Upload folder using huggingface_hub

checkpoint-7630/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "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_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-7630/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-7630/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfab70691f5f05f8ff4c5b4a75d1e7e9295860a0fbf86a86a379fe65b9fdda68
+size 4976687216

checkpoint-7630/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faab92c079dee70573da2aa38bf83c1a2a2858fbee7104c30f77e30eb62ed67f
+size 4778622352

checkpoint-7630/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d579560f2723d4a62b22ef6ec0d935dfbc2ddf0f14fc9efeac83bf5b586bf9d6
+size 4932743960

checkpoint-7630/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089cf99962fd351ceb590220ea351f1d18937b35376077982b276416f768317a
+size 4932743992

checkpoint-7630/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b61bee4a8b5e41f744ec0820def58c39c0c333e6787b7e24146468348f082a0
+size 4998852296

checkpoint-7630/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0feb13bd700274f0aa0c0c4f1a30677c05eec8937feabfbdf3dc9c3caf9e6c1c
+size 3662865184

checkpoint-7630/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47fcfe212792633421ed1d9a0347637c8e801e23aff74d858e27f4f5531013ec
+size 2179989632

checkpoint-7630/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-7630/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78a04ca713748d566ff2381bd1975a2d316286192533a0b4f9568c6e574c4d3
+size 16177880918

checkpoint-7630/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-7630/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:534e20fd2d9d5b7f7b2cacb37e2f2890c1ef6152d939158d158e395d1f32997e
+size 1064

checkpoint-7630/trainer_state.json

@@ -0,0 +1,1755 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.20034134173559143,
+  "eval_steps": 500,
+  "global_step": 7630,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008139687541026651,
+      "grad_norm": 3.665264844894409,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 2.1812,
+      "step": 31
+    },
+    {
+      "epoch": 0.0016279375082053301,
+      "grad_norm": 2.4676246643066406,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 2.0535,
+      "step": 62
+    },
+    {
+      "epoch": 0.0024419062623079954,
+      "grad_norm": 2.878305196762085,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.9458,
+      "step": 93
+    },
+    {
+      "epoch": 0.0032558750164106602,
+      "grad_norm": 2.694674015045166,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.8719,
+      "step": 124
+    },
+    {
+      "epoch": 0.004069843770513325,
+      "grad_norm": 2.7240898609161377,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.8334,
+      "step": 155
+    },
+    {
+      "epoch": 0.004883812524615991,
+      "grad_norm": 3.3849148750305176,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 1.7827,
+      "step": 186
+    },
+    {
+      "epoch": 0.005697781278718656,
+      "grad_norm": 3.106435537338257,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 1.7446,
+      "step": 217
+    },
+    {
+      "epoch": 0.0065117500328213205,
+      "grad_norm": 4.933763027191162,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 1.7271,
+      "step": 248
+    },
+    {
+      "epoch": 0.007325718786923986,
+      "grad_norm": 3.060612678527832,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 1.6866,
+      "step": 279
+    },
+    {
+      "epoch": 0.00813968754102665,
+      "grad_norm": 3.417919158935547,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 1.6634,
+      "step": 310
+    },
+    {
+      "epoch": 0.008953656295129316,
+      "grad_norm": 4.560545444488525,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 1.6522,
+      "step": 341
+    },
+    {
+      "epoch": 0.009767625049231982,
+      "grad_norm": 2.6599414348602295,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 1.6286,
+      "step": 372
+    },
+    {
+      "epoch": 0.010581593803334646,
+      "grad_norm": 3.5111501216888428,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 1.6086,
+      "step": 403
+    },
+    {
+      "epoch": 0.011395562557437311,
+      "grad_norm": 3.8709545135498047,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 1.6005,
+      "step": 434
+    },
+    {
+      "epoch": 0.012209531311539977,
+      "grad_norm": 2.655081272125244,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 1.5753,
+      "step": 465
+    },
+    {
+      "epoch": 0.013023500065642641,
+      "grad_norm": 4.050207614898682,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 1.5758,
+      "step": 496
+    },
+    {
+      "epoch": 0.013837468819745307,
+      "grad_norm": 2.916259527206421,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 1.5491,
+      "step": 527
+    },
+    {
+      "epoch": 0.014651437573847972,
+      "grad_norm": 4.070659160614014,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 1.5347,
+      "step": 558
+    },
+    {
+      "epoch": 0.015465406327950636,
+      "grad_norm": 3.4878790378570557,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 1.5151,
+      "step": 589
+    },
+    {
+      "epoch": 0.0162793750820533,
+      "grad_norm": 2.949390172958374,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 1.5107,
+      "step": 620
+    },
+    {
+      "epoch": 0.017093343836155968,
+      "grad_norm": 3.1922178268432617,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 1.5001,
+      "step": 651
+    },
+    {
