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 sha256:7144d5a713ea1e354c22755ae424ae312499b5242f57986a859d4a3392521e3a
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09fd3fe1dc02a36cd2cd143cb0625c42f43e5bba7b517263782579adedd7ffe4
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a73e84b94ee758a59b5564e851281999b964045abcca8764f35deb4b464c793
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d4ebaf3c548041b3b9c355e881704cdda5be104775b0b9ae457f7cb799fca9
+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 +1,131 @@
+{"current_steps": 1, "total_steps": 650, "loss": 0.9112, "lr": 6.153846153846155e-07, "epoch": 0.007659167065581618, "percentage": 0.15, "elapsed_time": "0:01:43", "remaining_time": "18:39:57"}
+{"current_steps": 2, "total_steps": 650, "loss": 0.9517, "lr": 1.230769230769231e-06, "epoch": 0.015318334131163236, "percentage": 0.31, "elapsed_time": "0:03:25", "remaining_time": "18:31:25"}
+{"current_steps": 3, "total_steps": 650, "loss": 0.9295, "lr": 1.8461538461538465e-06, "epoch": 0.022977501196744854, "percentage": 0.46, "elapsed_time": "0:05:01", "remaining_time": "18:04:32"}
+{"current_steps": 4, "total_steps": 650, "loss": 0.9235, "lr": 2.461538461538462e-06, "epoch": 0.030636668262326472, "percentage": 0.62, "elapsed_time": "0:06:35", "remaining_time": "17:44:30"}
+{"current_steps": 5, "total_steps": 650, "loss": 0.9035, "lr": 3.0769230769230774e-06, "epoch": 0.03829583532790809, "percentage": 0.77, "elapsed_time": "0:07:52", "remaining_time": "16:55:24"}
+{"current_steps": 6, "total_steps": 650, "loss": 0.8544, "lr": 3.692307692307693e-06, "epoch": 0.04595500239348971, "percentage": 0.92, "elapsed_time": "0:09:45", "remaining_time": "17:28:07"}
+{"current_steps": 7, "total_steps": 650, "loss": 0.8081, "lr": 4.307692307692308e-06, "epoch": 0.053614169459071326, "percentage": 1.08, "elapsed_time": "0:11:14", "remaining_time": "17:12:23"}
+{"current_steps": 8, "total_steps": 650, "loss": 0.836, "lr": 4.923076923076924e-06, "epoch": 0.061273336524652944, "percentage": 1.23, "elapsed_time": "0:13:03", "remaining_time": "17:28:16"}
+{"current_steps": 9, "total_steps": 650, "loss": 0.7788, "lr": 5.538461538461539e-06, "epoch": 0.06893250359023456, "percentage": 1.38, "elapsed_time": "0:14:48", "remaining_time": "17:35:08"}
+{"current_steps": 10, "total_steps": 650, "loss": 0.8309, "lr": 6.153846153846155e-06, "epoch": 0.07659167065581618, "percentage": 1.54, "elapsed_time": "0:16:34", "remaining_time": "17:41:12"}
+{"current_steps": 11, "total_steps": 650, "loss": 0.8224, "lr": 6.76923076923077e-06, "epoch": 0.0842508377213978, "percentage": 1.69, "elapsed_time": "0:18:10", "remaining_time": "17:35:34"}
+{"current_steps": 12, "total_steps": 650, "loss": 0.7941, "lr": 7.384615384615386e-06, "epoch": 0.09191000478697942, "percentage": 1.85, "elapsed_time": "0:20:02", "remaining_time": "17:45:34"}
+{"current_steps": 13, "total_steps": 650, "loss": 0.7635, "lr": 8.000000000000001e-06, "epoch": 0.09956917185256103, "percentage": 2.0, "elapsed_time": "0:21:39", "remaining_time": "17:41:15"}
+{"current_steps": 14, "total_steps": 650, "loss": 0.7327, "lr": 8.615384615384617e-06, "epoch": 0.10722833891814265, "percentage": 2.15, "elapsed_time": "0:23:25", "remaining_time": "17:44:08"}
