Training in progress, step 87

.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 +1,34 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-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": {
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "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 sha256:0d905acee7d7079c5bfd6b141429cc536634804d268def6ad0158ca79855635b
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc5e1db452eb70a5c22c0333ec2317ff556f75db0aeb9f944fb1a7f1b0b38da
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af03c084b1ba0639cc3d63f706cf9f7d5f364e863e64aa8dbda2758499d533c
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810098e41fb0827de7bb557c377e573fecbe1cc7de3711bd78c5abfe039f277d
+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 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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 16384,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,88 @@
+{"current_steps": 1, "total_steps": 87, "loss": 0.435, "lr": 1.111111111111111e-06, "epoch": 0.034482758620689655, "percentage": 1.15, "elapsed_time": "0:00:54", "remaining_time": "1:18:00"}
+{"current_steps": 2, "total_steps": 87, "loss": 0.3556, "lr": 2.222222222222222e-06, "epoch": 0.06896551724137931, "percentage": 2.3, "elapsed_time": "0:01:47", "remaining_time": "1:16:19"}
+{"current_steps": 3, "total_steps": 87, "loss": 0.3895, "lr": 3.3333333333333333e-06, "epoch": 0.10344827586206896, "percentage": 3.45, "elapsed_time": "0:02:50", "remaining_time": "1:19:20"}
+{"current_steps": 4, "total_steps": 87, "loss": 0.3798, "lr": 4.444444444444444e-06, "epoch": 0.13793103448275862, "percentage": 4.6, "elapsed_time": "0:03:44", "remaining_time": "1:17:47"}
+{"current_steps": 5, "total_steps": 87, "loss": 0.3282, "lr": 5.555555555555557e-06, "epoch": 0.1724137931034483, "percentage": 5.75, "elapsed_time": "0:04:45", "remaining_time": "1:18:06"}
+{"current_steps": 6, "total_steps": 87, "loss": 0.2932, "lr": 6.666666666666667e-06, "epoch": 0.20689655172413793, "percentage": 6.9, "elapsed_time": "0:05:54", "remaining_time": "1:19:39"}
+{"current_steps": 7, "total_steps": 87, "loss": 0.3141, "lr": 7.77777777777778e-06, "epoch": 0.2413793103448276, "percentage": 8.05, "elapsed_time": "0:06:56", "remaining_time": "1:19:21"}
+{"current_steps": 8, "total_steps": 87, "loss": 0.2514, "lr": 8.888888888888888e-06, "epoch": 0.27586206896551724, "percentage": 9.2, "elapsed_time": "0:07:44", "remaining_time": "1:16:31"}
+{"current_steps": 9, "total_steps": 87, "loss": 0.2285, "lr": 1e-05, "epoch": 0.3103448275862069, "percentage": 10.34, "elapsed_time": "0:08:44", "remaining_time": "1:15:41"}
+{"current_steps": 10, "total_steps": 87, "loss": 0.3054, "lr": 9.995944990857848e-06, "epoch": 0.3448275862068966, "percentage": 11.49, "elapsed_time": "0:09:38", "remaining_time": "1:14:16"}
+{"current_steps": 11, "total_steps": 87, "loss": 0.2962, "lr": 9.983786540671052e-06, "epoch": 0.3793103448275862, "percentage": 12.64, "elapsed_time": "0:10:49", "remaining_time": "1:14:50"}
+{"current_steps": 12, "total_steps": 87, "loss": 0.2805, "lr": 9.96354437049027e-06, "epoch": 0.41379310344827586, "percentage": 13.79, "elapsed_time": "0:11:33", "remaining_time": "1:12:14"}
+{"current_steps": 13, "total_steps": 87, "loss": 0.2664, "lr": 9.935251313189564e-06, "epoch": 0.4482758620689655, "percentage": 14.94, "elapsed_time": "0:12:22", "remaining_time": "1:10:24"}
+{"current_steps": 14, "total_steps": 87, "loss": 0.2748, "lr": 9.89895326021134e-06, "epoch": 0.4827586206896552, "percentage": 16.09, "elapsed_time": "0:13:16", "remaining_time": "1:09:12"}
