Training in progress, step 195

.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 sha256:8adcd0a509ea328eed9a02a9672657b51731cbd77a98d94768309cd488e6acca
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e51c109e4ed34300b9da5e473c190662c5ffae3b456520dd8a131c28f270cc6
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61da58027eea179fbb3592283fe7503f5831161c3f96f3eebaccd053ac97d8c4
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44235128df2e5b0620a2f0c25631b6ab5e8fbb5841784a5e670b0ed636ae7368
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48cc2b030ee0b30b00d6a75b3c2f4ee21451c1e0361baf38ec65fdbf340a23b
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e968a61d5f7ad383dff7af9c09e29a949b36536211c41115e4eff2a2950d27f7
+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": 16384,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,196 @@
+{"current_steps": 1, "total_steps": 195, "loss": 0.7433, "lr": 0.0, "epoch": 0.015170670037926675, "percentage": 0.51, "elapsed_time": "0:04:06", "remaining_time": "13:16:39"}
+{"current_steps": 2, "total_steps": 195, "loss": 0.761, "lr": 5.000000000000001e-07, "epoch": 0.03034134007585335, "percentage": 1.03, "elapsed_time": "0:07:19", "remaining_time": "11:47:28"}
+{"current_steps": 3, "total_steps": 195, "loss": 0.8263, "lr": 1.0000000000000002e-06, "epoch": 0.045512010113780026, "percentage": 1.54, "elapsed_time": "0:10:44", "remaining_time": "11:27:22"}
+{"current_steps": 4, "total_steps": 195, "loss": 0.7565, "lr": 1.5e-06, "epoch": 0.0606826801517067, "percentage": 2.05, "elapsed_time": "0:14:18", "remaining_time": "11:23:21"}
+{"current_steps": 5, "total_steps": 195, "loss": 0.7118, "lr": 2.0000000000000003e-06, "epoch": 0.07585335018963338, "percentage": 2.56, "elapsed_time": "0:18:14", "remaining_time": "11:32:55"}
+{"current_steps": 6, "total_steps": 195, "loss": 0.7609, "lr": 2.5e-06, "epoch": 0.09102402022756005, "percentage": 3.08, "elapsed_time": "0:22:05", "remaining_time": "11:35:45"}
+{"current_steps": 7, "total_steps": 195, "loss": 0.8174, "lr": 3e-06, "epoch": 0.10619469026548672, "percentage": 3.59, "elapsed_time": "0:25:13", "remaining_time": "11:17:35"}
+{"current_steps": 8, "total_steps": 195, "loss": 0.7995, "lr": 3.5e-06, "epoch": 0.1213653603034134, "percentage": 4.1, "elapsed_time": "0:28:24", "remaining_time": "11:04:04"}
+{"current_steps": 9, "total_steps": 195, "loss": 0.7482, "lr": 4.000000000000001e-06, "epoch": 0.13653603034134007, "percentage": 4.62, "elapsed_time": "0:31:59", "remaining_time": "11:01:11"}
+{"current_steps": 10, "total_steps": 195, "loss": 0.7357, "lr": 4.5e-06, "epoch": 0.15170670037926676, "percentage": 5.13, "elapsed_time": "0:35:03", "remaining_time": "10:48:27"}
+{"current_steps": 11, "total_steps": 195, "loss": 0.7524, "lr": 5e-06, "epoch": 0.16687737041719342, "percentage": 5.64, "elapsed_time": "0:38:45", "remaining_time": "10:48:15"}
+{"current_steps": 12, "total_steps": 195, "loss": 0.6702, "lr": 5.500000000000001e-06, "epoch": 0.1820480404551201, "percentage": 6.15, "elapsed_time": "0:42:04", "remaining_time": "10:41:31"}
+{"current_steps": 13, "total_steps": 195, "loss": 0.6509, "lr": 6e-06, "epoch": 0.1972187104930468, "percentage": 6.67, "elapsed_time": "0:44:53", "remaining_time": "10:28:28"}
+{"current_steps": 14, "total_steps": 195, "loss": 0.7482, "lr": 6.5000000000000004e-06, "epoch": 0.21238938053097345, "percentage": 7.18, "elapsed_time": "0:48:01", "remaining_time": "10:20:47"}
+{"current_steps": 15, "total_steps": 195, "loss": 0.6602, "lr": 7e-06, "epoch": 0.22756005056890014, "percentage": 7.69, "elapsed_time": "0:51:32", "remaining_time": "10:18:35"}
+{"current_steps": 16, "total_steps": 195, "loss": 0.7036, "lr": 7.500000000000001e-06, "epoch": 0.2427307206068268, "percentage": 8.21, "elapsed_time": "0:55:03", "remaining_time": "10:15:56"}
+{"current_steps": 17, "total_steps": 195, "loss": 0.6934, "lr": 8.000000000000001e-06, "epoch": 0.2579013906447535, "percentage": 8.72, "elapsed_time": "0:58:11", "remaining_time": "10:09:12"}
+{"current_steps": 18, "total_steps": 195, "loss": 0.6572, "lr": 8.5e-06, "epoch": 0.27307206068268014, "percentage": 9.23, "elapsed_time": "1:02:07", "remaining_time": "10:10:54"}
+{"current_steps": 19, "total_steps": 195, "loss": 0.646, "lr": 9e-06, "epoch": 0.28824273072060685, "percentage": 9.74, "elapsed_time": "1:05:47", "remaining_time": "10:09:21"}
+{"current_steps": 20, "total_steps": 195, "loss": 0.7002, "lr": 9.5e-06, "epoch": 0.3034134007585335, "percentage": 10.26, "elapsed_time": "1:09:05", "remaining_time": "10:04:32"}
+{"current_steps": 21, "total_steps": 195, "loss": 0.6522, "lr": 1e-05, "epoch": 0.3185840707964602, "percentage": 10.77, "elapsed_time": "1:12:38", "remaining_time": "10:01:53"}