+{"current_steps": 15, "total_steps": 650, "loss": 0.7094, "lr": 9.230769230769232e-06, "epoch": 0.11488750598372427, "percentage": 2.31, "elapsed_time": "0:25:03", "remaining_time": "17:41:00"}
+{"current_steps": 16, "total_steps": 650, "loss": 0.6849, "lr": 9.846153846153848e-06, "epoch": 0.12254667304930589, "percentage": 2.46, "elapsed_time": "0:26:46", "remaining_time": "17:41:10"}
+{"current_steps": 17, "total_steps": 650, "loss": 0.6811, "lr": 1.0461538461538463e-05, "epoch": 0.1302058401148875, "percentage": 2.62, "elapsed_time": "0:28:22", "remaining_time": "17:36:50"}
+{"current_steps": 18, "total_steps": 650, "loss": 0.6745, "lr": 1.1076923076923079e-05, "epoch": 0.13786500718046912, "percentage": 2.77, "elapsed_time": "0:30:05", "remaining_time": "17:36:23"}
+{"current_steps": 19, "total_steps": 650, "loss": 0.6578, "lr": 1.1692307692307694e-05, "epoch": 0.14552417424605074, "percentage": 2.92, "elapsed_time": "0:31:54", "remaining_time": "17:39:54"}
+{"current_steps": 20, "total_steps": 650, "loss": 0.6754, "lr": 1.230769230769231e-05, "epoch": 0.15318334131163236, "percentage": 3.08, "elapsed_time": "0:33:28", "remaining_time": "17:34:24"}
+{"current_steps": 21, "total_steps": 650, "loss": 0.6655, "lr": 1.2923076923076925e-05, "epoch": 0.16084250837721398, "percentage": 3.23, "elapsed_time": "0:35:15", "remaining_time": "17:35:50"}
+{"current_steps": 22, "total_steps": 650, "loss": 0.64, "lr": 1.353846153846154e-05, "epoch": 0.1685016754427956, "percentage": 3.38, "elapsed_time": "0:36:54", "remaining_time": "17:33:45"}
+{"current_steps": 23, "total_steps": 650, "loss": 0.6226, "lr": 1.4153846153846156e-05, "epoch": 0.1761608425083772, "percentage": 3.54, "elapsed_time": "0:39:05", "remaining_time": "17:45:39"}
+{"current_steps": 24, "total_steps": 650, "loss": 0.5999, "lr": 1.4769230769230772e-05, "epoch": 0.18382000957395883, "percentage": 3.69, "elapsed_time": "0:40:26", "remaining_time": "17:34:53"}
+{"current_steps": 25, "total_steps": 650, "loss": 0.6224, "lr": 1.5384615384615387e-05, "epoch": 0.19147917663954045, "percentage": 3.85, "elapsed_time": "0:42:03", "remaining_time": "17:31:22"}
+{"current_steps": 26, "total_steps": 650, "loss": 0.6382, "lr": 1.6000000000000003e-05, "epoch": 0.19913834370512207, "percentage": 4.0, "elapsed_time": "0:43:43", "remaining_time": "17:29:15"}
+{"current_steps": 27, "total_steps": 650, "loss": 0.6216, "lr": 1.6615384615384618e-05, "epoch": 0.20679751077070369, "percentage": 4.15, "elapsed_time": "0:45:43", "remaining_time": "17:35:13"}
+{"current_steps": 28, "total_steps": 650, "loss": 0.6154, "lr": 1.7230769230769234e-05, "epoch": 0.2144566778362853, "percentage": 4.31, "elapsed_time": "0:47:40", "remaining_time": "17:38:55"}
+{"current_steps": 29, "total_steps": 650, "loss": 0.6128, "lr": 1.784615384615385e-05, "epoch": 0.22211584490186692, "percentage": 4.46, "elapsed_time": "0:49:39", "remaining_time": "17:43:12"}
+{"current_steps": 30, "total_steps": 650, "loss": 0.5937, "lr": 1.8461538461538465e-05, "epoch": 0.22977501196744854, "percentage": 4.62, "elapsed_time": "0:51:24", "remaining_time": "17:42:31"}
+{"current_steps": 31, "total_steps": 650, "loss": 0.6247, "lr": 1.907692307692308e-05, "epoch": 0.23743417903303016, "percentage": 4.77, "elapsed_time": "0:53:09", "remaining_time": "17:41:31"}
