Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 0413-7B/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+link-0501-7B/tokenizer.json filter=lfs diff=lfs merge=lfs -text

link-0501-7B/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
+}

link-0501-7B/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/home/xulilin/Qwen2.5-instruct-7B",
+  "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": "4.46.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

link-0501-7B/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.0"
+}

link-0501-7B/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d0b9880426be2b6f6373c3bcdfe545035f54c5f1e9f4ba652c9dbfe742a5ce2
+size 4877660776

link-0501-7B/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d077f95c10ded549daee0abe391ce8937223c4db354744f341a31b2c132a46de
+size 4932751008

link-0501-7B/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57eee202e539fd4902ebc6214bd347c577430a11ca86e1f321c205e3ac5ea2cb
+size 4330865200

link-0501-7B/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a532a2b1ec0fecbbf56fcae776944466e4770b404e51cfed3aef624ba0e1c742
+size 1089994880

link-0501-7B/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"
+  }
+}

link-0501-7B/runs/May01_21-44-49_ubuntu-Super-Server/events.out.tfevents.1746107156.ubuntu-Super-Server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8517dbbf9ecb32cb2a83867bde45c9ec801c3aef88200e95efc05039c55c61
+size 64045

link-0501-7B/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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
+  }
+}

link-0501-7B/tokenizer.json

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

link-0501-7B/tokenizer_config.json

@@ -0,0 +1,198 @@
+{
+  "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_end|>",
+    "<|im_start|>"
+  ],
+  "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": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation": true,
+  "unk_token": null
+}

