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 sha256:98fe32d49dbce641074c4b99593cf7c6be1e3b51ae3163aa4a8deaea40385836
+size 4877660776

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce7fc8917fc0b2d5030401dc15e69f9945286aa50a36b961cd5cf786f4d5455
+size 4932751008

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4501713fa01b7285abe58e4803bb617c9063f6ff434063a1c398eb62654ab279
+size 4330865200

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7107b36e2b3ed4ac74a9e2d74eac82e061e78e8454a0ca6e27d9d680c41c80ad
+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 sha256:8a3fcb7a7103993c508712eef6f5ed7e7b87ea1de7e6f403988fdc83f752acfc
+size 12919482

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964771ea4d152605618c22273abbcef8154a9735e5ca07daff1650a42df501c8
+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": 3.2125,
+  "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": 904.0,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 6.5545,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 912.0,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 6.5618,
+      "step": 20
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 944.0,
+      "learning_rate": 1.45e-06,
+      "loss": 6.4784,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1016.0,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 6.3282,
+      "step": 40
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 1232.0,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 6.1435,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1672.0,
+      "learning_rate": 2.95e-06,
+      "loss": 6.3152,
+      "step": 60
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 2320.0,
+      "learning_rate": 3.45e-06,
+      "loss": 6.3598,
+      "step": 70
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2080.0,
+      "learning_rate": 3.95e-06,
+      "loss": 5.9706,
+      "step": 80
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 2832.0,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 4.3504,
+      "step": 90
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 960.0,
+      "learning_rate": 4.95e-06,
+      "loss": 2.1286,
+      "step": 100
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 1200.0,
+      "learning_rate": 5.450000000000001e-06,
+      "loss": 1.6138,
+      "step": 110
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 432.0,
+      "learning_rate": 5.950000000000001e-06,
+      "loss": 1.3234,
+      "step": 120
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 69.0,
+      "learning_rate": 6.450000000000001e-06,
+      "loss": 1.1945,
+      "step": 130
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4224.0,
+      "learning_rate": 6.95e-06,
+      "loss": 1.2613,
+      "step": 140
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 712.0,
+      "learning_rate": 7.450000000000001e-06,
+      "loss": 1.4642,
+      "step": 150
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 42496.0,
+      "learning_rate": 7.950000000000002e-06,
+      "loss": 1.7337,
+      "step": 160
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 2432.0,
+      "learning_rate": 8.45e-06,
+      "loss": 0.3436,
+      "step": 170
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 5248.0,
+      "learning_rate": 8.95e-06,
+      "loss": 0.4058,
+      "step": 180
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 15.375,
+      "learning_rate": 9.450000000000001e-06,
+      "loss": 0.2938,
+      "step": 190
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 19.875,
+      "learning_rate": 9.950000000000001e-06,
+      "loss": 0.2518,
+      "step": 200
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 4.1875,
+      "learning_rate": 9.999383162408303e-06,
+      "loss": 0.364,
+      "step": 210
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2096.0,
+      "learning_rate": 9.997251079708788e-06,
+      "loss": 0.2952,
+      "step": 220