+      "epoch": 0.017907312590258632,
+      "grad_norm": 3.8529181480407715,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 1.4884,
+      "step": 682
+    },
+    {
+      "epoch": 0.018721281344361296,
+      "grad_norm": 3.2902474403381348,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 1.482,
+      "step": 713
+    },
+    {
+      "epoch": 0.019535250098463963,
+      "grad_norm": 2.9867563247680664,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 1.4658,
+      "step": 744
+    },
+    {
+      "epoch": 0.020349218852566627,
+      "grad_norm": 3.0621280670166016,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 1.4581,
+      "step": 775
+    },
+    {
+      "epoch": 0.02116318760666929,
+      "grad_norm": 3.839115619659424,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 1.4552,
+      "step": 806
+    },
+    {
+      "epoch": 0.02197715636077196,
+      "grad_norm": 2.9147427082061768,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 1.4368,
+      "step": 837
+    },
+    {
+      "epoch": 0.022791125114874623,
+      "grad_norm": 3.521418333053589,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 1.4435,
+      "step": 868
+    },
+    {
+      "epoch": 0.023605093868977287,
+      "grad_norm": 2.9942727088928223,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 1.4255,
+      "step": 899
+    },
+    {
+      "epoch": 0.024419062623079954,
+      "grad_norm": 5.096376419067383,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 1.4206,
+      "step": 930
+    },
+    {
+      "epoch": 0.025233031377182618,
+      "grad_norm": 2.957164764404297,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 1.4177,
+      "step": 961
+    },
+    {
+      "epoch": 0.026047000131285282,
+      "grad_norm": 2.8639140129089355,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 1.4082,
+      "step": 992
+    },
+    {
+      "epoch": 0.02686096888538795,
+      "grad_norm": 5.731191635131836,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 1.4017,
+      "step": 1023
+    },
+    {
+      "epoch": 0.027674937639490613,
+      "grad_norm": 2.957393169403076,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 1.4075,
+      "step": 1054
+    },
+    {
+      "epoch": 0.028488906393593277,
+      "grad_norm": 2.716973304748535,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 1.392,
+      "step": 1085
+    },
+    {
+      "epoch": 0.029302875147695945,
+      "grad_norm": 2.8386828899383545,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 1.3803,
+      "step": 1116
+    },
+    {
+      "epoch": 0.03011684390179861,
+      "grad_norm": 3.3751955032348633,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 1.3613,
+      "step": 1147
+    },
+    {
+      "epoch": 0.030930812655901273,
+      "grad_norm": 2.9111735820770264,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 1.3638,
+      "step": 1178
+    },
+    {
+      "epoch": 0.03174478141000394,
+      "grad_norm": 2.3721137046813965,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 1.3706,
+      "step": 1209
+    },
+    {
+      "epoch": 0.0325587501641066,
+      "grad_norm": 3.0478310585021973,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 1.3646,
+      "step": 1240
+    },
+    {
+      "epoch": 0.03337271891820927,
+      "grad_norm": 2.796151638031006,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 1.3521,
+      "step": 1271
+    },
+    {
+      "epoch": 0.034186687672311936,
+      "grad_norm": 3.2832095623016357,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 1.3445,
+      "step": 1302
+    },
+    {
+      "epoch": 0.035000656426414596,
+      "grad_norm": 2.7193307876586914,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 1.341,
+      "step": 1333
+    },
+    {
+      "epoch": 0.035814625180517264,
+      "grad_norm": 2.3204262256622314,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 1.3392,
+      "step": 1364
+    },
+    {
+      "epoch": 0.03662859393461993,
+      "grad_norm": 3.0932254791259766,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 1.3473,
+      "step": 1395
+    },
+    {
+      "epoch": 0.03744256268872259,
+      "grad_norm": 2.749105930328369,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 1.3355,
+      "step": 1426
+    },
+    {
+      "epoch": 0.03825653144282526,
+      "grad_norm": 3.433612108230591,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 1.3358,
+      "step": 1457
+    },
+    {
+      "epoch": 0.039070500196927926,
+      "grad_norm": 2.8213951587677,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 1.3274,
+      "step": 1488
+    },
+    {
+      "epoch": 0.03988446895103059,
+      "grad_norm": 55.82658004760742,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 2.3909,
+      "step": 1519
+    },
+    {
+      "epoch": 0.040698437705133254,
+      "grad_norm": 11.446126937866211,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 1.8256,
+      "step": 1550
+    },
+    {
+      "epoch": 0.04151240645923592,
+      "grad_norm": 2.9234585762023926,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 1.5262,
+      "step": 1581
+    },
+    {
+      "epoch": 0.04232637521333858,
+      "grad_norm": 2.534860372543335,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 1.4296,
+      "step": 1612
+    },
+    {
+      "epoch": 0.04314034396744125,
+      "grad_norm": 3.393228054046631,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 1.367,
+      "step": 1643
+    },
+    {
+      "epoch": 0.04395431272154392,