link-0501-7B/trainer_state.json

@@ -0,0 +1,1995 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.976,
+  "eval_steps": 500,
+  "global_step": 279,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010666666666666666,
+      "grad_norm": 11.754026412963867,
+      "learning_rate": 0.0,
+      "loss": 0.3055,
+      "step": 1
+    },
+    {
+      "epoch": 0.021333333333333333,
+      "grad_norm": 168.7552032470703,
+      "learning_rate": 7.525749891599529e-06,
+      "loss": 0.3533,
+      "step": 2
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 186.65489196777344,
+      "learning_rate": 1.192803136799156e-05,
+      "loss": 0.3818,
+      "step": 3
+    },
+    {
+      "epoch": 0.042666666666666665,
+      "grad_norm": 8.70337200164795,
+      "learning_rate": 1.5051499783199057e-05,
+      "loss": 0.233,
+      "step": 4
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 18.427181243896484,
+      "learning_rate": 1.7474250108400467e-05,
+      "loss": 0.5997,
+      "step": 5
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 10.40682315826416,
+      "learning_rate": 1.945378125959109e-05,
+      "loss": 0.1481,
+      "step": 6
+    },
+    {
+      "epoch": 0.07466666666666667,
+      "grad_norm": 2.7625439167022705,
+      "learning_rate": 2.1127451000356418e-05,
+      "loss": 0.071,
+      "step": 7
+    },
+    {
+      "epoch": 0.08533333333333333,
+      "grad_norm": 1.7677353620529175,
+      "learning_rate": 2.2577249674798584e-05,
+      "loss": 0.0424,
+      "step": 8
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 191.71823120117188,
+      "learning_rate": 2.385606273598312e-05,
+      "loss": 0.068,
+      "step": 9
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 4.576934337615967,
+      "learning_rate": 2.4999999999999998e-05,
+      "loss": 0.0876,
+      "step": 10
+    },
+    {
+      "epoch": 0.11733333333333333,
+      "grad_norm": 2.2950680255889893,
+      "learning_rate": 2.6034817128955623e-05,
+      "loss": 0.0549,
+      "step": 11
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 1.4517072439193726,
+      "learning_rate": 2.6979531151190617e-05,
+      "loss": 0.0306,
+      "step": 12
+    },
+    {
+      "epoch": 0.13866666666666666,
+      "grad_norm": 1.2535955905914307,
+      "learning_rate": 2.7848583807670913e-05,
+      "loss": 0.0316,
+      "step": 13
+    },
+    {
+      "epoch": 0.14933333333333335,
+      "grad_norm": 0.7079260945320129,
+      "learning_rate": 2.8653200891955945e-05,
+      "loss": 0.0226,
+      "step": 14
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.4892561435699463,
+      "learning_rate": 2.940228147639203e-05,
+      "loss": 0.0123,
+      "step": 15
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 1.0918864011764526,
+      "learning_rate": 3.0102999566398115e-05,
+      "loss": 0.0176,
+      "step": 16
+    },
+    {
+      "epoch": 0.18133333333333335,
+      "grad_norm": 1.0043039321899414,
+      "learning_rate": 3.076122303445685e-05,
+      "loss": 0.0178,
+      "step": 17
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.5436441898345947,
+      "learning_rate": 3.1381812627582646e-05,
+      "loss": 0.015,
+      "step": 18
+    },
+    {
+      "epoch": 0.20266666666666666,
+      "grad_norm": 1.5427027940750122,
+      "learning_rate": 3.1968840023820715e-05,
+      "loss": 0.0095,
+      "step": 19
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.7236639857292175,
+      "learning_rate": 3.2525749891599525e-05,
+      "loss": 0.0092,
+      "step": 20
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.37848928570747375,
+      "learning_rate": 3.305548236834798e-05,
+      "loss": 0.0055,
+      "step": 21
+    },
+    {
+      "epoch": 0.23466666666666666,
+      "grad_norm": 0.561617374420166,
+      "learning_rate": 3.3560567020555153e-05,
+      "loss": 0.0089,
+      "step": 22
+    },
+    {
+      "epoch": 0.24533333333333332,
+      "grad_norm": 0.6394134759902954,
+      "learning_rate": 3.404319590043982e-05,
+      "loss": 0.0077,
+      "step": 23
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.33990687131881714,
+      "learning_rate": 3.450528104279015e-05,
+      "loss": 0.0036,
+      "step": 24
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.16947203874588013,
+      "learning_rate": 3.4948500216800935e-05,
+      "loss": 0.0015,
+      "step": 25
+    },
+    {
+      "epoch": 0.2773333333333333,
+      "grad_norm": 0.5070152878761292,
+      "learning_rate": 3.537433369927044e-05,
+      "loss": 0.005,
+      "step": 26
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.2414875030517578,
+      "learning_rate": 3.578409410397468e-05,
+      "loss": 0.0036,
+      "step": 27
+    },
+    {
+      "epoch": 0.2986666666666667,
+      "grad_norm": 0.7398623824119568,
+      "learning_rate": 3.6178950783555475e-05,
+      "loss": 0.003,
+      "step": 28
+    },
+    {
+      "epoch": 0.30933333333333335,
+      "grad_norm": 1.3114838600158691,
+      "learning_rate": 3.65599499474739e-05,
+      "loss": 0.0231,
+      "step": 29
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.7240581512451172,
+      "learning_rate": 3.6928031367991554e-05,
+      "loss": 0.0181,
+      "step": 30
+    },
+    {
+      "epoch": 0.33066666666666666,
+      "grad_norm": 0.4996863901615143,
+      "learning_rate": 3.728404234585681e-05,
+      "loss": 0.0187,
+      "step": 31
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 1.1202421188354492,
+      "learning_rate": 3.762874945799765e-05,
+      "loss": 0.0104,
+      "step": 32
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6726235747337341,
+      "learning_rate": 3.796284849694718e-05,
+      "loss": 0.0076,
+      "step": 33
+    },
+    {
+      "epoch": 0.3626666666666667,
+      "grad_norm": 0.5757638812065125,
+      "learning_rate": 3.8286972926056376e-05,
+      "loss": 0.0092,
+      "step": 34
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 4.56654691696167,
+      "learning_rate": 3.8601701108756885e-05,
+      "loss": 0.0033,
+      "step": 35
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.46551939845085144,
+      "learning_rate": 3.890756251918218e-05,
+      "loss": 0.0062,
+      "step": 36
+    },
+    {
+      "epoch": 0.39466666666666667,
+      "grad_norm": 0.17347362637519836,
+      "learning_rate": 3.920504310167487e-05,
+      "loss": 0.0015,
+      "step": 37
+    },
+    {
+      "epoch": 0.4053333333333333,
+      "grad_norm": 0.6298040747642517,
+      "learning_rate": 3.949458991542025e-05,
+      "loss": 0.0035,
+      "step": 38
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.46180495619773865,
+      "learning_rate": 3.977661517566247e-05,
+      "loss": 0.0034,
+      "step": 39
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.22213543951511383,
+      "learning_rate": 4.005149978319905e-05,
+      "loss": 0.0059,
+      "step": 40
