch": 1.4221105527638191, "percentage": 47.56, "elapsed_time": "4:41:41", "remaining_time": "5:10:34"}
+{"current_steps": 118, "total_steps": 246, "loss": 0.3958, "lr": 6.299815555760478e-06, "epoch": 1.4341708542713567, "percentage": 47.97, "elapsed_time": "4:44:21", "remaining_time": "5:08:27"}
+{"current_steps": 119, "total_steps": 246, "loss": 0.3428, "lr": 6.231053503776363e-06, "epoch": 1.4462311557788945, "percentage": 48.37, "elapsed_time": "4:46:25", "remaining_time": "5:05:40"}
+{"current_steps": 120, "total_steps": 246, "loss": 0.3709, "lr": 6.1620426893492645e-06, "epoch": 1.4582914572864323, "percentage": 48.78, "elapsed_time": "4:48:38", "remaining_time": "5:03:04"}
+{"current_steps": 121, "total_steps": 246, "loss": 0.3549, "lr": 6.092797057688496e-06, "epoch": 1.4703517587939698, "percentage": 49.19, "elapsed_time": "4:51:06", "remaining_time": "5:00:43"}
+{"current_steps": 122, "total_steps": 246, "loss": 0.3535, "lr": 6.0233306014535505e-06, "epoch": 1.4824120603015074, "percentage": 49.59, "elapsed_time": "4:53:31", "remaining_time": "4:58:20"}
+{"current_steps": 123, "total_steps": 246, "loss": 0.3775, "lr": 5.953657357926569e-06, "epoch": 1.4944723618090452, "percentage": 50.0, "elapsed_time": "4:56:03", "remaining_time": "4:56:03"}
+{"current_steps": 124, "total_steps": 246, "loss": 0.3546, "lr": 5.883791406175775e-06, "epoch": 1.506532663316583, "percentage": 50.41, "elapsed_time": "4:58:10", "remaining_time": "4:53:21"}
+{"current_steps": 125, "total_steps": 246, "loss": 0.3883, "lr": 5.813746864210489e-06, "epoch": 1.5185929648241205, "percentage": 50.81, "elapsed_time": "5:00:19", "remaining_time": "4:50:43"}
+{"current_steps": 126, "total_steps": 246, "loss": 0.4005, "lr": 5.743537886128258e-06, "epoch": 1.5306532663316583, "percentage": 51.22, "elapsed_time": "5:02:28", "remaining_time": "4:48:04"}
+{"current_steps": 127, "total_steps": 246, "loss": 0.3475, "lr": 5.673178659254698e-06, "epoch": 1.542713567839196, "percentage": 51.63, "elapsed_time": "5:04:38", "remaining_time": "4:45:26"}
+{"current_steps": 128, "total_steps": 246, "loss": 0.399, "lr": 5.6026834012766155e-06, "epoch": 1.5547738693467337, "percentage": 52.03, "elapsed_time": "5:07:11", "remaining_time": "4:43:11"}
+{"current_steps": 129, "total_steps": 246, "loss": 0.3404, "lr": 5.532066357369012e-06, "epoch": 1.5668341708542712, "percentage": 52.44, "elapsed_time": "5:09:36", "remaining_time": "4:40:48"}
+{"current_steps": 130, "total_steps": 246, "loss": 0.402, "lr": 5.46134179731651e-06, "epoch": 1.578894472361809, "percentage": 52.85, "elapsed_time": "5:11:57", "remaining_time": "4:38:22"}
+{"current_steps": 131, "total_steps": 246, "loss": 0.3735, "lr": 5.390524012629824e-06, "epoch": 1.5909547738693468, "percentage": 53.25, "elapsed_time": "5:14:25", "remaining_time": "4:36:01"}
+{"current_steps": 132, "total_steps": 246, "loss": 0.3455, "lr": 5.319627313657829e-06, "epoch": 1.6030150753768844, "percentage": 53.66, "elapsed_time": "5:16:39", "remaining_time": "4:33:28"}
+{"current_steps": 133, "total_steps": 246, "loss": 0.3252, "lr": 5.248666026695835e-06, "epoch": 1.6150753768844222, "percentage": 54.07, "elapsed_time": "5:18:50", "remaining_time": "4:30:53"}
+{"current_steps": 134, "total_steps": 246, "loss": 0.407, "lr": 5.177654491090627e-06, "epoch": 1.62713567839196, "percentage": 54.47, "elapsed_time": "5:20:58", "remaining_time": "4:28:16"}
