Training in progress, step 2000, checkpoint

checkpoint-2000/config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-2000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

checkpoint-2000/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c1f77bb2b3d7c6c986422d8c87a12adde7aac3a8b819aaf7730b07d5b49f626
+size 4877660776

checkpoint-2000/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b352b8c678ddb684744d02122746c36397fa21e312f90a6a6103fee9de06246b
+size 4932751008

checkpoint-2000/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5f86caabfa1ae8251fee5086c4f6f83228fb47378530885cd853ccca63a944
+size 4330865200

checkpoint-2000/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6293da3a5e1ef8f19980fb9747712dc52fe5d169ca8b1965b39bbca9b9a415b5
+size 1089994880

checkpoint-2000/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"
+  }
+}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:436ac228fea86fd023b0c850f4579e0ddaabe06a57f5d45b2e277a97d9de9b24
+size 12919482

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835f869ea325fd6edf27b48b589309fb66641cb92b45f2fc13d1bb6e8814106c
+size 14244

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382782d862255d071016cff9c6a4b56eed27c6324967e51b062457330841da4d
+size 1064

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005,
+      "grad_norm": 7.65625,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 0.3232,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.71875,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 0.285,
+      "step": 20
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.45e-06,
+      "loss": 0.2412,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.046875,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.2292,
+      "step": 40
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 1.5390625,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.2119,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.4765625,
+      "learning_rate": 2.95e-06,
+      "loss": 0.2054,
+      "step": 60
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 1.6484375,
+      "learning_rate": 3.45e-06,
+      "loss": 0.205,
+      "step": 70
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.15625,
+      "learning_rate": 3.95e-06,
+      "loss": 0.1893,
+      "step": 80
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 1.6875,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.181,
+      "step": 90
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.1015625,
+      "learning_rate": 4.95e-06,
+      "loss": 0.1848,
+      "step": 100
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 2.375,
+      "learning_rate": 5.450000000000001e-06,
+      "loss": 0.1875,
+      "step": 110
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 13.875,
+      "learning_rate": 5.950000000000001e-06,
+      "loss": 0.1799,
+      "step": 120
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 13.4375,
+      "learning_rate": 6.450000000000001e-06,
+      "loss": 0.1806,
+      "step": 130
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 8.625,
+      "learning_rate": 6.95e-06,
+      "loss": 0.1815,
+      "step": 140
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 3.75,
+      "learning_rate": 7.450000000000001e-06,
+      "loss": 0.1918,
+      "step": 150
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.65625,
+      "learning_rate": 7.950000000000002e-06,
+      "loss": 0.1877,
+      "step": 160
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 1.0859375,
+      "learning_rate": 8.45e-06,
+      "loss": 0.1948,
+      "step": 170
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 66.5,
+      "learning_rate": 8.95e-06,
+      "loss": 0.1751,
+      "step": 180
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 106.0,
+      "learning_rate": 9.450000000000001e-06,
+      "loss": 0.1802,
+      "step": 190
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.90625,
+      "learning_rate": 9.950000000000001e-06,
+      "loss": 0.176,
+      "step": 200
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 29.125,
+      "learning_rate": 9.999383162408303e-06,
+      "loss": 0.1758,
+      "step": 210
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 57.5,
+      "learning_rate": 9.997251079708788e-06,
+      "loss": 0.1643,
+      "step": 220
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 48.0,
+      "learning_rate": 9.993596785920932e-06,
+      "loss": 0.163,
+      "step": 230
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 12.9375,
