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 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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_mrope": 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 sha256:2845b2c2fbb325b07117280312ec89fa391559ff8a49386419fd0c7c249b5d56
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fb7ef9aecc47c86fb8747764a69785bf9d2e49bd26a86cfba51a86011c32fd
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad711b9b85d29072812cca1ea28597ebca80212c277b971608eca668396eae8
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28fda9f1102bb033980b7e4343e01abac9ff22c87b3c69a9bdcbc6d1d30570c8
+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": "<|im_end|>",
+    "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 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 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": "<|im_end|>",
+  "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 +1,100 @@
+{"current_steps": 1, "total_steps": 165, "loss": 0.8651, "lr": 5.882352941176471e-07, "epoch": 0.01809954751131222, "percentage": 0.61, "elapsed_time": "0:04:40", "remaining_time": "12:45:46"}
+{"current_steps": 2, "total_steps": 165, "loss": 0.834, "lr": 1.1764705882352942e-06, "epoch": 0.03619909502262444, "percentage": 1.21, "elapsed_time": "0:09:06", "remaining_time": "12:22:55"}
+{"current_steps": 3, "total_steps": 165, "loss": 0.8286, "lr": 1.7647058823529414e-06, "epoch": 0.05429864253393665, "percentage": 1.82, "elapsed_time": "0:13:34", "remaining_time": "12:12:46"}
+{"current_steps": 4, "total_steps": 165, "loss": 0.8592, "lr": 2.3529411764705885e-06, "epoch": 0.07239819004524888, "percentage": 2.42, "elapsed_time": "0:18:01", "remaining_time": "12:05:39"}
+{"current_steps": 5, "total_steps": 165, "loss": 0.8714, "lr": 2.9411764705882355e-06, "epoch": 0.09049773755656108, "percentage": 3.03, "elapsed_time": "0:22:28", "remaining_time": "11:59:09"}
+{"current_steps": 6, "total_steps": 165, "loss": 0.846, "lr": 3.529411764705883e-06, "epoch": 0.1085972850678733, "percentage": 3.64, "elapsed_time": "0:26:57", "remaining_time": "11:54:33"}
+{"current_steps": 7, "total_steps": 165, "loss": 0.8033, "lr": 4.11764705882353e-06, "epoch": 0.12669683257918551, "percentage": 4.24, "elapsed_time": "0:31:26", "remaining_time": "11:49:46"}
+{"current_steps": 8, "total_steps": 165, "loss": 0.7808, "lr": 4.705882352941177e-06, "epoch": 0.14479638009049775, "percentage": 4.85, "elapsed_time": "0:35:55", "remaining_time": "11:45:09"}
+{"current_steps": 9, "total_steps": 165, "loss": 0.7251, "lr": 5.294117647058824e-06, "epoch": 0.16289592760180996, "percentage": 5.45, "elapsed_time": "0:40:22", "remaining_time": "11:39:55"}
+{"current_steps": 10, "total_steps": 165, "loss": 0.756, "lr": 5.882352941176471e-06, "epoch": 0.18099547511312217, "percentage": 6.06, "elapsed_time": "0:44:49", "remaining_time": "11:34:50"}
+{"current_steps": 11, "total_steps": 165, "loss": 0.7291, "lr": 6.470588235294119e-06, "epoch": 0.19909502262443438, "percentage": 6.67, "elapsed_time": "0:49:16", "remaining_time": "11:29:50"}
+{"current_steps": 12, "total_steps": 165, "loss": 0.7187, "lr": 7.058823529411766e-06, "epoch": 0.2171945701357466, "percentage": 7.27, "elapsed_time": "0:53:44", "remaining_time": "11:25:09"}
+{"current_steps": 13, "total_steps": 165, "loss": 0.7101, "lr": 7.647058823529411e-06, "epoch": 0.23529411764705882, "percentage": 7.88, "elapsed_time": "0:58:11", "remaining_time": "11:20:21"}
