Training in progress, step 2500, checkpoint

.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
+checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-2500/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
+}

checkpoint-2500/config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-2500/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": "4.51.3"
+}

checkpoint-2500/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082eddb6584ed097dd0195f6ac834e6ed24c507ddc029a4b18e462ea1c7db73c
+size 4957560304

checkpoint-2500/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eefeab5718e5d0291126deafe43ce51c7637b9ef2b90d81581baca214eabc552
+size 1214366696

checkpoint-2500/model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 6171877376
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97bad4a787c70bbfe080c8aab47f1074f1b7799ee40e8d7a4cee97dc4df05d13
+size 9384243

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdf0878306dfabad22df73aa5835c9e34d3f3302f1c21c247c88f8c2ea4fd50f
+size 14244

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d944f5855dedd93de5810fb83351c896ba8bcf8ae6abf8ac51fb2013da8b6d
+size 1064

checkpoint-2500/special_tokens_map.json

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

checkpoint-2500/tokenizer.json

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

checkpoint-2500/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2500/trainer_state.json

@@ -0,0 +1,1784 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004,
+      "grad_norm": 54.75,
+      "learning_rate": 7.2e-07,
+      "loss": 13.3473,
+      "step": 10
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 65.0,
+      "learning_rate": 1.52e-06,
+      "loss": 13.3436,
+      "step": 20
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 57.0,
+      "learning_rate": 2.3200000000000002e-06,
+      "loss": 13.2209,
+      "step": 30
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 58.0,
+      "learning_rate": 3.12e-06,
+      "loss": 13.1524,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 59.0,
+      "learning_rate": 3.920000000000001e-06,
+      "loss": 12.7597,
+      "step": 50
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 80.5,
+      "learning_rate": 4.7200000000000005e-06,
+      "loss": 12.78,
+      "step": 60
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 64.5,
+      "learning_rate": 5.5200000000000005e-06,
+      "loss": 12.5047,
+      "step": 70
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 72.5,
+      "learning_rate": 6.3200000000000005e-06,
+      "loss": 12.1863,
+      "step": 80
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 58.0,
+      "learning_rate": 7.1200000000000004e-06,
+      "loss": 12.0318,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 57.25,
+      "learning_rate": 7.92e-06,
+      "loss": 11.5564,
+      "step": 100
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 47.0,
+      "learning_rate": 8.720000000000001e-06,
+      "loss": 11.5071,
+      "step": 110
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 40.5,
+      "learning_rate": 9.52e-06,
+      "loss": 10.9574,
+      "step": 120
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 41.5,
+      "learning_rate": 1.0320000000000001e-05,
+      "loss": 10.7984,
+      "step": 130
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 39.0,
+      "learning_rate": 1.1120000000000002e-05,
+      "loss": 10.665,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 57.25,
+      "learning_rate": 1.1920000000000001e-05,
+      "loss": 10.3269,
+      "step": 150
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 21.5,
+      "learning_rate": 1.2720000000000002e-05,
+      "loss": 10.2163,
+      "step": 160
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 58.25,
+      "learning_rate": 1.3520000000000003e-05,
+      "loss": 10.1014,
+      "step": 170
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 27.875,
+      "learning_rate": 1.432e-05,
+      "loss": 9.5063,
+      "step": 180
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 30.5,
+      "learning_rate": 1.5120000000000001e-05,
+      "loss": 9.6283,
+      "step": 190
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 27.5,
+      "learning_rate": 1.5920000000000003e-05,
+      "loss": 9.6242,
+      "step": 200
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 28.0,
+      "learning_rate": 1.672e-05,
+      "loss": 9.5881,
+      "step": 210
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 56.75,
+      "learning_rate": 1.752e-05,
+      "loss": 9.3942,
+      "step": 220
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 28.75,
+      "learning_rate": 1.832e-05,
+      "loss": 9.0517,
+      "step": 230
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 42.75,
+      "learning_rate": 1.912e-05,
+      "loss": 9.1673,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 43.25,