+    },
+    {
+      "epoch": 0.43733333333333335,
+      "grad_norm": 0.26860398054122925,
+      "learning_rate": 4.031959641799338e-05,
+      "loss": 0.0046,
+      "step": 41
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.07143426686525345,
+      "learning_rate": 4.058123225994751e-05,
+      "loss": 0.0005,
+      "step": 42
+    },
+    {
+      "epoch": 0.45866666666666667,
+      "grad_norm": 0.39327096939086914,
+      "learning_rate": 4.0836711389489654e-05,
+      "loss": 0.0025,
+      "step": 43
+    },
+    {
+      "epoch": 0.4693333333333333,
+      "grad_norm": 0.18292081356048584,
+      "learning_rate": 4.108631691215468e-05,
+      "loss": 0.0011,
+      "step": 44
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.2323281168937683,
+      "learning_rate": 4.133031284438358e-05,
+      "loss": 0.0042,
+      "step": 45
+    },
+    {
+      "epoch": 0.49066666666666664,
+      "grad_norm": 0.1796242743730545,
+      "learning_rate": 4.156894579203935e-05,
+      "loss": 0.0029,
+      "step": 46
+    },
+    {
+      "epoch": 0.5013333333333333,
+      "grad_norm": 0.2503258287906647,
+      "learning_rate": 4.180244644839293e-05,
+      "loss": 0.0014,
+      "step": 47
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.4935305714607239,
+      "learning_rate": 4.203103093438968e-05,
+      "loss": 0.0045,
+      "step": 48
+    },
+    {
+      "epoch": 0.5226666666666666,
+      "grad_norm": 0.09073633700609207,
+      "learning_rate": 4.2254902000712836e-05,
+      "loss": 0.0022,
+      "step": 49
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 18.01141929626465,
+      "learning_rate": 4.247425010840046e-05,
+      "loss": 0.0066,
+      "step": 50
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 10.438459396362305,
+      "learning_rate": 4.2689254402448405e-05,
+      "loss": 0.0033,
+      "step": 51
+    },
+    {
+      "epoch": 0.5546666666666666,
+      "grad_norm": 0.7780687808990479,
+      "learning_rate": 4.290008359086998e-05,
+      "loss": 0.0065,
+      "step": 52
+    },
+    {
+      "epoch": 0.5653333333333334,
+      "grad_norm": 1.873307704925537,
+      "learning_rate": 4.310689674001973e-05,
+      "loss": 0.0077,
+      "step": 53
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.2861614227294922,
+      "learning_rate": 4.330984399557421e-05,
+      "loss": 0.0025,
+      "step": 54
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.3399127721786499,
+      "learning_rate": 4.350906723735609e-05,
+      "loss": 0.0064,
+      "step": 55
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": 0.1241474598646164,
+      "learning_rate": 4.370470067515501e-05,
+      "loss": 0.0013,
+      "step": 56
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.9950242638587952,
+      "learning_rate": 4.3896871391812285e-05,
+      "loss": 0.0078,
+      "step": 57
+    },
+    {
+      "epoch": 0.6186666666666667,
+      "grad_norm": 0.4737244248390198,
+      "learning_rate": 4.408569983907343e-05,
+      "loss": 0.0052,
+      "step": 58
+    },
+    {
+      "epoch": 0.6293333333333333,
+      "grad_norm": 0.2054540067911148,
+      "learning_rate": 4.42713002910536e-05,
+      "loss": 0.0017,
+      "step": 59
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 10.90045166015625,
+      "learning_rate": 4.445378125959108e-05,
+      "loss": 0.058,
+      "step": 60
+    },
+    {
+      "epoch": 0.6506666666666666,
+      "grad_norm": 10.06686782836914,
+      "learning_rate": 4.463324587526917e-05,
+      "loss": 0.013,
+      "step": 61
+    },
+    {
+      "epoch": 0.6613333333333333,
+      "grad_norm": 1.0619251728057861,
+      "learning_rate": 4.4809792237456346e-05,
+      "loss": 0.0136,
+      "step": 62
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.42734405398368835,
+      "learning_rate": 4.498351373633954e-05,
+      "loss": 0.0082,
+      "step": 63
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 0.3401489555835724,
+      "learning_rate": 4.515449934959717e-05,
+      "loss": 0.0047,
+      "step": 64
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.436235636472702,
+      "learning_rate": 4.532283391607138e-05,
+      "loss": 0.0033,
+      "step": 65
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.16111600399017334,
+      "learning_rate": 4.548859838854671e-05,
+      "loss": 0.0026,
+      "step": 66
+    },
+    {
+      "epoch": 0.7146666666666667,
+      "grad_norm": 0.4501577317714691,
+      "learning_rate": 4.565187006752065e-05,
+      "loss": 0.0027,
+      "step": 67
+    },
+    {
+      "epoch": 0.7253333333333334,
+      "grad_norm": 0.13672642409801483,
+      "learning_rate": 4.581272281765591e-05,
+      "loss": 0.0028,
+      "step": 68
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.1461324542760849,
+      "learning_rate": 4.597122726843138e-05,
+      "loss": 0.0004,
+      "step": 69
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.918027400970459,
+      "learning_rate": 4.612745100035642e-05,
+      "loss": 0.0071,
+      "step": 70
+    },
+    {
+      "epoch": 0.7573333333333333,
+      "grad_norm": 0.15455181896686554,
+      "learning_rate": 4.628145871797688e-05,
+      "loss": 0.0006,
+      "step": 71
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 3.5162384510040283,
+      "learning_rate": 4.643331241078171e-05,
+      "loss": 0.0164,
+      "step": 72
+    },
+    {
+      "epoch": 0.7786666666666666,
+      "grad_norm": 0.21477486193180084,
+      "learning_rate": 4.658307150301139e-05,
+      "loss": 0.0016,
+      "step": 73
+    },
+    {
+      "epoch": 0.7893333333333333,
+      "grad_norm": 2.651820421218872,
+      "learning_rate": 4.67307929932744e-05,
+      "loss": 0.0014,
+      "step": 74
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.20848479866981506,
+      "learning_rate": 4.687653158479249e-05,
+      "loss": 0.0043,
+      "step": 75
+    },
+    {
+      "epoch": 0.8106666666666666,
+      "grad_norm": 0.08430308848619461,
+      "learning_rate": 4.702033980701978e-05,
+      "loss": 0.0003,
+      "step": 76
+    },
+    {
+      "epoch": 0.8213333333333334,
+      "grad_norm": 0.4553821384906769,
+      "learning_rate": 4.716226812931204e-05,
+      "loss": 0.0014,
+      "step": 77
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 1.0971914529800415,
+      "learning_rate": 4.7302365067262006e-05,
+      "loss": 0.0086,
+      "step": 78
+    },
+    {
+      "epoch": 0.8426666666666667,
+      "grad_norm": 0.5060430765151978,
+      "learning_rate": 4.744067728226103e-05,
+      "loss": 0.0036,
+      "step": 79
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.305854856967926,
+      "learning_rate": 4.757724967479858e-05,
+      "loss": 0.0013,
+      "step": 80
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.4014900326728821,
+      "learning_rate": 4.771212547196624e-05,
+      "loss": 0.0055,
