Training in progress, epoch 1

.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 sha256:7e8a622c524af5d550f9638d6c519ca53f8851cce103dac8934946b3bcf8b820
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f151143b549d299e71f4f2656d172d092ecbce977db15809b11d51bb69663c
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f35b306c365486dadc7396f527ed1ced0db9e5976acbcc1ee654107545b563
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c68a8399d891f2bd55139b5c8efcf3cabb24f0235b294c5656dfdc898735f4e
+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 +1,247 @@
+{"current_steps": 1, "total_steps": 1200, "loss": 1.0708, "lr": 3.3333333333333335e-07, "epoch": 0.004166666666666667, "percentage": 0.08, "elapsed_time": "0:00:28", "remaining_time": "9:32:49"}
+{"current_steps": 2, "total_steps": 1200, "loss": 1.0439, "lr": 6.666666666666667e-07, "epoch": 0.008333333333333333, "percentage": 0.17, "elapsed_time": "0:00:51", "remaining_time": "8:35:40"}
+{"current_steps": 3, "total_steps": 1200, "loss": 1.0359, "lr": 1.0000000000000002e-06, "epoch": 0.0125, "percentage": 0.25, "elapsed_time": "0:01:14", "remaining_time": "8:14:21"}
+{"current_steps": 4, "total_steps": 1200, "loss": 1.0264, "lr": 1.3333333333333334e-06, "epoch": 0.016666666666666666, "percentage": 0.33, "elapsed_time": "0:01:37", "remaining_time": "8:04:32"}
+{"current_steps": 5, "total_steps": 1200, "loss": 1.0219, "lr": 1.6666666666666667e-06, "epoch": 0.020833333333333332, "percentage": 0.42, "elapsed_time": "0:02:01", "remaining_time": "8:02:26"}
+{"current_steps": 6, "total_steps": 1200, "loss": 1.0423, "lr": 2.0000000000000003e-06, "epoch": 0.025, "percentage": 0.5, "elapsed_time": "0:02:24", "remaining_time": "7:58:12"}
+{"current_steps": 7, "total_steps": 1200, "loss": 0.9905, "lr": 2.3333333333333336e-06, "epoch": 0.029166666666666667, "percentage": 0.58, "elapsed_time": "0:02:46", "remaining_time": "7:53:49"}
+{"current_steps": 8, "total_steps": 1200, "loss": 0.9999, "lr": 2.666666666666667e-06, "epoch": 0.03333333333333333, "percentage": 0.67, "elapsed_time": "0:03:09", "remaining_time": "7:49:50"}
+{"current_steps": 9, "total_steps": 1200, "loss": 0.9511, "lr": 3e-06, "epoch": 0.0375, "percentage": 0.75, "elapsed_time": "0:03:31", "remaining_time": "7:47:07"}
+{"current_steps": 10, "total_steps": 1200, "loss": 0.9576, "lr": 3.3333333333333333e-06, "epoch": 0.041666666666666664, "percentage": 0.83, "elapsed_time": "0:03:54", "remaining_time": "7:45:46"}
+{"current_steps": 11, "total_steps": 1200, "loss": 0.9467, "lr": 3.6666666666666666e-06, "epoch": 0.04583333333333333, "percentage": 0.92, "elapsed_time": "0:04:18", "remaining_time": "7:45:37"}
+{"current_steps": 12, "total_steps": 1200, "loss": 0.923, "lr": 4.000000000000001e-06, "epoch": 0.05, "percentage": 1.0, "elapsed_time": "0:04:41", "remaining_time": "7:45:02"}
+{"current_steps": 13, "total_steps": 1200, "loss": 0.9284, "lr": 4.333333333333334e-06, "epoch": 0.05416666666666667, "percentage": 1.08, "elapsed_time": "0:05:05", "remaining_time": "7:44:38"}
+{"current_steps": 14, "total_steps": 1200, "loss": 0.9276, "lr": 4.666666666666667e-06, "epoch": 0.058333333333333334, "percentage": 1.17, "elapsed_time": "0:05:28", "remaining_time": "7:43:56"}
+{"current_steps": 15, "total_steps": 1200, "loss": 0.9148, "lr": 5e-06, "epoch": 0.0625, "percentage": 1.25, "elapsed_time": "0:05:53", "remaining_time": "7:44:47"}
+{"current_steps": 16, "total_steps": 1200, "loss": 0.8751, "lr": 5.333333333333334e-06, "epoch": 0.06666666666666667, "percentage": 1.33, "elapsed_time": "0:06:16", "remaining_time": "7:44:27"}
+{"current_steps": 17, "total_steps": 1200, "loss": 0.8635, "lr": 5.666666666666667e-06, "epoch": 0.07083333333333333, "percentage": 1.42, "elapsed_time": "0:06:39", "remaining_time": "7:43:28"}
+{"current_steps": 18, "total_steps": 1200, "loss": 0.8441, "lr": 6e-06, "epoch": 0.075, "percentage": 1.5, "elapsed_time": "0:07:03", "remaining_time": "7:43:26"}
+{"current_steps": 19, "total_steps": 1200, "loss": 0.8396, "lr": 6.333333333333333e-06, "epoch": 0.07916666666666666, "percentage": 1.58, "elapsed_time": "0:07:26", "remaining_time": "7:42:49"}
+{"current_steps": 20, "total_steps": 1200, "loss": 0.8143, "lr": 6.666666666666667e-06, "epoch": 0.08333333333333333, "percentage": 1.67, "elapsed_time": "0:07:50", "remaining_time": "7:42:22"}
+{"current_steps": 21, "total_steps": 1200, "loss": 0.8114, "lr": 7e-06, "epoch": 0.0875, "percentage": 1.75, "elapsed_time": "0:08:13", "remaining_time": "7:41:59"}
+{"current_steps": 22, "total_steps": 1200, "loss": 0.8006, "lr": 7.333333333333333e-06, "epoch": 0.09166666666666666, "percentage": 1.83, "elapsed_time": "0:08:37", "remaining_time": "7:42:16"}
+{"current_steps": 23, "total_steps": 1200, "loss": 0.7868, "lr": 7.666666666666667e-06, "epoch": 0.09583333333333334, "percentage": 1.92, "elapsed_time": "0:09:00", "remaining_time": "7:40:49"}
+{"current_steps": 24, "total_steps": 1200, "loss": 0.7731, "lr": 8.000000000000001e-06, "epoch": 0.1, "percentage": 2.0, "elapsed_time": "0:09:23", "remaining_time": "7:40:23"}
+{"current_steps": 25, "total_steps": 1200, "loss": 0.7738, "lr": 8.333333333333334e-06, "epoch": 0.10416666666666667, "percentage": 2.08, "elapsed_time": "0:09:47", "remaining_time": "7:40:13"}
+{"current_steps": 26, "total_steps": 1200, "loss": 0.7583, "lr": 8.666666666666668e-06, "epoch": 0.10833333333333334, "percentage": 2.17, "elapsed_time": "0:10:10", "remaining_time": "7:39:18"}
+{"current_steps": 27, "total_steps": 1200, "loss": 0.7399, "lr": 9e-06, "epoch": 0.1125, "percentage": 2.25, "elapsed_time": "0:10:32", "remaining_time": "7:38:15"}
+{"current_steps": 28, "total_steps": 1200, "loss": 0.7457, "lr": 9.333333333333334e-06, "epoch": 0.11666666666666667, "percentage": 2.33, "elapsed_time": "0:10:56", "remaining_time": "7:37:46"}
+{"current_steps": 29, "total_steps": 1200, "loss": 0.742, "lr": 9.666666666666667e-06, "epoch": 0.12083333333333333, "percentage": 2.42, "elapsed_time": "0:11:19", "remaining_time": "7:37:01"}