+{"current_steps": 32, "total_steps": 650, "loss": 0.5816, "lr": 1.9692307692307696e-05, "epoch": 0.24509334609861178, "percentage": 4.92, "elapsed_time": "0:55:06", "remaining_time": "17:44:09"}
+{"current_steps": 33, "total_steps": 650, "loss": 0.6311, "lr": 2.0307692307692308e-05, "epoch": 0.2527525131641934, "percentage": 5.08, "elapsed_time": "0:57:05", "remaining_time": "17:47:26"}
+{"current_steps": 34, "total_steps": 650, "loss": 0.6026, "lr": 2.0923076923076927e-05, "epoch": 0.260411680229775, "percentage": 5.23, "elapsed_time": "0:58:58", "remaining_time": "17:48:24"}
+{"current_steps": 35, "total_steps": 650, "loss": 0.5813, "lr": 2.153846153846154e-05, "epoch": 0.26807084729535663, "percentage": 5.38, "elapsed_time": "1:00:51", "remaining_time": "17:49:27"}
+{"current_steps": 36, "total_steps": 650, "loss": 0.5826, "lr": 2.2153846153846158e-05, "epoch": 0.27573001436093825, "percentage": 5.54, "elapsed_time": "1:02:41", "remaining_time": "17:49:18"}
+{"current_steps": 37, "total_steps": 650, "loss": 0.6061, "lr": 2.276923076923077e-05, "epoch": 0.28338918142651986, "percentage": 5.69, "elapsed_time": "1:04:44", "remaining_time": "17:52:29"}
+{"current_steps": 38, "total_steps": 650, "loss": 0.5535, "lr": 2.338461538461539e-05, "epoch": 0.2910483484921015, "percentage": 5.85, "elapsed_time": "1:06:26", "remaining_time": "17:50:02"}
+{"current_steps": 39, "total_steps": 650, "loss": 0.5891, "lr": 2.4e-05, "epoch": 0.2987075155576831, "percentage": 6.0, "elapsed_time": "1:08:18", "remaining_time": "17:50:16"}
+{"current_steps": 40, "total_steps": 650, "loss": 0.575, "lr": 2.461538461538462e-05, "epoch": 0.3063666826232647, "percentage": 6.15, "elapsed_time": "1:09:51", "remaining_time": "17:45:26"}
+{"current_steps": 41, "total_steps": 650, "loss": 0.5779, "lr": 2.523076923076923e-05, "epoch": 0.31402584968884634, "percentage": 6.31, "elapsed_time": "1:11:37", "remaining_time": "17:43:50"}
+{"current_steps": 42, "total_steps": 650, "loss": 0.5528, "lr": 2.584615384615385e-05, "epoch": 0.32168501675442795, "percentage": 6.46, "elapsed_time": "1:13:17", "remaining_time": "17:40:52"}
+{"current_steps": 43, "total_steps": 650, "loss": 0.5888, "lr": 2.6461538461538463e-05, "epoch": 0.3293441838200096, "percentage": 6.62, "elapsed_time": "1:15:03", "remaining_time": "17:39:32"}
+{"current_steps": 44, "total_steps": 650, "loss": 0.5559, "lr": 2.707692307692308e-05, "epoch": 0.3370033508855912, "percentage": 6.77, "elapsed_time": "1:16:54", "remaining_time": "17:39:14"}
+{"current_steps": 45, "total_steps": 650, "loss": 0.5612, "lr": 2.7692307692307694e-05, "epoch": 0.3446625179511728, "percentage": 6.92, "elapsed_time": "1:18:28", "remaining_time": "17:34:59"}
+{"current_steps": 46, "total_steps": 650, "loss": 0.584, "lr": 2.8307692307692312e-05, "epoch": 0.3523216850167544, "percentage": 7.08, "elapsed_time": "1:20:31", "remaining_time": "17:37:22"}
+{"current_steps": 47, "total_steps": 650, "loss": 0.5804, "lr": 2.8923076923076925e-05, "epoch": 0.35998085208233604, "percentage": 7.23, "elapsed_time": "1:22:22", "remaining_time": "17:36:52"}
+{"current_steps": 48, "total_steps": 650, "loss": 0.5518, "lr": 2.9538461538461543e-05, "epoch": 0.36764001914791766, "percentage": 7.38, "elapsed_time": "1:23:59", "remaining_time": "17:33:22"}
