Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825002e61ad640f852e9b20f5a98cea04953069ebca09c92f766a300fea5fa1d
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61b3b4b2f35fea11ec68598962aba9b7b61cfe55536994253eae9f5d2cd43535
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fc102864c26a657925f67bb06021fea4f03bc5265762078b913184024044f96
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f226d8c00df04eca64cc1a5b8bb5e6daf2c248fb98d21b9c92f83cef428420
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,110 @@
+{"current_steps": 1, "total_steps": 312, "loss": 0.8809, "lr": 1.25e-06, "epoch": 0.009584664536741214, "percentage": 0.32, "elapsed_time": "0:00:40", "remaining_time": "3:29:20"}
+{"current_steps": 2, "total_steps": 312, "loss": 0.8476, "lr": 2.5e-06, "epoch": 0.019169329073482427, "percentage": 0.64, "elapsed_time": "0:01:15", "remaining_time": "3:14:58"}
+{"current_steps": 3, "total_steps": 312, "loss": 0.8749, "lr": 3.7500000000000005e-06, "epoch": 0.02875399361022364, "percentage": 0.96, "elapsed_time": "0:01:50", "remaining_time": "3:08:56"}
+{"current_steps": 4, "total_steps": 312, "loss": 0.8422, "lr": 5e-06, "epoch": 0.038338658146964855, "percentage": 1.28, "elapsed_time": "0:02:25", "remaining_time": "3:07:05"}
+{"current_steps": 5, "total_steps": 312, "loss": 0.8005, "lr": 6.25e-06, "epoch": 0.04792332268370607, "percentage": 1.6, "elapsed_time": "0:02:53", "remaining_time": "2:57:36"}
+{"current_steps": 6, "total_steps": 312, "loss": 0.7687, "lr": 7.500000000000001e-06, "epoch": 0.05750798722044728, "percentage": 1.92, "elapsed_time": "0:03:26", "remaining_time": "2:55:34"}
+{"current_steps": 7, "total_steps": 312, "loss": 0.7686, "lr": 8.750000000000001e-06, "epoch": 0.0670926517571885, "percentage": 2.24, "elapsed_time": "0:04:00", "remaining_time": "2:54:22"}
+{"current_steps": 8, "total_steps": 312, "loss": 0.761, "lr": 1e-05, "epoch": 0.07667731629392971, "percentage": 2.56, "elapsed_time": "0:04:29", "remaining_time": "2:50:33"}
+{"current_steps": 9, "total_steps": 312, "loss": 0.7451, "lr": 1.125e-05, "epoch": 0.08626198083067092, "percentage": 2.88, "elapsed_time": "0:05:03", "remaining_time": "2:50:11"}
+{"current_steps": 10, "total_steps": 312, "loss": 0.7657, "lr": 1.25e-05, "epoch": 0.09584664536741214, "percentage": 3.21, "elapsed_time": "0:05:34", "remaining_time": "2:48:20"}
+{"current_steps": 11, "total_steps": 312, "loss": 0.7293, "lr": 1.375e-05, "epoch": 0.10543130990415335, "percentage": 3.53, "elapsed_time": "0:06:06", "remaining_time": "2:47:12"}
+{"current_steps": 12, "total_steps": 312, "loss": 0.6753, "lr": 1.5000000000000002e-05, "epoch": 0.11501597444089456, "percentage": 3.85, "elapsed_time": "0:06:42", "remaining_time": "2:47:34"}
+{"current_steps": 13, "total_steps": 312, "loss": 0.675, "lr": 1.6250000000000002e-05, "epoch": 0.12460063897763578, "percentage": 4.17, "elapsed_time": "0:07:17", "remaining_time": "2:47:31"}
+{"current_steps": 14, "total_steps": 312, "loss": 0.6346, "lr": 1.7500000000000002e-05, "epoch": 0.134185303514377, "percentage": 4.49, "elapsed_time": "0:07:50", "remaining_time": "2:46:44"}