+      "learning_rate": 1.9920000000000002e-05,
+      "loss": 8.6786,
+      "step": 250
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 35.75,
+      "learning_rate": 1.9999210442038164e-05,
+      "loss": 8.981,
+      "step": 260
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 19.125,
+      "learning_rate": 1.9996481265944146e-05,
+      "loss": 8.7596,
+      "step": 270
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 28.0,
+      "learning_rate": 1.9991803256020393e-05,
+      "loss": 8.6905,
+      "step": 280
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 37.25,
+      "learning_rate": 1.99851773242542e-05,
+      "loss": 8.5464,
+      "step": 290
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 26.5,
+      "learning_rate": 1.99766047623841e-05,
+      "loss": 8.5164,
+      "step": 300
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 29.875,
+      "learning_rate": 1.996608724164801e-05,
+      "loss": 8.4347,
+      "step": 310
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 30.375,
+      "learning_rate": 1.995362681245744e-05,
+      "loss": 8.1998,
+      "step": 320
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 27.0,
+      "learning_rate": 1.9939225903997748e-05,
+      "loss": 8.3628,
+      "step": 330
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 22.75,
+      "learning_rate": 1.992288732375458e-05,
+      "loss": 8.0026,
+      "step": 340
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 28.0,
+      "learning_rate": 1.9904614256966514e-05,
+      "loss": 8.1026,
+      "step": 350
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 25.125,
+      "learning_rate": 1.9884410266004134e-05,
+      "loss": 7.7991,
+      "step": 360
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 33.0,
+      "learning_rate": 1.986227928967551e-05,
+      "loss": 7.9716,
+      "step": 370
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 29.375,
+      "learning_rate": 1.983822564245833e-05,
+      "loss": 7.7902,
+      "step": 380
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 21.875,
+      "learning_rate": 1.981225401365877e-05,
+      "loss": 7.6093,
+      "step": 390
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 28.0,
+      "learning_rate": 1.9784369466497333e-05,
+      "loss": 7.6624,
+      "step": 400
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 23.25,
+      "learning_rate": 1.9754577437121733e-05,
+      "loss": 7.8131,
+      "step": 410
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 27.75,
+      "learning_rate": 1.9722883733547128e-05,
+      "loss": 7.7623,
+      "step": 420
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 20.375,
+      "learning_rate": 1.968929453452383e-05,
+      "loss": 7.6954,
+      "step": 430
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 25.125,
+      "learning_rate": 1.965381638833274e-05,
+      "loss": 7.6341,
+      "step": 440
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 31.25,
+      "learning_rate": 1.9616456211508756e-05,
+      "loss": 7.759,
+      "step": 450
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 29.125,
+      "learning_rate": 1.9577221287492368e-05,
+      "loss": 7.6304,
+      "step": 460
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 29.625,
+      "learning_rate": 1.9536119265209763e-05,
+      "loss": 7.3878,
+      "step": 470
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 19.875,
+      "learning_rate": 1.9493158157581617e-05,
+      "loss": 7.175,
+      "step": 480
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 21.625,
+      "learning_rate": 1.9448346339960984e-05,
+      "loss": 7.3158,
+      "step": 490
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 21.375,
+      "learning_rate": 1.9401692548500504e-05,
+      "loss": 7.1866,
+      "step": 500
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 22.875,
+      "learning_rate": 1.935320587844926e-05,
+      "loss": 7.2426,
+      "step": 510
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 23.0,
+      "learning_rate": 1.9302895782379648e-05,
+      "loss": 7.2151,
+      "step": 520
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 18.125,
+      "learning_rate": 1.925077206834458e-05,
+      "loss": 7.1319,
+      "step": 530
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 26.0,
+      "learning_rate": 1.9196844897965393e-05,
+      "loss": 7.2889,
+      "step": 540
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 17.875,
+      "learning_rate": 1.914112478445079e-05,
+      "loss": 7.1092,
+      "step": 550
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 28.5,
+      "learning_rate": 1.9083622590547313e-05,
+      "loss": 7.3018,
+      "step": 560
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 27.375,
+      "learning_rate": 1.9024349526421596e-05,
+      "loss": 7.1044,
+      "step": 570
