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 sha256:2a7711f9c4489399a2723bb187a2dad7a94cb1ad438d1fb9fa3825a8225b6613
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee9c30870d7c0dce6e042a3685ec95d8534d7ce1d9db6cc4da4639208755437
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af57f86d64b9f91fa0ade45de9b6f5c5fbecd20699d99655e040f27bc2988761
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:404c68693317bd47565803052363ac2cfd06929bcdc29cee4a3fac023077cee2
+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 +1,128 @@
+{"current_steps": 1, "total_steps": 625, "loss": 0.9312, "lr": 1.26984126984127e-06, "epoch": 0.00798801797304044, "percentage": 0.16, "elapsed_time": "0:01:55", "remaining_time": "19:56:42"}
+{"current_steps": 2, "total_steps": 625, "loss": 0.9351, "lr": 2.53968253968254e-06, "epoch": 0.01597603594608088, "percentage": 0.32, "elapsed_time": "0:03:39", "remaining_time": "18:57:10"}
+{"current_steps": 3, "total_steps": 625, "loss": 0.9345, "lr": 3.80952380952381e-06, "epoch": 0.023964053919121316, "percentage": 0.48, "elapsed_time": "0:05:23", "remaining_time": "18:36:22"}
+{"current_steps": 1, "total_steps": 625, "loss": 0.9312, "lr": 1.26984126984127e-06, "epoch": 0.00798801797304044, "percentage": 0.16, "elapsed_time": "0:03:34", "remaining_time": "1 day, 13:13:36"}
+{"current_steps": 2, "total_steps": 625, "loss": 0.9351, "lr": 2.53968253968254e-06, "epoch": 0.01597603594608088, "percentage": 0.32, "elapsed_time": "0:06:57", "remaining_time": "1 day, 12:06:55"}
+{"current_steps": 3, "total_steps": 625, "loss": 0.9346, "lr": 3.80952380952381e-06, "epoch": 0.023964053919121316, "percentage": 0.48, "elapsed_time": "0:10:18", "remaining_time": "1 day, 11:38:31"}
+{"current_steps": 4, "total_steps": 625, "loss": 0.9152, "lr": 5.07936507936508e-06, "epoch": 0.03195207189216176, "percentage": 0.64, "elapsed_time": "0:13:40", "remaining_time": "1 day, 11:23:26"}
+{"current_steps": 5, "total_steps": 625, "loss": 0.8778, "lr": 6.349206349206349e-06, "epoch": 0.0399400898652022, "percentage": 0.8, "elapsed_time": "0:17:02", "remaining_time": "1 day, 11:13:09"}
+{"current_steps": 6, "total_steps": 625, "loss": 0.8391, "lr": 7.61904761904762e-06, "epoch": 0.04792810783824263, "percentage": 0.96, "elapsed_time": "0:20:24", "remaining_time": "1 day, 11:05:31"}
+{"current_steps": 7, "total_steps": 625, "loss": 0.8725, "lr": 8.888888888888888e-06, "epoch": 0.05591612581128307, "percentage": 1.12, "elapsed_time": "0:23:46", "remaining_time": "1 day, 10:59:20"}
+{"current_steps": 8, "total_steps": 625, "loss": 0.8688, "lr": 1.015873015873016e-05, "epoch": 0.06390414378432352, "percentage": 1.28, "elapsed_time": "0:27:08", "remaining_time": "1 day, 10:53:01"}
+{"current_steps": 9, "total_steps": 625, "loss": 0.8277, "lr": 1.1428571428571429e-05, "epoch": 0.07189216175736396, "percentage": 1.44, "elapsed_time": "0:30:29", "remaining_time": "1 day, 10:47:18"}
+{"current_steps": 10, "total_steps": 625, "loss": 0.8228, "lr": 1.2698412698412699e-05, "epoch": 0.0798801797304044, "percentage": 1.6, "elapsed_time": "0:33:51", "remaining_time": "1 day, 10:42:31"}
+{"current_steps": 11, "total_steps": 625, "loss": 0.8102, "lr": 1.3968253968253968e-05, "epoch": 0.08786819770344484, "percentage": 1.76, "elapsed_time": "0:37:13", "remaining_time": "1 day, 10:37:33"}
