Training in progress, step 200

.gitattributes

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

added_tokens.json

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

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 48,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:284813b793c38081d4c9a1c92b0f6f9400be7e4336029a7e9b53aaf766876236
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac3f841225a72d3473735a825f2699a2c984e8123756cdf108703a29e650a08
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1606cbeae382859892871a35f9a5599a4c5cb93e0d46bdf2a322e113a3146434
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc93a8f228b65408c98c95670e7085cdd0759fc95c102e0fdd5f1a9e08b5d9f
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf593544a6b9bcae1227176f7c98e1c7fad15e3372b10d8ae3138c8894074721
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a0eb72fa1d9b006d5b2fd21c4f57d40fe29550d041500e63047e39cc4dc94b
+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 +1,203 @@
+{"current_steps": 1, "total_steps": 288, "loss": 0.7479, "lr": 0.0, "epoch": 0.010353753235547885, "percentage": 0.35, "elapsed_time": "0:02:13", "remaining_time": "10:37:16"}
+{"current_steps": 2, "total_steps": 288, "loss": 0.732, "lr": 3.4482758620689656e-07, "epoch": 0.02070750647109577, "percentage": 0.69, "elapsed_time": "0:04:21", "remaining_time": "10:23:50"}
+{"current_steps": 3, "total_steps": 288, "loss": 0.7576, "lr": 6.896551724137931e-07, "epoch": 0.031061259706643658, "percentage": 1.04, "elapsed_time": "0:06:26", "remaining_time": "10:12:09"}
+{"current_steps": 4, "total_steps": 288, "loss": 0.7226, "lr": 1.0344827586206898e-06, "epoch": 0.04141501294219154, "percentage": 1.39, "elapsed_time": "0:08:31", "remaining_time": "10:04:59"}
+{"current_steps": 5, "total_steps": 288, "loss": 0.7759, "lr": 1.3793103448275862e-06, "epoch": 0.05176876617773943, "percentage": 1.74, "elapsed_time": "0:10:36", "remaining_time": "10:00:23"}
+{"current_steps": 6, "total_steps": 288, "loss": 0.7468, "lr": 1.724137931034483e-06, "epoch": 0.062122519413287315, "percentage": 2.08, "elapsed_time": "0:12:37", "remaining_time": "9:53:29"}
+{"current_steps": 7, "total_steps": 288, "loss": 0.7563, "lr": 2.0689655172413796e-06, "epoch": 0.0724762726488352, "percentage": 2.43, "elapsed_time": "0:14:41", "remaining_time": "9:50:00"}
+{"current_steps": 8, "total_steps": 288, "loss": 0.7695, "lr": 2.4137931034482762e-06, "epoch": 0.08283002588438308, "percentage": 2.78, "elapsed_time": "0:16:38", "remaining_time": "9:42:42"}
+{"current_steps": 9, "total_steps": 288, "loss": 0.7124, "lr": 2.7586206896551725e-06, "epoch": 0.09318377911993098, "percentage": 3.12, "elapsed_time": "0:18:40", "remaining_time": "9:39:02"}
+{"current_steps": 10, "total_steps": 288, "loss": 0.7115, "lr": 3.103448275862069e-06, "epoch": 0.10353753235547886, "percentage": 3.47, "elapsed_time": "0:20:53", "remaining_time": "9:40:59"}
+{"current_steps": 11, "total_steps": 288, "loss": 0.6389, "lr": 3.448275862068966e-06, "epoch": 0.11389128559102675, "percentage": 3.82, "elapsed_time": "0:23:05", "remaining_time": "9:41:26"}
+{"current_steps": 12, "total_steps": 288, "loss": 0.6615, "lr": 3.793103448275862e-06, "epoch": 0.12424503882657463, "percentage": 4.17, "elapsed_time": "0:25:21", "remaining_time": "9:43:18"}
+{"current_steps": 13, "total_steps": 288, "loss": 0.6583, "lr": 4.137931034482759e-06, "epoch": 0.13459879206212252, "percentage": 4.51, "elapsed_time": "0:27:57", "remaining_time": "9:51:22"}
+{"current_steps": 14, "total_steps": 288, "loss": 0.6128, "lr": 4.482758620689656e-06, "epoch": 0.1449525452976704, "percentage": 4.86, "elapsed_time": "0:29:56", "remaining_time": "9:46:09"}
+{"current_steps": 15, "total_steps": 288, "loss": 0.6433, "lr": 4.8275862068965525e-06, "epoch": 0.15530629853321828, "percentage": 5.21, "elapsed_time": "0:31:54", "remaining_time": "9:40:44"}
+{"current_steps": 16, "total_steps": 288, "loss": 0.639, "lr": 5.172413793103449e-06, "epoch": 0.16566005176876616, "percentage": 5.56, "elapsed_time": "0:33:54", "remaining_time": "9:36:27"}
+{"current_steps": 17, "total_steps": 288, "loss": 0.6646, "lr": 5.517241379310345e-06, "epoch": 0.17601380500431407, "percentage": 5.9, "elapsed_time": "0:35:54", "remaining_time": "9:32:26"}
+{"current_steps": 18, "total_steps": 288, "loss": 0.617, "lr": 5.862068965517242e-06, "epoch": 0.18636755823986195, "percentage": 6.25, "elapsed_time": "0:37:53", "remaining_time": "9:28:22"}
+{"current_steps": 19, "total_steps": 288, "loss": 0.599, "lr": 6.206896551724138e-06, "epoch": 0.19672131147540983, "percentage": 6.6, "elapsed_time": "0:40:03", "remaining_time": "9:27:15"}
+{"current_steps": 20, "total_steps": 288, "loss": 0.6, "lr": 6.551724137931035e-06, "epoch": 0.2070750647109577, "percentage": 6.94, "elapsed_time": "0:42:00", "remaining_time": "9:22:48"}
+{"current_steps": 21, "total_steps": 288, "loss": 0.505, "lr": 6.896551724137932e-06, "epoch": 0.21742881794650562, "percentage": 7.29, "elapsed_time": "0:44:02", "remaining_time": "9:20:02"}