+{"current_steps": 15, "total_steps": 312, "loss": 0.6395, "lr": 1.8750000000000002e-05, "epoch": 0.14376996805111822, "percentage": 4.81, "elapsed_time": "0:08:22", "remaining_time": "2:45:47"}
+{"current_steps": 16, "total_steps": 312, "loss": 0.6605, "lr": 2e-05, "epoch": 0.15335463258785942, "percentage": 5.13, "elapsed_time": "0:08:50", "remaining_time": "2:43:33"}
+{"current_steps": 17, "total_steps": 312, "loss": 0.6345, "lr": 2.125e-05, "epoch": 0.16293929712460065, "percentage": 5.45, "elapsed_time": "0:09:23", "remaining_time": "2:42:51"}
+{"current_steps": 18, "total_steps": 312, "loss": 0.6313, "lr": 2.25e-05, "epoch": 0.17252396166134185, "percentage": 5.77, "elapsed_time": "0:09:53", "remaining_time": "2:41:30"}
+{"current_steps": 19, "total_steps": 312, "loss": 0.6093, "lr": 2.375e-05, "epoch": 0.18210862619808307, "percentage": 6.09, "elapsed_time": "0:10:22", "remaining_time": "2:39:54"}
+{"current_steps": 20, "total_steps": 312, "loss": 0.5867, "lr": 2.5e-05, "epoch": 0.19169329073482427, "percentage": 6.41, "elapsed_time": "0:10:52", "remaining_time": "2:38:39"}
+{"current_steps": 21, "total_steps": 312, "loss": 0.5876, "lr": 2.625e-05, "epoch": 0.2012779552715655, "percentage": 6.73, "elapsed_time": "0:11:19", "remaining_time": "2:37:01"}
+{"current_steps": 22, "total_steps": 312, "loss": 0.5909, "lr": 2.75e-05, "epoch": 0.2108626198083067, "percentage": 7.05, "elapsed_time": "0:11:49", "remaining_time": "2:35:52"}
+{"current_steps": 23, "total_steps": 312, "loss": 0.5739, "lr": 2.875e-05, "epoch": 0.22044728434504793, "percentage": 7.37, "elapsed_time": "0:12:19", "remaining_time": "2:34:57"}
+{"current_steps": 24, "total_steps": 312, "loss": 0.588, "lr": 3.0000000000000004e-05, "epoch": 0.23003194888178913, "percentage": 7.69, "elapsed_time": "0:12:53", "remaining_time": "2:34:40"}
+{"current_steps": 25, "total_steps": 312, "loss": 0.5675, "lr": 3.125e-05, "epoch": 0.23961661341853036, "percentage": 8.01, "elapsed_time": "0:13:27", "remaining_time": "2:34:26"}
+{"current_steps": 26, "total_steps": 312, "loss": 0.5492, "lr": 3.2500000000000004e-05, "epoch": 0.24920127795527156, "percentage": 8.33, "elapsed_time": "0:13:59", "remaining_time": "2:33:51"}
+{"current_steps": 27, "total_steps": 312, "loss": 0.5539, "lr": 3.375e-05, "epoch": 0.25878594249201275, "percentage": 8.65, "elapsed_time": "0:14:31", "remaining_time": "2:33:16"}
+{"current_steps": 28, "total_steps": 312, "loss": 0.5319, "lr": 3.5000000000000004e-05, "epoch": 0.268370607028754, "percentage": 8.97, "elapsed_time": "0:14:56", "remaining_time": "2:31:30"}
+{"current_steps": 29, "total_steps": 312, "loss": 0.5722, "lr": 3.625e-05, "epoch": 0.2779552715654952, "percentage": 9.29, "elapsed_time": "0:15:29", "remaining_time": "2:31:06"}
+{"current_steps": 30, "total_steps": 312, "loss": 0.5514, "lr": 3.7500000000000003e-05, "epoch": 0.28753993610223644, "percentage": 9.62, "elapsed_time": "0:16:05", "remaining_time": "2:31:18"}
+{"current_steps": 31, "total_steps": 312, "loss": 0.548, "lr": 3.875e-05, "epoch": 0.2971246006389776, "percentage": 9.94, "elapsed_time": "0:16:40", "remaining_time": "2:31:07"}