+{"current_steps": 22, "total_steps": 195, "loss": 0.5982, "lr": 9.999194339645292e-06, "epoch": 0.33375474083438683, "percentage": 11.28, "elapsed_time": "1:16:16", "remaining_time": "9:59:48"}
+{"current_steps": 23, "total_steps": 195, "loss": 0.6258, "lr": 9.996777618216608e-06, "epoch": 0.34892541087231355, "percentage": 11.79, "elapsed_time": "1:19:42", "remaining_time": "9:56:01"}
+{"current_steps": 24, "total_steps": 195, "loss": 0.6204, "lr": 9.992750614536606e-06, "epoch": 0.3640960809102402, "percentage": 12.31, "elapsed_time": "1:23:10", "remaining_time": "9:52:37"}
+{"current_steps": 25, "total_steps": 195, "loss": 0.6947, "lr": 9.987114626364172e-06, "epoch": 0.37926675094816686, "percentage": 12.82, "elapsed_time": "1:26:04", "remaining_time": "9:45:19"}
+{"current_steps": 26, "total_steps": 195, "loss": 0.6215, "lr": 9.979871469976197e-06, "epoch": 0.3944374209860936, "percentage": 13.33, "elapsed_time": "1:28:49", "remaining_time": "9:37:24"}
+{"current_steps": 27, "total_steps": 195, "loss": 0.5899, "lr": 9.971023479582258e-06, "epoch": 0.40960809102402024, "percentage": 13.85, "elapsed_time": "1:31:48", "remaining_time": "9:31:13"}
+{"current_steps": 28, "total_steps": 195, "loss": 0.6689, "lr": 9.960573506572391e-06, "epoch": 0.4247787610619469, "percentage": 14.36, "elapsed_time": "1:34:58", "remaining_time": "9:26:25"}
+{"current_steps": 29, "total_steps": 195, "loss": 0.6031, "lr": 9.948524918598175e-06, "epoch": 0.43994943109987356, "percentage": 14.87, "elapsed_time": "1:38:21", "remaining_time": "9:23:01"}
+{"current_steps": 30, "total_steps": 195, "loss": 0.5164, "lr": 9.934881598487478e-06, "epoch": 0.45512010113780027, "percentage": 15.38, "elapsed_time": "1:41:49", "remaining_time": "9:20:00"}
+{"current_steps": 31, "total_steps": 195, "loss": 0.6158, "lr": 9.91964794299315e-06, "epoch": 0.47029077117572693, "percentage": 15.9, "elapsed_time": "1:45:19", "remaining_time": "9:17:09"}
+{"current_steps": 32, "total_steps": 195, "loss": 0.6044, "lr": 9.902828861376101e-06, "epoch": 0.4854614412136536, "percentage": 16.41, "elapsed_time": "1:48:17", "remaining_time": "9:11:37"}
+{"current_steps": 33, "total_steps": 195, "loss": 0.5945, "lr": 9.884429773823238e-06, "epoch": 0.5006321112515802, "percentage": 16.92, "elapsed_time": "1:51:22", "remaining_time": "9:06:46"}
+{"current_steps": 34, "total_steps": 195, "loss": 0.595, "lr": 9.864456609700726e-06, "epoch": 0.515802781289507, "percentage": 17.44, "elapsed_time": "1:54:32", "remaining_time": "9:02:25"}
+{"current_steps": 35, "total_steps": 195, "loss": 0.5832, "lr": 9.842915805643156e-06, "epoch": 0.5309734513274337, "percentage": 17.95, "elapsed_time": "1:58:11", "remaining_time": "9:00:19"}
+{"current_steps": 36, "total_steps": 195, "loss": 0.5983, "lr": 9.819814303479268e-06, "epoch": 0.5461441213653603, "percentage": 18.46, "elapsed_time": "2:01:48", "remaining_time": "8:58:01"}
+{"current_steps": 37, "total_steps": 195, "loss": 0.6261, "lr": 9.79515954799483e-06, "epoch": 0.561314791403287, "percentage": 18.97, "elapsed_time": "2:04:55", "remaining_time": "8:53:28"}
+{"current_steps": 38, "total_steps": 195, "loss": 0.5501, "lr": 9.768959484533461e-06, "epoch": 0.5764854614412137, "percentage": 19.49, "elapsed_time": "2:08:32", "remaining_time": "8:51:05"}
+{"current_steps": 39, "total_steps": 195, "loss": 0.6143, "lr": 9.741222556436132e-06, "epoch": 0.5916561314791403, "percentage": 20.0, "elapsed_time": "2:11:27", "remaining_time": "8:45:48"}
+{"current_steps": 40, "total_steps": 195, "loss": 0.5895, "lr": 9.711957702320176e-06, "epoch": 0.606826801517067, "percentage": 20.51, "elapsed_time": "2:14:36", "remaining_time": "8:41:35"}
+{"current_steps": 41, "total_steps": 195, "loss": 0.6084, "lr": 9.681174353198687e-06, "epoch": 0.6219974715549936, "percentage": 21.03, "elapsed_time": "2:17:59", "remaining_time": "8:38:19"}
+{"current_steps": 42, "total_steps": 195, "loss": 0.5517, "lr": 9.648882429441258e-06, "epoch": 0.6371681415929203, "percentage": 21.54, "elapsed_time": "2:21:09", "remaining_time": "8:34:12"}
+{"current_steps": 43, "total_steps": 195, "loss": 0.5322, "lr": 9.615092337576987e-06, "epoch": 0.6523388116308471, "percentage": 22.05, "elapsed_time": "2:24:34", "remaining_time": "8:31:03"}
+{"current_steps": 44, "total_steps": 195, "loss": 0.614, "lr": 9.579814966940833e-06, "epoch": 0.6675094816687737, "percentage": 22.56, "elapsed_time": "2:27:48", "remaining_time": "8:27:15"}
+{"current_steps": 45, "total_steps": 195, "loss": 0.6005, "lr": 9.543061686164374e-06, "epoch": 0.6826801517067004, "percentage": 23.08, "elapsed_time": "2:31:20", "remaining_time": "8:24:28"}
+{"current_steps": 46, "total_steps": 195, "loss": 0.6009, "lr": 9.504844339512096e-06, "epoch": 0.6978508217446271, "percentage": 23.59, "elapsed_time": "2:35:12", "remaining_time": "8:22:44"}
+{"current_steps": 47, "total_steps": 195, "loss": 0.589, "lr": 9.465175243064428e-06, "epoch": 0.7130214917825537, "percentage": 24.1, "elapsed_time": "2:39:06", "remaining_time": "8:21:01"}
