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:cec9e38c90fa0de69fb5f4f8c606539b3ddf4f14f71b3f9935ea5e959869ae6f
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f88847bf3782b27a1cac1677b5b72657058b53f9d5b6f4584b14233380690f4
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45fb3a46d9a5100bd2dc9478e4ec58dac78a34987a5357ca261ed4167f889603
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5906bae41f886eee5a626553a767136806a9a866dfa3908670dd59cc15b3c9
+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 +1,148 @@
+{"current_steps": 1, "total_steps": 441, "loss": 1.1988, "lr": 1.777777777777778e-06, "epoch": 0.006782534972445952, "percentage": 0.23, "elapsed_time": "0:01:56", "remaining_time": "14:17:15"}
+{"current_steps": 2, "total_steps": 441, "loss": 1.1926, "lr": 3.555555555555556e-06, "epoch": 0.013565069944891903, "percentage": 0.45, "elapsed_time": "0:03:45", "remaining_time": "13:45:36"}
+{"current_steps": 3, "total_steps": 441, "loss": 1.1857, "lr": 5.333333333333334e-06, "epoch": 0.020347604917337857, "percentage": 0.68, "elapsed_time": "0:05:33", "remaining_time": "13:30:57"}
+{"current_steps": 4, "total_steps": 441, "loss": 1.1299, "lr": 7.111111111111112e-06, "epoch": 0.027130139889783807, "percentage": 0.91, "elapsed_time": "0:07:21", "remaining_time": "13:23:34"}
+{"current_steps": 5, "total_steps": 441, "loss": 1.0926, "lr": 8.888888888888888e-06, "epoch": 0.03391267486222976, "percentage": 1.13, "elapsed_time": "0:09:09", "remaining_time": "13:18:29"}
+{"current_steps": 6, "total_steps": 441, "loss": 1.0767, "lr": 1.0666666666666667e-05, "epoch": 0.040695209834675714, "percentage": 1.36, "elapsed_time": "0:10:56", "remaining_time": "13:13:31"}
+{"current_steps": 7, "total_steps": 441, "loss": 1.0742, "lr": 1.2444444444444446e-05, "epoch": 0.04747774480712166, "percentage": 1.59, "elapsed_time": "0:12:44", "remaining_time": "13:10:06"}
+{"current_steps": 8, "total_steps": 441, "loss": 1.0239, "lr": 1.4222222222222224e-05, "epoch": 0.05426027977956761, "percentage": 1.81, "elapsed_time": "0:14:32", "remaining_time": "13:06:42"}
+{"current_steps": 9, "total_steps": 441, "loss": 1.0123, "lr": 1.6000000000000003e-05, "epoch": 0.06104281475201356, "percentage": 2.04, "elapsed_time": "0:16:19", "remaining_time": "13:03:38"}
+{"current_steps": 10, "total_steps": 441, "loss": 0.9613, "lr": 1.7777777777777777e-05, "epoch": 0.06782534972445951, "percentage": 2.27, "elapsed_time": "0:18:06", "remaining_time": "13:00:45"}
+{"current_steps": 11, "total_steps": 441, "loss": 0.9432, "lr": 1.9555555555555557e-05, "epoch": 0.07460788469690546, "percentage": 2.49, "elapsed_time": "0:19:54", "remaining_time": "12:58:01"}
+{"current_steps": 12, "total_steps": 441, "loss": 0.9219, "lr": 2.1333333333333335e-05, "epoch": 0.08139041966935143, "percentage": 2.72, "elapsed_time": "0:21:41", "remaining_time": "12:55:29"}
+{"current_steps": 13, "total_steps": 441, "loss": 0.8906, "lr": 2.3111111111111112e-05, "epoch": 0.08817295464179738, "percentage": 2.95, "elapsed_time": "0:23:29", "remaining_time": "12:53:16"}
+{"current_steps": 14, "total_steps": 441, "loss": 0.8878, "lr": 2.4888888888888893e-05, "epoch": 0.09495548961424333, "percentage": 3.17, "elapsed_time": "0:25:17", "remaining_time": "12:51:09"}
+{"current_steps": 15, "total_steps": 441, "loss": 0.8858, "lr": 2.6666666666666667e-05, "epoch": 0.10173802458668928, "percentage": 3.4, "elapsed_time": "0:27:04", "remaining_time": "12:48:57"}
+{"current_steps": 16, "total_steps": 441, "loss": 0.845, "lr": 2.8444444444444447e-05, "epoch": 0.10852055955913523, "percentage": 3.63, "elapsed_time": "0:28:51", "remaining_time": "12:46:43"}
