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 sha256:57a38dd6109f574708538f246813233de7b4de64efecba54d4d1aaafe503199a
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5bdc49f6af7a19900bab212ee0c7708ca6bd70cd1e9c33e4a1f7402db52903
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64eee520b9c2d4a00f69a74c7920c79f7d98bc15305c3ccdeaf95b68901a0da0
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127e0e2da19629eeadd10ded103c154d82937eee9cc6460ee40ef635014f2f0c
+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 +1,101 @@
+{"current_steps": 1, "total_steps": 3561, "loss": 0.8129, "lr": 2.8011204481792718e-08, "epoch": 0.0008424008424008424, "percentage": 0.03, "elapsed_time": "0:01:08", "remaining_time": "2 days, 19:44:26"}
+{"current_steps": 2, "total_steps": 3561, "loss": 0.8147, "lr": 5.6022408963585437e-08, "epoch": 0.0016848016848016849, "percentage": 0.06, "elapsed_time": "0:02:18", "remaining_time": "2 days, 20:18:21"}
+{"current_steps": 3, "total_steps": 3561, "loss": 0.8391, "lr": 8.403361344537815e-08, "epoch": 0.0025272025272025274, "percentage": 0.08, "elapsed_time": "0:03:09", "remaining_time": "2 days, 14:21:52"}
+{"current_steps": 4, "total_steps": 3561, "loss": 0.8272, "lr": 1.1204481792717087e-07, "epoch": 0.0033696033696033697, "percentage": 0.11, "elapsed_time": "0:04:08", "remaining_time": "2 days, 13:25:48"}
+{"current_steps": 5, "total_steps": 3561, "loss": 0.8544, "lr": 1.400560224089636e-07, "epoch": 0.004212004212004212, "percentage": 0.14, "elapsed_time": "0:05:14", "remaining_time": "2 days, 14:08:24"}
+{"current_steps": 6, "total_steps": 3561, "loss": 0.8662, "lr": 1.680672268907563e-07, "epoch": 0.005054405054405055, "percentage": 0.17, "elapsed_time": "0:06:13", "remaining_time": "2 days, 13:28:14"}
+{"current_steps": 7, "total_steps": 3561, "loss": 0.902, "lr": 1.9607843137254904e-07, "epoch": 0.005896805896805897, "percentage": 0.2, "elapsed_time": "0:07:16", "remaining_time": "2 days, 13:32:35"}
+{"current_steps": 8, "total_steps": 3561, "loss": 0.862, "lr": 2.2408963585434175e-07, "epoch": 0.006739206739206739, "percentage": 0.22, "elapsed_time": "0:08:26", "remaining_time": "2 days, 14:25:57"}
+{"current_steps": 9, "total_steps": 3561, "loss": 0.8482, "lr": 2.5210084033613445e-07, "epoch": 0.007581607581607581, "percentage": 0.25, "elapsed_time": "0:09:19", "remaining_time": "2 days, 13:18:30"}
+{"current_steps": 10, "total_steps": 3561, "loss": 0.8638, "lr": 2.801120448179272e-07, "epoch": 0.008424008424008424, "percentage": 0.28, "elapsed_time": "0:10:14", "remaining_time": "2 days, 12:37:19"}
+{"current_steps": 11, "total_steps": 3561, "loss": 0.8513, "lr": 3.081232492997199e-07, "epoch": 0.009266409266409266, "percentage": 0.31, "elapsed_time": "0:11:11", "remaining_time": "2 days, 12:09:30"}
+{"current_steps": 12, "total_steps": 3561, "loss": 0.8474, "lr": 3.361344537815126e-07, "epoch": 0.01010881010881011, "percentage": 0.34, "elapsed_time": "0:12:19", "remaining_time": "2 days, 12:43:10"}