+{"current_steps": 30, "total_steps": 1200, "loss": 0.7327, "lr": 1e-05, "epoch": 0.125, "percentage": 2.5, "elapsed_time": "0:11:42", "remaining_time": "7:36:45"}
+{"current_steps": 31, "total_steps": 1200, "loss": 0.7368, "lr": 1.0333333333333335e-05, "epoch": 0.12916666666666668, "percentage": 2.58, "elapsed_time": "0:12:05", "remaining_time": "7:36:14"}
+{"current_steps": 32, "total_steps": 1200, "loss": 0.7302, "lr": 1.0666666666666667e-05, "epoch": 0.13333333333333333, "percentage": 2.67, "elapsed_time": "0:12:29", "remaining_time": "7:35:39"}
+{"current_steps": 33, "total_steps": 1200, "loss": 0.7265, "lr": 1.1000000000000001e-05, "epoch": 0.1375, "percentage": 2.75, "elapsed_time": "0:12:52", "remaining_time": "7:35:16"}
+{"current_steps": 34, "total_steps": 1200, "loss": 0.7121, "lr": 1.1333333333333334e-05, "epoch": 0.14166666666666666, "percentage": 2.83, "elapsed_time": "0:13:16", "remaining_time": "7:35:11"}
+{"current_steps": 35, "total_steps": 1200, "loss": 0.722, "lr": 1.1666666666666668e-05, "epoch": 0.14583333333333334, "percentage": 2.92, "elapsed_time": "0:13:38", "remaining_time": "7:34:06"}
+{"current_steps": 36, "total_steps": 1200, "loss": 0.7071, "lr": 1.2e-05, "epoch": 0.15, "percentage": 3.0, "elapsed_time": "0:14:02", "remaining_time": "7:33:46"}
+{"current_steps": 37, "total_steps": 1200, "loss": 0.7115, "lr": 1.2333333333333334e-05, "epoch": 0.15416666666666667, "percentage": 3.08, "elapsed_time": "0:14:25", "remaining_time": "7:33:23"}
+{"current_steps": 38, "total_steps": 1200, "loss": 0.7029, "lr": 1.2666666666666667e-05, "epoch": 0.15833333333333333, "percentage": 3.17, "elapsed_time": "0:14:48", "remaining_time": "7:32:54"}
+{"current_steps": 39, "total_steps": 1200, "loss": 0.7006, "lr": 1.3000000000000001e-05, "epoch": 0.1625, "percentage": 3.25, "elapsed_time": "0:15:12", "remaining_time": "7:32:32"}
+{"current_steps": 40, "total_steps": 1200, "loss": 0.7006, "lr": 1.3333333333333333e-05, "epoch": 0.16666666666666666, "percentage": 3.33, "elapsed_time": "0:15:35", "remaining_time": "7:32:20"}
+{"current_steps": 41, "total_steps": 1200, "loss": 0.7444, "lr": 1.3666666666666667e-05, "epoch": 0.17083333333333334, "percentage": 3.42, "elapsed_time": "0:15:58", "remaining_time": "7:31:28"}
+{"current_steps": 42, "total_steps": 1200, "loss": 0.681, "lr": 1.4e-05, "epoch": 0.175, "percentage": 3.5, "elapsed_time": "0:16:22", "remaining_time": "7:31:19"}
+{"current_steps": 43, "total_steps": 1200, "loss": 0.6917, "lr": 1.4333333333333334e-05, "epoch": 0.17916666666666667, "percentage": 3.58, "elapsed_time": "0:16:45", "remaining_time": "7:31:06"}
+{"current_steps": 44, "total_steps": 1200, "loss": 0.6949, "lr": 1.4666666666666666e-05, "epoch": 0.18333333333333332, "percentage": 3.67, "elapsed_time": "0:17:08", "remaining_time": "7:30:21"}
+{"current_steps": 45, "total_steps": 1200, "loss": 0.6754, "lr": 1.5000000000000002e-05, "epoch": 0.1875, "percentage": 3.75, "elapsed_time": "0:17:31", "remaining_time": "7:29:37"}
+{"current_steps": 46, "total_steps": 1200, "loss": 0.6694, "lr": 1.5333333333333334e-05, "epoch": 0.19166666666666668, "percentage": 3.83, "elapsed_time": "0:17:54", "remaining_time": "7:29:08"}
+{"current_steps": 47, "total_steps": 1200, "loss": 0.6691, "lr": 1.5666666666666667e-05, "epoch": 0.19583333333333333, "percentage": 3.92, "elapsed_time": "0:18:16", "remaining_time": "7:28:24"}
+{"current_steps": 48, "total_steps": 1200, "loss": 0.6866, "lr": 1.6000000000000003e-05, "epoch": 0.2, "percentage": 4.0, "elapsed_time": "0:18:39", "remaining_time": "7:27:50"}
+{"current_steps": 49, "total_steps": 1200, "loss": 0.6857, "lr": 1.6333333333333335e-05, "epoch": 0.20416666666666666, "percentage": 4.08, "elapsed_time": "0:19:01", "remaining_time": "7:27:03"}
+{"current_steps": 50, "total_steps": 1200, "loss": 0.6718, "lr": 1.6666666666666667e-05, "epoch": 0.20833333333333334, "percentage": 4.17, "elapsed_time": "0:19:24", "remaining_time": "7:26:16"}
+{"current_steps": 51, "total_steps": 1200, "loss": 0.651, "lr": 1.7e-05, "epoch": 0.2125, "percentage": 4.25, "elapsed_time": "0:19:46", "remaining_time": "7:25:35"}
+{"current_steps": 52, "total_steps": 1200, "loss": 0.6701, "lr": 1.7333333333333336e-05, "epoch": 0.21666666666666667, "percentage": 4.33, "elapsed_time": "0:20:10", "remaining_time": "7:25:14"}
+{"current_steps": 53, "total_steps": 1200, "loss": 0.6612, "lr": 1.7666666666666668e-05, "epoch": 0.22083333333333333, "percentage": 4.42, "elapsed_time": "0:20:33", "remaining_time": "7:24:54"}
+{"current_steps": 54, "total_steps": 1200, "loss": 0.6612, "lr": 1.8e-05, "epoch": 0.225, "percentage": 4.5, "elapsed_time": "0:20:56", "remaining_time": "7:24:21"}
+{"current_steps": 55, "total_steps": 1200, "loss": 0.6698, "lr": 1.8333333333333333e-05, "epoch": 0.22916666666666666, "percentage": 4.58, "elapsed_time": "0:21:19", "remaining_time": "7:24:05"}
+{"current_steps": 56, "total_steps": 1200, "loss": 0.6617, "lr": 1.866666666666667e-05, "epoch": 0.23333333333333334, "percentage": 4.67, "elapsed_time": "0:21:42", "remaining_time": "7:23:25"}
+{"current_steps": 57, "total_steps": 1200, "loss": 0.6677, "lr": 1.9e-05, "epoch": 0.2375, "percentage": 4.75, "elapsed_time": "0:22:05", "remaining_time": "7:23:02"}
+{"current_steps": 58, "total_steps": 1200, "loss": 0.6706, "lr": 1.9333333333333333e-05, "epoch": 0.24166666666666667, "percentage": 4.83, "elapsed_time": "0:22:26", "remaining_time": "7:21:55"}
+{"current_steps": 59, "total_steps": 1200, "loss": 0.6566, "lr": 1.9666666666666666e-05, "epoch": 0.24583333333333332, "percentage": 4.92, "elapsed_time": "0:22:49", "remaining_time": "7:21:17"}
+{"current_steps": 60, "total_steps": 1200, "loss": 0.6574, "lr": 2e-05, "epoch": 0.25, "percentage": 5.0, "elapsed_time": "0:23:12", "remaining_time": "7:21:06"}