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 1712.0,
+      "learning_rate": 9.993596785920932e-06,
+      "loss": 0.314,
+      "step": 230
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 14.0625,
+      "learning_rate": 9.988421394178027e-06,
+      "loss": 0.2486,
+      "step": 240
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 378.0,
+      "learning_rate": 9.981726480954532e-06,
+      "loss": 0.2512,
+      "step": 250
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 24.875,
+      "learning_rate": 9.973514085585871e-06,
+      "loss": 0.2496,
+      "step": 260
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 9.75,
+      "learning_rate": 9.963786709647228e-06,
+      "loss": 0.2458,
+      "step": 270
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 82.5,
+      "learning_rate": 9.952547316191545e-06,
+      "loss": 0.2497,
+      "step": 280
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 55.75,
+      "learning_rate": 9.939799328846947e-06,
+      "loss": 0.2545,
+      "step": 290
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 14.4375,
+      "learning_rate": 9.92554663077387e-06,
+      "loss": 0.2487,
+      "step": 300
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 50.75,
+      "learning_rate": 9.90979356348222e-06,
+      "loss": 0.2444,
+      "step": 310
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 11.375,
+      "learning_rate": 9.892544925508894e-06,
+      "loss": 0.2371,
+      "step": 320
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 66.0,
+      "learning_rate": 9.87380597095611e-06,
+      "loss": 0.2388,
+      "step": 330
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 139.0,
+      "learning_rate": 9.853582407890954e-06,
+      "loss": 0.2471,
+      "step": 340
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 1784.0,
+      "learning_rate": 9.831880396606649e-06,
+      "loss": 0.2951,
+      "step": 350
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.1875,
+      "learning_rate": 9.808706547746057e-06,
+      "loss": 0.8401,
+      "step": 360
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 2624.0,
+      "learning_rate": 9.78406792028804e-06,
+      "loss": 0.4471,
+      "step": 370
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 8.5,
+      "learning_rate": 9.757972019397192e-06,
+      "loss": 0.2911,
+      "step": 380
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 5504.0,
+      "learning_rate": 9.730426794137727e-06,
+      "loss": 0.4079,
+      "step": 390
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5696.0,
+      "learning_rate": 9.701440635052094e-06,
+      "loss": 0.4635,
+      "step": 400
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 5408.0,
+      "learning_rate": 9.671022371605148e-06,
+      "loss": 0.3101,
+      "step": 410
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 74.0,
+      "learning_rate": 9.6391812694946e-06,
+      "loss": 0.3079,
+      "step": 420
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 352.0,
+      "learning_rate": 9.605927027828608e-06,
+      "loss": 0.2892,
+      "step": 430
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 24.25,
+      "learning_rate": 9.571269776171319e-06,
+      "loss": 0.2703,
+      "step": 440
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 16640.0,
+      "learning_rate": 9.535220071457325e-06,
+      "loss": 0.2782,
+      "step": 450
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 22.5,
+      "learning_rate": 9.497788894775903e-06,
+      "loss": 0.2908,
+      "step": 460
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 37.5,
+      "learning_rate": 9.458987648026071e-06,
+      "loss": 0.2667,
+      "step": 470
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 55.0,
+      "learning_rate": 9.418828150443469e-06,
+      "loss": 0.256,
+      "step": 480
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 30.0,