+      "grad_norm": 5.319057464599609,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 1.4302,
+      "step": 1674
+    },
+    {
+      "epoch": 0.04476828147564658,
+      "grad_norm": 2.2556281089782715,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 1.3762,
+      "step": 1705
+    },
+    {
+      "epoch": 0.045582250229749245,
+      "grad_norm": 11.374442100524902,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 1.4159,
+      "step": 1736
+    },
+    {
+      "epoch": 0.04639621898385191,
+      "grad_norm": 2.643413782119751,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 1.4324,
+      "step": 1767
+    },
+    {
+      "epoch": 0.04721018773795457,
+      "grad_norm": 4.3118109703063965,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 1.399,
+      "step": 1798
+    },
+    {
+      "epoch": 0.04802415649205724,
+      "grad_norm": 2.8440845012664795,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 1.3763,
+      "step": 1829
+    },
+    {
+      "epoch": 0.04883812524615991,
+      "grad_norm": 3.8986079692840576,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 1.3756,
+      "step": 1860
+    },
+    {
+      "epoch": 0.04965209400026257,
+      "grad_norm": 3.168850898742676,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 1.3393,
+      "step": 1891
+    },
+    {
+      "epoch": 0.050466062754365236,
+      "grad_norm": 2.3892204761505127,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 1.3304,
+      "step": 1922
+    },
+    {
+      "epoch": 0.0512800315084679,
+      "grad_norm": 2.0968079566955566,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 1.3187,
+      "step": 1953
+    },
+    {
+      "epoch": 0.052094000262570564,
+      "grad_norm": 7.010090351104736,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 1.3172,
+      "step": 1984
+    },
+    {
+      "epoch": 0.05290796901667323,
+      "grad_norm": 2.074108362197876,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 1.2991,
+      "step": 2015
+    },
+    {
+      "epoch": 0.0537219377707759,
+      "grad_norm": 2.41266131401062,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 1.2839,
+      "step": 2046
+    },
+    {
+      "epoch": 0.05453590652487856,
+      "grad_norm": 2.0564286708831787,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 1.2844,
+      "step": 2077
+    },
+    {
+      "epoch": 0.05534987527898123,
+      "grad_norm": 2.0147621631622314,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 1.2869,
+      "step": 2108
+    },
+    {
+      "epoch": 0.056163844033083894,
+      "grad_norm": 2.451154947280884,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 1.2789,
+      "step": 2139
+    },
+    {
+      "epoch": 0.056977812787186555,
+      "grad_norm": 2.770345449447632,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 1.2736,
+      "step": 2170
+    },
+    {
+      "epoch": 0.05779178154128922,
+      "grad_norm": 2.041412830352783,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 1.2717,
+      "step": 2201
+    },
+    {
+      "epoch": 0.05860575029539189,
+      "grad_norm": 2.171128511428833,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 1.2516,
+      "step": 2232
+    },
+    {
+      "epoch": 0.05941971904949455,
+      "grad_norm": 2.7466177940368652,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 1.2617,
+      "step": 2263
+    },
+    {
+      "epoch": 0.06023368780359722,
+      "grad_norm": 2.0188562870025635,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 1.261,
+      "step": 2294
+    },
+    {
+      "epoch": 0.061047656557699885,
+      "grad_norm": 2.229243516921997,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 1.2552,
+      "step": 2325
+    },
+    {
+      "epoch": 0.061861625311802546,
+      "grad_norm": 3.7142019271850586,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 1.2647,
+      "step": 2356
+    },
+    {
+      "epoch": 0.06267559406590521,
+      "grad_norm": 1.8443535566329956,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 1.2545,
+      "step": 2387
+    },
+    {
+      "epoch": 0.06348956282000788,
+      "grad_norm": 2.1792187690734863,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 1.2602,
+      "step": 2418
+    },
+    {
+      "epoch": 0.06430353157411055,
+      "grad_norm": 2.427130937576294,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 1.2599,
+      "step": 2449
+    },
+    {
+      "epoch": 0.0651175003282132,
+      "grad_norm": 2.40641450881958,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 1.2482,
+      "step": 2480
+    },
+    {
+      "epoch": 0.06593146908231587,
+      "grad_norm": 2.4361321926116943,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 1.2477,
+      "step": 2511
+    },
+    {
+      "epoch": 0.06674543783641854,
+      "grad_norm": 3.251391887664795,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 1.249,
+      "step": 2542
+    },
+    {
+      "epoch": 0.0675594065905212,
+      "grad_norm": 2.3272197246551514,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 1.2456,
+      "step": 2573
+    },
+    {
+      "epoch": 0.06837337534462387,
+      "grad_norm": 1.765633463859558,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 1.2275,
+      "step": 2604
+    },
+    {
+      "epoch": 0.06918734409872654,
+      "grad_norm": 2.487745761871338,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 1.2348,
+      "step": 2635
+    },
+    {
+      "epoch": 0.07000131285282919,