+{"current_steps": 48, "total_steps": 195, "loss": 0.562, "lr": 9.424067180748692e-06, "epoch": 0.7281921618204804, "percentage": 24.62, "elapsed_time": "2:42:20", "remaining_time": "8:17:11"}
+{"current_steps": 49, "total_steps": 195, "loss": 0.6247, "lr": 9.381533400219319e-06, "epoch": 0.7433628318584071, "percentage": 25.13, "elapsed_time": "2:45:29", "remaining_time": "8:13:04"}
+{"current_steps": 50, "total_steps": 195, "loss": 0.6327, "lr": 9.337587608588588e-06, "epoch": 0.7585335018963337, "percentage": 25.64, "elapsed_time": "2:48:27", "remaining_time": "8:08:31"}
+{"current_steps": 51, "total_steps": 195, "loss": 0.5905, "lr": 9.292243968009332e-06, "epoch": 0.7737041719342604, "percentage": 26.15, "elapsed_time": "2:52:15", "remaining_time": "8:06:23"}
+{"current_steps": 52, "total_steps": 195, "loss": 0.5787, "lr": 9.24551709111097e-06, "epoch": 0.7888748419721872, "percentage": 26.67, "elapsed_time": "2:55:47", "remaining_time": "8:03:25"}
+{"current_steps": 53, "total_steps": 195, "loss": 0.6414, "lr": 9.197422036290386e-06, "epoch": 0.8040455120101138, "percentage": 27.18, "elapsed_time": "2:59:01", "remaining_time": "7:59:38"}
+{"current_steps": 54, "total_steps": 195, "loss": 0.6136, "lr": 9.147974302859158e-06, "epoch": 0.8192161820480405, "percentage": 27.69, "elapsed_time": "3:02:21", "remaining_time": "7:56:08"}
+{"current_steps": 55, "total_steps": 195, "loss": 0.5687, "lr": 9.09718982604866e-06, "epoch": 0.8343868520859671, "percentage": 28.21, "elapsed_time": "3:05:31", "remaining_time": "7:52:14"}
+{"current_steps": 56, "total_steps": 195, "loss": 0.5977, "lr": 9.045084971874738e-06, "epoch": 0.8495575221238938, "percentage": 28.72, "elapsed_time": "3:08:22", "remaining_time": "7:47:34"}
+{"current_steps": 57, "total_steps": 195, "loss": 0.5718, "lr": 8.991676531863507e-06, "epoch": 0.8647281921618205, "percentage": 29.23, "elapsed_time": "3:10:56", "remaining_time": "7:42:16"}
+{"current_steps": 58, "total_steps": 195, "loss": 0.5713, "lr": 8.936981717640061e-06, "epoch": 0.8798988621997471, "percentage": 29.74, "elapsed_time": "3:14:14", "remaining_time": "7:38:48"}
+{"current_steps": 59, "total_steps": 195, "loss": 0.6296, "lr": 8.881018155381766e-06, "epoch": 0.8950695322376738, "percentage": 30.26, "elapsed_time": "3:17:15", "remaining_time": "7:34:42"}
+{"current_steps": 60, "total_steps": 195, "loss": 0.567, "lr": 8.823803880137993e-06, "epoch": 0.9102402022756005, "percentage": 30.77, "elapsed_time": "3:21:07", "remaining_time": "7:32:32"}
+{"current_steps": 61, "total_steps": 195, "loss": 0.5658, "lr": 8.765357330018056e-06, "epoch": 0.9254108723135271, "percentage": 31.28, "elapsed_time": "3:23:59", "remaining_time": "7:28:06"}
+{"current_steps": 62, "total_steps": 195, "loss": 0.5758, "lr": 8.705697340249275e-06, "epoch": 0.9405815423514539, "percentage": 31.79, "elapsed_time": "3:26:49", "remaining_time": "7:23:39"}
+{"current_steps": 63, "total_steps": 195, "loss": 0.5843, "lr": 8.644843137107058e-06, "epoch": 0.9557522123893806, "percentage": 32.31, "elapsed_time": "3:30:15", "remaining_time": "7:20:32"}
+{"current_steps": 64, "total_steps": 195, "loss": 0.5723, "lr": 8.582814331718961e-06, "epoch": 0.9709228824273072, "percentage": 32.82, "elapsed_time": "3:33:28", "remaining_time": "7:16:58"}
+{"current_steps": 65, "total_steps": 195, "loss": 0.6162, "lr": 8.519630913744726e-06, "epoch": 0.9860935524652339, "percentage": 33.33, "elapsed_time": "3:36:47", "remaining_time": "7:13:34"}
+{"current_steps": 66, "total_steps": 195, "loss": 1.1143, "lr": 8.455313244934324e-06, "epoch": 1.0151706700379266, "percentage": 33.85, "elapsed_time": "3:42:05", "remaining_time": "7:14:05"}
+{"current_steps": 67, "total_steps": 195, "loss": 0.4743, "lr": 8.389882052566106e-06, "epoch": 1.0303413400758534, "percentage": 34.36, "elapsed_time": "3:44:52", "remaining_time": "7:09:36"}
+{"current_steps": 68, "total_steps": 195, "loss": 0.483, "lr": 8.32335842276713e-06, "epoch": 1.04551201011378, "percentage": 34.87, "elapsed_time": "3:48:17", "remaining_time": "7:06:21"}
+{"current_steps": 69, "total_steps": 195, "loss": 0.5228, "lr": 8.255763793717868e-06, "epoch": 1.0606826801517066, "percentage": 35.38, "elapsed_time": "3:51:45", "remaining_time": "7:03:12"}
+{"current_steps": 70, "total_steps": 195, "loss": 0.4833, "lr": 8.18711994874345e-06, "epoch": 1.0758533501896335, "percentage": 35.9, "elapsed_time": "3:54:58", "remaining_time": "6:59:36"}
+{"current_steps": 71, "total_steps": 195, "loss": 0.5248, "lr": 8.117449009293668e-06, "epoch": 1.09102402022756, "percentage": 36.41, "elapsed_time": "3:58:52", "remaining_time": "6:57:12"}
+{"current_steps": 72, "total_steps": 195, "loss": 0.4946, "lr": 8.046773427814043e-06, "epoch": 1.1061946902654867, "percentage": 36.92, "elapsed_time": "4:01:57", "remaining_time": "6:53:21"}