+{"current_steps": 32, "total_steps": 312, "loss": 0.5776, "lr": 4e-05, "epoch": 0.30670926517571884, "percentage": 10.26, "elapsed_time": "0:17:15", "remaining_time": "2:31:03"}
+{"current_steps": 33, "total_steps": 312, "loss": 0.5444, "lr": 3.9998741135094016e-05, "epoch": 0.31629392971246006, "percentage": 10.58, "elapsed_time": "0:17:41", "remaining_time": "2:29:30"}
+{"current_steps": 34, "total_steps": 312, "loss": 0.5704, "lr": 3.999496469885014e-05, "epoch": 0.3258785942492013, "percentage": 10.9, "elapsed_time": "0:18:14", "remaining_time": "2:29:05"}
+{"current_steps": 35, "total_steps": 312, "loss": 0.5477, "lr": 3.998867116667067e-05, "epoch": 0.3354632587859425, "percentage": 11.22, "elapsed_time": "0:18:50", "remaining_time": "2:29:10"}
+{"current_steps": 36, "total_steps": 312, "loss": 0.5534, "lr": 3.9979861330826295e-05, "epoch": 0.3450479233226837, "percentage": 11.54, "elapsed_time": "0:19:19", "remaining_time": "2:28:11"}
+{"current_steps": 37, "total_steps": 312, "loss": 0.5655, "lr": 3.996853630035634e-05, "epoch": 0.3546325878594249, "percentage": 11.86, "elapsed_time": "0:19:51", "remaining_time": "2:27:37"}
+{"current_steps": 38, "total_steps": 312, "loss": 0.5817, "lr": 3.995469750092912e-05, "epoch": 0.36421725239616615, "percentage": 12.18, "elapsed_time": "0:20:24", "remaining_time": "2:27:09"}
+{"current_steps": 39, "total_steps": 312, "loss": 0.5044, "lr": 3.9938346674662565e-05, "epoch": 0.3738019169329074, "percentage": 12.5, "elapsed_time": "0:20:57", "remaining_time": "2:26:40"}
+{"current_steps": 40, "total_steps": 312, "loss": 0.5359, "lr": 3.991948587990479e-05, "epoch": 0.38338658146964855, "percentage": 12.82, "elapsed_time": "0:21:30", "remaining_time": "2:26:16"}
+{"current_steps": 41, "total_steps": 312, "loss": 0.5537, "lr": 3.989811749097505e-05, "epoch": 0.3929712460063898, "percentage": 13.14, "elapsed_time": "0:22:05", "remaining_time": "2:25:58"}
+{"current_steps": 42, "total_steps": 312, "loss": 0.5782, "lr": 3.9874244197864856e-05, "epoch": 0.402555910543131, "percentage": 13.46, "elapsed_time": "0:22:41", "remaining_time": "2:25:52"}
+{"current_steps": 43, "total_steps": 312, "loss": 0.5415, "lr": 3.984786900589929e-05, "epoch": 0.41214057507987223, "percentage": 13.78, "elapsed_time": "0:23:15", "remaining_time": "2:25:29"}
+{"current_steps": 44, "total_steps": 312, "loss": 0.5542, "lr": 3.98189952353587e-05, "epoch": 0.4217252396166134, "percentage": 14.1, "elapsed_time": "0:23:46", "remaining_time": "2:24:48"}
+{"current_steps": 45, "total_steps": 312, "loss": 0.5483, "lr": 3.9787626521060736e-05, "epoch": 0.43130990415335463, "percentage": 14.42, "elapsed_time": "0:24:18", "remaining_time": "2:24:14"}
+{"current_steps": 46, "total_steps": 312, "loss": 0.5473, "lr": 3.9753766811902756e-05, "epoch": 0.44089456869009586, "percentage": 14.74, "elapsed_time": "0:24:49", "remaining_time": "2:23:31"}
+{"current_steps": 47, "total_steps": 312, "loss": 0.5634, "lr": 3.971742037036472e-05, "epoch": 0.4504792332268371, "percentage": 15.06, "elapsed_time": "0:25:22", "remaining_time": "2:23:02"}