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 23.5,
+      "learning_rate": 1.896331714747493e-05,
+      "loss": 7.2433,
+      "step": 580
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 22.625,
+      "learning_rate": 1.8900537352090523e-05,
+      "loss": 6.9127,
+      "step": 590
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 29.75,
+      "learning_rate": 1.8836022379313884e-05,
+      "loss": 7.0044,
+      "step": 600
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 23.625,
+      "learning_rate": 1.8769784806466768e-05,
+      "loss": 6.7093,
+      "step": 610
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 18.875,
+      "learning_rate": 1.870183754669526e-05,
+      "loss": 6.7646,
+      "step": 620
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 20.5,
+      "learning_rate": 1.863219384645227e-05,
+      "loss": 6.8328,
+      "step": 630
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 27.75,
+      "learning_rate": 1.8560867282915164e-05,
+      "loss": 6.7888,
+      "step": 640
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 20.25,
+      "learning_rate": 1.848787176133882e-05,
+      "loss": 6.8189,
+      "step": 650
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 28.125,
+      "learning_rate": 1.8413221512344805e-05,
+      "loss": 6.8333,
+      "step": 660
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 20.0,
+      "learning_rate": 1.8336931089147076e-05,
+      "loss": 6.6808,
+      "step": 670
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 18.625,
+      "learning_rate": 1.8259015364714786e-05,
+      "loss": 6.6521,
+      "step": 680
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 22.75,
+      "learning_rate": 1.8179489528872808e-05,
+      "loss": 6.7383,
+      "step": 690
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 25.125,
+      "learning_rate": 1.80983690853404e-05,
+      "loss": 6.77,
+      "step": 700
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 26.875,
+      "learning_rate": 1.8015669848708768e-05,
+      "loss": 6.7929,
+      "step": 710
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 23.375,
+      "learning_rate": 1.793140794135795e-05,
+      "loss": 6.7116,
+      "step": 720
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 23.125,
+      "learning_rate": 1.7845599790313735e-05,
+      "loss": 6.5916,
+      "step": 730
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 21.125,
+      "learning_rate": 1.7758262124045195e-05,
+      "loss": 6.6243,
+      "step": 740
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 19.625,
+      "learning_rate": 1.7669411969203417e-05,
+      "loss": 6.6006,
+      "step": 750
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 28.25,
+      "learning_rate": 1.7579066647302134e-05,
+      "loss": 6.5745,
+      "step": 760
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 16.0,
+      "learning_rate": 1.7487243771340862e-05,
+      "loss": 6.4531,
+      "step": 770
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 20.875,
+      "learning_rate": 1.7393961242371203e-05,
+      "loss": 6.5237,
+      "step": 780
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 15.9375,
+      "learning_rate": 1.7299237246007018e-05,
+      "loss": 6.3753,
+      "step": 790
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 18.875,
+      "learning_rate": 1.720309024887907e-05,
+      "loss": 6.419,
+      "step": 800
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 20.875,
+      "learning_rate": 1.710553899503496e-05,
+      "loss": 6.3493,
+      "step": 810
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 20.625,
+      "learning_rate": 1.700660250228492e-05,
+      "loss": 6.376,
+      "step": 820
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 18.375,
+      "learning_rate": 1.690630005849423e-05,
+      "loss": 6.471,
+      "step": 830
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 15.1875,
+      "learning_rate": 1.6804651217823055e-05,
+      "loss": 6.43,
+      "step": 840
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 15.875,
+      "learning_rate": 1.6701675796914284e-05,
+      "loss": 6.2644,
+      "step": 850
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 18.125,
+      "learning_rate": 1.6597393871030264e-05,
+      "loss": 6.2126,
+      "step": 860
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 19.75,
+      "learning_rate": 1.649182577013906e-05,
+      "loss": 6.3967,
+      "step": 870
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 25.5,
+      "learning_rate": 1.6384992074951124e-05,
+      "loss": 6.2047,
+      "step": 880
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 23.75,
+      "learning_rate": 1.6276913612907005e-05,
+      "loss": 6.4128,
+      "step": 890
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 43.75,
+      "learning_rate": 1.6167611454117027e-05,
+      "loss": 6.1328,