+      "grad_norm": 2.476963520050049,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 1.222,
+      "step": 2666
+    },
+    {
+      "epoch": 0.07081528160693186,
+      "grad_norm": 2.867267370223999,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 1.2393,
+      "step": 2697
+    },
+    {
+      "epoch": 0.07162925036103453,
+      "grad_norm": 2.260697841644287,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 1.2454,
+      "step": 2728
+    },
+    {
+      "epoch": 0.0724432191151372,
+      "grad_norm": 2.2477054595947266,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 1.2461,
+      "step": 2759
+    },
+    {
+      "epoch": 0.07325718786923986,
+      "grad_norm": 4.51762056350708,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 1.2167,
+      "step": 2790
+    },
+    {
+      "epoch": 0.07407115662334253,
+      "grad_norm": 1.9302934408187866,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 1.2335,
+      "step": 2821
+    },
+    {
+      "epoch": 0.07488512537744518,
+      "grad_norm": 2.1645681858062744,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 1.238,
+      "step": 2852
+    },
+    {
+      "epoch": 0.07569909413154785,
+      "grad_norm": 2.2581164836883545,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 1.2147,
+      "step": 2883
+    },
+    {
+      "epoch": 0.07651306288565052,
+      "grad_norm": 1.9437881708145142,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 1.2344,
+      "step": 2914
+    },
+    {
+      "epoch": 0.07732703163975319,
+      "grad_norm": 1.807570219039917,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 1.2186,
+      "step": 2945
+    },
+    {
+      "epoch": 0.07814100039385585,
+      "grad_norm": 2.321345567703247,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 1.2151,
+      "step": 2976
+    },
+    {
+      "epoch": 0.07895496914795852,
+      "grad_norm": 2.279082775115967,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 1.2187,
+      "step": 3007
+    },
+    {
+      "epoch": 0.07976893790206117,
+      "grad_norm": 1.6429636478424072,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 1.2104,
+      "step": 3038
+    },
+    {
+      "epoch": 0.08058290665616384,
+      "grad_norm": 1.9841675758361816,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 1.2183,
+      "step": 3069
+    },
+    {
+      "epoch": 0.08139687541026651,
+      "grad_norm": 2.1972384452819824,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 1.2156,
+      "step": 3100
+    },
+    {
+      "epoch": 0.08221084416436918,
+      "grad_norm": 1.8140931129455566,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 1.205,
+      "step": 3131
+    },
+    {
+      "epoch": 0.08302481291847184,
+      "grad_norm": 1.7327383756637573,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 1.2105,
+      "step": 3162
+    },
+    {
+      "epoch": 0.08383878167257451,
+      "grad_norm": 1.5160003900527954,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 1.2089,
+      "step": 3193
+    },
+    {
+      "epoch": 0.08465275042667716,
+      "grad_norm": 2.113037109375,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 1.1991,
+      "step": 3224
+    },
+    {
+      "epoch": 0.08546671918077983,
+      "grad_norm": 1.807724118232727,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 1.2026,
+      "step": 3255
+    },
+    {
+      "epoch": 0.0862806879348825,
+      "grad_norm": 1.8682724237442017,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 1.193,
+      "step": 3286
+    },
+    {
+      "epoch": 0.08709465668898517,
+      "grad_norm": 2.3081648349761963,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 1.2019,
+      "step": 3317
+    },
+    {
+      "epoch": 0.08790862544308783,
+      "grad_norm": 1.8127061128616333,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 1.1934,
+      "step": 3348
+    },
+    {
+      "epoch": 0.08872259419719049,
+      "grad_norm": 1.8878953456878662,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 1.1923,
+      "step": 3379
+    },
+    {
+      "epoch": 0.08953656295129316,
+      "grad_norm": 1.6906676292419434,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 1.1993,
+      "step": 3410
+    },
+    {
+      "epoch": 0.09035053170539582,
+      "grad_norm": 2.181830883026123,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 1.1911,
+      "step": 3441
+    },
+    {
+      "epoch": 0.09116450045949849,
+      "grad_norm": 2.4296047687530518,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 1.198,
+      "step": 3472
+    },
+    {
+      "epoch": 0.09197846921360116,
+      "grad_norm": 1.9574142694473267,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 1.1938,
+      "step": 3503
+    },
+    {
+      "epoch": 0.09279243796770383,
+      "grad_norm": 1.6882851123809814,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 1.1974,
+      "step": 3534
+    },
+    {
+      "epoch": 0.09360640672180648,
+      "grad_norm": 2.3280014991760254,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 1.194,
+      "step": 3565
+    },
+    {
+      "epoch": 0.09442037547590915,
+      "grad_norm": 2.2544307708740234,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 1.1814,
+      "step": 3596
+    },
+    {
+      "epoch": 0.09523434423001181,
+      "grad_norm": 2.25360369682312,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 1.1737,
+      "step": 3627
+    },
+    {
+      "epoch": 0.09604831298411448,
+      "grad_norm": 1.5724776983261108,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 1.1766,
