Training in progress, step 100

.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:b08bdaf3cdd53e3d001770fac4350497140a358ec77c827c1079e4c72ee5b86e
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:331076717441289ce469ba75cc08f110f27697a3bf656a8e4051048022b1053f
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cce9b00baeec8e068da62ece624cd46f4ba382aa307010b2927be5c80620871
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:360801a13fc9640bfaaa8e68dcdef0ae6cd41d9b7a3020291b1eda4ff5e5c270
+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 +1,108 @@
+{"current_steps": 1, "total_steps": 2712, "loss": 0.9258, "lr": 3.6764705882352945e-08, "epoch": 0.001105379513633014, "percentage": 0.04, "elapsed_time": "0:00:31", "remaining_time": "23:22:31"}
+{"current_steps": 2, "total_steps": 2712, "loss": 0.8939, "lr": 7.352941176470589e-08, "epoch": 0.002210759027266028, "percentage": 0.07, "elapsed_time": "0:00:54", "remaining_time": "20:27:35"}
+{"current_steps": 3, "total_steps": 2712, "loss": 0.943, "lr": 1.1029411764705884e-07, "epoch": 0.003316138540899042, "percentage": 0.11, "elapsed_time": "0:01:18", "remaining_time": "19:34:57"}
+{"current_steps": 4, "total_steps": 2712, "loss": 0.9192, "lr": 1.4705882352941178e-07, "epoch": 0.004421518054532056, "percentage": 0.15, "elapsed_time": "0:01:36", "remaining_time": "18:10:54"}
+{"current_steps": 5, "total_steps": 2712, "loss": 0.9211, "lr": 1.8382352941176472e-07, "epoch": 0.00552689756816507, "percentage": 0.18, "elapsed_time": "0:01:53", "remaining_time": "17:00:31"}
+{"current_steps": 6, "total_steps": 2712, "loss": 0.8763, "lr": 2.2058823529411768e-07, "epoch": 0.006632277081798084, "percentage": 0.22, "elapsed_time": "0:02:15", "remaining_time": "16:57:20"}
+{"current_steps": 7, "total_steps": 2712, "loss": 0.8715, "lr": 2.573529411764706e-07, "epoch": 0.007737656595431098, "percentage": 0.26, "elapsed_time": "0:02:35", "remaining_time": "16:42:45"}
+{"current_steps": 8, "total_steps": 2712, "loss": 0.915, "lr": 2.9411764705882356e-07, "epoch": 0.008843036109064112, "percentage": 0.29, "elapsed_time": "0:02:56", "remaining_time": "16:33:58"}
+{"current_steps": 9, "total_steps": 2712, "loss": 0.9309, "lr": 3.308823529411765e-07, "epoch": 0.009948415622697125, "percentage": 0.33, "elapsed_time": "0:03:18", "remaining_time": "16:35:35"}
+{"current_steps": 10, "total_steps": 2712, "loss": 0.8831, "lr": 3.6764705882352943e-07, "epoch": 0.01105379513633014, "percentage": 0.37, "elapsed_time": "0:03:39", "remaining_time": "16:28:38"}
+{"current_steps": 11, "total_steps": 2712, "loss": 0.9572, "lr": 4.044117647058824e-07, "epoch": 0.012159174649963155, "percentage": 0.41, "elapsed_time": "0:03:59", "remaining_time": "16:21:08"}
+{"current_steps": 12, "total_steps": 2712, "loss": 0.909, "lr": 4.4117647058823536e-07, "epoch": 0.013264554163596167, "percentage": 0.44, "elapsed_time": "0:04:22", "remaining_time": "16:23:50"}
+{"current_steps": 13, "total_steps": 2712, "loss": 0.8688, "lr": 4.779411764705882e-07, "epoch": 0.014369933677229182, "percentage": 0.48, "elapsed_time": "0:04:43", "remaining_time": "16:20:58"}