+      "learning_rate": 9.988421394178027e-06,
+      "loss": 0.1813,
+      "step": 240
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.921875,
+      "learning_rate": 9.981726480954532e-06,
+      "loss": 0.1661,
+      "step": 250
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.7109375,
+      "learning_rate": 9.973514085585871e-06,
+      "loss": 0.1708,
+      "step": 260
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 0.6953125,
+      "learning_rate": 9.963786709647228e-06,
+      "loss": 0.1671,
+      "step": 270
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 272.0,
+      "learning_rate": 9.952547316191545e-06,
+      "loss": 0.1554,
+      "step": 280
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 6.90625,
+      "learning_rate": 9.939799328846947e-06,
+      "loss": 0.1525,
+      "step": 290
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.69921875,
+      "learning_rate": 9.92554663077387e-06,
+      "loss": 0.1676,
+      "step": 300
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 36.0,
+      "learning_rate": 9.90979356348222e-06,
+      "loss": 0.1685,
+      "step": 310
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 11.9375,
+      "learning_rate": 9.892544925508894e-06,
+      "loss": 0.1595,
+      "step": 320
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 99.0,
+      "learning_rate": 9.87380597095611e-06,
+      "loss": 0.1662,
+      "step": 330
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 57.5,
+      "learning_rate": 9.853582407890954e-06,
+      "loss": 0.1706,
+      "step": 340
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 25.125,
+      "learning_rate": 9.831880396606649e-06,
+      "loss": 0.1602,
+      "step": 350
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 85.5,
+      "learning_rate": 9.808706547746057e-06,
+      "loss": 0.1659,
+      "step": 360
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 12.9375,
+      "learning_rate": 9.78406792028804e-06,
+      "loss": 0.1559,
+      "step": 370
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 55.5,
+      "learning_rate": 9.757972019397192e-06,
+      "loss": 0.1681,
+      "step": 380
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 0.71484375,
+      "learning_rate": 9.730426794137727e-06,
+      "loss": 0.1666,
+      "step": 390
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.73828125,
+      "learning_rate": 9.701440635052094e-06,
+      "loss": 0.1599,
+      "step": 400
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 0.703125,
+      "learning_rate": 9.671022371605148e-06,
+      "loss": 0.1643,
+      "step": 410
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.671875,
+      "learning_rate": 9.6391812694946e-06,
+      "loss": 0.1482,
+      "step": 420
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 10.9375,
+      "learning_rate": 9.605927027828608e-06,
+      "loss": 0.1483,
+      "step": 430
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 33.75,
+      "learning_rate": 9.571269776171319e-06,
+      "loss": 0.1548,
+      "step": 440
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 6.59375,
+      "learning_rate": 9.535220071457325e-06,
+      "loss": 0.1401,
+      "step": 450
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 20.625,
+      "learning_rate": 9.497788894775903e-06,
+      "loss": 0.1427,
+      "step": 460
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 6.03125,
+      "learning_rate": 9.458987648026071e-06,
+      "loss": 0.1464,
+      "step": 470
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.703125,
+      "learning_rate": 9.418828150443469e-06,
+      "loss": 0.1409,
+      "step": 480
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 0.734375,
+      "learning_rate": 9.37732263500009e-06,
+      "loss": 0.1522,
+      "step": 490
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.6640625,
+      "learning_rate": 9.334483744678015e-06,
+      "loss": 0.1586,
+      "step": 500
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 0.73046875,
+      "learning_rate": 9.290324528618225e-06,
+      "loss": 0.1518,
+      "step": 510
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.375,
+      "learning_rate": 9.244858438145709e-06,
+      "loss": 0.1648,
+      "step": 520
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 2.21875,
+      "learning_rate": 9.198099322672066e-06,
+      "loss": 0.1529,
+      "step": 530
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 25.625,