+{"current_steps": 22, "total_steps": 288, "loss": 0.5636, "lr": 7.241379310344828e-06, "epoch": 0.2277825711820535, "percentage": 7.64, "elapsed_time": "0:46:08", "remaining_time": "9:17:57"}
+{"current_steps": 23, "total_steps": 288, "loss": 0.5808, "lr": 7.586206896551724e-06, "epoch": 0.23813632441760138, "percentage": 7.99, "elapsed_time": "0:48:08", "remaining_time": "9:14:44"}
+{"current_steps": 24, "total_steps": 288, "loss": 0.617, "lr": 7.93103448275862e-06, "epoch": 0.24849007765314926, "percentage": 8.33, "elapsed_time": "0:50:08", "remaining_time": "9:11:36"}
+{"current_steps": 25, "total_steps": 288, "loss": 0.6029, "lr": 8.275862068965518e-06, "epoch": 0.25884383088869717, "percentage": 8.68, "elapsed_time": "0:52:19", "remaining_time": "9:10:25"}
+{"current_steps": 26, "total_steps": 288, "loss": 0.5683, "lr": 8.620689655172414e-06, "epoch": 0.26919758412424505, "percentage": 9.03, "elapsed_time": "0:54:19", "remaining_time": "9:07:22"}
+{"current_steps": 27, "total_steps": 288, "loss": 0.5317, "lr": 8.965517241379312e-06, "epoch": 0.27955133735979293, "percentage": 9.38, "elapsed_time": "0:56:19", "remaining_time": "9:04:23"}
+{"current_steps": 28, "total_steps": 288, "loss": 0.5543, "lr": 9.310344827586207e-06, "epoch": 0.2899050905953408, "percentage": 9.72, "elapsed_time": "0:58:15", "remaining_time": "9:00:55"}
+{"current_steps": 29, "total_steps": 288, "loss": 0.5266, "lr": 9.655172413793105e-06, "epoch": 0.3002588438308887, "percentage": 10.07, "elapsed_time": "1:00:23", "remaining_time": "8:59:24"}
+{"current_steps": 30, "total_steps": 288, "loss": 0.5046, "lr": 1e-05, "epoch": 0.31061259706643657, "percentage": 10.42, "elapsed_time": "1:02:22", "remaining_time": "8:56:27"}
+{"current_steps": 31, "total_steps": 288, "loss": 0.557, "lr": 9.999632180371776e-06, "epoch": 0.32096635030198445, "percentage": 10.76, "elapsed_time": "1:04:22", "remaining_time": "8:53:39"}
+{"current_steps": 32, "total_steps": 288, "loss": 0.4942, "lr": 9.998528775603612e-06, "epoch": 0.33132010353753233, "percentage": 11.11, "elapsed_time": "1:06:17", "remaining_time": "8:50:17"}
+{"current_steps": 33, "total_steps": 288, "loss": 0.5955, "lr": 9.996689948037081e-06, "epoch": 0.34167385677308026, "percentage": 11.46, "elapsed_time": "1:08:18", "remaining_time": "8:47:52"}
+{"current_steps": 34, "total_steps": 288, "loss": 0.5172, "lr": 9.994115968214933e-06, "epoch": 0.35202761000862814, "percentage": 11.81, "elapsed_time": "1:10:20", "remaining_time": "8:45:28"}
+{"current_steps": 35, "total_steps": 288, "loss": 0.4873, "lr": 9.990807214841288e-06, "epoch": 0.362381363244176, "percentage": 12.15, "elapsed_time": "1:12:14", "remaining_time": "8:42:15"}
+{"current_steps": 36, "total_steps": 288, "loss": 0.4851, "lr": 9.98676417472592e-06, "epoch": 0.3727351164797239, "percentage": 12.5, "elapsed_time": "1:14:11", "remaining_time": "8:39:19"}
+{"current_steps": 37, "total_steps": 288, "loss": 0.4837, "lr": 9.981987442712634e-06, "epoch": 0.3830888697152718, "percentage": 12.85, "elapsed_time": "1:16:08", "remaining_time": "8:36:29"}
+{"current_steps": 38, "total_steps": 288, "loss": 0.4959, "lr": 9.976477721591746e-06, "epoch": 0.39344262295081966, "percentage": 13.19, "elapsed_time": "1:18:22", "remaining_time": "8:35:35"}
+{"current_steps": 39, "total_steps": 288, "loss": 0.5141, "lr": 9.97023582199669e-06, "epoch": 0.40379637618636754, "percentage": 13.54, "elapsed_time": "1:20:24", "remaining_time": "8:33:22"}
+{"current_steps": 40, "total_steps": 288, "loss": 0.5679, "lr": 9.963262662284735e-06, "epoch": 0.4141501294219154, "percentage": 13.89, "elapsed_time": "1:22:20", "remaining_time": "8:30:31"}
+{"current_steps": 41, "total_steps": 288, "loss": 0.4824, "lr": 9.955559268401893e-06, "epoch": 0.4245038826574633, "percentage": 14.24, "elapsed_time": "1:24:19", "remaining_time": "8:27:58"}
+{"current_steps": 42, "total_steps": 288, "loss": 0.5263, "lr": 9.947126773731949e-06, "epoch": 0.43485763589301124, "percentage": 14.58, "elapsed_time": "1:26:13", "remaining_time": "8:25:03"}
+{"current_steps": 43, "total_steps": 288, "loss": 0.55, "lr": 9.937966418929725e-06, "epoch": 0.4452113891285591, "percentage": 14.93, "elapsed_time": "1:28:10", "remaining_time": "8:22:25"}
+{"current_steps": 44, "total_steps": 288, "loss": 0.4922, "lr": 9.928079551738542e-06, "epoch": 0.455565142364107, "percentage": 15.28, "elapsed_time": "1:30:07", "remaining_time": "8:19:44"}
+{"current_steps": 45, "total_steps": 288, "loss": 0.4621, "lr": 9.917467626791925e-06, "epoch": 0.4659188955996549, "percentage": 15.62, "elapsed_time": "1:32:12", "remaining_time": "8:17:56"}
+{"current_steps": 46, "total_steps": 288, "loss": 0.5049, "lr": 9.90613220539959e-06, "epoch": 0.47627264883520276, "percentage": 15.97, "elapsed_time": "1:34:14", "remaining_time": "8:15:49"}
+{"current_steps": 47, "total_steps": 288, "loss": 0.4702, "lr": 9.89407495531773e-06, "epoch": 0.48662640207075064, "percentage": 16.32, "elapsed_time": "1:36:16", "remaining_time": "8:13:40"}
