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:ecf1d912fe324116593da075376da190d9833c8e2cb29427361d6208195f9c54
+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 sha256:4b4938ec87ac8d9940b90a64e5b5cb6de0cc3852f1816630ad93c6bae9ea2182
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8867e3c6a7c5dfae7830ab25fcd5dc6c9260f61d6db6c03d38095656d804f5
+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:b0d5743072d1dd14504f72482fb6c2852f2c920e0b529c5286331fc6606239e5
+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": 0.11447776085700782,
+  "eval_steps": 500,
+  "global_step": 7630,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000465112789851539,
+      "grad_norm": 1.784651517868042,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 1.2289,
+      "step": 31
+    },
+    {
+      "epoch": 0.000930225579703078,
+      "grad_norm": 1.6836942434310913,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 1.204,
+      "step": 62
+    },
+    {
+      "epoch": 0.001395338369554617,
+      "grad_norm": 1.5462840795516968,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.1613,
+      "step": 93
+    },
+    {
+      "epoch": 0.001860451159406156,
+      "grad_norm": 1.6598711013793945,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.1533,
+      "step": 124
+    },
+    {
+      "epoch": 0.002325563949257695,
+      "grad_norm": 1.6803102493286133,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.1145,
+      "step": 155
+    },
+    {
+      "epoch": 0.002790676739109234,
+      "grad_norm": 1.7680474519729614,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 1.1144,
+      "step": 186
+    },
+    {
+      "epoch": 0.003255789528960773,
+      "grad_norm": 1.9584507942199707,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 1.1003,
+      "step": 217
+    },
+    {
+      "epoch": 0.003720902318812312,
+      "grad_norm": 1.9814798831939697,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 1.1109,
+      "step": 248
+    },
+    {
+      "epoch": 0.004186015108663851,
+      "grad_norm": 1.8097580671310425,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 1.0843,
+      "step": 279
+    },
+    {
+      "epoch": 0.00465112789851539,
+      "grad_norm": 2.0356101989746094,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 1.0692,
+      "step": 310
+    },
+    {
+      "epoch": 0.005116240688366929,
+      "grad_norm": 1.9637826681137085,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 1.0607,
+      "step": 341
+    },
+    {
+      "epoch": 0.005581353478218468,
+      "grad_norm": 1.7614696025848389,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 1.0709,
+      "step": 372
+    },
+    {
+      "epoch": 0.006046466268070007,
+      "grad_norm": 1.9089475870132446,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 1.0488,
+      "step": 403
+    },
+    {
+      "epoch": 0.006511579057921546,
+      "grad_norm": 1.7092220783233643,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 1.0464,
+      "step": 434
+    },
+    {
+      "epoch": 0.006976691847773085,
+      "grad_norm": 1.9329888820648193,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 1.0461,
+      "step": 465
+    },
+    {
+      "epoch": 0.007441804637624624,
+      "grad_norm": 2.172822952270508,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 1.0419,
+      "step": 496
+    },
+    {
+      "epoch": 0.007906917427476163,
+      "grad_norm": 2.104287624359131,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 1.0332,
+      "step": 527
+    },
+    {
+      "epoch": 0.008372030217327702,
+      "grad_norm": 1.766613483428955,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 1.0327,
+      "step": 558
+    },
+    {
+      "epoch": 0.00883714300717924,
+      "grad_norm": 2.012824058532715,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 1.0354,
+      "step": 589
+    },
+    {
+      "epoch": 0.00930225579703078,
+      "grad_norm": 2.0188724994659424,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 1.0198,
+      "step": 620
+    },
+    {
+      "epoch": 0.009767368586882319,
+      "grad_norm": 1.7517170906066895,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 1.0161,
+      "step": 651
+    },
+    {
+      "epoch": 0.010232481376733858,
+      "grad_norm": 2.030271530151367,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 1.0026,
+      "step": 682
+    },
+    {
+      "epoch": 0.010697594166585398,
+      "grad_norm": 1.7064554691314697,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 1.0051,
+      "step": 713
+    },
+    {
+      "epoch": 0.011162706956436936,
+      "grad_norm": 1.7866902351379395,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 1.0055,
+      "step": 744
+    },
+    {
+      "epoch": 0.011627819746288475,
+      "grad_norm": 1.6631230115890503,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 0.9984,
+      "step": 775
+    },
+    {
+      "epoch": 0.012092932536140013,
+      "grad_norm": 1.9981967210769653,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 1.0003,
+      "step": 806
+    },
+    {
+      "epoch": 0.012558045325991554,
+      "grad_norm": 1.6636446714401245,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 0.9871,
+      "step": 837
+    },
+    {
+      "epoch": 0.013023158115843092,