+      "learning_rate": 9.150061425476839e-06,
+      "loss": 0.1521,
+      "step": 540
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 22.5,
+      "learning_rate": 9.100759379368863e-06,
+      "loss": 0.1612,
+      "step": 550
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.050208202228981e-06,
+      "loss": 0.171,
+      "step": 560
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 225.0,
+      "learning_rate": 8.998423292435455e-06,
+      "loss": 0.1437,
+      "step": 570
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 6.40625,
+      "learning_rate": 8.945420424173455e-06,
+      "loss": 0.1524,
+      "step": 580
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 13.4375,
+      "learning_rate": 8.891215742630106e-06,
+      "loss": 0.1257,
+      "step": 590
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.09375,
+      "learning_rate": 8.8358257590765e-06,
+      "loss": 0.1348,
+      "step": 600
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 48.5,
+      "learning_rate": 8.779267345838198e-06,
+      "loss": 0.1396,
+      "step": 610
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.5703125,
+      "learning_rate": 8.72155773115577e-06,
+      "loss": 0.1345,
+      "step": 620
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 0.796875,
+      "learning_rate": 8.662714493936895e-06,
+      "loss": 0.1675,
+      "step": 630
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.62109375,
+      "learning_rate": 8.602755558401653e-06,
+      "loss": 0.1451,
+      "step": 640
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.734375,
+      "learning_rate": 8.541699188622645e-06,
+      "loss": 0.1328,
+      "step": 650
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 80.5,
+      "learning_rate": 8.479563982961572e-06,
+      "loss": 0.1443,
+      "step": 660
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 2.75,
+      "learning_rate": 8.416368868403997e-06,
+      "loss": 0.1348,
+      "step": 670
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 40.0,
+      "learning_rate": 8.352133094793996e-06,
+      "loss": 0.1315,
+      "step": 680
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 31.0,
+      "learning_rate": 8.28687622897048e-06,
+      "loss": 0.1359,
+      "step": 690
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.70703125,
+      "learning_rate": 8.220618148806934e-06,
+      "loss": 0.145,
+      "step": 700
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 7.5625,
+      "learning_rate": 8.153379037156433e-06,
+      "loss": 0.1619,
+      "step": 710
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.9140625,
+      "learning_rate": 8.085179375703745e-06,
+      "loss": 0.1393,
+      "step": 720
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 14.0625,
+      "learning_rate": 8.016039938726413e-06,
+      "loss": 0.1495,
+      "step": 730
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.640625,
+      "learning_rate": 7.945981786766712e-06,
+      "loss": 0.1356,
+      "step": 740
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.6953125,
+      "learning_rate": 7.875026260216395e-06,
+      "loss": 0.1548,
+      "step": 750
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.296875,
+      "learning_rate": 7.80319497281621e-06,
+      "loss": 0.1436,
+      "step": 760
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 0.6875,
+      "learning_rate": 7.730509805072146e-06,
+      "loss": 0.1369,
+      "step": 770
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.60546875,
+      "learning_rate": 7.656992897590416e-06,
+      "loss": 0.1196,
+      "step": 780
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 0.65234375,
+      "learning_rate": 7.58266664433321e-06,
+      "loss": 0.1295,
+      "step": 790
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 44.0,
+      "learning_rate": 7.507553685797288e-06,
+      "loss": 0.1048,
+      "step": 800
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 3.109375,
+      "learning_rate": 7.431676902117453e-06,
+      "loss": 0.1345,
+      "step": 810
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.40625,
+      "learning_rate": 7.35505940609705e-06,
+      "loss": 0.1286,
+      "step": 820
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 0.59765625,
+      "learning_rate": 7.2777245361675786e-06,
+      "loss": 0.1197,
+      "step": 830
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.62890625,
+      "learning_rate": 7.199695849279576e-06,