+{"current_steps": 13, "total_steps": 3561, "loss": 0.8612, "lr": 3.641456582633054e-07, "epoch": 0.010951210951210951, "percentage": 0.37, "elapsed_time": "0:13:15", "remaining_time": "2 days, 12:20:26"}
+{"current_steps": 14, "total_steps": 3561, "loss": 0.8762, "lr": 3.921568627450981e-07, "epoch": 0.011793611793611793, "percentage": 0.39, "elapsed_time": "0:14:19", "remaining_time": "2 days, 12:30:16"}
+{"current_steps": 15, "total_steps": 3561, "loss": 0.8423, "lr": 4.201680672268908e-07, "epoch": 0.012636012636012635, "percentage": 0.42, "elapsed_time": "0:15:16", "remaining_time": "2 days, 12:12:35"}
+{"current_steps": 16, "total_steps": 3561, "loss": 0.778, "lr": 4.481792717086835e-07, "epoch": 0.013478413478413479, "percentage": 0.45, "elapsed_time": "0:16:21", "remaining_time": "2 days, 12:24:04"}
+{"current_steps": 17, "total_steps": 3561, "loss": 0.8601, "lr": 4.7619047619047623e-07, "epoch": 0.01432081432081432, "percentage": 0.48, "elapsed_time": "0:17:24", "remaining_time": "2 days, 12:30:23"}
+{"current_steps": 18, "total_steps": 3561, "loss": 0.8292, "lr": 5.042016806722689e-07, "epoch": 0.015163215163215163, "percentage": 0.51, "elapsed_time": "0:18:24", "remaining_time": "2 days, 12:23:53"}
+{"current_steps": 19, "total_steps": 3561, "loss": 0.8305, "lr": 5.322128851540616e-07, "epoch": 0.016005616005616004, "percentage": 0.53, "elapsed_time": "0:19:26", "remaining_time": "2 days, 12:24:26"}
+{"current_steps": 20, "total_steps": 3561, "loss": 0.8026, "lr": 5.602240896358544e-07, "epoch": 0.016848016848016848, "percentage": 0.56, "elapsed_time": "0:20:20", "remaining_time": "2 days, 12:02:03"}
+{"current_steps": 21, "total_steps": 3561, "loss": 0.8122, "lr": 5.882352941176471e-07, "epoch": 0.01769041769041769, "percentage": 0.59, "elapsed_time": "0:21:17", "remaining_time": "2 days, 11:49:35"}
+{"current_steps": 22, "total_steps": 3561, "loss": 0.7928, "lr": 6.162464985994398e-07, "epoch": 0.018532818532818532, "percentage": 0.62, "elapsed_time": "0:22:08", "remaining_time": "2 days, 11:22:00"}
+{"current_steps": 23, "total_steps": 3561, "loss": 0.7786, "lr": 6.442577030812325e-07, "epoch": 0.019375219375219375, "percentage": 0.65, "elapsed_time": "0:23:04", "remaining_time": "2 days, 11:08:35"}
+{"current_steps": 24, "total_steps": 3561, "loss": 0.8231, "lr": 6.722689075630252e-07, "epoch": 0.02021762021762022, "percentage": 0.67, "elapsed_time": "0:24:06", "remaining_time": "2 days, 11:12:35"}
+{"current_steps": 25, "total_steps": 3561, "loss": 0.8064, "lr": 7.002801120448179e-07, "epoch": 0.02106002106002106, "percentage": 0.7, "elapsed_time": "0:25:07", "remaining_time": "2 days, 11:14:32"}
+{"current_steps": 26, "total_steps": 3561, "loss": 0.7966, "lr": 7.282913165266108e-07, "epoch": 0.021902421902421903, "percentage": 0.73, "elapsed_time": "0:26:02", "remaining_time": "2 days, 11:00:06"}
+{"current_steps": 27, "total_steps": 3561, "loss": 0.7699, "lr": 7.563025210084034e-07, "epoch": 0.022744822744822746, "percentage": 0.76, "elapsed_time": "0:26:58", "remaining_time": "2 days, 10:51:12"}