+      "grad_norm": 1.6821868419647217,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.9869,
+      "step": 868
+    },
+    {
+      "epoch": 0.01348827090569463,
+      "grad_norm": 1.7862061262130737,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.9782,
+      "step": 899
+    },
+    {
+      "epoch": 0.01395338369554617,
+      "grad_norm": 1.743594765663147,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.9848,
+      "step": 930
+    },
+    {
+      "epoch": 0.01441849648539771,
+      "grad_norm": 1.673101782798767,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.9799,
+      "step": 961
+    },
+    {
+      "epoch": 0.014883609275249248,
+      "grad_norm": 1.7535595893859863,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.9868,
+      "step": 992
+    },
+    {
+      "epoch": 0.015348722065100786,
+      "grad_norm": 1.6869490146636963,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.9743,
+      "step": 1023
+    },
+    {
+      "epoch": 0.015813834854952327,
+      "grad_norm": 2.0066351890563965,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.9642,
+      "step": 1054
+    },
+    {
+      "epoch": 0.016278947644803865,
+      "grad_norm": 1.7409238815307617,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.9658,
+      "step": 1085
+    },
+    {
+      "epoch": 0.016744060434655404,
+      "grad_norm": 1.4720958471298218,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.9546,
+      "step": 1116
+    },
+    {
+      "epoch": 0.017209173224506942,
+      "grad_norm": 1.3574339151382446,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.9588,
+      "step": 1147
+    },
+    {
+      "epoch": 0.01767428601435848,
+      "grad_norm": 1.4988070726394653,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.961,
+      "step": 1178
+    },
+    {
+      "epoch": 0.018139398804210023,
+      "grad_norm": 1.5694591999053955,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.9572,
+      "step": 1209
+    },
+    {
+      "epoch": 0.01860451159406156,
+      "grad_norm": 1.530637502670288,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.951,
+      "step": 1240
+    },
+    {
+      "epoch": 0.0190696243839131,
+      "grad_norm": 1.5758073329925537,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.9545,
+      "step": 1271
+    },
+    {
+      "epoch": 0.019534737173764638,
+      "grad_norm": 1.2776768207550049,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.9451,
+      "step": 1302
+    },
+    {
+      "epoch": 0.019999849963616177,
+      "grad_norm": 1.353869915008545,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.9447,
+      "step": 1333
+    },
+    {
+      "epoch": 0.020464962753467715,
+      "grad_norm": 1.312809944152832,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.9378,
+      "step": 1364
+    },
+    {
+      "epoch": 0.020930075543319254,
+      "grad_norm": 1.4820533990859985,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.9387,
+      "step": 1395
+    },
+    {
+      "epoch": 0.021395188333170796,
+      "grad_norm": 1.4796900749206543,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.9404,
+      "step": 1426
+    },
+    {
+      "epoch": 0.021860301123022334,
+      "grad_norm": 1.2076773643493652,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.9456,
+      "step": 1457
+    },
+    {
+      "epoch": 0.022325413912873873,
+      "grad_norm": 1.5685315132141113,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.9295,
+      "step": 1488
+    },
+    {
+      "epoch": 0.02279052670272541,
+      "grad_norm": 1.2706167697906494,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 0.9363,
+      "step": 1519
+    },
+    {
+      "epoch": 0.02325563949257695,
+      "grad_norm": 1.6134260892868042,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.9358,
+      "step": 1550
+    },
+    {
+      "epoch": 0.023720752282428488,
+      "grad_norm": 1.5067273378372192,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.9246,
+      "step": 1581
+    },
+    {
+      "epoch": 0.024185865072280027,
+      "grad_norm": 1.2844847440719604,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.9249,
+      "step": 1612
+    },
+    {
+      "epoch": 0.02465097786213157,
+      "grad_norm": 1.3331553936004639,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.9126,
+      "step": 1643
+    },
+    {
+      "epoch": 0.025116090651983107,
+      "grad_norm": 1.296553611755371,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 0.9256,
+      "step": 1674
+    },
+    {
+      "epoch": 0.025581203441834646,
+      "grad_norm": 1.5404491424560547,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 0.9203,
+      "step": 1705
+    },
+    {
+      "epoch": 0.026046316231686184,
+      "grad_norm": 1.2730467319488525,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.9121,
+      "step": 1736
+    },
+    {
+      "epoch": 0.026511429021537723,
+      "grad_norm": 1.0022433996200562,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.9092,
+      "step": 1767
+    },
+    {
+      "epoch": 0.02697654181138926,
+      "grad_norm": 1.0976656675338745,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.9051,
+      "step": 1798
+    },
+    {
+      "epoch": 0.0274416546012408,
+      "grad_norm": 1.2798818349838257,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.9079,