+{"current_steps": 17, "total_steps": 441, "loss": 0.8413, "lr": 3.0222222222222225e-05, "epoch": 0.11530309453158118, "percentage": 3.85, "elapsed_time": "0:30:39", "remaining_time": "12:44:28"}
+{"current_steps": 18, "total_steps": 441, "loss": 0.8427, "lr": 3.2000000000000005e-05, "epoch": 0.12208562950402713, "percentage": 4.08, "elapsed_time": "0:32:26", "remaining_time": "12:42:24"}
+{"current_steps": 19, "total_steps": 441, "loss": 0.8427, "lr": 3.377777777777778e-05, "epoch": 0.1288681644764731, "percentage": 4.31, "elapsed_time": "0:34:13", "remaining_time": "12:40:08"}
+{"current_steps": 20, "total_steps": 441, "loss": 0.8361, "lr": 3.555555555555555e-05, "epoch": 0.13565069944891903, "percentage": 4.54, "elapsed_time": "0:36:00", "remaining_time": "12:38:08"}
+{"current_steps": 21, "total_steps": 441, "loss": 0.8125, "lr": 3.733333333333334e-05, "epoch": 0.142433234421365, "percentage": 4.76, "elapsed_time": "0:37:49", "remaining_time": "12:36:20"}
+{"current_steps": 22, "total_steps": 441, "loss": 0.8096, "lr": 3.9111111111111115e-05, "epoch": 0.14921576939381093, "percentage": 4.99, "elapsed_time": "0:39:36", "remaining_time": "12:34:18"}
+{"current_steps": 23, "total_steps": 441, "loss": 0.7992, "lr": 4.088888888888889e-05, "epoch": 0.1559983043662569, "percentage": 5.22, "elapsed_time": "0:41:23", "remaining_time": "12:32:15"}
+{"current_steps": 24, "total_steps": 441, "loss": 0.8177, "lr": 4.266666666666667e-05, "epoch": 0.16278083933870285, "percentage": 5.44, "elapsed_time": "0:43:10", "remaining_time": "12:30:16"}
+{"current_steps": 25, "total_steps": 441, "loss": 0.8192, "lr": 4.444444444444445e-05, "epoch": 0.1695633743111488, "percentage": 5.67, "elapsed_time": "0:44:58", "remaining_time": "12:28:18"}
+{"current_steps": 26, "total_steps": 441, "loss": 0.8082, "lr": 4.6222222222222224e-05, "epoch": 0.17634590928359475, "percentage": 5.9, "elapsed_time": "0:46:46", "remaining_time": "12:26:30"}
+{"current_steps": 27, "total_steps": 441, "loss": 0.7944, "lr": 4.8e-05, "epoch": 0.1831284442560407, "percentage": 6.12, "elapsed_time": "0:48:33", "remaining_time": "12:24:30"}
+{"current_steps": 28, "total_steps": 441, "loss": 0.8017, "lr": 4.9777777777777785e-05, "epoch": 0.18991097922848665, "percentage": 6.35, "elapsed_time": "0:50:20", "remaining_time": "12:22:38"}
+{"current_steps": 29, "total_steps": 441, "loss": 0.7945, "lr": 5.155555555555556e-05, "epoch": 0.1966935142009326, "percentage": 6.58, "elapsed_time": "0:52:09", "remaining_time": "12:20:57"}
+{"current_steps": 30, "total_steps": 441, "loss": 0.7945, "lr": 5.333333333333333e-05, "epoch": 0.20347604917337855, "percentage": 6.8, "elapsed_time": "0:53:56", "remaining_time": "12:19:05"}
+{"current_steps": 31, "total_steps": 441, "loss": 0.7844, "lr": 5.511111111111112e-05, "epoch": 0.2102585841458245, "percentage": 7.03, "elapsed_time": "0:55:44", "remaining_time": "12:17:10"}
+{"current_steps": 32, "total_steps": 441, "loss": 0.7812, "lr": 5.6888888888888895e-05, "epoch": 0.21704111911827045, "percentage": 7.26, "elapsed_time": "0:57:33", "remaining_time": "12:15:36"}
+{"current_steps": 33, "total_steps": 441, "loss": 0.8027, "lr": 5.8666666666666665e-05, "epoch": 0.22382365409071642, "percentage": 7.48, "elapsed_time": "0:59:21", "remaining_time": "12:13:47"}
+{"current_steps": 34, "total_steps": 441, "loss": 0.7876, "lr": 6.044444444444445e-05, "epoch": 0.23060618906316235, "percentage": 7.71, "elapsed_time": "1:01:07", "remaining_time": "12:11:47"}
+{"current_steps": 35, "total_steps": 441, "loss": 0.7992, "lr": 6.222222222222223e-05, "epoch": 0.23738872403560832, "percentage": 7.94, "elapsed_time": "1:02:57", "remaining_time": "12:10:13"}
