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:c0093b3cc62007ed8805594a0177cb0db61981d1831423eefa26cdd445ed97f2
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d5878b01db985f7d82df769dd3ce2e8dd2b36ee7b7078d5f0b0a65f4bd7d62
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1afa237f771942e3061f6f8952a96ae7e59f9f888e621e678c6ee2f2c71234dd
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:437d366e2f0922597b0240a1c7f1807ad328ec931ec71b9cbf753dda974b4076
+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 +1,163 @@
+{"current_steps": 1, "total_steps": 805, "loss": 1.6775, "lr": 9.876543209876544e-07, "epoch": 0.0061823802163833074, "percentage": 0.12, "elapsed_time": "0:01:34", "remaining_time": "21:10:05"}
+{"current_steps": 2, "total_steps": 805, "loss": 1.6824, "lr": 1.9753086419753087e-06, "epoch": 0.012364760432766615, "percentage": 0.25, "elapsed_time": "0:02:25", "remaining_time": "16:16:08"}
+{"current_steps": 3, "total_steps": 805, "loss": 1.6745, "lr": 2.962962962962963e-06, "epoch": 0.01854714064914992, "percentage": 0.37, "elapsed_time": "0:03:17", "remaining_time": "14:38:14"}
+{"current_steps": 4, "total_steps": 805, "loss": 1.6421, "lr": 3.9506172839506175e-06, "epoch": 0.02472952086553323, "percentage": 0.5, "elapsed_time": "0:04:08", "remaining_time": "13:48:37"}
+{"current_steps": 5, "total_steps": 805, "loss": 1.5691, "lr": 4.938271604938272e-06, "epoch": 0.030911901081916538, "percentage": 0.62, "elapsed_time": "0:04:59", "remaining_time": "13:18:34"}
+{"current_steps": 6, "total_steps": 805, "loss": 1.5004, "lr": 5.925925925925926e-06, "epoch": 0.03709428129829984, "percentage": 0.75, "elapsed_time": "0:05:50", "remaining_time": "12:58:18"}
+{"current_steps": 7, "total_steps": 805, "loss": 1.4777, "lr": 6.913580246913581e-06, "epoch": 0.04327666151468315, "percentage": 0.87, "elapsed_time": "0:06:41", "remaining_time": "12:43:35"}
+{"current_steps": 8, "total_steps": 805, "loss": 1.4747, "lr": 7.901234567901235e-06, "epoch": 0.04945904173106646, "percentage": 0.99, "elapsed_time": "0:07:32", "remaining_time": "12:31:54"}
+{"current_steps": 9, "total_steps": 805, "loss": 1.4418, "lr": 8.888888888888888e-06, "epoch": 0.05564142194744977, "percentage": 1.12, "elapsed_time": "0:08:23", "remaining_time": "12:22:37"}
+{"current_steps": 10, "total_steps": 805, "loss": 1.3952, "lr": 9.876543209876543e-06, "epoch": 0.061823802163833076, "percentage": 1.24, "elapsed_time": "0:09:15", "remaining_time": "12:15:41"}
+{"current_steps": 11, "total_steps": 805, "loss": 1.3959, "lr": 1.0864197530864198e-05, "epoch": 0.06800618238021638, "percentage": 1.37, "elapsed_time": "0:10:06", "remaining_time": "12:09:21"}
+{"current_steps": 12, "total_steps": 805, "loss": 1.363, "lr": 1.1851851851851852e-05, "epoch": 0.07418856259659969, "percentage": 1.49, "elapsed_time": "0:10:57", "remaining_time": "12:03:53"}
+{"current_steps": 13, "total_steps": 805, "loss": 1.3392, "lr": 1.2839506172839507e-05, "epoch": 0.080370942812983, "percentage": 1.61, "elapsed_time": "0:11:55", "remaining_time": "12:06:29"}
+{"current_steps": 14, "total_steps": 805, "loss": 1.3045, "lr": 1.3827160493827162e-05, "epoch": 0.0865533230293663, "percentage": 1.74, "elapsed_time": "0:12:46", "remaining_time": "12:01:47"}
+{"current_steps": 15, "total_steps": 805, "loss": 1.2877, "lr": 1.4814814814814815e-05, "epoch": 0.09273570324574962, "percentage": 1.86, "elapsed_time": "0:13:37", "remaining_time": "11:57:31"}
+{"current_steps": 16, "total_steps": 805, "loss": 1.2683, "lr": 1.580246913580247e-05, "epoch": 0.09891808346213292, "percentage": 1.99, "elapsed_time": "0:14:28", "remaining_time": "11:53:52"}
+{"current_steps": 17, "total_steps": 805, "loss": 1.2722, "lr": 1.6790123456790123e-05, "epoch": 0.10510046367851623, "percentage": 2.11, "elapsed_time": "0:15:19", "remaining_time": "11:50:37"}
+{"current_steps": 18, "total_steps": 805, "loss": 1.2427, "lr": 1.7777777777777777e-05, "epoch": 0.11128284389489954, "percentage": 2.24, "elapsed_time": "0:16:11", "remaining_time": "11:47:34"}