+{"current_steps": 15, "total_steps": 87, "loss": 0.1965, "lr": 9.854709087130261e-06, "epoch": 0.5172413793103449, "percentage": 17.24, "elapsed_time": "0:14:16", "remaining_time": "1:08:31"}
+{"current_steps": 16, "total_steps": 87, "loss": 0.2413, "lr": 9.802590558156863e-06, "epoch": 0.5517241379310345, "percentage": 18.39, "elapsed_time": "0:15:14", "remaining_time": "1:07:36"}
+{"current_steps": 17, "total_steps": 87, "loss": 0.216, "lr": 9.742682209735727e-06, "epoch": 0.5862068965517241, "percentage": 19.54, "elapsed_time": "0:16:18", "remaining_time": "1:07:09"}
+{"current_steps": 18, "total_steps": 87, "loss": 0.2056, "lr": 9.675081213427076e-06, "epoch": 0.6206896551724138, "percentage": 20.69, "elapsed_time": "0:17:15", "remaining_time": "1:06:10"}
+{"current_steps": 19, "total_steps": 87, "loss": 0.2318, "lr": 9.599897218294122e-06, "epoch": 0.6551724137931034, "percentage": 21.84, "elapsed_time": "0:18:04", "remaining_time": "1:04:40"}
+{"current_steps": 20, "total_steps": 87, "loss": 0.2306, "lr": 9.517252173051912e-06, "epoch": 0.6896551724137931, "percentage": 22.99, "elapsed_time": "0:18:51", "remaining_time": "1:03:11"}
+{"current_steps": 21, "total_steps": 87, "loss": 0.1925, "lr": 9.427280128266049e-06, "epoch": 0.7241379310344828, "percentage": 24.14, "elapsed_time": "0:19:42", "remaining_time": "1:01:57"}
+{"current_steps": 22, "total_steps": 87, "loss": 0.2035, "lr": 9.330127018922195e-06, "epoch": 0.7586206896551724, "percentage": 25.29, "elapsed_time": "0:20:40", "remaining_time": "1:01:05"}
+{"current_steps": 23, "total_steps": 87, "loss": 0.2447, "lr": 9.225950427718974e-06, "epoch": 0.7931034482758621, "percentage": 26.44, "elapsed_time": "0:21:36", "remaining_time": "1:00:07"}
+{"current_steps": 24, "total_steps": 87, "loss": 0.1961, "lr": 9.114919329468283e-06, "epoch": 0.8275862068965517, "percentage": 27.59, "elapsed_time": "0:22:33", "remaining_time": "0:59:13"}
+{"current_steps": 25, "total_steps": 87, "loss": 0.2143, "lr": 8.997213817017508e-06, "epoch": 0.8620689655172413, "percentage": 28.74, "elapsed_time": "0:23:36", "remaining_time": "0:58:32"}
+{"current_steps": 26, "total_steps": 87, "loss": 0.2177, "lr": 8.873024809138272e-06, "epoch": 0.896551724137931, "percentage": 29.89, "elapsed_time": "0:24:24", "remaining_time": "0:57:14"}
+{"current_steps": 27, "total_steps": 87, "loss": 0.2078, "lr": 8.742553740855507e-06, "epoch": 0.9310344827586207, "percentage": 31.03, "elapsed_time": "0:25:14", "remaining_time": "0:56:06"}
+{"current_steps": 28, "total_steps": 87, "loss": 0.2053, "lr": 8.606012236719073e-06, "epoch": 0.9655172413793104, "percentage": 32.18, "elapsed_time": "0:26:13", "remaining_time": "0:55:16"}
+{"current_steps": 29, "total_steps": 87, "loss": 0.2078, "lr": 8.463621767547998e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:27:06", "remaining_time": "0:54:13"}
+{"current_steps": 30, "total_steps": 87, "loss": 0.1503, "lr": 8.315613291203977e-06, "epoch": 1.0344827586206897, "percentage": 34.48, "elapsed_time": "0:28:00", "remaining_time": "0:53:13"}
+{"current_steps": 31, "total_steps": 87, "loss": 0.1624, "lr": 8.162226877976886e-06, "epoch": 1.0689655172413792, "percentage": 35.63, "elapsed_time": "0:28:57", "remaining_time": "0:52:18"}
+{"current_steps": 32, "total_steps": 87, "loss": 0.1525, "lr": 8.003711321189895e-06, "epoch": 1.103448275862069, "percentage": 36.78, "elapsed_time": "0:29:57", "remaining_time": "0:51:29"}
