Upload folder using huggingface_hub

checkpoint-526/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-526/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

checkpoint-526/model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d64e21cda543d75107d9194030ca982fea41c94d8d0ff3a0d9728177f667a59
+size 4498420872

checkpoint-526/model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa5b922a150134c361c4d17dde78af8923fb433cc87ce6c1a4414835a966fe82
+size 4718804768

checkpoint-526/model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9314092d6b41574be1888569687ec6b74be867d733274a85c1b31c506393805
+size 4467075880

checkpoint-526/model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:723059ed3aaecb22f77503de6ca60d8f6a5e51edfd3fe9f4d20fd5036e4f86fe
+size 4467075880

checkpoint-526/model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b50bcf47963165025f4b41dc34ae095e31c2a6eb83e6af163d93a70d6000384
+size 4718804760

checkpoint-526/model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5d2b2a1d7ae6879eb88c50559f31fdcf35a723e354ed1e1a8e016aeecae1fa
+size 4467075904

checkpoint-526/model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f0a0e6685a57febc12941bc863e3b37fb519b8292cbfe8c67302bd0048ee3be
+size 4467075904

checkpoint-526/model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf4a3e01859f9eeab6bcc21f4a6786a2389ac47281477efafd23b6cb033d1465
+size 4718804800

checkpoint-526/model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ecfaa82d6407668253d6df502949c83c2659ad182801584a5116f9b978e89d
+size 4467075904

checkpoint-526/model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b0ea228937683436d852338436380fd74f94eed22077ce062dbf70490d263a
+size 4467075904

checkpoint-526/model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad042682c62dcabd32c950eb6eda0b61d6a18714832896e16f4c22b4c56e234a
+size 4718804800

checkpoint-526/model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92aaf203ffe74d3ed4ffcbf3d8ea77e7172e77fdbd240709a3105704841da7e9
+size 4467075904

checkpoint-526/model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ed271e0348c7125c517ef17c0bfa3d20b2ad289110bbd6c53b9178389a9f700
+size 4467075904

checkpoint-526/model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c425b251038ebe729e97c3897fa903ebed7dbf4700d1acfb5501431f63f481a
+size 4718804800

checkpoint-526/model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e7004c43c5348de0318ead0b1151b70dd686e4c616c2eff1ac0ee4beea21d3e
+size 4467075904

checkpoint-526/model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65096fde296dfb75915806244de63f576229e2ec394b6f027bc7048ed985ac4
+size 4467075904

checkpoint-526/model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99757de2b12cb470f2eb0d92ae2de59df83c6d77bf8c3f0b848279350e235fd4
+size 4718804800

checkpoint-526/model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c3a8fc668cb3464dc02424e22b3e492c00ad578dd512529f3fdef1d75491cd1
+size 4467075904

checkpoint-526/model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e14cf9af9f01c9864cf412043b9aefa1989f556c71a97eaa10022ffb5afaade3
+size 4467075904

checkpoint-526/model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcaacddbadcd95bf47e8a6cf4535358e0b29e47a5ec5100316164f45e0916996
+size 4718804800

checkpoint-526/model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47db5818914b807d14274b7bde0165f327aab808cd41dcb54db055a5d0ee01ae
+size 4467075904

checkpoint-526/model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c0c926dbed1e2dc85c3aee24394f24d2675009dd86a944a143177f02541d299
+size 4467075904

checkpoint-526/model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988696afc7b311f9c2816e83fd99f9882ddb46cfd237f3fd49c518bda5a620dc
+size 4718804800

checkpoint-526/model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4d8c50c62092b2f0d1f21f2c2557d60f42c7a22d89e925c2d3cbf51d3327ef
+size 4467075904

checkpoint-526/model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328d52a54a35678b867a12f1bef4b04bf127e98292d8fce67d0ec7177c6c5cfd
+size 4467075904

checkpoint-526/model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558fc99700a3381053620b86650b620ef39395f6ec9f8725832dc1ff1db24876
+size 4718804800

checkpoint-526/model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e2234f8544ea04f4c33e40f1248aed7f957515890e96402047c0812d8530ce2
+size 4467075904

checkpoint-526/model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9023379cf3b53d5234aad8aa06b988801660146ec75e2793c7459f4929169f2e
+size 4467075904

checkpoint-526/model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8906b2a5c1449bf0b5361ca2920fd44a7be87cfb3155c5b49f366b07d96582e9
+size 3680563768

checkpoint-526/model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 131055505408
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00029-of-00029.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00006-of-00029.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00006-of-00029.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00007-of-00029.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00007-of-00029.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00008-of-00029.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00009-of-00029.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00009-of-00029.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00010-of-00029.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00010-of-00029.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00011-of-00029.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00012-of-00029.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00012-of-00029.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00013-of-00029.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00013-of-00029.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00014-of-00029.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00015-of-00029.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00015-of-00029.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00016-of-00029.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00016-of-00029.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00017-of-00029.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00018-of-00029.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00029.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00018-of-00029.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00019-of-00029.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00019-of-00029.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00020-of-00029.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00021-of-00029.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00021-of-00029.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00022-of-00029.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00022-of-00029.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00023-of-00029.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00024-of-00029.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00024-of-00029.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00025-of-00029.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00025-of-00029.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00026-of-00029.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00004-of-00029.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00027-of-00029.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00027-of-00029.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00028-of-00029.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00028-of-00029.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00004-of-00029.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00005-of-00029.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.norm.weight": "model-00029-of-00029.safetensors"
+  }
+}