+{"current_steps": 19, "total_steps": 805, "loss": 1.238, "lr": 1.8765432098765433e-05, "epoch": 0.11746522411128284, "percentage": 2.36, "elapsed_time": "0:17:01", "remaining_time": "11:44:34"}
+{"current_steps": 20, "total_steps": 805, "loss": 1.2214, "lr": 1.9753086419753087e-05, "epoch": 0.12364760432766615, "percentage": 2.48, "elapsed_time": "0:17:52", "remaining_time": "11:41:50"}
+{"current_steps": 21, "total_steps": 805, "loss": 1.21, "lr": 2.074074074074074e-05, "epoch": 0.12982998454404945, "percentage": 2.61, "elapsed_time": "0:18:43", "remaining_time": "11:39:15"}
+{"current_steps": 22, "total_steps": 805, "loss": 1.1865, "lr": 2.1728395061728397e-05, "epoch": 0.13601236476043277, "percentage": 2.73, "elapsed_time": "0:19:34", "remaining_time": "11:36:55"}
+{"current_steps": 23, "total_steps": 805, "loss": 1.195, "lr": 2.271604938271605e-05, "epoch": 0.14219474497681608, "percentage": 2.86, "elapsed_time": "0:20:25", "remaining_time": "11:34:37"}
+{"current_steps": 24, "total_steps": 805, "loss": 1.1696, "lr": 2.3703703703703703e-05, "epoch": 0.14837712519319937, "percentage": 2.98, "elapsed_time": "0:21:16", "remaining_time": "11:32:28"}
+{"current_steps": 25, "total_steps": 805, "loss": 1.1892, "lr": 2.469135802469136e-05, "epoch": 0.1545595054095827, "percentage": 3.11, "elapsed_time": "0:22:08", "remaining_time": "11:30:39"}
+{"current_steps": 26, "total_steps": 805, "loss": 1.1793, "lr": 2.5679012345679013e-05, "epoch": 0.160741885625966, "percentage": 3.23, "elapsed_time": "0:22:59", "remaining_time": "11:28:57"}
+{"current_steps": 27, "total_steps": 805, "loss": 1.1664, "lr": 2.6666666666666667e-05, "epoch": 0.16692426584234932, "percentage": 3.35, "elapsed_time": "0:23:52", "remaining_time": "11:27:46"}
+{"current_steps": 28, "total_steps": 805, "loss": 1.1573, "lr": 2.7654320987654323e-05, "epoch": 0.1731066460587326, "percentage": 3.48, "elapsed_time": "0:24:49", "remaining_time": "11:29:00"}
+{"current_steps": 29, "total_steps": 805, "loss": 1.1501, "lr": 2.8641975308641977e-05, "epoch": 0.17928902627511592, "percentage": 3.6, "elapsed_time": "0:25:40", "remaining_time": "11:27:13"}
+{"current_steps": 30, "total_steps": 805, "loss": 1.1608, "lr": 2.962962962962963e-05, "epoch": 0.18547140649149924, "percentage": 3.73, "elapsed_time": "0:26:32", "remaining_time": "11:25:26"}
+{"current_steps": 31, "total_steps": 805, "loss": 1.1451, "lr": 3.061728395061729e-05, "epoch": 0.19165378670788252, "percentage": 3.85, "elapsed_time": "0:27:23", "remaining_time": "11:23:43"}
+{"current_steps": 32, "total_steps": 805, "loss": 1.1408, "lr": 3.160493827160494e-05, "epoch": 0.19783616692426584, "percentage": 3.98, "elapsed_time": "0:28:13", "remaining_time": "11:21:58"}
+{"current_steps": 33, "total_steps": 805, "loss": 1.1346, "lr": 3.259259259259259e-05, "epoch": 0.20401854714064915, "percentage": 4.1, "elapsed_time": "0:29:04", "remaining_time": "11:20:15"}
+{"current_steps": 34, "total_steps": 805, "loss": 1.1582, "lr": 3.3580246913580247e-05, "epoch": 0.21020092735703247, "percentage": 4.22, "elapsed_time": "0:29:55", "remaining_time": "11:18:37"}
+{"current_steps": 35, "total_steps": 805, "loss": 1.1558, "lr": 3.45679012345679e-05, "epoch": 0.21638330757341576, "percentage": 4.35, "elapsed_time": "0:30:46", "remaining_time": "11:17:05"}
+{"current_steps": 36, "total_steps": 805, "loss": 1.1431, "lr": 3.555555555555555e-05, "epoch": 0.22256568778979907, "percentage": 4.47, "elapsed_time": "0:31:37", "remaining_time": "11:15:37"}
+{"current_steps": 37, "total_steps": 805, "loss": 1.1463, "lr": 3.654320987654321e-05, "epoch": 0.2287480680061824, "percentage": 4.6, "elapsed_time": "0:32:28", "remaining_time": "11:14:09"}
+{"current_steps": 38, "total_steps": 805, "loss": 1.1307, "lr": 3.7530864197530867e-05, "epoch": 0.23493044822256567, "percentage": 4.72, "elapsed_time": "0:33:19", "remaining_time": "11:12:42"}
+{"current_steps": 39, "total_steps": 805, "loss": 1.1272, "lr": 3.851851851851852e-05, "epoch": 0.241112828438949, "percentage": 4.84, "elapsed_time": "0:34:10", "remaining_time": "11:11:21"}