+{"current_steps": 36, "total_steps": 441, "loss": 0.7788, "lr": 6.400000000000001e-05, "epoch": 0.24417125900805425, "percentage": 8.16, "elapsed_time": "1:04:44", "remaining_time": "12:08:23"}
+{"current_steps": 37, "total_steps": 441, "loss": 0.7907, "lr": 6.577777777777777e-05, "epoch": 0.2509537939805002, "percentage": 8.39, "elapsed_time": "1:06:33", "remaining_time": "12:06:39"}
+{"current_steps": 38, "total_steps": 441, "loss": 0.7894, "lr": 6.755555555555557e-05, "epoch": 0.2577363289529462, "percentage": 8.62, "elapsed_time": "1:08:20", "remaining_time": "12:04:45"}
+{"current_steps": 39, "total_steps": 441, "loss": 0.7795, "lr": 6.933333333333334e-05, "epoch": 0.2645188639253921, "percentage": 8.84, "elapsed_time": "1:10:07", "remaining_time": "12:02:50"}
+{"current_steps": 40, "total_steps": 441, "loss": 0.7823, "lr": 7.11111111111111e-05, "epoch": 0.27130139889783805, "percentage": 9.07, "elapsed_time": "1:11:55", "remaining_time": "12:01:07"}
+{"current_steps": 41, "total_steps": 441, "loss": 0.7768, "lr": 7.28888888888889e-05, "epoch": 0.278083933870284, "percentage": 9.3, "elapsed_time": "1:13:43", "remaining_time": "11:59:13"}
+{"current_steps": 42, "total_steps": 441, "loss": 0.7841, "lr": 7.466666666666667e-05, "epoch": 0.28486646884273, "percentage": 9.52, "elapsed_time": "1:15:30", "remaining_time": "11:57:22"}
+{"current_steps": 43, "total_steps": 441, "loss": 0.7818, "lr": 7.644444444444445e-05, "epoch": 0.29164900381517594, "percentage": 9.75, "elapsed_time": "1:17:17", "remaining_time": "11:55:26"}
+{"current_steps": 44, "total_steps": 441, "loss": 0.7641, "lr": 7.822222222222223e-05, "epoch": 0.29843153878762185, "percentage": 9.98, "elapsed_time": "1:19:04", "remaining_time": "11:53:29"}
+{"current_steps": 45, "total_steps": 441, "loss": 0.7673, "lr": 8e-05, "epoch": 0.3052140737600678, "percentage": 10.2, "elapsed_time": "1:20:51", "remaining_time": "11:51:31"}
+{"current_steps": 46, "total_steps": 441, "loss": 0.7792, "lr": 7.999874125693333e-05, "epoch": 0.3119966087325138, "percentage": 10.43, "elapsed_time": "1:22:38", "remaining_time": "11:49:39"}
+{"current_steps": 47, "total_steps": 441, "loss": 0.7703, "lr": 7.999496510695501e-05, "epoch": 0.31877914370495974, "percentage": 10.66, "elapsed_time": "1:24:25", "remaining_time": "11:47:46"}
+{"current_steps": 48, "total_steps": 441, "loss": 0.7712, "lr": 7.998867178772517e-05, "epoch": 0.3255616786774057, "percentage": 10.88, "elapsed_time": "1:26:13", "remaining_time": "11:45:55"}
+{"current_steps": 49, "total_steps": 441, "loss": 0.7637, "lr": 7.997986169532741e-05, "epoch": 0.3323442136498516, "percentage": 11.11, "elapsed_time": "1:28:01", "remaining_time": "11:44:09"}
+{"current_steps": 50, "total_steps": 441, "loss": 0.7827, "lr": 7.996853538424387e-05, "epoch": 0.3391267486222976, "percentage": 11.34, "elapsed_time": "1:29:48", "remaining_time": "11:42:15"}
+{"current_steps": 51, "total_steps": 441, "loss": 0.7689, "lr": 7.995469356732033e-05, "epoch": 0.34590928359474354, "percentage": 11.56, "elapsed_time": "1:31:35", "remaining_time": "11:40:21"}
+{"current_steps": 52, "total_steps": 441, "loss": 0.7764, "lr": 7.993833711572133e-05, "epoch": 0.3526918185671895, "percentage": 11.79, "elapsed_time": "1:33:22", "remaining_time": "11:38:31"}
+{"current_steps": 53, "total_steps": 441, "loss": 0.7583, "lr": 7.991946705887539e-05, "epoch": 0.3594743535396354, "percentage": 12.02, "elapsed_time": "1:35:10", "remaining_time": "11:36:41"}
+{"current_steps": 54, "total_steps": 441, "loss": 0.755, "lr": 7.989808458441014e-05, "epoch": 0.3662568885120814, "percentage": 12.24, "elapsed_time": "1:36:57", "remaining_time": "11:34:49"}