+      "step": 1829
+    },
+    {
+      "epoch": 0.02790676739109234,
+      "grad_norm": 1.268423318862915,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 0.903,
+      "step": 1860
+    },
+    {
+      "epoch": 0.02837188018094388,
+      "grad_norm": 1.323930263519287,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 0.891,
+      "step": 1891
+    },
+    {
+      "epoch": 0.02883699297079542,
+      "grad_norm": 1.283535361289978,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 0.8989,
+      "step": 1922
+    },
+    {
+      "epoch": 0.029302105760646957,
+      "grad_norm": 0.993127167224884,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 0.8975,
+      "step": 1953
+    },
+    {
+      "epoch": 0.029767218550498496,
+      "grad_norm": 1.5712456703186035,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 0.9039,
+      "step": 1984
+    },
+    {
+      "epoch": 0.030232331340350034,
+      "grad_norm": 1.1176402568817139,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.9021,
+      "step": 2015
+    },
+    {
+      "epoch": 0.030697444130201573,
+      "grad_norm": 1.0235352516174316,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.8972,
+      "step": 2046
+    },
+    {
+      "epoch": 0.031162556920053115,
+      "grad_norm": 1.385221004486084,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.8961,
+      "step": 2077
+    },
+    {
+      "epoch": 0.03162766970990465,
+      "grad_norm": 1.4159470796585083,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.8769,
+      "step": 2108
+    },
+    {
+      "epoch": 0.03209278249975619,
+      "grad_norm": 1.193058729171753,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.8968,
+      "step": 2139
+    },
+    {
+      "epoch": 0.03255789528960773,
+      "grad_norm": 1.2686582803726196,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.8898,
+      "step": 2170
+    },
+    {
+      "epoch": 0.03302300807945927,
+      "grad_norm": 1.0854675769805908,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 0.8915,
+      "step": 2201
+    },
+    {
+      "epoch": 0.03348812086931081,
+      "grad_norm": 0.9129638075828552,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 0.8902,
+      "step": 2232
+    },
+    {
+      "epoch": 0.03395323365916235,
+      "grad_norm": 0.984368622303009,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.8846,
+      "step": 2263
+    },
+    {
+      "epoch": 0.034418346449013884,
+      "grad_norm": 1.0718238353729248,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.8766,
+      "step": 2294
+    },
+    {
+      "epoch": 0.034883459238865426,
+      "grad_norm": 1.1199841499328613,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.8804,
+      "step": 2325
+    },
+    {
+      "epoch": 0.03534857202871696,
+      "grad_norm": 0.9969766736030579,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.8763,
+      "step": 2356
+    },
+    {
+      "epoch": 0.0358136848185685,
+      "grad_norm": 0.946407675743103,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.8742,
+      "step": 2387
+    },
+    {
+      "epoch": 0.036278797608420045,
+      "grad_norm": 0.889814019203186,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.8777,
+      "step": 2418
+    },
+    {
+      "epoch": 0.03674391039827158,
+      "grad_norm": 1.116170883178711,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.8763,
+      "step": 2449
+    },
+    {
+      "epoch": 0.03720902318812312,
+      "grad_norm": 1.0878428220748901,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.8642,
+      "step": 2480
+    },
+    {
+      "epoch": 0.03767413597797466,
+      "grad_norm": 0.9776530861854553,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.8677,
+      "step": 2511
+    },
+    {
+      "epoch": 0.0381392487678262,
+      "grad_norm": 0.8906075954437256,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.865,
+      "step": 2542
+    },
+    {
+      "epoch": 0.038604361557677734,
+      "grad_norm": 1.0723177194595337,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.8688,
+      "step": 2573
+    },
+    {
+      "epoch": 0.039069474347529276,
+      "grad_norm": 1.1505682468414307,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.8662,
+      "step": 2604
+    },
+    {
+      "epoch": 0.03953458713738082,
+      "grad_norm": 1.0024772882461548,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.8583,
+      "step": 2635
+    },
+    {
+      "epoch": 0.03999969992723235,
+      "grad_norm": 1.0406173467636108,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.8743,
+      "step": 2666
+    },
+    {
+      "epoch": 0.040464812717083895,
+      "grad_norm": 1.101955533027649,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.8606,
+      "step": 2697
+    },
+    {
+      "epoch": 0.04092992550693543,
+      "grad_norm": 0.9971107244491577,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.8778,
+      "step": 2728
+    },
+    {
+      "epoch": 0.04139503829678697,
+      "grad_norm": 0.8673920035362244,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.8666,
+      "step": 2759
+    },
+    {
+      "epoch": 0.04186015108663851,
+      "grad_norm": 1.0579853057861328,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.8657,