+{"current_steps": 14, "total_steps": 165, "loss": 0.693, "lr": 8.23529411764706e-06, "epoch": 0.25339366515837103, "percentage": 8.48, "elapsed_time": "1:02:39", "remaining_time": "11:15:51"}
+{"current_steps": 15, "total_steps": 165, "loss": 0.7142, "lr": 8.823529411764707e-06, "epoch": 0.27149321266968324, "percentage": 9.09, "elapsed_time": "1:07:08", "remaining_time": "11:11:27"}
+{"current_steps": 16, "total_steps": 165, "loss": 0.6941, "lr": 9.411764705882354e-06, "epoch": 0.2895927601809955, "percentage": 9.7, "elapsed_time": "1:11:38", "remaining_time": "11:07:12"}
+{"current_steps": 17, "total_steps": 165, "loss": 0.6946, "lr": 1e-05, "epoch": 0.3076923076923077, "percentage": 10.3, "elapsed_time": "1:16:04", "remaining_time": "11:02:21"}
+{"current_steps": 18, "total_steps": 165, "loss": 0.6559, "lr": 9.998873580873848e-06, "epoch": 0.3257918552036199, "percentage": 10.91, "elapsed_time": "1:20:32", "remaining_time": "10:57:45"}
+{"current_steps": 19, "total_steps": 165, "loss": 0.6293, "lr": 9.99549483102341e-06, "epoch": 0.3438914027149321, "percentage": 11.52, "elapsed_time": "1:25:00", "remaining_time": "10:53:10"}
+{"current_steps": 20, "total_steps": 165, "loss": 0.6363, "lr": 9.989865272804064e-06, "epoch": 0.36199095022624433, "percentage": 12.12, "elapsed_time": "1:29:31", "remaining_time": "10:49:02"}
+{"current_steps": 21, "total_steps": 165, "loss": 0.619, "lr": 9.981987442712634e-06, "epoch": 0.38009049773755654, "percentage": 12.73, "elapsed_time": "1:34:00", "remaining_time": "10:44:38"}
+{"current_steps": 22, "total_steps": 165, "loss": 0.6137, "lr": 9.971864890244514e-06, "epoch": 0.39819004524886875, "percentage": 13.33, "elapsed_time": "1:38:29", "remaining_time": "10:40:11"}
+{"current_steps": 23, "total_steps": 165, "loss": 0.6142, "lr": 9.959502176294384e-06, "epoch": 0.416289592760181, "percentage": 13.94, "elapsed_time": "1:42:57", "remaining_time": "10:35:40"}
+{"current_steps": 24, "total_steps": 165, "loss": 0.618, "lr": 9.944904871101227e-06, "epoch": 0.4343891402714932, "percentage": 14.55, "elapsed_time": "1:47:23", "remaining_time": "10:30:58"}
+{"current_steps": 25, "total_steps": 165, "loss": 0.6177, "lr": 9.928079551738542e-06, "epoch": 0.45248868778280543, "percentage": 15.15, "elapsed_time": "1:51:51", "remaining_time": "10:26:22"}
+{"current_steps": 26, "total_steps": 165, "loss": 0.6323, "lr": 9.909033799150947e-06, "epoch": 0.47058823529411764, "percentage": 15.76, "elapsed_time": "1:56:20", "remaining_time": "10:21:57"}
+{"current_steps": 27, "total_steps": 165, "loss": 0.5826, "lr": 9.887776194738433e-06, "epoch": 0.48868778280542985, "percentage": 16.36, "elapsed_time": "2:00:49", "remaining_time": "10:17:30"}
+{"current_steps": 28, "total_steps": 165, "loss": 0.578, "lr": 9.864316316489873e-06, "epoch": 0.5067873303167421, "percentage": 16.97, "elapsed_time": "2:05:19", "remaining_time": "10:13:13"}
+{"current_steps": 29, "total_steps": 165, "loss": 0.6192, "lr": 9.838664734667496e-06, "epoch": 0.5248868778280543, "percentage": 17.58, "elapsed_time": "2:09:50", "remaining_time": "10:08:56"}
+{"current_steps": 30, "total_steps": 165, "loss": 0.5858, "lr": 9.810833007044247e-06, "epoch": 0.5429864253393665, "percentage": 18.18, "elapsed_time": "2:14:19", "remaining_time": "10:04:29"}