+{"current_steps": 55, "total_steps": 441, "loss": 0.7467, "lr": 7.98741910380777e-05, "epoch": 0.37303942348452734, "percentage": 12.47, "elapsed_time": "1:38:43", "remaining_time": "11:32:55"}
+{"current_steps": 56, "total_steps": 441, "loss": 0.7476, "lr": 7.984778792366983e-05, "epoch": 0.3798219584569733, "percentage": 12.7, "elapsed_time": "1:40:30", "remaining_time": "11:31:01"}
+{"current_steps": 57, "total_steps": 441, "loss": 0.7477, "lr": 7.981887690292339e-05, "epoch": 0.38660449342941927, "percentage": 12.93, "elapsed_time": "1:42:17", "remaining_time": "11:29:09"}
+{"current_steps": 58, "total_steps": 441, "loss": 0.7456, "lr": 7.978745979541574e-05, "epoch": 0.3933870284018652, "percentage": 13.15, "elapsed_time": "1:44:04", "remaining_time": "11:27:14"}
+{"current_steps": 59, "total_steps": 441, "loss": 0.7453, "lr": 7.975353857845017e-05, "epoch": 0.40016956337431114, "percentage": 13.38, "elapsed_time": "1:45:51", "remaining_time": "11:25:23"}
+{"current_steps": 60, "total_steps": 441, "loss": 0.7652, "lr": 7.971711538693153e-05, "epoch": 0.4069520983467571, "percentage": 13.61, "elapsed_time": "1:47:38", "remaining_time": "11:23:30"}
+{"current_steps": 61, "total_steps": 441, "loss": 0.7468, "lr": 7.967819251323182e-05, "epoch": 0.41373463331920307, "percentage": 13.83, "elapsed_time": "1:49:25", "remaining_time": "11:21:41"}
+{"current_steps": 62, "total_steps": 441, "loss": 0.7476, "lr": 7.963677240704588e-05, "epoch": 0.420517168291649, "percentage": 14.06, "elapsed_time": "1:51:13", "remaining_time": "11:19:53"}
+{"current_steps": 63, "total_steps": 441, "loss": 0.7486, "lr": 7.959285767523732e-05, "epoch": 0.42729970326409494, "percentage": 14.29, "elapsed_time": "1:53:01", "remaining_time": "11:18:06"}
+{"current_steps": 64, "total_steps": 441, "loss": 0.7542, "lr": 7.954645108167432e-05, "epoch": 0.4340822382365409, "percentage": 14.51, "elapsed_time": "1:54:48", "remaining_time": "11:16:18"}
+{"current_steps": 65, "total_steps": 441, "loss": 0.7517, "lr": 7.949755554705577e-05, "epoch": 0.44086477320898687, "percentage": 14.74, "elapsed_time": "1:56:35", "remaining_time": "11:14:27"}
+{"current_steps": 66, "total_steps": 441, "loss": 0.7589, "lr": 7.944617414872747e-05, "epoch": 0.44764730818143283, "percentage": 14.97, "elapsed_time": "1:58:23", "remaining_time": "11:12:38"}
+{"current_steps": 67, "total_steps": 441, "loss": 0.7345, "lr": 7.939231012048833e-05, "epoch": 0.45442984315387874, "percentage": 15.19, "elapsed_time": "2:00:10", "remaining_time": "11:10:48"}
+{"current_steps": 68, "total_steps": 441, "loss": 0.7478, "lr": 7.933596685238697e-05, "epoch": 0.4612123781263247, "percentage": 15.42, "elapsed_time": "2:01:57", "remaining_time": "11:08:57"}
+{"current_steps": 69, "total_steps": 441, "loss": 0.732, "lr": 7.927714789050826e-05, "epoch": 0.46799491309877067, "percentage": 15.65, "elapsed_time": "2:03:45", "remaining_time": "11:07:10"}
+{"current_steps": 70, "total_steps": 441, "loss": 0.7385, "lr": 7.921585693675029e-05, "epoch": 0.47477744807121663, "percentage": 15.87, "elapsed_time": "2:05:32", "remaining_time": "11:05:20"}
+{"current_steps": 71, "total_steps": 441, "loss": 0.7334, "lr": 7.915209784859116e-05, "epoch": 0.48155998304366254, "percentage": 16.1, "elapsed_time": "2:07:19", "remaining_time": "11:03:33"}
+{"current_steps": 72, "total_steps": 441, "loss": 0.7501, "lr": 7.908587463884638e-05, "epoch": 0.4883425180161085, "percentage": 16.33, "elapsed_time": "2:09:09", "remaining_time": "11:01:53"}
+{"current_steps": 73, "total_steps": 441, "loss": 0.7323, "lr": 7.90171914754163e-05, "epoch": 0.49512505298855447, "percentage": 16.55, "elapsed_time": "2:10:56", "remaining_time": "11:00:03"}