+{"current_steps": 28, "total_steps": 3561, "loss": 0.7631, "lr": 7.843137254901962e-07, "epoch": 0.023587223587223587, "percentage": 0.79, "elapsed_time": "0:27:54", "remaining_time": "2 days, 10:41:09"}
+{"current_steps": 29, "total_steps": 3561, "loss": 0.7371, "lr": 8.123249299719889e-07, "epoch": 0.02442962442962443, "percentage": 0.81, "elapsed_time": "0:28:55", "remaining_time": "2 days, 10:42:16"}
+{"current_steps": 30, "total_steps": 3561, "loss": 0.7855, "lr": 8.403361344537816e-07, "epoch": 0.02527202527202527, "percentage": 0.84, "elapsed_time": "0:29:58", "remaining_time": "2 days, 10:47:54"}
+{"current_steps": 31, "total_steps": 3561, "loss": 0.7574, "lr": 8.683473389355742e-07, "epoch": 0.026114426114426114, "percentage": 0.87, "elapsed_time": "0:30:52", "remaining_time": "2 days, 10:36:07"}
+{"current_steps": 32, "total_steps": 3561, "loss": 0.7558, "lr": 8.96358543417367e-07, "epoch": 0.026956826956826958, "percentage": 0.9, "elapsed_time": "0:31:55", "remaining_time": "2 days, 10:40:10"}
+{"current_steps": 33, "total_steps": 3561, "loss": 0.744, "lr": 9.243697478991598e-07, "epoch": 0.027799227799227798, "percentage": 0.93, "elapsed_time": "0:32:52", "remaining_time": "2 days, 10:34:05"}
+{"current_steps": 34, "total_steps": 3561, "loss": 0.7321, "lr": 9.523809523809525e-07, "epoch": 0.02864162864162864, "percentage": 0.95, "elapsed_time": "0:33:59", "remaining_time": "2 days, 10:45:41"}
+{"current_steps": 35, "total_steps": 3561, "loss": 0.7501, "lr": 9.80392156862745e-07, "epoch": 0.029484029484029485, "percentage": 0.98, "elapsed_time": "0:35:01", "remaining_time": "2 days, 10:47:55"}
+{"current_steps": 36, "total_steps": 3561, "loss": 0.6992, "lr": 1.0084033613445378e-06, "epoch": 0.030326430326430325, "percentage": 1.01, "elapsed_time": "0:35:56", "remaining_time": "2 days, 10:38:51"}
+{"current_steps": 37, "total_steps": 3561, "loss": 0.7004, "lr": 1.0364145658263308e-06, "epoch": 0.03116883116883117, "percentage": 1.04, "elapsed_time": "0:36:57", "remaining_time": "2 days, 10:39:46"}
+{"current_steps": 38, "total_steps": 3561, "loss": 0.7279, "lr": 1.0644257703081233e-06, "epoch": 0.03201123201123201, "percentage": 1.07, "elapsed_time": "0:37:51", "remaining_time": "2 days, 10:30:04"}
+{"current_steps": 39, "total_steps": 3561, "loss": 0.7352, "lr": 1.092436974789916e-06, "epoch": 0.03285363285363285, "percentage": 1.1, "elapsed_time": "0:38:57", "remaining_time": "2 days, 10:37:30"}
+{"current_steps": 40, "total_steps": 3561, "loss": 0.6987, "lr": 1.1204481792717088e-06, "epoch": 0.033696033696033696, "percentage": 1.12, "elapsed_time": "0:39:56", "remaining_time": "2 days, 10:36:09"}
+{"current_steps": 41, "total_steps": 3561, "loss": 0.6993, "lr": 1.1484593837535015e-06, "epoch": 0.03453843453843454, "percentage": 1.15, "elapsed_time": "0:40:48", "remaining_time": "2 days, 10:24:12"}
+{"current_steps": 42, "total_steps": 3561, "loss": 0.7012, "lr": 1.1764705882352942e-06, "epoch": 0.03538083538083538, "percentage": 1.18, "elapsed_time": "0:41:45", "remaining_time": "2 days, 10:19:00"}