+{"current_steps": 31, "total_steps": 165, "loss": 0.5912, "lr": 9.780833673696255e-06, "epoch": 0.5610859728506787, "percentage": 18.79, "elapsed_time": "2:18:48", "remaining_time": "10:00:01"}
+{"current_steps": 32, "total_steps": 165, "loss": 0.601, "lr": 9.74868025135266e-06, "epoch": 0.579185520361991, "percentage": 19.39, "elapsed_time": "2:23:16", "remaining_time": "9:55:28"}
+{"current_steps": 33, "total_steps": 165, "loss": 0.5716, "lr": 9.714387227305422e-06, "epoch": 0.5972850678733032, "percentage": 20.0, "elapsed_time": "2:27:43", "remaining_time": "9:50:55"}
+{"current_steps": 34, "total_steps": 165, "loss": 0.6004, "lr": 9.677970052881811e-06, "epoch": 0.6153846153846154, "percentage": 20.61, "elapsed_time": "2:32:13", "remaining_time": "9:46:29"}
+{"current_steps": 35, "total_steps": 165, "loss": 0.5771, "lr": 9.639445136482549e-06, "epoch": 0.6334841628959276, "percentage": 21.21, "elapsed_time": "2:36:44", "remaining_time": "9:42:09"}
+{"current_steps": 36, "total_steps": 165, "loss": 0.5837, "lr": 9.598829836188694e-06, "epoch": 0.6515837104072398, "percentage": 21.82, "elapsed_time": "2:41:13", "remaining_time": "9:37:43"}
+{"current_steps": 37, "total_steps": 165, "loss": 0.5963, "lr": 9.55614245194068e-06, "epoch": 0.669683257918552, "percentage": 22.42, "elapsed_time": "2:45:42", "remaining_time": "9:33:14"}
+{"current_steps": 38, "total_steps": 165, "loss": 0.5633, "lr": 9.511402217292927e-06, "epoch": 0.6877828054298643, "percentage": 23.03, "elapsed_time": "2:50:09", "remaining_time": "9:28:40"}
+{"current_steps": 39, "total_steps": 165, "loss": 0.5607, "lr": 9.464629290747844e-06, "epoch": 0.7058823529411765, "percentage": 23.64, "elapsed_time": "2:54:37", "remaining_time": "9:24:09"}
+{"current_steps": 40, "total_steps": 165, "loss": 0.5778, "lr": 9.415844746673047e-06, "epoch": 0.7239819004524887, "percentage": 24.24, "elapsed_time": "2:59:05", "remaining_time": "9:19:39"}
+{"current_steps": 41, "total_steps": 165, "loss": 0.5649, "lr": 9.365070565805941e-06, "epoch": 0.7420814479638009, "percentage": 24.85, "elapsed_time": "3:03:33", "remaining_time": "9:15:08"}
+{"current_steps": 42, "total_steps": 165, "loss": 0.5701, "lr": 9.312329625349903e-06, "epoch": 0.7601809954751131, "percentage": 25.45, "elapsed_time": "3:08:01", "remaining_time": "9:10:38"}
+{"current_steps": 43, "total_steps": 165, "loss": 0.5641, "lr": 9.257645688666557e-06, "epoch": 0.7782805429864253, "percentage": 26.06, "elapsed_time": "3:12:29", "remaining_time": "9:06:08"}
+{"current_steps": 44, "total_steps": 165, "loss": 0.5511, "lr": 9.201043394568773e-06, "epoch": 0.7963800904977375, "percentage": 26.67, "elapsed_time": "3:16:57", "remaining_time": "9:01:37"}
+{"current_steps": 45, "total_steps": 165, "loss": 0.5626, "lr": 9.142548246219212e-06, "epoch": 0.8144796380090498, "percentage": 27.27, "elapsed_time": "3:21:24", "remaining_time": "8:57:05"}
+{"current_steps": 46, "total_steps": 165, "loss": 0.5659, "lr": 9.082186599639429e-06, "epoch": 0.832579185520362, "percentage": 27.88, "elapsed_time": "3:25:52", "remaining_time": "8:52:34"}
+{"current_steps": 47, "total_steps": 165, "loss": 0.572, "lr": 9.019985651834703e-06, "epoch": 0.8506787330316742, "percentage": 28.48, "elapsed_time": "3:30:21", "remaining_time": "8:48:08"}
+{"current_steps": 48, "total_steps": 165, "loss": 0.5755, "lr": 8.955973428539943e-06, "epoch": 0.8687782805429864, "percentage": 29.09, "elapsed_time": "3:34:50", "remaining_time": "8:43:40"}
