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 sha256:4065981afb34f891ec6df1507ca456755b055942d92da5181de0081455cb84d0
+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:d3f917079e285b2a26da2887fb3be3d610c740ed7a86737a9b16461d071fa045
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a383cf91fb9acd7ea23fffb697ca541891f67fb1b76b04cd9d6b1536050d14f7
+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 sha256:9ee7178df40a683e74f30d906181b5d9eda6c5eca36742f6e55163f01d829312
+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": 0.07077593803626919,
+  "eval_steps": 500,
+  "global_step": 7630,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00028755623579611333,
+      "grad_norm": 1.9455794095993042,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 1.1457,
+      "step": 31
+    },
+    {
+      "epoch": 0.0005751124715922267,
+      "grad_norm": 1.4712188243865967,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 1.0982,
+      "step": 62
+    },
+    {
+      "epoch": 0.0008626687073883401,
+      "grad_norm": 1.4395982027053833,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.0874,
+      "step": 93
+    },
+    {
+      "epoch": 0.0011502249431844533,
+      "grad_norm": 1.635319709777832,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.0666,
+      "step": 124
+    },
+    {
+      "epoch": 0.0014377811789805669,
+      "grad_norm": 1.7644890546798706,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.0566,
+      "step": 155
+    },
+    {
+      "epoch": 0.0017253374147766802,
+      "grad_norm": 1.4304418563842773,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 1.0297,
+      "step": 186
+    },
+    {
+      "epoch": 0.0020128936505727935,
+      "grad_norm": 1.7738460302352905,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 1.0381,
+      "step": 217
+    },
+    {
+      "epoch": 0.0023004498863689066,
+      "grad_norm": 1.5791255235671997,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 1.0349,
+      "step": 248
+    },
+    {
+      "epoch": 0.00258800612216502,
+      "grad_norm": 1.8046092987060547,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 1.0162,
+      "step": 279
+    },
+    {
+      "epoch": 0.0028755623579611337,
+      "grad_norm": 2.3568904399871826,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 0.9985,
+      "step": 310
+    },
+    {
+      "epoch": 0.003163118593757247,
+      "grad_norm": 1.7427752017974854,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 0.9988,
+      "step": 341
+    },
+    {
+      "epoch": 0.0034506748295533604,
+      "grad_norm": 2.1790356636047363,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 1.0013,
+      "step": 372
+    },
+    {
+      "epoch": 0.0037382310653494735,
+      "grad_norm": 1.9367269277572632,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 0.9964,
+      "step": 403
+    },
+    {
+      "epoch": 0.004025787301145587,
+      "grad_norm": 2.1018896102905273,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 0.9887,
+      "step": 434
+    },
+    {
+      "epoch": 0.0043133435369417,
+      "grad_norm": 1.754103660583496,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 0.9825,
+      "step": 465
+    },
+    {
+      "epoch": 0.004600899772737813,
+      "grad_norm": 1.9631413221359253,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 0.9743,
+      "step": 496
+    },
+    {
+      "epoch": 0.004888456008533927,
+      "grad_norm": 2.701847553253174,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 0.9757,
+      "step": 527
+    },
+    {
+      "epoch": 0.00517601224433004,
+      "grad_norm": 2.436610460281372,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 0.9554,
+      "step": 558
+    },
+    {
+      "epoch": 0.0054635684801261535,
+      "grad_norm": 2.111328363418579,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 0.966,
+      "step": 589
+    },
+    {
+      "epoch": 0.0057511247159222675,
+      "grad_norm": 1.7960383892059326,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 0.9542,
+      "step": 620
+    },
+    {
+      "epoch": 0.006038680951718381,
+      "grad_norm": 1.5837233066558838,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 0.9525,
+      "step": 651
+    },
+    {
+      "epoch": 0.006326237187514494,
+      "grad_norm": 1.5429449081420898,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 0.9474,
+      "step": 682
+    },
+    {
+      "epoch": 0.006613793423310607,
+      "grad_norm": 2.7319698333740234,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 0.9475,
+      "step": 713
+    },
+    {
+      "epoch": 0.006901349659106721,
+      "grad_norm": 2.2479138374328613,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 0.9513,
+      "step": 744
+    },
+    {
+      "epoch": 0.007188905894902834,
+      "grad_norm": 1.517256498336792,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 0.9488,
+      "step": 775
+    },
+    {
+      "epoch": 0.007476462130698947,
+      "grad_norm": 1.5688025951385498,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 0.94,
+      "step": 806
+    },
+    {
+      "epoch": 0.00776401836649506,
+      "grad_norm": 1.5743234157562256,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 0.9313,
+      "step": 837
+    },
+    {
+      "epoch": 0.008051574602291174,