+{"current_steps": 48, "total_steps": 288, "loss": 0.4999, "lr": 9.881297650503641e-06, "epoch": 0.4969801553062985, "percentage": 16.67, "elapsed_time": "1:38:11", "remaining_time": "8:10:55"}
+{"current_steps": 49, "total_steps": 288, "loss": 0.5259, "lr": 9.867802170854724e-06, "epoch": 0.5073339085418465, "percentage": 17.01, "elapsed_time": "1:40:08", "remaining_time": "8:08:24"}
+{"current_steps": 50, "total_steps": 288, "loss": 0.4437, "lr": 9.853590501931905e-06, "epoch": 0.5176876617773943, "percentage": 17.36, "elapsed_time": "1:42:04", "remaining_time": "8:05:51"}
+{"current_steps": 51, "total_steps": 288, "loss": 0.5207, "lr": 9.838664734667496e-06, "epoch": 0.5280414150129422, "percentage": 17.71, "elapsed_time": "1:43:59", "remaining_time": "8:03:16"}
+{"current_steps": 52, "total_steps": 288, "loss": 0.5003, "lr": 9.82302706505756e-06, "epoch": 0.5383951682484901, "percentage": 18.06, "elapsed_time": "1:46:02", "remaining_time": "8:01:14"}
+{"current_steps": 53, "total_steps": 288, "loss": 0.4519, "lr": 9.806679793838829e-06, "epoch": 0.548748921484038, "percentage": 18.4, "elapsed_time": "1:47:57", "remaining_time": "7:58:42"}
+{"current_steps": 54, "total_steps": 288, "loss": 0.5469, "lr": 9.78962532615019e-06, "epoch": 0.5591026747195859, "percentage": 18.75, "elapsed_time": "1:49:56", "remaining_time": "7:56:24"}
+{"current_steps": 55, "total_steps": 288, "loss": 0.5073, "lr": 9.771866171178832e-06, "epoch": 0.5694564279551337, "percentage": 19.1, "elapsed_time": "1:51:52", "remaining_time": "7:53:55"}
+{"current_steps": 56, "total_steps": 288, "loss": 0.4626, "lr": 9.753404941791063e-06, "epoch": 0.5798101811906816, "percentage": 19.44, "elapsed_time": "1:53:49", "remaining_time": "7:51:32"}
+{"current_steps": 57, "total_steps": 288, "loss": 0.5279, "lr": 9.734244354147897e-06, "epoch": 0.5901639344262295, "percentage": 19.79, "elapsed_time": "1:55:46", "remaining_time": "7:49:10"}
+{"current_steps": 58, "total_steps": 288, "loss": 0.5055, "lr": 9.714387227305422e-06, "epoch": 0.6005176876617774, "percentage": 20.14, "elapsed_time": "1:57:41", "remaining_time": "7:46:43"}
+{"current_steps": 59, "total_steps": 288, "loss": 0.4659, "lr": 9.693836482800044e-06, "epoch": 0.6108714408973253, "percentage": 20.49, "elapsed_time": "1:59:38", "remaining_time": "7:44:22"}
+{"current_steps": 60, "total_steps": 288, "loss": 0.4821, "lr": 9.672595144218646e-06, "epoch": 0.6212251941328731, "percentage": 20.83, "elapsed_time": "2:01:40", "remaining_time": "7:42:20"}
+{"current_steps": 61, "total_steps": 288, "loss": 0.4258, "lr": 9.65066633675373e-06, "epoch": 0.631578947368421, "percentage": 21.18, "elapsed_time": "2:03:41", "remaining_time": "7:40:17"}
+{"current_steps": 62, "total_steps": 288, "loss": 0.4869, "lr": 9.628053286743619e-06, "epoch": 0.6419327006039689, "percentage": 21.53, "elapsed_time": "2:05:35", "remaining_time": "7:37:47"}
+{"current_steps": 63, "total_steps": 288, "loss": 0.4904, "lr": 9.604759321197775e-06, "epoch": 0.6522864538395168, "percentage": 21.88, "elapsed_time": "2:07:32", "remaining_time": "7:35:29"}
+{"current_steps": 64, "total_steps": 288, "loss": 0.5157, "lr": 9.580787867307293e-06, "epoch": 0.6626402070750647, "percentage": 22.22, "elapsed_time": "2:09:31", "remaining_time": "7:33:19"}
+{"current_steps": 65, "total_steps": 288, "loss": 0.4694, "lr": 9.55614245194068e-06, "epoch": 0.6729939603106126, "percentage": 22.57, "elapsed_time": "2:11:29", "remaining_time": "7:31:08"}
+{"current_steps": 66, "total_steps": 288, "loss": 0.4878, "lr": 9.53082670112494e-06, "epoch": 0.6833477135461605, "percentage": 22.92, "elapsed_time": "2:13:30", "remaining_time": "7:29:03"}
+{"current_steps": 67, "total_steps": 288, "loss": 0.4975, "lr": 9.504844339512096e-06, "epoch": 0.6937014667817084, "percentage": 23.26, "elapsed_time": "2:15:30", "remaining_time": "7:26:57"}
+{"current_steps": 68, "total_steps": 288, "loss": 0.4884, "lr": 9.478199189831184e-06, "epoch": 0.7040552200172563, "percentage": 23.61, "elapsed_time": "2:17:29", "remaining_time": "7:24:48"}
+{"current_steps": 69, "total_steps": 288, "loss": 0.4872, "lr": 9.450895172325822e-06, "epoch": 0.7144089732528042, "percentage": 23.96, "elapsed_time": "2:19:46", "remaining_time": "7:23:38"}
+{"current_steps": 70, "total_steps": 288, "loss": 0.4751, "lr": 9.422936304177439e-06, "epoch": 0.724762726488352, "percentage": 24.31, "elapsed_time": "2:21:54", "remaining_time": "7:21:55"}
+{"current_steps": 71, "total_steps": 288, "loss": 0.4412, "lr": 9.394326698914229e-06, "epoch": 0.7351164797238999, "percentage": 24.65, "elapsed_time": "2:23:50", "remaining_time": "7:19:37"}
+{"current_steps": 72, "total_steps": 288, "loss": 0.4475, "lr": 9.365070565805941e-06, "epoch": 0.7454702329594478, "percentage": 25.0, "elapsed_time": "2:25:48", "remaining_time": "7:17:25"}
+{"current_steps": 73, "total_steps": 288, "loss": 0.4977, "lr": 9.335172209244577e-06, "epoch": 0.7558239861949957, "percentage": 25.35, "elapsed_time": "2:27:43", "remaining_time": "7:15:05"}