+{"current_steps": 73, "total_steps": 195, "loss": 0.5118, "lr": 7.975115980510187e-06, "epoch": 1.1213653603034135, "percentage": 37.44, "elapsed_time": "4:05:05", "remaining_time": "6:49:35"}
+{"current_steps": 74, "total_steps": 195, "loss": 0.5132, "lr": 7.902499760007867e-06, "epoch": 1.13653603034134, "percentage": 37.95, "elapsed_time": "4:08:38", "remaining_time": "6:46:33"}
+{"current_steps": 75, "total_steps": 195, "loss": 0.51, "lr": 7.828948167911073e-06, "epoch": 1.1517067003792667, "percentage": 38.46, "elapsed_time": "4:11:56", "remaining_time": "6:43:06"}
+{"current_steps": 76, "total_steps": 195, "loss": 0.4863, "lr": 7.754484907260513e-06, "epoch": 1.1668773704171933, "percentage": 38.97, "elapsed_time": "4:15:18", "remaining_time": "6:39:45"}
+{"current_steps": 77, "total_steps": 195, "loss": 0.5083, "lr": 7.679133974894984e-06, "epoch": 1.1820480404551201, "percentage": 39.49, "elapsed_time": "4:18:43", "remaining_time": "6:36:29"}
+{"current_steps": 78, "total_steps": 195, "loss": 0.5121, "lr": 7.602919653718044e-06, "epoch": 1.1972187104930467, "percentage": 40.0, "elapsed_time": "4:21:17", "remaining_time": "6:31:56"}
+{"current_steps": 79, "total_steps": 195, "loss": 0.4804, "lr": 7.5258665048725065e-06, "epoch": 1.2123893805309733, "percentage": 40.51, "elapsed_time": "4:24:35", "remaining_time": "6:28:30"}
+{"current_steps": 80, "total_steps": 195, "loss": 0.4756, "lr": 7.447999359825263e-06, "epoch": 1.2275600505689002, "percentage": 41.03, "elapsed_time": "4:27:59", "remaining_time": "6:25:14"}
+{"current_steps": 81, "total_steps": 195, "loss": 0.4748, "lr": 7.369343312364994e-06, "epoch": 1.2427307206068268, "percentage": 41.54, "elapsed_time": "4:31:12", "remaining_time": "6:21:42"}
+{"current_steps": 82, "total_steps": 195, "loss": 0.4969, "lr": 7.289923710515338e-06, "epoch": 1.2579013906447534, "percentage": 42.05, "elapsed_time": "4:34:08", "remaining_time": "6:17:47"}
+{"current_steps": 83, "total_steps": 195, "loss": 0.5173, "lr": 7.2097661483661355e-06, "epoch": 1.2730720606826802, "percentage": 42.56, "elapsed_time": "4:37:37", "remaining_time": "6:14:37"}
+{"current_steps": 84, "total_steps": 195, "loss": 0.5154, "lr": 7.128896457825364e-06, "epoch": 1.2882427307206068, "percentage": 43.08, "elapsed_time": "4:40:44", "remaining_time": "6:10:58"}
+{"current_steps": 85, "total_steps": 195, "loss": 0.4539, "lr": 7.047340700294454e-06, "epoch": 1.3034134007585334, "percentage": 43.59, "elapsed_time": "4:44:20", "remaining_time": "6:07:58"}
+{"current_steps": 86, "total_steps": 195, "loss": 0.5475, "lr": 6.965125158269619e-06, "epoch": 1.3185840707964602, "percentage": 44.1, "elapsed_time": "4:47:39", "remaining_time": "6:04:35"}
+{"current_steps": 87, "total_steps": 195, "loss": 0.4785, "lr": 6.88227632687196e-06, "epoch": 1.3337547408343868, "percentage": 44.62, "elapsed_time": "4:50:54", "remaining_time": "6:01:07"}
+{"current_steps": 88, "total_steps": 195, "loss": 0.4832, "lr": 6.798820905309036e-06, "epoch": 1.3489254108723134, "percentage": 45.13, "elapsed_time": "4:53:38", "remaining_time": "5:57:01"}
+{"current_steps": 89, "total_steps": 195, "loss": 0.4991, "lr": 6.714785788270658e-06, "epoch": 1.3640960809102403, "percentage": 45.64, "elapsed_time": "4:56:50", "remaining_time": "5:53:32"}
+{"current_steps": 90, "total_steps": 195, "loss": 0.5147, "lr": 6.63019805726171e-06, "epoch": 1.3792667509481669, "percentage": 46.15, "elapsed_time": "5:00:13", "remaining_time": "5:50:16"}
+{"current_steps": 91, "total_steps": 195, "loss": 0.468, "lr": 6.545084971874738e-06, "epoch": 1.3944374209860935, "percentage": 46.67, "elapsed_time": "5:03:44", "remaining_time": "5:47:07"}
+{"current_steps": 92, "total_steps": 195, "loss": 0.4465, "lr": 6.459473961005168e-06, "epoch": 1.4096080910240203, "percentage": 47.18, "elapsed_time": "5:06:33", "remaining_time": "5:43:13"}
+{"current_steps": 93, "total_steps": 195, "loss": 0.4599, "lr": 6.373392614011952e-06, "epoch": 1.424778761061947, "percentage": 47.69, "elapsed_time": "5:10:10", "remaining_time": "5:40:11"}
+{"current_steps": 94, "total_steps": 195, "loss": 0.4809, "lr": 6.286868671826513e-06, "epoch": 1.4399494310998735, "percentage": 48.21, "elapsed_time": "5:13:37", "remaining_time": "5:36:59"}
+{"current_steps": 95, "total_steps": 195, "loss": 0.4756, "lr": 6.19993001801283e-06, "epoch": 1.4551201011378003, "percentage": 48.72, "elapsed_time": "5:17:06", "remaining_time": "5:33:47"}
+{"current_steps": 96, "total_steps": 195, "loss": 0.4996, "lr": 6.112604669781572e-06, "epoch": 1.470290771175727, "percentage": 49.23, "elapsed_time": "5:20:46", "remaining_time": "5:30:48"}
+{"current_steps": 97, "total_steps": 195, "loss": 0.5203, "lr": 6.024920768961153e-06, "epoch": 1.4854614412136535, "percentage": 49.74, "elapsed_time": "5:24:36", "remaining_time": "5:27:56"}