+{"current_steps": 40, "total_steps": 805, "loss": 1.1137, "lr": 3.950617283950617e-05, "epoch": 0.2472952086553323, "percentage": 4.97, "elapsed_time": "0:35:02", "remaining_time": "11:10:02"}
+{"current_steps": 41, "total_steps": 805, "loss": 1.1247, "lr": 4.049382716049383e-05, "epoch": 0.2534775888717156, "percentage": 5.09, "elapsed_time": "0:35:53", "remaining_time": "11:08:52"}
+{"current_steps": 42, "total_steps": 805, "loss": 1.1334, "lr": 4.148148148148148e-05, "epoch": 0.2596599690880989, "percentage": 5.22, "elapsed_time": "0:36:46", "remaining_time": "11:08:12"}
+{"current_steps": 43, "total_steps": 805, "loss": 1.1114, "lr": 4.246913580246914e-05, "epoch": 0.26584234930448225, "percentage": 5.34, "elapsed_time": "0:37:45", "remaining_time": "11:09:12"}
+{"current_steps": 44, "total_steps": 805, "loss": 1.1182, "lr": 4.345679012345679e-05, "epoch": 0.27202472952086554, "percentage": 5.47, "elapsed_time": "0:38:36", "remaining_time": "11:07:52"}
+{"current_steps": 45, "total_steps": 805, "loss": 1.1157, "lr": 4.444444444444445e-05, "epoch": 0.2782071097372488, "percentage": 5.59, "elapsed_time": "0:39:28", "remaining_time": "11:06:33"}
+{"current_steps": 46, "total_steps": 805, "loss": 1.1158, "lr": 4.54320987654321e-05, "epoch": 0.28438948995363217, "percentage": 5.71, "elapsed_time": "0:40:19", "remaining_time": "11:05:14"}
+{"current_steps": 47, "total_steps": 805, "loss": 1.1214, "lr": 4.641975308641976e-05, "epoch": 0.29057187017001546, "percentage": 5.84, "elapsed_time": "0:41:09", "remaining_time": "11:03:54"}
+{"current_steps": 48, "total_steps": 805, "loss": 1.1072, "lr": 4.7407407407407407e-05, "epoch": 0.29675425038639874, "percentage": 5.96, "elapsed_time": "0:42:00", "remaining_time": "11:02:35"}
+{"current_steps": 49, "total_steps": 805, "loss": 1.1125, "lr": 4.8395061728395067e-05, "epoch": 0.3029366306027821, "percentage": 6.09, "elapsed_time": "0:42:52", "remaining_time": "11:01:24"}
+{"current_steps": 50, "total_steps": 805, "loss": 1.1076, "lr": 4.938271604938272e-05, "epoch": 0.3091190108191654, "percentage": 6.21, "elapsed_time": "0:43:43", "remaining_time": "11:00:11"}
+{"current_steps": 51, "total_steps": 805, "loss": 1.1039, "lr": 5.037037037037037e-05, "epoch": 0.31530139103554866, "percentage": 6.34, "elapsed_time": "0:44:34", "remaining_time": "10:58:59"}
+{"current_steps": 52, "total_steps": 805, "loss": 1.1083, "lr": 5.1358024691358027e-05, "epoch": 0.321483771251932, "percentage": 6.46, "elapsed_time": "0:45:25", "remaining_time": "10:57:51"}
+{"current_steps": 53, "total_steps": 805, "loss": 1.0969, "lr": 5.234567901234569e-05, "epoch": 0.3276661514683153, "percentage": 6.58, "elapsed_time": "0:46:16", "remaining_time": "10:56:39"}
+{"current_steps": 54, "total_steps": 805, "loss": 1.1009, "lr": 5.333333333333333e-05, "epoch": 0.33384853168469864, "percentage": 6.71, "elapsed_time": "0:47:07", "remaining_time": "10:55:29"}
+{"current_steps": 55, "total_steps": 805, "loss": 1.1071, "lr": 5.432098765432099e-05, "epoch": 0.3400309119010819, "percentage": 6.83, "elapsed_time": "0:47:59", "remaining_time": "10:54:19"}
+{"current_steps": 56, "total_steps": 805, "loss": 1.1034, "lr": 5.5308641975308647e-05, "epoch": 0.3462132921174652, "percentage": 6.96, "elapsed_time": "0:48:50", "remaining_time": "10:53:10"}
+{"current_steps": 57, "total_steps": 805, "loss": 1.0926, "lr": 5.62962962962963e-05, "epoch": 0.35239567233384855, "percentage": 7.08, "elapsed_time": "0:49:44", "remaining_time": "10:52:40"}
+{"current_steps": 58, "total_steps": 805, "loss": 1.0998, "lr": 5.728395061728395e-05, "epoch": 0.35857805255023184, "percentage": 7.2, "elapsed_time": "0:50:42", "remaining_time": "10:53:11"}
+{"current_steps": 59, "total_steps": 805, "loss": 1.0936, "lr": 5.827160493827161e-05, "epoch": 0.36476043276661513, "percentage": 7.33, "elapsed_time": "0:51:34", "remaining_time": "10:52:00"}
+{"current_steps": 60, "total_steps": 805, "loss": 1.0865, "lr": 5.925925925925926e-05, "epoch": 0.37094281298299847, "percentage": 7.45, "elapsed_time": "0:52:24", "remaining_time": "10:50:49"}