+      "step": 900
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 19.625,
+      "learning_rate": 1.6057106907253617e-05,
+      "loss": 6.2045,
+      "step": 910
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 18.75,
+      "learning_rate": 1.5945421515397135e-05,
+      "loss": 6.1914,
+      "step": 920
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 26.125,
+      "learning_rate": 1.5832577051836016e-05,
+      "loss": 6.3516,
+      "step": 930
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 20.375,
+      "learning_rate": 1.5718595515822027e-05,
+      "loss": 6.2091,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 19.75,
+      "learning_rate": 1.5603499128281447e-05,
+      "loss": 6.148,
+      "step": 950
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 18.0,
+      "learning_rate": 1.5487310327483087e-05,
+      "loss": 6.0491,
+      "step": 960
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 14.1875,
+      "learning_rate": 1.5370051764663872e-05,
+      "loss": 6.2801,
+      "step": 970
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 14.0,
+      "learning_rate": 1.5251746299612959e-05,
+      "loss": 6.1509,
+      "step": 980
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 17.25,
+      "learning_rate": 1.5132416996215171e-05,
+      "loss": 6.1506,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 21.625,
+      "learning_rate": 1.5012087117954643e-05,
+      "loss": 6.1863,
+      "step": 1000
+    },
+    {
+      "epoch": 0.404,
+      "grad_norm": 22.875,
+      "learning_rate": 1.4890780123379565e-05,
+      "loss": 6.1573,
+      "step": 1010
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 18.375,
+      "learning_rate": 1.4768519661528879e-05,
+      "loss": 6.0607,
+      "step": 1020
+    },
+    {
+      "epoch": 0.412,
+      "grad_norm": 20.0,
+      "learning_rate": 1.464532956732188e-05,
+      "loss": 6.1736,
+      "step": 1030
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 14.375,
+      "learning_rate": 1.4521233856911507e-05,
+      "loss": 6.0672,
+      "step": 1040
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 13.9375,
+      "learning_rate": 1.43962567230024e-05,
+      "loss": 5.7487,
+      "step": 1050
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 14.375,
+      "learning_rate": 1.4270422530134433e-05,
+      "loss": 6.0476,
+      "step": 1060
+    },
+    {
+      "epoch": 0.428,
+      "grad_norm": 15.0625,
+      "learning_rate": 1.4143755809932843e-05,
+      "loss": 6.1103,
+      "step": 1070
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 13.5,
+      "learning_rate": 1.4016281256325702e-05,
+      "loss": 5.907,
+      "step": 1080
+    },
+    {
+      "epoch": 0.436,
+      "grad_norm": 14.875,
+      "learning_rate": 1.388802372072981e-05,
+      "loss": 5.9089,
+      "step": 1090
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 15.625,
+      "learning_rate": 1.3759008207205869e-05,
+      "loss": 5.9699,
+      "step": 1100
+    },
+    {
+      "epoch": 0.444,
+      "grad_norm": 20.0,
+      "learning_rate": 1.3629259867583864e-05,
+      "loss": 5.7375,
+      "step": 1110
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 14.6875,
+      "learning_rate": 1.349880399655969e-05,
+      "loss": 5.9555,
+      "step": 1120
+    },
+    {
+      "epoch": 0.452,
+      "grad_norm": 18.125,
+      "learning_rate": 1.3367666026763884e-05,
+      "loss": 5.986,
+      "step": 1130
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 19.125,
+      "learning_rate": 1.3235871523803496e-05,
+      "loss": 5.896,
+      "step": 1140
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 14.125,
+      "learning_rate": 1.3103446181278015e-05,
+      "loss": 5.8373,
+      "step": 1150
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 14.125,
+      "learning_rate": 1.297041581577035e-05,
+      "loss": 5.8646,
+      "step": 1160
+    },
+    {
+      "epoch": 0.468,
+      "grad_norm": 17.25,
+      "learning_rate": 1.2836806361813846e-05,
+      "loss": 5.8566,
+      "step": 1170
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 21.75,
+      "learning_rate": 1.270264386683628e-05,
+      "loss": 5.6326,
+      "step": 1180
+    },
+    {
+      "epoch": 0.476,
+      "grad_norm": 14.375,
+      "learning_rate": 1.256795448608188e-05,
+      "loss": 5.7247,
+      "step": 1190
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 15.875,
+      "learning_rate": 1.2432764477512294e-05,
+      "loss": 5.6694,
+      "step": 1200
+    },
+    {
+      "epoch": 0.484,
+      "grad_norm": 16.25,
+      "learning_rate": 1.2297100196687557e-05,
+      "loss": 5.8965,
+      "step": 1210
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 14.3125,
+      "learning_rate": 1.2160988091628023e-05,
+      "loss": 5.6092,
+      "step": 1220
+    },
+    {
+      "epoch": 0.492,
+      "grad_norm": 15.25,