+      "step": 2790
+    },
+    {
+      "epoch": 0.04232526387649005,
+      "grad_norm": 1.0492053031921387,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.8584,
+      "step": 2821
+    },
+    {
+      "epoch": 0.04279037666634159,
+      "grad_norm": 1.1503852605819702,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.864,
+      "step": 2852
+    },
+    {
+      "epoch": 0.043255489456193126,
+      "grad_norm": 0.8799801468849182,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.863,
+      "step": 2883
+    },
+    {
+      "epoch": 0.04372060224604467,
+      "grad_norm": 1.1941951513290405,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.8499,
+      "step": 2914
+    },
+    {
+      "epoch": 0.0441857150358962,
+      "grad_norm": 1.0688523054122925,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.8532,
+      "step": 2945
+    },
+    {
+      "epoch": 0.044650827825747745,
+      "grad_norm": 1.3390436172485352,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.8585,
+      "step": 2976
+    },
+    {
+      "epoch": 0.04511594061559928,
+      "grad_norm": 0.8603100776672363,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.849,
+      "step": 3007
+    },
+    {
+      "epoch": 0.04558105340545082,
+      "grad_norm": 0.9069570302963257,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.855,
+      "step": 3038
+    },
+    {
+      "epoch": 0.046046166195302364,
+      "grad_norm": 1.161732792854309,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.8482,
+      "step": 3069
+    },
+    {
+      "epoch": 0.0465112789851539,
+      "grad_norm": 1.013755202293396,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.8407,
+      "step": 3100
+    },
+    {
+      "epoch": 0.04697639177500544,
+      "grad_norm": 0.9744968414306641,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.8485,
+      "step": 3131
+    },
+    {
+      "epoch": 0.047441504564856976,
+      "grad_norm": 0.9489821195602417,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.8514,
+      "step": 3162
+    },
+    {
+      "epoch": 0.04790661735470852,
+      "grad_norm": 2.6967334747314453,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.8586,
+      "step": 3193
+    },
+    {
+      "epoch": 0.04837173014456005,
+      "grad_norm": 11.866981506347656,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.8763,
+      "step": 3224
+    },
+    {
+      "epoch": 0.048836842934411595,
+      "grad_norm": 1.2520198822021484,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.8835,
+      "step": 3255
+    },
+    {
+      "epoch": 0.04930195572426314,
+      "grad_norm": 0.9215310215950012,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.8711,
+      "step": 3286
+    },
+    {
+      "epoch": 0.04976706851411467,
+      "grad_norm": 0.9236088991165161,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.8604,
+      "step": 3317
+    },
+    {
+      "epoch": 0.050232181303966214,
+      "grad_norm": 1.3709129095077515,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.8534,
+      "step": 3348
+    },
+    {
+      "epoch": 0.05069729409381775,
+      "grad_norm": 1.0045708417892456,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.8623,
+      "step": 3379
+    },
+    {
+      "epoch": 0.05116240688366929,
+      "grad_norm": 0.8312323689460754,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.863,
+      "step": 3410
+    },
+    {
+      "epoch": 0.051627519673520826,
+      "grad_norm": 0.9344459772109985,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.8713,
+      "step": 3441
+    },
+    {
+      "epoch": 0.05209263246337237,
+      "grad_norm": 1.153365969657898,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.8603,
+      "step": 3472
+    },
+    {
+      "epoch": 0.05255774525322391,
+      "grad_norm": 4.937042713165283,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.88,
+      "step": 3503
+    },
+    {
+      "epoch": 0.053022858043075445,
+      "grad_norm": 4.450394153594971,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 1.0639,
+      "step": 3534
+    },
+    {
+      "epoch": 0.05348797083292699,
+      "grad_norm": 3.7118916511535645,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.9212,
+      "step": 3565
+    },
+    {
+      "epoch": 0.05395308362277852,
+      "grad_norm": 0.9944353103637695,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.8721,
+      "step": 3596
+    },
+    {
+      "epoch": 0.054418196412630064,
+      "grad_norm": 19.067886352539062,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.8704,
+      "step": 3627
+    },
+    {
+      "epoch": 0.0548833092024816,
+      "grad_norm": 0.9959452748298645,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.8574,
+      "step": 3658
+    },
+    {
+      "epoch": 0.05534842199233314,
+      "grad_norm": 0.9663693308830261,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.849,
+      "step": 3689
+    },
+    {
+      "epoch": 0.05581353478218468,
+      "grad_norm": 0.8385364413261414,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.8511,
+      "step": 3720
+    },
+    {
+      "epoch": 0.05627864757203622,
+      "grad_norm": 0.9639562964439392,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.8439,
+      "step": 3751
+    },
+    {
+      "epoch": 0.05674376036188776,
