Training in progress, epoch 0

.gitattributes

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

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5105c793eceefa873b7db60adb69fc3099387bc094c3e79ac607ab866ca2da
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3757f38d9a56b05240b69f1c260a136528f15daa959448b8f4111bae15a88f3
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:104d44e1ab9ba72bebb32cd77a75061fd8483e0ec6bb4e60008022ccd3e2c5b9
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc577704a1f6be90b9306b7f80ea08808b505d1c73d6da70ac1244ea9bac7436
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

trainer_log.jsonl

@@ -0,0 +1,158 @@
+{"current_steps": 1, "total_steps": 775, "loss": 1.0664, "lr": 5.128205128205128e-07, "epoch": 0.006430868167202572, "percentage": 0.13, "elapsed_time": "0:00:54", "remaining_time": "11:47:36"}
+{"current_steps": 2, "total_steps": 775, "loss": 1.0667, "lr": 1.0256410256410257e-06, "epoch": 0.012861736334405145, "percentage": 0.26, "elapsed_time": "0:01:38", "remaining_time": "10:31:47"}
+{"current_steps": 3, "total_steps": 775, "loss": 1.0695, "lr": 1.5384615384615387e-06, "epoch": 0.01929260450160772, "percentage": 0.39, "elapsed_time": "0:02:20", "remaining_time": "10:01:10"}
+{"current_steps": 4, "total_steps": 775, "loss": 1.0442, "lr": 2.0512820512820513e-06, "epoch": 0.02572347266881029, "percentage": 0.52, "elapsed_time": "0:02:58", "remaining_time": "9:33:14"}
+{"current_steps": 5, "total_steps": 775, "loss": 1.051, "lr": 2.564102564102564e-06, "epoch": 0.03215434083601286, "percentage": 0.65, "elapsed_time": "0:03:45", "remaining_time": "9:37:34"}
+{"current_steps": 6, "total_steps": 775, "loss": 1.0002, "lr": 3.0769230769230774e-06, "epoch": 0.03858520900321544, "percentage": 0.77, "elapsed_time": "0:04:32", "remaining_time": "9:42:33"}
+{"current_steps": 7, "total_steps": 775, "loss": 0.9527, "lr": 3.58974358974359e-06, "epoch": 0.04501607717041801, "percentage": 0.9, "elapsed_time": "0:05:13", "remaining_time": "9:33:09"}
+{"current_steps": 8, "total_steps": 775, "loss": 0.9526, "lr": 4.102564102564103e-06, "epoch": 0.05144694533762058, "percentage": 1.03, "elapsed_time": "0:05:58", "remaining_time": "9:33:02"}
+{"current_steps": 9, "total_steps": 775, "loss": 0.9463, "lr": 4.615384615384616e-06, "epoch": 0.05787781350482315, "percentage": 1.16, "elapsed_time": "0:06:44", "remaining_time": "9:33:06"}
+{"current_steps": 10, "total_steps": 775, "loss": 0.9295, "lr": 5.128205128205128e-06, "epoch": 0.06430868167202572, "percentage": 1.29, "elapsed_time": "0:07:31", "remaining_time": "9:35:20"}
+{"current_steps": 11, "total_steps": 775, "loss": 0.9365, "lr": 5.641025641025641e-06, "epoch": 0.0707395498392283, "percentage": 1.42, "elapsed_time": "0:08:20", "remaining_time": "9:39:06"}
+{"current_steps": 12, "total_steps": 775, "loss": 0.9149, "lr": 6.153846153846155e-06, "epoch": 0.07717041800643087, "percentage": 1.55, "elapsed_time": "0:09:00", "remaining_time": "9:32:27"}
+{"current_steps": 13, "total_steps": 775, "loss": 0.853, "lr": 6.666666666666667e-06, "epoch": 0.08360128617363344, "percentage": 1.68, "elapsed_time": "0:09:47", "remaining_time": "9:33:51"}
+{"current_steps": 14, "total_steps": 775, "loss": 0.8424, "lr": 7.17948717948718e-06, "epoch": 0.09003215434083602, "percentage": 1.81, "elapsed_time": "0:10:24", "remaining_time": "9:25:39"}
+{"current_steps": 15, "total_steps": 775, "loss": 0.8309, "lr": 7.692307692307694e-06, "epoch": 0.09646302250803858, "percentage": 1.94, "elapsed_time": "0:11:09", "remaining_time": "9:25:38"}
+{"current_steps": 16, "total_steps": 775, "loss": 0.8064, "lr": 8.205128205128205e-06, "epoch": 0.10289389067524116, "percentage": 2.06, "elapsed_time": "0:11:52", "remaining_time": "9:23:11"}
+{"current_steps": 17, "total_steps": 775, "loss": 0.775, "lr": 8.717948717948719e-06, "epoch": 0.10932475884244373, "percentage": 2.19, "elapsed_time": "0:12:32", "remaining_time": "9:19:33"}