+      "learning_rate": 9.37732263500009e-06,
+      "loss": 0.2418,
+      "step": 490
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4256.0,
+      "learning_rate": 9.334483744678015e-06,
+      "loss": 0.2442,
+      "step": 500
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 0.79296875,
+      "learning_rate": 9.290324528618225e-06,
+      "loss": 0.2417,
+      "step": 510
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 74.0,
+      "learning_rate": 9.244858438145709e-06,
+      "loss": 0.2357,
+      "step": 520
+    },
+    {
+      "epoch": 1.0025,
+      "grad_norm": 38.0,
+      "learning_rate": 9.198099322672066e-06,
+      "loss": 0.3075,
+      "step": 530
+    },
+    {
+      "epoch": 1.0075,
+      "grad_norm": 2.171875,
+      "learning_rate": 9.150061425476839e-06,
+      "loss": 0.2534,
+      "step": 540
+    },
+    {
+      "epoch": 1.0125,
+      "grad_norm": 10.625,
+      "learning_rate": 9.100759379368863e-06,
+      "loss": 0.25,
+      "step": 550
+    },
+    {
+      "epoch": 1.0175,
+      "grad_norm": 2.921875,
+      "learning_rate": 9.050208202228981e-06,
+      "loss": 0.2437,
+      "step": 560
+    },
+    {
+      "epoch": 1.0225,
+      "grad_norm": 7.6875,
+      "learning_rate": 8.998423292435455e-06,
+      "loss": 0.2423,
+      "step": 570
+    },
+    {
+      "epoch": 1.0275,
+      "grad_norm": 676.0,
+      "learning_rate": 8.945420424173455e-06,
+      "loss": 0.3032,
+      "step": 580
+    },
+    {
+      "epoch": 1.0325,
+      "grad_norm": 3.296875,
+      "learning_rate": 8.891215742630106e-06,
+      "loss": 0.2467,
+      "step": 590
+    },
+    {
+      "epoch": 1.0375,
+      "grad_norm": 1.578125,
+      "learning_rate": 8.8358257590765e-06,
+      "loss": 0.2491,
+      "step": 600
+    },
+    {
+      "epoch": 1.0425,
+      "grad_norm": 0.69921875,
+      "learning_rate": 8.779267345838198e-06,
+      "loss": 0.2337,
+      "step": 610
+    },
+    {
+      "epoch": 1.0475,
+      "grad_norm": 0.6328125,
+      "learning_rate": 8.72155773115577e-06,
+      "loss": 0.236,
+      "step": 620
+    },
+    {
+      "epoch": 1.0525,
+      "grad_norm": 8.0625,
+      "learning_rate": 8.662714493936895e-06,
+      "loss": 0.239,
+      "step": 630
+    },
+    {
+      "epoch": 1.0575,
+      "grad_norm": 1.8671875,
+      "learning_rate": 8.602755558401653e-06,
+      "loss": 0.2309,
+      "step": 640
+    },
+    {
+      "epoch": 1.0625,
+      "grad_norm": 242.0,
+      "learning_rate": 8.541699188622645e-06,
+      "loss": 0.3474,
+      "step": 650
+    },
+    {
+      "epoch": 1.0675,
+      "grad_norm": 2.25,
+      "learning_rate": 8.479563982961572e-06,
+      "loss": 0.2682,
+      "step": 660
+    },
+    {
+      "epoch": 1.0725,
+      "grad_norm": 4.09375,
+      "learning_rate": 8.416368868403997e-06,
+      "loss": 0.2419,
+      "step": 670
+    },
+    {
+      "epoch": 1.0775,
+      "grad_norm": 4.25,
+      "learning_rate": 8.352133094793996e-06,
+      "loss": 0.2473,
+      "step": 680
+    },
+    {
+      "epoch": 1.0825,
+      "grad_norm": 6.4375,
+      "learning_rate": 8.28687622897048e-06,
+      "loss": 0.2477,
+      "step": 690
+    },
+    {
+      "epoch": 1.0875,
+      "grad_norm": 8.0,
+      "learning_rate": 8.220618148806934e-06,
+      "loss": 0.2335,
+      "step": 700
+    },
+    {
+      "epoch": 1.0925,
+      "grad_norm": 18.0,
+      "learning_rate": 8.153379037156433e-06,
+      "loss": 0.2411,
+      "step": 710
+    },
+    {
+      "epoch": 1.0975,
+      "grad_norm": 17.875,
+      "learning_rate": 8.085179375703745e-06,
+      "loss": 0.2335,
+      "step": 720
+    },
+    {
+      "epoch": 1.1025,
+      "grad_norm": 37.75,
+      "learning_rate": 8.016039938726413e-06,
+      "loss": 0.2333,
+      "step": 730
+    },
+    {
+      "epoch": 1.1075,
+      "grad_norm": 37.0,
+      "learning_rate": 7.945981786766712e-06,
+      "loss": 0.2295,
+      "step": 740