+{"current_steps": 12, "total_steps": 625, "loss": 0.7681, "lr": 1.523809523809524e-05, "epoch": 0.09585621567648527, "percentage": 1.92, "elapsed_time": "0:40:35", "remaining_time": "1 day, 10:33:15"}
+{"current_steps": 13, "total_steps": 625, "loss": 0.7459, "lr": 1.6507936507936507e-05, "epoch": 0.1038442336495257, "percentage": 2.08, "elapsed_time": "0:43:56", "remaining_time": "1 day, 10:28:43"}
+{"current_steps": 14, "total_steps": 625, "loss": 0.7385, "lr": 1.7777777777777777e-05, "epoch": 0.11183225162256615, "percentage": 2.24, "elapsed_time": "0:47:18", "remaining_time": "1 day, 10:24:18"}
+{"current_steps": 15, "total_steps": 625, "loss": 0.7141, "lr": 1.904761904761905e-05, "epoch": 0.11982026959560658, "percentage": 2.4, "elapsed_time": "0:50:39", "remaining_time": "1 day, 10:20:00"}
+{"current_steps": 16, "total_steps": 625, "loss": 0.7027, "lr": 2.031746031746032e-05, "epoch": 0.12780828756864704, "percentage": 2.56, "elapsed_time": "0:54:00", "remaining_time": "1 day, 10:15:50"}
+{"current_steps": 17, "total_steps": 625, "loss": 0.6974, "lr": 2.158730158730159e-05, "epoch": 0.13579630554168748, "percentage": 2.72, "elapsed_time": "0:57:22", "remaining_time": "1 day, 10:12:10"}
+{"current_steps": 18, "total_steps": 625, "loss": 0.6925, "lr": 2.2857142857142858e-05, "epoch": 0.14378432351472792, "percentage": 2.88, "elapsed_time": "1:00:44", "remaining_time": "1 day, 10:08:17"}
+{"current_steps": 19, "total_steps": 625, "loss": 0.6782, "lr": 2.4126984126984128e-05, "epoch": 0.15177234148776836, "percentage": 3.04, "elapsed_time": "1:04:05", "remaining_time": "1 day, 10:04:23"}
+{"current_steps": 20, "total_steps": 625, "loss": 0.6794, "lr": 2.5396825396825397e-05, "epoch": 0.1597603594608088, "percentage": 3.2, "elapsed_time": "1:07:27", "remaining_time": "1 day, 10:00:30"}
+{"current_steps": 21, "total_steps": 625, "loss": 0.668, "lr": 2.6666666666666667e-05, "epoch": 0.16774837743384924, "percentage": 3.36, "elapsed_time": "1:10:49", "remaining_time": "1 day, 9:56:49"}
+{"current_steps": 22, "total_steps": 625, "loss": 0.6699, "lr": 2.7936507936507936e-05, "epoch": 0.17573639540688968, "percentage": 3.52, "elapsed_time": "1:14:10", "remaining_time": "1 day, 9:53:03"}
+{"current_steps": 23, "total_steps": 625, "loss": 0.6494, "lr": 2.9206349206349206e-05, "epoch": 0.18372441337993012, "percentage": 3.68, "elapsed_time": "1:17:31", "remaining_time": "1 day, 9:49:19"}
+{"current_steps": 24, "total_steps": 625, "loss": 0.6583, "lr": 3.047619047619048e-05, "epoch": 0.19171243135297053, "percentage": 3.84, "elapsed_time": "1:20:53", "remaining_time": "1 day, 9:45:35"}
+{"current_steps": 25, "total_steps": 625, "loss": 0.6518, "lr": 3.1746031746031745e-05, "epoch": 0.19970044932601097, "percentage": 4.0, "elapsed_time": "1:24:14", "remaining_time": "1 day, 9:41:57"}
+{"current_steps": 26, "total_steps": 625, "loss": 0.6498, "lr": 3.3015873015873014e-05, "epoch": 0.2076884672990514, "percentage": 4.16, "elapsed_time": "1:27:36", "remaining_time": "1 day, 9:38:19"}
+{"current_steps": 27, "total_steps": 625, "loss": 0.6598, "lr": 3.4285714285714284e-05, "epoch": 0.21567648527209185, "percentage": 4.32, "elapsed_time": "1:30:57", "remaining_time": "1 day, 9:34:41"}