+{"current_steps": 61, "total_steps": 805, "loss": 1.094, "lr": 6.024691358024692e-05, "epoch": 0.37712519319938176, "percentage": 7.58, "elapsed_time": "0:53:15", "remaining_time": "10:49:40"}
+{"current_steps": 62, "total_steps": 805, "loss": 1.0724, "lr": 6.123456790123457e-05, "epoch": 0.38330757341576505, "percentage": 7.7, "elapsed_time": "0:54:07", "remaining_time": "10:48:33"}
+{"current_steps": 63, "total_steps": 805, "loss": 1.1097, "lr": 6.222222222222223e-05, "epoch": 0.3894899536321484, "percentage": 7.83, "elapsed_time": "0:54:58", "remaining_time": "10:47:26"}
+{"current_steps": 64, "total_steps": 805, "loss": 1.0972, "lr": 6.320987654320988e-05, "epoch": 0.3956723338485317, "percentage": 7.95, "elapsed_time": "0:55:49", "remaining_time": "10:46:21"}
+{"current_steps": 65, "total_steps": 805, "loss": 1.0954, "lr": 6.419753086419754e-05, "epoch": 0.401854714064915, "percentage": 8.07, "elapsed_time": "0:56:40", "remaining_time": "10:45:18"}
+{"current_steps": 66, "total_steps": 805, "loss": 1.0887, "lr": 6.518518518518519e-05, "epoch": 0.4080370942812983, "percentage": 8.2, "elapsed_time": "0:57:31", "remaining_time": "10:44:11"}
+{"current_steps": 67, "total_steps": 805, "loss": 1.0847, "lr": 6.617283950617285e-05, "epoch": 0.4142194744976816, "percentage": 8.32, "elapsed_time": "0:58:23", "remaining_time": "10:43:09"}
+{"current_steps": 68, "total_steps": 805, "loss": 1.1009, "lr": 6.716049382716049e-05, "epoch": 0.42040185471406494, "percentage": 8.45, "elapsed_time": "0:59:14", "remaining_time": "10:42:02"}
+{"current_steps": 69, "total_steps": 805, "loss": 1.092, "lr": 6.814814814814815e-05, "epoch": 0.4265842349304482, "percentage": 8.57, "elapsed_time": "1:00:05", "remaining_time": "10:40:58"}
+{"current_steps": 70, "total_steps": 805, "loss": 1.0721, "lr": 6.91358024691358e-05, "epoch": 0.4327666151468315, "percentage": 8.7, "elapsed_time": "1:00:56", "remaining_time": "10:39:55"}
+{"current_steps": 71, "total_steps": 805, "loss": 1.0752, "lr": 7.012345679012346e-05, "epoch": 0.43894899536321486, "percentage": 8.82, "elapsed_time": "1:01:47", "remaining_time": "10:38:49"}
+{"current_steps": 72, "total_steps": 805, "loss": 1.0763, "lr": 7.11111111111111e-05, "epoch": 0.44513137557959814, "percentage": 8.94, "elapsed_time": "1:02:42", "remaining_time": "10:38:21"}
+{"current_steps": 73, "total_steps": 805, "loss": 1.0855, "lr": 7.209876543209877e-05, "epoch": 0.45131375579598143, "percentage": 9.07, "elapsed_time": "1:03:40", "remaining_time": "10:38:32"}
+{"current_steps": 74, "total_steps": 805, "loss": 1.0781, "lr": 7.308641975308643e-05, "epoch": 0.4574961360123648, "percentage": 9.19, "elapsed_time": "1:04:31", "remaining_time": "10:37:27"}
+{"current_steps": 75, "total_steps": 805, "loss": 1.0864, "lr": 7.407407407407409e-05, "epoch": 0.46367851622874806, "percentage": 9.32, "elapsed_time": "1:05:22", "remaining_time": "10:36:22"}
+{"current_steps": 76, "total_steps": 805, "loss": 1.077, "lr": 7.506172839506173e-05, "epoch": 0.46986089644513135, "percentage": 9.44, "elapsed_time": "1:06:13", "remaining_time": "10:35:17"}
+{"current_steps": 77, "total_steps": 805, "loss": 1.0873, "lr": 7.60493827160494e-05, "epoch": 0.4760432766615147, "percentage": 9.57, "elapsed_time": "1:07:04", "remaining_time": "10:34:13"}
+{"current_steps": 78, "total_steps": 805, "loss": 1.0912, "lr": 7.703703703703704e-05, "epoch": 0.482225656877898, "percentage": 9.69, "elapsed_time": "1:07:56", "remaining_time": "10:33:10"}
+{"current_steps": 79, "total_steps": 805, "loss": 1.0905, "lr": 7.80246913580247e-05, "epoch": 0.4884080370942813, "percentage": 9.81, "elapsed_time": "1:08:47", "remaining_time": "10:32:06"}
+{"current_steps": 80, "total_steps": 805, "loss": 1.0796, "lr": 7.901234567901235e-05, "epoch": 0.4945904173106646, "percentage": 9.94, "elapsed_time": "1:09:38", "remaining_time": "10:31:04"}