+      "grad_norm": 2.008028507232666,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.9361,
+      "step": 868
+    },
+    {
+      "epoch": 0.008339130838087287,
+      "grad_norm": 1.65324866771698,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.9219,
+      "step": 899
+    },
+    {
+      "epoch": 0.0086266870738834,
+      "grad_norm": 1.5716785192489624,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.9227,
+      "step": 930
+    },
+    {
+      "epoch": 0.008914243309679513,
+      "grad_norm": 1.7367960214614868,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.9339,
+      "step": 961
+    },
+    {
+      "epoch": 0.009201799545475627,
+      "grad_norm": 1.3708274364471436,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.9181,
+      "step": 992
+    },
+    {
+      "epoch": 0.009489355781271741,
+      "grad_norm": 2.4203550815582275,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.9196,
+      "step": 1023
+    },
+    {
+      "epoch": 0.009776912017067855,
+      "grad_norm": 1.926921010017395,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.9285,
+      "step": 1054
+    },
+    {
+      "epoch": 0.010064468252863968,
+      "grad_norm": 1.27815842628479,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.9083,
+      "step": 1085
+    },
+    {
+      "epoch": 0.01035202448866008,
+      "grad_norm": 1.1785378456115723,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.9171,
+      "step": 1116
+    },
+    {
+      "epoch": 0.010639580724456194,
+      "grad_norm": 1.4379056692123413,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.9228,
+      "step": 1147
+    },
+    {
+      "epoch": 0.010927136960252307,
+      "grad_norm": 1.2898954153060913,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.9049,
+      "step": 1178
+    },
+    {
+      "epoch": 0.01121469319604842,
+      "grad_norm": 1.3358045816421509,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.9065,
+      "step": 1209
+    },
+    {
+      "epoch": 0.011502249431844535,
+      "grad_norm": 1.3427420854568481,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.9043,
+      "step": 1240
+    },
+    {
+      "epoch": 0.011789805667640648,
+      "grad_norm": 1.602563738822937,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.8835,
+      "step": 1271
+    },
+    {
+      "epoch": 0.012077361903436761,
+      "grad_norm": 1.4587140083312988,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.8932,
+      "step": 1302
+    },
+    {
+      "epoch": 0.012364918139232874,
+      "grad_norm": 1.4665412902832031,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.889,
+      "step": 1333
+    },
+    {
+      "epoch": 0.012652474375028987,
+      "grad_norm": 1.1323597431182861,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.9121,
+      "step": 1364
+    },
+    {
+      "epoch": 0.0129400306108251,
+      "grad_norm": 1.342729091644287,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.8945,
+      "step": 1395
+    },
+    {
+      "epoch": 0.013227586846621214,
+      "grad_norm": 1.1981477737426758,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.8945,
+      "step": 1426
+    },
+    {
+      "epoch": 0.013515143082417327,
+      "grad_norm": 1.2309355735778809,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.8912,
+      "step": 1457
+    },
+    {
+      "epoch": 0.013802699318213442,
+      "grad_norm": 1.352373480796814,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.8807,
+      "step": 1488
+    },
+    {
+      "epoch": 0.014090255554009555,
+      "grad_norm": 1.0303138494491577,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 0.8901,
+      "step": 1519
+    },
+    {
+      "epoch": 0.014377811789805668,
+      "grad_norm": 1.3504307270050049,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.8822,
+      "step": 1550
+    },
+    {
+      "epoch": 0.014665368025601781,
+      "grad_norm": 1.4113889932632446,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.8784,
+      "step": 1581
+    },
+    {
+      "epoch": 0.014952924261397894,
+      "grad_norm": 1.0135654211044312,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.8848,
+      "step": 1612
+    },
+    {
+      "epoch": 0.015240480497194007,
+      "grad_norm": 1.190436601638794,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.8833,
+      "step": 1643
+    },
+    {
+      "epoch": 0.01552803673299012,
+      "grad_norm": 1.0690772533416748,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 0.871,
+      "step": 1674
+    },
+    {
+      "epoch": 0.015815592968786235,
+      "grad_norm": 1.8002996444702148,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 0.8676,
+      "step": 1705
+    },
+    {
+      "epoch": 0.016103149204582348,
+      "grad_norm": 1.1526492834091187,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.8663,
+      "step": 1736
+    },
+    {
+      "epoch": 0.01639070544037846,
+      "grad_norm": 1.0163888931274414,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.8499,
+      "step": 1767
+    },
+    {
+      "epoch": 0.016678261676174574,
+      "grad_norm": 1.2611489295959473,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.8662,
+      "step": 1798
+    },
+    {
+      "epoch": 0.016965817911970688,
+      "grad_norm": 1.2373474836349487,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.8502,