+{"current_steps": 61, "total_steps": 1200, "loss": 0.6621, "lr": 2.0333333333333334e-05, "epoch": 0.25416666666666665, "percentage": 5.08, "elapsed_time": "0:23:36", "remaining_time": "7:20:45"}
+{"current_steps": 62, "total_steps": 1200, "loss": 0.6586, "lr": 2.066666666666667e-05, "epoch": 0.25833333333333336, "percentage": 5.17, "elapsed_time": "0:23:58", "remaining_time": "7:20:02"}
+{"current_steps": 63, "total_steps": 1200, "loss": 0.658, "lr": 2.1000000000000002e-05, "epoch": 0.2625, "percentage": 5.25, "elapsed_time": "0:24:21", "remaining_time": "7:19:41"}
+{"current_steps": 64, "total_steps": 1200, "loss": 0.6642, "lr": 2.1333333333333335e-05, "epoch": 0.26666666666666666, "percentage": 5.33, "elapsed_time": "0:24:45", "remaining_time": "7:19:19"}
+{"current_steps": 65, "total_steps": 1200, "loss": 0.6381, "lr": 2.1666666666666667e-05, "epoch": 0.2708333333333333, "percentage": 5.42, "elapsed_time": "0:25:08", "remaining_time": "7:18:56"}
+{"current_steps": 66, "total_steps": 1200, "loss": 0.6583, "lr": 2.2000000000000003e-05, "epoch": 0.275, "percentage": 5.5, "elapsed_time": "0:25:31", "remaining_time": "7:18:34"}
+{"current_steps": 67, "total_steps": 1200, "loss": 0.6542, "lr": 2.2333333333333335e-05, "epoch": 0.2791666666666667, "percentage": 5.58, "elapsed_time": "0:25:54", "remaining_time": "7:18:12"}
+{"current_steps": 68, "total_steps": 1200, "loss": 0.6405, "lr": 2.2666666666666668e-05, "epoch": 0.2833333333333333, "percentage": 5.67, "elapsed_time": "0:26:18", "remaining_time": "7:17:52"}
+{"current_steps": 69, "total_steps": 1200, "loss": 0.6495, "lr": 2.3e-05, "epoch": 0.2875, "percentage": 5.75, "elapsed_time": "0:26:41", "remaining_time": "7:17:33"}
+{"current_steps": 70, "total_steps": 1200, "loss": 0.6528, "lr": 2.3333333333333336e-05, "epoch": 0.2916666666666667, "percentage": 5.83, "elapsed_time": "0:27:05", "remaining_time": "7:17:17"}
+{"current_steps": 71, "total_steps": 1200, "loss": 0.6464, "lr": 2.3666666666666668e-05, "epoch": 0.29583333333333334, "percentage": 5.92, "elapsed_time": "0:27:28", "remaining_time": "7:16:59"}
+{"current_steps": 72, "total_steps": 1200, "loss": 0.6532, "lr": 2.4e-05, "epoch": 0.3, "percentage": 6.0, "elapsed_time": "0:27:52", "remaining_time": "7:16:40"}
+{"current_steps": 73, "total_steps": 1200, "loss": 0.6456, "lr": 2.4333333333333333e-05, "epoch": 0.30416666666666664, "percentage": 6.08, "elapsed_time": "0:28:15", "remaining_time": "7:16:23"}
+{"current_steps": 74, "total_steps": 1200, "loss": 0.6456, "lr": 2.466666666666667e-05, "epoch": 0.30833333333333335, "percentage": 6.17, "elapsed_time": "0:28:39", "remaining_time": "7:16:00"}
+{"current_steps": 75, "total_steps": 1200, "loss": 0.6513, "lr": 2.5e-05, "epoch": 0.3125, "percentage": 6.25, "elapsed_time": "0:29:03", "remaining_time": "7:15:49"}
+{"current_steps": 76, "total_steps": 1200, "loss": 0.6372, "lr": 2.5333333333333334e-05, "epoch": 0.31666666666666665, "percentage": 6.33, "elapsed_time": "0:29:26", "remaining_time": "7:15:24"}
+{"current_steps": 77, "total_steps": 1200, "loss": 0.6548, "lr": 2.566666666666667e-05, "epoch": 0.32083333333333336, "percentage": 6.42, "elapsed_time": "0:29:49", "remaining_time": "7:15:03"}
+{"current_steps": 78, "total_steps": 1200, "loss": 0.6259, "lr": 2.6000000000000002e-05, "epoch": 0.325, "percentage": 6.5, "elapsed_time": "0:30:13", "remaining_time": "7:14:44"}
+{"current_steps": 79, "total_steps": 1200, "loss": 0.6471, "lr": 2.6333333333333334e-05, "epoch": 0.32916666666666666, "percentage": 6.58, "elapsed_time": "0:30:36", "remaining_time": "7:14:24"}
+{"current_steps": 80, "total_steps": 1200, "loss": 0.6327, "lr": 2.6666666666666667e-05, "epoch": 0.3333333333333333, "percentage": 6.67, "elapsed_time": "0:31:00", "remaining_time": "7:14:05"}
+{"current_steps": 81, "total_steps": 1200, "loss": 0.6384, "lr": 2.7000000000000002e-05, "epoch": 0.3375, "percentage": 6.75, "elapsed_time": "0:31:23", "remaining_time": "7:13:37"}
+{"current_steps": 82, "total_steps": 1200, "loss": 0.6439, "lr": 2.7333333333333335e-05, "epoch": 0.3416666666666667, "percentage": 6.83, "elapsed_time": "0:31:46", "remaining_time": "7:13:11"}
+{"current_steps": 83, "total_steps": 1200, "loss": 0.6346, "lr": 2.7666666666666667e-05, "epoch": 0.3458333333333333, "percentage": 6.92, "elapsed_time": "0:32:09", "remaining_time": "7:12:48"}
+{"current_steps": 84, "total_steps": 1200, "loss": 0.6144, "lr": 2.8e-05, "epoch": 0.35, "percentage": 7.0, "elapsed_time": "0:32:32", "remaining_time": "7:12:19"}
+{"current_steps": 85, "total_steps": 1200, "loss": 0.6345, "lr": 2.833333333333334e-05, "epoch": 0.3541666666666667, "percentage": 7.08, "elapsed_time": "0:32:55", "remaining_time": "7:12:00"}
+{"current_steps": 86, "total_steps": 1200, "loss": 0.6389, "lr": 2.8666666666666668e-05, "epoch": 0.35833333333333334, "percentage": 7.17, "elapsed_time": "0:33:19", "remaining_time": "7:11:35"}
+{"current_steps": 87, "total_steps": 1200, "loss": 0.6421, "lr": 2.9e-05, "epoch": 0.3625, "percentage": 7.25, "elapsed_time": "0:33:41", "remaining_time": "7:11:05"}
+{"current_steps": 88, "total_steps": 1200, "loss": 0.6361, "lr": 2.9333333333333333e-05, "epoch": 0.36666666666666664, "percentage": 7.33, "elapsed_time": "0:34:04", "remaining_time": "7:10:29"}
+{"current_steps": 89, "total_steps": 1200, "loss": 0.6314, "lr": 2.9666666666666672e-05, "epoch": 0.37083333333333335, "percentage": 7.42, "elapsed_time": "0:34:27", "remaining_time": "7:10:03"}
+{"current_steps": 90, "total_steps": 1200, "loss": 0.6353, "lr": 3.0000000000000004e-05, "epoch": 0.375, "percentage": 7.5, "elapsed_time": "0:34:49", "remaining_time": "7:09:33"}
+{"current_steps": 91, "total_steps": 1200, "loss": 0.6317, "lr": 3.0333333333333333e-05, "epoch": 0.37916666666666665, "percentage": 7.58, "elapsed_time": "0:35:13", "remaining_time": "7:09:19"}
+{"current_steps": 92, "total_steps": 1200, "loss": 0.6308, "lr": 3.066666666666667e-05, "epoch": 0.38333333333333336, "percentage": 7.67, "elapsed_time": "0:35:37", "remaining_time": "7:09:00"}