+      "step": 81
+    },
+    {
+      "epoch": 0.8746666666666667,
+      "grad_norm": 0.1626356542110443,
+      "learning_rate": 4.7845346309592914e-05,
+      "loss": 0.0034,
+      "step": 82
+    },
+    {
+      "epoch": 0.8853333333333333,
+      "grad_norm": 0.3583512306213379,
+      "learning_rate": 4.7976952309401844e-05,
+      "loss": 0.0052,
+      "step": 83
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.12416330724954605,
+      "learning_rate": 4.810698215154703e-05,
+      "loss": 0.002,
+      "step": 84
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.28302738070487976,
+      "learning_rate": 4.823547314285732e-05,
+      "loss": 0.0022,
+      "step": 85
+    },
+    {
+      "epoch": 0.9173333333333333,
+      "grad_norm": 0.22168681025505066,
+      "learning_rate": 4.836246128108918e-05,
+      "loss": 0.0013,
+      "step": 86
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.09444810450077057,
+      "learning_rate": 4.8487981315465456e-05,
+      "loss": 0.0019,
+      "step": 87
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": 0.2013028860092163,
+      "learning_rate": 4.8612066803754214e-05,
+      "loss": 0.0007,
+      "step": 88
+    },
+    {
+      "epoch": 0.9493333333333334,
+      "grad_norm": 0.04223403334617615,
+      "learning_rate": 4.873475016612281e-05,
+      "loss": 0.0003,
+      "step": 89
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.23566360771656036,
+      "learning_rate": 4.885606273598312e-05,
+      "loss": 0.0015,
+      "step": 90
+    },
+    {
+      "epoch": 0.9706666666666667,
+      "grad_norm": 0.13892315328121185,
+      "learning_rate": 4.897603480802733e-05,
+      "loss": 0.0007,
+      "step": 91
+    },
+    {
+      "epoch": 0.9813333333333333,
+      "grad_norm": 0.0873648077249527,
+      "learning_rate": 4.909469568363888e-05,
+      "loss": 0.0018,
+      "step": 92
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.17551331222057343,
+      "learning_rate": 4.9212073713848375e-05,
+      "loss": 0.002,
+      "step": 93
+    },
+    {
+      "epoch": 1.0026666666666666,
+      "grad_norm": 0.049495816230773926,
+      "learning_rate": 4.932819633999246e-05,
+      "loss": 0.0003,
+      "step": 94
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 0.0984305739402771,
+      "learning_rate": 4.9443090132221186e-05,
+      "loss": 0.0004,
+      "step": 95
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.27251753211021423,
+      "learning_rate": 4.9556780825989205e-05,
+      "loss": 0.0019,
+      "step": 96
+    },
+    {
+      "epoch": 1.0346666666666666,
+      "grad_norm": 0.18246564269065857,
+      "learning_rate": 4.9669293356656114e-05,
+      "loss": 0.0021,
+      "step": 97
+    },
+    {
+      "epoch": 1.0453333333333332,
+      "grad_norm": 0.19564488530158997,
+      "learning_rate": 4.978065189231237e-05,
+      "loss": 0.001,
+      "step": 98
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 1.6231553554534912,
+      "learning_rate": 4.989087986493874e-05,
+      "loss": 0.0046,
+      "step": 99
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 3.983646869659424,
+      "learning_rate": 4.9999999999999996e-05,
+      "loss": 0.1327,
+      "step": 100
+    },
+    {
+      "epoch": 1.0773333333333333,
+      "grad_norm": 7.237143516540527,
+      "learning_rate": 5e-05,
+      "loss": 0.1628,
+      "step": 101
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 24.995555877685547,
+      "learning_rate": 4.9720670391061455e-05,
+      "loss": 0.1324,
+      "step": 102
+    },
+    {
+      "epoch": 1.0986666666666667,
+      "grad_norm": 3.7747557163238525,
+      "learning_rate": 4.944134078212291e-05,
+      "loss": 0.0792,
+      "step": 103
+    },
+    {
+      "epoch": 1.1093333333333333,
+      "grad_norm": 2.0382823944091797,
+      "learning_rate": 4.916201117318436e-05,
+      "loss": 0.0301,
+      "step": 104
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.4077985286712646,
+      "learning_rate": 4.8882681564245814e-05,
+      "loss": 0.0192,
+      "step": 105
+    },
+    {
+      "epoch": 1.1306666666666667,
+      "grad_norm": 2.8298680782318115,
+      "learning_rate": 4.860335195530727e-05,
+      "loss": 0.0947,
+      "step": 106
+    },
+    {
+      "epoch": 1.1413333333333333,
+      "grad_norm": 5.259606838226318,
+      "learning_rate": 4.832402234636872e-05,
+      "loss": 0.0329,
+      "step": 107
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.7519811987876892,
+      "learning_rate": 4.8044692737430166e-05,
+      "loss": 0.0122,
+      "step": 108
+    },
+    {
+      "epoch": 1.1626666666666667,
+      "grad_norm": 8.479069709777832,
+      "learning_rate": 4.7765363128491626e-05,
+      "loss": 0.0726,
+      "step": 109
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 0.757892906665802,
+      "learning_rate": 4.748603351955307e-05,
+      "loss": 0.011,
+      "step": 110
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 3.707771062850952,
+      "learning_rate": 4.7206703910614525e-05,
+      "loss": 0.0517,
+      "step": 111
+    },
+    {
+      "epoch": 1.1946666666666665,
+      "grad_norm": 1.249261498451233,
+      "learning_rate": 4.692737430167598e-05,
+      "loss": 0.0178,
+      "step": 112
+    },
+    {
+      "epoch": 1.2053333333333334,
+      "grad_norm": 0.34927159547805786,
+      "learning_rate": 4.664804469273743e-05,
+      "loss": 0.0076,
+      "step": 113
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.4342691898345947,
+      "learning_rate": 4.6368715083798884e-05,
+      "loss": 0.007,
+      "step": 114
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 0.36366787552833557,
+      "learning_rate": 4.6089385474860336e-05,
+      "loss": 0.0049,
+      "step": 115
+    },
+    {
+      "epoch": 1.2373333333333334,
+      "grad_norm": 0.264613538980484,
+      "learning_rate": 4.581005586592179e-05,
+      "loss": 0.0038,
+      "step": 116
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.22927503287792206,
+      "learning_rate": 4.553072625698324e-05,
+      "loss": 0.0036,
+      "step": 117
+    },
+    {
+      "epoch": 1.2586666666666666,
+      "grad_norm": 0.0749870091676712,
+      "learning_rate": 4.5251396648044695e-05,
+      "loss": 0.0009,
+      "step": 118
+    },
+    {
+      "epoch": 1.2693333333333334,
+      "grad_norm": 0.34930863976478577,
+      "learning_rate": 4.497206703910615e-05,
+      "loss": 0.0019,
+      "step": 119
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.48471134901046753,
+      "learning_rate": 4.4692737430167594e-05,
+      "loss": 0.003,
+      "step": 120
+    },
+    {
+      "epoch": 1.2906666666666666,
+      "grad_norm": 0.17621633410453796,
+      "learning_rate": 4.4413407821229054e-05,
+      "loss": 0.0027,
+      "step": 121
+    },
+    {
+      "epoch": 1.3013333333333335,
+      "grad_norm": 0.15077757835388184,