+{"current_steps": 14, "total_steps": 2712, "loss": 0.8938, "lr": 5.147058823529412e-07, "epoch": 0.015475313190862197, "percentage": 0.52, "elapsed_time": "0:05:03", "remaining_time": "16:16:10"}
+{"current_steps": 15, "total_steps": 2712, "loss": 0.9133, "lr": 5.514705882352942e-07, "epoch": 0.01658069270449521, "percentage": 0.55, "elapsed_time": "0:05:25", "remaining_time": "16:14:19"}
+{"current_steps": 16, "total_steps": 2712, "loss": 0.9289, "lr": 5.882352941176471e-07, "epoch": 0.017686072218128224, "percentage": 0.59, "elapsed_time": "0:05:43", "remaining_time": "16:04:24"}
+{"current_steps": 17, "total_steps": 2712, "loss": 0.8333, "lr": 6.25e-07, "epoch": 0.01879145173176124, "percentage": 0.63, "elapsed_time": "0:06:02", "remaining_time": "15:57:05"}
+{"current_steps": 18, "total_steps": 2712, "loss": 0.8533, "lr": 6.61764705882353e-07, "epoch": 0.01989683124539425, "percentage": 0.66, "elapsed_time": "0:06:23", "remaining_time": "15:56:08"}
+{"current_steps": 19, "total_steps": 2712, "loss": 0.8767, "lr": 6.985294117647059e-07, "epoch": 0.021002210759027265, "percentage": 0.7, "elapsed_time": "0:06:45", "remaining_time": "15:57:59"}
+{"current_steps": 20, "total_steps": 2712, "loss": 0.862, "lr": 7.352941176470589e-07, "epoch": 0.02210759027266028, "percentage": 0.74, "elapsed_time": "0:07:04", "remaining_time": "15:53:17"}
+{"current_steps": 21, "total_steps": 2712, "loss": 0.8554, "lr": 7.720588235294119e-07, "epoch": 0.023212969786293294, "percentage": 0.77, "elapsed_time": "0:07:23", "remaining_time": "15:47:14"}
+{"current_steps": 22, "total_steps": 2712, "loss": 0.8273, "lr": 8.088235294117648e-07, "epoch": 0.02431834929992631, "percentage": 0.81, "elapsed_time": "0:07:40", "remaining_time": "15:38:17"}
+{"current_steps": 23, "total_steps": 2712, "loss": 0.8214, "lr": 8.455882352941178e-07, "epoch": 0.025423728813559324, "percentage": 0.85, "elapsed_time": "0:08:00", "remaining_time": "15:35:50"}
+{"current_steps": 24, "total_steps": 2712, "loss": 0.7957, "lr": 8.823529411764707e-07, "epoch": 0.026529108327192335, "percentage": 0.88, "elapsed_time": "0:08:19", "remaining_time": "15:32:56"}
+{"current_steps": 25, "total_steps": 2712, "loss": 0.7873, "lr": 9.191176470588237e-07, "epoch": 0.02763448784082535, "percentage": 0.92, "elapsed_time": "0:08:40", "remaining_time": "15:33:00"}
+{"current_steps": 26, "total_steps": 2712, "loss": 0.7918, "lr": 9.558823529411764e-07, "epoch": 0.028739867354458364, "percentage": 0.96, "elapsed_time": "0:08:58", "remaining_time": "15:26:35"}
+{"current_steps": 27, "total_steps": 2712, "loss": 0.8047, "lr": 9.926470588235295e-07, "epoch": 0.02984524686809138, "percentage": 1.0, "elapsed_time": "0:09:19", "remaining_time": "15:26:48"}
+{"current_steps": 28, "total_steps": 2712, "loss": 0.8122, "lr": 1.0294117647058825e-06, "epoch": 0.030950626381724394, "percentage": 1.03, "elapsed_time": "0:09:41", "remaining_time": "15:29:42"}
+{"current_steps": 29, "total_steps": 2712, "loss": 0.7882, "lr": 1.0661764705882354e-06, "epoch": 0.032056005895357405, "percentage": 1.07, "elapsed_time": "0:10:00", "remaining_time": "15:25:28"}