+      "step": 3658
+    },
+    {
+      "epoch": 0.09686228173821715,
+      "grad_norm": 1.8221943378448486,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 1.183,
+      "step": 3689
+    },
+    {
+      "epoch": 0.09767625049231982,
+      "grad_norm": 1.722594141960144,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 1.1681,
+      "step": 3720
+    },
+    {
+      "epoch": 0.09849021924642247,
+      "grad_norm": 1.5307432413101196,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 1.1737,
+      "step": 3751
+    },
+    {
+      "epoch": 0.09930418800052514,
+      "grad_norm": 2.0803110599517822,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 1.1698,
+      "step": 3782
+    },
+    {
+      "epoch": 0.1001181567546278,
+      "grad_norm": 1.7529264688491821,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 1.1752,
+      "step": 3813
+    },
+    {
+      "epoch": 0.10093212550873047,
+      "grad_norm": 1.4459233283996582,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 1.154,
+      "step": 3844
+    },
+    {
+      "epoch": 0.10174609426283314,
+      "grad_norm": 1.980885624885559,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 1.1751,
+      "step": 3875
+    },
+    {
+      "epoch": 0.1025600630169358,
+      "grad_norm": 2.3104734420776367,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 1.1609,
+      "step": 3906
+    },
+    {
+      "epoch": 0.10337403177103846,
+      "grad_norm": 1.7842062711715698,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 1.1737,
+      "step": 3937
+    },
+    {
+      "epoch": 0.10418800052514113,
+      "grad_norm": 1.6121835708618164,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 1.1681,
+      "step": 3968
+    },
+    {
+      "epoch": 0.1050019692792438,
+      "grad_norm": 2.3961281776428223,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 1.1686,
+      "step": 3999
+    },
+    {
+      "epoch": 0.10581593803334646,
+      "grad_norm": 1.7535598278045654,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 1.169,
+      "step": 4030
+    },
+    {
+      "epoch": 0.10662990678744913,
+      "grad_norm": 1.7736597061157227,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 1.1627,
+      "step": 4061
+    },
+    {
+      "epoch": 0.1074438755415518,
+      "grad_norm": 1.7297468185424805,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 1.152,
+      "step": 4092
+    },
+    {
+      "epoch": 0.10825784429565445,
+      "grad_norm": 2.4818034172058105,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 1.1757,
+      "step": 4123
+    },
+    {
+      "epoch": 0.10907181304975712,
+      "grad_norm": 1.5024869441986084,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 1.1645,
+      "step": 4154
+    },
+    {
+      "epoch": 0.10988578180385979,
+      "grad_norm": 2.0316147804260254,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 1.1607,
+      "step": 4185
+    },
+    {
+      "epoch": 0.11069975055796245,
+      "grad_norm": 2.1756372451782227,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 1.1504,
+      "step": 4216
+    },
+    {
+      "epoch": 0.11151371931206512,
+      "grad_norm": 1.5000461339950562,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 1.1768,
+      "step": 4247
+    },
+    {
+      "epoch": 0.11232768806616779,
+      "grad_norm": 2.6072757244110107,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 1.1499,
+      "step": 4278
+    },
+    {
+      "epoch": 0.11314165682027044,
+      "grad_norm": 1.3471242189407349,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 1.158,
+      "step": 4309
+    },
+    {
+      "epoch": 0.11395562557437311,
+      "grad_norm": 1.6472967863082886,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 1.1474,
+      "step": 4340
+    },
+    {
+      "epoch": 0.11476959432847578,
+      "grad_norm": 2.29596209526062,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 1.1526,
+      "step": 4371
+    },
+    {
+      "epoch": 0.11558356308257844,
+      "grad_norm": 1.2598167657852173,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 1.1563,
+      "step": 4402
+    },
+    {
+      "epoch": 0.11639753183668111,
+      "grad_norm": 1.800126075744629,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.1527,
+      "step": 4433
+    },
+    {
+      "epoch": 0.11721150059078378,
+      "grad_norm": 1.5320085287094116,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 1.154,
+      "step": 4464
+    },
+    {
+      "epoch": 0.11802546934488643,
+      "grad_norm": 1.6290438175201416,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 1.1564,
+      "step": 4495
+    },
+    {
+      "epoch": 0.1188394380989891,
+      "grad_norm": 1.6375097036361694,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 1.1641,
+      "step": 4526
+    },
+    {
+      "epoch": 0.11965340685309177,
+      "grad_norm": 1.5468589067459106,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 1.1419,
+      "step": 4557
+    },
+    {
+      "epoch": 0.12046737560719444,
+      "grad_norm": 1.6913152933120728,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 1.1506,
+      "step": 4588
+    },
+    {
+      "epoch": 0.1212813443612971,
+      "grad_norm": 1.8452041149139404,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 1.1469,
+      "step": 4619
+    },
+    {
+      "epoch": 0.12209531311539977,
+      "grad_norm": 1.7008527517318726,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.1458,
+      "step": 4650