+      "step": 1829
+    },
+    {
+      "epoch": 0.0172533741477668,
+      "grad_norm": 1.1296851634979248,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 0.8484,
+      "step": 1860
+    },
+    {
+      "epoch": 0.017540930383562914,
+      "grad_norm": 1.0827291011810303,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 0.8544,
+      "step": 1891
+    },
+    {
+      "epoch": 0.017828486619359027,
+      "grad_norm": 1.3426434993743896,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 0.857,
+      "step": 1922
+    },
+    {
+      "epoch": 0.01811604285515514,
+      "grad_norm": 1.201955795288086,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 0.8603,
+      "step": 1953
+    },
+    {
+      "epoch": 0.018403599090951253,
+      "grad_norm": 1.3037333488464355,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 0.8452,
+      "step": 1984
+    },
+    {
+      "epoch": 0.018691155326747366,
+      "grad_norm": 0.8663549423217773,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.8372,
+      "step": 2015
+    },
+    {
+      "epoch": 0.018978711562543483,
+      "grad_norm": 0.9077154397964478,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.8541,
+      "step": 2046
+    },
+    {
+      "epoch": 0.019266267798339596,
+      "grad_norm": 0.9359773397445679,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.843,
+      "step": 2077
+    },
+    {
+      "epoch": 0.01955382403413571,
+      "grad_norm": 1.0448205471038818,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.8461,
+      "step": 2108
+    },
+    {
+      "epoch": 0.019841380269931822,
+      "grad_norm": 1.0004512071609497,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.8451,
+      "step": 2139
+    },
+    {
+      "epoch": 0.020128936505727935,
+      "grad_norm": 0.9513603448867798,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.8404,
+      "step": 2170
+    },
+    {
+      "epoch": 0.02041649274152405,
+      "grad_norm": 0.8558681607246399,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 0.8436,
+      "step": 2201
+    },
+    {
+      "epoch": 0.02070404897732016,
+      "grad_norm": 1.0582232475280762,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 0.8317,
+      "step": 2232
+    },
+    {
+      "epoch": 0.020991605213116275,
+      "grad_norm": 0.8992099761962891,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.8263,
+      "step": 2263
+    },
+    {
+      "epoch": 0.021279161448912388,
+      "grad_norm": 1.0153640508651733,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.816,
+      "step": 2294
+    },
+    {
+      "epoch": 0.0215667176847085,
+      "grad_norm": 0.8875217437744141,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.8287,
+      "step": 2325
+    },
+    {
+      "epoch": 0.021854273920504614,
+      "grad_norm": 0.9286942481994629,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.8359,
+      "step": 2356
+    },
+    {
+      "epoch": 0.022141830156300727,
+      "grad_norm": 1.0928508043289185,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.8214,
+      "step": 2387
+    },
+    {
+      "epoch": 0.02242938639209684,
+      "grad_norm": 1.0555698871612549,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.8254,
+      "step": 2418
+    },
+    {
+      "epoch": 0.022716942627892953,
+      "grad_norm": 0.7832269668579102,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.822,
+      "step": 2449
+    },
+    {
+      "epoch": 0.02300449886368907,
+      "grad_norm": 0.9921287298202515,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.8266,
+      "step": 2480
+    },
+    {
+      "epoch": 0.023292055099485183,
+      "grad_norm": 0.9082629084587097,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.8309,
+      "step": 2511
+    },
+    {
+      "epoch": 0.023579611335281296,
+      "grad_norm": 0.6366026401519775,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.8246,
+      "step": 2542
+    },
+    {
+      "epoch": 0.02386716757107741,
+      "grad_norm": 0.7414658665657043,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.8231,
+      "step": 2573
+    },
+    {
+      "epoch": 0.024154723806873522,
+      "grad_norm": 1.1124039888381958,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.819,
+      "step": 2604
+    },
+    {
+      "epoch": 0.024442280042669635,
+      "grad_norm": 0.7437085509300232,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.8018,
+      "step": 2635
+    },
+    {
+      "epoch": 0.02472983627846575,
+      "grad_norm": 0.809686541557312,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.8117,
+      "step": 2666
+    },
+    {
+      "epoch": 0.02501739251426186,
+      "grad_norm": 0.8334315419197083,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.8065,
+      "step": 2697
+    },
+    {
+      "epoch": 0.025304948750057975,
+      "grad_norm": 0.8860774636268616,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.8051,
+      "step": 2728
+    },
+    {
+      "epoch": 0.025592504985854088,
+      "grad_norm": 1.0246986150741577,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.817,
+      "step": 2759
+    },
+    {
+      "epoch": 0.0258800612216502,
+      "grad_norm": 0.9289675354957581,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.8166,