checkpoint-526/trainer_state.json

@@ -0,0 +1,3715 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9971523493118177,
+  "eval_steps": 500,
+  "global_step": 526,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0037968675842429997,
+      "grad_norm": 190.1852569580078,
+      "learning_rate": 1.8518518518518518e-07,
+      "loss": 2.1743,
+      "step": 1
+    },
+    {
+      "epoch": 0.007593735168485999,
+      "grad_norm": 318.4629211425781,
+      "learning_rate": 3.7037037037037036e-07,
+      "loss": 2.1888,
+      "step": 2
+    },
+    {
+      "epoch": 0.011390602752728999,
+      "grad_norm": 4.048186302185059,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 1.8374,
+      "step": 3
+    },
+    {
+      "epoch": 0.015187470336971999,
+      "grad_norm": 149.984375,
+      "learning_rate": 7.407407407407407e-07,
+      "loss": 2.2082,
+      "step": 4
+    },
+    {
+      "epoch": 0.018984337921214997,
+      "grad_norm": 140.36471557617188,
+      "learning_rate": 9.259259259259259e-07,
+      "loss": 2.5169,
+      "step": 5
+    },
+    {
+      "epoch": 0.022781205505457997,
+      "grad_norm": 81.98410034179688,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 2.0747,
+      "step": 6
+    },
+    {
+      "epoch": 0.026578073089700997,
+      "grad_norm": 3.9009580612182617,
+      "learning_rate": 1.2962962962962962e-06,
+      "loss": 1.8328,
+      "step": 7
+    },
+    {
+      "epoch": 0.030374940673943997,
+      "grad_norm": 239.54661560058594,
+      "learning_rate": 1.4814814814814815e-06,
+      "loss": 2.1877,
+      "step": 8
+    },
+    {
+      "epoch": 0.034171808258187,
+      "grad_norm": 181.9974822998047,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.9126,
+      "step": 9
+    },
+    {
+      "epoch": 0.037968675842429994,
+      "grad_norm": 71.94468688964844,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 1.9289,
+      "step": 10
+    },
+    {
+      "epoch": 0.041765543426673,
+      "grad_norm": 327.50091552734375,
+      "learning_rate": 2.037037037037037e-06,
+      "loss": 1.8236,
+      "step": 11
+    },
+    {
+      "epoch": 0.045562411010915994,
+      "grad_norm": 3.223841667175293,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.7878,
+      "step": 12
+    },
+    {
+      "epoch": 0.04935927859515899,
+      "grad_norm": 230.49221801757812,
+      "learning_rate": 2.4074074074074075e-06,
+      "loss": 1.6871,
+      "step": 13
+    },
+    {
+      "epoch": 0.053156146179401995,
+      "grad_norm": 18558.3125,
+      "learning_rate": 2.5925925925925925e-06,
+      "loss": 1.6958,
+      "step": 14
+    },
+    {
+      "epoch": 0.05695301376364499,
+      "grad_norm": 2.5916926860809326,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 1.7525,
+      "step": 15
+    },
+    {
+      "epoch": 0.060749881347887995,
+      "grad_norm": 2.61940598487854,
+      "learning_rate": 2.962962962962963e-06,
+      "loss": 1.7431,
+      "step": 16
+    },
+    {
+      "epoch": 0.064546748932131,
+      "grad_norm": 175.40200805664062,
+      "learning_rate": 3.1481481481481483e-06,
+      "loss": 1.6176,
+      "step": 17
+    },
+    {
+      "epoch": 0.068343616516374,
+      "grad_norm": 2.723275899887085,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.7091,
+      "step": 18
+    },
+    {
+      "epoch": 0.07214048410061699,
+      "grad_norm": 575.9302368164062,
+      "learning_rate": 3.5185185185185187e-06,
+      "loss": 1.4155,
+      "step": 19
+    },
+    {
+      "epoch": 0.07593735168485999,
+      "grad_norm": 1.5204131603240967,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 1.668,
+      "step": 20
+    },
+    {
+      "epoch": 0.07973421926910298,
+      "grad_norm": 172.04342651367188,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 1.5175,
+      "step": 21
+    },
+    {
+      "epoch": 0.083531086853346,
+      "grad_norm": 36.41116714477539,
+      "learning_rate": 4.074074074074074e-06,
+      "loss": 1.3265,
+      "step": 22
+    },
+    {
+      "epoch": 0.08732795443758899,
+      "grad_norm": 1.3005378246307373,
+      "learning_rate": 4.2592592592592596e-06,
+      "loss": 1.6097,
+      "step": 23
+    },
+    {
+      "epoch": 0.09112482202183199,
+      "grad_norm": 23.33233642578125,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.4055,
+      "step": 24
+    },
+    {
+      "epoch": 0.09492168960607499,
+      "grad_norm": 1.2947165966033936,
+      "learning_rate": 4.62962962962963e-06,
+      "loss": 1.552,
+      "step": 25
+    },
+    {
+      "epoch": 0.09871855719031798,
+      "grad_norm": 62.264190673828125,
+      "learning_rate": 4.814814814814815e-06,
+      "loss": 1.198,
+      "step": 26
+    },
+    {
+      "epoch": 0.10251542477456099,
+      "grad_norm": 16.471799850463867,
+      "learning_rate": 5e-06,
+      "loss": 1.3374,
+      "step": 27
+    },
+    {
+      "epoch": 0.10631229235880399,
+      "grad_norm": 9.552218437194824,
+      "learning_rate": 4.999950454155801e-06,
+      "loss": 1.3352,
+      "step": 28
+    },
+    {
+      "epoch": 0.11010915994304699,
+      "grad_norm": 1.3561033010482788,
+      "learning_rate": 4.999801818587036e-06,
+      "loss": 1.5152,
+      "step": 29
+    },
+    {
+      "epoch": 0.11390602752728998,
+      "grad_norm": 3.8642690181732178,
+      "learning_rate": 4.999554099185124e-06,
+      "loss": 1.3093,
+      "step": 30
+    },
+    {
+      "epoch": 0.11770289511153298,
+      "grad_norm": 0.9432722926139832,
+      "learning_rate": 4.999207305768841e-06,
+      "loss": 1.3048,
+      "step": 31
+    },
+    {
+      "epoch": 0.12149976269577599,
+      "grad_norm": 0.9486730694770813,
+      "learning_rate": 4.998761452083922e-06,
+      "loss": 1.4368,
+      "step": 32
+    },
+    {
+      "epoch": 0.12529663028001897,
+      "grad_norm": 0.7894783020019531,
+      "learning_rate": 4.998216555802526e-06,
+      "loss": 1.2765,
+      "step": 33
+    },
+    {
+      "epoch": 0.129093497864262,
+      "grad_norm": 0.8032355308532715,
+      "learning_rate": 4.997572638522531e-06,
+      "loss": 1.425,
+      "step": 34
+    },
+    {
+      "epoch": 0.132890365448505,
+      "grad_norm": 0.6962498426437378,
+      "learning_rate": 4.996829725766676e-06,
+      "loss": 1.4005,
+      "step": 35
+    },
+    {
+      "epoch": 0.136687233032748,
+      "grad_norm": 0.6125718355178833,
+      "learning_rate": 4.995987846981554e-06,
+      "loss": 1.0826,
+      "step": 36
+    },
+    {
+      "epoch": 0.140484100616991,
+      "grad_norm": 0.6794630885124207,
+      "learning_rate": 4.995047035536439e-06,
+      "loss": 1.0644,
+      "step": 37
+    },
+    {
+      "epoch": 0.14428096820123398,
+      "grad_norm": 0.6797907948493958,
+      "learning_rate": 4.9940073287219705e-06,
+      "loss": 1.0821,
+      "step": 38
+    },
+    {
+      "epoch": 0.14807783578547698,
+      "grad_norm": 0.6790012121200562,
+      "learning_rate": 4.992868767748669e-06,
+      "loss": 1.2284,
+      "step": 39
+    },
+    {
+      "epoch": 0.15187470336971998,
+      "grad_norm": 0.6396064758300781,
+      "learning_rate": 4.991631397745307e-06,
+      "loss": 1.197,
+      "step": 40
+    },
+    {
+      "epoch": 0.15567157095396297,
+      "grad_norm": 0.6216674447059631,
+      "learning_rate": 4.990295267757117e-06,
+      "loss": 1.3547,
+      "step": 41
+    },
+    {
+      "epoch": 0.15946843853820597,
+      "grad_norm": 0.49298611283302307,
+      "learning_rate": 4.98886043074385e-06,
+      "loss": 0.8974,
+      "step": 42
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 0.5648188591003418,