+{"current_steps": 49, "total_steps": 650, "loss": 0.5846, "lr": 3.0153846153846155e-05, "epoch": 0.3752991862134993, "percentage": 7.54, "elapsed_time": "1:25:42", "remaining_time": "17:31:19"}
+{"current_steps": 50, "total_steps": 650, "loss": 0.5487, "lr": 3.0769230769230774e-05, "epoch": 0.3829583532790809, "percentage": 7.69, "elapsed_time": "1:27:01", "remaining_time": "17:24:17"}
+{"current_steps": 51, "total_steps": 650, "loss": 0.5395, "lr": 3.1384615384615386e-05, "epoch": 0.3906175203446625, "percentage": 7.85, "elapsed_time": "1:28:43", "remaining_time": "17:22:10"}
+{"current_steps": 52, "total_steps": 650, "loss": 0.5657, "lr": 3.2000000000000005e-05, "epoch": 0.39827668741024413, "percentage": 8.0, "elapsed_time": "1:30:35", "remaining_time": "17:21:48"}
+{"current_steps": 53, "total_steps": 650, "loss": 0.5399, "lr": 3.261538461538462e-05, "epoch": 0.40593585447582575, "percentage": 8.15, "elapsed_time": "1:32:10", "remaining_time": "17:18:16"}
+{"current_steps": 54, "total_steps": 650, "loss": 0.5377, "lr": 3.3230769230769236e-05, "epoch": 0.41359502154140737, "percentage": 8.31, "elapsed_time": "1:33:44", "remaining_time": "17:14:36"}
+{"current_steps": 55, "total_steps": 650, "loss": 0.5551, "lr": 3.384615384615385e-05, "epoch": 0.421254188606989, "percentage": 8.46, "elapsed_time": "1:35:31", "remaining_time": "17:13:19"}
+{"current_steps": 56, "total_steps": 650, "loss": 0.5702, "lr": 3.446153846153847e-05, "epoch": 0.4289133556725706, "percentage": 8.62, "elapsed_time": "1:37:15", "remaining_time": "17:11:38"}
+{"current_steps": 57, "total_steps": 650, "loss": 0.5552, "lr": 3.507692307692308e-05, "epoch": 0.4365725227381522, "percentage": 8.77, "elapsed_time": "1:39:02", "remaining_time": "17:10:18"}
+{"current_steps": 58, "total_steps": 650, "loss": 0.5688, "lr": 3.56923076923077e-05, "epoch": 0.44423168980373384, "percentage": 8.92, "elapsed_time": "1:40:48", "remaining_time": "17:08:51"}
+{"current_steps": 59, "total_steps": 650, "loss": 0.5641, "lr": 3.630769230769231e-05, "epoch": 0.45189085686931546, "percentage": 9.08, "elapsed_time": "1:42:45", "remaining_time": "17:09:24"}
+{"current_steps": 60, "total_steps": 650, "loss": 0.5536, "lr": 3.692307692307693e-05, "epoch": 0.4595500239348971, "percentage": 9.23, "elapsed_time": "1:44:56", "remaining_time": "17:11:57"}
+{"current_steps": 61, "total_steps": 650, "loss": 0.5497, "lr": 3.753846153846154e-05, "epoch": 0.4672091910004787, "percentage": 9.38, "elapsed_time": "1:46:35", "remaining_time": "17:09:14"}
+{"current_steps": 62, "total_steps": 650, "loss": 0.5611, "lr": 3.815384615384616e-05, "epoch": 0.4748683580660603, "percentage": 9.54, "elapsed_time": "1:48:32", "remaining_time": "17:09:23"}
+{"current_steps": 63, "total_steps": 650, "loss": 0.5703, "lr": 3.876923076923077e-05, "epoch": 0.48252752513164193, "percentage": 9.69, "elapsed_time": "1:50:07", "remaining_time": "17:06:00"}
+{"current_steps": 64, "total_steps": 650, "loss": 0.5468, "lr": 3.938461538461539e-05, "epoch": 0.49018669219722355, "percentage": 9.85, "elapsed_time": "1:51:47", "remaining_time": "17:03:32"}
+{"current_steps": 65, "total_steps": 650, "loss": 0.564, "lr": 4e-05, "epoch": 0.49784585926280517, "percentage": 10.0, "elapsed_time": "1:53:37", "remaining_time": "17:02:38"}