+{"current_steps": 28, "total_steps": 625, "loss": 0.6394, "lr": 3.555555555555555e-05, "epoch": 0.2236645032451323, "percentage": 4.48, "elapsed_time": "1:34:19", "remaining_time": "1 day, 9:31:14"}
+{"current_steps": 29, "total_steps": 625, "loss": 0.6469, "lr": 3.682539682539683e-05, "epoch": 0.23165252121817273, "percentage": 4.64, "elapsed_time": "1:37:41", "remaining_time": "1 day, 9:27:47"}
+{"current_steps": 30, "total_steps": 625, "loss": 0.6303, "lr": 3.80952380952381e-05, "epoch": 0.23964053919121317, "percentage": 4.8, "elapsed_time": "1:41:03", "remaining_time": "1 day, 9:24:21"}
+{"current_steps": 31, "total_steps": 625, "loss": 0.6367, "lr": 3.936507936507937e-05, "epoch": 0.2476285571642536, "percentage": 4.96, "elapsed_time": "1:44:24", "remaining_time": "1 day, 9:20:43"}
+{"current_steps": 32, "total_steps": 625, "loss": 0.6235, "lr": 4.063492063492064e-05, "epoch": 0.2556165751372941, "percentage": 5.12, "elapsed_time": "1:47:46", "remaining_time": "1 day, 9:17:10"}
+{"current_steps": 33, "total_steps": 625, "loss": 0.6257, "lr": 4.190476190476191e-05, "epoch": 0.2636045931103345, "percentage": 5.28, "elapsed_time": "1:51:07", "remaining_time": "1 day, 9:13:37"}
+{"current_steps": 34, "total_steps": 625, "loss": 0.6182, "lr": 4.317460317460318e-05, "epoch": 0.27159261108337496, "percentage": 5.44, "elapsed_time": "1:54:29", "remaining_time": "1 day, 9:10:05"}
+{"current_steps": 35, "total_steps": 625, "loss": 0.6213, "lr": 4.444444444444445e-05, "epoch": 0.2795806290564154, "percentage": 5.6, "elapsed_time": "1:57:50", "remaining_time": "1 day, 9:06:32"}
+{"current_steps": 36, "total_steps": 625, "loss": 0.617, "lr": 4.5714285714285716e-05, "epoch": 0.28756864702945584, "percentage": 5.76, "elapsed_time": "2:01:12", "remaining_time": "1 day, 9:02:59"}
+{"current_steps": 37, "total_steps": 625, "loss": 0.612, "lr": 4.698412698412699e-05, "epoch": 0.2955566650024963, "percentage": 5.92, "elapsed_time": "2:04:33", "remaining_time": "1 day, 8:59:26"}
+{"current_steps": 38, "total_steps": 625, "loss": 0.6095, "lr": 4.8253968253968255e-05, "epoch": 0.3035446829755367, "percentage": 6.08, "elapsed_time": "2:07:54", "remaining_time": "1 day, 8:55:56"}
+{"current_steps": 39, "total_steps": 625, "loss": 0.6104, "lr": 4.952380952380953e-05, "epoch": 0.31153270094857716, "percentage": 6.24, "elapsed_time": "2:11:16", "remaining_time": "1 day, 8:52:27"}
+{"current_steps": 40, "total_steps": 625, "loss": 0.6037, "lr": 5.0793650793650794e-05, "epoch": 0.3195207189216176, "percentage": 6.4, "elapsed_time": "2:14:37", "remaining_time": "1 day, 8:48:57"}
+{"current_steps": 41, "total_steps": 625, "loss": 0.6248, "lr": 5.206349206349207e-05, "epoch": 0.32750873689465804, "percentage": 6.56, "elapsed_time": "2:17:59", "remaining_time": "1 day, 8:45:26"}
+{"current_steps": 42, "total_steps": 625, "loss": 0.6036, "lr": 5.333333333333333e-05, "epoch": 0.3354967548676985, "percentage": 6.72, "elapsed_time": "2:21:20", "remaining_time": "1 day, 8:41:55"}
+{"current_steps": 43, "total_steps": 625, "loss": 0.6116, "lr": 5.460317460317461e-05, "epoch": 0.3434847728407389, "percentage": 6.88, "elapsed_time": "2:24:41", "remaining_time": "1 day, 8:38:27"}
+{"current_steps": 44, "total_steps": 625, "loss": 0.6069, "lr": 5.587301587301587e-05, "epoch": 0.35147279081377936, "percentage": 7.04, "elapsed_time": "2:28:03", "remaining_time": "1 day, 8:34:58"}