+{"current_steps": 74, "total_steps": 288, "loss": 0.4861, "lr": 9.304636028111093e-06, "epoch": 0.7661777394305436, "percentage": 25.69, "elapsed_time": "2:29:42", "remaining_time": "7:12:57"}
+{"current_steps": 75, "total_steps": 288, "loss": 0.4793, "lr": 9.273466515128209e-06, "epoch": 0.7765314926660914, "percentage": 26.04, "elapsed_time": "2:31:40", "remaining_time": "7:10:45"}
+{"current_steps": 76, "total_steps": 288, "loss": 0.4584, "lr": 9.241668256199392e-06, "epoch": 0.7868852459016393, "percentage": 26.39, "elapsed_time": "2:33:36", "remaining_time": "7:08:28"}
+{"current_steps": 77, "total_steps": 288, "loss": 0.4829, "lr": 9.209245929734156e-06, "epoch": 0.7972389991371872, "percentage": 26.74, "elapsed_time": "2:35:35", "remaining_time": "7:06:22"}
+{"current_steps": 78, "total_steps": 288, "loss": 0.4953, "lr": 9.176204305959727e-06, "epoch": 0.8075927523727351, "percentage": 27.08, "elapsed_time": "2:37:31", "remaining_time": "7:04:07"}
+{"current_steps": 79, "total_steps": 288, "loss": 0.4603, "lr": 9.142548246219212e-06, "epoch": 0.817946505608283, "percentage": 27.43, "elapsed_time": "2:39:27", "remaining_time": "7:01:50"}
+{"current_steps": 80, "total_steps": 288, "loss": 0.4412, "lr": 9.108282702256366e-06, "epoch": 0.8283002588438308, "percentage": 27.78, "elapsed_time": "2:41:32", "remaining_time": "7:00:01"}
+{"current_steps": 81, "total_steps": 288, "loss": 0.4558, "lr": 9.073412715487045e-06, "epoch": 0.8386540120793787, "percentage": 28.12, "elapsed_time": "2:43:29", "remaining_time": "6:57:49"}
+{"current_steps": 82, "total_steps": 288, "loss": 0.452, "lr": 9.037943416257475e-06, "epoch": 0.8490077653149266, "percentage": 28.47, "elapsed_time": "2:45:24", "remaining_time": "6:55:32"}
+{"current_steps": 83, "total_steps": 288, "loss": 0.4715, "lr": 9.001880023089442e-06, "epoch": 0.8593615185504746, "percentage": 28.82, "elapsed_time": "2:47:24", "remaining_time": "6:53:28"}
+{"current_steps": 84, "total_steps": 288, "loss": 0.4535, "lr": 8.96522784191249e-06, "epoch": 0.8697152717860225, "percentage": 29.17, "elapsed_time": "2:49:22", "remaining_time": "6:51:19"}
+{"current_steps": 85, "total_steps": 288, "loss": 0.4342, "lr": 8.927992265283282e-06, "epoch": 0.8800690250215704, "percentage": 29.51, "elapsed_time": "2:51:18", "remaining_time": "6:49:08"}
+{"current_steps": 86, "total_steps": 288, "loss": 0.4547, "lr": 8.890178771592198e-06, "epoch": 0.8904227782571182, "percentage": 29.86, "elapsed_time": "2:53:18", "remaining_time": "6:47:04"}
+{"current_steps": 87, "total_steps": 288, "loss": 0.4548, "lr": 8.851792924257316e-06, "epoch": 0.9007765314926661, "percentage": 30.21, "elapsed_time": "2:55:13", "remaining_time": "6:44:50"}
+{"current_steps": 88, "total_steps": 288, "loss": 0.4541, "lr": 8.812840370905872e-06, "epoch": 0.911130284728214, "percentage": 30.56, "elapsed_time": "2:57:11", "remaining_time": "6:42:42"}
+{"current_steps": 89, "total_steps": 288, "loss": 0.497, "lr": 8.773326842543348e-06, "epoch": 0.9214840379637619, "percentage": 30.9, "elapsed_time": "2:59:15", "remaining_time": "6:40:48"}
+{"current_steps": 90, "total_steps": 288, "loss": 0.4835, "lr": 8.733258152710262e-06, "epoch": 0.9318377911993098, "percentage": 31.25, "elapsed_time": "3:01:09", "remaining_time": "6:38:33"}
+{"current_steps": 91, "total_steps": 288, "loss": 0.4916, "lr": 8.692640196626859e-06, "epoch": 0.9421915444348576, "percentage": 31.6, "elapsed_time": "3:03:17", "remaining_time": "6:36:48"}
+{"current_steps": 92, "total_steps": 288, "loss": 0.4552, "lr": 8.651478950325739e-06, "epoch": 0.9525452976704055, "percentage": 31.94, "elapsed_time": "3:05:20", "remaining_time": "6:34:51"}
+{"current_steps": 93, "total_steps": 288, "loss": 0.4602, "lr": 8.609780469772623e-06, "epoch": 0.9628990509059534, "percentage": 32.29, "elapsed_time": "3:07:17", "remaining_time": "6:32:42"}
+{"current_steps": 94, "total_steps": 288, "loss": 0.4887, "lr": 8.567550889975362e-06, "epoch": 0.9732528041415013, "percentage": 32.64, "elapsed_time": "3:09:14", "remaining_time": "6:30:34"}
+{"current_steps": 95, "total_steps": 288, "loss": 0.4663, "lr": 8.524796424081291e-06, "epoch": 0.9836065573770492, "percentage": 32.99, "elapsed_time": "3:11:24", "remaining_time": "6:28:51"}
+{"current_steps": 96, "total_steps": 288, "loss": 0.476, "lr": 8.481523362463111e-06, "epoch": 0.993960310612597, "percentage": 33.33, "elapsed_time": "3:13:19", "remaining_time": "6:26:38"}
+{"current_steps": 97, "total_steps": 288, "loss": 0.7575, "lr": 8.437738071793394e-06, "epoch": 1.010353753235548, "percentage": 33.68, "elapsed_time": "3:15:57", "remaining_time": "6:25:50"}
+{"current_steps": 98, "total_steps": 288, "loss": 0.3624, "lr": 8.393446994107876e-06, "epoch": 1.0207075064710958, "percentage": 34.03, "elapsed_time": "3:18:08", "remaining_time": "6:24:08"}
+{"current_steps": 99, "total_steps": 288, "loss": 0.3567, "lr": 8.348656645857648e-06, "epoch": 1.0310612597066438, "percentage": 34.38, "elapsed_time": "3:20:04", "remaining_time": "6:21:58"}
+{"current_steps": 100, "total_steps": 288, "loss": 0.404, "lr": 8.303373616950408e-06, "epoch": 1.0414150129421915, "percentage": 34.72, "elapsed_time": "3:22:08", "remaining_time": "6:20:02"}