+      "loss": 0.1242,
+      "step": 840
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 12.5625,
+      "learning_rate": 7.120997113726951e-06,
+      "loss": 0.1275,
+      "step": 850
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.73046875,
+      "learning_rate": 7.041652301906925e-06,
+      "loss": 0.1331,
+      "step": 860
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 0.62109375,
+      "learning_rate": 6.961685583017808e-06,
+      "loss": 0.1286,
+      "step": 870
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.5625,
+      "learning_rate": 6.881121315696828e-06,
+      "loss": 0.1348,
+      "step": 880
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 278.0,
+      "learning_rate": 6.799984040600257e-06,
+      "loss": 0.1358,
+      "step": 890
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 4.3125,
+      "learning_rate": 6.718298472928082e-06,
+      "loss": 0.127,
+      "step": 900
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 0.63671875,
+      "learning_rate": 6.63608949489552e-06,
+      "loss": 0.1317,
+      "step": 910
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 184.0,
+      "learning_rate": 6.55338214815366e-06,
+      "loss": 0.1283,
+      "step": 920
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 7.125,
+      "learning_rate": 6.47020162616152e-06,
+      "loss": 0.1306,
+      "step": 930
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.65234375,
+      "learning_rate": 6.386573266511891e-06,
+      "loss": 0.1369,
+      "step": 940
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.59375,
+      "learning_rate": 6.3025225432132434e-06,
+      "loss": 0.109,
+      "step": 950
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.671875,
+      "learning_rate": 6.218075058930113e-06,
+      "loss": 0.1213,
+      "step": 960
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 2.203125,
+      "learning_rate": 6.133256537184276e-06,
+      "loss": 0.1237,
+      "step": 970
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.66796875,
+      "learning_rate": 6.048092814519109e-06,
+      "loss": 0.1121,
+      "step": 980
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 2.90625,
+      "learning_rate": 5.962609832629538e-06,
+      "loss": 0.1065,
+      "step": 990
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 11.5,
+      "learning_rate": 5.876833630459936e-06,
+      "loss": 0.1054,
+      "step": 1000
+    },
+    {
+      "epoch": 0.505,
+      "grad_norm": 1208.0,
+      "learning_rate": 5.7907903362724195e-06,
+      "loss": 0.1123,
+      "step": 1010
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.66015625,
+      "learning_rate": 5.704506159687914e-06,
+      "loss": 0.1317,
+      "step": 1020
+    },
+    {
+      "epoch": 0.515,
+      "grad_norm": 0.69921875,
+      "learning_rate": 5.618007383702464e-06,
+      "loss": 0.1168,
+      "step": 1030
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.5390625,
+      "learning_rate": 5.5313203566811666e-06,
+      "loss": 0.1157,
+      "step": 1040
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.6171875,
+      "learning_rate": 5.4444714843322085e-06,
+      "loss": 0.1085,
+      "step": 1050
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.68359375,
+      "learning_rate": 5.35748722166343e-06,
+      "loss": 0.1309,
+      "step": 1060
+    },
+    {
+      "epoch": 0.535,
+      "grad_norm": 1064.0,
+      "learning_rate": 5.270394064923878e-06,
+      "loss": 0.1137,
+      "step": 1070
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.56640625,
+      "learning_rate": 5.183218543532782e-06,
+      "loss": 0.1291,
+      "step": 1080
+    },
+    {
+      "epoch": 0.545,
+      "grad_norm": 1.34375,
+      "learning_rate": 5.09598721199845e-06,
+      "loss": 0.1225,
+      "step": 1090
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1744.0,
+      "learning_rate": 5.008726641829492e-06,
+      "loss": 0.1157,
+      "step": 1100
+    },
+    {
+      "epoch": 0.555,
+      "grad_norm": 0.6015625,
+      "learning_rate": 4.921463413440898e-06,
+      "loss": 0.1181,
+      "step": 1110
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.5078125,
+      "learning_rate": 4.8342241080573696e-06,
+      "loss": 0.1171,
+      "step": 1120
+    },
+    {
+      "epoch": 0.565,
+      "grad_norm": 0.796875,
+      "learning_rate": 4.747035299616434e-06,
+      "loss": 0.1225,
+      "step": 1130
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.41796875,