+{"current_steps": 45, "total_steps": 625, "loss": 0.6094, "lr": 5.714285714285715e-05, "epoch": 0.3594608087868198, "percentage": 7.2, "elapsed_time": "2:31:24", "remaining_time": "1 day, 8:31:29"}
+{"current_steps": 46, "total_steps": 625, "loss": 0.5904, "lr": 5.841269841269841e-05, "epoch": 0.36744882675986024, "percentage": 7.36, "elapsed_time": "2:34:46", "remaining_time": "1 day, 8:28:05"}
+{"current_steps": 47, "total_steps": 625, "loss": 0.6025, "lr": 5.968253968253969e-05, "epoch": 0.3754368447329007, "percentage": 7.52, "elapsed_time": "2:38:07", "remaining_time": "1 day, 8:24:40"}
+{"current_steps": 48, "total_steps": 625, "loss": 0.5944, "lr": 6.095238095238096e-05, "epoch": 0.38342486270594106, "percentage": 7.68, "elapsed_time": "2:41:29", "remaining_time": "1 day, 8:21:12"}
+{"current_steps": 49, "total_steps": 625, "loss": 0.6016, "lr": 6.222222222222223e-05, "epoch": 0.3914128806789815, "percentage": 7.84, "elapsed_time": "2:44:50", "remaining_time": "1 day, 8:17:47"}
+{"current_steps": 50, "total_steps": 625, "loss": 0.6023, "lr": 6.349206349206349e-05, "epoch": 0.39940089865202194, "percentage": 8.0, "elapsed_time": "2:48:12", "remaining_time": "1 day, 8:14:21"}
+{"current_steps": 51, "total_steps": 625, "loss": 0.604, "lr": 6.476190476190477e-05, "epoch": 0.4073889166250624, "percentage": 8.16, "elapsed_time": "2:51:33", "remaining_time": "1 day, 8:10:54"}
+{"current_steps": 52, "total_steps": 625, "loss": 0.5906, "lr": 6.603174603174603e-05, "epoch": 0.4153769345981028, "percentage": 8.32, "elapsed_time": "2:54:55", "remaining_time": "1 day, 8:07:29"}
+{"current_steps": 53, "total_steps": 625, "loss": 0.5937, "lr": 6.730158730158731e-05, "epoch": 0.42336495257114326, "percentage": 8.48, "elapsed_time": "2:58:16", "remaining_time": "1 day, 8:04:03"}
+{"current_steps": 54, "total_steps": 625, "loss": 0.5959, "lr": 6.857142857142857e-05, "epoch": 0.4313529705441837, "percentage": 8.64, "elapsed_time": "3:01:38", "remaining_time": "1 day, 8:00:38"}
+{"current_steps": 55, "total_steps": 625, "loss": 0.5922, "lr": 6.984126984126985e-05, "epoch": 0.43934098851722414, "percentage": 8.8, "elapsed_time": "3:05:00", "remaining_time": "1 day, 7:57:17"}
+{"current_steps": 56, "total_steps": 625, "loss": 0.5935, "lr": 7.11111111111111e-05, "epoch": 0.4473290064902646, "percentage": 8.96, "elapsed_time": "3:08:21", "remaining_time": "1 day, 7:53:51"}
+{"current_steps": 57, "total_steps": 625, "loss": 0.6013, "lr": 7.238095238095239e-05, "epoch": 0.455317024463305, "percentage": 9.12, "elapsed_time": "3:11:42", "remaining_time": "1 day, 7:50:26"}
+{"current_steps": 58, "total_steps": 625, "loss": 0.5966, "lr": 7.365079365079366e-05, "epoch": 0.46330504243634546, "percentage": 9.28, "elapsed_time": "3:15:04", "remaining_time": "1 day, 7:47:01"}
+{"current_steps": 59, "total_steps": 625, "loss": 0.5816, "lr": 7.492063492063493e-05, "epoch": 0.4712930604093859, "percentage": 9.44, "elapsed_time": "3:18:25", "remaining_time": "1 day, 7:43:35"}
+{"current_steps": 60, "total_steps": 625, "loss": 0.6024, "lr": 7.61904761904762e-05, "epoch": 0.47928107838242634, "percentage": 9.6, "elapsed_time": "3:21:47", "remaining_time": "1 day, 7:40:10"}