+    },
+    {
+      "epoch": 1.1125,
+      "grad_norm": 194.0,
+      "learning_rate": 7.875026260216395e-06,
+      "loss": 0.2344,
+      "step": 750
+    },
+    {
+      "epoch": 1.1175,
+      "grad_norm": 223.0,
+      "learning_rate": 7.80319497281621e-06,
+      "loss": 0.2417,
+      "step": 760
+    },
+    {
+      "epoch": 1.1225,
+      "grad_norm": 3776.0,
+      "learning_rate": 7.730509805072146e-06,
+      "loss": 0.2648,
+      "step": 770
+    },
+    {
+      "epoch": 1.1275,
+      "grad_norm": 160768.0,
+      "learning_rate": 7.656992897590416e-06,
+      "loss": 0.3771,
+      "step": 780
+    },
+    {
+      "epoch": 1.1325,
+      "grad_norm": 45824.0,
+      "learning_rate": 7.58266664433321e-06,
+      "loss": 0.3346,
+      "step": 790
+    },
+    {
+      "epoch": 1.1375,
+      "grad_norm": 1080.0,
+      "learning_rate": 7.507553685797288e-06,
+      "loss": 0.3542,
+      "step": 800
+    },
+    {
+      "epoch": 1.1425,
+      "grad_norm": 80896.0,
+      "learning_rate": 7.431676902117453e-06,
+      "loss": 0.3665,
+      "step": 810
+    },
+    {
+      "epoch": 1.1475,
+      "grad_norm": 28544.0,
+      "learning_rate": 7.35505940609705e-06,
+      "loss": 0.534,
+      "step": 820
+    },
+    {
+      "epoch": 1.1525,
+      "grad_norm": 22400.0,
+      "learning_rate": 7.2777245361675786e-06,
+      "loss": 0.6078,
+      "step": 830
+    },
+    {
+      "epoch": 1.1575,
+      "grad_norm": 71680.0,
+      "learning_rate": 7.199695849279576e-06,
+      "loss": 0.5148,
+      "step": 840
+    },
+    {
+      "epoch": 1.1625,
+      "grad_norm": 211968.0,
+      "learning_rate": 7.120997113726951e-06,
+      "loss": 0.5792,
+      "step": 850
+    },
+    {
+      "epoch": 1.1675,
+      "grad_norm": 69632.0,
+      "learning_rate": 7.041652301906925e-06,
+      "loss": 0.8445,
+      "step": 860
+    },
+    {
+      "epoch": 1.1724999999999999,
+      "grad_norm": 59648.0,
+      "learning_rate": 6.961685583017808e-06,
+      "loss": 1.0295,
+      "step": 870
+    },
+    {
+      "epoch": 1.1775,
+      "grad_norm": 173056.0,
+      "learning_rate": 6.881121315696828e-06,
+      "loss": 1.0565,
+      "step": 880
+    },
+    {
+      "epoch": 1.1825,
+      "grad_norm": 126976.0,
+      "learning_rate": 6.799984040600257e-06,
+      "loss": 1.2456,
+      "step": 890
+    },
+    {
+      "epoch": 1.1875,
+      "grad_norm": 70144.0,
+      "learning_rate": 6.718298472928082e-06,
+      "loss": 1.5558,
+      "step": 900
+    },
+    {
+      "epoch": 1.1925,
+      "grad_norm": 196608.0,
+      "learning_rate": 6.63608949489552e-06,
+      "loss": 1.9166,
+      "step": 910
+    },
+    {
+      "epoch": 1.1975,
+      "grad_norm": 181248.0,
+      "learning_rate": 6.55338214815366e-06,
+      "loss": 1.9923,
+      "step": 920
+    },
+    {
+      "epoch": 1.2025000000000001,
+      "grad_norm": 97792.0,
+      "learning_rate": 6.47020162616152e-06,
+      "loss": 2.0694,
+      "step": 930
+    },
+    {
+      "epoch": 1.2075,
+      "grad_norm": 223232.0,
+      "learning_rate": 6.386573266511891e-06,
+      "loss": 2.1291,
+      "step": 940
+    },
+    {
+      "epoch": 1.2125,
+      "grad_norm": 98816.0,
+      "learning_rate": 6.3025225432132434e-06,
+      "loss": 2.4113,
+      "step": 950
+    },
+    {
+      "epoch": 1.2175,
+      "grad_norm": 84992.0,
+      "learning_rate": 6.218075058930113e-06,
+      "loss": 2.3453,
+      "step": 960
+    },
+    {
+      "epoch": 1.2225,
+      "grad_norm": 97792.0,
+      "learning_rate": 6.133256537184276e-06,
+      "loss": 2.346,
+      "step": 970
+    },
+    {
+      "epoch": 1.2275,
+      "grad_norm": 175104.0,
+      "learning_rate": 6.048092814519109e-06,
+      "loss": 2.2811,
+      "step": 980
+    },
+    {
+      "epoch": 1.2325,
+      "grad_norm": 76288.0,
+      "learning_rate": 5.962609832629538e-06,
+      "loss": 2.2716,
+      "step": 990
+    },
+    {