+{"current_steps": 93, "total_steps": 1200, "loss": 0.6301, "lr": 3.1e-05, "epoch": 0.3875, "percentage": 7.75, "elapsed_time": "0:36:00", "remaining_time": "7:08:32"}
+{"current_steps": 94, "total_steps": 1200, "loss": 0.6173, "lr": 3.1333333333333334e-05, "epoch": 0.39166666666666666, "percentage": 7.83, "elapsed_time": "0:36:23", "remaining_time": "7:08:09"}
+{"current_steps": 95, "total_steps": 1200, "loss": 0.6374, "lr": 3.1666666666666666e-05, "epoch": 0.3958333333333333, "percentage": 7.92, "elapsed_time": "0:36:45", "remaining_time": "7:07:36"}
+{"current_steps": 96, "total_steps": 1200, "loss": 0.6276, "lr": 3.2000000000000005e-05, "epoch": 0.4, "percentage": 8.0, "elapsed_time": "0:37:09", "remaining_time": "7:07:17"}
+{"current_steps": 97, "total_steps": 1200, "loss": 0.6266, "lr": 3.233333333333334e-05, "epoch": 0.4041666666666667, "percentage": 8.08, "elapsed_time": "0:37:32", "remaining_time": "7:06:58"}
+{"current_steps": 98, "total_steps": 1200, "loss": 0.6115, "lr": 3.266666666666667e-05, "epoch": 0.4083333333333333, "percentage": 8.17, "elapsed_time": "0:37:56", "remaining_time": "7:06:38"}
+{"current_steps": 99, "total_steps": 1200, "loss": 0.6411, "lr": 3.3e-05, "epoch": 0.4125, "percentage": 8.25, "elapsed_time": "0:38:19", "remaining_time": "7:06:13"}
+{"current_steps": 100, "total_steps": 1200, "loss": 0.6296, "lr": 3.3333333333333335e-05, "epoch": 0.4166666666666667, "percentage": 8.33, "elapsed_time": "0:38:43", "remaining_time": "7:05:53"}
+{"current_steps": 101, "total_steps": 1200, "loss": 0.6306, "lr": 3.366666666666667e-05, "epoch": 0.42083333333333334, "percentage": 8.42, "elapsed_time": "0:39:04", "remaining_time": "7:05:15"}
+{"current_steps": 102, "total_steps": 1200, "loss": 0.6332, "lr": 3.4e-05, "epoch": 0.425, "percentage": 8.5, "elapsed_time": "0:39:27", "remaining_time": "7:04:45"}
+{"current_steps": 103, "total_steps": 1200, "loss": 0.6239, "lr": 3.433333333333333e-05, "epoch": 0.42916666666666664, "percentage": 8.58, "elapsed_time": "0:39:50", "remaining_time": "7:04:19"}
+{"current_steps": 104, "total_steps": 1200, "loss": 0.6329, "lr": 3.466666666666667e-05, "epoch": 0.43333333333333335, "percentage": 8.67, "elapsed_time": "0:40:14", "remaining_time": "7:04:05"}
+{"current_steps": 105, "total_steps": 1200, "loss": 0.628, "lr": 3.5000000000000004e-05, "epoch": 0.4375, "percentage": 8.75, "elapsed_time": "0:40:37", "remaining_time": "7:03:43"}
+{"current_steps": 106, "total_steps": 1200, "loss": 0.6242, "lr": 3.5333333333333336e-05, "epoch": 0.44166666666666665, "percentage": 8.83, "elapsed_time": "0:41:01", "remaining_time": "7:03:24"}
+{"current_steps": 107, "total_steps": 1200, "loss": 0.6293, "lr": 3.566666666666667e-05, "epoch": 0.44583333333333336, "percentage": 8.92, "elapsed_time": "0:41:24", "remaining_time": "7:02:58"}
+{"current_steps": 108, "total_steps": 1200, "loss": 0.6314, "lr": 3.6e-05, "epoch": 0.45, "percentage": 9.0, "elapsed_time": "0:41:47", "remaining_time": "7:02:34"}
+{"current_steps": 109, "total_steps": 1200, "loss": 0.6141, "lr": 3.633333333333333e-05, "epoch": 0.45416666666666666, "percentage": 9.08, "elapsed_time": "0:42:09", "remaining_time": "7:01:57"}
+{"current_steps": 110, "total_steps": 1200, "loss": 0.6278, "lr": 3.6666666666666666e-05, "epoch": 0.4583333333333333, "percentage": 9.17, "elapsed_time": "0:42:32", "remaining_time": "7:01:32"}
+{"current_steps": 111, "total_steps": 1200, "loss": 0.6282, "lr": 3.7000000000000005e-05, "epoch": 0.4625, "percentage": 9.25, "elapsed_time": "0:42:54", "remaining_time": "7:00:58"}
+{"current_steps": 112, "total_steps": 1200, "loss": 0.6462, "lr": 3.733333333333334e-05, "epoch": 0.4666666666666667, "percentage": 9.33, "elapsed_time": "0:43:17", "remaining_time": "7:00:33"}
+{"current_steps": 113, "total_steps": 1200, "loss": 0.6271, "lr": 3.766666666666667e-05, "epoch": 0.4708333333333333, "percentage": 9.42, "elapsed_time": "0:43:40", "remaining_time": "7:00:07"}
+{"current_steps": 114, "total_steps": 1200, "loss": 0.6216, "lr": 3.8e-05, "epoch": 0.475, "percentage": 9.5, "elapsed_time": "0:44:04", "remaining_time": "6:59:48"}
+{"current_steps": 115, "total_steps": 1200, "loss": 0.6232, "lr": 3.833333333333334e-05, "epoch": 0.4791666666666667, "percentage": 9.58, "elapsed_time": "0:44:27", "remaining_time": "6:59:24"}
+{"current_steps": 116, "total_steps": 1200, "loss": 0.6221, "lr": 3.866666666666667e-05, "epoch": 0.48333333333333334, "percentage": 9.67, "elapsed_time": "0:44:48", "remaining_time": "6:58:45"}
+{"current_steps": 117, "total_steps": 1200, "loss": 0.6091, "lr": 3.9e-05, "epoch": 0.4875, "percentage": 9.75, "elapsed_time": "0:45:11", "remaining_time": "6:58:21"}
+{"current_steps": 118, "total_steps": 1200, "loss": 0.6217, "lr": 3.933333333333333e-05, "epoch": 0.49166666666666664, "percentage": 9.83, "elapsed_time": "0:45:34", "remaining_time": "6:57:57"}
+{"current_steps": 119, "total_steps": 1200, "loss": 0.6359, "lr": 3.966666666666667e-05, "epoch": 0.49583333333333335, "percentage": 9.92, "elapsed_time": "0:45:58", "remaining_time": "6:57:36"}
+{"current_steps": 120, "total_steps": 1200, "loss": 0.6169, "lr": 4e-05, "epoch": 0.5, "percentage": 10.0, "elapsed_time": "0:46:21", "remaining_time": "6:57:12"}
+{"current_steps": 121, "total_steps": 1200, "loss": 0.6164, "lr": 3.999991538410973e-05, "epoch": 0.5041666666666667, "percentage": 10.08, "elapsed_time": "0:46:44", "remaining_time": "6:56:51"}
+{"current_steps": 122, "total_steps": 1200, "loss": 0.6193, "lr": 3.999966153715489e-05, "epoch": 0.5083333333333333, "percentage": 10.17, "elapsed_time": "0:47:07", "remaining_time": "6:56:25"}
+{"current_steps": 123, "total_steps": 1200, "loss": 0.6262, "lr": 3.999923846128343e-05, "epoch": 0.5125, "percentage": 10.25, "elapsed_time": "0:47:30", "remaining_time": "6:56:02"}
+{"current_steps": 124, "total_steps": 1200, "loss": 0.6212, "lr": 3.999864616007525e-05, "epoch": 0.5166666666666667, "percentage": 10.33, "elapsed_time": "0:47:54", "remaining_time": "6:55:39"}