+{"current_steps": 101, "total_steps": 288, "loss": 0.358, "lr": 8.257604569780898e-06, "epoch": 1.0517687661777395, "percentage": 35.07, "elapsed_time": "3:24:08", "remaining_time": "6:17:57"}
+{"current_steps": 102, "total_steps": 288, "loss": 0.363, "lr": 8.21135623825068e-06, "epoch": 1.0621225194132873, "percentage": 35.42, "elapsed_time": "3:26:04", "remaining_time": "6:15:46"}
+{"current_steps": 103, "total_steps": 288, "loss": 0.3619, "lr": 8.164635426777404e-06, "epoch": 1.0724762726488353, "percentage": 35.76, "elapsed_time": "3:28:00", "remaining_time": "6:13:37"}
+{"current_steps": 104, "total_steps": 288, "loss": 0.3751, "lr": 8.117449009293668e-06, "epoch": 1.082830025884383, "percentage": 36.11, "elapsed_time": "3:29:54", "remaining_time": "6:11:23"}
+{"current_steps": 105, "total_steps": 288, "loss": 0.4263, "lr": 8.069803928235689e-06, "epoch": 1.093183779119931, "percentage": 36.46, "elapsed_time": "3:31:51", "remaining_time": "6:09:14"}
+{"current_steps": 106, "total_steps": 288, "loss": 0.3849, "lr": 8.021707193521865e-06, "epoch": 1.1035375323554788, "percentage": 36.81, "elapsed_time": "3:33:49", "remaining_time": "6:07:07"}
+{"current_steps": 107, "total_steps": 288, "loss": 0.3909, "lr": 7.973165881521435e-06, "epoch": 1.1138912855910268, "percentage": 37.15, "elapsed_time": "3:35:44", "remaining_time": "6:04:57"}
+{"current_steps": 108, "total_steps": 288, "loss": 0.372, "lr": 7.924187134013323e-06, "epoch": 1.1242450388265746, "percentage": 37.5, "elapsed_time": "3:37:40", "remaining_time": "6:02:47"}
+{"current_steps": 109, "total_steps": 288, "loss": 0.3604, "lr": 7.874778157135416e-06, "epoch": 1.1345987920621226, "percentage": 37.85, "elapsed_time": "3:39:38", "remaining_time": "6:00:42"}
+{"current_steps": 110, "total_steps": 288, "loss": 0.344, "lr": 7.824946220324313e-06, "epoch": 1.1449525452976703, "percentage": 38.19, "elapsed_time": "3:41:36", "remaining_time": "5:58:36"}
+{"current_steps": 111, "total_steps": 288, "loss": 0.3529, "lr": 7.774698655245802e-06, "epoch": 1.1553062985332183, "percentage": 38.54, "elapsed_time": "3:43:31", "remaining_time": "5:56:26"}
+{"current_steps": 112, "total_steps": 288, "loss": 0.3796, "lr": 7.724042854716169e-06, "epoch": 1.165660051768766, "percentage": 38.89, "elapsed_time": "3:45:27", "remaining_time": "5:54:17"}
+{"current_steps": 113, "total_steps": 288, "loss": 0.3657, "lr": 7.6729862716145e-06, "epoch": 1.176013805004314, "percentage": 39.24, "elapsed_time": "3:47:22", "remaining_time": "5:52:08"}
+{"current_steps": 114, "total_steps": 288, "loss": 0.3641, "lr": 7.621536417786159e-06, "epoch": 1.186367558239862, "percentage": 39.58, "elapsed_time": "3:49:33", "remaining_time": "5:50:22"}
+{"current_steps": 115, "total_steps": 288, "loss": 0.384, "lr": 7.56970086293759e-06, "epoch": 1.1967213114754098, "percentage": 39.93, "elapsed_time": "3:51:31", "remaining_time": "5:48:17"}
+{"current_steps": 116, "total_steps": 288, "loss": 0.3504, "lr": 7.5174872335226e-06, "epoch": 1.2070750647109576, "percentage": 40.28, "elapsed_time": "3:53:26", "remaining_time": "5:46:07"}
+{"current_steps": 117, "total_steps": 288, "loss": 0.3564, "lr": 7.464903211620291e-06, "epoch": 1.2174288179465056, "percentage": 40.62, "elapsed_time": "3:55:25", "remaining_time": "5:44:05"}
+{"current_steps": 118, "total_steps": 288, "loss": 0.336, "lr": 7.4119565338048195e-06, "epoch": 1.2277825711820536, "percentage": 40.97, "elapsed_time": "3:57:26", "remaining_time": "5:42:04"}
+{"current_steps": 119, "total_steps": 288, "loss": 0.3829, "lr": 7.358654990007123e-06, "epoch": 1.2381363244176014, "percentage": 41.32, "elapsed_time": "3:59:25", "remaining_time": "5:40:01"}
+{"current_steps": 120, "total_steps": 288, "loss": 0.3567, "lr": 7.305006422368811e-06, "epoch": 1.2484900776531493, "percentage": 41.67, "elapsed_time": "4:01:21", "remaining_time": "5:37:54"}
+{"current_steps": 121, "total_steps": 288, "loss": 0.3624, "lr": 7.251018724088367e-06, "epoch": 1.2588438308886971, "percentage": 42.01, "elapsed_time": "4:03:17", "remaining_time": "5:35:46"}
+{"current_steps": 122, "total_steps": 288, "loss": 0.358, "lr": 7.196699838259834e-06, "epoch": 1.269197584124245, "percentage": 42.36, "elapsed_time": "4:05:15", "remaining_time": "5:33:42"}
+{"current_steps": 123, "total_steps": 288, "loss": 0.3766, "lr": 7.142057756704168e-06, "epoch": 1.2795513373597929, "percentage": 42.71, "elapsed_time": "4:07:14", "remaining_time": "5:31:39"}
+{"current_steps": 124, "total_steps": 288, "loss": 0.3702, "lr": 7.087100518793421e-06, "epoch": 1.2899050905953409, "percentage": 43.06, "elapsed_time": "4:09:26", "remaining_time": "5:29:54"}
+{"current_steps": 125, "total_steps": 288, "loss": 0.3891, "lr": 7.031836210267915e-06, "epoch": 1.3002588438308886, "percentage": 43.4, "elapsed_time": "4:11:33", "remaining_time": "5:28:02"}
+{"current_steps": 126, "total_steps": 288, "loss": 0.3843, "lr": 6.976272962046619e-06, "epoch": 1.3106125970664366, "percentage": 43.75, "elapsed_time": "4:13:35", "remaining_time": "5:26:03"}