+{"current_steps": 18, "total_steps": 775, "loss": 0.7639, "lr": 9.230769230769232e-06, "epoch": 0.1157556270096463, "percentage": 2.32, "elapsed_time": "0:13:19", "remaining_time": "9:20:29"}
+{"current_steps": 19, "total_steps": 775, "loss": 0.7516, "lr": 9.743589743589744e-06, "epoch": 0.12218649517684887, "percentage": 2.45, "elapsed_time": "0:14:00", "remaining_time": "9:17:15"}
+{"current_steps": 20, "total_steps": 775, "loss": 0.7362, "lr": 1.0256410256410256e-05, "epoch": 0.12861736334405144, "percentage": 2.58, "elapsed_time": "0:14:44", "remaining_time": "9:16:39"}
+{"current_steps": 21, "total_steps": 775, "loss": 0.7299, "lr": 1.076923076923077e-05, "epoch": 0.13504823151125403, "percentage": 2.71, "elapsed_time": "0:15:30", "remaining_time": "9:16:39"}
+{"current_steps": 22, "total_steps": 775, "loss": 0.7297, "lr": 1.1282051282051283e-05, "epoch": 0.1414790996784566, "percentage": 2.84, "elapsed_time": "0:16:16", "remaining_time": "9:16:54"}
+{"current_steps": 23, "total_steps": 775, "loss": 0.7151, "lr": 1.1794871794871796e-05, "epoch": 0.14790996784565916, "percentage": 2.97, "elapsed_time": "0:16:58", "remaining_time": "9:14:56"}
+{"current_steps": 24, "total_steps": 775, "loss": 0.7028, "lr": 1.230769230769231e-05, "epoch": 0.15434083601286175, "percentage": 3.1, "elapsed_time": "0:17:43", "remaining_time": "9:14:25"}
+{"current_steps": 25, "total_steps": 775, "loss": 0.7069, "lr": 1.2820512820512823e-05, "epoch": 0.1607717041800643, "percentage": 3.23, "elapsed_time": "0:18:24", "remaining_time": "9:12:18"}
+{"current_steps": 26, "total_steps": 775, "loss": 0.6947, "lr": 1.3333333333333333e-05, "epoch": 0.16720257234726688, "percentage": 3.35, "elapsed_time": "0:19:02", "remaining_time": "9:08:29"}
+{"current_steps": 27, "total_steps": 775, "loss": 0.6988, "lr": 1.3846153846153847e-05, "epoch": 0.17363344051446947, "percentage": 3.48, "elapsed_time": "0:19:48", "remaining_time": "9:08:40"}
+{"current_steps": 28, "total_steps": 775, "loss": 0.6953, "lr": 1.435897435897436e-05, "epoch": 0.18006430868167203, "percentage": 3.61, "elapsed_time": "0:20:32", "remaining_time": "9:07:52"}
+{"current_steps": 29, "total_steps": 775, "loss": 0.6853, "lr": 1.4871794871794874e-05, "epoch": 0.1864951768488746, "percentage": 3.74, "elapsed_time": "0:21:14", "remaining_time": "9:06:15"}
+{"current_steps": 30, "total_steps": 775, "loss": 0.6826, "lr": 1.5384615384615387e-05, "epoch": 0.19292604501607716, "percentage": 3.87, "elapsed_time": "0:21:55", "remaining_time": "9:04:35"}
+{"current_steps": 31, "total_steps": 775, "loss": 0.6692, "lr": 1.5897435897435897e-05, "epoch": 0.19935691318327975, "percentage": 4.0, "elapsed_time": "0:22:42", "remaining_time": "9:05:10"}
+{"current_steps": 32, "total_steps": 775, "loss": 0.6762, "lr": 1.641025641025641e-05, "epoch": 0.2057877813504823, "percentage": 4.13, "elapsed_time": "0:23:31", "remaining_time": "9:06:02"}
+{"current_steps": 33, "total_steps": 775, "loss": 0.6586, "lr": 1.6923076923076924e-05, "epoch": 0.21221864951768488, "percentage": 4.26, "elapsed_time": "0:24:13", "remaining_time": "9:04:33"}
+{"current_steps": 34, "total_steps": 775, "loss": 0.6572, "lr": 1.7435897435897438e-05, "epoch": 0.21864951768488747, "percentage": 4.39, "elapsed_time": "0:24:54", "remaining_time": "9:03:01"}
+{"current_steps": 35, "total_steps": 775, "loss": 0.6528, "lr": 1.794871794871795e-05, "epoch": 0.22508038585209003, "percentage": 4.52, "elapsed_time": "0:25:40", "remaining_time": "9:02:54"}
+{"current_steps": 36, "total_steps": 775, "loss": 0.6412, "lr": 1.8461538461538465e-05, "epoch": 0.2315112540192926, "percentage": 4.65, "elapsed_time": "0:26:23", "remaining_time": "9:01:53"}
+{"current_steps": 37, "total_steps": 775, "loss": 0.6677, "lr": 1.8974358974358975e-05, "epoch": 0.2379421221864952, "percentage": 4.77, "elapsed_time": "0:27:04", "remaining_time": "9:00:11"}