+{"current_steps": 49, "total_steps": 165, "loss": 0.578, "lr": 8.890178771592198e-06, "epoch": 0.8868778280542986, "percentage": 29.7, "elapsed_time": "3:39:18", "remaining_time": "8:39:11"}
+{"current_steps": 50, "total_steps": 165, "loss": 0.5742, "lr": 8.822631325935463e-06, "epoch": 0.9049773755656109, "percentage": 30.3, "elapsed_time": "3:43:47", "remaining_time": "8:34:44"}
+{"current_steps": 51, "total_steps": 165, "loss": 0.5581, "lr": 8.753361526263622e-06, "epoch": 0.9230769230769231, "percentage": 30.91, "elapsed_time": "3:48:15", "remaining_time": "8:30:13"}
+{"current_steps": 52, "total_steps": 165, "loss": 0.5684, "lr": 8.682400583307562e-06, "epoch": 0.9411764705882353, "percentage": 31.52, "elapsed_time": "3:52:43", "remaining_time": "8:25:43"}
+{"current_steps": 53, "total_steps": 165, "loss": 0.556, "lr": 8.609780469772623e-06, "epoch": 0.9592760180995475, "percentage": 32.12, "elapsed_time": "3:57:09", "remaining_time": "8:21:10"}
+{"current_steps": 54, "total_steps": 165, "loss": 0.5514, "lr": 8.535533905932739e-06, "epoch": 0.9773755656108597, "percentage": 32.73, "elapsed_time": "4:01:35", "remaining_time": "8:16:36"}
+{"current_steps": 55, "total_steps": 165, "loss": 0.5925, "lr": 8.459694344887732e-06, "epoch": 0.995475113122172, "percentage": 33.33, "elapsed_time": "4:06:02", "remaining_time": "8:12:05"}
+{"current_steps": 56, "total_steps": 165, "loss": 0.9574, "lr": 8.382295957490435e-06, "epoch": 1.0135746606334841, "percentage": 33.94, "elapsed_time": "4:10:59", "remaining_time": "8:08:33"}
+{"current_steps": 57, "total_steps": 165, "loss": 0.5356, "lr": 8.303373616950408e-06, "epoch": 1.0316742081447963, "percentage": 34.55, "elapsed_time": "4:15:28", "remaining_time": "8:04:03"}
+{"current_steps": 58, "total_steps": 165, "loss": 0.5521, "lr": 8.222962883121196e-06, "epoch": 1.0497737556561086, "percentage": 35.15, "elapsed_time": "4:19:57", "remaining_time": "7:59:34"}
+{"current_steps": 59, "total_steps": 165, "loss": 0.5362, "lr": 8.141099986478212e-06, "epoch": 1.0678733031674208, "percentage": 35.76, "elapsed_time": "4:24:24", "remaining_time": "7:55:01"}
+{"current_steps": 60, "total_steps": 165, "loss": 0.541, "lr": 8.057821811794457e-06, "epoch": 1.085972850678733, "percentage": 36.36, "elapsed_time": "4:28:52", "remaining_time": "7:50:31"}
+{"current_steps": 61, "total_steps": 165, "loss": 0.5467, "lr": 7.973165881521435e-06, "epoch": 1.1040723981900453, "percentage": 36.97, "elapsed_time": "4:33:21", "remaining_time": "7:46:03"}
+{"current_steps": 62, "total_steps": 165, "loss": 0.5462, "lr": 7.887170338882742e-06, "epoch": 1.1221719457013575, "percentage": 37.58, "elapsed_time": "4:37:51", "remaining_time": "7:41:36"}
+{"current_steps": 63, "total_steps": 165, "loss": 0.5171, "lr": 7.799873930687979e-06, "epoch": 1.1402714932126696, "percentage": 38.18, "elapsed_time": "4:42:19", "remaining_time": "7:37:05"}
+{"current_steps": 64, "total_steps": 165, "loss": 0.507, "lr": 7.711315989874677e-06, "epoch": 1.1583710407239818, "percentage": 38.79, "elapsed_time": "4:46:46", "remaining_time": "7:32:33"}
+{"current_steps": 65, "total_steps": 165, "loss": 0.5174, "lr": 7.621536417786159e-06, "epoch": 1.1764705882352942, "percentage": 39.39, "elapsed_time": "4:51:14", "remaining_time": "7:28:03"}