+{"current_steps": 127, "total_steps": 288, "loss": 0.3673, "lr": 6.920418949030856e-06, "epoch": 1.3209663503019844, "percentage": 44.1, "elapsed_time": "4:15:33", "remaining_time": "5:23:58"}
+{"current_steps": 128, "total_steps": 288, "loss": 0.3498, "lr": 6.864282388901544e-06, "epoch": 1.3313201035375324, "percentage": 44.44, "elapsed_time": "4:17:44", "remaining_time": "5:22:10"}
+{"current_steps": 129, "total_steps": 288, "loss": 0.3577, "lr": 6.807871540910155e-06, "epoch": 1.3416738567730802, "percentage": 44.79, "elapsed_time": "4:19:43", "remaining_time": "5:20:07"}
+{"current_steps": 130, "total_steps": 288, "loss": 0.382, "lr": 6.751194704663544e-06, "epoch": 1.3520276100086281, "percentage": 45.14, "elapsed_time": "4:21:40", "remaining_time": "5:18:02"}
+{"current_steps": 131, "total_steps": 288, "loss": 0.3512, "lr": 6.694260218902845e-06, "epoch": 1.3623813632441761, "percentage": 45.49, "elapsed_time": "4:23:44", "remaining_time": "5:16:04"}
+{"current_steps": 132, "total_steps": 288, "loss": 0.3925, "lr": 6.637076460276612e-06, "epoch": 1.372735116479724, "percentage": 45.83, "elapsed_time": "4:25:40", "remaining_time": "5:13:58"}
+{"current_steps": 133, "total_steps": 288, "loss": 0.3616, "lr": 6.579651842108381e-06, "epoch": 1.3830888697152717, "percentage": 46.18, "elapsed_time": "4:27:37", "remaining_time": "5:11:54"}
+{"current_steps": 134, "total_steps": 288, "loss": 0.3601, "lr": 6.521994813158834e-06, "epoch": 1.3934426229508197, "percentage": 46.53, "elapsed_time": "4:29:42", "remaining_time": "5:09:58"}
+{"current_steps": 135, "total_steps": 288, "loss": 0.3847, "lr": 6.464113856382752e-06, "epoch": 1.4037963761863677, "percentage": 46.88, "elapsed_time": "4:31:38", "remaining_time": "5:07:51"}
+{"current_steps": 136, "total_steps": 288, "loss": 0.3572, "lr": 6.406017487680938e-06, "epoch": 1.4141501294219154, "percentage": 47.22, "elapsed_time": "4:33:33", "remaining_time": "5:05:44"}
+{"current_steps": 137, "total_steps": 288, "loss": 0.3917, "lr": 6.3477142546472836e-06, "epoch": 1.4245038826574632, "percentage": 47.57, "elapsed_time": "4:35:31", "remaining_time": "5:03:41"}
+{"current_steps": 138, "total_steps": 288, "loss": 0.3873, "lr": 6.28921273531119e-06, "epoch": 1.4348576358930112, "percentage": 47.92, "elapsed_time": "4:37:32", "remaining_time": "5:01:40"}
+{"current_steps": 139, "total_steps": 288, "loss": 0.3733, "lr": 6.230521536875494e-06, "epoch": 1.4452113891285592, "percentage": 48.26, "elapsed_time": "4:39:36", "remaining_time": "4:59:43"}
+{"current_steps": 140, "total_steps": 288, "loss": 0.3769, "lr": 6.171649294450113e-06, "epoch": 1.455565142364107, "percentage": 48.61, "elapsed_time": "4:41:34", "remaining_time": "4:57:39"}
+{"current_steps": 141, "total_steps": 288, "loss": 0.3231, "lr": 6.112604669781572e-06, "epoch": 1.465918895599655, "percentage": 48.96, "elapsed_time": "4:43:38", "remaining_time": "4:55:43"}
+{"current_steps": 142, "total_steps": 288, "loss": 0.3191, "lr": 6.053396349978632e-06, "epoch": 1.4762726488352027, "percentage": 49.31, "elapsed_time": "4:45:35", "remaining_time": "4:53:38"}
+{"current_steps": 143, "total_steps": 288, "loss": 0.3905, "lr": 5.994033046234163e-06, "epoch": 1.4866264020707507, "percentage": 49.65, "elapsed_time": "4:47:41", "remaining_time": "4:51:42"}
+{"current_steps": 144, "total_steps": 288, "loss": 0.3678, "lr": 5.934523492543489e-06, "epoch": 1.4969801553062985, "percentage": 50.0, "elapsed_time": "4:49:38", "remaining_time": "4:49:38"}
+{"current_steps": 145, "total_steps": 288, "loss": 0.3716, "lr": 5.874876444419377e-06, "epoch": 1.5073339085418465, "percentage": 50.35, "elapsed_time": "4:51:44", "remaining_time": "4:47:43"}
+{"current_steps": 146, "total_steps": 288, "loss": 0.371, "lr": 5.815100677603854e-06, "epoch": 1.5176876617773942, "percentage": 50.69, "elapsed_time": "4:53:44", "remaining_time": "4:45:41"}
+{"current_steps": 147, "total_steps": 288, "loss": 0.392, "lr": 5.75520498677705e-06, "epoch": 1.5280414150129422, "percentage": 51.04, "elapsed_time": "4:55:39", "remaining_time": "4:43:35"}
+{"current_steps": 148, "total_steps": 288, "loss": 0.3468, "lr": 5.695198184263259e-06, "epoch": 1.5383951682484902, "percentage": 51.39, "elapsed_time": "4:57:38", "remaining_time": "4:41:33"}
+{"current_steps": 149, "total_steps": 288, "loss": 0.3831, "lr": 5.635089098734394e-06, "epoch": 1.548748921484038, "percentage": 51.74, "elapsed_time": "4:59:42", "remaining_time": "4:39:35"}
+{"current_steps": 150, "total_steps": 288, "loss": 0.3618, "lr": 5.574886573911056e-06, "epoch": 1.5591026747195857, "percentage": 52.08, "elapsed_time": "5:01:41", "remaining_time": "4:37:33"}
+{"current_steps": 151, "total_steps": 288, "loss": 0.3432, "lr": 5.514599467261363e-06, "epoch": 1.5694564279551337, "percentage": 52.43, "elapsed_time": "5:03:36", "remaining_time": "4:35:27"}
+{"current_steps": 152, "total_steps": 288, "loss": 0.357, "lr": 5.454236648697776e-06, "epoch": 1.5798101811906817, "percentage": 52.78, "elapsed_time": "5:05:35", "remaining_time": "4:33:25"}