+{"current_steps": 66, "total_steps": 650, "loss": 0.5677, "lr": 3.999971160550277e-05, "epoch": 0.5055050263283868, "percentage": 10.15, "elapsed_time": "1:55:41", "remaining_time": "17:03:45"}
+{"current_steps": 67, "total_steps": 650, "loss": 0.5606, "lr": 3.999884643032821e-05, "epoch": 0.5131641933939685, "percentage": 10.31, "elapsed_time": "1:57:38", "remaining_time": "17:03:37"}
+{"current_steps": 68, "total_steps": 650, "loss": 0.551, "lr": 3.9997404499427494e-05, "epoch": 0.52082336045955, "percentage": 10.46, "elapsed_time": "1:59:18", "remaining_time": "17:01:04"}
+{"current_steps": 69, "total_steps": 650, "loss": 0.542, "lr": 3.9995385854385124e-05, "epoch": 0.5284825275251317, "percentage": 10.62, "elapsed_time": "2:01:12", "remaining_time": "17:00:34"}
+{"current_steps": 70, "total_steps": 650, "loss": 0.5255, "lr": 3.999279055341771e-05, "epoch": 0.5361416945907133, "percentage": 10.77, "elapsed_time": "2:02:51", "remaining_time": "16:57:58"}
+{"current_steps": 71, "total_steps": 650, "loss": 0.5578, "lr": 3.9989618671372304e-05, "epoch": 0.5438008616562949, "percentage": 10.92, "elapsed_time": "2:04:32", "remaining_time": "16:55:36"}
+{"current_steps": 72, "total_steps": 650, "loss": 0.5729, "lr": 3.998587029972423e-05, "epoch": 0.5514600287218765, "percentage": 11.08, "elapsed_time": "2:06:19", "remaining_time": "16:54:04"}
+{"current_steps": 73, "total_steps": 650, "loss": 0.5621, "lr": 3.998154554657448e-05, "epoch": 0.5591191957874582, "percentage": 11.23, "elapsed_time": "2:08:11", "remaining_time": "16:53:12"}
+{"current_steps": 74, "total_steps": 650, "loss": 0.539, "lr": 3.997664453664654e-05, "epoch": 0.5667783628530397, "percentage": 11.38, "elapsed_time": "2:09:54", "remaining_time": "16:51:10"}
+{"current_steps": 75, "total_steps": 650, "loss": 0.5451, "lr": 3.9971167411282835e-05, "epoch": 0.5744375299186214, "percentage": 11.54, "elapsed_time": "2:11:22", "remaining_time": "16:47:09"}
+{"current_steps": 76, "total_steps": 650, "loss": 0.5649, "lr": 3.996511432844067e-05, "epoch": 0.582096696984203, "percentage": 11.69, "elapsed_time": "2:13:06", "remaining_time": "16:45:16"}
+{"current_steps": 77, "total_steps": 650, "loss": 0.5518, "lr": 3.9958485462687606e-05, "epoch": 0.5897558640497846, "percentage": 11.85, "elapsed_time": "2:14:45", "remaining_time": "16:42:50"}
+{"current_steps": 78, "total_steps": 650, "loss": 0.5514, "lr": 3.9951281005196486e-05, "epoch": 0.5974150311153662, "percentage": 12.0, "elapsed_time": "2:16:35", "remaining_time": "16:41:41"}
+{"current_steps": 79, "total_steps": 650, "loss": 0.5408, "lr": 3.994350116373991e-05, "epoch": 0.6050741981809479, "percentage": 12.15, "elapsed_time": "2:18:02", "remaining_time": "16:37:41"}
+{"current_steps": 80, "total_steps": 650, "loss": 0.5507, "lr": 3.9935146162684206e-05, "epoch": 0.6127333652465294, "percentage": 12.31, "elapsed_time": "2:19:47", "remaining_time": "16:35:58"}
+{"current_steps": 81, "total_steps": 650, "loss": 0.5569, "lr": 3.9926216242983017e-05, "epoch": 0.6203925323121111, "percentage": 12.46, "elapsed_time": "2:21:27", "remaining_time": "16:33:40"}