+      "learning_rate": 4.987326943577675e-06,
+      "loss": 1.1868,
+      "step": 43
+    },
+    {
+      "epoch": 0.167062173706692,
+      "grad_norm": 0.5617629885673523,
+      "learning_rate": 4.985694867040924e-06,
+      "loss": 1.197,
+      "step": 44
+    },
+    {
+      "epoch": 0.170859041290935,
+      "grad_norm": 0.5470258593559265,
+      "learning_rate": 4.983964265823687e-06,
+      "loss": 1.0242,
+      "step": 45
+    },
+    {
+      "epoch": 0.17465590887517798,
+      "grad_norm": 0.5692163705825806,
+      "learning_rate": 4.98213520852124e-06,
+      "loss": 1.3244,
+      "step": 46
+    },
+    {
+      "epoch": 0.17845277645942098,
+      "grad_norm": 0.4028306007385254,
+      "learning_rate": 4.980207767631335e-06,
+      "loss": 0.7001,
+      "step": 47
+    },
+    {
+      "epoch": 0.18224964404366398,
+      "grad_norm": 0.49932053685188293,
+      "learning_rate": 4.978182019551321e-06,
+      "loss": 1.1597,
+      "step": 48
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 0.5206290483474731,
+      "learning_rate": 4.976058044575116e-06,
+      "loss": 1.3185,
+      "step": 49
+    },
+    {
+      "epoch": 0.18984337921214997,
+      "grad_norm": 0.534298300743103,
+      "learning_rate": 4.973835926890027e-06,
+      "loss": 1.3182,
+      "step": 50
+    },
+    {
+      "epoch": 0.19364024679639297,
+      "grad_norm": 0.4649883210659027,
+      "learning_rate": 4.9715157545734124e-06,
+      "loss": 1.1734,
+      "step": 51
+    },
+    {
+      "epoch": 0.19743711438063596,
+      "grad_norm": 0.45419999957084656,
+      "learning_rate": 4.969097619589187e-06,
+      "loss": 1.1433,
+      "step": 52
+    },
+    {
+      "epoch": 0.201233981964879,
+      "grad_norm": 0.4962867498397827,
+      "learning_rate": 4.9665816177841845e-06,
+      "loss": 1.1749,
+      "step": 53
+    },
+    {
+      "epoch": 0.20503084954912199,
+      "grad_norm": 0.4966491162776947,
+      "learning_rate": 4.963967848884349e-06,
+      "loss": 1.1595,
+      "step": 54
+    },
+    {
+      "epoch": 0.20882771713336498,
+      "grad_norm": 0.4114384055137634,
+      "learning_rate": 4.961256416490793e-06,
+      "loss": 0.8368,
+      "step": 55
+    },
+    {
+      "epoch": 0.21262458471760798,
+      "grad_norm": 0.438700407743454,
+      "learning_rate": 4.9584474280756785e-06,
+      "loss": 1.1412,
+      "step": 56
+    },
+    {
+      "epoch": 0.21642145230185098,
+      "grad_norm": 0.45085862278938293,
+      "learning_rate": 4.9555409949779695e-06,
+      "loss": 1.1312,
+      "step": 57
+    },
+    {
+      "epoch": 0.22021831988609397,
+      "grad_norm": 0.4020615220069885,
+      "learning_rate": 4.952537232399012e-06,
+      "loss": 0.9898,
+      "step": 58
+    },
+    {
+      "epoch": 0.22401518747033697,
+      "grad_norm": 0.43643948435783386,
+      "learning_rate": 4.9494362593979665e-06,
+      "loss": 1.1352,
+      "step": 59
+    },
+    {
+      "epoch": 0.22781205505457996,
+      "grad_norm": 0.40290120244026184,
+      "learning_rate": 4.946238198887093e-06,
+      "loss": 0.9822,
+      "step": 60
+    },
+    {
+      "epoch": 0.23160892263882296,
+      "grad_norm": 0.4434157609939575,
+      "learning_rate": 4.942943177626879e-06,
+      "loss": 1.1303,
+      "step": 61
+    },
+    {
+      "epoch": 0.23540579022306596,
+      "grad_norm": 0.48527973890304565,
+      "learning_rate": 4.939551326221012e-06,
+      "loss": 1.2812,
+      "step": 62
+    },
+    {
+      "epoch": 0.23920265780730898,
+      "grad_norm": 0.4416787028312683,
+      "learning_rate": 4.936062779111205e-06,
+      "loss": 1.1381,
+      "step": 63
+    },
+    {
+      "epoch": 0.24299952539155198,
+      "grad_norm": 0.4510328769683838,
+      "learning_rate": 4.932477674571867e-06,
+      "loss": 1.2696,
+      "step": 64
+    },
+    {
+      "epoch": 0.24679639297579498,
+      "grad_norm": 0.38020116090774536,
+      "learning_rate": 4.928796154704623e-06,
+      "loss": 0.9767,
+      "step": 65
+    },
+    {
+      "epoch": 0.25059326056003794,
+      "grad_norm": 0.4880014657974243,
+      "learning_rate": 4.925018365432681e-06,
+      "loss": 1.2679,
+      "step": 66
+    },
+    {
+      "epoch": 0.25439012814428097,
+      "grad_norm": 0.4506332576274872,
+      "learning_rate": 4.921144456495048e-06,
+      "loss": 1.1344,
+      "step": 67
+    },
+    {
+      "epoch": 0.258186995728524,
+      "grad_norm": 0.45424792170524597,
+      "learning_rate": 4.9171745814405945e-06,
+      "loss": 1.2797,
+      "step": 68
+    },
+    {
+      "epoch": 0.26198386331276696,
+      "grad_norm": 0.4969100058078766,
+      "learning_rate": 4.9131088976219695e-06,
+      "loss": 1.2685,
+      "step": 69
+    },
+    {
+      "epoch": 0.26578073089701,
+      "grad_norm": 0.4142298400402069,
+      "learning_rate": 4.908947566189362e-06,
+      "loss": 1.1168,
+      "step": 70
+    },
+    {
+      "epoch": 0.26957759848125296,
+      "grad_norm": 0.4250011444091797,
+      "learning_rate": 4.904690752084117e-06,
+      "loss": 1.1161,
+      "step": 71
+    },
+    {
+      "epoch": 0.273374466065496,
+      "grad_norm": 0.4570682644844055,
+      "learning_rate": 4.900338624032191e-06,
+      "loss": 1.2663,
+      "step": 72
+    },
+    {
+      "epoch": 0.27717133364973895,
+      "grad_norm": 0.43025946617126465,
+      "learning_rate": 4.895891354537472e-06,
+      "loss": 1.2616,
+      "step": 73
+    },
+    {
+      "epoch": 0.280968201233982,
+      "grad_norm": 0.42482641339302063,
+      "learning_rate": 4.891349119874936e-06,
+      "loss": 1.1215,
+      "step": 74
+    },
+    {
+      "epoch": 0.28476506881822494,
+      "grad_norm": 0.4691850244998932,
+      "learning_rate": 4.886712100083664e-06,
+      "loss": 1.1117,
+      "step": 75
+    },
+    {
+      "epoch": 0.28856193640246797,
+      "grad_norm": 0.4500940442085266,
+      "learning_rate": 4.881980478959707e-06,
+      "loss": 1.1082,
+      "step": 76
+    },
+    {
+      "epoch": 0.292358803986711,
+      "grad_norm": 0.3645106256008148,
+      "learning_rate": 4.877154444048792e-06,
+      "loss": 0.9683,
+      "step": 77
+    },
+    {
+      "epoch": 0.29615567157095396,
+      "grad_norm": 0.42706671357154846,
+      "learning_rate": 4.872234186638898e-06,
+      "loss": 1.106,
+      "step": 78
+    },
+    {
+      "epoch": 0.299952539155197,
+      "grad_norm": 0.416423499584198,
+      "learning_rate": 4.8672199017526725e-06,
+      "loss": 1.1109,
+      "step": 79
+    },
+    {
+      "epoch": 0.30374940673943995,
+      "grad_norm": 0.46140867471694946,
+      "learning_rate": 4.862111788139697e-06,
+      "loss": 1.2646,
+      "step": 80
+    },
+    {
+      "epoch": 0.307546274323683,
+      "grad_norm": 0.4429333508014679,
+      "learning_rate": 4.856910048268613e-06,
+      "loss": 1.1331,
+      "step": 81
+    },
+    {
+      "epoch": 0.31134314190792595,
+      "grad_norm": 0.42622944712638855,
+      "learning_rate": 4.851614888319093e-06,
+      "loss": 1.0966,
+      "step": 82
+    },
+    {
+      "epoch": 0.31514000949216897,
+      "grad_norm": 0.5261926054954529,
+      "learning_rate": 4.846226518173676e-06,
+      "loss": 1.2528,
+      "step": 83
+    },
+    {
+      "epoch": 0.31893687707641194,
+      "grad_norm": 0.4338201880455017,
+      "learning_rate": 4.840745151409437e-06,
+      "loss": 1.2542,
+      "step": 84
+    },
+    {
+      "epoch": 0.32273374466065496,
+      "grad_norm": 0.44151878356933594,
+      "learning_rate": 4.835171005289533e-06,
+      "loss": 1.1135,
+      "step": 85
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.4812638461589813,