+{"current_steps": 30, "total_steps": 2712, "loss": 0.7848, "lr": 1.1029411764705884e-06, "epoch": 0.03316138540899042, "percentage": 1.11, "elapsed_time": "0:10:18", "remaining_time": "15:21:10"}
+{"current_steps": 31, "total_steps": 2712, "loss": 0.7818, "lr": 1.1397058823529413e-06, "epoch": 0.034266764922623434, "percentage": 1.14, "elapsed_time": "0:10:37", "remaining_time": "15:18:33"}
+{"current_steps": 32, "total_steps": 2712, "loss": 0.7708, "lr": 1.1764705882352942e-06, "epoch": 0.03537214443625645, "percentage": 1.18, "elapsed_time": "0:10:57", "remaining_time": "15:17:13"}
+{"current_steps": 33, "total_steps": 2712, "loss": 0.7839, "lr": 1.2132352941176472e-06, "epoch": 0.036477523949889464, "percentage": 1.22, "elapsed_time": "0:11:20", "remaining_time": "15:20:50"}
+{"current_steps": 34, "total_steps": 2712, "loss": 0.7884, "lr": 1.25e-06, "epoch": 0.03758290346352248, "percentage": 1.25, "elapsed_time": "0:11:39", "remaining_time": "15:17:53"}
+{"current_steps": 35, "total_steps": 2712, "loss": 0.7463, "lr": 1.2867647058823528e-06, "epoch": 0.03868828297715549, "percentage": 1.29, "elapsed_time": "0:11:56", "remaining_time": "15:13:55"}
+{"current_steps": 36, "total_steps": 2712, "loss": 0.7583, "lr": 1.323529411764706e-06, "epoch": 0.0397936624907885, "percentage": 1.33, "elapsed_time": "0:12:16", "remaining_time": "15:12:02"}
+{"current_steps": 37, "total_steps": 2712, "loss": 0.7734, "lr": 1.360294117647059e-06, "epoch": 0.040899042004421515, "percentage": 1.36, "elapsed_time": "0:12:37", "remaining_time": "15:12:34"}
+{"current_steps": 38, "total_steps": 2712, "loss": 0.7595, "lr": 1.3970588235294119e-06, "epoch": 0.04200442151805453, "percentage": 1.4, "elapsed_time": "0:12:56", "remaining_time": "15:11:02"}
+{"current_steps": 39, "total_steps": 2712, "loss": 0.7487, "lr": 1.4338235294117648e-06, "epoch": 0.043109801031687545, "percentage": 1.44, "elapsed_time": "0:13:17", "remaining_time": "15:10:34"}
+{"current_steps": 40, "total_steps": 2712, "loss": 0.7241, "lr": 1.4705882352941177e-06, "epoch": 0.04421518054532056, "percentage": 1.47, "elapsed_time": "0:13:37", "remaining_time": "15:10:02"}
+{"current_steps": 41, "total_steps": 2712, "loss": 0.7356, "lr": 1.5073529411764707e-06, "epoch": 0.045320560058953574, "percentage": 1.51, "elapsed_time": "0:13:57", "remaining_time": "15:09:31"}
+{"current_steps": 42, "total_steps": 2712, "loss": 0.7589, "lr": 1.5441176470588238e-06, "epoch": 0.04642593957258659, "percentage": 1.55, "elapsed_time": "0:14:18", "remaining_time": "15:09:32"}
+{"current_steps": 43, "total_steps": 2712, "loss": 0.7037, "lr": 1.5808823529411765e-06, "epoch": 0.0475313190862196, "percentage": 1.59, "elapsed_time": "0:14:38", "remaining_time": "15:08:20"}
+{"current_steps": 44, "total_steps": 2712, "loss": 0.7111, "lr": 1.6176470588235297e-06, "epoch": 0.04863669859985262, "percentage": 1.62, "elapsed_time": "0:14:56", "remaining_time": "15:06:15"}
+{"current_steps": 45, "total_steps": 2712, "loss": 0.695, "lr": 1.6544117647058824e-06, "epoch": 0.04974207811348563, "percentage": 1.66, "elapsed_time": "0:15:17", "remaining_time": "15:06:43"}