+      "grad_norm": 0.8767015337944031,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.8505,
+      "step": 3782
+    },
+    {
+      "epoch": 0.057208873151739295,
+      "grad_norm": 0.9551979899406433,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.8492,
+      "step": 3813
+    },
+    {
+      "epoch": 0.05767398594159084,
+      "grad_norm": 0.9914498329162598,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.85,
+      "step": 3844
+    },
+    {
+      "epoch": 0.05813909873144237,
+      "grad_norm": 1.0119316577911377,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.8503,
+      "step": 3875
+    },
+    {
+      "epoch": 0.058604211521293914,
+      "grad_norm": 0.9795874357223511,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.8582,
+      "step": 3906
+    },
+    {
+      "epoch": 0.059069324311145456,
+      "grad_norm": 1.235706090927124,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.8509,
+      "step": 3937
+    },
+    {
+      "epoch": 0.05953443710099699,
+      "grad_norm": 0.9522190093994141,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.8331,
+      "step": 3968
+    },
+    {
+      "epoch": 0.05999954989084853,
+      "grad_norm": 1.1398371458053589,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.8384,
+      "step": 3999
+    },
+    {
+      "epoch": 0.06046466268070007,
+      "grad_norm": 2.206756353378296,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.8339,
+      "step": 4030
+    },
+    {
+      "epoch": 0.06092977547055161,
+      "grad_norm": 0.9003246426582336,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.8328,
+      "step": 4061
+    },
+    {
+      "epoch": 0.061394888260403145,
+      "grad_norm": 0.9644908308982849,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.8363,
+      "step": 4092
+    },
+    {
+      "epoch": 0.06186000105025469,
+      "grad_norm": 1.2581112384796143,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.8371,
+      "step": 4123
+    },
+    {
+      "epoch": 0.06232511384010623,
+      "grad_norm": 0.9921565055847168,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.8451,
+      "step": 4154
+    },
+    {
+      "epoch": 0.06279022662995777,
+      "grad_norm": 0.9277012944221497,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.8408,
+      "step": 4185
+    },
+    {
+      "epoch": 0.0632553394198093,
+      "grad_norm": 7.32985782623291,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.978,
+      "step": 4216
+    },
+    {
+      "epoch": 0.06372045220966084,
+      "grad_norm": 1.1323987245559692,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.884,
+      "step": 4247
+    },
+    {
+      "epoch": 0.06418556499951238,
+      "grad_norm": 1.2052208185195923,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.8319,
+      "step": 4278
+    },
+    {
+      "epoch": 0.06465067778936393,
+      "grad_norm": 0.778343915939331,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.8297,
+      "step": 4309
+    },
+    {
+      "epoch": 0.06511579057921546,
+      "grad_norm": 0.9384486675262451,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.8435,
+      "step": 4340
+    },
+    {
+      "epoch": 0.065580903369067,
+      "grad_norm": 0.9519233703613281,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.8448,
+      "step": 4371
+    },
+    {
+      "epoch": 0.06604601615891854,
+      "grad_norm": 0.9713039398193359,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.8214,
+      "step": 4402
+    },
+    {
+      "epoch": 0.06651112894877008,
+      "grad_norm": 0.8167161345481873,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.8241,
+      "step": 4433
+    },
+    {
+      "epoch": 0.06697624173862161,
+      "grad_norm": 0.8841028809547424,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.8273,
+      "step": 4464
+    },
+    {
+      "epoch": 0.06744135452847315,
+      "grad_norm": 1.3484187126159668,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.827,
+      "step": 4495
+    },
+    {
+      "epoch": 0.0679064673183247,
+      "grad_norm": 0.8538167476654053,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.8239,
+      "step": 4526
+    },
+    {
+      "epoch": 0.06837158010817623,
+      "grad_norm": 1.1297218799591064,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.8358,
+      "step": 4557
+    },
+    {
+      "epoch": 0.06883669289802777,
+      "grad_norm": 0.9539270997047424,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.8331,
+      "step": 4588
+    },
+    {
+      "epoch": 0.06930180568787932,
+      "grad_norm": 0.9373602867126465,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.8318,
+      "step": 4619
+    },
+    {
+      "epoch": 0.06976691847773085,
+      "grad_norm": 1.1780788898468018,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.8395,
+      "step": 4650
+    },
+    {
+      "epoch": 0.07023203126758239,
+      "grad_norm": 0.8912601470947266,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.8255,
+      "step": 4681
+    },
+    {
+      "epoch": 0.07069714405743392,
+      "grad_norm": 0.8823812007904053,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.8234,
+      "step": 4712
+    },
+    {
+      "epoch": 0.07116225684728547,