+      "learning_rate": 4.8295043007545836e-06,
+      "loss": 1.2653,
+      "step": 86
+    },
+    {
+      "epoch": 0.33032747982914096,
+      "grad_norm": 0.562940239906311,
+      "learning_rate": 4.823745262413917e-06,
+      "loss": 1.2494,
+      "step": 87
+    },
+    {
+      "epoch": 0.334124347413384,
+      "grad_norm": 0.4242718517780304,
+      "learning_rate": 4.817894118536667e-06,
+      "loss": 1.1076,
+      "step": 88
+    },
+    {
+      "epoch": 0.33792121499762695,
+      "grad_norm": 0.45141878724098206,
+      "learning_rate": 4.811951101042722e-06,
+      "loss": 1.1108,
+      "step": 89
+    },
+    {
+      "epoch": 0.34171808258187,
+      "grad_norm": 0.5067852139472961,
+      "learning_rate": 4.805916445493538e-06,
+      "loss": 1.2272,
+      "step": 90
+    },
+    {
+      "epoch": 0.34551495016611294,
+      "grad_norm": 0.4855363965034485,
+      "learning_rate": 4.799790391082799e-06,
+      "loss": 1.1,
+      "step": 91
+    },
+    {
+      "epoch": 0.34931181775035597,
+      "grad_norm": 0.47762539982795715,
+      "learning_rate": 4.793573180626934e-06,
+      "loss": 1.2453,
+      "step": 92
+    },
+    {
+      "epoch": 0.35310868533459894,
+      "grad_norm": 0.5055530071258545,
+      "learning_rate": 4.787265060555495e-06,
+      "loss": 1.2437,
+      "step": 93
+    },
+    {
+      "epoch": 0.35690555291884196,
+      "grad_norm": 0.4677724838256836,
+      "learning_rate": 4.7808662809013895e-06,
+      "loss": 1.223,
+      "step": 94
+    },
+    {
+      "epoch": 0.36070242050308493,
+      "grad_norm": 0.47210943698883057,
+      "learning_rate": 4.774377095290969e-06,
+      "loss": 1.2287,
+      "step": 95
+    },
+    {
+      "epoch": 0.36449928808732796,
+      "grad_norm": 0.48820409178733826,
+      "learning_rate": 4.76779776093398e-06,
+      "loss": 1.0997,
+      "step": 96
+    },
+    {
+      "epoch": 0.368296155671571,
+      "grad_norm": 0.509981632232666,
+      "learning_rate": 4.761128538613359e-06,
+      "loss": 1.2303,
+      "step": 97
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 0.46266815066337585,
+      "learning_rate": 4.754369692674906e-06,
+      "loss": 1.2366,
+      "step": 98
+    },
+    {
+      "epoch": 0.375889890840057,
+      "grad_norm": 0.4689420759677887,
+      "learning_rate": 4.747521491016805e-06,
+      "loss": 1.2379,
+      "step": 99
+    },
+    {
+      "epoch": 0.37968675842429994,
+      "grad_norm": 0.454712837934494,
+      "learning_rate": 4.740584205079002e-06,
+      "loss": 1.1078,
+      "step": 100
+    },
+    {
+      "epoch": 0.38348362600854297,
+      "grad_norm": 0.5033725500106812,
+      "learning_rate": 4.7335581098324465e-06,
+      "loss": 1.2319,
+      "step": 101
+    },
+    {
+      "epoch": 0.38728049359278593,
+      "grad_norm": 0.5276666283607483,
+      "learning_rate": 4.726443483768195e-06,
+      "loss": 1.2373,
+      "step": 102
+    },
+    {
+      "epoch": 0.39107736117702896,
+      "grad_norm": 0.4005415737628937,
+      "learning_rate": 4.719240608886372e-06,
+      "loss": 0.9373,
+      "step": 103
+    },
+    {
+      "epoch": 0.39487422876127193,
+      "grad_norm": 0.456887423992157,
+      "learning_rate": 4.711949770684989e-06,
+      "loss": 1.2402,
+      "step": 104
+    },
+    {
+      "epoch": 0.39867109634551495,
+      "grad_norm": 0.4958035349845886,
+      "learning_rate": 4.704571258148634e-06,
+      "loss": 1.2327,
+      "step": 105
+    },
+    {
+      "epoch": 0.402467963929758,
+      "grad_norm": 0.40182697772979736,
+      "learning_rate": 4.697105363737015e-06,
+      "loss": 0.9684,
+      "step": 106
+    },
+    {
+      "epoch": 0.40626483151400095,
+      "grad_norm": 0.43226033449172974,
+      "learning_rate": 4.689552383373362e-06,
+      "loss": 1.0848,
+      "step": 107
+    },
+    {
+      "epoch": 0.41006169909824397,
+      "grad_norm": 0.4296877682209015,
+      "learning_rate": 4.681912616432707e-06,
+      "loss": 0.9568,
+      "step": 108
+    },
+    {
+      "epoch": 0.41385856668248694,
+      "grad_norm": 0.5179736018180847,
+      "learning_rate": 4.674186365730012e-06,
+      "loss": 1.2286,
+      "step": 109
+    },
+    {
+      "epoch": 0.41765543426672996,
+      "grad_norm": 0.4191986620426178,
+      "learning_rate": 4.666373937508166e-06,
+      "loss": 0.9606,
+      "step": 110
+    },
+    {
+      "epoch": 0.42145230185097293,
+      "grad_norm": 0.412567675113678,
+      "learning_rate": 4.658475641425854e-06,
+      "loss": 1.0793,
+      "step": 111
+    },
+    {
+      "epoch": 0.42524916943521596,
+      "grad_norm": 0.4645300507545471,
+      "learning_rate": 4.6504917905452705e-06,
+      "loss": 1.0835,
+      "step": 112
+    },
+    {
+      "epoch": 0.4290460370194589,
+      "grad_norm": 0.3561910092830658,
+      "learning_rate": 4.6424227013197235e-06,
+      "loss": 0.7952,
+      "step": 113
+    },
+    {
+      "epoch": 0.43284290460370195,
+      "grad_norm": 0.5064642429351807,
+      "learning_rate": 4.6342686935810795e-06,
+      "loss": 1.2319,
+      "step": 114
+    },
+    {
+      "epoch": 0.4366397721879449,
+      "grad_norm": 0.4808673858642578,
+      "learning_rate": 4.6260300905271e-06,
+      "loss": 1.223,
+      "step": 115
+    },
+    {
+      "epoch": 0.44043663977218794,
+      "grad_norm": 0.4152892529964447,
+      "learning_rate": 4.617707218708617e-06,
+      "loss": 1.0765,
+      "step": 116
+    },
+    {
+      "epoch": 0.44423350735643097,
+      "grad_norm": 0.49487704038619995,
+      "learning_rate": 4.6093004080166e-06,
+      "loss": 1.2205,
+      "step": 117
+    },
+    {
+      "epoch": 0.44803037494067394,
+      "grad_norm": 0.4736645817756653,
+      "learning_rate": 4.600809991669076e-06,
+      "loss": 1.0811,
+      "step": 118
+    },
+    {
+      "epoch": 0.45182724252491696,
+      "grad_norm": 0.46936193108558655,
+      "learning_rate": 4.59223630619792e-06,
+      "loss": 1.0809,
+      "step": 119
+    },
+    {
+      "epoch": 0.45562411010915993,
+      "grad_norm": 0.4555075466632843,
+      "learning_rate": 4.5835796914355195e-06,
+      "loss": 1.1008,
+      "step": 120
+    },
+    {
+      "epoch": 0.45942097769340295,
+      "grad_norm": 0.43824076652526855,
+      "learning_rate": 4.5748404905013045e-06,
+      "loss": 1.1092,
+      "step": 121
+    },
+    {
+      "epoch": 0.4632178452776459,
+      "grad_norm": 0.4486856162548065,
+      "learning_rate": 4.5660190497881455e-06,
+      "loss": 1.0784,
+      "step": 122
+    },
+    {
+      "epoch": 0.46701471286188895,
+      "grad_norm": 0.4244840145111084,
+      "learning_rate": 4.557115718948622e-06,
+      "loss": 0.958,
+      "step": 123
+    },
+    {
+      "epoch": 0.4708115804461319,
+      "grad_norm": 0.4413922429084778,
+      "learning_rate": 4.548130850881171e-06,
+      "loss": 1.2196,
+      "step": 124
+    },
+    {
+      "epoch": 0.47460844803037494,
+      "grad_norm": 0.4678729772567749,
+      "learning_rate": 4.53906480171609e-06,
+      "loss": 1.1124,
+      "step": 125
+    },
+    {
+      "epoch": 0.47840531561461797,
+      "grad_norm": 0.48969003558158875,
+      "learning_rate": 4.529917930801427e-06,
+      "loss": 1.2281,
+      "step": 126
+    },
+    {
+      "epoch": 0.48220218319886093,
+      "grad_norm": 0.4379821717739105,
+      "learning_rate": 4.520690600688734e-06,
+      "loss": 1.0849,
+      "step": 127
+    },
+    {
+      "epoch": 0.48599905078310396,
+      "grad_norm": 0.4471890330314636,
+      "learning_rate": 4.5113831771187e-06,
+      "loss": 1.0791,
+      "step": 128
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 0.49659088253974915,