+      "learning_rate": 4.41340782122905e-05,
+      "loss": 0.0012,
+      "step": 122
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.4124365746974945,
+      "learning_rate": 4.385474860335196e-05,
+      "loss": 0.0006,
+      "step": 123
+    },
+    {
+      "epoch": 1.3226666666666667,
+      "grad_norm": 0.17212143540382385,
+      "learning_rate": 4.3575418994413406e-05,
+      "loss": 0.0004,
+      "step": 124
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.37609782814979553,
+      "learning_rate": 4.3296089385474866e-05,
+      "loss": 0.0014,
+      "step": 125
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 1.3432490825653076,
+      "learning_rate": 4.301675977653631e-05,
+      "loss": 0.0037,
+      "step": 126
+    },
+    {
+      "epoch": 1.3546666666666667,
+      "grad_norm": 0.8700277209281921,
+      "learning_rate": 4.273743016759777e-05,
+      "loss": 0.0032,
+      "step": 127
+    },
+    {
+      "epoch": 1.3653333333333333,
+      "grad_norm": 0.9334002137184143,
+      "learning_rate": 4.245810055865922e-05,
+      "loss": 0.0037,
+      "step": 128
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.708004891872406,
+      "learning_rate": 4.217877094972068e-05,
+      "loss": 0.0037,
+      "step": 129
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 4.463681697845459,
+      "learning_rate": 4.1899441340782123e-05,
+      "loss": 0.0493,
+      "step": 130
+    },
+    {
+      "epoch": 1.3973333333333333,
+      "grad_norm": 6.200061321258545,
+      "learning_rate": 4.1620111731843576e-05,
+      "loss": 0.1214,
+      "step": 131
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 1.0150177478790283,
+      "learning_rate": 4.134078212290503e-05,
+      "loss": 0.007,
+      "step": 132
+    },
+    {
+      "epoch": 1.4186666666666667,
+      "grad_norm": 0.3300838768482208,
+      "learning_rate": 4.106145251396648e-05,
+      "loss": 0.0036,
+      "step": 133
+    },
+    {
+      "epoch": 1.4293333333333333,
+      "grad_norm": 1.5166386365890503,
+      "learning_rate": 4.0782122905027935e-05,
+      "loss": 0.0205,
+      "step": 134
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.33347228169441223,
+      "learning_rate": 4.050279329608939e-05,
+      "loss": 0.0038,
+      "step": 135
+    },
+    {
+      "epoch": 1.4506666666666668,
+      "grad_norm": 0.1739296317100525,
+      "learning_rate": 4.022346368715084e-05,
+      "loss": 0.003,
+      "step": 136
+    },
+    {
+      "epoch": 1.4613333333333334,
+      "grad_norm": 2.0085268020629883,
+      "learning_rate": 3.9944134078212294e-05,
+      "loss": 0.011,
+      "step": 137
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.4423629641532898,
+      "learning_rate": 3.966480446927375e-05,
+      "loss": 0.0049,
+      "step": 138
+    },
+    {
+      "epoch": 1.4826666666666668,
+      "grad_norm": 0.08329877257347107,
+      "learning_rate": 3.93854748603352e-05,
+      "loss": 0.0008,
+      "step": 139
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 0.3476015627384186,
+      "learning_rate": 3.9106145251396646e-05,
+      "loss": 0.0039,
+      "step": 140
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.13725365698337555,
+      "learning_rate": 3.8826815642458106e-05,
+      "loss": 0.002,
+      "step": 141
+    },
+    {
+      "epoch": 1.5146666666666668,
+      "grad_norm": 1.4891648292541504,
+      "learning_rate": 3.854748603351955e-05,
+      "loss": 0.0024,
+      "step": 142
+    },
+    {
+      "epoch": 1.5253333333333332,
+      "grad_norm": 0.17973513901233673,
+      "learning_rate": 3.826815642458101e-05,
+      "loss": 0.0005,
+      "step": 143
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.44285571575164795,
+      "learning_rate": 3.798882681564246e-05,
+      "loss": 0.0015,
+      "step": 144
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 0.04738277941942215,
+      "learning_rate": 3.770949720670392e-05,
+      "loss": 0.0006,
+      "step": 145
+    },
+    {
+      "epoch": 1.5573333333333332,
+      "grad_norm": 0.10860025882720947,
+      "learning_rate": 3.743016759776536e-05,
+      "loss": 0.0026,
+      "step": 146
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.0797608345746994,
+      "learning_rate": 3.715083798882682e-05,
+      "loss": 0.0016,
+      "step": 147
+    },
+    {
+      "epoch": 1.5786666666666667,
+      "grad_norm": 0.10588238388299942,
+      "learning_rate": 3.687150837988827e-05,
+      "loss": 0.0012,
+      "step": 148
+    },
+    {
+      "epoch": 1.5893333333333333,
+      "grad_norm": 0.3855038583278656,
+      "learning_rate": 3.659217877094972e-05,
+      "loss": 0.0005,
+      "step": 149
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.2765641212463379,
+      "learning_rate": 3.6312849162011175e-05,
+      "loss": 0.0004,
+      "step": 150
+    },
+    {
+      "epoch": 1.6106666666666667,
+      "grad_norm": 0.16704051196575165,
+      "learning_rate": 3.603351955307263e-05,
+      "loss": 0.0003,
+      "step": 151
+    },
+    {
+      "epoch": 1.6213333333333333,
+      "grad_norm": 0.2472914755344391,
+      "learning_rate": 3.575418994413408e-05,
+      "loss": 0.0009,
+      "step": 152
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.9229430556297302,
+      "learning_rate": 3.5474860335195534e-05,
+      "loss": 0.0033,
+      "step": 153
+    },
+    {
+      "epoch": 1.6426666666666667,
+      "grad_norm": 4.948991775512695,
+      "learning_rate": 3.519553072625699e-05,
+      "loss": 0.0145,
+      "step": 154
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 7.2115349769592285,
+      "learning_rate": 3.491620111731844e-05,
+      "loss": 0.0138,
+      "step": 155
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.2628196179866791,
+      "learning_rate": 3.463687150837989e-05,
+      "loss": 0.0024,
+      "step": 156
+    },
+    {
+      "epoch": 1.6746666666666665,
+      "grad_norm": 0.207715705037117,
+      "learning_rate": 3.4357541899441345e-05,
+      "loss": 0.0019,
+      "step": 157
+    },
+    {
+      "epoch": 1.6853333333333333,
+      "grad_norm": 0.4124593436717987,
+      "learning_rate": 3.407821229050279e-05,
+      "loss": 0.0036,
+      "step": 158
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.2701805830001831,
+      "learning_rate": 3.3798882681564244e-05,
+      "loss": 0.0011,
+      "step": 159
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 0.1480611115694046,
+      "learning_rate": 3.35195530726257e-05,
+      "loss": 0.0032,
+      "step": 160
+    },
+    {
+      "epoch": 1.7173333333333334,
+      "grad_norm": 0.6081339120864868,
+      "learning_rate": 3.324022346368715e-05,
+      "loss": 0.0043,
+      "step": 161
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.057961639016866684,
+      "learning_rate": 3.29608938547486e-05,
+      "loss": 0.0003,
+      "step": 162
+    },