+{"current_steps": 125, "total_steps": 1200, "loss": 0.6233, "lr": 3.999788463854215e-05, "epoch": 0.5208333333333334, "percentage": 10.42, "elapsed_time": "0:48:18", "remaining_time": "6:55:24"}
+{"current_steps": 126, "total_steps": 1200, "loss": 0.616, "lr": 3.999695390312783e-05, "epoch": 0.525, "percentage": 10.5, "elapsed_time": "0:48:41", "remaining_time": "6:54:58"}
+{"current_steps": 127, "total_steps": 1200, "loss": 0.614, "lr": 3.999585396170777e-05, "epoch": 0.5291666666666667, "percentage": 10.58, "elapsed_time": "0:49:03", "remaining_time": "6:54:27"}
+{"current_steps": 128, "total_steps": 1200, "loss": 0.6153, "lr": 3.999458482358924e-05, "epoch": 0.5333333333333333, "percentage": 10.67, "elapsed_time": "0:49:26", "remaining_time": "6:54:03"}
+{"current_steps": 129, "total_steps": 1200, "loss": 0.6009, "lr": 3.9993146499511146e-05, "epoch": 0.5375, "percentage": 10.75, "elapsed_time": "0:49:50", "remaining_time": "6:53:46"}
+{"current_steps": 130, "total_steps": 1200, "loss": 0.6212, "lr": 3.9991539001644015e-05, "epoch": 0.5416666666666666, "percentage": 10.83, "elapsed_time": "0:50:13", "remaining_time": "6:53:24"}
+{"current_steps": 131, "total_steps": 1200, "loss": 0.5999, "lr": 3.998976234358982e-05, "epoch": 0.5458333333333333, "percentage": 10.92, "elapsed_time": "0:50:37", "remaining_time": "6:53:05"}
+{"current_steps": 132, "total_steps": 1200, "loss": 0.6096, "lr": 3.998781654038192e-05, "epoch": 0.55, "percentage": 11.0, "elapsed_time": "0:50:59", "remaining_time": "6:52:36"}
+{"current_steps": 133, "total_steps": 1200, "loss": 0.5941, "lr": 3.9985701608484896e-05, "epoch": 0.5541666666666667, "percentage": 11.08, "elapsed_time": "0:51:23", "remaining_time": "6:52:17"}
+{"current_steps": 134, "total_steps": 1200, "loss": 0.6203, "lr": 3.998341756579443e-05, "epoch": 0.5583333333333333, "percentage": 11.17, "elapsed_time": "0:51:47", "remaining_time": "6:52:00"}
+{"current_steps": 135, "total_steps": 1200, "loss": 0.5934, "lr": 3.998096443163716e-05, "epoch": 0.5625, "percentage": 11.25, "elapsed_time": "0:52:09", "remaining_time": "6:51:29"}
+{"current_steps": 136, "total_steps": 1200, "loss": 0.6207, "lr": 3.99783422267705e-05, "epoch": 0.5666666666666667, "percentage": 11.33, "elapsed_time": "0:52:33", "remaining_time": "6:51:07"}
+{"current_steps": 137, "total_steps": 1200, "loss": 0.6041, "lr": 3.9975550973382454e-05, "epoch": 0.5708333333333333, "percentage": 11.42, "elapsed_time": "0:52:56", "remaining_time": "6:50:49"}
+{"current_steps": 138, "total_steps": 1200, "loss": 0.6185, "lr": 3.9972590695091476e-05, "epoch": 0.575, "percentage": 11.5, "elapsed_time": "0:53:20", "remaining_time": "6:50:27"}
+{"current_steps": 139, "total_steps": 1200, "loss": 0.6129, "lr": 3.9969461416946226e-05, "epoch": 0.5791666666666667, "percentage": 11.58, "elapsed_time": "0:53:42", "remaining_time": "6:49:59"}
+{"current_steps": 140, "total_steps": 1200, "loss": 0.6096, "lr": 3.996616316542537e-05, "epoch": 0.5833333333333334, "percentage": 11.67, "elapsed_time": "0:54:05", "remaining_time": "6:49:34"}
+{"current_steps": 141, "total_steps": 1200, "loss": 0.6054, "lr": 3.996269596843734e-05, "epoch": 0.5875, "percentage": 11.75, "elapsed_time": "0:54:28", "remaining_time": "6:49:12"}
+{"current_steps": 142, "total_steps": 1200, "loss": 0.6099, "lr": 3.995905985532015e-05, "epoch": 0.5916666666666667, "percentage": 11.83, "elapsed_time": "0:54:52", "remaining_time": "6:48:51"}
+{"current_steps": 143, "total_steps": 1200, "loss": 0.6421, "lr": 3.995525485684109e-05, "epoch": 0.5958333333333333, "percentage": 11.92, "elapsed_time": "0:55:16", "remaining_time": "6:48:31"}
+{"current_steps": 144, "total_steps": 1200, "loss": 0.6136, "lr": 3.9951281005196486e-05, "epoch": 0.6, "percentage": 12.0, "elapsed_time": "0:55:39", "remaining_time": "6:48:09"}
+{"current_steps": 145, "total_steps": 1200, "loss": 0.61, "lr": 3.994713833401145e-05, "epoch": 0.6041666666666666, "percentage": 12.08, "elapsed_time": "0:56:01", "remaining_time": "6:47:41"}
+{"current_steps": 146, "total_steps": 1200, "loss": 0.6207, "lr": 3.9942826878339554e-05, "epoch": 0.6083333333333333, "percentage": 12.17, "elapsed_time": "0:56:24", "remaining_time": "6:47:14"}
+{"current_steps": 147, "total_steps": 1200, "loss": 0.6077, "lr": 3.9938346674662565e-05, "epoch": 0.6125, "percentage": 12.25, "elapsed_time": "0:56:48", "remaining_time": "6:46:56"}
+{"current_steps": 148, "total_steps": 1200, "loss": 0.5942, "lr": 3.993369776089012e-05, "epoch": 0.6166666666666667, "percentage": 12.33, "elapsed_time": "0:57:12", "remaining_time": "6:46:36"}
+{"current_steps": 149, "total_steps": 1200, "loss": 0.603, "lr": 3.992888017635944e-05, "epoch": 0.6208333333333333, "percentage": 12.42, "elapsed_time": "0:57:35", "remaining_time": "6:46:14"}
+{"current_steps": 150, "total_steps": 1200, "loss": 0.6195, "lr": 3.9923893961834914e-05, "epoch": 0.625, "percentage": 12.5, "elapsed_time": "0:57:58", "remaining_time": "6:45:50"}
+{"current_steps": 151, "total_steps": 1200, "loss": 0.6009, "lr": 3.991873915950786e-05, "epoch": 0.6291666666666667, "percentage": 12.58, "elapsed_time": "0:58:21", "remaining_time": "6:45:22"}
+{"current_steps": 152, "total_steps": 1200, "loss": 0.6069, "lr": 3.991341581299609e-05, "epoch": 0.6333333333333333, "percentage": 12.67, "elapsed_time": "0:58:44", "remaining_time": "6:44:58"}
+{"current_steps": 153, "total_steps": 1200, "loss": 0.5993, "lr": 3.9907923967343583e-05, "epoch": 0.6375, "percentage": 12.75, "elapsed_time": "0:59:08", "remaining_time": "6:44:40"}
+{"current_steps": 154, "total_steps": 1200, "loss": 0.6061, "lr": 3.990226366902007e-05, "epoch": 0.6416666666666667, "percentage": 12.83, "elapsed_time": "0:59:32", "remaining_time": "6:44:23"}
+{"current_steps": 155, "total_steps": 1200, "loss": 0.6047, "lr": 3.989643496592067e-05, "epoch": 0.6458333333333334, "percentage": 12.92, "elapsed_time": "0:59:56", "remaining_time": "6:44:07"}