+      "learning_rate": 4.659923546673761e-06,
+      "loss": 0.1147,
+      "step": 1140
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.390625,
+      "learning_rate": 4.572915384313163e-06,
+      "loss": 0.0917,
+      "step": 1150
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.59375,
+      "learning_rate": 4.4860373160637665e-06,
+      "loss": 0.1165,
+      "step": 1160
+    },
+    {
+      "epoch": 0.585,
+      "grad_norm": 0.423828125,
+      "learning_rate": 4.399315805826765e-06,
+      "loss": 0.1047,
+      "step": 1170
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.8046875,
+      "learning_rate": 4.312777269814268e-06,
+      "loss": 0.107,
+      "step": 1180
+    },
+    {
+      "epoch": 0.595,
+      "grad_norm": 0.42578125,
+      "learning_rate": 4.226448068502661e-06,
+      "loss": 0.0948,
+      "step": 1190
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 45.5,
+      "learning_rate": 4.140354498602952e-06,
+      "loss": 0.105,
+      "step": 1200
+    },
+    {
+      "epoch": 0.605,
+      "grad_norm": 0.61328125,
+      "learning_rate": 4.054522785050543e-06,
+      "loss": 0.1044,
+      "step": 1210
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.40625,
+      "learning_rate": 3.968979073016853e-06,
+      "loss": 0.1084,
+      "step": 1220
+    },
+    {
+      "epoch": 0.615,
+      "grad_norm": 0.60546875,
+      "learning_rate": 3.883749419945244e-06,
+      "loss": 0.1227,
+      "step": 1230
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.458984375,
+      "learning_rate": 3.798859787613682e-06,
+      "loss": 0.1048,
+      "step": 1240
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.58203125,
+      "learning_rate": 3.7143360342265206e-06,
+      "loss": 0.1101,
+      "step": 1250
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.5390625,
+      "learning_rate": 3.630203906537838e-06,
+      "loss": 0.1292,
+      "step": 1260
+    },
+    {
+      "epoch": 0.635,
+      "grad_norm": 0.54296875,
+      "learning_rate": 3.5464890320087374e-06,
+      "loss": 0.113,
+      "step": 1270
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.625,
+      "learning_rate": 3.463216911000965e-06,
+      "loss": 0.1209,
+      "step": 1280
+    },
+    {
+      "epoch": 0.645,
+      "grad_norm": 0.53515625,
+      "learning_rate": 3.3804129090092542e-06,
+      "loss": 0.1129,
+      "step": 1290
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.5234375,
+      "learning_rate": 3.2981022489347503e-06,
+      "loss": 0.0997,
+      "step": 1300
+    },
+    {
+      "epoch": 0.655,
+      "grad_norm": 0.44140625,
+      "learning_rate": 3.2163100034018735e-06,
+      "loss": 0.1102,
+      "step": 1310
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.58984375,
+      "learning_rate": 3.1350610871209553e-06,
+      "loss": 0.1036,
+      "step": 1320
+    },
+    {
+      "epoch": 0.665,
+      "grad_norm": 1232.0,
+      "learning_rate": 3.0543802492989693e-06,
+      "loss": 0.1196,
+      "step": 1330
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.42578125,
+      "learning_rate": 2.974292066100688e-06,
+      "loss": 0.0981,
+      "step": 1340
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.39453125,
+      "learning_rate": 2.8948209331625454e-06,
+      "loss": 0.0964,
+      "step": 1350
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.4375,
+      "learning_rate": 2.8159910581614904e-06,
+      "loss": 0.1111,
+      "step": 1360
+    },
+    {
+      "epoch": 0.685,
+      "grad_norm": 0.419921875,
+      "learning_rate": 2.7378264534410865e-06,
+      "loss": 0.121,
+      "step": 1370
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.53125,
+      "learning_rate": 2.6603509286971342e-06,
+      "loss": 0.1113,
+      "step": 1380
+    },
+    {
+      "epoch": 0.695,
+      "grad_norm": 0.5078125,
+      "learning_rate": 2.5835880837249884e-06,
+      "loss": 0.1156,
+      "step": 1390
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.5234375,
+      "learning_rate": 2.507561301230849e-06,
+      "loss": 0.1158,
+      "step": 1400
+    },
+    {
+      "epoch": 0.705,
+      "grad_norm": 0.5546875,
+      "learning_rate": 2.432293739709151e-06,
+      "loss": 0.1078,
+      "step": 1410
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.458984375,
+      "learning_rate": 2.357808326388265e-06,
+      "loss": 0.1191,
+      "step": 1420
+    },
+    {
+      "epoch": 0.715,
+      "grad_norm": 1272.0,
+      "learning_rate": 2.284127750246646e-06,