+{"current_steps": 98, "total_steps": 195, "loss": 0.5112, "lr": 5.936906572928625e-06, "epoch": 1.5006321112515804, "percentage": 50.26, "elapsed_time": "5:27:50", "remaining_time": "5:24:29"}
+{"current_steps": 99, "total_steps": 195, "loss": 0.5077, "lr": 5.848590445503345e-06, "epoch": 1.515802781289507, "percentage": 50.77, "elapsed_time": "5:30:58", "remaining_time": "5:20:56"}
+{"current_steps": 100, "total_steps": 195, "loss": 0.5244, "lr": 5.760000847806337e-06, "epoch": 1.5309734513274336, "percentage": 51.28, "elapsed_time": "5:34:23", "remaining_time": "5:17:40"}
+{"current_steps": 101, "total_steps": 195, "loss": 0.4814, "lr": 5.671166329088278e-06, "epoch": 1.5461441213653604, "percentage": 51.79, "elapsed_time": "5:37:50", "remaining_time": "5:14:25"}
+{"current_steps": 102, "total_steps": 195, "loss": 0.4969, "lr": 5.582115517529114e-06, "epoch": 1.561314791403287, "percentage": 52.31, "elapsed_time": "5:41:39", "remaining_time": "5:11:30"}
+{"current_steps": 103, "total_steps": 195, "loss": 0.4738, "lr": 5.4928771110122185e-06, "epoch": 1.5764854614412136, "percentage": 52.82, "elapsed_time": "5:44:26", "remaining_time": "5:07:39"}
+{"current_steps": 104, "total_steps": 195, "loss": 0.4958, "lr": 5.403479867876087e-06, "epoch": 1.5916561314791404, "percentage": 53.33, "elapsed_time": "5:47:56", "remaining_time": "5:04:27"}
+{"current_steps": 105, "total_steps": 195, "loss": 0.446, "lr": 5.3139525976465675e-06, "epoch": 1.606826801517067, "percentage": 53.85, "elapsed_time": "5:51:26", "remaining_time": "5:01:14"}
+{"current_steps": 106, "total_steps": 195, "loss": 0.4789, "lr": 5.224324151752575e-06, "epoch": 1.6219974715549936, "percentage": 54.36, "elapsed_time": "5:55:03", "remaining_time": "4:58:07"}
+{"current_steps": 107, "total_steps": 195, "loss": 0.4801, "lr": 5.134623414228315e-06, "epoch": 1.6371681415929205, "percentage": 54.87, "elapsed_time": "5:58:08", "remaining_time": "4:54:33"}
+{"current_steps": 108, "total_steps": 195, "loss": 0.5132, "lr": 5.04487929240499e-06, "epoch": 1.652338811630847, "percentage": 55.38, "elapsed_time": "6:00:43", "remaining_time": "4:50:34"}
+{"current_steps": 109, "total_steps": 195, "loss": 0.4529, "lr": 4.955120707595011e-06, "epoch": 1.6675094816687737, "percentage": 55.9, "elapsed_time": "6:03:30", "remaining_time": "4:46:48"}
+{"current_steps": 110, "total_steps": 195, "loss": 0.4207, "lr": 4.865376585771687e-06, "epoch": 1.6826801517067005, "percentage": 56.41, "elapsed_time": "6:06:31", "remaining_time": "4:43:13"}
+{"current_steps": 111, "total_steps": 195, "loss": 0.4408, "lr": 4.775675848247427e-06, "epoch": 1.697850821744627, "percentage": 56.92, "elapsed_time": "6:09:16", "remaining_time": "4:39:26"}
+{"current_steps": 112, "total_steps": 195, "loss": 0.4526, "lr": 4.686047402353433e-06, "epoch": 1.7130214917825537, "percentage": 57.44, "elapsed_time": "6:12:34", "remaining_time": "4:36:05"}
+{"current_steps": 113, "total_steps": 195, "loss": 0.4952, "lr": 4.596520132123915e-06, "epoch": 1.7281921618204805, "percentage": 57.95, "elapsed_time": "6:16:02", "remaining_time": "4:32:52"}
+{"current_steps": 114, "total_steps": 195, "loss": 0.514, "lr": 4.507122888987782e-06, "epoch": 1.7433628318584071, "percentage": 58.46, "elapsed_time": "6:18:49", "remaining_time": "4:29:09"}
+{"current_steps": 115, "total_steps": 195, "loss": 0.4494, "lr": 4.417884482470887e-06, "epoch": 1.7585335018963337, "percentage": 58.97, "elapsed_time": "6:22:10", "remaining_time": "4:25:51"}
+{"current_steps": 116, "total_steps": 195, "loss": 0.4812, "lr": 4.3288336709117246e-06, "epoch": 1.7737041719342606, "percentage": 59.49, "elapsed_time": "6:26:00", "remaining_time": "4:22:53"}
+{"current_steps": 117, "total_steps": 195, "loss": 0.5324, "lr": 4.239999152193664e-06, "epoch": 1.7888748419721872, "percentage": 60.0, "elapsed_time": "6:29:06", "remaining_time": "4:19:24"}
+{"current_steps": 118, "total_steps": 195, "loss": 0.4907, "lr": 4.1514095544966556e-06, "epoch": 1.8040455120101138, "percentage": 60.51, "elapsed_time": "6:32:38", "remaining_time": "4:16:12"}
+{"current_steps": 119, "total_steps": 195, "loss": 0.53, "lr": 4.063093427071376e-06, "epoch": 1.8192161820480406, "percentage": 61.03, "elapsed_time": "6:35:59", "remaining_time": "4:12:53"}
+{"current_steps": 120, "total_steps": 195, "loss": 0.4665, "lr": 3.975079231038848e-06, "epoch": 1.834386852085967, "percentage": 61.54, "elapsed_time": "6:39:06", "remaining_time": "4:09:26"}
+{"current_steps": 121, "total_steps": 195, "loss": 0.5168, "lr": 3.887395330218429e-06, "epoch": 1.8495575221238938, "percentage": 62.05, "elapsed_time": "6:42:48", "remaining_time": "4:06:20"}
+{"current_steps": 122, "total_steps": 195, "loss": 0.5011, "lr": 3.8000699819871704e-06, "epoch": 1.8647281921618206, "percentage": 62.56, "elapsed_time": "6:45:54", "remaining_time": "4:02:52"}