+{"current_steps": 81, "total_steps": 805, "loss": 1.094, "lr": 8e-05, "epoch": 0.500772797527048, "percentage": 10.06, "elapsed_time": "1:10:29", "remaining_time": "10:30:04"}
+{"current_steps": 82, "total_steps": 805, "loss": 1.1031, "lr": 7.999962342461635e-05, "epoch": 0.5069551777434312, "percentage": 10.19, "elapsed_time": "1:11:20", "remaining_time": "10:29:01"}
+{"current_steps": 83, "total_steps": 805, "loss": 1.0726, "lr": 7.999849370555585e-05, "epoch": 0.5131375579598145, "percentage": 10.31, "elapsed_time": "1:12:11", "remaining_time": "10:27:58"}
+{"current_steps": 84, "total_steps": 805, "loss": 1.0824, "lr": 7.999661086408972e-05, "epoch": 0.5193199381761978, "percentage": 10.43, "elapsed_time": "1:13:02", "remaining_time": "10:26:56"}
+{"current_steps": 85, "total_steps": 805, "loss": 1.0752, "lr": 7.999397493566954e-05, "epoch": 0.5255023183925811, "percentage": 10.56, "elapsed_time": "1:13:53", "remaining_time": "10:25:56"}
+{"current_steps": 86, "total_steps": 805, "loss": 1.0908, "lr": 7.99905859699266e-05, "epoch": 0.5316846986089645, "percentage": 10.68, "elapsed_time": "1:14:44", "remaining_time": "10:24:56"}
+{"current_steps": 87, "total_steps": 805, "loss": 1.0721, "lr": 7.998644403067097e-05, "epoch": 0.5378670788253478, "percentage": 10.81, "elapsed_time": "1:15:39", "remaining_time": "10:24:27"}
+{"current_steps": 88, "total_steps": 805, "loss": 1.0776, "lr": 7.998154919589024e-05, "epoch": 0.5440494590417311, "percentage": 10.93, "elapsed_time": "1:16:38", "remaining_time": "10:24:26"}
+{"current_steps": 89, "total_steps": 805, "loss": 1.0733, "lr": 7.997590155774815e-05, "epoch": 0.5502318392581144, "percentage": 11.06, "elapsed_time": "1:17:29", "remaining_time": "10:23:23"}
+{"current_steps": 90, "total_steps": 805, "loss": 1.0577, "lr": 7.996950122258277e-05, "epoch": 0.5564142194744977, "percentage": 11.18, "elapsed_time": "1:18:20", "remaining_time": "10:22:22"}
+{"current_steps": 91, "total_steps": 805, "loss": 1.0793, "lr": 7.996234831090451e-05, "epoch": 0.5625965996908809, "percentage": 11.3, "elapsed_time": "1:19:11", "remaining_time": "10:21:21"}
+{"current_steps": 92, "total_steps": 805, "loss": 1.0775, "lr": 7.995444295739394e-05, "epoch": 0.5687789799072643, "percentage": 11.43, "elapsed_time": "1:20:02", "remaining_time": "10:20:20"}
+{"current_steps": 93, "total_steps": 805, "loss": 1.0927, "lr": 7.994578531089908e-05, "epoch": 0.5749613601236476, "percentage": 11.55, "elapsed_time": "1:20:53", "remaining_time": "10:19:19"}
+{"current_steps": 94, "total_steps": 805, "loss": 1.1068, "lr": 7.99363755344328e-05, "epoch": 0.5811437403400309, "percentage": 11.68, "elapsed_time": "1:21:44", "remaining_time": "10:18:18"}
+{"current_steps": 95, "total_steps": 805, "loss": 1.0885, "lr": 7.99262138051696e-05, "epoch": 0.5873261205564142, "percentage": 11.8, "elapsed_time": "1:22:35", "remaining_time": "10:17:19"}
+{"current_steps": 96, "total_steps": 805, "loss": 1.0838, "lr": 7.991530031444231e-05, "epoch": 0.5935085007727975, "percentage": 11.93, "elapsed_time": "1:23:27", "remaining_time": "10:16:19"}
+{"current_steps": 97, "total_steps": 805, "loss": 1.0947, "lr": 7.990363526773856e-05, "epoch": 0.5996908809891809, "percentage": 12.05, "elapsed_time": "1:24:18", "remaining_time": "10:15:18"}
+{"current_steps": 98, "total_steps": 805, "loss": 1.0835, "lr": 7.98912188846968e-05, "epoch": 0.6058732612055642, "percentage": 12.17, "elapsed_time": "1:25:09", "remaining_time": "10:14:18"}
+{"current_steps": 99, "total_steps": 805, "loss": 1.0601, "lr": 7.987805139910226e-05, "epoch": 0.6120556414219475, "percentage": 12.3, "elapsed_time": "1:25:59", "remaining_time": "10:13:16"}
+{"current_steps": 100, "total_steps": 805, "loss": 1.0628, "lr": 7.986413305888247e-05, "epoch": 0.6182380216383307, "percentage": 12.42, "elapsed_time": "1:26:50", "remaining_time": "10:12:16"}
+{"current_steps": 101, "total_steps": 805, "loss": 1.0746, "lr": 7.984946412610265e-05, "epoch": 0.624420401854714, "percentage": 12.55, "elapsed_time": "1:27:42", "remaining_time": "10:11:21"}