+{"current_steps": 43, "total_steps": 3561, "loss": 0.7059, "lr": 1.204481792717087e-06, "epoch": 0.03622323622323622, "percentage": 1.21, "elapsed_time": "0:42:43", "remaining_time": "2 days, 10:15:56"}
+{"current_steps": 44, "total_steps": 3561, "loss": 0.6757, "lr": 1.2324929971988797e-06, "epoch": 0.037065637065637064, "percentage": 1.24, "elapsed_time": "0:43:41", "remaining_time": "2 days, 10:12:53"}
+{"current_steps": 45, "total_steps": 3561, "loss": 0.706, "lr": 1.2605042016806724e-06, "epoch": 0.03790803790803791, "percentage": 1.26, "elapsed_time": "0:44:39", "remaining_time": "2 days, 10:08:50"}
+{"current_steps": 46, "total_steps": 3561, "loss": 0.6761, "lr": 1.288515406162465e-06, "epoch": 0.03875043875043875, "percentage": 1.29, "elapsed_time": "0:45:37", "remaining_time": "2 days, 10:06:18"}
+{"current_steps": 47, "total_steps": 3561, "loss": 0.7056, "lr": 1.316526610644258e-06, "epoch": 0.039592839592839595, "percentage": 1.32, "elapsed_time": "0:46:43", "remaining_time": "2 days, 10:13:54"}
+{"current_steps": 48, "total_steps": 3561, "loss": 0.653, "lr": 1.3445378151260504e-06, "epoch": 0.04043524043524044, "percentage": 1.35, "elapsed_time": "0:47:37", "remaining_time": "2 days, 10:05:56"}
+{"current_steps": 49, "total_steps": 3561, "loss": 0.6784, "lr": 1.3725490196078434e-06, "epoch": 0.041277641277641275, "percentage": 1.38, "elapsed_time": "0:48:40", "remaining_time": "2 days, 10:08:36"}
+{"current_steps": 50, "total_steps": 3561, "loss": 0.6257, "lr": 1.4005602240896359e-06, "epoch": 0.04212004212004212, "percentage": 1.4, "elapsed_time": "0:49:37", "remaining_time": "2 days, 10:04:36"}
+{"current_steps": 51, "total_steps": 3561, "loss": 0.6544, "lr": 1.4285714285714286e-06, "epoch": 0.04296244296244296, "percentage": 1.43, "elapsed_time": "0:50:42", "remaining_time": "2 days, 10:10:11"}
+{"current_steps": 52, "total_steps": 3561, "loss": 0.6438, "lr": 1.4565826330532216e-06, "epoch": 0.043804843804843806, "percentage": 1.46, "elapsed_time": "0:51:39", "remaining_time": "2 days, 10:06:17"}
+{"current_steps": 53, "total_steps": 3561, "loss": 0.6742, "lr": 1.484593837535014e-06, "epoch": 0.04464724464724465, "percentage": 1.49, "elapsed_time": "0:52:37", "remaining_time": "2 days, 10:02:45"}
+{"current_steps": 54, "total_steps": 3561, "loss": 0.668, "lr": 1.5126050420168068e-06, "epoch": 0.04548964548964549, "percentage": 1.52, "elapsed_time": "0:53:36", "remaining_time": "2 days, 10:01:57"}
+{"current_steps": 55, "total_steps": 3561, "loss": 0.6669, "lr": 1.5406162464985996e-06, "epoch": 0.04633204633204633, "percentage": 1.54, "elapsed_time": "0:54:30", "remaining_time": "2 days, 9:55:00"}
+{"current_steps": 56, "total_steps": 3561, "loss": 0.6503, "lr": 1.5686274509803923e-06, "epoch": 0.04717444717444717, "percentage": 1.57, "elapsed_time": "0:55:38", "remaining_time": "2 days, 10:02:39"}
+{"current_steps": 57, "total_steps": 3561, "loss": 0.6438, "lr": 1.5966386554621848e-06, "epoch": 0.04801684801684802, "percentage": 1.6, "elapsed_time": "0:56:49", "remaining_time": "2 days, 10:13:38"}