+{"current_steps": 123, "total_steps": 195, "loss": 0.4997, "lr": 3.7131313281734895e-06, "epoch": 1.879898862199747, "percentage": 63.08, "elapsed_time": "6:49:20", "remaining_time": "3:59:36"}
+{"current_steps": 124, "total_steps": 195, "loss": 0.4689, "lr": 3.62660738598805e-06, "epoch": 1.8950695322376738, "percentage": 63.59, "elapsed_time": "6:52:10", "remaining_time": "3:56:00"}
+{"current_steps": 125, "total_steps": 195, "loss": 0.5054, "lr": 3.540526038994834e-06, "epoch": 1.9102402022756007, "percentage": 64.1, "elapsed_time": "6:55:53", "remaining_time": "3:52:54"}
+{"current_steps": 126, "total_steps": 195, "loss": 0.4463, "lr": 3.4549150281252635e-06, "epoch": 1.925410872313527, "percentage": 64.62, "elapsed_time": "6:58:58", "remaining_time": "3:49:26"}
+{"current_steps": 127, "total_steps": 195, "loss": 0.4955, "lr": 3.3698019427382912e-06, "epoch": 1.9405815423514539, "percentage": 65.13, "elapsed_time": "7:02:17", "remaining_time": "3:46:06"}
+{"current_steps": 128, "total_steps": 195, "loss": 0.4706, "lr": 3.2852142117293435e-06, "epoch": 1.9557522123893807, "percentage": 65.64, "elapsed_time": "7:05:36", "remaining_time": "3:42:46"}
+{"current_steps": 129, "total_steps": 195, "loss": 0.5306, "lr": 3.2011790946909673e-06, "epoch": 1.970922882427307, "percentage": 66.15, "elapsed_time": "7:08:36", "remaining_time": "3:39:17"}
+{"current_steps": 130, "total_steps": 195, "loss": 0.4863, "lr": 3.11772367312804e-06, "epoch": 1.986093552465234, "percentage": 66.67, "elapsed_time": "7:11:44", "remaining_time": "3:35:52"}
+{"current_steps": 131, "total_steps": 195, "loss": 0.9358, "lr": 3.0348748417303826e-06, "epoch": 2.015170670037927, "percentage": 67.18, "elapsed_time": "7:17:35", "remaining_time": "3:33:46"}
+{"current_steps": 132, "total_steps": 195, "loss": 0.4256, "lr": 2.9526592997055488e-06, "epoch": 2.030341340075853, "percentage": 67.69, "elapsed_time": "7:21:15", "remaining_time": "3:30:36"}
+{"current_steps": 133, "total_steps": 195, "loss": 0.3838, "lr": 2.871103542174637e-06, "epoch": 2.04551201011378, "percentage": 68.21, "elapsed_time": "7:24:21", "remaining_time": "3:27:08"}
+{"current_steps": 134, "total_steps": 195, "loss": 0.4796, "lr": 2.790233851633868e-06, "epoch": 2.060682680151707, "percentage": 68.72, "elapsed_time": "7:27:40", "remaining_time": "3:23:47"}
+{"current_steps": 135, "total_steps": 195, "loss": 0.4175, "lr": 2.7100762894846633e-06, "epoch": 2.0758533501896332, "percentage": 69.23, "elapsed_time": "7:30:40", "remaining_time": "3:20:18"}
+{"current_steps": 136, "total_steps": 195, "loss": 0.4059, "lr": 2.6306566876350072e-06, "epoch": 2.09102402022756, "percentage": 69.74, "elapsed_time": "7:34:27", "remaining_time": "3:17:09"}
+{"current_steps": 137, "total_steps": 195, "loss": 0.4155, "lr": 2.55200064017474e-06, "epoch": 2.106194690265487, "percentage": 70.26, "elapsed_time": "7:37:36", "remaining_time": "3:13:44"}
+{"current_steps": 138, "total_steps": 195, "loss": 0.4085, "lr": 2.4741334951274948e-06, "epoch": 2.1213653603034133, "percentage": 70.77, "elapsed_time": "7:40:33", "remaining_time": "3:10:13"}
+{"current_steps": 139, "total_steps": 195, "loss": 0.413, "lr": 2.3970803462819586e-06, "epoch": 2.13653603034134, "percentage": 71.28, "elapsed_time": "7:43:32", "remaining_time": "3:06:44"}
+{"current_steps": 140, "total_steps": 195, "loss": 0.3982, "lr": 2.320866025105016e-06, "epoch": 2.151706700379267, "percentage": 71.79, "elapsed_time": "7:46:52", "remaining_time": "3:03:24"}
+{"current_steps": 141, "total_steps": 195, "loss": 0.4189, "lr": 2.245515092739488e-06, "epoch": 2.1668773704171933, "percentage": 72.31, "elapsed_time": "7:50:12", "remaining_time": "3:00:04"}
+{"current_steps": 142, "total_steps": 195, "loss": 0.4274, "lr": 2.171051832088928e-06, "epoch": 2.18204804045512, "percentage": 72.82, "elapsed_time": "7:53:08", "remaining_time": "2:56:35"}
+{"current_steps": 143, "total_steps": 195, "loss": 0.4309, "lr": 2.097500239992132e-06, "epoch": 2.197218710493047, "percentage": 73.33, "elapsed_time": "7:56:26", "remaining_time": "2:53:15"}
+{"current_steps": 144, "total_steps": 195, "loss": 0.428, "lr": 2.0248840194898155e-06, "epoch": 2.2123893805309733, "percentage": 73.85, "elapsed_time": "7:59:40", "remaining_time": "2:49:53"}
+{"current_steps": 145, "total_steps": 195, "loss": 0.4206, "lr": 1.95322657218596e-06, "epoch": 2.2275600505689, "percentage": 74.36, "elapsed_time": "8:03:25", "remaining_time": "2:46:42"}
+{"current_steps": 146, "total_steps": 195, "loss": 0.4085, "lr": 1.8825509907063328e-06, "epoch": 2.242730720606827, "percentage": 74.87, "elapsed_time": "8:06:50", "remaining_time": "2:43:23"}
+{"current_steps": 147, "total_steps": 195, "loss": 0.3596, "lr": 1.8128800512565514e-06, "epoch": 2.2579013906447534, "percentage": 75.38, "elapsed_time": "8:09:58", "remaining_time": "2:39:59"}