+{"current_steps": 156, "total_steps": 1200, "loss": 0.6163, "lr": 3.989043790736547e-05, "epoch": 0.65, "percentage": 13.0, "elapsed_time": "1:00:19", "remaining_time": "6:43:40"}
+{"current_steps": 157, "total_steps": 1200, "loss": 0.6064, "lr": 3.9884272544099126e-05, "epoch": 0.6541666666666667, "percentage": 13.08, "elapsed_time": "1:00:42", "remaining_time": "6:43:15"}
+{"current_steps": 158, "total_steps": 1200, "loss": 0.61, "lr": 3.98779389282904e-05, "epoch": 0.6583333333333333, "percentage": 13.17, "elapsed_time": "1:01:05", "remaining_time": "6:42:51"}
+{"current_steps": 159, "total_steps": 1200, "loss": 0.6001, "lr": 3.9871437113531757e-05, "epoch": 0.6625, "percentage": 13.25, "elapsed_time": "1:01:28", "remaining_time": "6:42:28"}
+{"current_steps": 160, "total_steps": 1200, "loss": 0.6013, "lr": 3.9864767154838864e-05, "epoch": 0.6666666666666666, "percentage": 13.33, "elapsed_time": "1:01:51", "remaining_time": "6:42:06"}
+{"current_steps": 161, "total_steps": 1200, "loss": 0.6115, "lr": 3.9857929108650186e-05, "epoch": 0.6708333333333333, "percentage": 13.42, "elapsed_time": "1:02:14", "remaining_time": "6:41:39"}
+{"current_steps": 162, "total_steps": 1200, "loss": 0.5974, "lr": 3.985092303282645e-05, "epoch": 0.675, "percentage": 13.5, "elapsed_time": "1:02:37", "remaining_time": "6:41:17"}
+{"current_steps": 163, "total_steps": 1200, "loss": 0.6027, "lr": 3.9843748986650185e-05, "epoch": 0.6791666666666667, "percentage": 13.58, "elapsed_time": "1:03:01", "remaining_time": "6:40:56"}
+{"current_steps": 164, "total_steps": 1200, "loss": 0.6093, "lr": 3.983640703082523e-05, "epoch": 0.6833333333333333, "percentage": 13.67, "elapsed_time": "1:03:25", "remaining_time": "6:40:36"}
+{"current_steps": 165, "total_steps": 1200, "loss": 0.604, "lr": 3.982889722747621e-05, "epoch": 0.6875, "percentage": 13.75, "elapsed_time": "1:03:47", "remaining_time": "6:40:06"}
+{"current_steps": 166, "total_steps": 1200, "loss": 0.6017, "lr": 3.982121964014797e-05, "epoch": 0.6916666666666667, "percentage": 13.83, "elapsed_time": "1:04:10", "remaining_time": "6:39:43"}
+{"current_steps": 167, "total_steps": 1200, "loss": 0.6043, "lr": 3.981337433380512e-05, "epoch": 0.6958333333333333, "percentage": 13.92, "elapsed_time": "1:04:34", "remaining_time": "6:39:25"}
+{"current_steps": 168, "total_steps": 1200, "loss": 0.603, "lr": 3.980536137483141e-05, "epoch": 0.7, "percentage": 14.0, "elapsed_time": "1:04:59", "remaining_time": "6:39:13"}
+{"current_steps": 169, "total_steps": 1200, "loss": 0.6033, "lr": 3.97971808310292e-05, "epoch": 0.7041666666666667, "percentage": 14.08, "elapsed_time": "1:05:22", "remaining_time": "6:38:50"}
+{"current_steps": 170, "total_steps": 1200, "loss": 0.6129, "lr": 3.978883277161889e-05, "epoch": 0.7083333333333334, "percentage": 14.17, "elapsed_time": "1:05:45", "remaining_time": "6:38:27"}
+{"current_steps": 171, "total_steps": 1200, "loss": 0.602, "lr": 3.978031726723834e-05, "epoch": 0.7125, "percentage": 14.25, "elapsed_time": "1:06:09", "remaining_time": "6:38:05"}
+{"current_steps": 172, "total_steps": 1200, "loss": 0.6022, "lr": 3.977163438994223e-05, "epoch": 0.7166666666666667, "percentage": 14.33, "elapsed_time": "1:06:32", "remaining_time": "6:37:39"}
+{"current_steps": 173, "total_steps": 1200, "loss": 0.6046, "lr": 3.976278421320152e-05, "epoch": 0.7208333333333333, "percentage": 14.42, "elapsed_time": "1:06:54", "remaining_time": "6:37:12"}
+{"current_steps": 174, "total_steps": 1200, "loss": 0.5952, "lr": 3.9753766811902756e-05, "epoch": 0.725, "percentage": 14.5, "elapsed_time": "1:07:17", "remaining_time": "6:36:50"}
+{"current_steps": 175, "total_steps": 1200, "loss": 0.5924, "lr": 3.9744582262347486e-05, "epoch": 0.7291666666666666, "percentage": 14.58, "elapsed_time": "1:07:40", "remaining_time": "6:36:25"}
+{"current_steps": 176, "total_steps": 1200, "loss": 0.6038, "lr": 3.973523064225159e-05, "epoch": 0.7333333333333333, "percentage": 14.67, "elapsed_time": "1:08:04", "remaining_time": "6:36:03"}
+{"current_steps": 177, "total_steps": 1200, "loss": 0.6138, "lr": 3.972571203074463e-05, "epoch": 0.7375, "percentage": 14.75, "elapsed_time": "1:08:26", "remaining_time": "6:35:35"}
+{"current_steps": 178, "total_steps": 1200, "loss": 0.6115, "lr": 3.9716026508369193e-05, "epoch": 0.7416666666666667, "percentage": 14.83, "elapsed_time": "1:08:50", "remaining_time": "6:35:15"}
+{"current_steps": 179, "total_steps": 1200, "loss": 0.5983, "lr": 3.970617415708019e-05, "epoch": 0.7458333333333333, "percentage": 14.92, "elapsed_time": "1:09:13", "remaining_time": "6:34:52"}
+{"current_steps": 180, "total_steps": 1200, "loss": 0.6102, "lr": 3.9696155060244166e-05, "epoch": 0.75, "percentage": 15.0, "elapsed_time": "1:09:37", "remaining_time": "6:34:30"}
+{"current_steps": 181, "total_steps": 1200, "loss": 0.6058, "lr": 3.96859693026386e-05, "epoch": 0.7541666666666667, "percentage": 15.08, "elapsed_time": "1:10:00", "remaining_time": "6:34:09"}
+{"current_steps": 182, "total_steps": 1200, "loss": 0.6251, "lr": 3.967561697045118e-05, "epoch": 0.7583333333333333, "percentage": 15.17, "elapsed_time": "1:10:23", "remaining_time": "6:33:44"}
+{"current_steps": 183, "total_steps": 1200, "loss": 0.6186, "lr": 3.96650981512791e-05, "epoch": 0.7625, "percentage": 15.25, "elapsed_time": "1:10:47", "remaining_time": "6:33:25"}
+{"current_steps": 184, "total_steps": 1200, "loss": 0.6222, "lr": 3.965441293412827e-05, "epoch": 0.7666666666666667, "percentage": 15.33, "elapsed_time": "1:11:10", "remaining_time": "6:33:01"}
+{"current_steps": 185, "total_steps": 1200, "loss": 0.6142, "lr": 3.964356140941262e-05, "epoch": 0.7708333333333334, "percentage": 15.42, "elapsed_time": "1:11:33", "remaining_time": "6:32:38"}
+{"current_steps": 186, "total_steps": 1200, "loss": 0.6074, "lr": 3.9632543668953284e-05, "epoch": 0.775, "percentage": 15.5, "elapsed_time": "1:11:56", "remaining_time": "6:32:12"}