+{"current_steps": 38, "total_steps": 775, "loss": 0.6502, "lr": 1.9487179487179488e-05, "epoch": 0.24437299035369775, "percentage": 4.9, "elapsed_time": "0:27:48", "remaining_time": "8:59:24"}
+{"current_steps": 39, "total_steps": 775, "loss": 0.6567, "lr": 2e-05, "epoch": 0.2508038585209003, "percentage": 5.03, "elapsed_time": "0:28:32", "remaining_time": "8:58:29"}
+{"current_steps": 40, "total_steps": 775, "loss": 0.6623, "lr": 2.0512820512820512e-05, "epoch": 0.2572347266881029, "percentage": 5.16, "elapsed_time": "0:29:15", "remaining_time": "8:57:29"}
+{"current_steps": 41, "total_steps": 775, "loss": 0.6574, "lr": 2.102564102564103e-05, "epoch": 0.26366559485530544, "percentage": 5.29, "elapsed_time": "0:29:58", "remaining_time": "8:56:39"}
+{"current_steps": 42, "total_steps": 775, "loss": 0.6479, "lr": 2.153846153846154e-05, "epoch": 0.27009646302250806, "percentage": 5.42, "elapsed_time": "0:30:42", "remaining_time": "8:55:50"}
+{"current_steps": 43, "total_steps": 775, "loss": 0.6367, "lr": 2.2051282051282056e-05, "epoch": 0.2765273311897106, "percentage": 5.55, "elapsed_time": "0:31:24", "remaining_time": "8:54:33"}
+{"current_steps": 44, "total_steps": 775, "loss": 0.6349, "lr": 2.2564102564102566e-05, "epoch": 0.2829581993569132, "percentage": 5.68, "elapsed_time": "0:32:07", "remaining_time": "8:53:37"}
+{"current_steps": 45, "total_steps": 775, "loss": 0.6389, "lr": 2.3076923076923076e-05, "epoch": 0.28938906752411575, "percentage": 5.81, "elapsed_time": "0:32:51", "remaining_time": "8:53:03"}
+{"current_steps": 46, "total_steps": 775, "loss": 0.6297, "lr": 2.3589743589743593e-05, "epoch": 0.2958199356913183, "percentage": 5.94, "elapsed_time": "0:33:28", "remaining_time": "8:50:29"}
+{"current_steps": 47, "total_steps": 775, "loss": 0.6293, "lr": 2.4102564102564103e-05, "epoch": 0.3022508038585209, "percentage": 6.06, "elapsed_time": "0:34:14", "remaining_time": "8:50:26"}
+{"current_steps": 48, "total_steps": 775, "loss": 0.6243, "lr": 2.461538461538462e-05, "epoch": 0.3086816720257235, "percentage": 6.19, "elapsed_time": "0:34:53", "remaining_time": "8:48:31"}
+{"current_steps": 49, "total_steps": 775, "loss": 0.6402, "lr": 2.512820512820513e-05, "epoch": 0.31511254019292606, "percentage": 6.32, "elapsed_time": "0:35:36", "remaining_time": "8:47:35"}
+{"current_steps": 50, "total_steps": 775, "loss": 0.6205, "lr": 2.5641025641025646e-05, "epoch": 0.3215434083601286, "percentage": 6.45, "elapsed_time": "0:36:22", "remaining_time": "8:47:29"}
+{"current_steps": 51, "total_steps": 775, "loss": 0.6264, "lr": 2.6153846153846157e-05, "epoch": 0.3279742765273312, "percentage": 6.58, "elapsed_time": "0:37:06", "remaining_time": "8:46:41"}
+{"current_steps": 52, "total_steps": 775, "loss": 0.6151, "lr": 2.6666666666666667e-05, "epoch": 0.33440514469453375, "percentage": 6.71, "elapsed_time": "0:37:54", "remaining_time": "8:47:02"}
+{"current_steps": 53, "total_steps": 775, "loss": 0.6295, "lr": 2.7179487179487183e-05, "epoch": 0.3408360128617363, "percentage": 6.84, "elapsed_time": "0:38:39", "remaining_time": "8:46:34"}
+{"current_steps": 54, "total_steps": 775, "loss": 0.6304, "lr": 2.7692307692307694e-05, "epoch": 0.34726688102893893, "percentage": 6.97, "elapsed_time": "0:39:21", "remaining_time": "8:45:35"}
+{"current_steps": 55, "total_steps": 775, "loss": 0.6312, "lr": 2.820512820512821e-05, "epoch": 0.3536977491961415, "percentage": 7.1, "elapsed_time": "0:40:01", "remaining_time": "8:43:59"}
+{"current_steps": 56, "total_steps": 775, "loss": 0.6206, "lr": 2.871794871794872e-05, "epoch": 0.36012861736334406, "percentage": 7.23, "elapsed_time": "0:40:46", "remaining_time": "8:43:33"}
+{"current_steps": 57, "total_steps": 775, "loss": 0.6147, "lr": 2.923076923076923e-05, "epoch": 0.3665594855305466, "percentage": 7.35, "elapsed_time": "0:41:30", "remaining_time": "8:42:53"}