+{"current_steps": 46, "total_steps": 2712, "loss": 0.678, "lr": 1.6911764705882356e-06, "epoch": 0.05084745762711865, "percentage": 1.7, "elapsed_time": "0:15:38", "remaining_time": "15:06:19"}
+{"current_steps": 47, "total_steps": 2712, "loss": 0.6947, "lr": 1.7279411764705883e-06, "epoch": 0.051952837140751655, "percentage": 1.73, "elapsed_time": "0:15:56", "remaining_time": "15:04:02"}
+{"current_steps": 48, "total_steps": 2712, "loss": 0.665, "lr": 1.7647058823529414e-06, "epoch": 0.05305821665438467, "percentage": 1.77, "elapsed_time": "0:16:18", "remaining_time": "15:04:51"}
+{"current_steps": 49, "total_steps": 2712, "loss": 0.7202, "lr": 1.8014705882352942e-06, "epoch": 0.054163596168017684, "percentage": 1.81, "elapsed_time": "0:16:36", "remaining_time": "15:02:42"}
+{"current_steps": 50, "total_steps": 2712, "loss": 0.7269, "lr": 1.8382352941176473e-06, "epoch": 0.0552689756816507, "percentage": 1.84, "elapsed_time": "0:16:59", "remaining_time": "15:04:47"}
+{"current_steps": 51, "total_steps": 2712, "loss": 0.654, "lr": 1.8750000000000003e-06, "epoch": 0.056374355195283714, "percentage": 1.88, "elapsed_time": "0:17:20", "remaining_time": "15:04:53"}
+{"current_steps": 52, "total_steps": 2712, "loss": 0.65, "lr": 1.9117647058823528e-06, "epoch": 0.05747973470891673, "percentage": 1.92, "elapsed_time": "0:17:41", "remaining_time": "15:04:53"}
+{"current_steps": 53, "total_steps": 2712, "loss": 0.6335, "lr": 1.948529411764706e-06, "epoch": 0.05858511422254974, "percentage": 1.95, "elapsed_time": "0:17:59", "remaining_time": "15:02:40"}
+{"current_steps": 54, "total_steps": 2712, "loss": 0.6667, "lr": 1.985294117647059e-06, "epoch": 0.05969049373618276, "percentage": 1.99, "elapsed_time": "0:18:23", "remaining_time": "15:05:12"}
+{"current_steps": 55, "total_steps": 2712, "loss": 0.6748, "lr": 2.022058823529412e-06, "epoch": 0.06079587324981577, "percentage": 2.03, "elapsed_time": "0:18:43", "remaining_time": "15:04:38"}
+{"current_steps": 56, "total_steps": 2712, "loss": 0.6538, "lr": 2.058823529411765e-06, "epoch": 0.06190125276344879, "percentage": 2.06, "elapsed_time": "0:19:06", "remaining_time": "15:06:04"}
+{"current_steps": 57, "total_steps": 2712, "loss": 0.6614, "lr": 2.095588235294118e-06, "epoch": 0.0630066322770818, "percentage": 2.1, "elapsed_time": "0:19:24", "remaining_time": "15:04:17"}
+{"current_steps": 58, "total_steps": 2712, "loss": 0.6756, "lr": 2.132352941176471e-06, "epoch": 0.06411201179071481, "percentage": 2.14, "elapsed_time": "0:19:44", "remaining_time": "15:03:40"}
+{"current_steps": 59, "total_steps": 2712, "loss": 0.6665, "lr": 2.1691176470588238e-06, "epoch": 0.06521739130434782, "percentage": 2.18, "elapsed_time": "0:20:04", "remaining_time": "15:02:32"}
+{"current_steps": 60, "total_steps": 2712, "loss": 0.6593, "lr": 2.2058823529411767e-06, "epoch": 0.06632277081798084, "percentage": 2.21, "elapsed_time": "0:20:24", "remaining_time": "15:02:06"}
+{"current_steps": 61, "total_steps": 2712, "loss": 0.6593, "lr": 2.2426470588235296e-06, "epoch": 0.06742815033161385, "percentage": 2.25, "elapsed_time": "0:20:43", "remaining_time": "15:00:47"}