+      "learning_rate": 4.501996029006651e-06,
+      "loss": 1.097,
+      "step": 129
+    },
+    {
+      "epoch": 0.49359278595158995,
+      "grad_norm": 0.4094451665878296,
+      "learning_rate": 4.492529528427929e-06,
+      "loss": 0.972,
+      "step": 130
+    },
+    {
+      "epoch": 0.4973896535358329,
+      "grad_norm": 0.4491405487060547,
+      "learning_rate": 4.4829840506031455e-06,
+      "loss": 1.0826,
+      "step": 131
+    },
+    {
+      "epoch": 0.5011865211200759,
+      "grad_norm": 0.42457208037376404,
+      "learning_rate": 4.473359973883305e-06,
+      "loss": 1.1066,
+      "step": 132
+    },
+    {
+      "epoch": 0.5049833887043189,
+      "grad_norm": 0.4856266379356384,
+      "learning_rate": 4.463657679734813e-06,
+      "loss": 1.225,
+      "step": 133
+    },
+    {
+      "epoch": 0.5087802562885619,
+      "grad_norm": 0.47458940744400024,
+      "learning_rate": 4.453877552724352e-06,
+      "loss": 1.2234,
+      "step": 134
+    },
+    {
+      "epoch": 0.512577123872805,
+      "grad_norm": 0.36578264832496643,
+      "learning_rate": 4.444019980503641e-06,
+      "loss": 0.9276,
+      "step": 135
+    },
+    {
+      "epoch": 0.516373991457048,
+      "grad_norm": 0.4141775965690613,
+      "learning_rate": 4.4340853537940715e-06,
+      "loss": 1.0895,
+      "step": 136
+    },
+    {
+      "epoch": 0.5201708590412909,
+      "grad_norm": 0.4604395031929016,
+      "learning_rate": 4.424074066371216e-06,
+      "loss": 1.2279,
+      "step": 137
+    },
+    {
+      "epoch": 0.5239677266255339,
+      "grad_norm": 0.4443908929824829,
+      "learning_rate": 4.4139865150492235e-06,
+      "loss": 1.0862,
+      "step": 138
+    },
+    {
+      "epoch": 0.527764594209777,
+      "grad_norm": 0.4457070529460907,
+      "learning_rate": 4.403823099665093e-06,
+      "loss": 1.2267,
+      "step": 139
+    },
+    {
+      "epoch": 0.53156146179402,
+      "grad_norm": 0.4152843952178955,
+      "learning_rate": 4.393584223062819e-06,
+      "loss": 1.0827,
+      "step": 140
+    },
+    {
+      "epoch": 0.5353583293782629,
+      "grad_norm": 0.42452365159988403,
+      "learning_rate": 4.38327029107743e-06,
+      "loss": 1.0743,
+      "step": 141
+    },
+    {
+      "epoch": 0.5391551969625059,
+      "grad_norm": 0.3921717703342438,
+      "learning_rate": 4.372881712518898e-06,
+      "loss": 0.9454,
+      "step": 142
+    },
+    {
+      "epoch": 0.5429520645467489,
+      "grad_norm": 0.5372737646102905,
+      "learning_rate": 4.362418899155941e-06,
+      "loss": 1.227,
+      "step": 143
+    },
+    {
+      "epoch": 0.546748932130992,
+      "grad_norm": 0.5399878621101379,
+      "learning_rate": 4.351882265699696e-06,
+      "loss": 1.2155,
+      "step": 144
+    },
+    {
+      "epoch": 0.550545799715235,
+      "grad_norm": 0.44373106956481934,
+      "learning_rate": 4.341272229787281e-06,
+      "loss": 1.0809,
+      "step": 145
+    },
+    {
+      "epoch": 0.5543426672994779,
+      "grad_norm": 0.4626406133174896,
+      "learning_rate": 4.330589211965246e-06,
+      "loss": 1.2145,
+      "step": 146
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 0.4238491356372833,
+      "learning_rate": 4.319833635672899e-06,
+      "loss": 1.0835,
+      "step": 147
+    },
+    {
+      "epoch": 0.561936402467964,
+      "grad_norm": 0.5245795249938965,
+      "learning_rate": 4.309005927225528e-06,
+      "loss": 1.222,
+      "step": 148
+    },
+    {
+      "epoch": 0.565733270052207,
+      "grad_norm": 0.43987414240837097,
+      "learning_rate": 4.2981065157974955e-06,
+      "loss": 0.9477,
+      "step": 149
+    },
+    {
+      "epoch": 0.5695301376364499,
+      "grad_norm": 0.4053569734096527,
+      "learning_rate": 4.287135833405235e-06,
+      "loss": 1.0717,
+      "step": 150
+    },
+    {
+      "epoch": 0.5733270052206929,
+      "grad_norm": 0.411527544260025,
+      "learning_rate": 4.276094314890122e-06,
+      "loss": 0.9402,
+      "step": 151
+    },
+    {
+      "epoch": 0.5771238728049359,
+      "grad_norm": 0.5262433290481567,
+      "learning_rate": 4.2649823979012424e-06,
+      "loss": 1.2261,
+      "step": 152
+    },
+    {
+      "epoch": 0.580920740389179,
+      "grad_norm": 0.44064462184906006,
+      "learning_rate": 4.253800522878043e-06,
+      "loss": 1.0823,
+      "step": 153
+    },
+    {
+      "epoch": 0.584717607973422,
+      "grad_norm": 0.4491995871067047,
+      "learning_rate": 4.242549133032872e-06,
+      "loss": 1.2246,
+      "step": 154
+    },
+    {
+      "epoch": 0.5885144755576649,
+      "grad_norm": 0.44037237763404846,
+      "learning_rate": 4.2312286743334174e-06,
+      "loss": 1.08,
+      "step": 155
+    },
+    {
+      "epoch": 0.5923113431419079,
+      "grad_norm": 0.4179958701133728,
+      "learning_rate": 4.219839595485026e-06,
+      "loss": 1.0792,
+      "step": 156
+    },
+    {
+      "epoch": 0.5961082107261509,
+      "grad_norm": 0.4985540509223938,
+      "learning_rate": 4.2083823479129175e-06,
+      "loss": 1.2162,
+      "step": 157
+    },
+    {
+      "epoch": 0.599905078310394,
+      "grad_norm": 0.43255966901779175,
+      "learning_rate": 4.196857385744295e-06,
+      "loss": 1.0821,
+      "step": 158
+    },
+    {
+      "epoch": 0.6037019458946369,
+      "grad_norm": 0.38958489894866943,
+      "learning_rate": 4.185265165790343e-06,
+      "loss": 0.93,
+      "step": 159
+    },
+    {
+      "epoch": 0.6074988134788799,
+      "grad_norm": 0.43625640869140625,
+      "learning_rate": 4.17360614752812e-06,
+      "loss": 1.0673,
+      "step": 160
+    },
+    {
+      "epoch": 0.6112956810631229,
+      "grad_norm": 0.3636965751647949,
+      "learning_rate": 4.161880793082348e-06,
+      "loss": 0.9311,
+      "step": 161
+    },
+    {
+      "epoch": 0.615092548647366,
+      "grad_norm": 0.41958415508270264,
+      "learning_rate": 4.150089567207094e-06,
+      "loss": 0.9723,
+      "step": 162
+    },
+    {
+      "epoch": 0.6188894162316089,
+      "grad_norm": 0.4178905189037323,
+      "learning_rate": 4.138232937267351e-06,
+      "loss": 0.9489,
+      "step": 163
+    },
+    {
+      "epoch": 0.6226862838158519,
+      "grad_norm": 0.4551599621772766,
+      "learning_rate": 4.126311373220511e-06,
+      "loss": 1.0803,
+      "step": 164
+    },
+    {
+      "epoch": 0.6264831514000949,
+      "grad_norm": 0.3745613992214203,
+      "learning_rate": 4.114325347597736e-06,
+      "loss": 0.9532,
+      "step": 165
+    },
+    {
+      "epoch": 0.6302800189843379,
+      "grad_norm": 0.4355705976486206,
+      "learning_rate": 4.102275335485234e-06,
+      "loss": 1.2055,
+      "step": 166
+    },
+    {
+      "epoch": 0.634076886568581,
+      "grad_norm": 0.43142765760421753,
+      "learning_rate": 4.0901618145054246e-06,
+      "loss": 1.216,
+      "step": 167
+    },
+    {
+      "epoch": 0.6378737541528239,
+      "grad_norm": 0.3976465165615082,
+      "learning_rate": 4.077985264798004e-06,
+      "loss": 0.9956,
+      "step": 168
+    },
+    {
+      "epoch": 0.6416706217370669,
+      "grad_norm": 0.4292868375778198,
+      "learning_rate": 4.06574616900092e-06,
+      "loss": 1.0555,
+      "step": 169
+    },
+    {
+      "epoch": 0.6454674893213099,
+      "grad_norm": 0.5177546143531799,
+      "learning_rate": 4.053445012231241e-06,
+      "loss": 1.2066,
+      "step": 170
+    },
+    {
+      "epoch": 0.649264356905553,
+      "grad_norm": 0.41628462076187134,
+      "learning_rate": 4.041082282065922e-06,
+      "loss": 1.21,
+      "step": 171
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 0.44618961215019226,