+      "grad_norm": 0.7177905440330505,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.8132,
+      "step": 4743
+    },
+    {
+      "epoch": 0.071627369637137,
+      "grad_norm": 0.7038840651512146,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.8214,
+      "step": 4774
+    },
+    {
+      "epoch": 0.07209248242698854,
+      "grad_norm": 0.9733498096466064,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.8194,
+      "step": 4805
+    },
+    {
+      "epoch": 0.07255759521684009,
+      "grad_norm": 0.9749795794487,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.8168,
+      "step": 4836
+    },
+    {
+      "epoch": 0.07302270800669163,
+      "grad_norm": 0.9269246459007263,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.8276,
+      "step": 4867
+    },
+    {
+      "epoch": 0.07348782079654316,
+      "grad_norm": 0.8198825716972351,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.8245,
+      "step": 4898
+    },
+    {
+      "epoch": 0.0739529335863947,
+      "grad_norm": 0.8156753182411194,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.8131,
+      "step": 4929
+    },
+    {
+      "epoch": 0.07441804637624624,
+      "grad_norm": 0.9815400838851929,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.8081,
+      "step": 4960
+    },
+    {
+      "epoch": 0.07488315916609778,
+      "grad_norm": 0.8975831270217896,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.82,
+      "step": 4991
+    },
+    {
+      "epoch": 0.07534827195594931,
+      "grad_norm": 0.7986422181129456,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.8273,
+      "step": 5022
+    },
+    {
+      "epoch": 0.07581338474580086,
+      "grad_norm": 0.6942843794822693,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.8175,
+      "step": 5053
+    },
+    {
+      "epoch": 0.0762784975356524,
+      "grad_norm": 0.7459082007408142,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.8021,
+      "step": 5084
+    },
+    {
+      "epoch": 0.07674361032550393,
+      "grad_norm": 0.8253138065338135,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.8149,
+      "step": 5115
+    },
+    {
+      "epoch": 0.07720872311535547,
+      "grad_norm": 0.887172281742096,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.799,
+      "step": 5146
+    },
+    {
+      "epoch": 0.07767383590520702,
+      "grad_norm": 1.001217007637024,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.8054,
+      "step": 5177
+    },
+    {
+      "epoch": 0.07813894869505855,
+      "grad_norm": 0.8390373587608337,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.803,
+      "step": 5208
+    },
+    {
+      "epoch": 0.07860406148491009,
+      "grad_norm": 0.6997588872909546,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.8166,
+      "step": 5239
+    },
+    {
+      "epoch": 0.07906917427476164,
+      "grad_norm": 1.0146000385284424,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.8116,
+      "step": 5270
+    },
+    {
+      "epoch": 0.07953428706461317,
+      "grad_norm": 1.046372890472412,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.8144,
+      "step": 5301
+    },
+    {
+      "epoch": 0.0799993998544647,
+      "grad_norm": 7.797517776489258,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.8269,
+      "step": 5332
+    },
+    {
+      "epoch": 0.08046451264431624,
+      "grad_norm": 1.3370609283447266,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.8773,
+      "step": 5363
+    },
+    {
+      "epoch": 0.08092962543416779,
+      "grad_norm": 2.293041706085205,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.9105,
+      "step": 5394
+    },
+    {
+      "epoch": 0.08139473822401933,
+      "grad_norm": 2.027996301651001,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.8932,
+      "step": 5425
+    },
+    {
+      "epoch": 0.08185985101387086,
+      "grad_norm": 9.98909854888916,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.8539,
+      "step": 5456
+    },
+    {
+      "epoch": 0.08232496380372241,
+      "grad_norm": 0.7773656845092773,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.8295,
+      "step": 5487
+    },
+    {
+      "epoch": 0.08279007659357394,
+      "grad_norm": 0.8717573285102844,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.8207,
+      "step": 5518
+    },
+    {
+      "epoch": 0.08325518938342548,
+      "grad_norm": 0.7932561635971069,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.8149,
+      "step": 5549
+    },
+    {
+      "epoch": 0.08372030217327701,
+      "grad_norm": 0.6895427703857422,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.8309,
+      "step": 5580
+    },
+    {
+      "epoch": 0.08418541496312856,
+      "grad_norm": 0.7834138870239258,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.8261,
+      "step": 5611
+    },
+    {
+      "epoch": 0.0846505277529801,
+      "grad_norm": 1.246392011642456,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.8352,
+      "step": 5642
+    },
+    {
+      "epoch": 0.08511564054283163,
+      "grad_norm": 0.925993025302887,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.8235,
+      "step": 5673
+    },
+    {
+      "epoch": 0.08558075333268318,
+      "grad_norm": 0.7340030074119568,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.8183,
+      "step": 5704