+{"current_steps": 187, "total_steps": 1200, "loss": 0.6092, "lr": 3.962135980597786e-05, "epoch": 0.7791666666666667, "percentage": 15.58, "elapsed_time": "1:12:20", "remaining_time": "6:31:51"}
+{"current_steps": 188, "total_steps": 1200, "loss": 0.5987, "lr": 3.961000991511959e-05, "epoch": 0.7833333333333333, "percentage": 15.67, "elapsed_time": "1:12:43", "remaining_time": "6:31:30"}
+{"current_steps": 189, "total_steps": 1200, "loss": 0.6006, "lr": 3.9598494092416594e-05, "epoch": 0.7875, "percentage": 15.75, "elapsed_time": "1:13:07", "remaining_time": "6:31:08"}
+{"current_steps": 190, "total_steps": 1200, "loss": 0.6427, "lr": 3.958681243531103e-05, "epoch": 0.7916666666666666, "percentage": 15.83, "elapsed_time": "1:13:30", "remaining_time": "6:30:45"}
+{"current_steps": 191, "total_steps": 1200, "loss": 0.6164, "lr": 3.957496504264828e-05, "epoch": 0.7958333333333333, "percentage": 15.92, "elapsed_time": "1:13:54", "remaining_time": "6:30:25"}
+{"current_steps": 192, "total_steps": 1200, "loss": 0.5982, "lr": 3.9562952014676116e-05, "epoch": 0.8, "percentage": 16.0, "elapsed_time": "1:14:16", "remaining_time": "6:29:58"}
+{"current_steps": 193, "total_steps": 1200, "loss": 0.6145, "lr": 3.955077345304383e-05, "epoch": 0.8041666666666667, "percentage": 16.08, "elapsed_time": "1:14:40", "remaining_time": "6:29:36"}
+{"current_steps": 194, "total_steps": 1200, "loss": 0.6139, "lr": 3.953842946080142e-05, "epoch": 0.8083333333333333, "percentage": 16.17, "elapsed_time": "1:15:03", "remaining_time": "6:29:12"}
+{"current_steps": 195, "total_steps": 1200, "loss": 0.6156, "lr": 3.952592014239867e-05, "epoch": 0.8125, "percentage": 16.25, "elapsed_time": "1:15:26", "remaining_time": "6:28:48"}
+{"current_steps": 196, "total_steps": 1200, "loss": 0.6147, "lr": 3.951324560368429e-05, "epoch": 0.8166666666666667, "percentage": 16.33, "elapsed_time": "1:15:49", "remaining_time": "6:28:25"}
+{"current_steps": 197, "total_steps": 1200, "loss": 0.6109, "lr": 3.950040595190502e-05, "epoch": 0.8208333333333333, "percentage": 16.42, "elapsed_time": "1:16:13", "remaining_time": "6:28:03"}
+{"current_steps": 198, "total_steps": 1200, "loss": 0.604, "lr": 3.948740129570471e-05, "epoch": 0.825, "percentage": 16.5, "elapsed_time": "1:16:35", "remaining_time": "6:27:37"}
+{"current_steps": 199, "total_steps": 1200, "loss": 0.5978, "lr": 3.9474231745123425e-05, "epoch": 0.8291666666666667, "percentage": 16.58, "elapsed_time": "1:16:58", "remaining_time": "6:27:11"}
+{"current_steps": 200, "total_steps": 1200, "loss": 0.6025, "lr": 3.946089741159648e-05, "epoch": 0.8333333333333334, "percentage": 16.67, "elapsed_time": "1:17:21", "remaining_time": "6:26:46"}
+{"current_steps": 201, "total_steps": 1200, "loss": 0.6052, "lr": 3.9447398407953536e-05, "epoch": 0.8375, "percentage": 16.75, "elapsed_time": "1:17:43", "remaining_time": "6:26:19"}
+{"current_steps": 202, "total_steps": 1200, "loss": 0.5951, "lr": 3.943373484841761e-05, "epoch": 0.8416666666666667, "percentage": 16.83, "elapsed_time": "1:18:06", "remaining_time": "6:25:55"}
+{"current_steps": 203, "total_steps": 1200, "loss": 0.5983, "lr": 3.941990684860412e-05, "epoch": 0.8458333333333333, "percentage": 16.92, "elapsed_time": "1:18:30", "remaining_time": "6:25:33"}
+{"current_steps": 204, "total_steps": 1200, "loss": 0.6085, "lr": 3.940591452551993e-05, "epoch": 0.85, "percentage": 17.0, "elapsed_time": "1:18:53", "remaining_time": "6:25:09"}
+{"current_steps": 205, "total_steps": 1200, "loss": 0.591, "lr": 3.9391757997562323e-05, "epoch": 0.8541666666666666, "percentage": 17.08, "elapsed_time": "1:19:16", "remaining_time": "6:24:48"}
+{"current_steps": 206, "total_steps": 1200, "loss": 0.5937, "lr": 3.9377437384518014e-05, "epoch": 0.8583333333333333, "percentage": 17.17, "elapsed_time": "1:19:39", "remaining_time": "6:24:23"}
+{"current_steps": 207, "total_steps": 1200, "loss": 0.6022, "lr": 3.936295280756216e-05, "epoch": 0.8625, "percentage": 17.25, "elapsed_time": "1:20:03", "remaining_time": "6:24:00"}
+{"current_steps": 208, "total_steps": 1200, "loss": 0.6108, "lr": 3.934830438925728e-05, "epoch": 0.8666666666666667, "percentage": 17.33, "elapsed_time": "1:20:25", "remaining_time": "6:23:34"}
+{"current_steps": 209, "total_steps": 1200, "loss": 0.5914, "lr": 3.933349225355228e-05, "epoch": 0.8708333333333333, "percentage": 17.42, "elapsed_time": "1:20:47", "remaining_time": "6:23:06"}
+{"current_steps": 210, "total_steps": 1200, "loss": 0.5779, "lr": 3.931851652578137e-05, "epoch": 0.875, "percentage": 17.5, "elapsed_time": "1:21:10", "remaining_time": "6:22:42"}
+{"current_steps": 211, "total_steps": 1200, "loss": 0.5859, "lr": 3.930337733266299e-05, "epoch": 0.8791666666666667, "percentage": 17.58, "elapsed_time": "1:21:33", "remaining_time": "6:22:16"}
+{"current_steps": 212, "total_steps": 1200, "loss": 0.5968, "lr": 3.928807480229878e-05, "epoch": 0.8833333333333333, "percentage": 17.67, "elapsed_time": "1:21:57", "remaining_time": "6:21:56"}
+{"current_steps": 213, "total_steps": 1200, "loss": 0.5865, "lr": 3.927260906417246e-05, "epoch": 0.8875, "percentage": 17.75, "elapsed_time": "1:22:20", "remaining_time": "6:21:34"}
+{"current_steps": 214, "total_steps": 1200, "loss": 0.5919, "lr": 3.925698024914876e-05, "epoch": 0.8916666666666667, "percentage": 17.83, "elapsed_time": "1:22:43", "remaining_time": "6:21:08"}
+{"current_steps": 215, "total_steps": 1200, "loss": 0.6017, "lr": 3.9241188489472266e-05, "epoch": 0.8958333333333334, "percentage": 17.92, "elapsed_time": "1:23:06", "remaining_time": "6:20:46"}
+{"current_steps": 216, "total_steps": 1200, "loss": 0.5913, "lr": 3.922523391876638e-05, "epoch": 0.9, "percentage": 18.0, "elapsed_time": "1:23:29", "remaining_time": "6:20:20"}
+{"current_steps": 217, "total_steps": 1200, "loss": 0.6077, "lr": 3.920911667203211e-05, "epoch": 0.9041666666666667, "percentage": 18.08, "elapsed_time": "1:23:52", "remaining_time": "6:19:57"}