+{"current_steps": 58, "total_steps": 775, "loss": 0.6162, "lr": 2.9743589743589747e-05, "epoch": 0.3729903536977492, "percentage": 7.48, "elapsed_time": "0:42:16", "remaining_time": "8:42:37"}
+{"current_steps": 59, "total_steps": 775, "loss": 0.6209, "lr": 3.0256410256410257e-05, "epoch": 0.37942122186495175, "percentage": 7.61, "elapsed_time": "0:42:58", "remaining_time": "8:41:29"}
+{"current_steps": 60, "total_steps": 775, "loss": 0.6212, "lr": 3.0769230769230774e-05, "epoch": 0.3858520900321543, "percentage": 7.74, "elapsed_time": "0:43:44", "remaining_time": "8:41:19"}
+{"current_steps": 61, "total_steps": 775, "loss": 0.6109, "lr": 3.128205128205129e-05, "epoch": 0.39228295819935693, "percentage": 7.87, "elapsed_time": "0:44:24", "remaining_time": "8:39:52"}
+{"current_steps": 62, "total_steps": 775, "loss": 0.6151, "lr": 3.1794871794871795e-05, "epoch": 0.3987138263665595, "percentage": 8.0, "elapsed_time": "0:45:07", "remaining_time": "8:38:59"}
+{"current_steps": 63, "total_steps": 775, "loss": 0.6093, "lr": 3.230769230769231e-05, "epoch": 0.40514469453376206, "percentage": 8.13, "elapsed_time": "0:45:52", "remaining_time": "8:38:22"}
+{"current_steps": 64, "total_steps": 775, "loss": 0.6104, "lr": 3.282051282051282e-05, "epoch": 0.4115755627009646, "percentage": 8.26, "elapsed_time": "0:46:33", "remaining_time": "8:37:10"}
+{"current_steps": 65, "total_steps": 775, "loss": 0.5979, "lr": 3.3333333333333335e-05, "epoch": 0.4180064308681672, "percentage": 8.39, "elapsed_time": "0:47:16", "remaining_time": "8:36:19"}
+{"current_steps": 66, "total_steps": 775, "loss": 0.6219, "lr": 3.384615384615385e-05, "epoch": 0.42443729903536975, "percentage": 8.52, "elapsed_time": "0:47:59", "remaining_time": "8:35:30"}
+{"current_steps": 67, "total_steps": 775, "loss": 0.5993, "lr": 3.435897435897436e-05, "epoch": 0.43086816720257237, "percentage": 8.65, "elapsed_time": "0:48:43", "remaining_time": "8:34:55"}
+{"current_steps": 68, "total_steps": 775, "loss": 0.6114, "lr": 3.4871794871794875e-05, "epoch": 0.43729903536977494, "percentage": 8.77, "elapsed_time": "0:49:24", "remaining_time": "8:33:42"}
+{"current_steps": 69, "total_steps": 775, "loss": 0.6179, "lr": 3.538461538461539e-05, "epoch": 0.4437299035369775, "percentage": 8.9, "elapsed_time": "0:50:03", "remaining_time": "8:32:09"}
+{"current_steps": 70, "total_steps": 775, "loss": 0.6128, "lr": 3.58974358974359e-05, "epoch": 0.45016077170418006, "percentage": 9.03, "elapsed_time": "0:50:42", "remaining_time": "8:30:38"}
+{"current_steps": 71, "total_steps": 775, "loss": 0.6271, "lr": 3.6410256410256416e-05, "epoch": 0.4565916398713826, "percentage": 9.16, "elapsed_time": "0:51:28", "remaining_time": "8:30:23"}
+{"current_steps": 72, "total_steps": 775, "loss": 0.5979, "lr": 3.692307692307693e-05, "epoch": 0.4630225080385852, "percentage": 9.29, "elapsed_time": "0:52:07", "remaining_time": "8:28:54"}
+{"current_steps": 73, "total_steps": 775, "loss": 0.6097, "lr": 3.7435897435897436e-05, "epoch": 0.4694533762057878, "percentage": 9.42, "elapsed_time": "0:52:50", "remaining_time": "8:28:12"}
+{"current_steps": 74, "total_steps": 775, "loss": 0.6085, "lr": 3.794871794871795e-05, "epoch": 0.4758842443729904, "percentage": 9.55, "elapsed_time": "0:53:33", "remaining_time": "8:27:22"}
+{"current_steps": 75, "total_steps": 775, "loss": 0.614, "lr": 3.846153846153846e-05, "epoch": 0.48231511254019294, "percentage": 9.68, "elapsed_time": "0:54:21", "remaining_time": "8:27:25"}
+{"current_steps": 76, "total_steps": 775, "loss": 0.6112, "lr": 3.8974358974358976e-05, "epoch": 0.4887459807073955, "percentage": 9.81, "elapsed_time": "0:55:11", "remaining_time": "8:27:33"}
+{"current_steps": 77, "total_steps": 775, "loss": 0.6087, "lr": 3.948717948717949e-05, "epoch": 0.49517684887459806, "percentage": 9.94, "elapsed_time": "0:55:54", "remaining_time": "8:26:48"}
+{"current_steps": 78, "total_steps": 775, "loss": 0.6294, "lr": 4e-05, "epoch": 0.5016077170418006, "percentage": 10.06, "elapsed_time": "0:56:37", "remaining_time": "8:25:59"}