+{"current_steps": 82, "total_steps": 650, "loss": 0.5312, "lr": 3.991671166217031e-05, "epoch": 0.6280516993776927, "percentage": 12.62, "elapsed_time": "2:23:11", "remaining_time": "16:31:54"}
+{"current_steps": 83, "total_steps": 650, "loss": 0.5644, "lr": 3.990663269435298e-05, "epoch": 0.6357108664432743, "percentage": 12.77, "elapsed_time": "2:25:00", "remaining_time": "16:30:35"}
+{"current_steps": 84, "total_steps": 650, "loss": 0.5756, "lr": 3.989597963020289e-05, "epoch": 0.6433700335088559, "percentage": 12.92, "elapsed_time": "2:26:40", "remaining_time": "16:28:16"}
+{"current_steps": 85, "total_steps": 650, "loss": 0.5311, "lr": 3.9884752776948564e-05, "epoch": 0.6510292005744376, "percentage": 13.08, "elapsed_time": "2:28:13", "remaining_time": "16:25:14"}
+{"current_steps": 86, "total_steps": 650, "loss": 0.5574, "lr": 3.9872952458366267e-05, "epoch": 0.6586883676400191, "percentage": 13.23, "elapsed_time": "2:29:50", "remaining_time": "16:22:41"}
+{"current_steps": 87, "total_steps": 650, "loss": 0.5513, "lr": 3.986057901477069e-05, "epoch": 0.6663475347056008, "percentage": 13.38, "elapsed_time": "2:31:21", "remaining_time": "16:19:30"}
+{"current_steps": 88, "total_steps": 650, "loss": 0.5483, "lr": 3.984763280300514e-05, "epoch": 0.6740067017711824, "percentage": 13.54, "elapsed_time": "2:33:14", "remaining_time": "16:18:38"}
+{"current_steps": 89, "total_steps": 650, "loss": 0.5892, "lr": 3.983411419643125e-05, "epoch": 0.681665868836764, "percentage": 13.69, "elapsed_time": "2:35:13", "remaining_time": "16:18:27"}
+{"current_steps": 90, "total_steps": 650, "loss": 0.5342, "lr": 3.982002358491817e-05, "epoch": 0.6893250359023456, "percentage": 13.85, "elapsed_time": "2:37:01", "remaining_time": "16:17:02"}
+{"current_steps": 91, "total_steps": 650, "loss": 0.5552, "lr": 3.980536137483141e-05, "epoch": 0.6969842029679273, "percentage": 14.0, "elapsed_time": "2:38:59", "remaining_time": "16:16:37"}
+{"current_steps": 92, "total_steps": 650, "loss": 0.5336, "lr": 3.9790127989021024e-05, "epoch": 0.7046433700335089, "percentage": 14.15, "elapsed_time": "2:40:37", "remaining_time": "16:14:16"}
+{"current_steps": 93, "total_steps": 650, "loss": 0.5601, "lr": 3.9774323866809485e-05, "epoch": 0.7123025370990905, "percentage": 14.31, "elapsed_time": "2:42:28", "remaining_time": "16:13:06"}
+{"current_steps": 94, "total_steps": 650, "loss": 0.5659, "lr": 3.9757949463978975e-05, "epoch": 0.7199617041646721, "percentage": 14.46, "elapsed_time": "2:44:23", "remaining_time": "16:12:20"}
+{"current_steps": 95, "total_steps": 650, "loss": 0.5204, "lr": 3.9741005252758255e-05, "epoch": 0.7276208712302538, "percentage": 14.62, "elapsed_time": "2:46:08", "remaining_time": "16:10:38"}
+{"current_steps": 96, "total_steps": 650, "loss": 0.5498, "lr": 3.9723491721809076e-05, "epoch": 0.7352800382958353, "percentage": 14.77, "elapsed_time": "2:47:57", "remaining_time": "16:09:16"}
+{"current_steps": 97, "total_steps": 650, "loss": 0.565, "lr": 3.970540937621201e-05, "epoch": 0.742939205361417, "percentage": 14.92, "elapsed_time": "2:49:40", "remaining_time": "16:07:17"}
+{"current_steps": 98, "total_steps": 650, "loss": 0.55, "lr": 3.9686758737451955e-05, "epoch": 0.7505983724269986, "percentage": 15.08, "elapsed_time": "2:51:12", "remaining_time": "16:04:22"}