+{"current_steps": 61, "total_steps": 625, "loss": 0.5928, "lr": 7.746031746031747e-05, "epoch": 0.4872690963554668, "percentage": 9.76, "elapsed_time": "3:25:08", "remaining_time": "1 day, 7:36:47"}
+{"current_steps": 62, "total_steps": 625, "loss": 0.5808, "lr": 7.873015873015874e-05, "epoch": 0.4952571143285072, "percentage": 9.92, "elapsed_time": "3:28:30", "remaining_time": "1 day, 7:33:22"}
+{"current_steps": 63, "total_steps": 625, "loss": 0.5915, "lr": 8e-05, "epoch": 0.5032451323015477, "percentage": 10.08, "elapsed_time": "3:31:51", "remaining_time": "1 day, 7:29:57"}
+{"current_steps": 64, "total_steps": 625, "loss": 0.5877, "lr": 7.999937503459301e-05, "epoch": 0.5112331502745882, "percentage": 10.24, "elapsed_time": "3:35:13", "remaining_time": "1 day, 7:26:32"}
+{"current_steps": 65, "total_steps": 625, "loss": 0.6112, "lr": 7.999750015790111e-05, "epoch": 0.5192211682476285, "percentage": 10.4, "elapsed_time": "3:38:34", "remaining_time": "1 day, 7:23:08"}
+{"current_steps": 66, "total_steps": 625, "loss": 0.5885, "lr": 7.999437542851095e-05, "epoch": 0.527209186220669, "percentage": 10.56, "elapsed_time": "3:41:56", "remaining_time": "1 day, 7:19:44"}
+{"current_steps": 67, "total_steps": 625, "loss": 0.5963, "lr": 7.999000094406493e-05, "epoch": 0.5351972041937094, "percentage": 10.72, "elapsed_time": "3:45:17", "remaining_time": "1 day, 7:16:20"}
+{"current_steps": 68, "total_steps": 625, "loss": 0.594, "lr": 7.998437684125812e-05, "epoch": 0.5431852221667499, "percentage": 10.88, "elapsed_time": "3:48:39", "remaining_time": "1 day, 7:12:55"}
+{"current_steps": 69, "total_steps": 625, "loss": 0.586, "lr": 7.997750329583402e-05, "epoch": 0.5511732401397903, "percentage": 11.04, "elapsed_time": "3:52:00", "remaining_time": "1 day, 7:09:33"}
+{"current_steps": 70, "total_steps": 625, "loss": 0.59, "lr": 7.9969380522579e-05, "epoch": 0.5591612581128308, "percentage": 11.2, "elapsed_time": "3:55:22", "remaining_time": "1 day, 7:06:11"}
+{"current_steps": 71, "total_steps": 625, "loss": 0.5841, "lr": 7.996000877531569e-05, "epoch": 0.5671492760858712, "percentage": 11.36, "elapsed_time": "3:58:44", "remaining_time": "1 day, 7:02:47"}
+{"current_steps": 72, "total_steps": 625, "loss": 0.5809, "lr": 7.9949388346895e-05, "epoch": 0.5751372940589117, "percentage": 11.52, "elapsed_time": "4:02:05", "remaining_time": "1 day, 6:59:22"}
+{"current_steps": 73, "total_steps": 625, "loss": 0.5696, "lr": 7.993751956918693e-05, "epoch": 0.5831253120319521, "percentage": 11.68, "elapsed_time": "4:05:26", "remaining_time": "1 day, 6:55:58"}
+{"current_steps": 74, "total_steps": 625, "loss": 0.5888, "lr": 7.992440281307027e-05, "epoch": 0.5911133300049926, "percentage": 11.84, "elapsed_time": "4:08:48", "remaining_time": "1 day, 6:52:35"}
+{"current_steps": 75, "total_steps": 625, "loss": 0.5748, "lr": 7.991003848842093e-05, "epoch": 0.5991013479780329, "percentage": 12.0, "elapsed_time": "4:12:09", "remaining_time": "1 day, 6:49:11"}
+{"current_steps": 76, "total_steps": 625, "loss": 0.5848, "lr": 7.989442704409925e-05, "epoch": 0.6070893659510734, "percentage": 12.16, "elapsed_time": "4:15:31", "remaining_time": "1 day, 6:45:48"}