+{"current_steps": 102, "total_steps": 805, "loss": 1.0712, "lr": 7.983404487696076e-05, "epoch": 0.6306027820710973, "percentage": 12.67, "elapsed_time": "1:28:38", "remaining_time": "10:10:58"}
+{"current_steps": 103, "total_steps": 805, "loss": 1.0555, "lr": 7.981787560178227e-05, "epoch": 0.6367851622874807, "percentage": 12.8, "elapsed_time": "1:29:38", "remaining_time": "10:10:59"}
+{"current_steps": 104, "total_steps": 805, "loss": 1.0705, "lr": 7.980095660501473e-05, "epoch": 0.642967542503864, "percentage": 12.92, "elapsed_time": "1:30:29", "remaining_time": "10:09:59"}
+{"current_steps": 105, "total_steps": 805, "loss": 1.0593, "lr": 7.978328820522204e-05, "epoch": 0.6491499227202473, "percentage": 13.04, "elapsed_time": "1:31:20", "remaining_time": "10:08:58"}
+{"current_steps": 106, "total_steps": 805, "loss": 1.0485, "lr": 7.976487073507839e-05, "epoch": 0.6553323029366306, "percentage": 13.17, "elapsed_time": "1:32:11", "remaining_time": "10:07:59"}
+{"current_steps": 107, "total_steps": 805, "loss": 1.0623, "lr": 7.974570454136212e-05, "epoch": 0.6615146831530139, "percentage": 13.29, "elapsed_time": "1:33:02", "remaining_time": "10:06:59"}
+{"current_steps": 108, "total_steps": 805, "loss": 1.06, "lr": 7.972578998494903e-05, "epoch": 0.6676970633693973, "percentage": 13.42, "elapsed_time": "1:33:54", "remaining_time": "10:06:00"}
+{"current_steps": 109, "total_steps": 805, "loss": 1.0646, "lr": 7.970512744080571e-05, "epoch": 0.6738794435857806, "percentage": 13.54, "elapsed_time": "1:34:45", "remaining_time": "10:05:00"}
+{"current_steps": 110, "total_steps": 805, "loss": 1.0578, "lr": 7.968371729798246e-05, "epoch": 0.6800618238021638, "percentage": 13.66, "elapsed_time": "1:35:36", "remaining_time": "10:04:02"}
+{"current_steps": 111, "total_steps": 805, "loss": 1.0495, "lr": 7.96615599596059e-05, "epoch": 0.6862442040185471, "percentage": 13.79, "elapsed_time": "1:36:27", "remaining_time": "10:03:03"}
+{"current_steps": 112, "total_steps": 805, "loss": 1.0482, "lr": 7.963865584287142e-05, "epoch": 0.6924265842349304, "percentage": 13.91, "elapsed_time": "1:37:18", "remaining_time": "10:02:04"}
+{"current_steps": 113, "total_steps": 805, "loss": 1.0478, "lr": 7.96150053790354e-05, "epoch": 0.6986089644513137, "percentage": 14.04, "elapsed_time": "1:38:09", "remaining_time": "10:01:06"}
+{"current_steps": 114, "total_steps": 805, "loss": 1.0644, "lr": 7.959060901340691e-05, "epoch": 0.7047913446676971, "percentage": 14.16, "elapsed_time": "1:39:00", "remaining_time": "10:00:08"}
+{"current_steps": 115, "total_steps": 805, "loss": 1.0581, "lr": 7.956546720533952e-05, "epoch": 0.7109737248840804, "percentage": 14.29, "elapsed_time": "1:39:51", "remaining_time": "9:59:10"}
+{"current_steps": 116, "total_steps": 805, "loss": 1.0577, "lr": 7.953958042822252e-05, "epoch": 0.7171561051004637, "percentage": 14.41, "elapsed_time": "1:40:43", "remaining_time": "9:58:13"}
+{"current_steps": 117, "total_steps": 805, "loss": 1.0562, "lr": 7.951294916947206e-05, "epoch": 0.723338485316847, "percentage": 14.53, "elapsed_time": "1:41:39", "remaining_time": "9:57:47"}
+{"current_steps": 118, "total_steps": 805, "loss": 1.052, "lr": 7.948557393052195e-05, "epoch": 0.7295208655332303, "percentage": 14.66, "elapsed_time": "1:42:38", "remaining_time": "9:57:36"}
+{"current_steps": 119, "total_steps": 805, "loss": 1.0645, "lr": 7.945745522681429e-05, "epoch": 0.7357032457496137, "percentage": 14.78, "elapsed_time": "1:43:29", "remaining_time": "9:56:37"}
+{"current_steps": 120, "total_steps": 805, "loss": 1.0469, "lr": 7.942859358778961e-05, "epoch": 0.7418856259659969, "percentage": 14.91, "elapsed_time": "1:44:20", "remaining_time": "9:55:38"}
+{"current_steps": 121, "total_steps": 805, "loss": 1.0442, "lr": 7.939898955687709e-05, "epoch": 0.7480680061823802, "percentage": 15.03, "elapsed_time": "1:45:11", "remaining_time": "9:54:40"}
+{"current_steps": 122, "total_steps": 805, "loss": 1.0608, "lr": 7.936864369148418e-05, "epoch": 0.7542503863987635, "percentage": 15.16, "elapsed_time": "1:46:03", "remaining_time": "9:53:42"}