+    },
+    {
+      "epoch": 0.08604586612253472,
+      "grad_norm": 1.0153193473815918,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.8061,
+      "step": 5735
+    },
+    {
+      "epoch": 0.08651097891238625,
+      "grad_norm": 0.7152019739151001,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.8065,
+      "step": 5766
+    },
+    {
+      "epoch": 0.08697609170223779,
+      "grad_norm": 1.4204005002975464,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.7952,
+      "step": 5797
+    },
+    {
+      "epoch": 0.08744120449208934,
+      "grad_norm": 0.911857008934021,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.811,
+      "step": 5828
+    },
+    {
+      "epoch": 0.08790631728194087,
+      "grad_norm": 0.817642092704773,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.8,
+      "step": 5859
+    },
+    {
+      "epoch": 0.0883714300717924,
+      "grad_norm": 0.6920213103294373,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.8044,
+      "step": 5890
+    },
+    {
+      "epoch": 0.08883654286164396,
+      "grad_norm": 0.7869626879692078,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.8013,
+      "step": 5921
+    },
+    {
+      "epoch": 0.08930165565149549,
+      "grad_norm": 0.6730135679244995,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.8022,
+      "step": 5952
+    },
+    {
+      "epoch": 0.08976676844134703,
+      "grad_norm": 0.6608561873435974,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.8098,
+      "step": 5983
+    },
+    {
+      "epoch": 0.09023188123119856,
+      "grad_norm": 0.7139790058135986,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.8061,
+      "step": 6014
+    },
+    {
+      "epoch": 0.09069699402105011,
+      "grad_norm": 1.003175973892212,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.7951,
+      "step": 6045
+    },
+    {
+      "epoch": 0.09116210681090164,
+      "grad_norm": 0.7580083608627319,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.7971,
+      "step": 6076
+    },
+    {
+      "epoch": 0.09162721960075318,
+      "grad_norm": 1.1409324407577515,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.8142,
+      "step": 6107
+    },
+    {
+      "epoch": 0.09209233239060473,
+      "grad_norm": 0.9261921048164368,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.7975,
+      "step": 6138
+    },
+    {
+      "epoch": 0.09255744518045626,
+      "grad_norm": 0.8468340039253235,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.8087,
+      "step": 6169
+    },
+    {
+      "epoch": 0.0930225579703078,
+      "grad_norm": 0.9738436341285706,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.7878,
+      "step": 6200
+    },
+    {
+      "epoch": 0.09348767076015933,
+      "grad_norm": 0.7266778349876404,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.7959,
+      "step": 6231
+    },
+    {
+      "epoch": 0.09395278355001088,
+      "grad_norm": 0.6330700516700745,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.7992,
+      "step": 6262
+    },
+    {
+      "epoch": 0.09441789633986242,
+      "grad_norm": 0.7615357637405396,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.8014,
+      "step": 6293
+    },
+    {
+      "epoch": 0.09488300912971395,
+      "grad_norm": 0.8778673410415649,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.7985,
+      "step": 6324
+    },
+    {
+      "epoch": 0.0953481219195655,
+      "grad_norm": 0.8122367262840271,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.8104,
+      "step": 6355
+    },
+    {
+      "epoch": 0.09581323470941704,
+      "grad_norm": 0.7950412631034851,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.8036,
+      "step": 6386
+    },
+    {
+      "epoch": 0.09627834749926857,
+      "grad_norm": 0.9101532101631165,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.8017,
+      "step": 6417
+    },
+    {
+      "epoch": 0.0967434602891201,
+      "grad_norm": 1.452165126800537,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.8082,
+      "step": 6448
+    },
+    {
+      "epoch": 0.09720857307897166,
+      "grad_norm": 0.7584947347640991,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.8104,
+      "step": 6479
+    },
+    {
+      "epoch": 0.09767368586882319,
+      "grad_norm": 1.1697564125061035,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.8019,
+      "step": 6510
+    },
+    {
+      "epoch": 0.09813879865867473,
+      "grad_norm": 0.6125388741493225,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.7949,
+      "step": 6541
+    },
+    {
+      "epoch": 0.09860391144852627,
+      "grad_norm": 0.8032566905021667,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.8,
+      "step": 6572
+    },
+    {
+      "epoch": 0.09906902423837781,
+      "grad_norm": 0.8577548861503601,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.7888,
+      "step": 6603
+    },
+    {
+      "epoch": 0.09953413702822934,
+      "grad_norm": 0.7905965447425842,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.7946,
+      "step": 6634
+    },
+    {
+      "epoch": 0.09999924981808088,
+      "grad_norm": 0.678344190120697,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.7826,
+      "step": 6665
+    },
+    {
+      "epoch": 0.10046436260793243,