+{"current_steps": 79, "total_steps": 775, "loss": 0.5991, "lr": 3.999979684222212e-05, "epoch": 0.5080385852090032, "percentage": 10.19, "elapsed_time": "0:57:19", "remaining_time": "8:25:00"}
+{"current_steps": 80, "total_steps": 775, "loss": 0.6033, "lr": 3.999918737301574e-05, "epoch": 0.5144694533762058, "percentage": 10.32, "elapsed_time": "0:58:05", "remaining_time": "8:24:35"}
+{"current_steps": 81, "total_steps": 775, "loss": 0.6081, "lr": 3.9998171604762734e-05, "epoch": 0.5209003215434084, "percentage": 10.45, "elapsed_time": "0:58:51", "remaining_time": "8:24:15"}
+{"current_steps": 82, "total_steps": 775, "loss": 0.6128, "lr": 3.999674955809922e-05, "epoch": 0.5273311897106109, "percentage": 10.58, "elapsed_time": "0:59:44", "remaining_time": "8:24:53"}
+{"current_steps": 83, "total_steps": 775, "loss": 0.6239, "lr": 3.9994921261915174e-05, "epoch": 0.5337620578778135, "percentage": 10.71, "elapsed_time": "1:00:32", "remaining_time": "8:24:44"}
+{"current_steps": 84, "total_steps": 775, "loss": 0.6027, "lr": 3.999268675335385e-05, "epoch": 0.5401929260450161, "percentage": 10.84, "elapsed_time": "1:01:18", "remaining_time": "8:24:18"}
+{"current_steps": 85, "total_steps": 775, "loss": 0.6178, "lr": 3.999004607781104e-05, "epoch": 0.5466237942122186, "percentage": 10.97, "elapsed_time": "1:01:55", "remaining_time": "8:22:42"}
+{"current_steps": 86, "total_steps": 775, "loss": 0.6159, "lr": 3.998699928893412e-05, "epoch": 0.5530546623794212, "percentage": 11.1, "elapsed_time": "1:02:41", "remaining_time": "8:22:18"}
+{"current_steps": 87, "total_steps": 775, "loss": 0.6224, "lr": 3.998354644862097e-05, "epoch": 0.5594855305466238, "percentage": 11.23, "elapsed_time": "1:03:20", "remaining_time": "8:20:53"}
+{"current_steps": 88, "total_steps": 775, "loss": 0.6168, "lr": 3.997968762701873e-05, "epoch": 0.5659163987138264, "percentage": 11.35, "elapsed_time": "1:04:03", "remaining_time": "8:20:03"}
+{"current_steps": 89, "total_steps": 775, "loss": 0.5944, "lr": 3.997542290252236e-05, "epoch": 0.572347266881029, "percentage": 11.48, "elapsed_time": "1:04:40", "remaining_time": "8:18:33"}
+{"current_steps": 90, "total_steps": 775, "loss": 0.6196, "lr": 3.997075236177305e-05, "epoch": 0.5787781350482315, "percentage": 11.61, "elapsed_time": "1:05:24", "remaining_time": "8:17:51"}
+{"current_steps": 91, "total_steps": 775, "loss": 0.6113, "lr": 3.9965676099656486e-05, "epoch": 0.5852090032154341, "percentage": 11.74, "elapsed_time": "1:06:10", "remaining_time": "8:17:25"}
+{"current_steps": 92, "total_steps": 775, "loss": 0.6005, "lr": 3.9960194219300856e-05, "epoch": 0.5916398713826366, "percentage": 11.87, "elapsed_time": "1:06:53", "remaining_time": "8:16:37"}
+{"current_steps": 93, "total_steps": 775, "loss": 0.5957, "lr": 3.995430683207485e-05, "epoch": 0.5980707395498392, "percentage": 12.0, "elapsed_time": "1:07:36", "remaining_time": "8:15:45"}
+{"current_steps": 94, "total_steps": 775, "loss": 0.6016, "lr": 3.9948014057585294e-05, "epoch": 0.6045016077170418, "percentage": 12.13, "elapsed_time": "1:08:20", "remaining_time": "8:15:10"}
+{"current_steps": 95, "total_steps": 775, "loss": 0.591, "lr": 3.994131602367481e-05, "epoch": 0.6109324758842444, "percentage": 12.26, "elapsed_time": "1:08:59", "remaining_time": "8:13:47"}
+{"current_steps": 96, "total_steps": 775, "loss": 0.5922, "lr": 3.993421286641917e-05, "epoch": 0.617363344051447, "percentage": 12.39, "elapsed_time": "1:09:36", "remaining_time": "8:12:23"}
+{"current_steps": 97, "total_steps": 775, "loss": 0.611, "lr": 3.992670473012453e-05, "epoch": 0.6237942122186495, "percentage": 12.52, "elapsed_time": "1:10:23", "remaining_time": "8:12:00"}
+{"current_steps": 98, "total_steps": 775, "loss": 0.6017, "lr": 3.9918791767324514e-05, "epoch": 0.6302250803858521, "percentage": 12.65, "elapsed_time": "1:11:05", "remaining_time": "8:11:06"}