+{"current_steps": 74, "total_steps": 441, "loss": 0.7284, "lr": 7.894605268102365e-05, "epoch": 0.5019075879610004, "percentage": 16.78, "elapsed_time": "2:12:43", "remaining_time": "10:58:14"}
+{"current_steps": 75, "total_steps": 441, "loss": 0.7345, "lr": 7.887246273294167e-05, "epoch": 0.5086901229334464, "percentage": 17.01, "elapsed_time": "2:14:29", "remaining_time": "10:56:20"}
+{"current_steps": 76, "total_steps": 441, "loss": 0.7346, "lr": 7.87964262627122e-05, "epoch": 0.5154726579058924, "percentage": 17.23, "elapsed_time": "2:16:16", "remaining_time": "10:54:29"}
+{"current_steps": 77, "total_steps": 441, "loss": 0.7313, "lr": 7.871794805585427e-05, "epoch": 0.5222551928783383, "percentage": 17.46, "elapsed_time": "2:18:04", "remaining_time": "10:52:41"}
+{"current_steps": 78, "total_steps": 441, "loss": 0.7217, "lr": 7.863703305156273e-05, "epoch": 0.5290377278507842, "percentage": 17.69, "elapsed_time": "2:19:51", "remaining_time": "10:50:53"}
+{"current_steps": 79, "total_steps": 441, "loss": 0.7338, "lr": 7.855368634239769e-05, "epoch": 0.5358202628232301, "percentage": 17.91, "elapsed_time": "2:21:38", "remaining_time": "10:49:03"}
+{"current_steps": 80, "total_steps": 441, "loss": 0.7275, "lr": 7.846791317396373e-05, "epoch": 0.5426027977956761, "percentage": 18.14, "elapsed_time": "2:23:25", "remaining_time": "10:47:12"}
+{"current_steps": 81, "total_steps": 441, "loss": 0.7459, "lr": 7.837971894457991e-05, "epoch": 0.5493853327681221, "percentage": 18.37, "elapsed_time": "2:25:12", "remaining_time": "10:45:20"}
+{"current_steps": 82, "total_steps": 441, "loss": 0.7176, "lr": 7.828910920493995e-05, "epoch": 0.556167867740568, "percentage": 18.59, "elapsed_time": "2:26:59", "remaining_time": "10:43:31"}
+{"current_steps": 83, "total_steps": 441, "loss": 0.7378, "lr": 7.819608965776295e-05, "epoch": 0.562950402713014, "percentage": 18.82, "elapsed_time": "2:28:46", "remaining_time": "10:41:41"}
+{"current_steps": 84, "total_steps": 441, "loss": 0.7235, "lr": 7.810066615743443e-05, "epoch": 0.56973293768546, "percentage": 19.05, "elapsed_time": "2:30:33", "remaining_time": "10:39:52"}
+{"current_steps": 85, "total_steps": 441, "loss": 0.7245, "lr": 7.800284470963783e-05, "epoch": 0.5765154726579059, "percentage": 19.27, "elapsed_time": "2:32:20", "remaining_time": "10:38:03"}
+{"current_steps": 86, "total_steps": 441, "loss": 0.7358, "lr": 7.790263147097661e-05, "epoch": 0.5832980076303519, "percentage": 19.5, "elapsed_time": "2:34:07", "remaining_time": "10:36:13"}
+{"current_steps": 87, "total_steps": 441, "loss": 0.7222, "lr": 7.780003274858674e-05, "epoch": 0.5900805426027977, "percentage": 19.73, "elapsed_time": "2:35:55", "remaining_time": "10:34:25"}
+{"current_steps": 88, "total_steps": 441, "loss": 0.716, "lr": 7.769505499973977e-05, "epoch": 0.5968630775752437, "percentage": 19.95, "elapsed_time": "2:37:42", "remaining_time": "10:32:36"}
+{"current_steps": 89, "total_steps": 441, "loss": 0.7268, "lr": 7.758770483143634e-05, "epoch": 0.6036456125476897, "percentage": 20.18, "elapsed_time": "2:39:29", "remaining_time": "10:30:47"}
+{"current_steps": 90, "total_steps": 441, "loss": 0.7407, "lr": 7.747798899999048e-05, "epoch": 0.6104281475201356, "percentage": 20.41, "elapsed_time": "2:41:16", "remaining_time": "10:28:56"}
+{"current_steps": 91, "total_steps": 441, "loss": 0.7326, "lr": 7.736591441060427e-05, "epoch": 0.6172106824925816, "percentage": 20.63, "elapsed_time": "2:43:02", "remaining_time": "10:27:06"}
+{"current_steps": 92, "total_steps": 441, "loss": 0.7336, "lr": 7.725148811693336e-05, "epoch": 0.6239932174650276, "percentage": 20.86, "elapsed_time": "2:44:49", "remaining_time": "10:25:17"}