+{"current_steps": 77, "total_steps": 625, "loss": 0.5815, "lr": 7.987756896793583e-05, "epoch": 0.6150773839241138, "percentage": 12.32, "elapsed_time": "4:18:52", "remaining_time": "1 day, 6:42:24"}
+{"current_steps": 78, "total_steps": 625, "loss": 0.5736, "lr": 7.985946478671642e-05, "epoch": 0.6230654018971543, "percentage": 12.48, "elapsed_time": "4:22:14", "remaining_time": "1 day, 6:39:01"}
+{"current_steps": 79, "total_steps": 625, "loss": 0.5816, "lr": 7.984011506616534e-05, "epoch": 0.6310534198701947, "percentage": 12.64, "elapsed_time": "4:25:35", "remaining_time": "1 day, 6:35:38"}
+{"current_steps": 80, "total_steps": 625, "loss": 0.5732, "lr": 7.981952041092792e-05, "epoch": 0.6390414378432352, "percentage": 12.8, "elapsed_time": "4:28:57", "remaining_time": "1 day, 6:32:13"}
+{"current_steps": 81, "total_steps": 625, "loss": 0.5687, "lr": 7.979768146455148e-05, "epoch": 0.6470294558162756, "percentage": 12.96, "elapsed_time": "4:32:18", "remaining_time": "1 day, 6:28:50"}
+{"current_steps": 82, "total_steps": 625, "loss": 0.57, "lr": 7.977459890946534e-05, "epoch": 0.6550174737893161, "percentage": 13.12, "elapsed_time": "4:35:40", "remaining_time": "1 day, 6:25:27"}
+{"current_steps": 83, "total_steps": 625, "loss": 0.5609, "lr": 7.975027346695943e-05, "epoch": 0.6630054917623565, "percentage": 13.28, "elapsed_time": "4:39:01", "remaining_time": "1 day, 6:22:03"}
+{"current_steps": 84, "total_steps": 625, "loss": 0.5782, "lr": 7.972470589716175e-05, "epoch": 0.670993509735397, "percentage": 13.44, "elapsed_time": "4:42:22", "remaining_time": "1 day, 6:18:39"}
+{"current_steps": 85, "total_steps": 625, "loss": 0.5709, "lr": 7.969789699901462e-05, "epoch": 0.6789815277084373, "percentage": 13.6, "elapsed_time": "4:45:44", "remaining_time": "1 day, 6:15:16"}
+{"current_steps": 86, "total_steps": 625, "loss": 0.5705, "lr": 7.966984761024974e-05, "epoch": 0.6869695456814778, "percentage": 13.76, "elapsed_time": "4:49:05", "remaining_time": "1 day, 6:11:52"}
+{"current_steps": 87, "total_steps": 625, "loss": 0.5655, "lr": 7.964055860736199e-05, "epoch": 0.6949575636545182, "percentage": 13.92, "elapsed_time": "4:52:27", "remaining_time": "1 day, 6:08:29"}
+{"current_steps": 88, "total_steps": 625, "loss": 0.564, "lr": 7.961003090558208e-05, "epoch": 0.7029455816275587, "percentage": 14.08, "elapsed_time": "4:55:48", "remaining_time": "1 day, 6:05:06"}
+{"current_steps": 89, "total_steps": 625, "loss": 0.56, "lr": 7.957826545884786e-05, "epoch": 0.7109335996005991, "percentage": 14.24, "elapsed_time": "4:59:10", "remaining_time": "1 day, 6:01:43"}
+{"current_steps": 90, "total_steps": 625, "loss": 0.5586, "lr": 7.95452632597746e-05, "epoch": 0.7189216175736396, "percentage": 14.4, "elapsed_time": "5:02:31", "remaining_time": "1 day, 5:58:19"}
+{"current_steps": 91, "total_steps": 625, "loss": 0.5571, "lr": 7.951102533962393e-05, "epoch": 0.72690963554668, "percentage": 14.56, "elapsed_time": "5:05:52", "remaining_time": "1 day, 5:54:56"}
+{"current_steps": 92, "total_steps": 625, "loss": 0.5637, "lr": 7.947555276827166e-05, "epoch": 0.7348976535197205, "percentage": 14.72, "elapsed_time": "5:09:14", "remaining_time": "1 day, 5:51:34"}
+{"current_steps": 93, "total_steps": 625, "loss": 0.5646, "lr": 7.94388466541743e-05, "epoch": 0.7428856714927609, "percentage": 14.88, "elapsed_time": "5:12:35", "remaining_time": "1 day, 5:48:11"}