+{"current_steps": 62, "total_steps": 2712, "loss": 0.6155, "lr": 2.2794117647058826e-06, "epoch": 0.06853352984524687, "percentage": 2.29, "elapsed_time": "0:21:05", "remaining_time": "15:01:50"}
+{"current_steps": 63, "total_steps": 2712, "loss": 0.6269, "lr": 2.3161764705882355e-06, "epoch": 0.06963890935887988, "percentage": 2.32, "elapsed_time": "0:21:26", "remaining_time": "15:01:32"}
+{"current_steps": 64, "total_steps": 2712, "loss": 0.634, "lr": 2.3529411764705885e-06, "epoch": 0.0707442888725129, "percentage": 2.36, "elapsed_time": "0:21:49", "remaining_time": "15:03:11"}
+{"current_steps": 65, "total_steps": 2712, "loss": 0.6291, "lr": 2.3897058823529414e-06, "epoch": 0.07184966838614591, "percentage": 2.4, "elapsed_time": "0:22:09", "remaining_time": "15:02:20"}
+{"current_steps": 66, "total_steps": 2712, "loss": 0.6303, "lr": 2.4264705882352943e-06, "epoch": 0.07295504789977893, "percentage": 2.43, "elapsed_time": "0:22:30", "remaining_time": "15:02:29"}
+{"current_steps": 67, "total_steps": 2712, "loss": 0.6252, "lr": 2.4632352941176473e-06, "epoch": 0.07406042741341194, "percentage": 2.47, "elapsed_time": "0:22:49", "remaining_time": "15:01:17"}
+{"current_steps": 68, "total_steps": 2712, "loss": 0.6296, "lr": 2.5e-06, "epoch": 0.07516580692704496, "percentage": 2.51, "elapsed_time": "0:23:09", "remaining_time": "15:00:08"}
+{"current_steps": 69, "total_steps": 2712, "loss": 0.6291, "lr": 2.536764705882353e-06, "epoch": 0.07627118644067797, "percentage": 2.54, "elapsed_time": "0:23:30", "remaining_time": "15:00:27"}
+{"current_steps": 70, "total_steps": 2712, "loss": 0.601, "lr": 2.5735294117647057e-06, "epoch": 0.07737656595431099, "percentage": 2.58, "elapsed_time": "0:23:53", "remaining_time": "15:01:29"}
+{"current_steps": 71, "total_steps": 2712, "loss": 0.5915, "lr": 2.610294117647059e-06, "epoch": 0.078481945467944, "percentage": 2.62, "elapsed_time": "0:24:13", "remaining_time": "15:01:12"}
+{"current_steps": 72, "total_steps": 2712, "loss": 0.6266, "lr": 2.647058823529412e-06, "epoch": 0.079587324981577, "percentage": 2.65, "elapsed_time": "0:24:33", "remaining_time": "15:00:22"}
+{"current_steps": 73, "total_steps": 2712, "loss": 0.6247, "lr": 2.683823529411765e-06, "epoch": 0.08069270449521002, "percentage": 2.69, "elapsed_time": "0:24:54", "remaining_time": "15:00:17"}
+{"current_steps": 74, "total_steps": 2712, "loss": 0.6536, "lr": 2.720588235294118e-06, "epoch": 0.08179808400884303, "percentage": 2.73, "elapsed_time": "0:25:13", "remaining_time": "14:59:16"}
+{"current_steps": 75, "total_steps": 2712, "loss": 0.6491, "lr": 2.757352941176471e-06, "epoch": 0.08290346352247605, "percentage": 2.77, "elapsed_time": "0:25:33", "remaining_time": "14:58:49"}
+{"current_steps": 76, "total_steps": 2712, "loss": 0.5848, "lr": 2.7941176470588237e-06, "epoch": 0.08400884303610906, "percentage": 2.8, "elapsed_time": "0:25:55", "remaining_time": "14:59:20"}
+{"current_steps": 77, "total_steps": 2712, "loss": 0.6338, "lr": 2.8308823529411766e-06, "epoch": 0.08511422254974207, "percentage": 2.84, "elapsed_time": "0:26:16", "remaining_time": "14:59:23"}