+      "learning_rate": 4.028658468522489e-06,
+      "loss": 1.2193,
+      "step": 172
+    },
+    {
+      "epoch": 0.6568580920740389,
+      "grad_norm": 0.44253483414649963,
+      "learning_rate": 4.016174064039602e-06,
+      "loss": 1.2155,
+      "step": 173
+    },
+    {
+      "epoch": 0.6606549596582819,
+      "grad_norm": 0.3929227292537689,
+      "learning_rate": 4.003629563457551e-06,
+      "loss": 1.0683,
+      "step": 174
+    },
+    {
+      "epoch": 0.6644518272425249,
+      "grad_norm": 0.5715161561965942,
+      "learning_rate": 3.991025463998632e-06,
+      "loss": 1.2264,
+      "step": 175
+    },
+    {
+      "epoch": 0.668248694826768,
+      "grad_norm": 0.4098718762397766,
+      "learning_rate": 3.978362265247444e-06,
+      "loss": 1.0723,
+      "step": 176
+    },
+    {
+      "epoch": 0.6720455624110109,
+      "grad_norm": 0.4266994595527649,
+      "learning_rate": 3.965640469131084e-06,
+      "loss": 1.0663,
+      "step": 177
+    },
+    {
+      "epoch": 0.6758424299952539,
+      "grad_norm": 0.379220187664032,
+      "learning_rate": 3.952860579899257e-06,
+      "loss": 0.9418,
+      "step": 178
+    },
+    {
+      "epoch": 0.6796392975794969,
+      "grad_norm": 0.3946760594844818,
+      "learning_rate": 3.940023104104281e-06,
+      "loss": 1.0605,
+      "step": 179
+    },
+    {
+      "epoch": 0.68343616516374,
+      "grad_norm": 0.47356459498405457,
+      "learning_rate": 3.9271285505810185e-06,
+      "loss": 1.0615,
+      "step": 180
+    },
+    {
+      "epoch": 0.6872330327479829,
+      "grad_norm": 0.4356970489025116,
+      "learning_rate": 3.9141774304267e-06,
+      "loss": 1.0714,
+      "step": 181
+    },
+    {
+      "epoch": 0.6910299003322259,
+      "grad_norm": 0.4237845540046692,
+      "learning_rate": 3.9011702569806716e-06,
+      "loss": 1.0862,
+      "step": 182
+    },
+    {
+      "epoch": 0.6948267679164689,
+      "grad_norm": 0.4926426410675049,
+      "learning_rate": 3.888107545804043e-06,
+      "loss": 1.2091,
+      "step": 183
+    },
+    {
+      "epoch": 0.6986236355007119,
+      "grad_norm": 0.43669024109840393,
+      "learning_rate": 3.874989814659258e-06,
+      "loss": 1.0805,
+      "step": 184
+    },
+    {
+      "epoch": 0.702420503084955,
+      "grad_norm": 0.435596227645874,
+      "learning_rate": 3.861817583489566e-06,
+      "loss": 1.2199,
+      "step": 185
+    },
+    {
+      "epoch": 0.7062173706691979,
+      "grad_norm": 0.407825231552124,
+      "learning_rate": 3.848591374398421e-06,
+      "loss": 1.1038,
+      "step": 186
+    },
+    {
+      "epoch": 0.7100142382534409,
+      "grad_norm": 0.41674646735191345,
+      "learning_rate": 3.835311711628774e-06,
+      "loss": 1.0718,
+      "step": 187
+    },
+    {
+      "epoch": 0.7138111058376839,
+      "grad_norm": 0.4335026144981384,
+      "learning_rate": 3.82197912154231e-06,
+      "loss": 1.0727,
+      "step": 188
+    },
+    {
+      "epoch": 0.717607973421927,
+      "grad_norm": 0.47680917382240295,
+      "learning_rate": 3.808594132598574e-06,
+      "loss": 1.2056,
+      "step": 189
+    },
+    {
+      "epoch": 0.7214048410061699,
+      "grad_norm": 0.38044315576553345,
+      "learning_rate": 3.7951572753340273e-06,
+      "loss": 0.9217,
+      "step": 190
+    },
+    {
+      "epoch": 0.7252017085904129,
+      "grad_norm": 0.4642685353755951,
+      "learning_rate": 3.781669082341018e-06,
+      "loss": 1.071,
+      "step": 191
+    },
+    {
+      "epoch": 0.7289985761746559,
+      "grad_norm": 0.4392843544483185,
+      "learning_rate": 3.768130088246674e-06,
+      "loss": 1.2135,
+      "step": 192
+    },
+    {
+      "epoch": 0.7327954437588989,
+      "grad_norm": 0.4412919580936432,
+      "learning_rate": 3.7545408296917087e-06,
+      "loss": 1.2025,
+      "step": 193
+    },
+    {
+      "epoch": 0.736592311343142,
+      "grad_norm": 0.4227074682712555,
+      "learning_rate": 3.740901845309152e-06,
+      "loss": 1.0674,
+      "step": 194
+    },
+    {
+      "epoch": 0.7403891789273849,
+      "grad_norm": 0.45686036348342896,
+      "learning_rate": 3.727213675703e-06,
+      "loss": 1.2151,
+      "step": 195
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 0.4000316262245178,
+      "learning_rate": 3.713476863426787e-06,
+      "loss": 1.0748,
+      "step": 196
+    },
+    {
+      "epoch": 0.7479829140958709,
+      "grad_norm": 0.42302843928337097,
+      "learning_rate": 3.699691952962083e-06,
+      "loss": 1.0892,
+      "step": 197
+    },
+    {
+      "epoch": 0.751779781680114,
+      "grad_norm": 0.4179258644580841,
+      "learning_rate": 3.6858594906969073e-06,
+      "loss": 1.0626,
+      "step": 198
+    },
+    {
+      "epoch": 0.7555766492643569,
+      "grad_norm": 0.4555260241031647,
+      "learning_rate": 3.6719800249040778e-06,
+      "loss": 1.2077,
+      "step": 199
+    },
+    {
+      "epoch": 0.7593735168485999,
+      "grad_norm": 0.36426669359207153,
+      "learning_rate": 3.6580541057194728e-06,
+      "loss": 0.944,
+      "step": 200
+    },
+    {
+      "epoch": 0.7631703844328429,
+      "grad_norm": 0.3654433786869049,
+      "learning_rate": 3.6440822851202312e-06,
+      "loss": 0.9322,
+      "step": 201
+    },
+    {
+      "epoch": 0.7669672520170859,
+      "grad_norm": 0.49382278323173523,
+      "learning_rate": 3.63006511690287e-06,
+      "loss": 1.2109,
+      "step": 202
+    },
+    {
+      "epoch": 0.770764119601329,
+      "grad_norm": 0.4325428307056427,
+      "learning_rate": 3.616003156661334e-06,
+      "loss": 1.0696,
+      "step": 203
+    },
+    {
+      "epoch": 0.7745609871855719,
+      "grad_norm": 0.4158753454685211,
+      "learning_rate": 3.6018969617649784e-06,
+      "loss": 1.0642,
+      "step": 204
+    },
+    {
+      "epoch": 0.7783578547698149,
+      "grad_norm": 0.4324316382408142,
+      "learning_rate": 3.5877470913364697e-06,
+      "loss": 1.2037,
+      "step": 205
+    },
+    {
+      "epoch": 0.7821547223540579,
+      "grad_norm": 0.46198171377182007,
+      "learning_rate": 3.5735541062296287e-06,
+      "loss": 1.0685,
+      "step": 206
+    },
+    {
+      "epoch": 0.7859515899383009,
+      "grad_norm": 0.43740782141685486,
+      "learning_rate": 3.559318569007198e-06,
+      "loss": 0.9377,
+      "step": 207
+    },
+    {
+      "epoch": 0.7897484575225439,
+      "grad_norm": 0.4424276351928711,
+      "learning_rate": 3.545041043918546e-06,
+      "loss": 1.2036,
+      "step": 208
+    },
+    {
+      "epoch": 0.7935453251067869,
+      "grad_norm": 0.4607738256454468,
+      "learning_rate": 3.5307220968772983e-06,
+      "loss": 1.2091,
+      "step": 209
+    },
+    {
+      "epoch": 0.7973421926910299,
+      "grad_norm": 0.4169575273990631,
+      "learning_rate": 3.516362295438911e-06,
+      "loss": 1.0704,
+      "step": 210
+    },
+    {
+      "epoch": 0.8011390602752729,
+      "grad_norm": 0.5177940130233765,
+      "learning_rate": 3.501962208778172e-06,
+      "loss": 1.2059,
+      "step": 211
+    },
+    {
+      "epoch": 0.804935927859516,
+      "grad_norm": 0.4142232835292816,
+      "learning_rate": 3.487522407666641e-06,
+      "loss": 1.0769,
+      "step": 212
+    },
+    {
+      "epoch": 0.8087327954437589,
+      "grad_norm": 0.4076462984085083,
+      "learning_rate": 3.473043464450027e-06,
+      "loss": 1.0677,
+      "step": 213
+    },
+    {
+      "epoch": 0.8125296630280019,
+      "grad_norm": 0.5051140785217285,
+      "learning_rate": 3.458525953025503e-06,
+      "loss": 1.0704,
+      "step": 214