+{"current_steps": 148, "total_steps": 195, "loss": 0.4303, "lr": 1.7442362062821323e-06, "epoch": 2.27307206068268, "percentage": 75.9, "elapsed_time": "8:13:20", "remaining_time": "2:36:40"}
+{"current_steps": 149, "total_steps": 195, "loss": 0.4721, "lr": 1.6766415772328732e-06, "epoch": 2.288242730720607, "percentage": 76.41, "elapsed_time": "8:16:56", "remaining_time": "2:33:25"}
+{"current_steps": 150, "total_steps": 195, "loss": 0.3937, "lr": 1.610117947433897e-06, "epoch": 2.3034134007585334, "percentage": 76.92, "elapsed_time": "8:19:41", "remaining_time": "2:29:54"}
+{"current_steps": 151, "total_steps": 195, "loss": 0.4465, "lr": 1.544686755065677e-06, "epoch": 2.3185840707964602, "percentage": 77.44, "elapsed_time": "8:22:59", "remaining_time": "2:26:34"}
+{"current_steps": 152, "total_steps": 195, "loss": 0.4034, "lr": 1.4803690862552755e-06, "epoch": 2.3337547408343866, "percentage": 77.95, "elapsed_time": "8:26:35", "remaining_time": "2:23:18"}
+{"current_steps": 153, "total_steps": 195, "loss": 0.3969, "lr": 1.4171856682810386e-06, "epoch": 2.3489254108723134, "percentage": 78.46, "elapsed_time": "8:29:57", "remaining_time": "2:19:59"}
+{"current_steps": 154, "total_steps": 195, "loss": 0.421, "lr": 1.3551568628929434e-06, "epoch": 2.3640960809102403, "percentage": 78.97, "elapsed_time": "8:33:48", "remaining_time": "2:16:47"}
+{"current_steps": 155, "total_steps": 195, "loss": 0.4364, "lr": 1.2943026597507268e-06, "epoch": 2.379266750948167, "percentage": 79.49, "elapsed_time": "8:36:54", "remaining_time": "2:13:23"}
+{"current_steps": 156, "total_steps": 195, "loss": 0.4293, "lr": 1.234642669981946e-06, "epoch": 2.3944374209860935, "percentage": 80.0, "elapsed_time": "8:40:37", "remaining_time": "2:10:09"}
+{"current_steps": 157, "total_steps": 195, "loss": 0.4273, "lr": 1.1761961198620081e-06, "epoch": 2.4096080910240203, "percentage": 80.51, "elapsed_time": "8:44:15", "remaining_time": "2:06:53"}
+{"current_steps": 158, "total_steps": 195, "loss": 0.4646, "lr": 1.118981844618236e-06, "epoch": 2.4247787610619467, "percentage": 81.03, "elapsed_time": "8:47:39", "remaining_time": "2:03:33"}
+{"current_steps": 159, "total_steps": 195, "loss": 0.3575, "lr": 1.06301828235994e-06, "epoch": 2.4399494310998735, "percentage": 81.54, "elapsed_time": "8:50:40", "remaining_time": "2:00:09"}
+{"current_steps": 160, "total_steps": 195, "loss": 0.4138, "lr": 1.0083234681364934e-06, "epoch": 2.4551201011378003, "percentage": 82.05, "elapsed_time": "8:53:38", "remaining_time": "1:56:44"}
+{"current_steps": 161, "total_steps": 195, "loss": 0.3955, "lr": 9.549150281252633e-07, "epoch": 2.470290771175727, "percentage": 82.56, "elapsed_time": "8:56:37", "remaining_time": "1:53:19"}
+{"current_steps": 162, "total_steps": 195, "loss": 0.4322, "lr": 9.028101739513406e-07, "epoch": 2.4854614412136535, "percentage": 83.08, "elapsed_time": "8:59:38", "remaining_time": "1:49:55"}
+{"current_steps": 163, "total_steps": 195, "loss": 0.403, "lr": 8.520256971408453e-07, "epoch": 2.5006321112515804, "percentage": 83.59, "elapsed_time": "9:03:08", "remaining_time": "1:46:37"}
+{"current_steps": 164, "total_steps": 195, "loss": 0.4441, "lr": 8.025779637096138e-07, "epoch": 2.5158027812895067, "percentage": 84.1, "elapsed_time": "9:06:37", "remaining_time": "1:43:19"}
+{"current_steps": 165, "total_steps": 195, "loss": 0.4202, "lr": 7.544829088890326e-07, "epoch": 2.5309734513274336, "percentage": 84.62, "elapsed_time": "9:09:45", "remaining_time": "1:39:57"}
+{"current_steps": 166, "total_steps": 195, "loss": 0.385, "lr": 7.077560319906696e-07, "epoch": 2.5461441213653604, "percentage": 85.13, "elapsed_time": "9:12:59", "remaining_time": "1:36:36"}
+{"current_steps": 167, "total_steps": 195, "loss": 0.4306, "lr": 6.624123914114122e-07, "epoch": 2.561314791403287, "percentage": 85.64, "elapsed_time": "9:16:17", "remaining_time": "1:33:16"}
+{"current_steps": 168, "total_steps": 195, "loss": 0.4068, "lr": 6.184665997806832e-07, "epoch": 2.5764854614412136, "percentage": 86.15, "elapsed_time": "9:19:33", "remaining_time": "1:29:55"}
+{"current_steps": 169, "total_steps": 195, "loss": 0.4043, "lr": 5.759328192513075e-07, "epoch": 2.5916561314791404, "percentage": 86.67, "elapsed_time": "9:22:35", "remaining_time": "1:26:33"}
+{"current_steps": 170, "total_steps": 195, "loss": 0.3979, "lr": 5.348247569355736e-07, "epoch": 2.606826801517067, "percentage": 87.18, "elapsed_time": "9:26:01", "remaining_time": "1:23:14"}
+{"current_steps": 171, "total_steps": 195, "loss": 0.4319, "lr": 4.951556604879049e-07, "epoch": 2.6219974715549936, "percentage": 87.69, "elapsed_time": "9:29:11", "remaining_time": "1:19:53"}