+      "step": 2790
+    },
+    {
+      "epoch": 0.026167617457446314,
+      "grad_norm": 0.8356702327728271,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.7965,
+      "step": 2821
+    },
+    {
+      "epoch": 0.026455173693242427,
+      "grad_norm": 0.8671677708625793,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.8011,
+      "step": 2852
+    },
+    {
+      "epoch": 0.02674272992903854,
+      "grad_norm": 0.7215815186500549,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.8101,
+      "step": 2883
+    },
+    {
+      "epoch": 0.027030286164834653,
+      "grad_norm": 0.7657960057258606,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.8125,
+      "step": 2914
+    },
+    {
+      "epoch": 0.02731784240063077,
+      "grad_norm": 0.9577224254608154,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.8057,
+      "step": 2945
+    },
+    {
+      "epoch": 0.027605398636426883,
+      "grad_norm": 0.8292474746704102,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.8124,
+      "step": 2976
+    },
+    {
+      "epoch": 0.027892954872222996,
+      "grad_norm": 0.7864797711372375,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.8188,
+      "step": 3007
+    },
+    {
+      "epoch": 0.02818051110801911,
+      "grad_norm": 0.7558257579803467,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.8007,
+      "step": 3038
+    },
+    {
+      "epoch": 0.028468067343815222,
+      "grad_norm": 0.8115010857582092,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.8031,
+      "step": 3069
+    },
+    {
+      "epoch": 0.028755623579611336,
+      "grad_norm": 0.7696826457977295,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.7943,
+      "step": 3100
+    },
+    {
+      "epoch": 0.02904317981540745,
+      "grad_norm": 0.8541676998138428,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.8076,
+      "step": 3131
+    },
+    {
+      "epoch": 0.029330736051203562,
+      "grad_norm": 0.8071252107620239,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.8013,
+      "step": 3162
+    },
+    {
+      "epoch": 0.029618292286999675,
+      "grad_norm": 0.7903591990470886,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.8044,
+      "step": 3193
+    },
+    {
+      "epoch": 0.029905848522795788,
+      "grad_norm": 0.8176108002662659,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.8071,
+      "step": 3224
+    },
+    {
+      "epoch": 0.0301934047585919,
+      "grad_norm": 0.8619785308837891,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.7933,
+      "step": 3255
+    },
+    {
+      "epoch": 0.030480960994388014,
+      "grad_norm": 0.9317312240600586,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.7923,
+      "step": 3286
+    },
+    {
+      "epoch": 0.030768517230184127,
+      "grad_norm": 4.923175811767578,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.8053,
+      "step": 3317
+    },
+    {
+      "epoch": 0.03105607346598024,
+      "grad_norm": 0.8844607472419739,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.7995,
+      "step": 3348
+    },
+    {
+      "epoch": 0.03134362970177636,
+      "grad_norm": 0.9158428311347961,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.7944,
+      "step": 3379
+    },
+    {
+      "epoch": 0.03163118593757247,
+      "grad_norm": 0.7781556844711304,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.7916,
+      "step": 3410
+    },
+    {
+      "epoch": 0.03191874217336858,
+      "grad_norm": 0.9503144025802612,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.8013,
+      "step": 3441
+    },
+    {
+      "epoch": 0.032206298409164696,
+      "grad_norm": 0.7559428215026855,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.7816,
+      "step": 3472
+    },
+    {
+      "epoch": 0.03249385464496081,
+      "grad_norm": 0.7235283851623535,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.7884,
+      "step": 3503
+    },
+    {
+      "epoch": 0.03278141088075692,
+      "grad_norm": 0.6889526844024658,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.7869,
+      "step": 3534
+    },
+    {
+      "epoch": 0.033068967116553036,
+      "grad_norm": 0.6442049741744995,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.7882,
+      "step": 3565
+    },
+    {
+      "epoch": 0.03335652335234915,
+      "grad_norm": 0.7874131798744202,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.7943,
+      "step": 3596
+    },
+    {
+      "epoch": 0.03364407958814526,
+      "grad_norm": 0.9890303611755371,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.7953,
+      "step": 3627
+    },
+    {
+      "epoch": 0.033931635823941375,
+      "grad_norm": 0.7489719390869141,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.7941,
+      "step": 3658
+    },
+    {
+      "epoch": 0.03421919205973749,
+      "grad_norm": 1.4524290561676025,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.7871,
+      "step": 3689
+    },
+    {
+      "epoch": 0.0345067482955336,
+      "grad_norm": 0.9255936145782471,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.7832,
+      "step": 3720
+    },
+    {
+      "epoch": 0.034794304531329714,
+      "grad_norm": 0.7341301441192627,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.7739,
+      "step": 3751
+    },
+    {
+      "epoch": 0.03508186076712583,