+      "grad_norm": 0.7858152985572815,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.793,
+      "step": 6696
+    },
+    {
+      "epoch": 0.10092947539778396,
+      "grad_norm": 0.7910358309745789,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.7985,
+      "step": 6727
+    },
+    {
+      "epoch": 0.1013945881876355,
+      "grad_norm": 0.814469575881958,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.7856,
+      "step": 6758
+    },
+    {
+      "epoch": 0.10185970097748705,
+      "grad_norm": 0.8370437622070312,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.7896,
+      "step": 6789
+    },
+    {
+      "epoch": 0.10232481376733858,
+      "grad_norm": 0.6987704038619995,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.7952,
+      "step": 6820
+    },
+    {
+      "epoch": 0.10278992655719012,
+      "grad_norm": 0.7554413676261902,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.7927,
+      "step": 6851
+    },
+    {
+      "epoch": 0.10325503934704165,
+      "grad_norm": 0.7269867658615112,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.789,
+      "step": 6882
+    },
+    {
+      "epoch": 0.1037201521368932,
+      "grad_norm": 0.7761571407318115,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.7807,
+      "step": 6913
+    },
+    {
+      "epoch": 0.10418526492674474,
+      "grad_norm": 0.7546917796134949,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.7873,
+      "step": 6944
+    },
+    {
+      "epoch": 0.10465037771659627,
+      "grad_norm": 0.6880353093147278,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.7907,
+      "step": 6975
+    },
+    {
+      "epoch": 0.10511549050644782,
+      "grad_norm": 0.6309835314750671,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.7918,
+      "step": 7006
+    },
+    {
+      "epoch": 0.10558060329629936,
+      "grad_norm": 0.7071651220321655,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.7841,
+      "step": 7037
+    },
+    {
+      "epoch": 0.10604571608615089,
+      "grad_norm": 0.6908242106437683,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.7827,
+      "step": 7068
+    },
+    {
+      "epoch": 0.10651082887600243,
+      "grad_norm": 0.8168213963508606,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.7868,
+      "step": 7099
+    },
+    {
+      "epoch": 0.10697594166585397,
+      "grad_norm": 0.8654292225837708,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.8004,
+      "step": 7130
+    },
+    {
+      "epoch": 0.10744105445570551,
+      "grad_norm": 0.8038971424102783,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.793,
+      "step": 7161
+    },
+    {
+      "epoch": 0.10790616724555704,
+      "grad_norm": 0.6893990635871887,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.7837,
+      "step": 7192
+    },
+    {
+      "epoch": 0.1083712800354086,
+      "grad_norm": 0.8243061900138855,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.7944,
+      "step": 7223
+    },
+    {
+      "epoch": 0.10883639282526013,
+      "grad_norm": 0.7790378928184509,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.7885,
+      "step": 7254
+    },
+    {
+      "epoch": 0.10930150561511166,
+      "grad_norm": 0.731829047203064,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.7898,
+      "step": 7285
+    },
+    {
+      "epoch": 0.1097666184049632,
+      "grad_norm": 0.8384029269218445,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.7875,
+      "step": 7316
+    },
+    {
+      "epoch": 0.11023173119481475,
+      "grad_norm": 0.6856273412704468,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.7841,
+      "step": 7347
+    },
+    {
+      "epoch": 0.11069684398466628,
+      "grad_norm": 0.7017887830734253,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.7828,
+      "step": 7378
+    },
+    {
+      "epoch": 0.11116195677451782,
+      "grad_norm": 0.7566471099853516,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.7891,
+      "step": 7409
+    },
+    {
+      "epoch": 0.11162706956436937,
+      "grad_norm": 0.7368637323379517,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.7761,
+      "step": 7440
+    },
+    {
+      "epoch": 0.1120921823542209,
+      "grad_norm": 0.6670425534248352,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.7865,
+      "step": 7471
+    },
+    {
+      "epoch": 0.11255729514407244,
+      "grad_norm": 0.7009292840957642,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.79,
+      "step": 7502
+    },
+    {
+      "epoch": 0.11302240793392397,
+      "grad_norm": 0.8546404242515564,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.7914,
+      "step": 7533
+    },
+    {
+      "epoch": 0.11348752072377552,
+      "grad_norm": 0.7382566928863525,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.7949,
+      "step": 7564
+    },
+    {
+      "epoch": 0.11395263351362706,
+      "grad_norm": 0.7818961143493652,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.7815,
+      "step": 7595
+    },
+    {
+      "epoch": 0.11441774630347859,
+      "grad_norm": 0.7249829769134521,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.7973,
+      "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 sha256:32a5ee6195ed946d44003064f63b0ea2e1d660daea1faba926ec7d283df386ab
+size 5240