+{"current_steps": 218, "total_steps": 1200, "loss": 0.5913, "lr": 3.919283688564699e-05, "epoch": 0.9083333333333333, "percentage": 18.17, "elapsed_time": "1:24:16", "remaining_time": "6:19:35"}
+{"current_steps": 219, "total_steps": 1200, "loss": 0.589, "lr": 3.917639469736386e-05, "epoch": 0.9125, "percentage": 18.25, "elapsed_time": "1:24:39", "remaining_time": "6:19:15"}
+{"current_steps": 220, "total_steps": 1200, "loss": 0.582, "lr": 3.915979024630978e-05, "epoch": 0.9166666666666666, "percentage": 18.33, "elapsed_time": "1:25:03", "remaining_time": "6:18:52"}
+{"current_steps": 221, "total_steps": 1200, "loss": 0.5905, "lr": 3.914302367298478e-05, "epoch": 0.9208333333333333, "percentage": 18.42, "elapsed_time": "1:25:26", "remaining_time": "6:18:31"}
+{"current_steps": 222, "total_steps": 1200, "loss": 0.6087, "lr": 3.912609511926071e-05, "epoch": 0.925, "percentage": 18.5, "elapsed_time": "1:25:49", "remaining_time": "6:18:06"}
+{"current_steps": 223, "total_steps": 1200, "loss": 0.5858, "lr": 3.910900472838004e-05, "epoch": 0.9291666666666667, "percentage": 18.58, "elapsed_time": "1:26:12", "remaining_time": "6:17:42"}
+{"current_steps": 224, "total_steps": 1200, "loss": 0.601, "lr": 3.909175264495464e-05, "epoch": 0.9333333333333333, "percentage": 18.67, "elapsed_time": "1:26:35", "remaining_time": "6:17:18"}
+{"current_steps": 225, "total_steps": 1200, "loss": 0.5961, "lr": 3.907433901496454e-05, "epoch": 0.9375, "percentage": 18.75, "elapsed_time": "1:26:59", "remaining_time": "6:16:58"}
+{"current_steps": 226, "total_steps": 1200, "loss": 0.5832, "lr": 3.9056763985756724e-05, "epoch": 0.9416666666666667, "percentage": 18.83, "elapsed_time": "1:27:22", "remaining_time": "6:16:32"}
+{"current_steps": 227, "total_steps": 1200, "loss": 0.5935, "lr": 3.903902770604386e-05, "epoch": 0.9458333333333333, "percentage": 18.92, "elapsed_time": "1:27:45", "remaining_time": "6:16:09"}
+{"current_steps": 228, "total_steps": 1200, "loss": 0.5871, "lr": 3.9021130325903076e-05, "epoch": 0.95, "percentage": 19.0, "elapsed_time": "1:28:08", "remaining_time": "6:15:46"}
+{"current_steps": 229, "total_steps": 1200, "loss": 0.5869, "lr": 3.900307199677462e-05, "epoch": 0.9541666666666667, "percentage": 19.08, "elapsed_time": "1:28:31", "remaining_time": "6:15:23"}
+{"current_steps": 230, "total_steps": 1200, "loss": 0.5792, "lr": 3.898485287146068e-05, "epoch": 0.9583333333333334, "percentage": 19.17, "elapsed_time": "1:28:55", "remaining_time": "6:15:00"}
+{"current_steps": 231, "total_steps": 1200, "loss": 0.5875, "lr": 3.896647310412399e-05, "epoch": 0.9625, "percentage": 19.25, "elapsed_time": "1:29:18", "remaining_time": "6:14:36"}
+{"current_steps": 232, "total_steps": 1200, "loss": 0.5884, "lr": 3.8947932850286585e-05, "epoch": 0.9666666666666667, "percentage": 19.33, "elapsed_time": "1:29:40", "remaining_time": "6:14:11"}
+{"current_steps": 233, "total_steps": 1200, "loss": 0.5829, "lr": 3.892923226682849e-05, "epoch": 0.9708333333333333, "percentage": 19.42, "elapsed_time": "1:30:04", "remaining_time": "6:13:50"}
+{"current_steps": 234, "total_steps": 1200, "loss": 0.5735, "lr": 3.891037151198634e-05, "epoch": 0.975, "percentage": 19.5, "elapsed_time": "1:30:27", "remaining_time": "6:13:24"}
+{"current_steps": 235, "total_steps": 1200, "loss": 0.5798, "lr": 3.88913507453521e-05, "epoch": 0.9791666666666666, "percentage": 19.58, "elapsed_time": "1:30:50", "remaining_time": "6:13:02"}
+{"current_steps": 236, "total_steps": 1200, "loss": 0.5786, "lr": 3.887217012787167e-05, "epoch": 0.9833333333333333, "percentage": 19.67, "elapsed_time": "1:31:14", "remaining_time": "6:12:42"}
+{"current_steps": 237, "total_steps": 1200, "loss": 0.591, "lr": 3.885282982184357e-05, "epoch": 0.9875, "percentage": 19.75, "elapsed_time": "1:31:38", "remaining_time": "6:12:22"}
+{"current_steps": 238, "total_steps": 1200, "loss": 0.582, "lr": 3.883332999091751e-05, "epoch": 0.9916666666666667, "percentage": 19.83, "elapsed_time": "1:32:01", "remaining_time": "6:11:57"}
+{"current_steps": 239, "total_steps": 1200, "loss": 0.5841, "lr": 3.8813670800093046e-05, "epoch": 0.9958333333333333, "percentage": 19.92, "elapsed_time": "1:32:24", "remaining_time": "6:11:34"}
+{"current_steps": 240, "total_steps": 1200, "loss": 0.5872, "lr": 3.879385241571817e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "1:32:48", "remaining_time": "6:11:13"}
+{"current_steps": 241, "total_steps": 1200, "loss": 0.5473, "lr": 3.877387500548791e-05, "epoch": 1.0041666666666667, "percentage": 20.08, "elapsed_time": "1:34:50", "remaining_time": "6:17:22"}
+{"current_steps": 242, "total_steps": 1200, "loss": 0.5601, "lr": 3.87537387384429e-05, "epoch": 1.0083333333333333, "percentage": 20.17, "elapsed_time": "1:35:12", "remaining_time": "6:16:55"}
+{"current_steps": 243, "total_steps": 1200, "loss": 0.543, "lr": 3.873344378496795e-05, "epoch": 1.0125, "percentage": 20.25, "elapsed_time": "1:35:36", "remaining_time": "6:16:32"}
+{"current_steps": 244, "total_steps": 1200, "loss": 0.548, "lr": 3.8712990316790633e-05, "epoch": 1.0166666666666666, "percentage": 20.33, "elapsed_time": "1:36:00", "remaining_time": "6:16:09"}
+{"current_steps": 245, "total_steps": 1200, "loss": 0.5424, "lr": 3.8692378506979775e-05, "epoch": 1.0208333333333333, "percentage": 20.42, "elapsed_time": "1:36:23", "remaining_time": "6:15:45"}
+{"current_steps": 246, "total_steps": 1200, "loss": 0.5459, "lr": 3.8671608529944035e-05, "epoch": 1.025, "percentage": 20.5, "elapsed_time": "1:36:47", "remaining_time": "6:15:20"}
+{"current_steps": 247, "total_steps": 1200, "loss": 0.5367, "lr": 3.8650680561430444e-05, "epoch": 1.0291666666666666, "percentage": 20.58, "elapsed_time": "1:37:11", "remaining_time": "6:14:58"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d686c92cb0bd3bffeff8c0b0a5ea255b1e25f8cb96aa9e65db242be1870fb8
+size 7224