+    {
+      "epoch": 1.7386666666666666,
+      "grad_norm": 0.7412406206130981,
+      "learning_rate": 3.2681564245810056e-05,
+      "loss": 0.0149,
+      "step": 163
+    },
+    {
+      "epoch": 1.7493333333333334,
+      "grad_norm": 0.37741097807884216,
+      "learning_rate": 3.240223463687151e-05,
+      "loss": 0.002,
+      "step": 164
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.2457031011581421,
+      "learning_rate": 3.212290502793296e-05,
+      "loss": 0.0016,
+      "step": 165
+    },
+    {
+      "epoch": 1.7706666666666666,
+      "grad_norm": 1.1554524898529053,
+      "learning_rate": 3.1843575418994415e-05,
+      "loss": 0.0068,
+      "step": 166
+    },
+    {
+      "epoch": 1.7813333333333334,
+      "grad_norm": 0.3106505572795868,
+      "learning_rate": 3.156424581005587e-05,
+      "loss": 0.0028,
+      "step": 167
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 1.0734516382217407,
+      "learning_rate": 3.128491620111732e-05,
+      "loss": 0.0065,
+      "step": 168
+    },
+    {
+      "epoch": 1.8026666666666666,
+      "grad_norm": 0.19787649810314178,
+      "learning_rate": 3.1005586592178774e-05,
+      "loss": 0.0015,
+      "step": 169
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 0.13204191625118256,
+      "learning_rate": 3.0726256983240227e-05,
+      "loss": 0.0013,
+      "step": 170
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.06732651591300964,
+      "learning_rate": 3.0446927374301676e-05,
+      "loss": 0.001,
+      "step": 171
+    },
+    {
+      "epoch": 1.8346666666666667,
+      "grad_norm": 0.14684773981571198,
+      "learning_rate": 3.0167597765363132e-05,
+      "loss": 0.0016,
+      "step": 172
+    },
+    {
+      "epoch": 1.8453333333333335,
+      "grad_norm": 0.12232063710689545,
+      "learning_rate": 2.9888268156424582e-05,
+      "loss": 0.0009,
+      "step": 173
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.056549813598394394,
+      "learning_rate": 2.9608938547486038e-05,
+      "loss": 0.0008,
+      "step": 174
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.13325779139995575,
+      "learning_rate": 2.9329608938547488e-05,
+      "loss": 0.0021,
+      "step": 175
+    },
+    {
+      "epoch": 1.8773333333333333,
+      "grad_norm": 0.10193920135498047,
+      "learning_rate": 2.9050279329608944e-05,
+      "loss": 0.0006,
+      "step": 176
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.045487429946660995,
+      "learning_rate": 2.8770949720670394e-05,
+      "loss": 0.0002,
+      "step": 177
+    },
+    {
+      "epoch": 1.8986666666666667,
+      "grad_norm": 0.09325730055570602,
+      "learning_rate": 2.8491620111731843e-05,
+      "loss": 0.0019,
+      "step": 178
+    },
+    {
+      "epoch": 1.9093333333333333,
+      "grad_norm": 0.06580926477909088,
+      "learning_rate": 2.82122905027933e-05,
+      "loss": 0.0002,
+      "step": 179
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.11411436647176743,
+      "learning_rate": 2.793296089385475e-05,
+      "loss": 0.0018,
+      "step": 180
+    },
+    {
+      "epoch": 1.9306666666666668,
+      "grad_norm": 0.10508397221565247,
+      "learning_rate": 2.7653631284916205e-05,
+      "loss": 0.0022,
+      "step": 181
+    },
+    {
+      "epoch": 1.9413333333333334,
+      "grad_norm": 0.009333553723990917,
+      "learning_rate": 2.7374301675977655e-05,
+      "loss": 0.0001,
+      "step": 182
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.052240923047065735,
+      "learning_rate": 2.7094972067039108e-05,
+      "loss": 0.0013,
+      "step": 183
+    },
+    {
+      "epoch": 1.9626666666666668,
+      "grad_norm": 0.04163605347275734,
+      "learning_rate": 2.681564245810056e-05,
+      "loss": 0.0002,
+      "step": 184
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 0.00853386614471674,
+      "learning_rate": 2.6536312849162014e-05,
+      "loss": 0.0001,
+      "step": 185
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.04537208378314972,
+      "learning_rate": 2.6256983240223466e-05,
+      "loss": 0.0006,
+      "step": 186
+    },
+    {
+      "epoch": 1.9946666666666668,
+      "grad_norm": 0.03813478350639343,
+      "learning_rate": 2.5977653631284916e-05,
+      "loss": 0.0004,
+      "step": 187
+    },
+    {
+      "epoch": 2.005333333333333,
+      "grad_norm": 0.08562111854553223,
+      "learning_rate": 2.569832402234637e-05,
+      "loss": 0.0021,
+      "step": 188
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.04714489355683327,
+      "learning_rate": 2.5418994413407822e-05,
+      "loss": 0.0007,
+      "step": 189
+    },
+    {
+      "epoch": 2.026666666666667,
+      "grad_norm": 0.1473880261182785,
+      "learning_rate": 2.5139664804469275e-05,
+      "loss": 0.0011,
+      "step": 190
+    },
+    {
+      "epoch": 2.037333333333333,
+      "grad_norm": 0.05946442857384682,
+      "learning_rate": 2.4860335195530728e-05,
+      "loss": 0.0011,
+      "step": 191
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.0025648127775639296,
+      "learning_rate": 2.458100558659218e-05,
+      "loss": 0.0,
+      "step": 192
+    },
+    {
+      "epoch": 2.058666666666667,
+      "grad_norm": 0.0019447746453806758,
+      "learning_rate": 2.4301675977653633e-05,
+      "loss": 0.0,
+      "step": 193
+    },
+    {
+      "epoch": 2.0693333333333332,
+      "grad_norm": 0.14827367663383484,
+      "learning_rate": 2.4022346368715083e-05,
+      "loss": 0.0019,
+      "step": 194
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.10748007893562317,
+      "learning_rate": 2.3743016759776536e-05,
+      "loss": 0.0015,
+      "step": 195
+    },
+    {
+      "epoch": 2.0906666666666665,
+      "grad_norm": 0.040777839720249176,
+      "learning_rate": 2.346368715083799e-05,
+      "loss": 0.0004,
+      "step": 196
+    },
+    {
+      "epoch": 2.1013333333333333,
+      "grad_norm": 0.062052927911281586,
+      "learning_rate": 2.3184357541899442e-05,
+      "loss": 0.0012,
+      "step": 197
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.0032981899566948414,
+      "learning_rate": 2.2905027932960895e-05,
+      "loss": 0.0,
+      "step": 198
+    },
+    {
+      "epoch": 2.1226666666666665,
+      "grad_norm": 0.00853727851063013,
+      "learning_rate": 2.2625698324022348e-05,
+      "loss": 0.0,
+      "step": 199
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.09509293735027313,
+      "learning_rate": 2.2346368715083797e-05,
+      "loss": 0.0011,
+      "step": 200
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.04704827442765236,
+      "learning_rate": 2.206703910614525e-05,
+      "loss": 0.0007,
+      "step": 201
+    },
+    {
+      "epoch": 2.1546666666666665,
+      "grad_norm": 0.028513964265584946,
+      "learning_rate": 2.1787709497206703e-05,
+      "loss": 0.0001,
+      "step": 202
+    },
+    {