+{"current_steps": 93, "total_steps": 441, "loss": 0.7173, "lr": 7.71347173206429e-05, "epoch": 0.6307757524374735, "percentage": 21.09, "elapsed_time": "2:46:36", "remaining_time": "10:23:27"}
+{"current_steps": 94, "total_steps": 441, "loss": 0.7303, "lr": 7.701560937095445e-05, "epoch": 0.6375582874099195, "percentage": 21.32, "elapsed_time": "2:48:23", "remaining_time": "10:21:38"}
+{"current_steps": 95, "total_steps": 441, "loss": 0.7185, "lr": 7.689417176418327e-05, "epoch": 0.6443408223823655, "percentage": 21.54, "elapsed_time": "2:50:11", "remaining_time": "10:19:51"}
+{"current_steps": 96, "total_steps": 441, "loss": 0.7357, "lr": 7.677041214326663e-05, "epoch": 0.6511233573548114, "percentage": 21.77, "elapsed_time": "2:51:58", "remaining_time": "10:18:01"}
+{"current_steps": 97, "total_steps": 441, "loss": 0.7155, "lr": 7.664433829728279e-05, "epoch": 0.6579058923272573, "percentage": 22.0, "elapsed_time": "2:53:46", "remaining_time": "10:16:15"}
+{"current_steps": 98, "total_steps": 441, "loss": 0.7109, "lr": 7.651595816096071e-05, "epoch": 0.6646884272997032, "percentage": 22.22, "elapsed_time": "2:55:32", "remaining_time": "10:14:25"}
+{"current_steps": 99, "total_steps": 441, "loss": 0.7333, "lr": 7.638527981418075e-05, "epoch": 0.6714709622721492, "percentage": 22.45, "elapsed_time": "2:57:19", "remaining_time": "10:12:34"}
+{"current_steps": 100, "total_steps": 441, "loss": 0.7097, "lr": 7.625231148146601e-05, "epoch": 0.6782534972445952, "percentage": 22.68, "elapsed_time": "2:59:06", "remaining_time": "10:10:46"}
+{"current_steps": 101, "total_steps": 441, "loss": 0.7128, "lr": 7.611706153146486e-05, "epoch": 0.6850360322170411, "percentage": 22.9, "elapsed_time": "3:00:53", "remaining_time": "10:08:55"}
+{"current_steps": 102, "total_steps": 441, "loss": 0.7241, "lr": 7.597953847642413e-05, "epoch": 0.6918185671894871, "percentage": 23.13, "elapsed_time": "3:02:40", "remaining_time": "10:07:06"}
+{"current_steps": 103, "total_steps": 441, "loss": 0.7189, "lr": 7.583975097165344e-05, "epoch": 0.698601102161933, "percentage": 23.36, "elapsed_time": "3:04:26", "remaining_time": "10:05:16"}
+{"current_steps": 104, "total_steps": 441, "loss": 0.7145, "lr": 7.56977078149804e-05, "epoch": 0.705383637134379, "percentage": 23.58, "elapsed_time": "3:06:13", "remaining_time": "10:03:26"}
+{"current_steps": 105, "total_steps": 441, "loss": 0.7107, "lr": 7.555341794619695e-05, "epoch": 0.712166172106825, "percentage": 23.81, "elapsed_time": "3:08:02", "remaining_time": "10:01:43"}
+{"current_steps": 106, "total_steps": 441, "loss": 0.703, "lr": 7.540689044649666e-05, "epoch": 0.7189487070792708, "percentage": 24.04, "elapsed_time": "3:09:51", "remaining_time": "10:00:00"}
+{"current_steps": 107, "total_steps": 441, "loss": 0.7127, "lr": 7.525813453790328e-05, "epoch": 0.7257312420517168, "percentage": 24.26, "elapsed_time": "3:11:38", "remaining_time": "9:58:11"}
+{"current_steps": 108, "total_steps": 441, "loss": 0.7052, "lr": 7.510715958269023e-05, "epoch": 0.7325137770241628, "percentage": 24.49, "elapsed_time": "3:13:28", "remaining_time": "9:56:33"}
+{"current_steps": 109, "total_steps": 441, "loss": 0.7109, "lr": 7.49539750827914e-05, "epoch": 0.7392963119966087, "percentage": 24.72, "elapsed_time": "3:15:19", "remaining_time": "9:54:56"}
+{"current_steps": 110, "total_steps": 441, "loss": 0.7037, "lr": 7.479859067920317e-05, "epoch": 0.7460788469690547, "percentage": 24.94, "elapsed_time": "3:17:06", "remaining_time": "9:53:06"}
+{"current_steps": 111, "total_steps": 441, "loss": 0.7075, "lr": 7.464101615137756e-05, "epoch": 0.7528613819415007, "percentage": 25.17, "elapsed_time": "3:18:53", "remaining_time": "9:51:18"}