+{"current_steps": 123, "total_steps": 805, "loss": 1.0668, "lr": 7.933755656298616e-05, "epoch": 0.7604327666151468, "percentage": 15.28, "elapsed_time": "1:46:54", "remaining_time": "9:52:44"}
+{"current_steps": 124, "total_steps": 805, "loss": 1.046, "lr": 7.930572875671542e-05, "epoch": 0.7666151468315301, "percentage": 15.4, "elapsed_time": "1:47:45", "remaining_time": "9:51:47"}
+{"current_steps": 125, "total_steps": 805, "loss": 1.0703, "lr": 7.927316087195035e-05, "epoch": 0.7727975270479135, "percentage": 15.53, "elapsed_time": "1:48:36", "remaining_time": "9:50:49"}
+{"current_steps": 126, "total_steps": 805, "loss": 1.0632, "lr": 7.923985352190416e-05, "epoch": 0.7789799072642968, "percentage": 15.65, "elapsed_time": "1:49:27", "remaining_time": "9:49:51"}
+{"current_steps": 127, "total_steps": 805, "loss": 1.0637, "lr": 7.920580733371325e-05, "epoch": 0.7851622874806801, "percentage": 15.78, "elapsed_time": "1:50:18", "remaining_time": "9:48:54"}
+{"current_steps": 128, "total_steps": 805, "loss": 1.0511, "lr": 7.917102294842545e-05, "epoch": 0.7913446676970634, "percentage": 15.9, "elapsed_time": "1:51:09", "remaining_time": "9:47:57"}
+{"current_steps": 129, "total_steps": 805, "loss": 1.0621, "lr": 7.913550102098789e-05, "epoch": 0.7975270479134466, "percentage": 16.02, "elapsed_time": "1:52:00", "remaining_time": "9:46:59"}
+{"current_steps": 130, "total_steps": 805, "loss": 1.0498, "lr": 7.909924222023478e-05, "epoch": 0.80370942812983, "percentage": 16.15, "elapsed_time": "1:52:52", "remaining_time": "9:46:04"}
+{"current_steps": 131, "total_steps": 805, "loss": 1.0555, "lr": 7.906224722887468e-05, "epoch": 0.8098918083462133, "percentage": 16.27, "elapsed_time": "1:53:43", "remaining_time": "9:45:09"}
+{"current_steps": 132, "total_steps": 805, "loss": 1.0547, "lr": 7.902451674347778e-05, "epoch": 0.8160741885625966, "percentage": 16.4, "elapsed_time": "1:54:41", "remaining_time": "9:44:45"}
+{"current_steps": 133, "total_steps": 805, "loss": 1.0459, "lr": 7.898605147446262e-05, "epoch": 0.8222565687789799, "percentage": 16.52, "elapsed_time": "1:55:40", "remaining_time": "9:44:28"}
+{"current_steps": 134, "total_steps": 805, "loss": 1.0442, "lr": 7.894685214608293e-05, "epoch": 0.8284389489953632, "percentage": 16.65, "elapsed_time": "1:56:31", "remaining_time": "9:43:31"}
+{"current_steps": 135, "total_steps": 805, "loss": 1.0553, "lr": 7.89069194964138e-05, "epoch": 0.8346213292117465, "percentage": 16.77, "elapsed_time": "1:57:23", "remaining_time": "9:42:34"}
+{"current_steps": 136, "total_steps": 805, "loss": 1.0479, "lr": 7.886625427733786e-05, "epoch": 0.8408037094281299, "percentage": 16.89, "elapsed_time": "1:58:14", "remaining_time": "9:41:37"}
+{"current_steps": 137, "total_steps": 805, "loss": 1.0315, "lr": 7.882485725453114e-05, "epoch": 0.8469860896445132, "percentage": 17.02, "elapsed_time": "1:59:05", "remaining_time": "9:40:39"}
+{"current_steps": 138, "total_steps": 805, "loss": 1.0496, "lr": 7.878272920744862e-05, "epoch": 0.8531684698608965, "percentage": 17.14, "elapsed_time": "1:59:56", "remaining_time": "9:39:42"}
+{"current_steps": 139, "total_steps": 805, "loss": 1.0407, "lr": 7.87398709293096e-05, "epoch": 0.8593508500772797, "percentage": 17.27, "elapsed_time": "2:00:47", "remaining_time": "9:38:45"}
+{"current_steps": 140, "total_steps": 805, "loss": 1.0551, "lr": 7.869628322708269e-05, "epoch": 0.865533230293663, "percentage": 17.39, "elapsed_time": "2:01:38", "remaining_time": "9:37:49"}
+{"current_steps": 141, "total_steps": 805, "loss": 1.0483, "lr": 7.865196692147066e-05, "epoch": 0.8717156105100463, "percentage": 17.52, "elapsed_time": "2:02:29", "remaining_time": "9:36:52"}
+{"current_steps": 142, "total_steps": 805, "loss": 1.0657, "lr": 7.860692284689502e-05, "epoch": 0.8778979907264297, "percentage": 17.64, "elapsed_time": "2:03:21", "remaining_time": "9:35:55"}
+{"current_steps": 143, "total_steps": 805, "loss": 1.056, "lr": 7.856115185148025e-05, "epoch": 0.884080370942813, "percentage": 17.76, "elapsed_time": "2:04:12", "remaining_time": "9:34:59"}