+      "learning_rate": 1.202445469765826e-05,
+      "loss": 5.6918,
+      "step": 1230
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 14.0,
+      "learning_rate": 1.1887526632233954e-05,
+      "loss": 5.8349,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 15.25,
+      "learning_rate": 1.1750230589752763e-05,
+      "loss": 5.8349,
+      "step": 1250
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 15.25,
+      "learning_rate": 1.1612593336350209e-05,
+      "loss": 5.6769,
+      "step": 1260
+    },
+    {
+      "epoch": 0.508,
+      "grad_norm": 16.875,
+      "learning_rate": 1.1474641704681551e-05,
+      "loss": 5.6439,
+      "step": 1270
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 12.6875,
+      "learning_rate": 1.1336402588690727e-05,
+      "loss": 5.653,
+      "step": 1280
+    },
+    {
+      "epoch": 0.516,
+      "grad_norm": 13.5,
+      "learning_rate": 1.1197902938367297e-05,
+      "loss": 5.5384,
+      "step": 1290
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 17.25,
+      "learning_rate": 1.105916975449252e-05,
+      "loss": 5.5844,
+      "step": 1300
+    },
+    {
+      "epoch": 0.524,
+      "grad_norm": 15.5625,
+      "learning_rate": 1.0920230083375474e-05,
+      "loss": 5.7039,
+      "step": 1310
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 14.75,
+      "learning_rate": 1.0781111011580336e-05,
+      "loss": 5.8199,
+      "step": 1320
+    },
+    {
+      "epoch": 0.532,
+      "grad_norm": 13.875,
+      "learning_rate": 1.0641839660645806e-05,
+      "loss": 5.6763,
+      "step": 1330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 14.125,
+      "learning_rate": 1.0502443181797696e-05,
+      "loss": 5.6979,
+      "step": 1340
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 15.5625,
+      "learning_rate": 1.036294875065576e-05,
+      "loss": 5.6108,
+      "step": 1350
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 14.5,
+      "learning_rate": 1.0223383561935738e-05,
+      "loss": 5.6434,
+      "step": 1360
+    },
+    {
+      "epoch": 0.548,
+      "grad_norm": 12.3125,
+      "learning_rate": 1.0083774824147707e-05,
+      "loss": 5.5022,
+      "step": 1370
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 22.875,
+      "learning_rate": 9.944149754291719e-06,
+      "loss": 5.6792,
+      "step": 1380
+    },
+    {
+      "epoch": 0.556,
+      "grad_norm": 15.1875,
+      "learning_rate": 9.80453557255179e-06,
+      "loss": 5.6344,
+      "step": 1390
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 13.5,
+      "learning_rate": 9.664959496989286e-06,
+      "loss": 5.5327,
+      "step": 1400
+    },
+    {
+      "epoch": 0.564,
+      "grad_norm": 13.125,
+      "learning_rate": 9.525448738236691e-06,
+      "loss": 5.477,
+      "step": 1410
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 12.625,
+      "learning_rate": 9.386030494192847e-06,
+      "loss": 5.5999,
+      "step": 1420
+    },
+    {
+      "epoch": 0.572,
+      "grad_norm": 15.875,
+      "learning_rate": 9.246731944720675e-06,
+      "loss": 5.6199,
+      "step": 1430
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 15.25,
+      "learning_rate": 9.107580246348395e-06,
+      "loss": 5.5676,
+      "step": 1440
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 12.25,
+      "learning_rate": 8.968602526975329e-06,
+      "loss": 5.4793,
+      "step": 1450
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 14.0,
+      "learning_rate": 8.829825880583228e-06,
+      "loss": 5.5789,
+      "step": 1460
+    },
+    {
+      "epoch": 0.588,
+      "grad_norm": 14.125,
+      "learning_rate": 8.69127736195428e-06,
+      "loss": 5.5571,
+      "step": 1470
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 14.1875,
+      "learning_rate": 8.552983981396709e-06,
+      "loss": 5.5194,
+      "step": 1480
+    },
+    {
+      "epoch": 0.596,
+      "grad_norm": 14.0,
+      "learning_rate": 8.414972699479076e-06,
+      "loss": 5.5605,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 13.375,
+      "learning_rate": 8.277270421774234e-06,
+      "loss": 5.4973,
+      "step": 1500
+    },
+    {
+      "epoch": 0.604,
+      "grad_norm": 15.6875,
+      "learning_rate": 8.139903993614069e-06,
+      "loss": 5.6634,
+      "step": 1510
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 15.625,
+      "learning_rate": 8.00290019485593e-06,
+      "loss": 5.6461,
+      "step": 1520
+    },
+    {
+      "epoch": 0.612,
+      "grad_norm": 13.6875,
+      "learning_rate": 7.866285734661842e-06,
+      "loss": 5.7029,
+      "step": 1530
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 15.1875,
+      "learning_rate": 7.730087246291503e-06,
+      "loss": 5.6841,
+      "step": 1540
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 13.8125,
+      "learning_rate": 7.594331281910082e-06,