+{"current_steps": 33, "total_steps": 87, "loss": 0.1743, "lr": 7.84032373365578e-06, "epoch": 1.1379310344827587, "percentage": 37.93, "elapsed_time": "0:30:57", "remaining_time": "0:50:39"}
+{"current_steps": 34, "total_steps": 87, "loss": 0.1839, "lr": 7.672329130639007e-06, "epoch": 1.1724137931034484, "percentage": 39.08, "elapsed_time": "0:31:40", "remaining_time": "0:49:22"}
+{"current_steps": 35, "total_steps": 87, "loss": 0.1691, "lr": 7.500000000000001e-06, "epoch": 1.206896551724138, "percentage": 40.23, "elapsed_time": "0:32:36", "remaining_time": "0:48:26"}
+{"current_steps": 36, "total_steps": 87, "loss": 0.1535, "lr": 7.323615860218844e-06, "epoch": 1.2413793103448276, "percentage": 41.38, "elapsed_time": "0:33:23", "remaining_time": "0:47:18"}
+{"current_steps": 37, "total_steps": 87, "loss": 0.1556, "lr": 7.143462807015271e-06, "epoch": 1.2758620689655173, "percentage": 42.53, "elapsed_time": "0:34:17", "remaining_time": "0:46:19"}
+{"current_steps": 38, "total_steps": 87, "loss": 0.1635, "lr": 6.959833049300376e-06, "epoch": 1.3103448275862069, "percentage": 43.68, "elapsed_time": "0:35:08", "remaining_time": "0:45:18"}
+{"current_steps": 39, "total_steps": 87, "loss": 0.1629, "lr": 6.773024435212678e-06, "epoch": 1.3448275862068966, "percentage": 44.83, "elapsed_time": "0:36:01", "remaining_time": "0:44:20"}
+{"current_steps": 40, "total_steps": 87, "loss": 0.1548, "lr": 6.583339969007364e-06, "epoch": 1.3793103448275863, "percentage": 45.98, "elapsed_time": "0:36:51", "remaining_time": "0:43:18"}
+{"current_steps": 41, "total_steps": 87, "loss": 0.1492, "lr": 6.391087319582264e-06, "epoch": 1.4137931034482758, "percentage": 47.13, "elapsed_time": "0:37:54", "remaining_time": "0:42:31"}
+{"current_steps": 42, "total_steps": 87, "loss": 0.1678, "lr": 6.1965783214377895e-06, "epoch": 1.4482758620689655, "percentage": 48.28, "elapsed_time": "0:38:50", "remaining_time": "0:41:36"}
+{"current_steps": 43, "total_steps": 87, "loss": 0.1352, "lr": 6.000128468880223e-06, "epoch": 1.4827586206896552, "percentage": 49.43, "elapsed_time": "0:39:39", "remaining_time": "0:40:35"}
+{"current_steps": 44, "total_steps": 87, "loss": 0.1535, "lr": 5.8020564042888015e-06, "epoch": 1.5172413793103448, "percentage": 50.57, "elapsed_time": "0:40:27", "remaining_time": "0:39:32"}
+{"current_steps": 45, "total_steps": 87, "loss": 0.1389, "lr": 5.6026834012766155e-06, "epoch": 1.5517241379310345, "percentage": 51.72, "elapsed_time": "0:41:23", "remaining_time": "0:38:38"}
+{"current_steps": 46, "total_steps": 87, "loss": 0.1418, "lr": 5.402332843583631e-06, "epoch": 1.5862068965517242, "percentage": 52.87, "elapsed_time": "0:42:22", "remaining_time": "0:37:46"}
+{"current_steps": 47, "total_steps": 87, "loss": 0.1318, "lr": 5.201329700547077e-06, "epoch": 1.6206896551724137, "percentage": 54.02, "elapsed_time": "0:43:17", "remaining_time": "0:36:50"}
+{"current_steps": 48, "total_steps": 87, "loss": 0.139, "lr": 5e-06, "epoch": 1.6551724137931034, "percentage": 55.17, "elapsed_time": "0:44:33", "remaining_time": "0:36:12"}
+{"current_steps": 49, "total_steps": 87, "loss": 0.132, "lr": 4.798670299452926e-06, "epoch": 1.6896551724137931, "percentage": 56.32, "elapsed_time": "0:45:21", "remaining_time": "0:35:10"}
+{"current_steps": 50, "total_steps": 87, "loss": 0.1459, "lr": 4.597667156416371e-06, "epoch": 1.7241379310344827, "percentage": 57.47, "elapsed_time": "0:46:19", "remaining_time": "0:34:16"}
+{"current_steps": 51, "total_steps": 87, "loss": 0.1898, "lr": 4.397316598723385e-06, "epoch": 1.7586206896551724, "percentage": 58.62, "elapsed_time": "0:47:04", "remaining_time": "0:33:13"}