+    },
+    {
+      "epoch": 0.12290928186950242,
+      "grad_norm": 1.6071614027023315,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.155,
+      "step": 4681
+    },
+    {
+      "epoch": 0.12372325062360509,
+      "grad_norm": 1.4235854148864746,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.1359,
+      "step": 4712
+    },
+    {
+      "epoch": 0.12453721937770776,
+      "grad_norm": 1.5262200832366943,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.1487,
+      "step": 4743
+    },
+    {
+      "epoch": 0.12535118813181043,
+      "grad_norm": 1.5988918542861938,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 1.1409,
+      "step": 4774
+    },
+    {
+      "epoch": 0.1261651568859131,
+      "grad_norm": 1.8762277364730835,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.1415,
+      "step": 4805
+    },
+    {
+      "epoch": 0.12697912564001576,
+      "grad_norm": 1.7586325407028198,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.1468,
+      "step": 4836
+    },
+    {
+      "epoch": 0.12779309439411843,
+      "grad_norm": 1.6530872583389282,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.1426,
+      "step": 4867
+    },
+    {
+      "epoch": 0.1286070631482211,
+      "grad_norm": 1.7553999423980713,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.1337,
+      "step": 4898
+    },
+    {
+      "epoch": 0.12942103190232376,
+      "grad_norm": 1.7332961559295654,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.1507,
+      "step": 4929
+    },
+    {
+      "epoch": 0.1302350006564264,
+      "grad_norm": 1.756203532218933,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.1451,
+      "step": 4960
+    },
+    {
+      "epoch": 0.13104896941052907,
+      "grad_norm": 1.4433952569961548,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.1481,
+      "step": 4991
+    },
+    {
+      "epoch": 0.13186293816463174,
+      "grad_norm": 1.4313442707061768,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.1465,
+      "step": 5022
+    },
+    {
+      "epoch": 0.1326769069187344,
+      "grad_norm": 1.5878046751022339,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.1327,
+      "step": 5053
+    },
+    {
+      "epoch": 0.13349087567283707,
+      "grad_norm": 1.4836533069610596,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 1.1336,
+      "step": 5084
+    },
+    {
+      "epoch": 0.13430484442693974,
+      "grad_norm": 1.5261276960372925,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.141,
+      "step": 5115
+    },
+    {
+      "epoch": 0.1351188131810424,
+      "grad_norm": 1.4848837852478027,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.137,
+      "step": 5146
+    },
+    {
+      "epoch": 0.13593278193514508,
+      "grad_norm": 2.077648401260376,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.1502,
+      "step": 5177
+    },
+    {
+      "epoch": 0.13674675068924774,
+      "grad_norm": 2.374537944793701,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.148,
+      "step": 5208
+    },
+    {
+      "epoch": 0.1375607194433504,
+      "grad_norm": 1.7867786884307861,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.1312,
+      "step": 5239
+    },
+    {
+      "epoch": 0.13837468819745308,
+      "grad_norm": 1.8930435180664062,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.1349,
+      "step": 5270
+    },
+    {
+      "epoch": 0.13918865695155572,
+      "grad_norm": 1.636661410331726,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.122,
+      "step": 5301
+    },
+    {
+      "epoch": 0.14000262570565838,
+      "grad_norm": 2.0743846893310547,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.1411,
+      "step": 5332
+    },
+    {
+      "epoch": 0.14081659445976105,
+      "grad_norm": 1.5637271404266357,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.1269,
+      "step": 5363
+    },
+    {
+      "epoch": 0.14163056321386372,
+      "grad_norm": 1.3702319860458374,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.132,
+      "step": 5394
+    },
+    {
+      "epoch": 0.1424445319679664,
+      "grad_norm": 1.3957338333129883,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.1343,
+      "step": 5425
+    },
+    {
+      "epoch": 0.14325850072206905,
+      "grad_norm": 1.6967320442199707,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.1344,
+      "step": 5456
+    },
+    {
+      "epoch": 0.14407246947617172,
+      "grad_norm": 1.5744746923446655,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.1339,
+      "step": 5487
+    },
+    {
+      "epoch": 0.1448864382302744,
+      "grad_norm": 1.5498865842819214,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.1398,
+      "step": 5518
+    },
+    {
+      "epoch": 0.14570040698437706,
+      "grad_norm": 1.3732212781906128,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.1273,
+      "step": 5549
+    },
+    {
+      "epoch": 0.14651437573847972,
+      "grad_norm": 1.3601373434066772,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.116,
+      "step": 5580
+    },
+    {
+      "epoch": 0.1473283444925824,
+      "grad_norm": 1.3350623846054077,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.1228,
+      "step": 5611
+    },
+    {
+      "epoch": 0.14814231324668506,
+      "grad_norm": 1.319671392440796,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.1156,
+      "step": 5642
+    },
+    {
+      "epoch": 0.1489562820007877,