+      "loss": 5.6831,
+      "step": 1550
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 13.3125,
+      "learning_rate": 7.4590443074118325e-06,
+      "loss": 5.6429,
+      "step": 1560
+    },
+    {
+      "epoch": 0.628,
+      "grad_norm": 12.1875,
+      "learning_rate": 7.324252697260475e-06,
+      "loss": 5.6396,
+      "step": 1570
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 14.125,
+      "learning_rate": 7.189982729347491e-06,
+      "loss": 5.7249,
+      "step": 1580
+    },
+    {
+      "epoch": 0.636,
+      "grad_norm": 14.25,
+      "learning_rate": 7.056260579869165e-06,
+      "loss": 5.6366,
+      "step": 1590
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 12.3125,
+      "learning_rate": 6.923112318223497e-06,
+      "loss": 5.5417,
+      "step": 1600
+    },
+    {
+      "epoch": 0.644,
+      "grad_norm": 14.625,
+      "learning_rate": 6.790563901927907e-06,
+      "loss": 5.5896,
+      "step": 1610
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 14.75,
+      "learning_rate": 6.658641171558785e-06,
+      "loss": 5.8033,
+      "step": 1620
+    },
+    {
+      "epoch": 0.652,
+      "grad_norm": 13.5,
+      "learning_rate": 6.52736984571381e-06,
+      "loss": 5.6251,
+      "step": 1630
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 15.375,
+      "learning_rate": 6.396775515998055e-06,
+      "loss": 5.5814,
+      "step": 1640
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 16.125,
+      "learning_rate": 6.2668836420348535e-06,
+      "loss": 5.5373,
+      "step": 1650
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 14.5,
+      "learning_rate": 6.137719546502401e-06,
+      "loss": 5.4405,
+      "step": 1660
+    },
+    {
+      "epoch": 0.668,
+      "grad_norm": 13.5625,
+      "learning_rate": 6.009308410197048e-06,
+      "loss": 5.5314,
+      "step": 1670
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 13.625,
+      "learning_rate": 5.881675267124254e-06,
+      "loss": 5.5082,
+      "step": 1680
+    },
+    {
+      "epoch": 0.676,
+      "grad_norm": 12.3125,
+      "learning_rate": 5.754844999618144e-06,
+      "loss": 5.5669,
+      "step": 1690
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 12.5,
+      "learning_rate": 5.628842333490674e-06,
+      "loss": 5.4605,
+      "step": 1700
+    },
+    {
+      "epoch": 0.684,
+      "grad_norm": 13.375,
+      "learning_rate": 5.50369183321126e-06,
+      "loss": 5.5224,
+      "step": 1710
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 12.5625,
+      "learning_rate": 5.379417897117917e-06,
+      "loss": 5.5977,
+      "step": 1720
+    },
+    {
+      "epoch": 0.692,
+      "grad_norm": 11.75,
+      "learning_rate": 5.256044752660709e-06,
+      "loss": 5.6513,
+      "step": 1730
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 16.375,
+      "learning_rate": 5.133596451678603e-06,
+      "loss": 5.6258,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 13.375,
+      "learning_rate": 5.012096865710494e-06,
+      "loss": 5.6574,
+      "step": 1750
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 12.9375,
+      "learning_rate": 4.891569681341403e-06,
+      "loss": 5.5567,
+      "step": 1760
+    },
+    {
+      "epoch": 0.708,
+      "grad_norm": 10.8125,
+      "learning_rate": 4.772038395584735e-06,
+      "loss": 5.438,
+      "step": 1770
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 13.0625,
+      "learning_rate": 4.6535263113014885e-06,
+      "loss": 5.3993,
+      "step": 1780
+    },
+    {
+      "epoch": 0.716,
+      "grad_norm": 15.25,
+      "learning_rate": 4.53605653265731e-06,
+      "loss": 5.7265,
+      "step": 1790
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 18.0,
+      "learning_rate": 4.419651960618302e-06,
+      "loss": 5.5694,
+      "step": 1800
+    },
+    {
+      "epoch": 0.724,
+      "grad_norm": 13.0,
+      "learning_rate": 4.304335288486426e-06,
+      "loss": 5.3722,
+      "step": 1810
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 12.1875,
+      "learning_rate": 4.190128997475402e-06,
+      "loss": 5.555,
+      "step": 1820
+    },
+    {
+      "epoch": 0.732,
+      "grad_norm": 12.0,
+      "learning_rate": 4.0770553523279535e-06,
+      "loss": 5.5382,
+      "step": 1830
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 13.8125,
+      "learning_rate": 3.965136396975235e-06,
+      "loss": 5.6195,
+      "step": 1840
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 12.5625,
+      "learning_rate": 3.854393950239356e-06,
+      "loss": 5.5777,
+      "step": 1850
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 14.375,
+      "learning_rate": 3.7448496015797296e-06,
+      "loss": 5.5992,
+      "step": 1860
+    },
+    {
+      "epoch": 0.748,
+      "grad_norm": 14.9375,
+      "learning_rate": 3.636524706884181e-06,
+      "loss": 5.5852,
+      "step": 1870