+{"current_steps": 135, "total_steps": 246, "loss": 0.3471, "lr": 5.1066070563428736e-06, "epoch": 1.6391959798994975, "percentage": 54.88, "elapsed_time": "5:23:09", "remaining_time": "4:25:42"}
+{"current_steps": 136, "total_steps": 246, "loss": 0.4174, "lr": 5.035538079207488e-06, "epoch": 1.651256281407035, "percentage": 55.28, "elapsed_time": "5:25:17", "remaining_time": "4:23:05"}
+{"current_steps": 137, "total_steps": 246, "loss": 0.386, "lr": 4.964461920792512e-06, "epoch": 1.6633165829145728, "percentage": 55.69, "elapsed_time": "5:27:23", "remaining_time": "4:20:28"}
+{"current_steps": 138, "total_steps": 246, "loss": 0.4146, "lr": 4.893392943657127e-06, "epoch": 1.6753768844221106, "percentage": 56.1, "elapsed_time": "5:29:30", "remaining_time": "4:17:52"}
+{"current_steps": 139, "total_steps": 246, "loss": 0.3379, "lr": 4.822345508909376e-06, "epoch": 1.6874371859296482, "percentage": 56.5, "elapsed_time": "5:31:51", "remaining_time": "4:15:27"}
+{"current_steps": 140, "total_steps": 246, "loss": 0.367, "lr": 4.751333973304166e-06, "epoch": 1.699497487437186, "percentage": 56.91, "elapsed_time": "5:34:27", "remaining_time": "4:13:14"}
+{"current_steps": 141, "total_steps": 246, "loss": 0.3457, "lr": 4.680372686342173e-06, "epoch": 1.7115577889447238, "percentage": 57.32, "elapsed_time": "5:36:56", "remaining_time": "4:10:54"}
+{"current_steps": 142, "total_steps": 246, "loss": 0.3802, "lr": 4.609475987370177e-06, "epoch": 1.7236180904522613, "percentage": 57.72, "elapsed_time": "5:39:35", "remaining_time": "4:08:43"}
+{"current_steps": 143, "total_steps": 246, "loss": 0.3698, "lr": 4.53865820268349e-06, "epoch": 1.735678391959799, "percentage": 58.13, "elapsed_time": "5:42:06", "remaining_time": "4:06:25"}
+{"current_steps": 144, "total_steps": 246, "loss": 0.3741, "lr": 4.467933642630989e-06, "epoch": 1.7477386934673367, "percentage": 58.54, "elapsed_time": "5:44:17", "remaining_time": "4:03:52"}
+{"current_steps": 145, "total_steps": 246, "loss": 0.3506, "lr": 4.397316598723385e-06, "epoch": 1.7597989949748745, "percentage": 58.94, "elapsed_time": "5:46:25", "remaining_time": "4:01:18"}
+{"current_steps": 146, "total_steps": 246, "loss": 0.3847, "lr": 4.326821340745304e-06, "epoch": 1.771859296482412, "percentage": 59.35, "elapsed_time": "5:48:36", "remaining_time": "3:58:46"}
+{"current_steps": 147, "total_steps": 246, "loss": 0.39, "lr": 4.256462113871741e-06, "epoch": 1.7839195979899496, "percentage": 59.76, "elapsed_time": "5:50:43", "remaining_time": "3:56:12"}
+{"current_steps": 148, "total_steps": 246, "loss": 0.375, "lr": 4.186253135789511e-06, "epoch": 1.7959798994974876, "percentage": 60.16, "elapsed_time": "5:52:51", "remaining_time": "3:53:38"}
+{"current_steps": 149, "total_steps": 246, "loss": 0.3851, "lr": 4.116208593824227e-06, "epoch": 1.8080402010050252, "percentage": 60.57, "elapsed_time": "5:55:03", "remaining_time": "3:51:08"}
+{"current_steps": 150, "total_steps": 246, "loss": 0.3792, "lr": 4.046342642073433e-06, "epoch": 1.8201005025125627, "percentage": 60.98, "elapsed_time": "5:57:12", "remaining_time": "3:48:36"}
+{"current_steps": 151, "total_steps": 246, "loss": 0.3225, "lr": 3.976669398546451e-06, "epoch": 1.8321608040201005, "percentage": 61.38, "elapsed_time": "5:59:18", "remaining_time": "3:46:03"}