+      "grad_norm": 0.8778953552246094,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.7825,
+      "step": 3782
+    },
+    {
+      "epoch": 0.03536941700292194,
+      "grad_norm": 0.7216904163360596,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.7897,
+      "step": 3813
+    },
+    {
+      "epoch": 0.035656973238718054,
+      "grad_norm": 0.682104766368866,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.7883,
+      "step": 3844
+    },
+    {
+      "epoch": 0.03594452947451417,
+      "grad_norm": 0.6915758848190308,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.7833,
+      "step": 3875
+    },
+    {
+      "epoch": 0.03623208571031028,
+      "grad_norm": 0.69737309217453,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.7761,
+      "step": 3906
+    },
+    {
+      "epoch": 0.03651964194610639,
+      "grad_norm": 0.6854519844055176,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.7836,
+      "step": 3937
+    },
+    {
+      "epoch": 0.036807198181902506,
+      "grad_norm": 0.7395520806312561,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.7879,
+      "step": 3968
+    },
+    {
+      "epoch": 0.03709475441769862,
+      "grad_norm": 0.8215503096580505,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.7789,
+      "step": 3999
+    },
+    {
+      "epoch": 0.03738231065349473,
+      "grad_norm": 0.7327520251274109,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.7822,
+      "step": 4030
+    },
+    {
+      "epoch": 0.03766986688929085,
+      "grad_norm": 0.6182845234870911,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.7706,
+      "step": 4061
+    },
+    {
+      "epoch": 0.037957423125086966,
+      "grad_norm": 0.6680454611778259,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.783,
+      "step": 4092
+    },
+    {
+      "epoch": 0.03824497936088308,
+      "grad_norm": 0.7800632119178772,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.7712,
+      "step": 4123
+    },
+    {
+      "epoch": 0.03853253559667919,
+      "grad_norm": 1.3335139751434326,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.7773,
+      "step": 4154
+    },
+    {
+      "epoch": 0.038820091832475305,
+      "grad_norm": 0.851414144039154,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.7887,
+      "step": 4185
+    },
+    {
+      "epoch": 0.03910764806827142,
+      "grad_norm": 0.9367514252662659,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.7665,
+      "step": 4216
+    },
+    {
+      "epoch": 0.03939520430406753,
+      "grad_norm": 0.9181923270225525,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.7656,
+      "step": 4247
+    },
+    {
+      "epoch": 0.039682760539863644,
+      "grad_norm": 0.7090054154396057,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.78,
+      "step": 4278
+    },
+    {
+      "epoch": 0.03997031677565976,
+      "grad_norm": 0.7867220640182495,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.7642,
+      "step": 4309
+    },
+    {
+      "epoch": 0.04025787301145587,
+      "grad_norm": 0.6757919788360596,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.7761,
+      "step": 4340
+    },
+    {
+      "epoch": 0.040545429247251984,
+      "grad_norm": 0.7119040489196777,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.7749,
+      "step": 4371
+    },
+    {
+      "epoch": 0.0408329854830481,
+      "grad_norm": 0.7401456236839294,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.7827,
+      "step": 4402
+    },
+    {
+      "epoch": 0.04112054171884421,
+      "grad_norm": 0.7937046885490417,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.7803,
+      "step": 4433
+    },
+    {
+      "epoch": 0.04140809795464032,
+      "grad_norm": 0.6040141582489014,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.7716,
+      "step": 4464
+    },
+    {
+      "epoch": 0.041695654190436436,
+      "grad_norm": 0.6961768269538879,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.7823,
+      "step": 4495
+    },
+    {
+      "epoch": 0.04198321042623255,
+      "grad_norm": 0.842772901058197,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.7803,
+      "step": 4526
+    },
+    {
+      "epoch": 0.04227076666202866,
+      "grad_norm": 0.7007623314857483,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.7621,
+      "step": 4557
+    },
+    {
+      "epoch": 0.042558322897824775,
+      "grad_norm": 0.8964999914169312,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.7725,
+      "step": 4588
+    },
+    {
+      "epoch": 0.04284587913362089,
+      "grad_norm": 0.6525081396102905,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.7713,
+      "step": 4619
+    },
+    {
+      "epoch": 0.043133435369417,
+      "grad_norm": 0.7347533106803894,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.7678,
+      "step": 4650
+    },
+    {
+      "epoch": 0.043420991605213115,
+      "grad_norm": 0.898430585861206,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.7768,
+      "step": 4681
+    },
+    {
+      "epoch": 0.04370854784100923,
+      "grad_norm": 0.8022106289863586,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.7613,
+      "step": 4712
+    },
+    {
+      "epoch": 0.04399610407680534,