+{"current_steps": 48, "total_steps": 312, "loss": 0.558, "lr": 3.96785917719726e-05, "epoch": 0.46006389776357826, "percentage": 15.38, "elapsed_time": "0:25:55", "remaining_time": "2:22:33"}
+{"current_steps": 49, "total_steps": 312, "loss": 0.5508, "lr": 3.9637285904722376e-05, "epoch": 0.4696485623003195, "percentage": 15.71, "elapsed_time": "0:26:29", "remaining_time": "2:22:11"}
+{"current_steps": 50, "total_steps": 312, "loss": 0.5478, "lr": 3.9593507968464714e-05, "epoch": 0.4792332268370607, "percentage": 16.03, "elapsed_time": "0:27:01", "remaining_time": "2:21:37"}
+{"current_steps": 51, "total_steps": 312, "loss": 0.5366, "lr": 3.9547263474250385e-05, "epoch": 0.48881789137380194, "percentage": 16.35, "elapsed_time": "0:27:34", "remaining_time": "2:21:07"}
+{"current_steps": 52, "total_steps": 312, "loss": 0.5544, "lr": 3.949855824363647e-05, "epoch": 0.4984025559105431, "percentage": 16.67, "elapsed_time": "0:28:08", "remaining_time": "2:20:40"}
+{"current_steps": 53, "total_steps": 312, "loss": 0.4976, "lr": 3.9447398407953536e-05, "epoch": 0.5079872204472844, "percentage": 16.99, "elapsed_time": "0:28:43", "remaining_time": "2:20:23"}
+{"current_steps": 54, "total_steps": 312, "loss": 0.5374, "lr": 3.939379040753374e-05, "epoch": 0.5175718849840255, "percentage": 17.31, "elapsed_time": "0:29:13", "remaining_time": "2:19:38"}
+{"current_steps": 55, "total_steps": 312, "loss": 0.5517, "lr": 3.933774099090013e-05, "epoch": 0.5271565495207667, "percentage": 17.63, "elapsed_time": "0:29:45", "remaining_time": "2:19:02"}
+{"current_steps": 56, "total_steps": 312, "loss": 0.5114, "lr": 3.927925721391707e-05, "epoch": 0.536741214057508, "percentage": 17.95, "elapsed_time": "0:30:17", "remaining_time": "2:18:29"}
+{"current_steps": 57, "total_steps": 312, "loss": 0.5556, "lr": 3.9218346438901996e-05, "epoch": 0.5463258785942492, "percentage": 18.27, "elapsed_time": "0:30:53", "remaining_time": "2:18:10"}
+{"current_steps": 58, "total_steps": 312, "loss": 0.5446, "lr": 3.9155016333698615e-05, "epoch": 0.5559105431309904, "percentage": 18.59, "elapsed_time": "0:31:23", "remaining_time": "2:17:29"}
+{"current_steps": 59, "total_steps": 312, "loss": 0.5297, "lr": 3.908927487071162e-05, "epoch": 0.5654952076677316, "percentage": 18.91, "elapsed_time": "0:31:55", "remaining_time": "2:16:54"}
+{"current_steps": 60, "total_steps": 312, "loss": 0.5283, "lr": 3.9021130325903076e-05, "epoch": 0.5750798722044729, "percentage": 19.23, "elapsed_time": "0:32:25", "remaining_time": "2:16:12"}
+{"current_steps": 61, "total_steps": 312, "loss": 0.5276, "lr": 3.895059127775058e-05, "epoch": 0.5846645367412141, "percentage": 19.55, "elapsed_time": "0:33:00", "remaining_time": "2:15:51"}
+{"current_steps": 62, "total_steps": 312, "loss": 0.5053, "lr": 3.8877666606167354e-05, "epoch": 0.5942492012779552, "percentage": 19.87, "elapsed_time": "0:33:33", "remaining_time": "2:15:18"}
+{"current_steps": 63, "total_steps": 312, "loss": 0.5019, "lr": 3.880236549138438e-05, "epoch": 0.6038338658146964, "percentage": 20.19, "elapsed_time": "0:34:10", "remaining_time": "2:15:03"}