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 13.0625,
+      "learning_rate": 3.5294403843055604e-06,
+      "loss": 5.5306,
+      "step": 1880
+    },
+    {
+      "epoch": 0.756,
+      "grad_norm": 19.375,
+      "learning_rate": 3.4236175101447265e-06,
+      "loss": 5.6253,
+      "step": 1890
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 13.25,
+      "learning_rate": 3.3190767147806825e-06,
+      "loss": 5.6067,
+      "step": 1900
+    },
+    {
+      "epoch": 0.764,
+      "grad_norm": 12.5625,
+      "learning_rate": 3.2158383786486204e-06,
+      "loss": 5.4635,
+      "step": 1910
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 13.5625,
+      "learning_rate": 3.113922628266718e-06,
+      "loss": 5.5343,
+      "step": 1920
+    },
+    {
+      "epoch": 0.772,
+      "grad_norm": 13.375,
+      "learning_rate": 3.013349332312451e-06,
+      "loss": 5.5415,
+      "step": 1930
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 12.9375,
+      "learning_rate": 2.9141380977491373e-06,
+      "loss": 5.4654,
+      "step": 1940
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 15.1875,
+      "learning_rate": 2.816308266003541e-06,
+      "loss": 5.7947,
+      "step": 1950
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 12.1875,
+      "learning_rate": 2.7198789091951903e-06,
+      "loss": 5.5924,
+      "step": 1960
+    },
+    {
+      "epoch": 0.788,
+      "grad_norm": 16.5,
+      "learning_rate": 2.624868826418262e-06,
+      "loss": 5.5665,
+      "step": 1970
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 11.75,
+      "learning_rate": 2.5312965400766475e-06,
+      "loss": 5.6325,
+      "step": 1980
+    },
+    {
+      "epoch": 0.796,
+      "grad_norm": 15.375,
+      "learning_rate": 2.4391802922729703e-06,
+      "loss": 5.5853,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 13.9375,
+      "learning_rate": 2.3485380412522586e-06,
+      "loss": 5.529,
+      "step": 2000
+    },
+    {
+      "epoch": 0.804,
+      "grad_norm": 11.3125,
+      "learning_rate": 2.259387457900948e-06,
+      "loss": 5.3686,
+      "step": 2010
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 12.3125,
+      "learning_rate": 2.171745922301903e-06,
+      "loss": 5.6398,
+      "step": 2020
+    },
+    {
+      "epoch": 0.812,
+      "grad_norm": 12.5625,
+      "learning_rate": 2.0856305203461436e-06,
+      "loss": 5.6724,
+      "step": 2030
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 12.0,
+      "learning_rate": 2.0010580404019066e-06,
+      "loss": 5.4096,
+      "step": 2040
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 14.5,
+      "learning_rate": 1.918044970041729e-06,
+      "loss": 5.5648,
+      "step": 2050
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 11.875,
+      "learning_rate": 1.8366074928281608e-06,
+      "loss": 5.4581,
+      "step": 2060
+    },
+    {
+      "epoch": 0.828,
+      "grad_norm": 13.3125,
+      "learning_rate": 1.7567614851587444e-06,
+      "loss": 5.5112,
+      "step": 2070
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 14.125,
+      "learning_rate": 1.6785225131708749e-06,
+      "loss": 5.5498,
+      "step": 2080
+    },
+    {
+      "epoch": 0.836,
+      "grad_norm": 12.375,
+      "learning_rate": 1.601905829707171e-06,
+      "loss": 5.6644,
+      "step": 2090
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 11.9375,
+      "learning_rate": 1.526926371341878e-06,
+      "loss": 5.6666,
+      "step": 2100
+    },
+    {
+      "epoch": 0.844,
+      "grad_norm": 13.25,
+      "learning_rate": 1.4535987554689712e-06,
+      "loss": 5.6801,
+      "step": 2110
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 13.8125,
+      "learning_rate": 1.381937277452451e-06,
+      "loss": 5.4535,
+      "step": 2120
+    },
+    {
+      "epoch": 0.852,
+      "grad_norm": 12.25,
+      "learning_rate": 1.3119559078394462e-06,
+      "loss": 5.5883,
+      "step": 2130
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 15.0625,
+      "learning_rate": 1.2436682896366282e-06,
+      "loss": 5.48,
+      "step": 2140
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 16.75,
+      "learning_rate": 1.1770877356504684e-06,
+      "loss": 5.6772,
+      "step": 2150
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 11.6875,
+      "learning_rate": 1.1122272258918864e-06,
+      "loss": 5.5312,
+      "step": 2160
+    },
+    {
+      "epoch": 0.868,
+      "grad_norm": 14.375,
+      "learning_rate": 1.0490994050457748e-06,
+      "loss": 5.5698,
+      "step": 2170
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 15.9375,
+      "learning_rate": 9.877165800058874e-07,
+      "loss": 5.5503,
+      "step": 2180
+    },
+    {
+      "epoch": 0.876,
+      "grad_norm": 14.5625,
+      "learning_rate": 9.280907174755916e-07,
+      "loss": 5.7086,
+      "step": 2190