+      "grad_norm": 0.6806633472442627,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.7611,
+      "step": 4743
+    },
+    {
+      "epoch": 0.044283660312601454,
+      "grad_norm": 0.6868746280670166,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.768,
+      "step": 4774
+    },
+    {
+      "epoch": 0.04457121654839757,
+      "grad_norm": 0.6708130836486816,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.7656,
+      "step": 4805
+    },
+    {
+      "epoch": 0.04485877278419368,
+      "grad_norm": 0.8395335078239441,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.7606,
+      "step": 4836
+    },
+    {
+      "epoch": 0.045146329019989793,
+      "grad_norm": 0.7094994783401489,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.7588,
+      "step": 4867
+    },
+    {
+      "epoch": 0.04543388525578591,
+      "grad_norm": 0.7718915343284607,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.7605,
+      "step": 4898
+    },
+    {
+      "epoch": 0.04572144149158202,
+      "grad_norm": 0.7593154311180115,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.7699,
+      "step": 4929
+    },
+    {
+      "epoch": 0.04600899772737814,
+      "grad_norm": 0.7768173217773438,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.7655,
+      "step": 4960
+    },
+    {
+      "epoch": 0.04629655396317425,
+      "grad_norm": 22.10868263244629,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.7834,
+      "step": 4991
+    },
+    {
+      "epoch": 0.046584110198970366,
+      "grad_norm": 0.7258509993553162,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.7762,
+      "step": 5022
+    },
+    {
+      "epoch": 0.04687166643476648,
+      "grad_norm": 0.6087211966514587,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.7764,
+      "step": 5053
+    },
+    {
+      "epoch": 0.04715922267056259,
+      "grad_norm": 0.7252562642097473,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.764,
+      "step": 5084
+    },
+    {
+      "epoch": 0.047446778906358705,
+      "grad_norm": 0.6546025276184082,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.7662,
+      "step": 5115
+    },
+    {
+      "epoch": 0.04773433514215482,
+      "grad_norm": 0.8831254243850708,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.7671,
+      "step": 5146
+    },
+    {
+      "epoch": 0.04802189137795093,
+      "grad_norm": 0.6685829162597656,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.7673,
+      "step": 5177
+    },
+    {
+      "epoch": 0.048309447613747045,
+      "grad_norm": 0.8013454079627991,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.7584,
+      "step": 5208
+    },
+    {
+      "epoch": 0.04859700384954316,
+      "grad_norm": 0.7176809906959534,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.741,
+      "step": 5239
+    },
+    {
+      "epoch": 0.04888456008533927,
+      "grad_norm": 0.7257890701293945,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.737,
+      "step": 5270
+    },
+    {
+      "epoch": 0.049172116321135384,
+      "grad_norm": 0.5510952472686768,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.7593,
+      "step": 5301
+    },
+    {
+      "epoch": 0.0494596725569315,
+      "grad_norm": 0.6861957907676697,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.7628,
+      "step": 5332
+    },
+    {
+      "epoch": 0.04974722879272761,
+      "grad_norm": 0.8587688207626343,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.7727,
+      "step": 5363
+    },
+    {
+      "epoch": 0.05003478502852372,
+      "grad_norm": 0.8064201474189758,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.7518,
+      "step": 5394
+    },
+    {
+      "epoch": 0.050322341264319836,
+      "grad_norm": 0.616675853729248,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.7441,
+      "step": 5425
+    },
+    {
+      "epoch": 0.05060989750011595,
+      "grad_norm": 0.649145245552063,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.7616,
+      "step": 5456
+    },
+    {
+      "epoch": 0.05089745373591206,
+      "grad_norm": 0.7101767063140869,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.7415,
+      "step": 5487
+    },
+    {
+      "epoch": 0.051185009971708176,
+      "grad_norm": 0.707365095615387,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.75,
+      "step": 5518
+    },
+    {
+      "epoch": 0.05147256620750429,
+      "grad_norm": 0.84593266248703,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.7518,
+      "step": 5549
+    },
+    {
+      "epoch": 0.0517601224433004,
+      "grad_norm": 0.7127841711044312,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.7542,
+      "step": 5580
+    },
+    {
+      "epoch": 0.052047678679096515,
+      "grad_norm": 0.6939860582351685,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.7644,
+      "step": 5611
+    },
+    {
+      "epoch": 0.05233523491489263,
+      "grad_norm": 0.6775111556053162,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.7527,
+      "step": 5642
+    },
+    {
+      "epoch": 0.05262279115068874,
+      "grad_norm": 0.714107096195221,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.7688,
+      "step": 5673
+    },
+    {
+      "epoch": 0.052910347386484854,
+      "grad_norm": 0.6642836928367615,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.7419,
+      "step": 5704