+{"current_steps": 78, "total_steps": 2712, "loss": 0.6127, "lr": 2.8676470588235296e-06, "epoch": 0.08621960206337509, "percentage": 2.88, "elapsed_time": "0:26:36", "remaining_time": "14:58:30"}
+{"current_steps": 79, "total_steps": 2712, "loss": 0.6039, "lr": 2.904411764705883e-06, "epoch": 0.0873249815770081, "percentage": 2.91, "elapsed_time": "0:26:57", "remaining_time": "14:58:13"}
+{"current_steps": 80, "total_steps": 2712, "loss": 0.6187, "lr": 2.9411764705882355e-06, "epoch": 0.08843036109064112, "percentage": 2.95, "elapsed_time": "0:27:16", "remaining_time": "14:57:19"}
+{"current_steps": 81, "total_steps": 2712, "loss": 0.6192, "lr": 2.9779411764705884e-06, "epoch": 0.08953574060427413, "percentage": 2.99, "elapsed_time": "0:27:34", "remaining_time": "14:55:46"}
+{"current_steps": 82, "total_steps": 2712, "loss": 0.6195, "lr": 3.0147058823529413e-06, "epoch": 0.09064112011790715, "percentage": 3.02, "elapsed_time": "0:27:54", "remaining_time": "14:55:05"}
+{"current_steps": 83, "total_steps": 2712, "loss": 0.5929, "lr": 3.0514705882352947e-06, "epoch": 0.09174649963154016, "percentage": 3.06, "elapsed_time": "0:28:10", "remaining_time": "14:52:35"}
+{"current_steps": 84, "total_steps": 2712, "loss": 0.6087, "lr": 3.0882352941176476e-06, "epoch": 0.09285187914517318, "percentage": 3.1, "elapsed_time": "0:28:29", "remaining_time": "14:51:11"}
+{"current_steps": 85, "total_steps": 2712, "loss": 0.5809, "lr": 3.125e-06, "epoch": 0.09395725865880619, "percentage": 3.13, "elapsed_time": "0:28:49", "remaining_time": "14:50:41"}
+{"current_steps": 86, "total_steps": 2712, "loss": 0.6211, "lr": 3.161764705882353e-06, "epoch": 0.0950626381724392, "percentage": 3.17, "elapsed_time": "0:29:07", "remaining_time": "14:49:30"}
+{"current_steps": 87, "total_steps": 2712, "loss": 0.6022, "lr": 3.198529411764706e-06, "epoch": 0.09616801768607222, "percentage": 3.21, "elapsed_time": "0:29:28", "remaining_time": "14:49:21"}
+{"current_steps": 88, "total_steps": 2712, "loss": 0.5997, "lr": 3.2352941176470594e-06, "epoch": 0.09727339719970524, "percentage": 3.24, "elapsed_time": "0:29:47", "remaining_time": "14:48:06"}
+{"current_steps": 89, "total_steps": 2712, "loss": 0.6108, "lr": 3.272058823529412e-06, "epoch": 0.09837877671333825, "percentage": 3.28, "elapsed_time": "0:30:09", "remaining_time": "14:48:55"}
+{"current_steps": 90, "total_steps": 2712, "loss": 0.5977, "lr": 3.308823529411765e-06, "epoch": 0.09948415622697127, "percentage": 3.32, "elapsed_time": "0:30:31", "remaining_time": "14:49:24"}
+{"current_steps": 91, "total_steps": 2712, "loss": 0.573, "lr": 3.3455882352941178e-06, "epoch": 0.10058953574060428, "percentage": 3.36, "elapsed_time": "0:30:53", "remaining_time": "14:49:36"}
+{"current_steps": 92, "total_steps": 2712, "loss": 0.583, "lr": 3.382352941176471e-06, "epoch": 0.1016949152542373, "percentage": 3.39, "elapsed_time": "0:31:13", "remaining_time": "14:49:08"}
+{"current_steps": 93, "total_steps": 2712, "loss": 0.5809, "lr": 3.419117647058824e-06, "epoch": 0.1028002947678703, "percentage": 3.43, "elapsed_time": "0:31:34", "remaining_time": "14:49:02"}