+{"current_steps": 112, "total_steps": 441, "loss": 0.7204, "lr": 7.448126141660678e-05, "epoch": 0.7596439169139466, "percentage": 25.4, "elapsed_time": "3:20:41", "remaining_time": "9:49:31"}
+{"current_steps": 113, "total_steps": 441, "loss": 0.7129, "lr": 7.431933652939909e-05, "epoch": 0.7664264518863926, "percentage": 25.62, "elapsed_time": "3:22:28", "remaining_time": "9:47:42"}
+{"current_steps": 114, "total_steps": 441, "loss": 0.708, "lr": 7.415525168084593e-05, "epoch": 0.7732089868588385, "percentage": 25.85, "elapsed_time": "3:24:15", "remaining_time": "9:45:54"}
+{"current_steps": 115, "total_steps": 441, "loss": 0.7102, "lr": 7.398901719798059e-05, "epoch": 0.7799915218312844, "percentage": 26.08, "elapsed_time": "3:26:02", "remaining_time": "9:44:06"}
+{"current_steps": 116, "total_steps": 441, "loss": 0.7098, "lr": 7.382064354312818e-05, "epoch": 0.7867740568037304, "percentage": 26.3, "elapsed_time": "3:27:51", "remaining_time": "9:42:20"}
+{"current_steps": 117, "total_steps": 441, "loss": 0.7029, "lr": 7.365014131324725e-05, "epoch": 0.7935565917761763, "percentage": 26.53, "elapsed_time": "3:29:38", "remaining_time": "9:40:32"}
+{"current_steps": 118, "total_steps": 441, "loss": 0.6972, "lr": 7.34775212392628e-05, "epoch": 0.8003391267486223, "percentage": 26.76, "elapsed_time": "3:31:25", "remaining_time": "9:38:43"}
+{"current_steps": 119, "total_steps": 441, "loss": 0.7018, "lr": 7.330279418539086e-05, "epoch": 0.8071216617210683, "percentage": 26.98, "elapsed_time": "3:33:12", "remaining_time": "9:36:55"}
+{"current_steps": 120, "total_steps": 441, "loss": 0.6981, "lr": 7.312597114845483e-05, "epoch": 0.8139041966935142, "percentage": 27.21, "elapsed_time": "3:34:59", "remaining_time": "9:35:07"}
+{"current_steps": 121, "total_steps": 441, "loss": 0.7195, "lr": 7.294706325719331e-05, "epoch": 0.8206867316659602, "percentage": 27.44, "elapsed_time": "3:36:47", "remaining_time": "9:33:19"}
+{"current_steps": 122, "total_steps": 441, "loss": 0.7033, "lr": 7.276608177155968e-05, "epoch": 0.8274692666384061, "percentage": 27.66, "elapsed_time": "3:38:34", "remaining_time": "9:31:30"}
+{"current_steps": 123, "total_steps": 441, "loss": 0.6984, "lr": 7.258303808201343e-05, "epoch": 0.8342518016108521, "percentage": 27.89, "elapsed_time": "3:40:21", "remaining_time": "9:29:43"}
+{"current_steps": 124, "total_steps": 441, "loss": 0.6921, "lr": 7.239794370880335e-05, "epoch": 0.841034336583298, "percentage": 28.12, "elapsed_time": "3:42:09", "remaining_time": "9:27:56"}
+{"current_steps": 125, "total_steps": 441, "loss": 0.6988, "lr": 7.221081030124235e-05, "epoch": 0.8478168715557439, "percentage": 28.34, "elapsed_time": "3:43:56", "remaining_time": "9:26:07"}
+{"current_steps": 126, "total_steps": 441, "loss": 0.6972, "lr": 7.202164963697442e-05, "epoch": 0.8545994065281899, "percentage": 28.57, "elapsed_time": "3:45:43", "remaining_time": "9:24:18"}
+{"current_steps": 127, "total_steps": 441, "loss": 0.7004, "lr": 7.183047362123329e-05, "epoch": 0.8613819415006359, "percentage": 28.8, "elapsed_time": "3:47:32", "remaining_time": "9:22:35"}
+{"current_steps": 128, "total_steps": 441, "loss": 0.6956, "lr": 7.163729428609318e-05, "epoch": 0.8681644764730818, "percentage": 29.02, "elapsed_time": "3:49:25", "remaining_time": "9:21:00"}
+{"current_steps": 129, "total_steps": 441, "loss": 0.7089, "lr": 7.144212378971151e-05, "epoch": 0.8749470114455278, "percentage": 29.25, "elapsed_time": "3:51:13", "remaining_time": "9:19:14"}
+{"current_steps": 130, "total_steps": 441, "loss": 0.7025, "lr": 7.124497441556374e-05, "epoch": 0.8817295464179737, "percentage": 29.48, "elapsed_time": "3:53:01", "remaining_time": "9:17:27"}