+{"current_steps": 64, "total_steps": 312, "loss": 0.5027, "lr": 3.872469741279475e-05, "epoch": 0.6134185303514377, "percentage": 20.51, "elapsed_time": "0:34:40", "remaining_time": "2:14:23"}
+{"current_steps": 65, "total_steps": 312, "loss": 0.5373, "lr": 3.8644672147760286e-05, "epoch": 0.6230031948881789, "percentage": 20.83, "elapsed_time": "0:35:13", "remaining_time": "2:13:52"}
+{"current_steps": 66, "total_steps": 312, "loss": 0.5141, "lr": 3.856229977038078e-05, "epoch": 0.6325878594249201, "percentage": 21.15, "elapsed_time": "0:35:45", "remaining_time": "2:13:17"}
+{"current_steps": 67, "total_steps": 312, "loss": 0.5237, "lr": 3.8477590650225735e-05, "epoch": 0.6421725239616614, "percentage": 21.47, "elapsed_time": "0:36:20", "remaining_time": "2:12:54"}
+{"current_steps": 68, "total_steps": 312, "loss": 0.5218, "lr": 3.839055545102902e-05, "epoch": 0.6517571884984026, "percentage": 21.79, "elapsed_time": "0:36:55", "remaining_time": "2:12:30"}
+{"current_steps": 69, "total_steps": 312, "loss": 0.5106, "lr": 3.83012051293464e-05, "epoch": 0.6613418530351438, "percentage": 22.12, "elapsed_time": "0:37:28", "remaining_time": "2:12:00"}
+{"current_steps": 70, "total_steps": 312, "loss": 0.5371, "lr": 3.8209550933176324e-05, "epoch": 0.670926517571885, "percentage": 22.44, "elapsed_time": "0:37:52", "remaining_time": "2:10:57"}
+{"current_steps": 71, "total_steps": 312, "loss": 0.5285, "lr": 3.8115604400543885e-05, "epoch": 0.6805111821086262, "percentage": 22.76, "elapsed_time": "0:38:24", "remaining_time": "2:10:20"}
+{"current_steps": 72, "total_steps": 312, "loss": 0.5226, "lr": 3.801937735804838e-05, "epoch": 0.6900958466453674, "percentage": 23.08, "elapsed_time": "0:38:54", "remaining_time": "2:09:41"}
+{"current_steps": 73, "total_steps": 312, "loss": 0.5575, "lr": 3.792088191937451e-05, "epoch": 0.6996805111821086, "percentage": 23.4, "elapsed_time": "0:39:24", "remaining_time": "2:09:02"}
+{"current_steps": 74, "total_steps": 312, "loss": 0.5331, "lr": 3.782013048376736e-05, "epoch": 0.7092651757188498, "percentage": 23.72, "elapsed_time": "0:39:56", "remaining_time": "2:08:27"}
+{"current_steps": 75, "total_steps": 312, "loss": 0.4955, "lr": 3.77171357344716e-05, "epoch": 0.7188498402555911, "percentage": 24.04, "elapsed_time": "0:40:20", "remaining_time": "2:07:29"}
+{"current_steps": 76, "total_steps": 312, "loss": 0.5319, "lr": 3.761191063713476e-05, "epoch": 0.7284345047923323, "percentage": 24.36, "elapsed_time": "0:40:54", "remaining_time": "2:07:01"}
+{"current_steps": 77, "total_steps": 312, "loss": 0.5286, "lr": 3.7504468438175076e-05, "epoch": 0.7380191693290735, "percentage": 24.68, "elapsed_time": "0:41:26", "remaining_time": "2:06:29"}
+{"current_steps": 78, "total_steps": 312, "loss": 0.5202, "lr": 3.7394822663113915e-05, "epoch": 0.7476038338658147, "percentage": 25.0, "elapsed_time": "0:41:56", "remaining_time": "2:05:48"}
+{"current_steps": 79, "total_steps": 312, "loss": 0.5094, "lr": 3.72829871148731e-05, "epoch": 0.7571884984025559, "percentage": 25.32, "elapsed_time": "0:42:31", "remaining_time": "2:05:24"}