+{"current_steps": 99, "total_steps": 650, "loss": 0.5348, "lr": 3.966754034340308e-05, "epoch": 0.7582575394925802, "percentage": 15.23, "elapsed_time": "2:52:56", "remaining_time": "16:02:29"}
+{"current_steps": 100, "total_steps": 650, "loss": 0.5242, "lr": 3.9647754748313294e-05, "epoch": 0.7659167065581618, "percentage": 15.38, "elapsed_time": "2:54:33", "remaining_time": "16:00:06"}
+{"current_steps": 101, "total_steps": 650, "loss": 0.542, "lr": 3.962740252278827e-05, "epoch": 0.7735758736237435, "percentage": 15.54, "elapsed_time": "2:56:08", "remaining_time": "15:57:26"}
+{"current_steps": 102, "total_steps": 650, "loss": 0.5465, "lr": 3.960648425377499e-05, "epoch": 0.781235040689325, "percentage": 15.69, "elapsed_time": "2:57:55", "remaining_time": "15:55:55"}
+{"current_steps": 103, "total_steps": 650, "loss": 0.5206, "lr": 3.958500054454482e-05, "epoch": 0.7888942077549067, "percentage": 15.85, "elapsed_time": "2:59:47", "remaining_time": "15:54:49"}
+{"current_steps": 104, "total_steps": 650, "loss": 0.5554, "lr": 3.9562952014676116e-05, "epoch": 0.7965533748204883, "percentage": 16.0, "elapsed_time": "3:01:23", "remaining_time": "15:52:16"}
+{"current_steps": 105, "total_steps": 650, "loss": 0.5745, "lr": 3.954033930003634e-05, "epoch": 0.8042125418860699, "percentage": 16.15, "elapsed_time": "3:03:16", "remaining_time": "15:51:14"}
+{"current_steps": 106, "total_steps": 650, "loss": 0.5413, "lr": 3.9517163052763756e-05, "epoch": 0.8118717089516515, "percentage": 16.31, "elapsed_time": "3:05:01", "remaining_time": "15:49:32"}
+{"current_steps": 107, "total_steps": 650, "loss": 0.5367, "lr": 3.9493423941248564e-05, "epoch": 0.8195308760172332, "percentage": 16.46, "elapsed_time": "3:06:46", "remaining_time": "15:47:48"}
+{"current_steps": 108, "total_steps": 650, "loss": 0.5643, "lr": 3.946912265011368e-05, "epoch": 0.8271900430828147, "percentage": 16.62, "elapsed_time": "3:08:29", "remaining_time": "15:45:57"}
+{"current_steps": 109, "total_steps": 650, "loss": 0.5434, "lr": 3.944425988019498e-05, "epoch": 0.8348492101483964, "percentage": 16.77, "elapsed_time": "3:10:34", "remaining_time": "15:45:53"}
+{"current_steps": 110, "total_steps": 650, "loss": 0.5313, "lr": 3.9418836348521045e-05, "epoch": 0.842508377213978, "percentage": 16.92, "elapsed_time": "3:12:31", "remaining_time": "15:45:05"}
+{"current_steps": 111, "total_steps": 650, "loss": 0.5257, "lr": 3.9392852788292556e-05, "epoch": 0.8501675442795597, "percentage": 17.08, "elapsed_time": "3:14:20", "remaining_time": "15:43:42"}
+{"current_steps": 112, "total_steps": 650, "loss": 0.5315, "lr": 3.936630994886109e-05, "epoch": 0.8578267113451412, "percentage": 17.23, "elapsed_time": "3:15:53", "remaining_time": "15:40:58"}
+{"current_steps": 113, "total_steps": 650, "loss": 0.5332, "lr": 3.933920859570753e-05, "epoch": 0.8654858784107229, "percentage": 17.38, "elapsed_time": "3:17:26", "remaining_time": "15:38:16"}
+{"current_steps": 114, "total_steps": 650, "loss": 0.5364, "lr": 3.931154951041998e-05, "epoch": 0.8731450454763044, "percentage": 17.54, "elapsed_time": "3:19:07", "remaining_time": "15:36:13"}
+{"current_steps": 115, "total_steps": 650, "loss": 0.5581, "lr": 3.928333349067125e-05, "epoch": 0.8808042125418861, "percentage": 17.69, "elapsed_time": "3:20:49", "remaining_time": "15:34:15"}