+{"current_steps": 58, "total_steps": 3561, "loss": 0.6279, "lr": 1.6246498599439778e-06, "epoch": 0.04885924885924886, "percentage": 1.63, "elapsed_time": "0:57:45", "remaining_time": "2 days, 10:08:03"}
+{"current_steps": 59, "total_steps": 3561, "loss": 0.5975, "lr": 1.6526610644257705e-06, "epoch": 0.049701649701649704, "percentage": 1.66, "elapsed_time": "0:58:46", "remaining_time": "2 days, 10:08:40"}
+{"current_steps": 60, "total_steps": 3561, "loss": 0.6672, "lr": 1.6806722689075632e-06, "epoch": 0.05054405054405054, "percentage": 1.68, "elapsed_time": "0:59:51", "remaining_time": "2 days, 10:13:06"}
+{"current_steps": 61, "total_steps": 3561, "loss": 0.6227, "lr": 1.708683473389356e-06, "epoch": 0.051386451386451384, "percentage": 1.71, "elapsed_time": "1:00:49", "remaining_time": "2 days, 10:09:55"}
+{"current_steps": 62, "total_steps": 3561, "loss": 0.6123, "lr": 1.7366946778711485e-06, "epoch": 0.05222885222885223, "percentage": 1.74, "elapsed_time": "1:01:36", "remaining_time": "2 days, 9:56:47"}
+{"current_steps": 63, "total_steps": 3561, "loss": 0.6373, "lr": 1.7647058823529414e-06, "epoch": 0.05307125307125307, "percentage": 1.77, "elapsed_time": "1:02:38", "remaining_time": "2 days, 9:58:30"}
+{"current_steps": 64, "total_steps": 3561, "loss": 0.5846, "lr": 1.792717086834734e-06, "epoch": 0.053913653913653915, "percentage": 1.8, "elapsed_time": "1:03:27", "remaining_time": "2 days, 9:47:51"}
+{"current_steps": 65, "total_steps": 3561, "loss": 0.5976, "lr": 1.8207282913165267e-06, "epoch": 0.05475605475605476, "percentage": 1.83, "elapsed_time": "1:04:31", "remaining_time": "2 days, 9:50:10"}
+{"current_steps": 66, "total_steps": 3561, "loss": 0.6183, "lr": 1.8487394957983196e-06, "epoch": 0.055598455598455596, "percentage": 1.85, "elapsed_time": "1:05:35", "remaining_time": "2 days, 9:53:48"}
+{"current_steps": 67, "total_steps": 3561, "loss": 0.613, "lr": 1.8767507002801122e-06, "epoch": 0.05644085644085644, "percentage": 1.88, "elapsed_time": "1:06:41", "remaining_time": "2 days, 9:57:52"}
+{"current_steps": 68, "total_steps": 3561, "loss": 0.5811, "lr": 1.904761904761905e-06, "epoch": 0.05728325728325728, "percentage": 1.91, "elapsed_time": "1:07:32", "remaining_time": "2 days, 9:49:29"}
+{"current_steps": 69, "total_steps": 3561, "loss": 0.6077, "lr": 1.932773109243698e-06, "epoch": 0.058125658125658126, "percentage": 1.94, "elapsed_time": "1:08:38", "remaining_time": "2 days, 9:53:54"}
+{"current_steps": 70, "total_steps": 3561, "loss": 0.5945, "lr": 1.96078431372549e-06, "epoch": 0.05896805896805897, "percentage": 1.97, "elapsed_time": "1:09:34", "remaining_time": "2 days, 9:49:44"}
+{"current_steps": 71, "total_steps": 3561, "loss": 0.6068, "lr": 1.988795518207283e-06, "epoch": 0.059810459810459814, "percentage": 1.99, "elapsed_time": "1:10:34", "remaining_time": "2 days, 9:49:01"}
+{"current_steps": 72, "total_steps": 3561, "loss": 0.6022, "lr": 2.0168067226890756e-06, "epoch": 0.06065286065286065, "percentage": 2.02, "elapsed_time": "1:11:41", "remaining_time": "2 days, 9:53:54"}