+      "loss": 0.1097,
+      "step": 1430
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.45703125,
+      "learning_rate": 2.2112744551015496e-06,
+      "loss": 0.0934,
+      "step": 1440
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.416015625,
+      "learning_rate": 2.13927063277242e-06,
+      "loss": 0.108,
+      "step": 1450
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.474609375,
+      "learning_rate": 2.0681382163210533e-06,
+      "loss": 0.1103,
+      "step": 1460
+    },
+    {
+      "epoch": 0.735,
+      "grad_norm": 25.375,
+      "learning_rate": 1.9978988733705807e-06,
+      "loss": 0.1024,
+      "step": 1470
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.4765625,
+      "learning_rate": 1.928573999505284e-06,
+      "loss": 0.1053,
+      "step": 1480
+    },
+    {
+      "epoch": 0.745,
+      "grad_norm": 0.3828125,
+      "learning_rate": 1.8601847117533112e-06,
+      "loss": 0.0983,
+      "step": 1490
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.404296875,
+      "learning_rate": 1.7927518421542106e-06,
+      "loss": 0.112,
+      "step": 1500
+    },
+    {
+      "epoch": 0.755,
+      "grad_norm": 20.0,
+      "learning_rate": 1.7262959314133015e-06,
+      "loss": 0.1054,
+      "step": 1510
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.451171875,
+      "learning_rate": 1.6608372226447678e-06,
+      "loss": 0.1233,
+      "step": 1520
+    },
+    {
+      "epoch": 0.765,
+      "grad_norm": 0.57421875,
+      "learning_rate": 1.596395655205411e-06,
+      "loss": 0.1035,
+      "step": 1530
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.45703125,
+      "learning_rate": 1.5329908586209347e-06,
+      "loss": 0.1088,
+      "step": 1540
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.4375,
+      "learning_rate": 1.4706421466065952e-06,
+      "loss": 0.0909,
+      "step": 1550
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.4921875,
+      "learning_rate": 1.4093685111840567e-06,
+      "loss": 0.1082,
+      "step": 1560
+    },
+    {
+      "epoch": 0.785,
+      "grad_norm": 0.51953125,
+      "learning_rate": 1.349188616896238e-06,
+      "loss": 0.1099,
+      "step": 1570
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.4453125,
+      "learning_rate": 1.2901207951219186e-06,
+      "loss": 0.1093,
+      "step": 1580
+    },
+    {
+      "epoch": 0.795,
+      "grad_norm": 0.439453125,
+      "learning_rate": 1.2321830384918116e-06,
+      "loss": 0.1081,
+      "step": 1590
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.470703125,
+      "learning_rate": 1.1753929954078414e-06,
+      "loss": 0.0944,
+      "step": 1600
+    },
+    {
+      "epoch": 0.805,
+      "grad_norm": 0.44140625,
+      "learning_rate": 1.1197679646672698e-06,
+      "loss": 0.1087,
+      "step": 1610
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.3828125,
+      "learning_rate": 1.065324890193314e-06,
+      "loss": 0.1035,
+      "step": 1620
+    },
+    {
+      "epoch": 0.815,
+      "grad_norm": 0.37109375,
+      "learning_rate": 1.0120803558738585e-06,
+      "loss": 0.1019,
+      "step": 1630
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.4453125,
+      "learning_rate": 9.600505805098486e-07,
+      "loss": 0.1028,
+      "step": 1640
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.447265625,
+      "learning_rate": 9.09251412874882e-07,
+      "loss": 0.123,
+      "step": 1650
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.4375,
+      "learning_rate": 8.596983268875281e-07,
+      "loss": 0.1013,
+      "step": 1660
+    },
+    {
+      "epoch": 0.835,
+      "grad_norm": 0.484375,
+      "learning_rate": 8.114064168978064e-07,
+      "loss": 0.1039,
+      "step": 1670
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.48828125,
+      "learning_rate": 7.643903930893154e-07,
+      "loss": 0.1038,
+      "step": 1680
+    },
+    {
+      "epoch": 0.845,
+      "grad_norm": 0.45703125,
+      "learning_rate": 7.186645769983591e-07,
+      "loss": 0.0997,
+      "step": 1690
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.33203125,
+      "learning_rate": 6.742428971514786e-07,
+      "loss": 0.1018,
+      "step": 1700
+    },
+    {
+      "epoch": 0.855,
+      "grad_norm": 0.4375,
+      "learning_rate": 6.311388848226741e-07,
+      "loss": 0.1103,
+      "step": 1710
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.42578125,
+      "learning_rate": 5.893656699116618e-07,
+      "loss": 0.1045,