+{"current_steps": 152, "total_steps": 246, "loss": 0.3902, "lr": 3.907202942311506e-06, "epoch": 1.8442211055276383, "percentage": 61.79, "elapsed_time": "6:01:25", "remaining_time": "3:43:30"}
+{"current_steps": 153, "total_steps": 246, "loss": 0.389, "lr": 3.837957310650738e-06, "epoch": 1.8562814070351759, "percentage": 62.2, "elapsed_time": "6:03:35", "remaining_time": "3:41:00"}
+{"current_steps": 154, "total_steps": 246, "loss": 0.3559, "lr": 3.7689464962236367e-06, "epoch": 1.8683417085427134, "percentage": 62.6, "elapsed_time": "6:05:45", "remaining_time": "3:38:30"}
+{"current_steps": 155, "total_steps": 246, "loss": 0.3671, "lr": 3.700184444239524e-06, "epoch": 1.8804020100502512, "percentage": 63.01, "elapsed_time": "6:07:53", "remaining_time": "3:35:59"}
+{"current_steps": 156, "total_steps": 246, "loss": 0.3956, "lr": 3.6316850496395863e-06, "epoch": 1.892462311557789, "percentage": 63.41, "elapsed_time": "6:10:02", "remaining_time": "3:33:29"}
+{"current_steps": 157, "total_steps": 246, "loss": 0.3755, "lr": 3.563462154289098e-06, "epoch": 1.9045226130653266, "percentage": 63.82, "elapsed_time": "6:12:10", "remaining_time": "3:30:58"}
+{"current_steps": 158, "total_steps": 246, "loss": 0.3806, "lr": 3.49552954418035e-06, "epoch": 1.9165829145728643, "percentage": 64.23, "elapsed_time": "6:14:21", "remaining_time": "3:28:30"}
+{"current_steps": 159, "total_steps": 246, "loss": 0.3885, "lr": 3.4279009466468825e-06, "epoch": 1.9286432160804021, "percentage": 64.63, "elapsed_time": "6:16:32", "remaining_time": "3:26:01"}
+{"current_steps": 160, "total_steps": 246, "loss": 0.3973, "lr": 3.3605900275895565e-06, "epoch": 1.9407035175879397, "percentage": 65.04, "elapsed_time": "6:18:38", "remaining_time": "3:23:31"}
+{"current_steps": 161, "total_steps": 246, "loss": 0.3687, "lr": 3.2936103887150484e-06, "epoch": 1.9527638190954772, "percentage": 65.45, "elapsed_time": "6:20:45", "remaining_time": "3:21:01"}
+{"current_steps": 162, "total_steps": 246, "loss": 0.4121, "lr": 3.226975564787322e-06, "epoch": 1.964824120603015, "percentage": 65.85, "elapsed_time": "6:22:53", "remaining_time": "3:18:32"}
+{"current_steps": 163, "total_steps": 246, "loss": 0.3836, "lr": 3.1606990208926125e-06, "epoch": 1.9768844221105528, "percentage": 66.26, "elapsed_time": "6:25:02", "remaining_time": "3:16:03"}
+{"current_steps": 164, "total_steps": 246, "loss": 0.3617, "lr": 3.0947941497184985e-06, "epoch": 1.9889447236180904, "percentage": 66.67, "elapsed_time": "6:27:13", "remaining_time": "3:13:36"}
+{"current_steps": 165, "total_steps": 246, "loss": 0.6955, "lr": 3.0292742688476125e-06, "epoch": 2.0120603015075376, "percentage": 67.07, "elapsed_time": "6:31:24", "remaining_time": "3:12:08"}
+{"current_steps": 166, "total_steps": 246, "loss": 0.2988, "lr": 2.964152618066508e-06, "epoch": 2.0241206030150756, "percentage": 67.48, "elapsed_time": "6:33:50", "remaining_time": "3:09:48"}
+{"current_steps": 167, "total_steps": 246, "loss": 0.2977, "lr": 2.899442356690271e-06, "epoch": 2.036180904522613, "percentage": 67.89, "elapsed_time": "6:36:20", "remaining_time": "3:07:29"}
+{"current_steps": 168, "total_steps": 246, "loss": 0.2701, "lr": 2.835156560903365e-06, "epoch": 2.0482412060301507, "percentage": 68.29, "elapsed_time": "6:38:54", "remaining_time": "3:05:12"}