+{"current_steps": 153, "total_steps": 288, "loss": 0.3948, "lr": 5.3938069992720894e-06, "epoch": 1.5901639344262295, "percentage": 53.12, "elapsed_time": "5:07:30", "remaining_time": "4:31:19"}
+{"current_steps": 154, "total_steps": 288, "loss": 0.3607, "lr": 5.333319409868777e-06, "epoch": 1.6005176876617773, "percentage": 53.47, "elapsed_time": "5:09:24", "remaining_time": "4:29:13"}
+{"current_steps": 155, "total_steps": 288, "loss": 0.4089, "lr": 5.272782779896898e-06, "epoch": 1.6108714408973253, "percentage": 53.82, "elapsed_time": "5:11:31", "remaining_time": "4:27:18"}
+{"current_steps": 156, "total_steps": 288, "loss": 0.3829, "lr": 5.212206015980742e-06, "epoch": 1.6212251941328732, "percentage": 54.17, "elapsed_time": "5:13:31", "remaining_time": "4:25:17"}
+{"current_steps": 157, "total_steps": 288, "loss": 0.3695, "lr": 5.151598030649425e-06, "epoch": 1.631578947368421, "percentage": 54.51, "elapsed_time": "5:15:27", "remaining_time": "4:23:13"}
+{"current_steps": 158, "total_steps": 288, "loss": 0.3551, "lr": 5.090967741025599e-06, "epoch": 1.6419327006039688, "percentage": 54.86, "elapsed_time": "5:17:24", "remaining_time": "4:21:09"}
+{"current_steps": 159, "total_steps": 288, "loss": 0.355, "lr": 5.030324067513499e-06, "epoch": 1.6522864538395168, "percentage": 55.21, "elapsed_time": "5:19:23", "remaining_time": "4:19:07"}
+{"current_steps": 160, "total_steps": 288, "loss": 0.4016, "lr": 4.969675932486503e-06, "epoch": 1.6626402070750648, "percentage": 55.56, "elapsed_time": "5:21:22", "remaining_time": "4:17:06"}
+{"current_steps": 161, "total_steps": 288, "loss": 0.3739, "lr": 4.909032258974403e-06, "epoch": 1.6729939603106128, "percentage": 55.9, "elapsed_time": "5:23:18", "remaining_time": "4:15:01"}
+{"current_steps": 162, "total_steps": 288, "loss": 0.3261, "lr": 4.848401969350577e-06, "epoch": 1.6833477135461605, "percentage": 56.25, "elapsed_time": "5:25:13", "remaining_time": "4:12:57"}
+{"current_steps": 163, "total_steps": 288, "loss": 0.3616, "lr": 4.78779398401926e-06, "epoch": 1.6937014667817083, "percentage": 56.6, "elapsed_time": "5:27:08", "remaining_time": "4:10:52"}
+{"current_steps": 164, "total_steps": 288, "loss": 0.3612, "lr": 4.7272172201031055e-06, "epoch": 1.7040552200172563, "percentage": 56.94, "elapsed_time": "5:29:03", "remaining_time": "4:08:47"}
+{"current_steps": 165, "total_steps": 288, "loss": 0.3371, "lr": 4.666680590131225e-06, "epoch": 1.7144089732528043, "percentage": 57.29, "elapsed_time": "5:30:59", "remaining_time": "4:06:44"}
+{"current_steps": 166, "total_steps": 288, "loss": 0.3718, "lr": 4.606193000727913e-06, "epoch": 1.724762726488352, "percentage": 57.64, "elapsed_time": "5:32:58", "remaining_time": "4:04:42"}
+{"current_steps": 167, "total_steps": 288, "loss": 0.3807, "lr": 4.545763351302224e-06, "epoch": 1.7351164797238998, "percentage": 57.99, "elapsed_time": "5:34:53", "remaining_time": "4:02:38"}
+{"current_steps": 168, "total_steps": 288, "loss": 0.4224, "lr": 4.485400532738638e-06, "epoch": 1.7454702329594478, "percentage": 58.33, "elapsed_time": "5:36:51", "remaining_time": "4:00:37"}
+{"current_steps": 169, "total_steps": 288, "loss": 0.3958, "lr": 4.425113426088945e-06, "epoch": 1.7558239861949958, "percentage": 58.68, "elapsed_time": "5:38:47", "remaining_time": "3:58:33"}
+{"current_steps": 170, "total_steps": 288, "loss": 0.3577, "lr": 4.364910901265607e-06, "epoch": 1.7661777394305436, "percentage": 59.03, "elapsed_time": "5:40:43", "remaining_time": "3:56:29"}
+{"current_steps": 171, "total_steps": 288, "loss": 0.3844, "lr": 4.3048018157367435e-06, "epoch": 1.7765314926660913, "percentage": 59.38, "elapsed_time": "5:42:40", "remaining_time": "3:54:27"}
+{"current_steps": 172, "total_steps": 288, "loss": 0.3444, "lr": 4.244795013222951e-06, "epoch": 1.7868852459016393, "percentage": 59.72, "elapsed_time": "5:44:46", "remaining_time": "3:52:31"}
+{"current_steps": 173, "total_steps": 288, "loss": 0.3345, "lr": 4.184899322396147e-06, "epoch": 1.7972389991371873, "percentage": 60.07, "elapsed_time": "5:46:44", "remaining_time": "3:50:29"}
+{"current_steps": 174, "total_steps": 288, "loss": 0.3668, "lr": 4.125123555580624e-06, "epoch": 1.807592752372735, "percentage": 60.42, "elapsed_time": "5:48:44", "remaining_time": "3:48:29"}
+{"current_steps": 175, "total_steps": 288, "loss": 0.3581, "lr": 4.0654765074565125e-06, "epoch": 1.8179465056082829, "percentage": 60.76, "elapsed_time": "5:50:50", "remaining_time": "3:46:32"}
+{"current_steps": 176, "total_steps": 288, "loss": 0.3596, "lr": 4.00596695376584e-06, "epoch": 1.8283002588438308, "percentage": 61.11, "elapsed_time": "5:52:50", "remaining_time": "3:44:31"}
+{"current_steps": 177, "total_steps": 288, "loss": 0.3612, "lr": 3.94660365002137e-06, "epoch": 1.8386540120793788, "percentage": 61.46, "elapsed_time": "5:55:07", "remaining_time": "3:42:42"}
+{"current_steps": 178, "total_steps": 288, "loss": 0.3428, "lr": 3.887395330218429e-06, "epoch": 1.8490077653149266, "percentage": 61.81, "elapsed_time": "5:57:05", "remaining_time": "3:40:40"}