+{"current_steps": 116, "total_steps": 650, "loss": 0.5153, "lr": 3.925456135019582e-05, "epoch": 0.8884633796074677, "percentage": 17.85, "elapsed_time": "3:22:19", "remaining_time": "15:31:25"}
+{"current_steps": 117, "total_steps": 650, "loss": 0.5397, "lr": 3.922523391876638e-05, "epoch": 0.8961225466730494, "percentage": 18.0, "elapsed_time": "3:24:01", "remaining_time": "15:29:27"}
+{"current_steps": 118, "total_steps": 650, "loss": 0.5434, "lr": 3.9195352042169924e-05, "epoch": 0.9037817137386309, "percentage": 18.15, "elapsed_time": "3:25:43", "remaining_time": "15:27:30"}
+{"current_steps": 119, "total_steps": 650, "loss": 0.5412, "lr": 3.916491658218333e-05, "epoch": 0.9114408808042126, "percentage": 18.31, "elapsed_time": "3:27:32", "remaining_time": "15:26:06"}
+{"current_steps": 120, "total_steps": 650, "loss": 0.5345, "lr": 3.913392841654851e-05, "epoch": 0.9191000478697942, "percentage": 18.46, "elapsed_time": "3:29:10", "remaining_time": "15:23:51"}
+{"current_steps": 121, "total_steps": 650, "loss": 0.5374, "lr": 3.9102388438947104e-05, "epoch": 0.9267592149353758, "percentage": 18.62, "elapsed_time": "3:30:48", "remaining_time": "15:21:38"}
+{"current_steps": 122, "total_steps": 650, "loss": 0.528, "lr": 3.907029755897473e-05, "epoch": 0.9344183820009574, "percentage": 18.77, "elapsed_time": "3:32:38", "remaining_time": "15:20:17"}
+{"current_steps": 123, "total_steps": 650, "loss": 0.5432, "lr": 3.903765670211469e-05, "epoch": 0.9420775490665391, "percentage": 18.92, "elapsed_time": "3:34:19", "remaining_time": "15:18:15"}
+{"current_steps": 124, "total_steps": 650, "loss": 0.55, "lr": 3.9004466809711343e-05, "epoch": 0.9497367161321206, "percentage": 19.08, "elapsed_time": "3:35:57", "remaining_time": "15:16:06"}
+{"current_steps": 125, "total_steps": 650, "loss": 0.5322, "lr": 3.897072883894291e-05, "epoch": 0.9573958831977023, "percentage": 19.23, "elapsed_time": "3:37:36", "remaining_time": "15:13:55"}
+{"current_steps": 126, "total_steps": 650, "loss": 0.5118, "lr": 3.893644376279392e-05, "epoch": 0.9650550502632839, "percentage": 19.38, "elapsed_time": "3:39:17", "remaining_time": "15:11:58"}
+{"current_steps": 127, "total_steps": 650, "loss": 0.5279, "lr": 3.89016125700271e-05, "epoch": 0.9727142173288655, "percentage": 19.54, "elapsed_time": "3:41:01", "remaining_time": "15:10:12"}
+{"current_steps": 128, "total_steps": 650, "loss": 0.5464, "lr": 3.8866236265154864e-05, "epoch": 0.9803733843944471, "percentage": 19.69, "elapsed_time": "3:42:49", "remaining_time": "15:08:40"}
+{"current_steps": 129, "total_steps": 650, "loss": 0.5544, "lr": 3.88303158684104e-05, "epoch": 0.9880325514600288, "percentage": 19.85, "elapsed_time": "3:44:29", "remaining_time": "15:06:40"}
+{"current_steps": 130, "total_steps": 650, "loss": 0.5686, "lr": 3.879385241571817e-05, "epoch": 0.9956917185256103, "percentage": 20.0, "elapsed_time": "3:46:22", "remaining_time": "15:05:30"}
+{"current_steps": 131, "total_steps": 650, "loss": 0.8604, "lr": 3.875684695866409e-05, "epoch": 1.0047869794159885, "percentage": 20.15, "elapsed_time": "3:49:15", "remaining_time": "15:08:18"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33717ad82fd3097ea166bdc9f84616aa0d71f732c53e0c4676fcf64b811505b2
+size 7160