+      "grad_norm": 1.8750630617141724,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.1269,
+      "step": 5673
+    },
+    {
+      "epoch": 0.14977025075489037,
+      "grad_norm": 2.0026299953460693,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.1278,
+      "step": 5704
+    },
+    {
+      "epoch": 0.15058421950899303,
+      "grad_norm": 1.418369174003601,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.1104,
+      "step": 5735
+    },
+    {
+      "epoch": 0.1513981882630957,
+      "grad_norm": 1.5593863725662231,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.1229,
+      "step": 5766
+    },
+    {
+      "epoch": 0.15221215701719837,
+      "grad_norm": 1.6161731481552124,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.1314,
+      "step": 5797
+    },
+    {
+      "epoch": 0.15302612577130104,
+      "grad_norm": 1.509048342704773,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.1192,
+      "step": 5828
+    },
+    {
+      "epoch": 0.1538400945254037,
+      "grad_norm": 1.9641119241714478,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.1221,
+      "step": 5859
+    },
+    {
+      "epoch": 0.15465406327950637,
+      "grad_norm": 1.7621874809265137,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.1223,
+      "step": 5890
+    },
+    {
+      "epoch": 0.15546803203360904,
+      "grad_norm": 2.2426326274871826,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.1266,
+      "step": 5921
+    },
+    {
+      "epoch": 0.1562820007877117,
+      "grad_norm": 1.9674558639526367,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.1243,
+      "step": 5952
+    },
+    {
+      "epoch": 0.15709596954181437,
+      "grad_norm": 1.4433611631393433,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.129,
+      "step": 5983
+    },
+    {
+      "epoch": 0.15790993829591704,
+      "grad_norm": 1.7753652334213257,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.12,
+      "step": 6014
+    },
+    {
+      "epoch": 0.15872390705001968,
+      "grad_norm": 1.9805961847305298,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.1068,
+      "step": 6045
+    },
+    {
+      "epoch": 0.15953787580412235,
+      "grad_norm": 1.1892720460891724,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.1216,
+      "step": 6076
+    },
+    {
+      "epoch": 0.16035184455822502,
+      "grad_norm": 1.7206059694290161,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.1148,
+      "step": 6107
+    },
+    {
+      "epoch": 0.16116581331232768,
+      "grad_norm": 1.7299422025680542,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.0974,
+      "step": 6138
+    },
+    {
+      "epoch": 0.16197978206643035,
+      "grad_norm": 1.5966317653656006,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.106,
+      "step": 6169
+    },
+    {
+      "epoch": 0.16279375082053302,
+      "grad_norm": 1.6218801736831665,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.1103,
+      "step": 6200
+    },
+    {
+      "epoch": 0.16360771957463568,
+      "grad_norm": 1.208667278289795,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.0979,
+      "step": 6231
+    },
+    {
+      "epoch": 0.16442168832873835,
+      "grad_norm": 1.98179030418396,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.1163,
+      "step": 6262
+    },
+    {
+      "epoch": 0.16523565708284102,
+      "grad_norm": 2.215501070022583,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.1213,
+      "step": 6293
+    },
+    {
+      "epoch": 0.1660496258369437,
+      "grad_norm": 1.575427770614624,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.1133,
+      "step": 6324
+    },
+    {
+      "epoch": 0.16686359459104635,
+      "grad_norm": 1.6315374374389648,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.1064,
+      "step": 6355
+    },
+    {
+      "epoch": 0.16767756334514902,
+      "grad_norm": 1.4703013896942139,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.121,
+      "step": 6386
+    },
+    {
+      "epoch": 0.16849153209925166,
+      "grad_norm": 1.553431749343872,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.1099,
+      "step": 6417
+    },
+    {
+      "epoch": 0.16930550085335433,
+      "grad_norm": 1.4701799154281616,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.1002,
+      "step": 6448
+    },
+    {
+      "epoch": 0.170119469607457,
+      "grad_norm": 1.7020679712295532,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.1033,
+      "step": 6479
+    },
+    {
+      "epoch": 0.17093343836155966,
+      "grad_norm": 1.8985180854797363,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.0935,
+      "step": 6510
+    },
+    {
+      "epoch": 0.17174740711566233,
+      "grad_norm": 1.4587364196777344,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.1169,
+      "step": 6541
+    },
+    {
+      "epoch": 0.172561375869765,
+      "grad_norm": 1.525999903678894,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.1205,
+      "step": 6572
+    },
+    {
+      "epoch": 0.17337534462386767,
+      "grad_norm": 1.961179494857788,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.1053,
+      "step": 6603
+    },
+    {
+      "epoch": 0.17418931337797033,
+      "grad_norm": 1.9014114141464233,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.1067,
+      "step": 6634
+    },
+    {
+      "epoch": 0.175003282132073,
+      "grad_norm": 1.3822484016418457,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.1145,
+      "step": 6665
+    },
+    {
+      "epoch": 0.17581725088617567,