+{"current_steps": 94, "total_steps": 625, "loss": 0.5493, "lr": 7.940090814433437e-05, "epoch": 0.7508736894658014, "percentage": 15.04, "elapsed_time": "5:15:57", "remaining_time": "1 day, 5:44:48"}
+{"current_steps": 95, "total_steps": 625, "loss": 0.5551, "lr": 7.936173842426473e-05, "epoch": 0.7588617074388417, "percentage": 15.2, "elapsed_time": "5:19:18", "remaining_time": "1 day, 5:41:26"}
+{"current_steps": 96, "total_steps": 625, "loss": 0.5598, "lr": 7.932133871795136e-05, "epoch": 0.7668497254118821, "percentage": 15.36, "elapsed_time": "5:22:40", "remaining_time": "1 day, 5:38:03"}
+{"current_steps": 97, "total_steps": 625, "loss": 0.5525, "lr": 7.927971028781522e-05, "epoch": 0.7748377433849226, "percentage": 15.52, "elapsed_time": "5:26:01", "remaining_time": "1 day, 5:34:41"}
+{"current_steps": 98, "total_steps": 625, "loss": 0.5407, "lr": 7.923685443467275e-05, "epoch": 0.782825761357963, "percentage": 15.68, "elapsed_time": "5:29:23", "remaining_time": "1 day, 5:31:18"}
+{"current_steps": 99, "total_steps": 625, "loss": 0.5567, "lr": 7.919277249769522e-05, "epoch": 0.7908137793310035, "percentage": 15.84, "elapsed_time": "5:32:44", "remaining_time": "1 day, 5:27:55"}
+{"current_steps": 100, "total_steps": 625, "loss": 0.5573, "lr": 7.914746585436692e-05, "epoch": 0.7988017973040439, "percentage": 16.0, "elapsed_time": "5:36:06", "remaining_time": "1 day, 5:24:32"}
+{"current_steps": 101, "total_steps": 625, "loss": 0.5465, "lr": 7.91009359204421e-05, "epoch": 0.8067898152770844, "percentage": 16.16, "elapsed_time": "5:39:27", "remaining_time": "1 day, 5:21:10"}
+{"current_steps": 102, "total_steps": 625, "loss": 0.5472, "lr": 7.90531841499007e-05, "epoch": 0.8147778332501248, "percentage": 16.32, "elapsed_time": "5:42:49", "remaining_time": "1 day, 5:17:47"}
+{"current_steps": 103, "total_steps": 625, "loss": 0.5468, "lr": 7.900421203490295e-05, "epoch": 0.8227658512231653, "percentage": 16.48, "elapsed_time": "5:46:10", "remaining_time": "1 day, 5:14:24"}
+{"current_steps": 104, "total_steps": 625, "loss": 0.5464, "lr": 7.895402110574277e-05, "epoch": 0.8307538691962056, "percentage": 16.64, "elapsed_time": "5:49:31", "remaining_time": "1 day, 5:11:00"}
+{"current_steps": 105, "total_steps": 625, "loss": 0.5491, "lr": 7.890261293079985e-05, "epoch": 0.8387418871692461, "percentage": 16.8, "elapsed_time": "5:52:53", "remaining_time": "1 day, 5:07:38"}
+{"current_steps": 106, "total_steps": 625, "loss": 0.5616, "lr": 7.884998911649077e-05, "epoch": 0.8467299051422865, "percentage": 16.96, "elapsed_time": "5:56:14", "remaining_time": "1 day, 5:04:16"}
+{"current_steps": 107, "total_steps": 625, "loss": 0.5386, "lr": 7.879615130721868e-05, "epoch": 0.854717923115327, "percentage": 17.12, "elapsed_time": "5:59:36", "remaining_time": "1 day, 5:00:53"}
+{"current_steps": 108, "total_steps": 625, "loss": 0.5437, "lr": 7.8741101185322e-05, "epoch": 0.8627059410883674, "percentage": 17.28, "elapsed_time": "6:02:57", "remaining_time": "1 day, 4:57:30"}
+{"current_steps": 109, "total_steps": 625, "loss": 0.5561, "lr": 7.868484047102183e-05, "epoch": 0.8706939590614079, "percentage": 17.44, "elapsed_time": "6:06:19", "remaining_time": "1 day, 4:54:08"}