+    },
+    {
+      "epoch": 0.05319790362228097,
+      "grad_norm": 0.6652647852897644,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.7364,
+      "step": 5735
+    },
+    {
+      "epoch": 0.05348545985807708,
+      "grad_norm": 0.7523749470710754,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.7417,
+      "step": 5766
+    },
+    {
+      "epoch": 0.053773016093873194,
+      "grad_norm": 0.7240698337554932,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.7475,
+      "step": 5797
+    },
+    {
+      "epoch": 0.05406057232966931,
+      "grad_norm": 0.6656080484390259,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.7549,
+      "step": 5828
+    },
+    {
+      "epoch": 0.05434812856546543,
+      "grad_norm": 0.7825058102607727,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.7617,
+      "step": 5859
+    },
+    {
+      "epoch": 0.05463568480126154,
+      "grad_norm": 0.6925270557403564,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.7645,
+      "step": 5890
+    },
+    {
+      "epoch": 0.05492324103705765,
+      "grad_norm": 0.6845418810844421,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.7651,
+      "step": 5921
+    },
+    {
+      "epoch": 0.055210797272853766,
+      "grad_norm": 0.7644496560096741,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.7416,
+      "step": 5952
+    },
+    {
+      "epoch": 0.05549835350864988,
+      "grad_norm": 0.6768073439598083,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.7382,
+      "step": 5983
+    },
+    {
+      "epoch": 0.05578590974444599,
+      "grad_norm": 0.7582330107688904,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.7576,
+      "step": 6014
+    },
+    {
+      "epoch": 0.056073465980242106,
+      "grad_norm": 0.7167056202888489,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.7531,
+      "step": 6045
+    },
+    {
+      "epoch": 0.05636102221603822,
+      "grad_norm": 0.7577204704284668,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.7435,
+      "step": 6076
+    },
+    {
+      "epoch": 0.05664857845183433,
+      "grad_norm": 0.6813349723815918,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.7394,
+      "step": 6107
+    },
+    {
+      "epoch": 0.056936134687630445,
+      "grad_norm": 0.7912815809249878,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.7497,
+      "step": 6138
+    },
+    {
+      "epoch": 0.05722369092342656,
+      "grad_norm": 0.6915249228477478,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.7442,
+      "step": 6169
+    },
+    {
+      "epoch": 0.05751124715922267,
+      "grad_norm": 0.6465253829956055,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.748,
+      "step": 6200
+    },
+    {
+      "epoch": 0.057798803395018784,
+      "grad_norm": 0.7075664401054382,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.7436,
+      "step": 6231
+    },
+    {
+      "epoch": 0.0580863596308149,
+      "grad_norm": 0.5963169932365417,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.7528,
+      "step": 6262
+    },
+    {
+      "epoch": 0.05837391586661101,
+      "grad_norm": 0.7071893811225891,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.7481,
+      "step": 6293
+    },
+    {
+      "epoch": 0.058661472102407124,
+      "grad_norm": 0.6649565696716309,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.7462,
+      "step": 6324
+    },
+    {
+      "epoch": 0.05894902833820324,
+      "grad_norm": 0.6576278209686279,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.7313,
+      "step": 6355
+    },
+    {
+      "epoch": 0.05923658457399935,
+      "grad_norm": 0.6180335283279419,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.7498,
+      "step": 6386
+    },
+    {
+      "epoch": 0.05952414080979546,
+      "grad_norm": 0.5831409096717834,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.7361,
+      "step": 6417
+    },
+    {
+      "epoch": 0.059811697045591576,
+      "grad_norm": 0.6521987318992615,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.7501,
+      "step": 6448
+    },
+    {
+      "epoch": 0.06009925328138769,
+      "grad_norm": 0.6368945240974426,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.7456,
+      "step": 6479
+    },
+    {
+      "epoch": 0.0603868095171838,
+      "grad_norm": 0.6165626049041748,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.7438,
+      "step": 6510
+    },
+    {
+      "epoch": 0.060674365752979915,
+      "grad_norm": 0.7067050337791443,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.7499,
+      "step": 6541
+    },
+    {
+      "epoch": 0.06096192198877603,
+      "grad_norm": 0.7632570862770081,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.7356,
+      "step": 6572
+    },
+    {
+      "epoch": 0.06124947822457214,
+      "grad_norm": 0.838828980922699,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.7384,
+      "step": 6603
+    },
+    {
+      "epoch": 0.061537034460368255,
+      "grad_norm": 0.7371137142181396,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.7423,
+      "step": 6634
+    },
+    {
+      "epoch": 0.06182459069616437,
+      "grad_norm": 0.6346718072891235,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.7354,
+      "step": 6665
+    },
+    {
+      "epoch": 0.06211214693196048,