+{"current_steps": 144, "total_steps": 805, "loss": 1.0549, "lr": 7.851465479703785e-05, "epoch": 0.8902627511591963, "percentage": 17.89, "elapsed_time": "2:05:03", "remaining_time": "9:34:03"}
+{"current_steps": 145, "total_steps": 805, "loss": 1.0483, "lr": 7.846743255905014e-05, "epoch": 0.8964451313755796, "percentage": 18.01, "elapsed_time": "2:05:54", "remaining_time": "9:33:08"}
+{"current_steps": 146, "total_steps": 805, "loss": 1.0423, "lr": 7.841948602665373e-05, "epoch": 0.9026275115919629, "percentage": 18.14, "elapsed_time": "2:06:46", "remaining_time": "9:32:11"}
+{"current_steps": 147, "total_steps": 805, "loss": 1.0486, "lr": 7.83708161026228e-05, "epoch": 0.9088098918083463, "percentage": 18.26, "elapsed_time": "2:07:44", "remaining_time": "9:31:49"}
+{"current_steps": 148, "total_steps": 805, "loss": 1.0445, "lr": 7.832142370335215e-05, "epoch": 0.9149922720247295, "percentage": 18.39, "elapsed_time": "2:08:43", "remaining_time": "9:31:27"}
+{"current_steps": 149, "total_steps": 805, "loss": 1.0206, "lr": 7.827130975883982e-05, "epoch": 0.9211746522411128, "percentage": 18.51, "elapsed_time": "2:09:35", "remaining_time": "9:30:31"}
+{"current_steps": 150, "total_steps": 805, "loss": 1.028, "lr": 7.822047521266973e-05, "epoch": 0.9273570324574961, "percentage": 18.63, "elapsed_time": "2:10:26", "remaining_time": "9:29:33"}
+{"current_steps": 151, "total_steps": 805, "loss": 1.0367, "lr": 7.816892102199382e-05, "epoch": 0.9335394126738794, "percentage": 18.76, "elapsed_time": "2:11:17", "remaining_time": "9:28:37"}
+{"current_steps": 152, "total_steps": 805, "loss": 1.0415, "lr": 7.811664815751404e-05, "epoch": 0.9397217928902627, "percentage": 18.88, "elapsed_time": "2:12:08", "remaining_time": "9:27:40"}
+{"current_steps": 153, "total_steps": 805, "loss": 1.0379, "lr": 7.806365760346409e-05, "epoch": 0.9459041731066461, "percentage": 19.01, "elapsed_time": "2:12:59", "remaining_time": "9:26:44"}
+{"current_steps": 154, "total_steps": 805, "loss": 1.0498, "lr": 7.800995035759087e-05, "epoch": 0.9520865533230294, "percentage": 19.13, "elapsed_time": "2:13:50", "remaining_time": "9:25:47"}
+{"current_steps": 155, "total_steps": 805, "loss": 1.0479, "lr": 7.795552743113573e-05, "epoch": 0.9582689335394127, "percentage": 19.25, "elapsed_time": "2:14:41", "remaining_time": "9:24:50"}
+{"current_steps": 156, "total_steps": 805, "loss": 1.0313, "lr": 7.79003898488154e-05, "epoch": 0.964451313755796, "percentage": 19.38, "elapsed_time": "2:15:32", "remaining_time": "9:23:54"}
+{"current_steps": 157, "total_steps": 805, "loss": 1.0474, "lr": 7.784453864880267e-05, "epoch": 0.9706336939721792, "percentage": 19.5, "elapsed_time": "2:16:24", "remaining_time": "9:22:58"}
+{"current_steps": 158, "total_steps": 805, "loss": 1.0511, "lr": 7.77879748827069e-05, "epoch": 0.9768160741885626, "percentage": 19.63, "elapsed_time": "2:17:15", "remaining_time": "9:22:02"}
+{"current_steps": 159, "total_steps": 805, "loss": 1.0603, "lr": 7.77306996155542e-05, "epoch": 0.9829984544049459, "percentage": 19.75, "elapsed_time": "2:18:06", "remaining_time": "9:21:06"}
+{"current_steps": 160, "total_steps": 805, "loss": 1.0626, "lr": 7.767271392576732e-05, "epoch": 0.9891808346213292, "percentage": 19.88, "elapsed_time": "2:18:57", "remaining_time": "9:20:11"}
+{"current_steps": 161, "total_steps": 805, "loss": 1.0638, "lr": 7.761401890514547e-05, "epoch": 0.9953632148377125, "percentage": 20.0, "elapsed_time": "2:19:48", "remaining_time": "9:19:13"}
+{"current_steps": 162, "total_steps": 805, "loss": 1.8415, "lr": 7.755461565884362e-05, "epoch": 1.0046367851622875, "percentage": 20.12, "elapsed_time": "2:22:05", "remaining_time": "9:23:59"}
+{"current_steps": 163, "total_steps": 805, "loss": 1.0416, "lr": 7.749450530535179e-05, "epoch": 1.010819165378671, "percentage": 20.25, "elapsed_time": "2:23:01", "remaining_time": "9:23:20"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b9bdb9ce59092d97b23ff76ea09f93b12847087d8be9ceab0006e9fc49d2177
+size 7160