+      "epoch": 1.2375,
+      "grad_norm": 204800.0,
+      "learning_rate": 5.876833630459936e-06,
+      "loss": 2.3423,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2425,
+      "grad_norm": 95744.0,
+      "learning_rate": 5.7907903362724195e-06,
+      "loss": 2.3138,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2475,
+      "grad_norm": 174080.0,
+      "learning_rate": 5.704506159687914e-06,
+      "loss": 2.409,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2525,
+      "grad_norm": 69632.0,
+      "learning_rate": 5.618007383702464e-06,
+      "loss": 2.3463,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2575,
+      "grad_norm": 50944.0,
+      "learning_rate": 5.5313203566811666e-06,
+      "loss": 2.2391,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2625,
+      "grad_norm": 33536.0,
+      "learning_rate": 5.4444714843322085e-06,
+      "loss": 2.1177,
+      "step": 1050
+    },
+    {
+      "epoch": 2.005,
+      "grad_norm": 218112.0,
+      "learning_rate": 5.35748722166343e-06,
+      "loss": 2.3,
+      "step": 1060
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 362496.0,
+      "learning_rate": 5.270394064923878e-06,
+      "loss": 2.0117,
+      "step": 1070
+    },
+    {
+      "epoch": 2.015,
+      "grad_norm": 73216.0,
+      "learning_rate": 5.183218543532782e-06,
+      "loss": 2.1228,
+      "step": 1080
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 311296.0,
+      "learning_rate": 5.09598721199845e-06,
+      "loss": 1.9065,
+      "step": 1090
+    },
+    {
+      "epoch": 2.025,
+      "grad_norm": 14144.0,
+      "learning_rate": 5.008726641829492e-06,
+      "loss": 2.1163,
+      "step": 1100
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 57856.0,
+      "learning_rate": 4.921463413440898e-06,
+      "loss": 1.989,
+      "step": 1110
+    },
+    {
+      "epoch": 2.035,
+      "grad_norm": 26.375,
+      "learning_rate": 4.8342241080573696e-06,
+      "loss": 1.3574,
+      "step": 1120
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 9.5,
+      "learning_rate": 4.747035299616434e-06,
+      "loss": 0.2283,
+      "step": 1130
+    },
+    {
+      "epoch": 2.045,
+      "grad_norm": 49.0,
+      "learning_rate": 4.659923546673761e-06,
+      "loss": 0.2114,
+      "step": 1140
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 67.5,
+      "learning_rate": 4.572915384313163e-06,
+      "loss": 0.2171,
+      "step": 1150
+    },
+    {
+      "epoch": 2.055,
+      "grad_norm": 3.015625,
+      "learning_rate": 4.4860373160637665e-06,
+      "loss": 0.2159,
+      "step": 1160
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 2.296875,
+      "learning_rate": 4.399315805826765e-06,
+      "loss": 0.2039,
+      "step": 1170
+    },
+    {
+      "epoch": 2.065,
+      "grad_norm": 0.99609375,
+      "learning_rate": 4.312777269814268e-06,
+      "loss": 0.2343,
+      "step": 1180
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 19.375,
+      "learning_rate": 4.226448068502661e-06,
+      "loss": 0.2123,
+      "step": 1190
+    },
+    {
+      "epoch": 2.075,
+      "grad_norm": 2.4375,
+      "learning_rate": 4.140354498602952e-06,
+      "loss": 0.2159,
+      "step": 1200
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 41.0,
+      "learning_rate": 4.054522785050543e-06,
+      "loss": 0.233,
+      "step": 1210
+    },
+    {
+      "epoch": 2.085,
+      "grad_norm": 62.5,
+      "learning_rate": 3.968979073016853e-06,
+      "loss": 0.2235,
+      "step": 1220
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 55.25,
+      "learning_rate": 3.883749419945244e-06,
+      "loss": 0.2261,
+      "step": 1230
+    },
+    {
+      "epoch": 2.095,
+      "grad_norm": 5.375,
+      "learning_rate": 3.798859787613682e-06,
+      "loss": 0.2343,
+      "step": 1240
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 27.0,
+      "learning_rate": 3.7143360342265206e-06,