+      "epoch": 2.1653333333333333,
+      "grad_norm": 0.061560481786727905,
+      "learning_rate": 2.1508379888268156e-05,
+      "loss": 0.0001,
+      "step": 203
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.08184992522001266,
+      "learning_rate": 2.122905027932961e-05,
+      "loss": 0.0014,
+      "step": 204
+    },
+    {
+      "epoch": 2.1866666666666665,
+      "grad_norm": 0.002128052059561014,
+      "learning_rate": 2.0949720670391062e-05,
+      "loss": 0.0,
+      "step": 205
+    },
+    {
+      "epoch": 2.1973333333333334,
+      "grad_norm": 0.0031687153968960047,
+      "learning_rate": 2.0670391061452515e-05,
+      "loss": 0.0,
+      "step": 206
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.009054739028215408,
+      "learning_rate": 2.0391061452513968e-05,
+      "loss": 0.0,
+      "step": 207
+    },
+    {
+      "epoch": 2.2186666666666666,
+      "grad_norm": 0.002092276234179735,
+      "learning_rate": 2.011173184357542e-05,
+      "loss": 0.0,
+      "step": 208
+    },
+    {
+      "epoch": 2.2293333333333334,
+      "grad_norm": 0.003741280408576131,
+      "learning_rate": 1.9832402234636873e-05,
+      "loss": 0.0,
+      "step": 209
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.060546036809682846,
+      "learning_rate": 1.9553072625698323e-05,
+      "loss": 0.0007,
+      "step": 210
+    },
+    {
+      "epoch": 2.2506666666666666,
+      "grad_norm": 0.035807061940431595,
+      "learning_rate": 1.9273743016759776e-05,
+      "loss": 0.0004,
+      "step": 211
+    },
+    {
+      "epoch": 2.2613333333333334,
+      "grad_norm": 0.006829680409282446,
+      "learning_rate": 1.899441340782123e-05,
+      "loss": 0.0,
+      "step": 212
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.0018316598143428564,
+      "learning_rate": 1.871508379888268e-05,
+      "loss": 0.0,
+      "step": 213
+    },
+    {
+      "epoch": 2.2826666666666666,
+      "grad_norm": 0.09956611692905426,
+      "learning_rate": 1.8435754189944135e-05,
+      "loss": 0.0026,
+      "step": 214
+    },
+    {
+      "epoch": 2.2933333333333334,
+      "grad_norm": 0.0347205325961113,
+      "learning_rate": 1.8156424581005588e-05,
+      "loss": 0.0007,
+      "step": 215
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.2268606573343277,
+      "learning_rate": 1.787709497206704e-05,
+      "loss": 0.0011,
+      "step": 216
+    },
+    {
+      "epoch": 2.3146666666666667,
+      "grad_norm": 0.09836770594120026,
+      "learning_rate": 1.7597765363128493e-05,
+      "loss": 0.0023,
+      "step": 217
+    },
+    {
+      "epoch": 2.3253333333333335,
+      "grad_norm": 0.0021363338455557823,
+      "learning_rate": 1.7318435754189946e-05,
+      "loss": 0.0,
+      "step": 218
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.0013842633925378323,
+      "learning_rate": 1.7039106145251396e-05,
+      "loss": 0.0,
+      "step": 219
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 0.0011928960448130965,
+      "learning_rate": 1.675977653631285e-05,
+      "loss": 0.0,
+      "step": 220
+    },
+    {
+      "epoch": 2.3573333333333335,
+      "grad_norm": 0.058396171778440475,
+      "learning_rate": 1.64804469273743e-05,
+      "loss": 0.001,
+      "step": 221
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.045910343527793884,
+      "learning_rate": 1.6201117318435755e-05,
+      "loss": 0.0007,
+      "step": 222
+    },
+    {
+      "epoch": 2.3786666666666667,
+      "grad_norm": 0.07413648068904877,
+      "learning_rate": 1.5921787709497207e-05,
+      "loss": 0.0018,
+      "step": 223
+    },
+    {
+      "epoch": 2.389333333333333,
+      "grad_norm": 0.005444883834570646,
+      "learning_rate": 1.564245810055866e-05,
+      "loss": 0.0,
+      "step": 224
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.003066364210098982,
+      "learning_rate": 1.5363128491620113e-05,
+      "loss": 0.0,
+      "step": 225
+    },
+    {
+      "epoch": 2.4106666666666667,
+      "grad_norm": 0.004307290073484182,
+      "learning_rate": 1.5083798882681566e-05,
+      "loss": 0.0,
+      "step": 226
+    },
+    {
+      "epoch": 2.421333333333333,
+      "grad_norm": 0.04870031774044037,
+      "learning_rate": 1.4804469273743019e-05,
+      "loss": 0.0008,
+      "step": 227
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.09409874677658081,
+      "learning_rate": 1.4525139664804472e-05,
+      "loss": 0.0009,
+      "step": 228
+    },
+    {
+      "epoch": 2.4426666666666668,
+      "grad_norm": 0.0015114648267626762,
+      "learning_rate": 1.4245810055865922e-05,
+      "loss": 0.0,
+      "step": 229
+    },
+    {
+      "epoch": 2.453333333333333,
+      "grad_norm": 0.07573592662811279,
+      "learning_rate": 1.3966480446927374e-05,
+      "loss": 0.0013,
+      "step": 230
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 0.014647366479039192,
+      "learning_rate": 1.3687150837988827e-05,
+      "loss": 0.0,
+      "step": 231
+    },
+    {
+      "epoch": 2.474666666666667,
+      "grad_norm": 0.042190633714199066,
+      "learning_rate": 1.340782122905028e-05,
+      "loss": 0.0005,
+      "step": 232
+    },
+    {
+      "epoch": 2.485333333333333,
+      "grad_norm": 0.001171190058812499,
+      "learning_rate": 1.3128491620111733e-05,
+      "loss": 0.0,
+      "step": 233
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.04019080847501755,
+      "learning_rate": 1.2849162011173184e-05,
+      "loss": 0.0004,
+      "step": 234
+    },
+    {
+      "epoch": 2.506666666666667,
+      "grad_norm": 0.04044044390320778,
+      "learning_rate": 1.2569832402234637e-05,
+      "loss": 0.0001,
+      "step": 235
+    },
+    {
+      "epoch": 2.517333333333333,
+      "grad_norm": 0.03946372866630554,
+      "learning_rate": 1.229050279329609e-05,
+      "loss": 0.0005,
+      "step": 236
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 0.0030067537445575,
+      "learning_rate": 1.2011173184357542e-05,
+      "loss": 0.0,
+      "step": 237
+    },
+    {
+      "epoch": 2.538666666666667,
+      "grad_norm": 0.040154166519641876,
+      "learning_rate": 1.1731843575418994e-05,
+      "loss": 0.0005,
+      "step": 238
+    },
+    {
+      "epoch": 2.5493333333333332,
+      "grad_norm": 0.0011710107792168856,
+      "learning_rate": 1.1452513966480447e-05,
+      "loss": 0.0,
+      "step": 239
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.043072838336229324,
+      "learning_rate": 1.1173184357541899e-05,
+      "loss": 0.0007,
+      "step": 240
+    },
+    {
+      "epoch": 2.570666666666667,
+      "grad_norm": 0.05513829365372658,
+      "learning_rate": 1.0893854748603351e-05,
+      "loss": 0.0011,
+      "step": 241
+    },
+    {
+      "epoch": 2.5813333333333333,
+      "grad_norm": 0.06224875524640083,
+      "learning_rate": 1.0614525139664804e-05,
+      "loss": 0.0009,
+      "step": 242