+{"current_steps": 172, "total_steps": 195, "loss": 0.3562, "lr": 4.569383138356276e-07, "epoch": 2.6371681415929205, "percentage": 88.21, "elapsed_time": "9:32:38", "remaining_time": "1:16:34"}
+{"current_steps": 173, "total_steps": 195, "loss": 0.446, "lr": 4.201850330591678e-07, "epoch": 2.6523388116308473, "percentage": 88.72, "elapsed_time": "9:35:47", "remaining_time": "1:13:13"}
+{"current_steps": 174, "total_steps": 195, "loss": 0.4152, "lr": 3.8490766242301356e-07, "epoch": 2.6675094816687737, "percentage": 89.23, "elapsed_time": "9:38:58", "remaining_time": "1:09:52"}
+{"current_steps": 175, "total_steps": 195, "loss": 0.4524, "lr": 3.511175705587433e-07, "epoch": 2.6826801517067005, "percentage": 89.74, "elapsed_time": "9:42:50", "remaining_time": "1:06:36"}
+{"current_steps": 176, "total_steps": 195, "loss": 0.4194, "lr": 3.18825646801314e-07, "epoch": 2.697850821744627, "percentage": 90.26, "elapsed_time": "9:46:17", "remaining_time": "1:03:17"}
+{"current_steps": 177, "total_steps": 195, "loss": 0.422, "lr": 2.8804229767982637e-07, "epoch": 2.7130214917825537, "percentage": 90.77, "elapsed_time": "9:49:50", "remaining_time": "0:59:58"}
+{"current_steps": 178, "total_steps": 195, "loss": 0.3963, "lr": 2.587774435638679e-07, "epoch": 2.7281921618204805, "percentage": 91.28, "elapsed_time": "9:53:12", "remaining_time": "0:56:39"}
+{"current_steps": 179, "total_steps": 195, "loss": 0.4196, "lr": 2.3104051546654016e-07, "epoch": 2.7433628318584073, "percentage": 91.79, "elapsed_time": "9:56:35", "remaining_time": "0:53:19"}
+{"current_steps": 180, "total_steps": 195, "loss": 0.3744, "lr": 2.0484045200517222e-07, "epoch": 2.7585335018963337, "percentage": 92.31, "elapsed_time": "9:59:56", "remaining_time": "0:49:59"}
+{"current_steps": 181, "total_steps": 195, "loss": 0.4358, "lr": 1.801856965207338e-07, "epoch": 2.7737041719342606, "percentage": 92.82, "elapsed_time": "10:03:09", "remaining_time": "0:46:39"}
+{"current_steps": 182, "total_steps": 195, "loss": 0.3991, "lr": 1.5708419435684463e-07, "epoch": 2.788874841972187, "percentage": 93.33, "elapsed_time": "10:06:10", "remaining_time": "0:43:17"}
+{"current_steps": 183, "total_steps": 195, "loss": 0.4408, "lr": 1.3554339029927532e-07, "epoch": 2.8040455120101138, "percentage": 93.85, "elapsed_time": "10:10:00", "remaining_time": "0:40:00"}
+{"current_steps": 184, "total_steps": 195, "loss": 0.4113, "lr": 1.1557022617676217e-07, "epoch": 2.8192161820480406, "percentage": 94.36, "elapsed_time": "10:12:54", "remaining_time": "0:36:38"}
+{"current_steps": 185, "total_steps": 195, "loss": 0.4321, "lr": 9.717113862389993e-08, "epoch": 2.834386852085967, "percentage": 94.87, "elapsed_time": "10:15:48", "remaining_time": "0:33:17"}
+{"current_steps": 186, "total_steps": 195, "loss": 0.383, "lr": 8.035205700685167e-08, "epoch": 2.849557522123894, "percentage": 95.38, "elapsed_time": "10:19:13", "remaining_time": "0:29:57"}
+{"current_steps": 187, "total_steps": 195, "loss": 0.4215, "lr": 6.511840151252169e-08, "epoch": 2.8647281921618206, "percentage": 95.9, "elapsed_time": "10:22:02", "remaining_time": "0:26:36"}
+{"current_steps": 188, "total_steps": 195, "loss": 0.4055, "lr": 5.1475081401825553e-08, "epoch": 2.879898862199747, "percentage": 96.41, "elapsed_time": "10:25:31", "remaining_time": "0:23:17"}
+{"current_steps": 189, "total_steps": 195, "loss": 0.416, "lr": 3.9426493427611177e-08, "epoch": 2.895069532237674, "percentage": 96.92, "elapsed_time": "10:28:56", "remaining_time": "0:19:57"}
+{"current_steps": 190, "total_steps": 195, "loss": 0.4056, "lr": 2.8976520417742794e-08, "epoch": 2.9102402022756007, "percentage": 97.44, "elapsed_time": "10:32:11", "remaining_time": "0:16:38"}
+{"current_steps": 191, "total_steps": 195, "loss": 0.4114, "lr": 2.012853002380466e-08, "epoch": 2.925410872313527, "percentage": 97.95, "elapsed_time": "10:35:51", "remaining_time": "0:13:18"}
+{"current_steps": 192, "total_steps": 195, "loss": 0.3915, "lr": 1.2885373635829756e-08, "epoch": 2.940581542351454, "percentage": 98.46, "elapsed_time": "10:39:11", "remaining_time": "0:09:59"}
+{"current_steps": 193, "total_steps": 195, "loss": 0.4121, "lr": 7.249385463395375e-09, "epoch": 2.9557522123893807, "percentage": 98.97, "elapsed_time": "10:42:40", "remaining_time": "0:06:39"}
+{"current_steps": 194, "total_steps": 195, "loss": 0.3977, "lr": 3.2223817833931803e-09, "epoch": 2.970922882427307, "percentage": 99.49, "elapsed_time": "10:45:59", "remaining_time": "0:03:19"}
+{"current_steps": 195, "total_steps": 195, "loss": 0.407, "lr": 8.056603547090813e-10, "epoch": 2.986093552465234, "percentage": 100.0, "elapsed_time": "10:48:58", "remaining_time": "0:00:00"}
+{"current_steps": 195, "total_steps": 195, "epoch": 2.986093552465234, "percentage": 100.0, "elapsed_time": "10:51:49", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66615377e8ae8671065f440a7b04c6cf61f3bae6b39fff37492be2681aafdfd5
+size 8120