+{"current_steps": 179, "total_steps": 288, "loss": 0.3782, "lr": 3.8283507055498886e-06, "epoch": 1.8593615185504746, "percentage": 62.15, "elapsed_time": "5:59:08", "remaining_time": "3:38:41"}
+{"current_steps": 180, "total_steps": 288, "loss": 0.3894, "lr": 3.7694784631245066e-06, "epoch": 1.8697152717860224, "percentage": 62.5, "elapsed_time": "6:01:03", "remaining_time": "3:36:38"}
+{"current_steps": 181, "total_steps": 288, "loss": 0.4078, "lr": 3.7107872646888115e-06, "epoch": 1.8800690250215704, "percentage": 62.85, "elapsed_time": "6:03:00", "remaining_time": "3:34:35"}
+{"current_steps": 182, "total_steps": 288, "loss": 0.3752, "lr": 3.6522857453527172e-06, "epoch": 1.8904227782571184, "percentage": 63.19, "elapsed_time": "6:05:11", "remaining_time": "3:32:41"}
+{"current_steps": 183, "total_steps": 288, "loss": 0.3941, "lr": 3.5939825123190637e-06, "epoch": 1.9007765314926661, "percentage": 63.54, "elapsed_time": "6:07:13", "remaining_time": "3:30:41"}
+{"current_steps": 184, "total_steps": 288, "loss": 0.3955, "lr": 3.5358861436172487e-06, "epoch": 1.911130284728214, "percentage": 63.89, "elapsed_time": "6:09:10", "remaining_time": "3:28:39"}
+{"current_steps": 185, "total_steps": 288, "loss": 0.3833, "lr": 3.478005186841167e-06, "epoch": 1.9214840379637619, "percentage": 64.24, "elapsed_time": "6:11:16", "remaining_time": "3:26:42"}
+{"current_steps": 186, "total_steps": 288, "loss": 0.376, "lr": 3.4203481578916197e-06, "epoch": 1.9318377911993099, "percentage": 64.58, "elapsed_time": "6:13:17", "remaining_time": "3:24:42"}
+{"current_steps": 187, "total_steps": 288, "loss": 0.3342, "lr": 3.3629235397233894e-06, "epoch": 1.9421915444348576, "percentage": 64.93, "elapsed_time": "6:15:13", "remaining_time": "3:22:39"}
+{"current_steps": 188, "total_steps": 288, "loss": 0.3724, "lr": 3.305739781097157e-06, "epoch": 1.9525452976704054, "percentage": 65.28, "elapsed_time": "6:17:14", "remaining_time": "3:20:39"}
+{"current_steps": 189, "total_steps": 288, "loss": 0.3924, "lr": 3.248805295336458e-06, "epoch": 1.9628990509059534, "percentage": 65.62, "elapsed_time": "6:19:09", "remaining_time": "3:18:36"}
+{"current_steps": 190, "total_steps": 288, "loss": 0.3281, "lr": 3.192128459089846e-06, "epoch": 1.9732528041415014, "percentage": 65.97, "elapsed_time": "6:21:05", "remaining_time": "3:16:33"}
+{"current_steps": 191, "total_steps": 288, "loss": 0.4028, "lr": 3.1357176110984578e-06, "epoch": 1.9836065573770492, "percentage": 66.32, "elapsed_time": "6:23:32", "remaining_time": "3:14:46"}
+{"current_steps": 192, "total_steps": 288, "loss": 0.3261, "lr": 3.079581050969146e-06, "epoch": 1.993960310612597, "percentage": 66.67, "elapsed_time": "6:25:28", "remaining_time": "3:12:44"}
+{"current_steps": 193, "total_steps": 288, "loss": 0.6913, "lr": 3.0237270379533823e-06, "epoch": 2.010353753235548, "percentage": 67.01, "elapsed_time": "6:27:42", "remaining_time": "3:10:50"}
+{"current_steps": 194, "total_steps": 288, "loss": 0.2789, "lr": 2.968163789732087e-06, "epoch": 2.020707506471096, "percentage": 67.36, "elapsed_time": "6:29:43", "remaining_time": "3:08:50"}
+{"current_steps": 195, "total_steps": 288, "loss": 0.2981, "lr": 2.912899481206582e-06, "epoch": 2.0310612597066435, "percentage": 67.71, "elapsed_time": "6:31:40", "remaining_time": "3:06:47"}
+{"current_steps": 196, "total_steps": 288, "loss": 0.298, "lr": 2.8579422432958316e-06, "epoch": 2.0414150129421915, "percentage": 68.06, "elapsed_time": "6:33:35", "remaining_time": "3:04:44"}
+{"current_steps": 197, "total_steps": 288, "loss": 0.2826, "lr": 2.803300161740166e-06, "epoch": 2.0517687661777395, "percentage": 68.4, "elapsed_time": "6:35:30", "remaining_time": "3:02:41"}
+{"current_steps": 198, "total_steps": 288, "loss": 0.2798, "lr": 2.748981275911633e-06, "epoch": 2.0621225194132875, "percentage": 68.75, "elapsed_time": "6:37:27", "remaining_time": "3:00:39"}
+{"current_steps": 199, "total_steps": 288, "loss": 0.2546, "lr": 2.69499357763119e-06, "epoch": 2.072476272648835, "percentage": 69.1, "elapsed_time": "6:39:24", "remaining_time": "2:58:37"}
+{"current_steps": 200, "total_steps": 288, "loss": 0.2816, "lr": 2.641345009992878e-06, "epoch": 2.082830025884383, "percentage": 69.44, "elapsed_time": "6:41:20", "remaining_time": "2:56:35"}
+{"current_steps": 201, "total_steps": 288, "loss": 0.2739, "lr": 2.5880434661951826e-06, "epoch": 2.093183779119931, "percentage": 69.79, "elapsed_time": "6:47:20", "remaining_time": "2:56:18"}
+{"current_steps": 202, "total_steps": 288, "loss": 0.2767, "lr": 2.5350967883797095e-06, "epoch": 2.103537532355479, "percentage": 70.14, "elapsed_time": "6:49:28", "remaining_time": "2:54:19"}
+{"current_steps": 203, "total_steps": 288, "loss": 0.2797, "lr": 2.4825127664774008e-06, "epoch": 2.1138912855910266, "percentage": 70.49, "elapsed_time": "6:51:22", "remaining_time": "2:52:15"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb81d192c71ee2ddde26785d4629a96984ece3333eefcaceff9bab8957054261
+size 8120