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.0010548674035817385,
+      "learning_rate": 1.0335195530726257e-05,
+      "loss": 0.0,
+      "step": 243
+    },
+    {
+      "epoch": 2.602666666666667,
+      "grad_norm": 0.049961354583501816,
+      "learning_rate": 1.005586592178771e-05,
+      "loss": 0.0004,
+      "step": 244
+    },
+    {
+      "epoch": 2.6133333333333333,
+      "grad_norm": 0.0009676855988800526,
+      "learning_rate": 9.776536312849161e-06,
+      "loss": 0.0,
+      "step": 245
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.0006135951261967421,
+      "learning_rate": 9.497206703910614e-06,
+      "loss": 0.0,
+      "step": 246
+    },
+    {
+      "epoch": 2.634666666666667,
+      "grad_norm": 0.0006113451672717929,
+      "learning_rate": 9.217877094972067e-06,
+      "loss": 0.0,
+      "step": 247
+    },
+    {
+      "epoch": 2.6453333333333333,
+      "grad_norm": 0.006534937769174576,
+      "learning_rate": 8.93854748603352e-06,
+      "loss": 0.0,
+      "step": 248
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 0.0005643428885377944,
+      "learning_rate": 8.659217877094973e-06,
+      "loss": 0.0,
+      "step": 249
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.043145984411239624,
+      "learning_rate": 8.379888268156424e-06,
+      "loss": 0.0004,
+      "step": 250
+    },
+    {
+      "epoch": 2.6773333333333333,
+      "grad_norm": 0.01648752950131893,
+      "learning_rate": 8.100558659217877e-06,
+      "loss": 0.0,
+      "step": 251
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.038292355835437775,
+      "learning_rate": 7.82122905027933e-06,
+      "loss": 0.0004,
+      "step": 252
+    },
+    {
+      "epoch": 2.6986666666666665,
+      "grad_norm": 0.05065096169710159,
+      "learning_rate": 7.541899441340783e-06,
+      "loss": 0.0006,
+      "step": 253
+    },
+    {
+      "epoch": 2.7093333333333334,
+      "grad_norm": 0.19275380671024323,
+      "learning_rate": 7.262569832402236e-06,
+      "loss": 0.0009,
+      "step": 254
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.04189510643482208,
+      "learning_rate": 6.983240223463687e-06,
+      "loss": 0.0005,
+      "step": 255
+    },
+    {
+      "epoch": 2.7306666666666666,
+      "grad_norm": 0.04453021287918091,
+      "learning_rate": 6.70391061452514e-06,
+      "loss": 0.0005,
+      "step": 256
+    },
+    {
+      "epoch": 2.7413333333333334,
+      "grad_norm": 0.03125462681055069,
+      "learning_rate": 6.424581005586592e-06,
+      "loss": 0.0003,
+      "step": 257
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 0.00153979507740587,
+      "learning_rate": 6.145251396648045e-06,
+      "loss": 0.0,
+      "step": 258
+    },
+    {
+      "epoch": 2.7626666666666666,
+      "grad_norm": 0.07148660719394684,
+      "learning_rate": 5.865921787709497e-06,
+      "loss": 0.0013,
+      "step": 259
+    },
+    {
+      "epoch": 2.7733333333333334,
+      "grad_norm": 0.0006887447671033442,
+      "learning_rate": 5.586592178770949e-06,
+      "loss": 0.0,
+      "step": 260
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 0.05413827300071716,
+      "learning_rate": 5.307262569832402e-06,
+      "loss": 0.0011,
+      "step": 261
+    },
+    {
+      "epoch": 2.7946666666666666,
+      "grad_norm": 0.03515135869383812,
+      "learning_rate": 5.027932960893855e-06,
+      "loss": 0.0001,
+      "step": 262
+    },
+    {
+      "epoch": 2.8053333333333335,
+      "grad_norm": 0.07630643993616104,
+      "learning_rate": 4.748603351955307e-06,
+      "loss": 0.0015,
+      "step": 263
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 0.07834295928478241,
+      "learning_rate": 4.46927374301676e-06,
+      "loss": 0.0014,
+      "step": 264
+    },
+    {
+      "epoch": 2.8266666666666667,
+      "grad_norm": 0.0061597335152328014,
+      "learning_rate": 4.189944134078212e-06,
+      "loss": 0.0,
+      "step": 265
+    },
+    {
+      "epoch": 2.8373333333333335,
+      "grad_norm": 0.041175998747348785,
+      "learning_rate": 3.910614525139665e-06,
+      "loss": 0.0001,
+      "step": 266
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 0.024731680750846863,
+      "learning_rate": 3.631284916201118e-06,
+      "loss": 0.0,
+      "step": 267
+    },
+    {
+      "epoch": 2.8586666666666667,
+      "grad_norm": 0.03547237440943718,
+      "learning_rate": 3.35195530726257e-06,
+      "loss": 0.0003,
+      "step": 268
+    },
+    {
+      "epoch": 2.8693333333333335,
+      "grad_norm": 0.058726560324430466,
+      "learning_rate": 3.0726256983240226e-06,
+      "loss": 0.0011,
+      "step": 269
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.0547514446079731,
+      "learning_rate": 2.7932960893854746e-06,
+      "loss": 0.0008,
+      "step": 270
+    },
+    {
+      "epoch": 2.8906666666666667,
+      "grad_norm": 0.06754053384065628,
+      "learning_rate": 2.5139664804469276e-06,
+      "loss": 0.0009,
+      "step": 271
+    },
+    {
+      "epoch": 2.9013333333333335,
+      "grad_norm": 0.001965736271813512,
+      "learning_rate": 2.23463687150838e-06,
+      "loss": 0.0,
+      "step": 272
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 0.032923754304647446,
+      "learning_rate": 1.9553072625698325e-06,
+      "loss": 0.0004,
+      "step": 273
+    },
+    {
+      "epoch": 2.9226666666666667,
+      "grad_norm": 0.07132994383573532,
+      "learning_rate": 1.675977653631285e-06,
+      "loss": 0.0012,
+      "step": 274
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.036451708525419235,
+      "learning_rate": 1.3966480446927373e-06,
+      "loss": 0.0005,
+      "step": 275
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 0.06345955282449722,
+      "learning_rate": 1.11731843575419e-06,
+      "loss": 0.001,
+      "step": 276
+    },
+    {
+      "epoch": 2.9546666666666668,
+      "grad_norm": 0.03317723795771599,
+      "learning_rate": 8.379888268156425e-07,
+      "loss": 0.0003,
+      "step": 277
+    },
+    {
+      "epoch": 2.9653333333333336,
+      "grad_norm": 0.000624113017693162,
+      "learning_rate": 5.58659217877095e-07,
+      "loss": 0.0,
+      "step": 278
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 0.05925130471587181,
+      "learning_rate": 2.793296089385475e-07,
+      "loss": 0.0008,
+      "step": 279
+    },
+    {
+      "epoch": 2.976,
+      "step": 279,
+      "total_flos": 20734602878976.0,
+      "train_loss": 0.015149302822543197,
+      "train_runtime": 44131.8109,
+      "train_samples_per_second": 0.204,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 279,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 20734602878976.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

link-0501-7B/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441eb113534de2ef72842be29417ee27018865e7e79862ff77c0e682a8354cd8
+size 7736