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.37081989645957947,
+      "learning_rate": 3.443970448818954e-06,
+      "loss": 0.9524,
+      "step": 215
+    },
+    {
+      "epoch": 0.8201233981964879,
+      "grad_norm": 0.3888426423072815,
+      "learning_rate": 3.429377528762177e-06,
+      "loss": 1.0749,
+      "step": 216
+    },
+    {
+      "epoch": 0.8239202657807309,
+      "grad_norm": 0.49155759811401367,
+      "learning_rate": 3.414747771270007e-06,
+      "loss": 1.2125,
+      "step": 217
+    },
+    {
+      "epoch": 0.8277171333649739,
+      "grad_norm": 0.38015004992485046,
+      "learning_rate": 3.40008175621739e-06,
+      "loss": 1.0571,
+      "step": 218
+    },
+    {
+      "epoch": 0.8315140009492169,
+      "grad_norm": 0.4071613848209381,
+      "learning_rate": 3.3853800649164053e-06,
+      "loss": 1.053,
+      "step": 219
+    },
+    {
+      "epoch": 0.8353108685334599,
+      "grad_norm": 0.42250776290893555,
+      "learning_rate": 3.3706432800932184e-06,
+      "loss": 1.0685,
+      "step": 220
+    },
+    {
+      "epoch": 0.8391077361177028,
+      "grad_norm": 0.431573748588562,
+      "learning_rate": 3.3558719858649835e-06,
+      "loss": 1.0752,
+      "step": 221
+    },
+    {
+      "epoch": 0.8429046037019459,
+      "grad_norm": 0.46120485663414,
+      "learning_rate": 3.341066767716697e-06,
+      "loss": 1.2063,
+      "step": 222
+    },
+    {
+      "epoch": 0.8467014712861889,
+      "grad_norm": 0.4283529818058014,
+      "learning_rate": 3.3262282124779823e-06,
+      "loss": 1.0799,
+      "step": 223
+    },
+    {
+      "epoch": 0.8504983388704319,
+      "grad_norm": 0.37570565938949585,
+      "learning_rate": 3.3113569082998367e-06,
+      "loss": 1.0655,
+      "step": 224
+    },
+    {
+      "epoch": 0.8542952064546749,
+      "grad_norm": 0.2539384663105011,
+      "learning_rate": 3.2964534446313163e-06,
+      "loss": 0.4994,
+      "step": 225
+    },
+    {
+      "epoch": 0.8580920740389179,
+      "grad_norm": 0.4729446470737457,
+      "learning_rate": 3.2815184121961725e-06,
+      "loss": 1.2129,
+      "step": 226
+    },
+    {
+      "epoch": 0.8618889416231609,
+      "grad_norm": 0.3342674672603607,
+      "learning_rate": 3.266552402969437e-06,
+      "loss": 0.7854,
+      "step": 227
+    },
+    {
+      "epoch": 0.8656858092074039,
+      "grad_norm": 0.45071637630462646,
+      "learning_rate": 3.251556010153958e-06,
+      "loss": 1.2061,
+      "step": 228
+    },
+    {
+      "epoch": 0.8694826767916469,
+      "grad_norm": 0.4373473525047302,
+      "learning_rate": 3.2365298281568913e-06,
+      "loss": 1.0659,
+      "step": 229
+    },
+    {
+      "epoch": 0.8732795443758898,
+      "grad_norm": 0.42635422945022583,
+      "learning_rate": 3.2214744525661336e-06,
+      "loss": 1.2066,
+      "step": 230
+    },
+    {
+      "epoch": 0.8770764119601329,
+      "grad_norm": 0.45856305956840515,
+      "learning_rate": 3.2063904801267184e-06,
+      "loss": 1.1959,
+      "step": 231
+    },
+    {
+      "epoch": 0.8808732795443759,
+      "grad_norm": 0.4771096408367157,
+      "learning_rate": 3.191278508717166e-06,
+      "loss": 1.2025,
+      "step": 232
+    },
+    {
+      "epoch": 0.8846701471286189,
+      "grad_norm": 0.4655088484287262,
+      "learning_rate": 3.176139137325781e-06,
+      "loss": 1.2094,
+      "step": 233
+    },
+    {
+      "epoch": 0.8884670147128619,
+      "grad_norm": 0.39348939061164856,
+      "learning_rate": 3.1609729660269114e-06,
+      "loss": 1.0672,
+      "step": 234
+    },
+    {
+      "epoch": 0.8922638822971048,
+      "grad_norm": 0.445089727640152,
+      "learning_rate": 3.1457805959571663e-06,
+      "loss": 1.1994,
+      "step": 235
+    },
+    {
+      "epoch": 0.8960607498813479,
+      "grad_norm": 0.3999580144882202,
+      "learning_rate": 3.130562629291586e-06,
+      "loss": 1.0561,
+      "step": 236
+    },
+    {
+      "epoch": 0.8998576174655909,
+      "grad_norm": 0.4471660554409027,
+      "learning_rate": 3.1153196692197747e-06,
+      "loss": 1.0674,
+      "step": 237
+    },
+    {
+      "epoch": 0.9036544850498339,
+      "grad_norm": 0.4131118655204773,
+      "learning_rate": 3.100052319921992e-06,
+      "loss": 0.9328,
+      "step": 238
+    },
+    {
+      "epoch": 0.9074513526340768,
+      "grad_norm": 0.4657612144947052,
+      "learning_rate": 3.0847611865452064e-06,
+      "loss": 1.2085,
+      "step": 239
+    },
+    {
+      "epoch": 0.9112482202183199,
+      "grad_norm": 0.4662039577960968,
+      "learning_rate": 3.069446875179106e-06,
+      "loss": 1.2029,
+      "step": 240
+    },
+    {
+      "epoch": 0.9150450878025629,
+      "grad_norm": 0.41623374819755554,
+      "learning_rate": 3.0541099928320806e-06,
+      "loss": 0.9324,
+      "step": 241
+    },
+    {
+      "epoch": 0.9188419553868059,
+      "grad_norm": 0.4404604434967041,
+      "learning_rate": 3.0387511474071556e-06,
+      "loss": 1.0648,
+      "step": 242
+    },
+    {
+      "epoch": 0.9226388229710489,
+      "grad_norm": 0.3622177243232727,
+      "learning_rate": 3.023370947677901e-06,
+      "loss": 0.9238,
+      "step": 243
+    },
+    {
+      "epoch": 0.9264356905552918,
+      "grad_norm": 0.4089031517505646,
+      "learning_rate": 3.007970003264301e-06,
+      "loss": 1.0869,
+      "step": 244
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.4477076232433319,
+      "learning_rate": 2.99254892460859e-06,
+      "loss": 1.1983,
+      "step": 245
+    },
+    {
+      "epoch": 0.9340294257237779,
+      "grad_norm": 0.46868517994880676,
+      "learning_rate": 2.9771083229510543e-06,
+      "loss": 1.1963,
+      "step": 246
+    },
+    {
+      "epoch": 0.9378262933080209,
+      "grad_norm": 0.3464803397655487,
+      "learning_rate": 2.9616488103058115e-06,
+      "loss": 0.9272,
+      "step": 247
+    },
+    {
+      "epoch": 0.9416231608922638,
+      "grad_norm": 0.45595675706863403,
+      "learning_rate": 2.9461709994365445e-06,
+      "loss": 1.2056,
+      "step": 248
+    },
+    {
+      "epoch": 0.9454200284765069,
+      "grad_norm": 0.39231353998184204,
+      "learning_rate": 2.930675503832217e-06,
+      "loss": 1.0618,
+      "step": 249
+    },
+    {
+      "epoch": 0.9492168960607499,
+      "grad_norm": 0.3708343505859375,
+      "learning_rate": 2.91516293768276e-06,
+      "loss": 0.9102,
+      "step": 250
+    },
+    {
+      "epoch": 0.9530137636449929,
+      "grad_norm": 0.4427671432495117,
+      "learning_rate": 2.899633915854721e-06,
+      "loss": 1.2012,
+      "step": 251
+    },
+    {
+      "epoch": 0.9568106312292359,
+      "grad_norm": 0.33957725763320923,
+      "learning_rate": 2.8840890538668955e-06,
+      "loss": 0.8041,
+      "step": 252
+    },
+    {
+      "epoch": 0.9606074988134788,
+      "grad_norm": 0.3556421995162964,
+      "learning_rate": 2.868528967865934e-06,
+      "loss": 0.9198,
+      "step": 253
+    },
+    {
+      "epoch": 0.9644043663977219,
+      "grad_norm": 0.4399990439414978,
+      "learning_rate": 2.8529542746019118e-06,
+      "loss": 1.1998,
+      "step": 254
+    },
+    {
+      "epoch": 0.9682012339819649,
+      "grad_norm": 0.4560842514038086,
+      "learning_rate": 2.8373655914038907e-06,
+      "loss": 1.2007,
+      "step": 255
+    },
+    {
+      "epoch": 0.9719981015662079,
+      "grad_norm": 0.38949334621429443,
+      "learning_rate": 2.821763536155446e-06,
+      "loss": 1.0533,
+      "step": 256
+    },
+    {
+      "epoch": 0.9757949691504508,
+      "grad_norm": 0.40262502431869507,
+      "learning_rate": 2.806148727270176e-06,
+      "loss": 1.0585,