+{"current_steps": 66, "total_steps": 165, "loss": 0.5317, "lr": 7.530575666193283e-06, "epoch": 1.1945701357466063, "percentage": 40.0, "elapsed_time": "4:55:42", "remaining_time": "7:23:34"}
+{"current_steps": 67, "total_steps": 165, "loss": 0.5274, "lr": 7.438474719068174e-06, "epoch": 1.2126696832579185, "percentage": 40.61, "elapsed_time": "5:00:09", "remaining_time": "7:19:01"}
+{"current_steps": 68, "total_steps": 165, "loss": 0.5135, "lr": 7.3452750741181855e-06, "epoch": 1.2307692307692308, "percentage": 41.21, "elapsed_time": "5:04:36", "remaining_time": "7:14:31"}
+{"current_steps": 69, "total_steps": 165, "loss": 0.5204, "lr": 7.251018724088367e-06, "epoch": 1.248868778280543, "percentage": 41.82, "elapsed_time": "5:09:05", "remaining_time": "7:10:02"}
+{"current_steps": 70, "total_steps": 165, "loss": 0.5479, "lr": 7.155748137840892e-06, "epoch": 1.2669683257918551, "percentage": 42.42, "elapsed_time": "5:13:32", "remaining_time": "7:05:30"}
+{"current_steps": 71, "total_steps": 165, "loss": 0.5434, "lr": 7.059506241219964e-06, "epoch": 1.2850678733031673, "percentage": 43.03, "elapsed_time": "5:18:00", "remaining_time": "7:01:01"}
+{"current_steps": 72, "total_steps": 165, "loss": 0.5253, "lr": 6.962336397710819e-06, "epoch": 1.3031674208144797, "percentage": 43.64, "elapsed_time": "5:22:26", "remaining_time": "6:56:29"}
+{"current_steps": 73, "total_steps": 165, "loss": 0.5076, "lr": 6.864282388901544e-06, "epoch": 1.3212669683257918, "percentage": 44.24, "elapsed_time": "5:26:54", "remaining_time": "6:51:59"}
+{"current_steps": 74, "total_steps": 165, "loss": 0.5365, "lr": 6.765388394756504e-06, "epoch": 1.3393665158371042, "percentage": 44.85, "elapsed_time": "5:31:21", "remaining_time": "6:47:28"}
+{"current_steps": 75, "total_steps": 165, "loss": 0.5393, "lr": 6.665698973710289e-06, "epoch": 1.3574660633484164, "percentage": 45.45, "elapsed_time": "5:35:47", "remaining_time": "6:42:57"}
+{"current_steps": 76, "total_steps": 165, "loss": 0.517, "lr": 6.565259042591112e-06, "epoch": 1.3755656108597285, "percentage": 46.06, "elapsed_time": "5:40:15", "remaining_time": "6:38:28"}
+{"current_steps": 77, "total_steps": 165, "loss": 0.5218, "lr": 6.464113856382752e-06, "epoch": 1.3936651583710407, "percentage": 46.67, "elapsed_time": "5:44:46", "remaining_time": "6:34:01"}
+{"current_steps": 78, "total_steps": 165, "loss": 0.5281, "lr": 6.3623089878341146e-06, "epoch": 1.4117647058823528, "percentage": 47.27, "elapsed_time": "5:49:17", "remaining_time": "6:29:35"}
+{"current_steps": 79, "total_steps": 165, "loss": 0.5494, "lr": 6.259890306925627e-06, "epoch": 1.4298642533936652, "percentage": 47.88, "elapsed_time": "5:53:46", "remaining_time": "6:25:07"}
+{"current_steps": 80, "total_steps": 165, "loss": 0.5215, "lr": 6.156903960201709e-06, "epoch": 1.4479638009049773, "percentage": 48.48, "elapsed_time": "5:58:15", "remaining_time": "6:20:38"}
+{"current_steps": 81, "total_steps": 165, "loss": 0.5124, "lr": 6.053396349978632e-06, "epoch": 1.4660633484162897, "percentage": 49.09, "elapsed_time": "6:02:43", "remaining_time": "6:16:09"}
+{"current_steps": 82, "total_steps": 165, "loss": 0.5297, "lr": 5.949414113437142e-06, "epoch": 1.4841628959276019, "percentage": 49.7, "elapsed_time": "6:07:12", "remaining_time": "6:11:41"}
+{"current_steps": 83, "total_steps": 165, "loss": 0.5395, "lr": 5.8450041016092465e-06, "epoch": 1.502262443438914, "percentage": 50.3, "elapsed_time": "6:11:41", "remaining_time": "6:07:12"}