+      "loss": 0.2322,
+      "step": 1250
+    },
+    {
+      "epoch": 2.105,
+      "grad_norm": 26.875,
+      "learning_rate": 3.630203906537838e-06,
+      "loss": 0.2278,
+      "step": 1260
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 12.0,
+      "learning_rate": 3.5464890320087374e-06,
+      "loss": 0.2292,
+      "step": 1270
+    },
+    {
+      "epoch": 2.115,
+      "grad_norm": 28.625,
+      "learning_rate": 3.463216911000965e-06,
+      "loss": 0.2397,
+      "step": 1280
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 8.3125,
+      "learning_rate": 3.3804129090092542e-06,
+      "loss": 0.2485,
+      "step": 1290
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 632.0,
+      "learning_rate": 3.2981022489347503e-06,
+      "loss": 0.2495,
+      "step": 1300
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 79.0,
+      "learning_rate": 3.2163100034018735e-06,
+      "loss": 0.2476,
+      "step": 1310
+    },
+    {
+      "epoch": 2.135,
+      "grad_norm": 480.0,
+      "learning_rate": 3.1350610871209553e-06,
+      "loss": 0.2492,
+      "step": 1320
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 10.75,
+      "learning_rate": 3.0543802492989693e-06,
+      "loss": 0.2473,
+      "step": 1330
+    },
+    {
+      "epoch": 2.145,
+      "grad_norm": 25.125,
+      "learning_rate": 2.974292066100688e-06,
+      "loss": 0.2596,
+      "step": 1340
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 13.0,
+      "learning_rate": 2.8948209331625454e-06,
+      "loss": 0.2566,
+      "step": 1350
+    },
+    {
+      "epoch": 2.155,
+      "grad_norm": 13.25,
+      "learning_rate": 2.8159910581614904e-06,
+      "loss": 0.2547,
+      "step": 1360
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 113.0,
+      "learning_rate": 2.7378264534410865e-06,
+      "loss": 0.2522,
+      "step": 1370
+    },
+    {
+      "epoch": 2.165,
+      "grad_norm": 16.375,
+      "learning_rate": 2.6603509286971342e-06,
+      "loss": 0.2514,
+      "step": 1380
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 56.75,
+      "learning_rate": 2.5835880837249884e-06,
+      "loss": 0.2645,
+      "step": 1390
+    },
+    {
+      "epoch": 2.175,
+      "grad_norm": 76.0,
+      "learning_rate": 2.507561301230849e-06,
+      "loss": 0.2791,
+      "step": 1400
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 282.0,
+      "learning_rate": 2.432293739709151e-06,
+      "loss": 0.2751,
+      "step": 1410
+    },
+    {
+      "epoch": 2.185,
+      "grad_norm": 55.25,
+      "learning_rate": 2.357808326388265e-06,
+      "loss": 0.32,
+      "step": 1420
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 182.0,
+      "learning_rate": 2.284127750246646e-06,
+      "loss": 0.2909,
+      "step": 1430
+    },
+    {
+      "epoch": 2.195,
+      "grad_norm": 684.0,
+      "learning_rate": 2.2112744551015496e-06,
+      "loss": 0.3536,
+      "step": 1440
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 241.0,
+      "learning_rate": 2.13927063277242e-06,
+      "loss": 0.4113,
+      "step": 1450
+    },
+    {
+      "epoch": 2.205,
+      "grad_norm": 324.0,
+      "learning_rate": 2.0681382163210533e-06,
+      "loss": 0.3519,
+      "step": 1460
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 204.0,
+      "learning_rate": 1.9978988733705807e-06,
+      "loss": 0.4423,
+      "step": 1470
+    },
+    {
+      "epoch": 2.215,
+      "grad_norm": 364.0,
+      "learning_rate": 1.928573999505284e-06,
+      "loss": 0.4239,
+      "step": 1480
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 560.0,
+      "learning_rate": 1.8601847117533112e-06,
+      "loss": 0.3873,
+      "step": 1490
+    },
+    {
+      "epoch": 2.225,
+      "grad_norm": 1064.0,
+      "learning_rate": 1.7927518421542106e-06,
+      "loss": 0.4393,
+      "step": 1500
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 75.0,