+{"current_steps": 131, "total_steps": 441, "loss": 0.7093, "lr": 7.104585857167028e-05, "epoch": 0.8885120813904197, "percentage": 29.71, "elapsed_time": "3:54:48", "remaining_time": "9:15:38"}
+{"current_steps": 132, "total_steps": 441, "loss": 0.7, "lr": 7.084478878981552e-05, "epoch": 0.8952946163628657, "percentage": 29.93, "elapsed_time": "3:56:34", "remaining_time": "9:13:49"}
+{"current_steps": 133, "total_steps": 441, "loss": 0.695, "lr": 7.064177772475912e-05, "epoch": 0.9020771513353115, "percentage": 30.16, "elapsed_time": "3:58:21", "remaining_time": "9:12:00"}
+{"current_steps": 134, "total_steps": 441, "loss": 0.6938, "lr": 7.043683815343967e-05, "epoch": 0.9088596863077575, "percentage": 30.39, "elapsed_time": "4:00:08", "remaining_time": "9:10:11"}
+{"current_steps": 135, "total_steps": 441, "loss": 0.6924, "lr": 7.022998297417034e-05, "epoch": 0.9156422212802034, "percentage": 30.61, "elapsed_time": "4:01:55", "remaining_time": "9:08:22"}
+{"current_steps": 136, "total_steps": 441, "loss": 0.6988, "lr": 7.00212252058273e-05, "epoch": 0.9224247562526494, "percentage": 30.84, "elapsed_time": "4:03:42", "remaining_time": "9:06:33"}
+{"current_steps": 137, "total_steps": 441, "loss": 0.6966, "lr": 6.98105779870302e-05, "epoch": 0.9292072912250954, "percentage": 31.07, "elapsed_time": "4:05:29", "remaining_time": "9:04:44"}
+{"current_steps": 138, "total_steps": 441, "loss": 0.6995, "lr": 6.959805457531536e-05, "epoch": 0.9359898261975413, "percentage": 31.29, "elapsed_time": "4:07:16", "remaining_time": "9:02:56"}
+{"current_steps": 139, "total_steps": 441, "loss": 0.689, "lr": 6.938366834630133e-05, "epoch": 0.9427723611699873, "percentage": 31.52, "elapsed_time": "4:09:03", "remaining_time": "9:01:07"}
+{"current_steps": 140, "total_steps": 441, "loss": 0.699, "lr": 6.916743279284709e-05, "epoch": 0.9495548961424333, "percentage": 31.75, "elapsed_time": "4:10:51", "remaining_time": "8:59:19"}
+{"current_steps": 141, "total_steps": 441, "loss": 0.6987, "lr": 6.89493615242028e-05, "epoch": 0.9563374311148792, "percentage": 31.97, "elapsed_time": "4:12:38", "remaining_time": "8:57:32"}
+{"current_steps": 142, "total_steps": 441, "loss": 0.7078, "lr": 6.872946826515338e-05, "epoch": 0.9631199660873251, "percentage": 32.2, "elapsed_time": "4:14:26", "remaining_time": "8:55:46"}
+{"current_steps": 143, "total_steps": 441, "loss": 0.6951, "lr": 6.850776685515453e-05, "epoch": 0.969902501059771, "percentage": 32.43, "elapsed_time": "4:16:15", "remaining_time": "8:54:00"}
+{"current_steps": 144, "total_steps": 441, "loss": 0.7059, "lr": 6.828427124746191e-05, "epoch": 0.976685036032217, "percentage": 32.65, "elapsed_time": "4:18:03", "remaining_time": "8:52:13"}
+{"current_steps": 145, "total_steps": 441, "loss": 0.7034, "lr": 6.805899550825285e-05, "epoch": 0.983467571004663, "percentage": 32.88, "elapsed_time": "4:19:53", "remaining_time": "8:50:31"}
+{"current_steps": 146, "total_steps": 441, "loss": 0.688, "lr": 6.78319538157411e-05, "epoch": 0.9902501059771089, "percentage": 33.11, "elapsed_time": "4:21:42", "remaining_time": "8:48:47"}
+{"current_steps": 147, "total_steps": 441, "loss": 0.6996, "lr": 6.760316045928449e-05, "epoch": 0.9970326409495549, "percentage": 33.33, "elapsed_time": "4:23:29", "remaining_time": "8:46:59"}
+{"current_steps": 148, "total_steps": 441, "loss": 1.0973, "lr": 6.737262983848554e-05, "epoch": 1.0038151759220009, "percentage": 33.56, "elapsed_time": "4:26:21", "remaining_time": "8:47:18"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6002b6ba3a49bf6c191e7d1f5a3b1fc7f8b4aff199c1554b3620b36487075c9e
+size 7288