+{"current_steps": 52, "total_steps": 87, "loss": 0.1519, "lr": 4.1979435957111984e-06, "epoch": 1.793103448275862, "percentage": 59.77, "elapsed_time": "0:48:10", "remaining_time": "0:32:25"}
+{"current_steps": 53, "total_steps": 87, "loss": 0.1563, "lr": 3.999871531119779e-06, "epoch": 1.8275862068965516, "percentage": 60.92, "elapsed_time": "0:49:19", "remaining_time": "0:31:38"}
+{"current_steps": 54, "total_steps": 87, "loss": 0.1538, "lr": 3.803421678562213e-06, "epoch": 1.8620689655172413, "percentage": 62.07, "elapsed_time": "0:50:10", "remaining_time": "0:30:39"}
+{"current_steps": 55, "total_steps": 87, "loss": 0.1312, "lr": 3.6089126804177373e-06, "epoch": 1.896551724137931, "percentage": 63.22, "elapsed_time": "0:51:06", "remaining_time": "0:29:43"}
+{"current_steps": 56, "total_steps": 87, "loss": 0.1248, "lr": 3.416660030992639e-06, "epoch": 1.9310344827586206, "percentage": 64.37, "elapsed_time": "0:52:12", "remaining_time": "0:28:54"}
+{"current_steps": 57, "total_steps": 87, "loss": 0.1217, "lr": 3.226975564787322e-06, "epoch": 1.9655172413793105, "percentage": 65.52, "elapsed_time": "0:53:07", "remaining_time": "0:27:57"}
+{"current_steps": 58, "total_steps": 87, "loss": 0.1601, "lr": 3.040166950699626e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:54:08", "remaining_time": "0:27:04"}
+{"current_steps": 59, "total_steps": 87, "loss": 0.1127, "lr": 2.8565371929847286e-06, "epoch": 2.0344827586206895, "percentage": 67.82, "elapsed_time": "0:55:08", "remaining_time": "0:26:10"}
+{"current_steps": 60, "total_steps": 87, "loss": 0.1301, "lr": 2.6763841397811576e-06, "epoch": 2.0689655172413794, "percentage": 68.97, "elapsed_time": "0:55:58", "remaining_time": "0:25:11"}
+{"current_steps": 61, "total_steps": 87, "loss": 0.1243, "lr": 2.5000000000000015e-06, "epoch": 2.103448275862069, "percentage": 70.11, "elapsed_time": "0:56:46", "remaining_time": "0:24:11"}
+{"current_steps": 62, "total_steps": 87, "loss": 0.1144, "lr": 2.3276708693609947e-06, "epoch": 2.1379310344827585, "percentage": 71.26, "elapsed_time": "0:57:33", "remaining_time": "0:23:12"}
+{"current_steps": 63, "total_steps": 87, "loss": 0.1063, "lr": 2.159676266344222e-06, "epoch": 2.1724137931034484, "percentage": 72.41, "elapsed_time": "0:58:38", "remaining_time": "0:22:20"}
+{"current_steps": 64, "total_steps": 87, "loss": 0.1259, "lr": 1.996288678810105e-06, "epoch": 2.206896551724138, "percentage": 73.56, "elapsed_time": "0:59:46", "remaining_time": "0:21:29"}
+{"current_steps": 65, "total_steps": 87, "loss": 0.1019, "lr": 1.8377731220231144e-06, "epoch": 2.2413793103448274, "percentage": 74.71, "elapsed_time": "1:00:43", "remaining_time": "0:20:33"}
+{"current_steps": 66, "total_steps": 87, "loss": 0.1049, "lr": 1.6843867087960252e-06, "epoch": 2.2758620689655173, "percentage": 75.86, "elapsed_time": "1:01:41", "remaining_time": "0:19:37"}
+{"current_steps": 67, "total_steps": 87, "loss": 0.1106, "lr": 1.5363782324520033e-06, "epoch": 2.310344827586207, "percentage": 77.01, "elapsed_time": "1:02:39", "remaining_time": "0:18:42"}
+{"current_steps": 68, "total_steps": 87, "loss": 0.1123, "lr": 1.3939877632809279e-06, "epoch": 2.344827586206897, "percentage": 78.16, "elapsed_time": "1:03:38", "remaining_time": "0:17:46"}
+{"current_steps": 69, "total_steps": 87, "loss": 0.102, "lr": 1.257446259144494e-06, "epoch": 2.3793103448275863, "percentage": 79.31, "elapsed_time": "1:04:31", "remaining_time": "0:16:49"}