+      "learning_rate": 1.7262959314133015e-06,
+      "loss": 0.3778,
+      "step": 1510
+    },
+    {
+      "epoch": 2.235,
+      "grad_norm": 51.25,
+      "learning_rate": 1.6608372226447678e-06,
+      "loss": 0.4037,
+      "step": 1520
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 332.0,
+      "learning_rate": 1.596395655205411e-06,
+      "loss": 0.352,
+      "step": 1530
+    },
+    {
+      "epoch": 2.245,
+      "grad_norm": 1112.0,
+      "learning_rate": 1.5329908586209347e-06,
+      "loss": 0.3604,
+      "step": 1540
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 13888.0,
+      "learning_rate": 1.4706421466065952e-06,
+      "loss": 0.2952,
+      "step": 1550
+    },
+    {
+      "epoch": 2.255,
+      "grad_norm": 286.0,
+      "learning_rate": 1.4093685111840567e-06,
+      "loss": 0.2647,
+      "step": 1560
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 240.0,
+      "learning_rate": 1.349188616896238e-06,
+      "loss": 0.2745,
+      "step": 1570
+    },
+    {
+      "epoch": 3.0025,
+      "grad_norm": 183.0,
+      "learning_rate": 1.2901207951219186e-06,
+      "loss": 0.3445,
+      "step": 1580
+    },
+    {
+      "epoch": 3.0075,
+      "grad_norm": 1608.0,
+      "learning_rate": 1.2321830384918116e-06,
+      "loss": 0.3354,
+      "step": 1590
+    },
+    {
+      "epoch": 3.0125,
+      "grad_norm": 1048.0,
+      "learning_rate": 1.1753929954078414e-06,
+      "loss": 0.3534,
+      "step": 1600
+    },
+    {
+      "epoch": 3.0175,
+      "grad_norm": 1872.0,
+      "learning_rate": 1.1197679646672698e-06,
+      "loss": 0.3545,
+      "step": 1610
+    },
+    {
+      "epoch": 3.0225,
+      "grad_norm": 223.0,
+      "learning_rate": 1.065324890193314e-06,
+      "loss": 0.3755,
+      "step": 1620
+    },
+    {
+      "epoch": 3.0275,
+      "grad_norm": 246.0,
+      "learning_rate": 1.0120803558738585e-06,
+      "loss": 0.3806,
+      "step": 1630
+    },
+    {
+      "epoch": 3.0325,
+      "grad_norm": 502.0,
+      "learning_rate": 9.600505805098486e-07,
+      "loss": 0.4116,
+      "step": 1640
+    },
+    {
+      "epoch": 3.0375,
+      "grad_norm": 101.0,
+      "learning_rate": 9.09251412874882e-07,
+      "loss": 0.4202,
+      "step": 1650
+    },
+    {
+      "epoch": 3.0425,
+      "grad_norm": 312.0,
+      "learning_rate": 8.596983268875281e-07,
+      "loss": 0.4025,
+      "step": 1660
+    },
+    {
+      "epoch": 3.0475,
+      "grad_norm": 230.0,
+      "learning_rate": 8.114064168978064e-07,
+      "loss": 0.4008,
+      "step": 1670
+    },
+    {
+      "epoch": 3.0525,
+      "grad_norm": 250.0,
+      "learning_rate": 7.643903930893154e-07,
+      "loss": 0.4165,
+      "step": 1680
+    },
+    {
+      "epoch": 3.0575,
+      "grad_norm": 1080.0,
+      "learning_rate": 7.186645769983591e-07,
+      "loss": 0.4121,
+      "step": 1690
+    },
+    {
+      "epoch": 3.0625,
+      "grad_norm": 224.0,
+      "learning_rate": 6.742428971514786e-07,
+      "loss": 0.4227,
+      "step": 1700
+    },
+    {
+      "epoch": 3.0675,
+      "grad_norm": 350.0,
+      "learning_rate": 6.311388848226741e-07,
+      "loss": 0.424,
+      "step": 1710
+    },
+    {
+      "epoch": 3.0725,
+      "grad_norm": 1512.0,
+      "learning_rate": 5.893656699116618e-07,
+      "loss": 0.4338,
+      "step": 1720
+    },
+    {
+      "epoch": 3.0775,
+      "grad_norm": 596.0,
+      "learning_rate": 5.489359769443675e-07,
+      "loss": 0.4446,
+      "step": 1730
+    },
+    {
+      "epoch": 3.0825,
+      "grad_norm": 129.0,
+      "learning_rate": 5.098621211969224e-07,
+      "loss": 0.4512,
+      "step": 1740
+    },
+    {
+      "epoch": 3.0875,
+      "grad_norm": 125.0,
+      "learning_rate": 4.72156004944303e-07,
+      "loss": 0.4246,
+      "step": 1750
+    },
+    {
+      "epoch": 3.0925,
+      "grad_norm": 173.0,
+      "learning_rate": 4.3582911383478646e-07,
+      "loss": 0.4568,