+{"current_steps": 99, "total_steps": 775, "loss": 0.5993, "lr": 3.991047413877713e-05, "epoch": 0.6366559485530546, "percentage": 12.77, "elapsed_time": "1:11:43", "remaining_time": "8:09:46"}
+{"current_steps": 100, "total_steps": 775, "loss": 0.6007, "lr": 3.990175201346146e-05, "epoch": 0.6430868167202572, "percentage": 12.9, "elapsed_time": "1:12:29", "remaining_time": "8:09:16"}
+{"current_steps": 101, "total_steps": 775, "loss": 0.5923, "lr": 3.9892625568574274e-05, "epoch": 0.6495176848874598, "percentage": 13.03, "elapsed_time": "1:13:17", "remaining_time": "8:09:05"}
+{"current_steps": 102, "total_steps": 775, "loss": 0.5862, "lr": 3.988309498952639e-05, "epoch": 0.6559485530546624, "percentage": 13.16, "elapsed_time": "1:14:03", "remaining_time": "8:08:40"}
+{"current_steps": 103, "total_steps": 775, "loss": 0.5956, "lr": 3.987316046993893e-05, "epoch": 0.662379421221865, "percentage": 13.29, "elapsed_time": "1:14:47", "remaining_time": "8:07:56"}
+{"current_steps": 104, "total_steps": 775, "loss": 0.599, "lr": 3.98628222116394e-05, "epoch": 0.6688102893890675, "percentage": 13.42, "elapsed_time": "1:15:31", "remaining_time": "8:07:17"}
+{"current_steps": 105, "total_steps": 775, "loss": 0.6034, "lr": 3.9852080424657545e-05, "epoch": 0.6752411575562701, "percentage": 13.55, "elapsed_time": "1:16:16", "remaining_time": "8:06:44"}
+{"current_steps": 106, "total_steps": 775, "loss": 0.5941, "lr": 3.9840935327221136e-05, "epoch": 0.6816720257234726, "percentage": 13.68, "elapsed_time": "1:17:01", "remaining_time": "8:06:09"}
+{"current_steps": 107, "total_steps": 775, "loss": 0.5795, "lr": 3.982938714575148e-05, "epoch": 0.6881028938906752, "percentage": 13.81, "elapsed_time": "1:17:48", "remaining_time": "8:05:47"}
+{"current_steps": 108, "total_steps": 775, "loss": 0.6033, "lr": 3.981743611485888e-05, "epoch": 0.6945337620578779, "percentage": 13.94, "elapsed_time": "1:18:36", "remaining_time": "8:05:25"}
+{"current_steps": 109, "total_steps": 775, "loss": 0.6061, "lr": 3.9805082477337815e-05, "epoch": 0.7009646302250804, "percentage": 14.06, "elapsed_time": "1:19:19", "remaining_time": "8:04:43"}
+{"current_steps": 110, "total_steps": 775, "loss": 0.5928, "lr": 3.979232648416204e-05, "epoch": 0.707395498392283, "percentage": 14.19, "elapsed_time": "1:20:02", "remaining_time": "8:03:52"}
+{"current_steps": 111, "total_steps": 775, "loss": 0.6003, "lr": 3.9779168394479486e-05, "epoch": 0.7138263665594855, "percentage": 14.32, "elapsed_time": "1:20:45", "remaining_time": "8:03:05"}
+{"current_steps": 112, "total_steps": 775, "loss": 0.5986, "lr": 3.976560847560697e-05, "epoch": 0.7202572347266881, "percentage": 14.45, "elapsed_time": "1:21:28", "remaining_time": "8:02:17"}
+{"current_steps": 113, "total_steps": 775, "loss": 0.6021, "lr": 3.97516470030248e-05, "epoch": 0.7266881028938906, "percentage": 14.58, "elapsed_time": "1:22:13", "remaining_time": "8:01:40"}
+{"current_steps": 114, "total_steps": 775, "loss": 0.5953, "lr": 3.9737284260371144e-05, "epoch": 0.7331189710610932, "percentage": 14.71, "elapsed_time": "1:22:55", "remaining_time": "8:00:48"}
+{"current_steps": 115, "total_steps": 775, "loss": 0.5966, "lr": 3.9722520539436286e-05, "epoch": 0.7395498392282959, "percentage": 14.84, "elapsed_time": "1:23:39", "remaining_time": "8:00:06"}
+{"current_steps": 116, "total_steps": 775, "loss": 0.5826, "lr": 3.970735614015671e-05, "epoch": 0.7459807073954984, "percentage": 14.97, "elapsed_time": "1:24:16", "remaining_time": "7:58:47"}
+{"current_steps": 117, "total_steps": 775, "loss": 0.5796, "lr": 3.969179137060897e-05, "epoch": 0.752411575562701, "percentage": 15.1, "elapsed_time": "1:24:56", "remaining_time": "7:57:45"}
+{"current_steps": 118, "total_steps": 775, "loss": 0.595, "lr": 3.967582654700348e-05, "epoch": 0.7588424437299035, "percentage": 15.23, "elapsed_time": "1:25:41", "remaining_time": "7:57:08"}