+{"current_steps": 169, "total_steps": 246, "loss": 0.2877, "lr": 2.771308221117309e-06, "epoch": 2.0603015075376883, "percentage": 68.7, "elapsed_time": "6:41:11", "remaining_time": "3:02:47"}
+{"current_steps": 170, "total_steps": 246, "loss": 0.2564, "lr": 2.7079102393456503e-06, "epoch": 2.0723618090452263, "percentage": 69.11, "elapsed_time": "6:43:18", "remaining_time": "3:00:18"}
+{"current_steps": 171, "total_steps": 246, "loss": 0.255, "lr": 2.6449754265968263e-06, "epoch": 2.084422110552764, "percentage": 69.51, "elapsed_time": "6:45:24", "remaining_time": "2:57:48"}
+{"current_steps": 172, "total_steps": 246, "loss": 0.2402, "lr": 2.5825165002854124e-06, "epoch": 2.0964824120603014, "percentage": 69.92, "elapsed_time": "6:47:32", "remaining_time": "2:55:20"}
+{"current_steps": 173, "total_steps": 246, "loss": 0.2902, "lr": 2.5205460816622684e-06, "epoch": 2.1085427135678394, "percentage": 70.33, "elapsed_time": "6:49:43", "remaining_time": "2:52:53"}
+{"current_steps": 174, "total_steps": 246, "loss": 0.283, "lr": 2.4590766932641353e-06, "epoch": 2.120603015075377, "percentage": 70.73, "elapsed_time": "6:51:50", "remaining_time": "2:50:25"}
+{"current_steps": 175, "total_steps": 246, "loss": 0.2608, "lr": 2.3981207563831633e-06, "epoch": 2.1326633165829145, "percentage": 71.14, "elapsed_time": "6:53:57", "remaining_time": "2:47:56"}
+{"current_steps": 176, "total_steps": 246, "loss": 0.2821, "lr": 2.3376905885569185e-06, "epoch": 2.144723618090452, "percentage": 71.54, "elapsed_time": "6:56:03", "remaining_time": "2:45:28"}
+{"current_steps": 177, "total_steps": 246, "loss": 0.2557, "lr": 2.2777984010793264e-06, "epoch": 2.15678391959799, "percentage": 71.95, "elapsed_time": "6:58:09", "remaining_time": "2:43:00"}
+{"current_steps": 178, "total_steps": 246, "loss": 0.2807, "lr": 2.2184562965331203e-06, "epoch": 2.1688442211055277, "percentage": 72.36, "elapsed_time": "7:00:20", "remaining_time": "2:40:34"}
+{"current_steps": 179, "total_steps": 246, "loss": 0.2861, "lr": 2.159676266344222e-06, "epoch": 2.180904522613065, "percentage": 72.76, "elapsed_time": "7:02:30", "remaining_time": "2:38:08"}
+{"current_steps": 180, "total_steps": 246, "loss": 0.2683, "lr": 2.1014701883586087e-06, "epoch": 2.192964824120603, "percentage": 73.17, "elapsed_time": "7:05:03", "remaining_time": "2:35:51"}
+{"current_steps": 181, "total_steps": 246, "loss": 0.2535, "lr": 2.043849824442124e-06, "epoch": 2.205025125628141, "percentage": 73.58, "elapsed_time": "7:07:16", "remaining_time": "2:33:26"}
+{"current_steps": 182, "total_steps": 246, "loss": 0.2965, "lr": 1.9868268181037186e-06, "epoch": 2.2170854271356784, "percentage": 73.98, "elapsed_time": "7:09:27", "remaining_time": "2:31:01"}
+{"current_steps": 183, "total_steps": 246, "loss": 0.2691, "lr": 1.9304126921426235e-06, "epoch": 2.229145728643216, "percentage": 74.39, "elapsed_time": "7:11:37", "remaining_time": "2:28:35"}
+{"current_steps": 184, "total_steps": 246, "loss": 0.2526, "lr": 1.8746188463198983e-06, "epoch": 2.241206030150754, "percentage": 74.8, "elapsed_time": "7:13:47", "remaining_time": "2:26:10"}
+{"current_steps": 185, "total_steps": 246, "loss": 0.2913, "lr": 1.8194565550548477e-06, "epoch": 2.2532663316582915, "percentage": 75.2, "elapsed_time": "7:15:59", "remaining_time": "2:23:45"}