+      "step": 1760
+    },
+    {
+      "epoch": 3.0975,
+      "grad_norm": 968.0,
+      "learning_rate": 4.0089251339131164e-07,
+      "loss": 0.4463,
+      "step": 1770
+    },
+    {
+      "epoch": 3.1025,
+      "grad_norm": 72.0,
+      "learning_rate": 3.6735684564081385e-07,
+      "loss": 0.4532,
+      "step": 1780
+    },
+    {
+      "epoch": 3.1075,
+      "grad_norm": 166.0,
+      "learning_rate": 3.352323258725554e-07,
+      "loss": 0.4359,
+      "step": 1790
+    },
+    {
+      "epoch": 3.1125,
+      "grad_norm": 138.0,
+      "learning_rate": 3.0452873952645455e-07,
+      "loss": 0.4516,
+      "step": 1800
+    },
+    {
+      "epoch": 3.1175,
+      "grad_norm": 69.0,
+      "learning_rate": 2.752554392123463e-07,
+      "loss": 0.4483,
+      "step": 1810
+    },
+    {
+      "epoch": 3.1225,
+      "grad_norm": 332.0,
+      "learning_rate": 2.474213418610816e-07,
+      "loss": 0.4764,
+      "step": 1820
+    },
+    {
+      "epoch": 3.1275,
+      "grad_norm": 1020.0,
+      "learning_rate": 2.210349260083494e-07,
+      "loss": 0.4649,
+      "step": 1830
+    },
+    {
+      "epoch": 3.1325,
+      "grad_norm": 410.0,
+      "learning_rate": 1.961042292120291e-07,
+      "loss": 0.4447,
+      "step": 1840
+    },
+    {
+      "epoch": 3.1375,
+      "grad_norm": 394.0,
+      "learning_rate": 1.7263684560387518e-07,
+      "loss": 0.4646,
+      "step": 1850
+    },
+    {
+      "epoch": 3.1425,
+      "grad_norm": 88.5,
+      "learning_rate": 1.5063992357626623e-07,
+      "loss": 0.4798,
+      "step": 1860
+    },
+    {
+      "epoch": 3.1475,
+      "grad_norm": 640.0,
+      "learning_rate": 1.3012016360474223e-07,
+      "loss": 0.4768,
+      "step": 1870
+    },
+    {
+      "epoch": 3.1525,
+      "grad_norm": 478.0,
+      "learning_rate": 1.1108381620696885e-07,
+      "loss": 0.4774,
+      "step": 1880
+    },
+    {
+      "epoch": 3.1575,
+      "grad_norm": 988.0,
+      "learning_rate": 9.353668003877437e-08,
+      "loss": 0.4793,
+      "step": 1890
+    },
+    {
+      "epoch": 3.1625,
+      "grad_norm": 1096.0,
+      "learning_rate": 7.748410012781705e-08,
+      "loss": 0.4356,
+      "step": 1900
+    },
+    {
+      "epoch": 3.1675,
+      "grad_norm": 254.0,
+      "learning_rate": 6.293096624544304e-08,
+      "loss": 0.4517,
+      "step": 1910
+    },
+    {
+      "epoch": 3.1725,
+      "grad_norm": 191.0,
+      "learning_rate": 4.988171141721232e-08,
+      "loss": 0.4873,
+      "step": 1920
+    },
+    {
+      "epoch": 3.1775,
+      "grad_norm": 390.0,
+      "learning_rate": 3.83403105725566e-08,
+      "loss": 0.4718,
+      "step": 1930
+    },
+    {
+      "epoch": 3.1825,
+      "grad_norm": 88.5,
+      "learning_rate": 2.8310279333976786e-08,
+      "loss": 0.4622,
+      "step": 1940
+    },
+    {
+      "epoch": 3.1875,
+      "grad_norm": 324.0,
+      "learning_rate": 1.9794672946152337e-08,
+      "loss": 0.4706,
+      "step": 1950
+    },
+    {
+      "epoch": 3.1925,
+      "grad_norm": 224.0,
+      "learning_rate": 1.2796085345280207e-08,
+      "loss": 0.4745,
+      "step": 1960
+    },
+    {
+      "epoch": 3.1975,
+      "grad_norm": 79.5,
+      "learning_rate": 7.3166483689413035e-09,
+      "loss": 0.4601,
+      "step": 1970
+    },
+    {
+      "epoch": 3.2025,
+      "grad_norm": 536.0,
+      "learning_rate": 3.3580311067188396e-09,
+      "loss": 0.4624,
+      "step": 1980
+    },
+    {
+      "epoch": 3.2075,
+      "grad_norm": 490.0,
+      "learning_rate": 9.214393917789111e-10,
+      "loss": 0.4498,
+      "step": 1990
+    },
+    {
+      "epoch": 3.2125,
+      "grad_norm": 242.0,
+      "learning_rate": 7.615433561536379e-12,
+      "loss": 0.4816,
+      "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": 1.1135848826902938e+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:f34774d52e164f61728b7e020f75bf9fe4663f6c90a704c0ec87cd2a46a0c496
+size 5304