+{"current_steps": 119, "total_steps": 775, "loss": 0.5922, "lr": 3.965946199367804e-05, "epoch": 0.7652733118971061, "percentage": 15.35, "elapsed_time": "1:26:19", "remaining_time": "7:55:51"}
+{"current_steps": 120, "total_steps": 775, "loss": 0.5982, "lr": 3.964269804309128e-05, "epoch": 0.7717041800643086, "percentage": 15.48, "elapsed_time": "1:27:04", "remaining_time": "7:55:18"}
+{"current_steps": 121, "total_steps": 775, "loss": 0.5984, "lr": 3.962553503581589e-05, "epoch": 0.7781350482315113, "percentage": 15.61, "elapsed_time": "1:27:42", "remaining_time": "7:54:05"}
+{"current_steps": 122, "total_steps": 775, "loss": 0.5967, "lr": 3.9607973320531725e-05, "epoch": 0.7845659163987139, "percentage": 15.74, "elapsed_time": "1:28:23", "remaining_time": "7:53:04"}
+{"current_steps": 123, "total_steps": 775, "loss": 0.5941, "lr": 3.959001325401868e-05, "epoch": 0.7909967845659164, "percentage": 15.87, "elapsed_time": "1:29:05", "remaining_time": "7:52:18"}
+{"current_steps": 124, "total_steps": 775, "loss": 0.584, "lr": 3.957165520114948e-05, "epoch": 0.797427652733119, "percentage": 16.0, "elapsed_time": "1:29:50", "remaining_time": "7:51:40"}
+{"current_steps": 125, "total_steps": 775, "loss": 0.5793, "lr": 3.955289953488224e-05, "epoch": 0.8038585209003215, "percentage": 16.13, "elapsed_time": "1:30:30", "remaining_time": "7:50:37"}
+{"current_steps": 126, "total_steps": 775, "loss": 0.5772, "lr": 3.9533746636252915e-05, "epoch": 0.8102893890675241, "percentage": 16.26, "elapsed_time": "1:31:09", "remaining_time": "7:49:30"}
+{"current_steps": 127, "total_steps": 775, "loss": 0.5929, "lr": 3.951419689436754e-05, "epoch": 0.8167202572347267, "percentage": 16.39, "elapsed_time": "1:31:48", "remaining_time": "7:48:26"}
+{"current_steps": 128, "total_steps": 775, "loss": 0.581, "lr": 3.949425070639432e-05, "epoch": 0.8231511254019293, "percentage": 16.52, "elapsed_time": "1:32:32", "remaining_time": "7:47:43"}
+{"current_steps": 129, "total_steps": 775, "loss": 0.5992, "lr": 3.947390847755559e-05, "epoch": 0.8295819935691319, "percentage": 16.65, "elapsed_time": "1:33:17", "remaining_time": "7:47:11"}
+{"current_steps": 130, "total_steps": 775, "loss": 0.5832, "lr": 3.945317062111953e-05, "epoch": 0.8360128617363344, "percentage": 16.77, "elapsed_time": "1:33:58", "remaining_time": "7:46:17"}
+{"current_steps": 131, "total_steps": 775, "loss": 0.5949, "lr": 3.943203755839184e-05, "epoch": 0.842443729903537, "percentage": 16.9, "elapsed_time": "1:34:40", "remaining_time": "7:45:23"}
+{"current_steps": 132, "total_steps": 775, "loss": 0.5812, "lr": 3.941050971870712e-05, "epoch": 0.8488745980707395, "percentage": 17.03, "elapsed_time": "1:35:22", "remaining_time": "7:44:37"}
+{"current_steps": 133, "total_steps": 775, "loss": 0.5821, "lr": 3.938858753942018e-05, "epoch": 0.8553054662379421, "percentage": 17.16, "elapsed_time": "1:36:05", "remaining_time": "7:43:49"}
+{"current_steps": 134, "total_steps": 775, "loss": 0.588, "lr": 3.936627146589715e-05, "epoch": 0.8617363344051447, "percentage": 17.29, "elapsed_time": "1:36:47", "remaining_time": "7:42:58"}
+{"current_steps": 135, "total_steps": 775, "loss": 0.5887, "lr": 3.93435619515064e-05, "epoch": 0.8681672025723473, "percentage": 17.42, "elapsed_time": "1:37:30", "remaining_time": "7:42:15"}
+{"current_steps": 136, "total_steps": 775, "loss": 0.5995, "lr": 3.932045945760939e-05, "epoch": 0.8745980707395499, "percentage": 17.55, "elapsed_time": "1:38:16", "remaining_time": "7:41:46"}
+{"current_steps": 137, "total_steps": 775, "loss": 0.5758, "lr": 3.929696445355126e-05, "epoch": 0.8810289389067524, "percentage": 17.68, "elapsed_time": "1:38:57", "remaining_time": "7:40:49"}
+{"current_steps": 138, "total_steps": 775, "loss": 0.5921, "lr": 3.9273077416651284e-05, "epoch": 0.887459807073955, "percentage": 17.81, "elapsed_time": "1:39:41", "remaining_time": "7:40:08"}