+{"current_steps": 186, "total_steps": 246, "loss": 0.2481, "lr": 1.764936965146773e-06, "epoch": 2.265326633165829, "percentage": 75.61, "elapsed_time": "7:18:12", "remaining_time": "2:21:21"}
+{"current_steps": 187, "total_steps": 246, "loss": 0.2529, "lr": 1.7110710935225055e-06, "epoch": 2.277386934673367, "percentage": 76.02, "elapsed_time": "7:20:22", "remaining_time": "2:18:56"}
+{"current_steps": 188, "total_steps": 246, "loss": 0.2787, "lr": 1.6578698250101828e-06, "epoch": 2.2894472361809046, "percentage": 76.42, "elapsed_time": "7:22:46", "remaining_time": "2:16:36"}
+{"current_steps": 189, "total_steps": 246, "loss": 0.2685, "lr": 1.6053439101397257e-06, "epoch": 2.301507537688442, "percentage": 76.83, "elapsed_time": "7:24:57", "remaining_time": "2:14:11"}
+{"current_steps": 190, "total_steps": 246, "loss": 0.2717, "lr": 1.5535039629704467e-06, "epoch": 2.3135678391959797, "percentage": 77.24, "elapsed_time": "7:27:11", "remaining_time": "2:11:48"}
+{"current_steps": 191, "total_steps": 246, "loss": 0.2569, "lr": 1.502360458946232e-06, "epoch": 2.3256281407035178, "percentage": 77.64, "elapsed_time": "7:29:28", "remaining_time": "2:09:25"}
+{"current_steps": 192, "total_steps": 246, "loss": 0.2682, "lr": 1.451923732778745e-06, "epoch": 2.3376884422110553, "percentage": 78.05, "elapsed_time": "7:31:43", "remaining_time": "2:07:02"}
+{"current_steps": 193, "total_steps": 246, "loss": 0.263, "lr": 1.4022039763590595e-06, "epoch": 2.349748743718593, "percentage": 78.46, "elapsed_time": "7:34:01", "remaining_time": "2:04:40"}
+{"current_steps": 194, "total_steps": 246, "loss": 0.2759, "lr": 1.3532112366981598e-06, "epoch": 2.3618090452261304, "percentage": 78.86, "elapsed_time": "7:36:17", "remaining_time": "2:02:18"}
+{"current_steps": 195, "total_steps": 246, "loss": 0.2345, "lr": 1.3049554138967052e-06, "epoch": 2.3738693467336685, "percentage": 79.27, "elapsed_time": "7:38:32", "remaining_time": "1:59:55"}
+{"current_steps": 196, "total_steps": 246, "loss": 0.2355, "lr": 1.257446259144494e-06, "epoch": 2.385929648241206, "percentage": 79.67, "elapsed_time": "7:40:55", "remaining_time": "1:57:34"}
+{"current_steps": 197, "total_steps": 246, "loss": 0.2882, "lr": 1.210693372750017e-06, "epoch": 2.3979899497487436, "percentage": 80.08, "elapsed_time": "7:43:06", "remaining_time": "1:55:11"}
+{"current_steps": 198, "total_steps": 246, "loss": 0.2363, "lr": 1.1647062022004845e-06, "epoch": 2.4100502512562816, "percentage": 80.49, "elapsed_time": "7:45:24", "remaining_time": "1:52:49"}
+{"current_steps": 199, "total_steps": 246, "loss": 0.3291, "lr": 1.1194940402527566e-06, "epoch": 2.422110552763819, "percentage": 80.89, "elapsed_time": "7:47:34", "remaining_time": "1:50:25"}
+{"current_steps": 200, "total_steps": 246, "loss": 0.2589, "lr": 1.075066023055527e-06, "epoch": 2.4341708542713567, "percentage": 81.3, "elapsed_time": "7:49:53", "remaining_time": "1:48:04"}
+{"current_steps": 201, "total_steps": 246, "loss": 0.2608, "lr": 1.0314311283031531e-06, "epoch": 2.4462311557788947, "percentage": 81.71, "elapsed_time": "7:56:03", "remaining_time": "1:46:34"}
+{"current_steps": 202, "total_steps": 246, "loss": 0.2862, "lr": 9.885981734215094e-07, "epoch": 2.4582914572864323, "percentage": 82.11, "elapsed_time": "7:58:25", "remaining_time": "1:44:12"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f319461ca2564796c9cca1c5068b1a777372f1c6e41ffae765ae516dd80d241
+size 8312