+{"current_steps": 80, "total_steps": 312, "loss": 0.5067, "lr": 3.716897587203733e-05, "epoch": 0.7667731629392971, "percentage": 25.64, "elapsed_time": "0:43:04", "remaining_time": "2:04:55"}
+{"current_steps": 81, "total_steps": 312, "loss": 0.5052, "lr": 3.705280328708185e-05, "epoch": 0.7763578274760383, "percentage": 25.96, "elapsed_time": "0:43:39", "remaining_time": "2:04:30"}
+{"current_steps": 82, "total_steps": 312, "loss": 0.5396, "lr": 3.6934483984565684e-05, "epoch": 0.7859424920127795, "percentage": 26.28, "elapsed_time": "0:44:11", "remaining_time": "2:03:57"}
+{"current_steps": 83, "total_steps": 312, "loss": 0.5372, "lr": 3.681403285929061e-05, "epoch": 0.7955271565495208, "percentage": 26.6, "elapsed_time": "0:44:46", "remaining_time": "2:03:31"}
+{"current_steps": 84, "total_steps": 312, "loss": 0.5022, "lr": 3.669146507442606e-05, "epoch": 0.805111821086262, "percentage": 26.92, "elapsed_time": "0:45:15", "remaining_time": "2:02:51"}
+{"current_steps": 85, "total_steps": 312, "loss": 0.4943, "lr": 3.6566796059600334e-05, "epoch": 0.8146964856230032, "percentage": 27.24, "elapsed_time": "0:45:48", "remaining_time": "2:02:19"}
+{"current_steps": 86, "total_steps": 312, "loss": 0.5137, "lr": 3.644004150895821e-05, "epoch": 0.8242811501597445, "percentage": 27.56, "elapsed_time": "0:46:21", "remaining_time": "2:01:50"}
+{"current_steps": 87, "total_steps": 312, "loss": 0.5211, "lr": 3.631121737918521e-05, "epoch": 0.8338658146964856, "percentage": 27.88, "elapsed_time": "0:46:53", "remaining_time": "2:01:16"}
+{"current_steps": 88, "total_steps": 312, "loss": 0.5426, "lr": 3.6180339887498953e-05, "epoch": 0.8434504792332268, "percentage": 28.21, "elapsed_time": "0:47:18", "remaining_time": "2:00:26"}
+{"current_steps": 89, "total_steps": 312, "loss": 0.4952, "lr": 3.6047425509607566e-05, "epoch": 0.853035143769968, "percentage": 28.53, "elapsed_time": "0:47:47", "remaining_time": "1:59:44"}
+{"current_steps": 90, "total_steps": 312, "loss": 0.5101, "lr": 3.591249097763562e-05, "epoch": 0.8626198083067093, "percentage": 28.85, "elapsed_time": "0:48:20", "remaining_time": "1:59:14"}
+{"current_steps": 91, "total_steps": 312, "loss": 0.5298, "lr": 3.5775553278017824e-05, "epoch": 0.8722044728434505, "percentage": 29.17, "elapsed_time": "0:48:54", "remaining_time": "1:58:47"}
+{"current_steps": 92, "total_steps": 312, "loss": 0.509, "lr": 3.56366296493606e-05, "epoch": 0.8817891373801917, "percentage": 29.49, "elapsed_time": "0:49:27", "remaining_time": "1:58:17"}
+{"current_steps": 93, "total_steps": 312, "loss": 0.5078, "lr": 3.5495737580272024e-05, "epoch": 0.8913738019169329, "percentage": 29.81, "elapsed_time": "0:50:02", "remaining_time": "1:57:50"}
+{"current_steps": 94, "total_steps": 312, "loss": 0.5207, "lr": 3.535289480716023e-05, "epoch": 0.9009584664536742, "percentage": 30.13, "elapsed_time": "0:50:37", "remaining_time": "1:57:24"}
+{"current_steps": 95, "total_steps": 312, "loss": 0.5141, "lr": 3.520811931200063e-05, "epoch": 0.9105431309904153, "percentage": 30.45, "elapsed_time": "0:51:04", "remaining_time": "1:56:38"}