+      "step": 1720
+    },
+    {
+      "epoch": 0.865,
+      "grad_norm": 0.431640625,
+      "learning_rate": 5.489359769443675e-07,
+      "loss": 0.1129,
+      "step": 1730
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.546875,
+      "learning_rate": 5.098621211969224e-07,
+      "loss": 0.1161,
+      "step": 1740
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.345703125,
+      "learning_rate": 4.72156004944303e-07,
+      "loss": 0.1061,
+      "step": 1750
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.376953125,
+      "learning_rate": 4.3582911383478646e-07,
+      "loss": 0.1022,
+      "step": 1760
+    },
+    {
+      "epoch": 0.885,
+      "grad_norm": 0.546875,
+      "learning_rate": 4.0089251339131164e-07,
+      "loss": 0.109,
+      "step": 1770
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 6.6875,
+      "learning_rate": 3.6735684564081385e-07,
+      "loss": 0.1044,
+      "step": 1780
+    },
+    {
+      "epoch": 0.895,
+      "grad_norm": 0.412109375,
+      "learning_rate": 3.352323258725554e-07,
+      "loss": 0.103,
+      "step": 1790
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.41796875,
+      "learning_rate": 3.0452873952645455e-07,
+      "loss": 0.1174,
+      "step": 1800
+    },
+    {
+      "epoch": 0.905,
+      "grad_norm": 2.3125,
+      "learning_rate": 2.752554392123463e-07,
+      "loss": 0.1116,
+      "step": 1810
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.447265625,
+      "learning_rate": 2.474213418610816e-07,
+      "loss": 0.1121,
+      "step": 1820
+    },
+    {
+      "epoch": 0.915,
+      "grad_norm": 6.21875,
+      "learning_rate": 2.210349260083494e-07,
+      "loss": 0.11,
+      "step": 1830
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.453125,
+      "learning_rate": 1.961042292120291e-07,
+      "loss": 0.1096,
+      "step": 1840
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 1096.0,
+      "learning_rate": 1.7263684560387518e-07,
+      "loss": 0.1173,
+      "step": 1850
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.515625,
+      "learning_rate": 1.5063992357626623e-07,
+      "loss": 0.1093,
+      "step": 1860
+    },
+    {
+      "epoch": 0.935,
+      "grad_norm": 0.64453125,
+      "learning_rate": 1.3012016360474223e-07,
+      "loss": 0.1025,
+      "step": 1870
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.421875,
+      "learning_rate": 1.1108381620696885e-07,
+      "loss": 0.1176,
+      "step": 1880
+    },
+    {
+      "epoch": 0.945,
+      "grad_norm": 0.41796875,
+      "learning_rate": 9.353668003877437e-08,
+      "loss": 0.1005,
+      "step": 1890
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.44140625,
+      "learning_rate": 7.748410012781705e-08,
+      "loss": 0.1127,
+      "step": 1900
+    },
+    {
+      "epoch": 0.955,
+      "grad_norm": 0.384765625,
+      "learning_rate": 6.293096624544304e-08,
+      "loss": 0.0938,
+      "step": 1910
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.45703125,
+      "learning_rate": 4.988171141721232e-08,
+      "loss": 0.1102,
+      "step": 1920
+    },
+    {
+      "epoch": 0.965,
+      "grad_norm": 0.31640625,
+      "learning_rate": 3.83403105725566e-08,
+      "loss": 0.0989,
+      "step": 1930
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.52734375,
+      "learning_rate": 2.8310279333976786e-08,
+      "loss": 0.1033,
+      "step": 1940
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 0.408203125,
+      "learning_rate": 1.9794672946152337e-08,
+      "loss": 0.0999,
+      "step": 1950
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.48828125,
+      "learning_rate": 1.2796085345280207e-08,
+      "loss": 0.1143,
+      "step": 1960
+    },
+    {
+      "epoch": 0.985,
+      "grad_norm": 740.0,
+      "learning_rate": 7.3166483689413035e-09,
+      "loss": 0.11,
+      "step": 1970
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.44921875,
+      "learning_rate": 3.3580311067188396e-09,
+      "loss": 0.1156,
+      "step": 1980
+    },
+    {
+      "epoch": 0.995,
+      "grad_norm": 77.5,
+      "learning_rate": 9.214393917789111e-10,
+      "loss": 0.11,
+      "step": 1990
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.46875,
+      "learning_rate": 7.615433561536379e-12,
+      "loss": 0.1143,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1121122028290048e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96fc1b9e41755c428b70ff1df5e8f77cbd574a671d04b46017e38fb8d8027c8d
+size 5304