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 12.4375,
+      "learning_rate": 8.702334416349279e-07,
+      "loss": 5.7326,
+      "step": 2200
+    },
+    {
+      "epoch": 0.884,
+      "grad_norm": 11.9375,
+      "learning_rate": 8.141560318744601e-07,
+      "loss": 5.6012,
+      "step": 2210
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 12.25,
+      "learning_rate": 7.598694205963331e-07,
+      "loss": 5.4755,
+      "step": 2220
+    },
+    {
+      "epoch": 0.892,
+      "grad_norm": 12.8125,
+      "learning_rate": 7.073841910829771e-07,
+      "loss": 5.6836,
+      "step": 2230
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 15.8125,
+      "learning_rate": 6.567105754338798e-07,
+      "loss": 5.6414,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 17.0,
+      "learning_rate": 6.078584525708175e-07,
+      "loss": 5.402,
+      "step": 2250
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 13.25,
+      "learning_rate": 5.608373463119354e-07,
+      "loss": 5.6034,
+      "step": 2260
+    },
+    {
+      "epoch": 0.908,
+      "grad_norm": 13.8125,
+      "learning_rate": 5.156564235150686e-07,
+      "loss": 5.5214,
+      "step": 2270
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 15.4375,
+      "learning_rate": 4.723244922906356e-07,
+      "loss": 5.7135,
+      "step": 2280
+    },
+    {
+      "epoch": 0.916,
+      "grad_norm": 14.1875,
+      "learning_rate": 4.308500002844862e-07,
+      "loss": 5.5808,
+      "step": 2290
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 13.6875,
+      "learning_rate": 3.912410330310157e-07,
+      "loss": 5.6566,
+      "step": 2300
+    },
+    {
+      "epoch": 0.924,
+      "grad_norm": 13.9375,
+      "learning_rate": 3.5350531237686723e-07,
+      "loss": 5.6426,
+      "step": 2310
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 12.8125,
+      "learning_rate": 3.1765019497555617e-07,
+      "loss": 5.5883,
+      "step": 2320
+    },
+    {
+      "epoch": 0.932,
+      "grad_norm": 12.9375,
+      "learning_rate": 2.836826708532603e-07,
+      "loss": 5.5928,
+      "step": 2330
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 12.1875,
+      "learning_rate": 2.516093620461124e-07,
+      "loss": 5.5457,
+      "step": 2340
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 13.6875,
+      "learning_rate": 2.214365213092118e-07,
+      "loss": 5.4391,
+      "step": 2350
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 13.0625,
+      "learning_rate": 1.9317003089764365e-07,
+      "loss": 5.4379,
+      "step": 2360
+    },
+    {
+      "epoch": 0.948,
+      "grad_norm": 11.875,
+      "learning_rate": 1.668154014197243e-07,
+      "loss": 5.441,
+      "step": 2370
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 11.25,
+      "learning_rate": 1.4237777076268723e-07,
+      "loss": 5.473,
+      "step": 2380
+    },
+    {
+      "epoch": 0.956,
+      "grad_norm": 12.6875,
+      "learning_rate": 1.1986190309104861e-07,
+      "loss": 5.571,
+      "step": 2390
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 14.25,
+      "learning_rate": 9.9272187917826e-08,
+      "loss": 5.6245,
+      "step": 2400
+    },
+    {
+      "epoch": 0.964,
+      "grad_norm": 11.875,
+      "learning_rate": 8.061263924878604e-08,
+      "loss": 5.4666,
+      "step": 2410
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 12.1875,
+      "learning_rate": 6.388689479991606e-08,
+      "loss": 5.4966,
+      "step": 2420
+    },
+    {
+      "epoch": 0.972,
+      "grad_norm": 11.1875,
+      "learning_rate": 4.9098215288235776e-08,
+      "loss": 5.6736,
+      "step": 2430
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 12.25,
+      "learning_rate": 3.6249483796116924e-08,
+      "loss": 5.5797,
+      "step": 2440
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 12.375,
+      "learning_rate": 2.5343205209225062e-08,
+      "loss": 5.564,
+      "step": 2450
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 13.0,
+      "learning_rate": 1.6381505728176872e-08,
+      "loss": 5.5886,
+      "step": 2460
+    },
+    {
+      "epoch": 0.988,
+      "grad_norm": 13.0625,
+      "learning_rate": 9.366132454046162e-09,
+      "loss": 5.6782,
+      "step": 2470
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 14.9375,
+      "learning_rate": 4.298453047749674e-09,
+      "loss": 5.5379,
+      "step": 2480
+    },
+    {
+      "epoch": 0.996,
+      "grad_norm": 11.75,
+      "learning_rate": 1.1794554634314558e-09,
+      "loss": 5.5883,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.125,
+      "learning_rate": 9.74775584916543e-12,
+      "loss": 5.4554,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 2500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3638567985152e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:762155c8e1e0d93ca8dda9683224aa9c91cb9e3a7c83499848661bec470eebc2
+size 5368