+{"current_steps": 70, "total_steps": 87, "loss": 0.0889, "lr": 1.1269751908617277e-06, "epoch": 2.413793103448276, "percentage": 80.46, "elapsed_time": "1:05:25", "remaining_time": "0:15:53"}
+{"current_steps": 71, "total_steps": 87, "loss": 0.0905, "lr": 1.0027861829824953e-06, "epoch": 2.4482758620689653, "percentage": 81.61, "elapsed_time": "1:06:33", "remaining_time": "0:14:59"}
+{"current_steps": 72, "total_steps": 87, "loss": 0.1079, "lr": 8.850806705317183e-07, "epoch": 2.4827586206896552, "percentage": 82.76, "elapsed_time": "1:07:29", "remaining_time": "0:14:03"}
+{"current_steps": 73, "total_steps": 87, "loss": 0.1079, "lr": 7.740495722810271e-07, "epoch": 2.5172413793103448, "percentage": 83.91, "elapsed_time": "1:08:17", "remaining_time": "0:13:05"}
+{"current_steps": 74, "total_steps": 87, "loss": 0.1037, "lr": 6.698729810778065e-07, "epoch": 2.5517241379310347, "percentage": 85.06, "elapsed_time": "1:09:06", "remaining_time": "0:12:08"}
+{"current_steps": 75, "total_steps": 87, "loss": 0.1075, "lr": 5.727198717339511e-07, "epoch": 2.586206896551724, "percentage": 86.21, "elapsed_time": "1:09:56", "remaining_time": "0:11:11"}
+{"current_steps": 76, "total_steps": 87, "loss": 0.1132, "lr": 4.827478269480895e-07, "epoch": 2.6206896551724137, "percentage": 87.36, "elapsed_time": "1:11:04", "remaining_time": "0:10:17"}
+{"current_steps": 77, "total_steps": 87, "loss": 0.1272, "lr": 4.001027817058789e-07, "epoch": 2.655172413793103, "percentage": 88.51, "elapsed_time": "1:12:03", "remaining_time": "0:09:21"}
+{"current_steps": 78, "total_steps": 87, "loss": 0.1086, "lr": 3.2491878657292643e-07, "epoch": 2.689655172413793, "percentage": 89.66, "elapsed_time": "1:13:09", "remaining_time": "0:08:26"}
+{"current_steps": 79, "total_steps": 87, "loss": 0.1214, "lr": 2.573177902642726e-07, "epoch": 2.7241379310344827, "percentage": 90.8, "elapsed_time": "1:14:04", "remaining_time": "0:07:30"}
+{"current_steps": 80, "total_steps": 87, "loss": 0.0993, "lr": 1.9740944184313882e-07, "epoch": 2.7586206896551726, "percentage": 91.95, "elapsed_time": "1:14:57", "remaining_time": "0:06:33"}
+{"current_steps": 81, "total_steps": 87, "loss": 0.1071, "lr": 1.4529091286973994e-07, "epoch": 2.793103448275862, "percentage": 93.1, "elapsed_time": "1:15:52", "remaining_time": "0:05:37"}
+{"current_steps": 82, "total_steps": 87, "loss": 0.1112, "lr": 1.0104673978866164e-07, "epoch": 2.8275862068965516, "percentage": 94.25, "elapsed_time": "1:16:41", "remaining_time": "0:04:40"}
+{"current_steps": 83, "total_steps": 87, "loss": 0.126, "lr": 6.474868681043578e-08, "epoch": 2.862068965517241, "percentage": 95.4, "elapsed_time": "1:17:37", "remaining_time": "0:03:44"}
+{"current_steps": 84, "total_steps": 87, "loss": 0.0979, "lr": 3.645562950973014e-08, "epoch": 2.896551724137931, "percentage": 96.55, "elapsed_time": "1:18:31", "remaining_time": "0:02:48"}
+{"current_steps": 85, "total_steps": 87, "loss": 0.1006, "lr": 1.6213459328950355e-08, "epoch": 2.9310344827586206, "percentage": 97.7, "elapsed_time": "1:19:21", "remaining_time": "0:01:52"}
+{"current_steps": 86, "total_steps": 87, "loss": 0.1012, "lr": 4.055009142152066e-09, "epoch": 2.9655172413793105, "percentage": 98.85, "elapsed_time": "1:20:21", "remaining_time": "0:00:56"}
+{"current_steps": 87, "total_steps": 87, "loss": 0.1129, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:21:10", "remaining_time": "0:00:00"}
+{"current_steps": 87, "total_steps": 87, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:22:46", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be33a1e8ea4650c82172ce53bd42bef06b2a01d125b4b8f667f0070c6cd1ce43
+size 7800