+{"current_steps": 139, "total_steps": 775, "loss": 0.582, "lr": 3.92487988321932e-05, "epoch": 0.8938906752411575, "percentage": 17.94, "elapsed_time": "1:40:25", "remaining_time": "7:39:31"}
+{"current_steps": 140, "total_steps": 775, "loss": 0.5885, "lr": 3.922412919341533e-05, "epoch": 0.9003215434083601, "percentage": 18.06, "elapsed_time": "1:41:08", "remaining_time": "7:38:46"}
+{"current_steps": 141, "total_steps": 775, "loss": 0.5894, "lr": 3.919906900150056e-05, "epoch": 0.9067524115755627, "percentage": 18.19, "elapsed_time": "1:41:48", "remaining_time": "7:37:46"}
+{"current_steps": 142, "total_steps": 775, "loss": 0.5776, "lr": 3.917361876556621e-05, "epoch": 0.9131832797427653, "percentage": 18.32, "elapsed_time": "1:42:35", "remaining_time": "7:37:18"}
+{"current_steps": 143, "total_steps": 775, "loss": 0.5827, "lr": 3.9147779002653606e-05, "epoch": 0.9196141479099679, "percentage": 18.45, "elapsed_time": "1:43:19", "remaining_time": "7:36:41"}
+{"current_steps": 144, "total_steps": 775, "loss": 0.5824, "lr": 3.912155023771762e-05, "epoch": 0.9260450160771704, "percentage": 18.58, "elapsed_time": "1:44:00", "remaining_time": "7:35:43"}
+{"current_steps": 145, "total_steps": 775, "loss": 0.5926, "lr": 3.909493300361602e-05, "epoch": 0.932475884244373, "percentage": 18.71, "elapsed_time": "1:44:46", "remaining_time": "7:35:15"}
+{"current_steps": 146, "total_steps": 775, "loss": 0.5855, "lr": 3.9067927841098614e-05, "epoch": 0.9389067524115756, "percentage": 18.84, "elapsed_time": "1:45:31", "remaining_time": "7:34:38"}
+{"current_steps": 147, "total_steps": 775, "loss": 0.5752, "lr": 3.904053529879629e-05, "epoch": 0.9453376205787781, "percentage": 18.97, "elapsed_time": "1:46:11", "remaining_time": "7:33:38"}
+{"current_steps": 148, "total_steps": 775, "loss": 0.5895, "lr": 3.9012755933209846e-05, "epoch": 0.9517684887459807, "percentage": 19.1, "elapsed_time": "1:46:51", "remaining_time": "7:32:44"}
+{"current_steps": 149, "total_steps": 775, "loss": 0.586, "lr": 3.89845903086987e-05, "epoch": 0.9581993569131833, "percentage": 19.23, "elapsed_time": "1:47:33", "remaining_time": "7:31:55"}
+{"current_steps": 150, "total_steps": 775, "loss": 0.5814, "lr": 3.8956038997469436e-05, "epoch": 0.9646302250803859, "percentage": 19.35, "elapsed_time": "1:48:17", "remaining_time": "7:31:11"}
+{"current_steps": 151, "total_steps": 775, "loss": 0.5758, "lr": 3.892710257956412e-05, "epoch": 0.9710610932475884, "percentage": 19.48, "elapsed_time": "1:48:56", "remaining_time": "7:30:11"}
+{"current_steps": 152, "total_steps": 775, "loss": 0.5791, "lr": 3.889778164284861e-05, "epoch": 0.977491961414791, "percentage": 19.61, "elapsed_time": "1:49:39", "remaining_time": "7:29:26"}
+{"current_steps": 153, "total_steps": 775, "loss": 0.5916, "lr": 3.886807678300053e-05, "epoch": 0.9839228295819936, "percentage": 19.74, "elapsed_time": "1:50:26", "remaining_time": "7:29:00"}
+{"current_steps": 154, "total_steps": 775, "loss": 0.5764, "lr": 3.883798860349722e-05, "epoch": 0.9903536977491961, "percentage": 19.87, "elapsed_time": "1:51:08", "remaining_time": "7:28:11"}
+{"current_steps": 155, "total_steps": 775, "loss": 0.5722, "lr": 3.880751771560344e-05, "epoch": 0.9967845659163987, "percentage": 20.0, "elapsed_time": "1:51:51", "remaining_time": "7:27:25"}
+{"current_steps": 156, "total_steps": 775, "loss": 0.5427, "lr": 3.877666473835899e-05, "epoch": 1.0032154340836013, "percentage": 20.13, "elapsed_time": "1:53:34", "remaining_time": "7:30:40"}
+{"current_steps": 157, "total_steps": 775, "loss": 0.5225, "lr": 3.874543029856609e-05, "epoch": 1.0096463022508038, "percentage": 20.26, "elapsed_time": "1:54:18", "remaining_time": "7:29:58"}
+{"current_steps": 158, "total_steps": 775, "loss": 0.5165, "lr": 3.871381503077668e-05, "epoch": 1.0160771704180065, "percentage": 20.39, "elapsed_time": "1:55:03", "remaining_time": "7:29:19"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e62da7c5567a2fb2f1a39b34ff7b78272d25072b388dfdc032fcc7c0250c38a3
+size 7761