+      "grad_norm": 1.573196530342102,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.0908,
+      "step": 6696
+    },
+    {
+      "epoch": 0.17663121964027834,
+      "grad_norm": 1.0946050882339478,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.1068,
+      "step": 6727
+    },
+    {
+      "epoch": 0.17744518839438098,
+      "grad_norm": 1.260721206665039,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.1089,
+      "step": 6758
+    },
+    {
+      "epoch": 0.17825915714848364,
+      "grad_norm": 1.9283548593521118,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.1133,
+      "step": 6789
+    },
+    {
+      "epoch": 0.1790731259025863,
+      "grad_norm": 1.4549671411514282,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.1,
+      "step": 6820
+    },
+    {
+      "epoch": 0.17988709465668898,
+      "grad_norm": 2.1779208183288574,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.1033,
+      "step": 6851
+    },
+    {
+      "epoch": 0.18070106341079165,
+      "grad_norm": 3.1343655586242676,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.104,
+      "step": 6882
+    },
+    {
+      "epoch": 0.1815150321648943,
+      "grad_norm": 1.5330688953399658,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.1068,
+      "step": 6913
+    },
+    {
+      "epoch": 0.18232900091899698,
+      "grad_norm": 1.4057691097259521,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.0965,
+      "step": 6944
+    },
+    {
+      "epoch": 0.18314296967309965,
+      "grad_norm": 1.360346794128418,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.0899,
+      "step": 6975
+    },
+    {
+      "epoch": 0.18395693842720232,
+      "grad_norm": 1.762463092803955,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.0973,
+      "step": 7006
+    },
+    {
+      "epoch": 0.18477090718130498,
+      "grad_norm": 1.6311441659927368,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.0991,
+      "step": 7037
+    },
+    {
+      "epoch": 0.18558487593540765,
+      "grad_norm": 2.032707929611206,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.1026,
+      "step": 7068
+    },
+    {
+      "epoch": 0.18639884468951032,
+      "grad_norm": 1.519220232963562,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.0988,
+      "step": 7099
+    },
+    {
+      "epoch": 0.18721281344361296,
+      "grad_norm": 1.2609440088272095,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.103,
+      "step": 7130
+    },
+    {
+      "epoch": 0.18802678219771563,
+      "grad_norm": 1.3468326330184937,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.0937,
+      "step": 7161
+    },
+    {
+      "epoch": 0.1888407509518183,
+      "grad_norm": 1.8098242282867432,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.0952,
+      "step": 7192
+    },
+    {
+      "epoch": 0.18965471970592096,
+      "grad_norm": 1.881813883781433,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.1013,
+      "step": 7223
+    },
+    {
+      "epoch": 0.19046868846002363,
+      "grad_norm": 1.517236351966858,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.1013,
+      "step": 7254
+    },
+    {
+      "epoch": 0.1912826572141263,
+      "grad_norm": 1.1923933029174805,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.0925,
+      "step": 7285
+    },
+    {
+      "epoch": 0.19209662596822896,
+      "grad_norm": 1.4103548526763916,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.0967,
+      "step": 7316
+    },
+    {
+      "epoch": 0.19291059472233163,
+      "grad_norm": 1.344855546951294,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.0959,
+      "step": 7347
+    },
+    {
+      "epoch": 0.1937245634764343,
+      "grad_norm": 1.6658297777175903,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.1007,
+      "step": 7378
+    },
+    {
+      "epoch": 0.19453853223053696,
+      "grad_norm": 1.3121784925460815,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.1026,
+      "step": 7409
+    },
+    {
+      "epoch": 0.19535250098463963,
+      "grad_norm": 1.4923721551895142,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.1003,
+      "step": 7440
+    },
+    {
+      "epoch": 0.1961664697387423,
+      "grad_norm": 1.6884660720825195,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.0965,
+      "step": 7471
+    },
+    {
+      "epoch": 0.19698043849284494,
+      "grad_norm": 1.6829025745391846,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.0976,
+      "step": 7502
+    },
+    {
+      "epoch": 0.1977944072469476,
+      "grad_norm": 1.8072466850280762,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.086,
+      "step": 7533
+    },
+    {
+      "epoch": 0.19860837600105027,
+      "grad_norm": 1.9585840702056885,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.091,
+      "step": 7564
+    },
+    {
+      "epoch": 0.19942234475515294,
+      "grad_norm": 1.1095181703567505,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.1001,
+      "step": 7595
+    },
+    {
+      "epoch": 0.2002363135092556,
+      "grad_norm": 1.4648469686508179,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.1025,
+      "step": 7626
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 7630,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.303385195250975e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-7630/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab9caa19bbcbaea1127e8615eb39fda6d96afa462c878d00c2364fcb7e8f8ea
+size 5240