+{"current_steps": 110, "total_steps": 625, "loss": 0.5422, "lr": 7.862737092236818e-05, "epoch": 0.8786819770344483, "percentage": 17.6, "elapsed_time": "6:09:40", "remaining_time": "1 day, 4:50:46"}
+{"current_steps": 111, "total_steps": 625, "loss": 0.5454, "lr": 7.856869433518506e-05, "epoch": 0.8866699950074888, "percentage": 17.76, "elapsed_time": "6:13:02", "remaining_time": "1 day, 4:47:24"}
+{"current_steps": 112, "total_steps": 625, "loss": 0.5531, "lr": 7.850881254301432e-05, "epoch": 0.8946580129805292, "percentage": 17.92, "elapsed_time": "6:16:23", "remaining_time": "1 day, 4:44:01"}
+{"current_steps": 113, "total_steps": 625, "loss": 0.5448, "lr": 7.844772741705835e-05, "epoch": 0.9026460309535697, "percentage": 18.08, "elapsed_time": "6:19:45", "remaining_time": "1 day, 4:40:39"}
+{"current_steps": 114, "total_steps": 625, "loss": 0.5452, "lr": 7.838544086612174e-05, "epoch": 0.91063404892661, "percentage": 18.24, "elapsed_time": "6:23:06", "remaining_time": "1 day, 4:37:17"}
+{"current_steps": 115, "total_steps": 625, "loss": 0.5372, "lr": 7.832195483655144e-05, "epoch": 0.9186220668996505, "percentage": 18.4, "elapsed_time": "6:26:28", "remaining_time": "1 day, 4:33:54"}
+{"current_steps": 116, "total_steps": 625, "loss": 0.5404, "lr": 7.825727131217609e-05, "epoch": 0.9266100848726909, "percentage": 18.56, "elapsed_time": "6:29:49", "remaining_time": "1 day, 4:30:31"}
+{"current_steps": 117, "total_steps": 625, "loss": 0.5536, "lr": 7.81913923142439e-05, "epoch": 0.9345981028457314, "percentage": 18.72, "elapsed_time": "6:33:11", "remaining_time": "1 day, 4:27:09"}
+{"current_steps": 118, "total_steps": 625, "loss": 0.5452, "lr": 7.812431990135965e-05, "epoch": 0.9425861208187718, "percentage": 18.88, "elapsed_time": "6:36:32", "remaining_time": "1 day, 4:23:47"}
+{"current_steps": 119, "total_steps": 625, "loss": 0.5506, "lr": 7.805605616942023e-05, "epoch": 0.9505741387918123, "percentage": 19.04, "elapsed_time": "6:39:53", "remaining_time": "1 day, 4:20:24"}
+{"current_steps": 120, "total_steps": 625, "loss": 0.5484, "lr": 7.798660325154917e-05, "epoch": 0.9585621567648527, "percentage": 19.2, "elapsed_time": "6:43:15", "remaining_time": "1 day, 4:17:02"}
+{"current_steps": 121, "total_steps": 625, "loss": 0.5437, "lr": 7.791596331803003e-05, "epoch": 0.9665501747378932, "percentage": 19.36, "elapsed_time": "6:46:36", "remaining_time": "1 day, 4:13:40"}
+{"current_steps": 122, "total_steps": 625, "loss": 0.5452, "lr": 7.784413857623856e-05, "epoch": 0.9745381927109336, "percentage": 19.52, "elapsed_time": "6:49:58", "remaining_time": "1 day, 4:10:17"}
+{"current_steps": 123, "total_steps": 625, "loss": 0.5471, "lr": 7.77711312705737e-05, "epoch": 0.982526210683974, "percentage": 19.68, "elapsed_time": "6:53:19", "remaining_time": "1 day, 4:06:55"}
+{"current_steps": 124, "total_steps": 625, "loss": 0.5417, "lr": 7.769694368238746e-05, "epoch": 0.9905142286570144, "percentage": 19.84, "elapsed_time": "6:56:41", "remaining_time": "1 day, 4:03:33"}
+{"current_steps": 125, "total_steps": 625, "loss": 0.539, "lr": 7.762157812991369e-05, "epoch": 0.9985022466300549, "percentage": 20.0, "elapsed_time": "7:00:02", "remaining_time": "1 day, 4:00:11"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:583ae469ca2e41446276577c1976872e09a97e5cc19081e4d5f6a876bd642a58
+size 7288