+{"current_steps": 84, "total_steps": 165, "loss": 0.5247, "lr": 5.740213358268658e-06, "epoch": 1.5203619909502262, "percentage": 50.91, "elapsed_time": "6:16:10", "remaining_time": "6:02:44"}
+{"current_steps": 85, "total_steps": 165, "loss": 0.5121, "lr": 5.635089098734394e-06, "epoch": 1.5384615384615383, "percentage": 51.52, "elapsed_time": "6:20:39", "remaining_time": "5:58:16"}
+{"current_steps": 86, "total_steps": 165, "loss": 0.5301, "lr": 5.529678688597081e-06, "epoch": 1.5565610859728507, "percentage": 52.12, "elapsed_time": "6:25:09", "remaining_time": "5:53:48"}
+{"current_steps": 87, "total_steps": 165, "loss": 0.5297, "lr": 5.4240296223775465e-06, "epoch": 1.5746606334841629, "percentage": 52.73, "elapsed_time": "6:29:38", "remaining_time": "5:49:20"}
+{"current_steps": 88, "total_steps": 165, "loss": 0.5346, "lr": 5.318189502127332e-06, "epoch": 1.5927601809954752, "percentage": 53.33, "elapsed_time": "6:34:07", "remaining_time": "5:44:51"}
+{"current_steps": 89, "total_steps": 165, "loss": 0.5442, "lr": 5.212206015980742e-06, "epoch": 1.6108597285067874, "percentage": 53.94, "elapsed_time": "6:38:35", "remaining_time": "5:40:21"}
+{"current_steps": 90, "total_steps": 165, "loss": 0.5139, "lr": 5.106126916668118e-06, "epoch": 1.6289592760180995, "percentage": 54.55, "elapsed_time": "6:43:02", "remaining_time": "5:35:52"}
+{"current_steps": 91, "total_steps": 165, "loss": 0.537, "lr": 5e-06, "epoch": 1.6470588235294117, "percentage": 55.15, "elapsed_time": "6:47:30", "remaining_time": "5:31:23"}
+{"current_steps": 92, "total_steps": 165, "loss": 0.5255, "lr": 4.8938730833318825e-06, "epoch": 1.6651583710407238, "percentage": 55.76, "elapsed_time": "6:52:00", "remaining_time": "5:26:54"}
+{"current_steps": 93, "total_steps": 165, "loss": 0.5312, "lr": 4.78779398401926e-06, "epoch": 1.6832579185520362, "percentage": 56.36, "elapsed_time": "6:56:28", "remaining_time": "5:22:25"}
+{"current_steps": 94, "total_steps": 165, "loss": 0.5404, "lr": 4.6818104978726685e-06, "epoch": 1.7013574660633484, "percentage": 56.97, "elapsed_time": "7:00:56", "remaining_time": "5:17:57"}
+{"current_steps": 95, "total_steps": 165, "loss": 0.5308, "lr": 4.575970377622456e-06, "epoch": 1.7194570135746607, "percentage": 57.58, "elapsed_time": "7:05:25", "remaining_time": "5:13:28"}
+{"current_steps": 96, "total_steps": 165, "loss": 0.5129, "lr": 4.47032131140292e-06, "epoch": 1.737556561085973, "percentage": 58.18, "elapsed_time": "7:09:56", "remaining_time": "5:09:00"}
+{"current_steps": 97, "total_steps": 165, "loss": 0.5324, "lr": 4.364910901265607e-06, "epoch": 1.755656108597285, "percentage": 58.79, "elapsed_time": "7:14:25", "remaining_time": "5:04:32"}
+{"current_steps": 98, "total_steps": 165, "loss": 0.5204, "lr": 4.259786641731344e-06, "epoch": 1.7737556561085972, "percentage": 59.39, "elapsed_time": "7:18:56", "remaining_time": "5:00:05"}
+{"current_steps": 99, "total_steps": 165, "loss": 0.5207, "lr": 4.154995898390756e-06, "epoch": 1.7918552036199094, "percentage": 60.0, "elapsed_time": "7:23:26", "remaining_time": "4:55:37"}
+{"current_steps": 100, "total_steps": 165, "loss": 0.5401, "lr": 4.050585886562858e-06, "epoch": 1.8099547511312217, "percentage": 60.61, "elapsed_time": "7:27:55", "remaining_time": "4:51:08"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8f17415010a72b6c9d9e9ac448ad826fad34b8afbc5ae32b9f04e9faab963a
+size 7160