+{"current_steps": 73, "total_steps": 3561, "loss": 0.6114, "lr": 2.0448179271708684e-06, "epoch": 0.061495261495261494, "percentage": 2.05, "elapsed_time": "1:12:49", "remaining_time": "2 days, 9:59:59"}
+{"current_steps": 74, "total_steps": 3561, "loss": 0.6032, "lr": 2.0728291316526615e-06, "epoch": 0.06233766233766234, "percentage": 2.08, "elapsed_time": "1:13:53", "remaining_time": "2 days, 10:01:49"}
+{"current_steps": 75, "total_steps": 3561, "loss": 0.5786, "lr": 2.100840336134454e-06, "epoch": 0.06318006318006318, "percentage": 2.11, "elapsed_time": "1:14:46", "remaining_time": "2 days, 9:55:32"}
+{"current_steps": 76, "total_steps": 3561, "loss": 0.561, "lr": 2.1288515406162466e-06, "epoch": 0.06402246402246402, "percentage": 2.13, "elapsed_time": "1:15:43", "remaining_time": "2 days, 9:52:15"}
+{"current_steps": 77, "total_steps": 3561, "loss": 0.5887, "lr": 2.1568627450980393e-06, "epoch": 0.06486486486486487, "percentage": 2.16, "elapsed_time": "1:16:31", "remaining_time": "2 days, 9:42:39"}
+{"current_steps": 78, "total_steps": 3561, "loss": 0.6228, "lr": 2.184873949579832e-06, "epoch": 0.0657072657072657, "percentage": 2.19, "elapsed_time": "1:17:35", "remaining_time": "2 days, 9:44:52"}
+{"current_steps": 79, "total_steps": 3561, "loss": 0.5736, "lr": 2.2128851540616248e-06, "epoch": 0.06654966654966656, "percentage": 2.22, "elapsed_time": "1:18:41", "remaining_time": "2 days, 9:48:04"}
+{"current_steps": 80, "total_steps": 3561, "loss": 0.6013, "lr": 2.2408963585434175e-06, "epoch": 0.06739206739206739, "percentage": 2.25, "elapsed_time": "1:19:50", "remaining_time": "2 days, 9:53:56"}
+{"current_steps": 81, "total_steps": 3561, "loss": 0.5799, "lr": 2.2689075630252102e-06, "epoch": 0.06823446823446823, "percentage": 2.27, "elapsed_time": "1:20:45", "remaining_time": "2 days, 9:49:57"}
+{"current_steps": 82, "total_steps": 3561, "loss": 0.5911, "lr": 2.296918767507003e-06, "epoch": 0.06907686907686908, "percentage": 2.3, "elapsed_time": "1:21:45", "remaining_time": "2 days, 9:49:04"}
+{"current_steps": 83, "total_steps": 3561, "loss": 0.5693, "lr": 2.3249299719887957e-06, "epoch": 0.06991926991926992, "percentage": 2.33, "elapsed_time": "1:22:42", "remaining_time": "2 days, 9:45:49"}
+{"current_steps": 84, "total_steps": 3561, "loss": 0.5935, "lr": 2.3529411764705885e-06, "epoch": 0.07076167076167077, "percentage": 2.36, "elapsed_time": "1:23:39", "remaining_time": "2 days, 9:42:31"}
+{"current_steps": 85, "total_steps": 3561, "loss": 0.5515, "lr": 2.380952380952381e-06, "epoch": 0.0716040716040716, "percentage": 2.39, "elapsed_time": "1:24:36", "remaining_time": "2 days, 9:40:11"}
+{"current_steps": 86, "total_steps": 3561, "loss": 0.6072, "lr": 2.408963585434174e-06, "epoch": 0.07244647244647244, "percentage": 2.42, "elapsed_time": "1:25:39", "remaining_time": "2 days, 9:41:07"}
+{"current_steps": 87, "total_steps": 3561, "loss": 0.5833, "lr": 2.4369747899159667e-06, "epoch": 0.07328887328887329, "percentage": 2.44, "elapsed_time": "1:26:35", "remaining_time": "2 days, 9:37:50"}