+{"current_steps": 96, "total_steps": 312, "loss": 0.509, "lr": 3.5061429320072225e-05, "epoch": 0.9201277955271565, "percentage": 30.77, "elapsed_time": "0:51:35", "remaining_time": "1:56:05"}
+{"current_steps": 97, "total_steps": 312, "loss": 0.5009, "lr": 3.4912843297663315e-05, "epoch": 0.9297124600638977, "percentage": 31.09, "elapsed_time": "0:52:10", "remaining_time": "1:55:39"}
+{"current_steps": 98, "total_steps": 312, "loss": 0.5094, "lr": 3.476237994974682e-05, "epoch": 0.939297124600639, "percentage": 31.41, "elapsed_time": "0:52:39", "remaining_time": "1:55:00"}
+{"current_steps": 99, "total_steps": 312, "loss": 0.5254, "lr": 3.4610058217625554e-05, "epoch": 0.9488817891373802, "percentage": 31.73, "elapsed_time": "0:53:10", "remaining_time": "1:54:24"}
+{"current_steps": 100, "total_steps": 312, "loss": 0.5103, "lr": 3.4455897276547836e-05, "epoch": 0.9584664536741214, "percentage": 32.05, "elapsed_time": "0:53:44", "remaining_time": "1:53:56"}
+{"current_steps": 101, "total_steps": 312, "loss": 0.4962, "lr": 3.429991653329351e-05, "epoch": 0.9680511182108626, "percentage": 32.37, "elapsed_time": "0:54:14", "remaining_time": "1:53:18"}
+{"current_steps": 102, "total_steps": 312, "loss": 0.4886, "lr": 3.4142135623730954e-05, "epoch": 0.9776357827476039, "percentage": 32.69, "elapsed_time": "0:54:46", "remaining_time": "1:52:46"}
+{"current_steps": 103, "total_steps": 312, "loss": 0.5153, "lr": 3.398257441034515e-05, "epoch": 0.987220447284345, "percentage": 33.01, "elapsed_time": "0:55:12", "remaining_time": "1:52:01"}
+{"current_steps": 104, "total_steps": 312, "loss": 0.5153, "lr": 3.38212529797373e-05, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:55:43", "remaining_time": "1:51:26"}
+{"current_steps": 105, "total_steps": 312, "loss": 0.8678, "lr": 3.365819164009614e-05, "epoch": 1.0063897763578276, "percentage": 33.65, "elapsed_time": "0:57:00", "remaining_time": "1:52:23"}
+{"current_steps": 106, "total_steps": 312, "loss": 0.3831, "lr": 3.349341091864149e-05, "epoch": 1.0159744408945688, "percentage": 33.97, "elapsed_time": "0:57:31", "remaining_time": "1:51:47"}
+{"current_steps": 107, "total_steps": 312, "loss": 0.4093, "lr": 3.3326931559040084e-05, "epoch": 1.0255591054313098, "percentage": 34.29, "elapsed_time": "0:58:04", "remaining_time": "1:51:16"}
+{"current_steps": 108, "total_steps": 312, "loss": 0.4151, "lr": 3.315877451879426e-05, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:58:33", "remaining_time": "1:50:37"}
+{"current_steps": 109, "total_steps": 312, "loss": 0.4591, "lr": 3.298896096660367e-05, "epoch": 1.0447284345047922, "percentage": 34.94, "elapsed_time": "0:59:04", "remaining_time": "1:50:01"}
+{"current_steps": 110, "total_steps": 312, "loss": 0.3995, "lr": 3.2817512279700486e-05, "epoch": 1.0543130990415335, "percentage": 35.26, "elapsed_time": "0:59:39", "remaining_time": "1:49:33"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2290d6b28a2830169931eba462dd531b1ef6aaa4d90c0335b4ec006d6dc12a57
+size 7224