+      "grad_norm": 0.6456010341644287,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.7342,
+      "step": 6696
+    },
+    {
+      "epoch": 0.062399703167756594,
+      "grad_norm": 0.6201857924461365,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.7282,
+      "step": 6727
+    },
+    {
+      "epoch": 0.06268725940355271,
+      "grad_norm": 0.6899628043174744,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.7375,
+      "step": 6758
+    },
+    {
+      "epoch": 0.06297481563934883,
+      "grad_norm": 0.599892258644104,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.7409,
+      "step": 6789
+    },
+    {
+      "epoch": 0.06326237187514494,
+      "grad_norm": 0.6443545818328857,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.7455,
+      "step": 6820
+    },
+    {
+      "epoch": 0.06354992811094105,
+      "grad_norm": 0.7208391427993774,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.7491,
+      "step": 6851
+    },
+    {
+      "epoch": 0.06383748434673717,
+      "grad_norm": 0.7535425424575806,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.7396,
+      "step": 6882
+    },
+    {
+      "epoch": 0.06412504058253328,
+      "grad_norm": 0.8142176866531372,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.7525,
+      "step": 6913
+    },
+    {
+      "epoch": 0.06441259681832939,
+      "grad_norm": 0.7619569897651672,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.7308,
+      "step": 6944
+    },
+    {
+      "epoch": 0.0647001530541255,
+      "grad_norm": 0.6831880807876587,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.7323,
+      "step": 6975
+    },
+    {
+      "epoch": 0.06498770928992162,
+      "grad_norm": 0.7584510445594788,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.7305,
+      "step": 7006
+    },
+    {
+      "epoch": 0.06527526552571773,
+      "grad_norm": 0.5771958827972412,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.7292,
+      "step": 7037
+    },
+    {
+      "epoch": 0.06556282176151385,
+      "grad_norm": 0.6861974596977234,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.7301,
+      "step": 7068
+    },
+    {
+      "epoch": 0.06585037799730996,
+      "grad_norm": 0.6061118841171265,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.738,
+      "step": 7099
+    },
+    {
+      "epoch": 0.06613793423310607,
+      "grad_norm": 0.5882508158683777,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.7499,
+      "step": 7130
+    },
+    {
+      "epoch": 0.06642549046890218,
+      "grad_norm": 0.6508737206459045,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.7484,
+      "step": 7161
+    },
+    {
+      "epoch": 0.0667130467046983,
+      "grad_norm": 0.5774248242378235,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.7351,
+      "step": 7192
+    },
+    {
+      "epoch": 0.06700060294049441,
+      "grad_norm": 0.8253674507141113,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.7329,
+      "step": 7223
+    },
+    {
+      "epoch": 0.06728815917629052,
+      "grad_norm": 0.6259687542915344,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.7375,
+      "step": 7254
+    },
+    {
+      "epoch": 0.06757571541208664,
+      "grad_norm": 0.6426525115966797,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.732,
+      "step": 7285
+    },
+    {
+      "epoch": 0.06786327164788275,
+      "grad_norm": 0.7058547139167786,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.7344,
+      "step": 7316
+    },
+    {
+      "epoch": 0.06815082788367886,
+      "grad_norm": 0.5909351706504822,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.7298,
+      "step": 7347
+    },
+    {
+      "epoch": 0.06843838411947498,
+      "grad_norm": 0.6617700457572937,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.7443,
+      "step": 7378
+    },
+    {
+      "epoch": 0.06872594035527109,
+      "grad_norm": 0.6690764427185059,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.7407,
+      "step": 7409
+    },
+    {
+      "epoch": 0.0690134965910672,
+      "grad_norm": 0.6452279686927795,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.7375,
+      "step": 7440
+    },
+    {
+      "epoch": 0.06930105282686332,
+      "grad_norm": 0.6305842399597168,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.7274,
+      "step": 7471
+    },
+    {
+      "epoch": 0.06958860906265943,
+      "grad_norm": 0.6651537418365479,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.7333,
+      "step": 7502
+    },
+    {
+      "epoch": 0.06987616529845554,
+      "grad_norm": 0.7118179202079773,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.7322,
+      "step": 7533
+    },
+    {
+      "epoch": 0.07016372153425166,
+      "grad_norm": 0.618417501449585,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.7286,
+      "step": 7564
+    },
+    {
+      "epoch": 0.07045127777004777,
+      "grad_norm": 0.5909223556518555,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.7338,
+      "step": 7595
+    },
+    {
+      "epoch": 0.07073883400584388,
+      "grad_norm": 0.6071949601173401,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.7218,
+      "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 sha256:08815548a100e5acdd0a48cf1bebdaf5ac1f995718a6e734dbfe9db26d9d6730
+size 5240