+{"current_steps": 94, "total_steps": 2712, "loss": 0.5715, "lr": 3.4558823529411766e-06, "epoch": 0.10390567428150331, "percentage": 3.47, "elapsed_time": "0:31:54", "remaining_time": "14:48:35"}
+{"current_steps": 95, "total_steps": 2712, "loss": 0.5743, "lr": 3.4926470588235295e-06, "epoch": 0.10501105379513632, "percentage": 3.5, "elapsed_time": "0:32:15", "remaining_time": "14:48:46"}
+{"current_steps": 96, "total_steps": 2712, "loss": 0.5728, "lr": 3.529411764705883e-06, "epoch": 0.10611643330876934, "percentage": 3.54, "elapsed_time": "0:32:35", "remaining_time": "14:48:13"}
+{"current_steps": 97, "total_steps": 2712, "loss": 0.5953, "lr": 3.566176470588236e-06, "epoch": 0.10722181282240235, "percentage": 3.58, "elapsed_time": "0:32:53", "remaining_time": "14:46:45"}
+{"current_steps": 98, "total_steps": 2712, "loss": 0.6019, "lr": 3.6029411764705883e-06, "epoch": 0.10832719233603537, "percentage": 3.61, "elapsed_time": "0:33:15", "remaining_time": "14:47:01"}
+{"current_steps": 99, "total_steps": 2712, "loss": 0.5998, "lr": 3.6397058823529413e-06, "epoch": 0.10943257184966838, "percentage": 3.65, "elapsed_time": "0:33:34", "remaining_time": "14:46:16"}
+{"current_steps": 100, "total_steps": 2712, "loss": 0.5941, "lr": 3.6764705882352946e-06, "epoch": 0.1105379513633014, "percentage": 3.69, "elapsed_time": "0:33:52", "remaining_time": "14:44:43"}
+{"current_steps": 101, "total_steps": 2712, "loss": 0.5631, "lr": 3.7132352941176476e-06, "epoch": 0.11164333087693441, "percentage": 3.72, "elapsed_time": "0:35:00", "remaining_time": "15:05:05"}
+{"current_steps": 102, "total_steps": 2712, "loss": 0.5963, "lr": 3.7500000000000005e-06, "epoch": 0.11274871039056743, "percentage": 3.76, "elapsed_time": "0:35:21", "remaining_time": "15:04:47"}
+{"current_steps": 103, "total_steps": 2712, "loss": 0.6126, "lr": 3.786764705882353e-06, "epoch": 0.11385408990420044, "percentage": 3.8, "elapsed_time": "0:35:39", "remaining_time": "15:03:14"}
+{"current_steps": 104, "total_steps": 2712, "loss": 0.5989, "lr": 3.8235294117647055e-06, "epoch": 0.11495946941783346, "percentage": 3.83, "elapsed_time": "0:36:00", "remaining_time": "15:02:50"}
+{"current_steps": 105, "total_steps": 2712, "loss": 0.5817, "lr": 3.860294117647059e-06, "epoch": 0.11606484893146647, "percentage": 3.87, "elapsed_time": "0:36:16", "remaining_time": "15:00:32"}
+{"current_steps": 106, "total_steps": 2712, "loss": 0.5783, "lr": 3.897058823529412e-06, "epoch": 0.11717022844509949, "percentage": 3.91, "elapsed_time": "0:36:35", "remaining_time": "14:59:34"}
+{"current_steps": 107, "total_steps": 2712, "loss": 0.5818, "lr": 3.933823529411765e-06, "epoch": 0.1182756079587325, "percentage": 3.95, "elapsed_time": "0:36:56", "remaining_time": "14:59:25"}
+{"current_steps": 108, "total_steps": 2712, "loss": 0.5875, "lr": 3.970588235294118e-06, "epoch": 0.11938098747236552, "percentage": 3.98, "elapsed_time": "0:37:15", "remaining_time": "14:58:22"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60476861909c15247f24aeb7571e7e62953ed9ea9a3cba27ae783204d083dfdf
+size 7352