+{"current_steps": 88, "total_steps": 3561, "loss": 0.5944, "lr": 2.4649859943977594e-06, "epoch": 0.07413127413127413, "percentage": 2.47, "elapsed_time": "1:27:36", "remaining_time": "2 days, 9:37:51"}
+{"current_steps": 89, "total_steps": 3561, "loss": 0.5765, "lr": 2.492997198879552e-06, "epoch": 0.07497367497367498, "percentage": 2.5, "elapsed_time": "1:28:38", "remaining_time": "2 days, 9:38:00"}
+{"current_steps": 90, "total_steps": 3561, "loss": 0.6108, "lr": 2.521008403361345e-06, "epoch": 0.07581607581607581, "percentage": 2.53, "elapsed_time": "1:29:38", "remaining_time": "2 days, 9:36:54"}
+{"current_steps": 91, "total_steps": 3561, "loss": 0.5654, "lr": 2.549019607843137e-06, "epoch": 0.07665847665847667, "percentage": 2.56, "elapsed_time": "1:30:34", "remaining_time": "2 days, 9:33:32"}
+{"current_steps": 92, "total_steps": 3561, "loss": 0.577, "lr": 2.57703081232493e-06, "epoch": 0.0775008775008775, "percentage": 2.58, "elapsed_time": "1:31:38", "remaining_time": "2 days, 9:35:45"}
+{"current_steps": 93, "total_steps": 3561, "loss": 0.5706, "lr": 2.605042016806723e-06, "epoch": 0.07834327834327834, "percentage": 2.61, "elapsed_time": "1:32:37", "remaining_time": "2 days, 9:33:53"}
+{"current_steps": 94, "total_steps": 3561, "loss": 0.6118, "lr": 2.633053221288516e-06, "epoch": 0.07918567918567919, "percentage": 2.64, "elapsed_time": "1:33:38", "remaining_time": "2 days, 9:33:53"}
+{"current_steps": 95, "total_steps": 3561, "loss": 0.577, "lr": 2.6610644257703085e-06, "epoch": 0.08002808002808003, "percentage": 2.67, "elapsed_time": "1:34:45", "remaining_time": "2 days, 9:37:25"}
+{"current_steps": 96, "total_steps": 3561, "loss": 0.5666, "lr": 2.689075630252101e-06, "epoch": 0.08087048087048088, "percentage": 2.7, "elapsed_time": "1:35:47", "remaining_time": "2 days, 9:37:11"}
+{"current_steps": 97, "total_steps": 3561, "loss": 0.5958, "lr": 2.7170868347338936e-06, "epoch": 0.08171288171288171, "percentage": 2.72, "elapsed_time": "1:36:35", "remaining_time": "2 days, 9:29:31"}
+{"current_steps": 98, "total_steps": 3561, "loss": 0.5476, "lr": 2.7450980392156867e-06, "epoch": 0.08255528255528255, "percentage": 2.75, "elapsed_time": "1:37:37", "remaining_time": "2 days, 9:29:46"}
+{"current_steps": 99, "total_steps": 3561, "loss": 0.5453, "lr": 2.7731092436974795e-06, "epoch": 0.0833976833976834, "percentage": 2.78, "elapsed_time": "1:38:34", "remaining_time": "2 days, 9:26:52"}
+{"current_steps": 100, "total_steps": 3561, "loss": 0.5826, "lr": 2.8011204481792718e-06, "epoch": 0.08424008424008424, "percentage": 2.81, "elapsed_time": "1:39:26", "remaining_time": "2 days, 9:21:44"}
+{"current_steps": 101, "total_steps": 3561, "loss": 0.5696, "lr": 2.8291316526610645e-06, "epoch": 0.08508248508248509, "percentage": 2.84, "elapsed_time": "1:41:30", "remaining_time": "2 days, 9:57:13"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ead11e894b0f505c2ed1b49a92ccaca15b886cc11c6bb942914f77a2696a3627
+size 7352