+      "step": 257
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 0.4113542139530182,
+      "learning_rate": 2.7905217836671915e-06,
+      "loss": 1.0601,
+      "step": 258
+    },
+    {
+      "epoch": 0.9833887043189369,
+      "grad_norm": 0.39467111229896545,
+      "learning_rate": 2.774883324746583e-06,
+      "loss": 1.0627,
+      "step": 259
+    },
+    {
+      "epoch": 0.9871855719031799,
+      "grad_norm": 0.4230286180973053,
+      "learning_rate": 2.7592339703648696e-06,
+      "loss": 1.2039,
+      "step": 260
+    },
+    {
+      "epoch": 0.9909824394874229,
+      "grad_norm": 0.3624156415462494,
+      "learning_rate": 2.743574340810431e-06,
+      "loss": 0.9253,
+      "step": 261
+    },
+    {
+      "epoch": 0.9947793070716658,
+      "grad_norm": 0.45184388756752014,
+      "learning_rate": 2.7279050567789195e-06,
+      "loss": 1.1943,
+      "step": 262
+    },
+    {
+      "epoch": 0.9985761746559089,
+      "grad_norm": 0.43259841203689575,
+      "learning_rate": 2.7122267393486605e-06,
+      "loss": 1.2086,
+      "step": 263
+    },
+    {
+      "epoch": 1.0023730422401518,
+      "grad_norm": 0.7363314628601074,
+      "learning_rate": 2.6965400099560305e-06,
+      "loss": 1.9312,
+      "step": 264
+    },
+    {
+      "epoch": 1.0061699098243948,
+      "grad_norm": 0.42088714241981506,
+      "learning_rate": 2.6808454903708313e-06,
+      "loss": 1.0671,
+      "step": 265
+    },
+    {
+      "epoch": 1.0099667774086378,
+      "grad_norm": 0.47700321674346924,
+      "learning_rate": 2.66514380267164e-06,
+      "loss": 1.2008,
+      "step": 266
+    },
+    {
+      "epoch": 1.0137636449928809,
+      "grad_norm": 0.40473899245262146,
+      "learning_rate": 2.6494355692211537e-06,
+      "loss": 1.0598,
+      "step": 267
+    },
+    {
+      "epoch": 1.0175605125771239,
+      "grad_norm": 0.40599343180656433,
+      "learning_rate": 2.6337214126415237e-06,
+      "loss": 1.0582,
+      "step": 268
+    },
+    {
+      "epoch": 1.021357380161367,
+      "grad_norm": 0.49867045879364014,
+      "learning_rate": 2.6180019557896725e-06,
+      "loss": 1.1879,
+      "step": 269
+    },
+    {
+      "epoch": 1.02515424774561,
+      "grad_norm": 0.432919442653656,
+      "learning_rate": 2.6022778217326077e-06,
+      "loss": 1.1843,
+      "step": 270
+    },
+    {
+      "epoch": 1.028951115329853,
+      "grad_norm": 0.40411439538002014,
+      "learning_rate": 2.586549633722726e-06,
+      "loss": 1.2015,
+      "step": 271
+    },
+    {
+      "epoch": 1.032747982914096,
+      "grad_norm": 0.4091154932975769,
+      "learning_rate": 2.5708180151731105e-06,
+      "loss": 1.0366,
+      "step": 272
+    },
+    {
+      "epoch": 1.0365448504983388,
+      "grad_norm": 0.41487744450569153,
+      "learning_rate": 2.555083589632818e-06,
+      "loss": 1.0597,
+      "step": 273
+    },
+    {
+      "epoch": 1.0403417180825818,
+      "grad_norm": 0.43414047360420227,
+      "learning_rate": 2.5393469807621646e-06,
+      "loss": 1.1722,
+      "step": 274
+    },
+    {
+      "epoch": 1.0441385856668248,
+      "grad_norm": 0.43517452478408813,
+      "learning_rate": 2.523608812308009e-06,
+      "loss": 1.1897,
+      "step": 275
+    },
+    {
+      "epoch": 1.0479354532510678,
+      "grad_norm": 0.41618216037750244,
+      "learning_rate": 2.5078697080790248e-06,
+      "loss": 1.0384,
+      "step": 276
+    },
+    {
+      "epoch": 1.0517323208353109,
+      "grad_norm": 0.3956233561038971,
+      "learning_rate": 2.4921302919209765e-06,
+      "loss": 1.0523,
+      "step": 277
+    },
+    {
+      "epoch": 1.055529188419554,
+      "grad_norm": 0.3869052231311798,
+      "learning_rate": 2.476391187691992e-06,
+      "loss": 1.0695,
+      "step": 278
+    },
+    {
+      "epoch": 1.059326056003797,
+      "grad_norm": 0.38108527660369873,
+      "learning_rate": 2.4606530192378358e-06,
+      "loss": 0.9268,
+      "step": 279
+    },
+    {
+      "epoch": 1.06312292358804,
+      "grad_norm": 0.40593841671943665,
+      "learning_rate": 2.4449164103671834e-06,
+      "loss": 1.0487,
+      "step": 280
+    },
+    {
+      "epoch": 1.0669197911722827,
+      "grad_norm": 0.35500654578208923,
+      "learning_rate": 2.4291819848268908e-06,
+      "loss": 0.9251,
+      "step": 281
+    },
+    {
+      "epoch": 1.0707166587565258,
+      "grad_norm": 0.40299785137176514,
+      "learning_rate": 2.4134503662772754e-06,
+      "loss": 1.0533,
+      "step": 282
+    },
+    {
+      "epoch": 1.0745135263407688,
+      "grad_norm": 0.43219995498657227,
+      "learning_rate": 2.3977221782673936e-06,
+      "loss": 1.1866,
+      "step": 283
+    },
+    {
+      "epoch": 1.0783103939250118,
+      "grad_norm": 0.45522886514663696,
+      "learning_rate": 2.3819980442103288e-06,
+      "loss": 1.2028,
+      "step": 284
+    },
+    {
+      "epoch": 1.0821072615092548,
+      "grad_norm": 0.4167502522468567,
+      "learning_rate": 2.3662785873584775e-06,
+      "loss": 1.0328,
+      "step": 285
+    },
+    {
+      "epoch": 1.0859041290934979,
+      "grad_norm": 0.402190238237381,
+      "learning_rate": 2.350564430778847e-06,
+      "loss": 1.0613,
+      "step": 286
+    },
+    {
+      "epoch": 1.089700996677741,
+      "grad_norm": 0.36273133754730225,
+      "learning_rate": 2.3348561973283613e-06,
+      "loss": 0.9201,
+      "step": 287
+    },
+    {
+      "epoch": 1.093497864261984,
+      "grad_norm": 0.41140493750572205,
+      "learning_rate": 2.31915450962917e-06,
+      "loss": 1.0598,
+      "step": 288
+    },
+    {
+      "epoch": 1.097294731846227,
+      "grad_norm": 0.3959132730960846,
+      "learning_rate": 2.3034599900439703e-06,
+      "loss": 1.0547,
+      "step": 289
+    },
+    {
+      "epoch": 1.10109159943047,
+      "grad_norm": 0.43085983395576477,
+      "learning_rate": 2.2877732606513407e-06,
+      "loss": 1.1836,
+      "step": 290
+    },
+    {
+      "epoch": 1.1048884670147128,
+      "grad_norm": 0.37919700145721436,
+      "learning_rate": 2.2720949432210813e-06,
+      "loss": 1.0431,
+      "step": 291
+    },
+    {
+      "epoch": 1.1086853345989558,
+      "grad_norm": 0.3869677186012268,
+      "learning_rate": 2.2564256591895695e-06,
+      "loss": 0.9199,
+      "step": 292
+    },
+    {
+      "epoch": 1.1124822021831988,
+      "grad_norm": 0.40192729234695435,
+      "learning_rate": 2.2407660296351313e-06,
+      "loss": 0.9259,
+      "step": 293
+    },
+    {
+      "epoch": 1.1162790697674418,
+      "grad_norm": 0.41164687275886536,
+      "learning_rate": 2.225116675253418e-06,
+      "loss": 1.0489,
+      "step": 294
+    },
+    {
+      "epoch": 1.1200759373516849,
+      "grad_norm": 0.3917531371116638,
+      "learning_rate": 2.209478216332809e-06,
+      "loss": 1.0493,
+      "step": 295
+    },
+    {
+      "epoch": 1.123872804935928,
+      "grad_norm": 0.3413256108760834,
+      "learning_rate": 2.193851272729825e-06,
+      "loss": 0.9091,
+      "step": 296
+    },
+    {
+      "epoch": 1.127669672520171,
+      "grad_norm": 0.4337766170501709,
+      "learning_rate": 2.1782364638445545e-06,
+      "loss": 1.191,
+      "step": 297
+    },
+    {
+      "epoch": 1.131466540104414,
+      "grad_norm": 0.42421215772628784,
+      "learning_rate": 2.16263440859611e-06,
+      "loss": 1.1943,
+      "step": 298
+    },
+    {
+      "epoch": 1.1352634076886567,
+      "grad_norm": 0.38704779744148254,
+      "learning_rate": 2.1470457253980887e-06,
+      "loss": 1.1828,
+      "step": 299
+    },
+    {
+      "epoch": 1.1390602752728998,
+      "grad_norm": 0.38762617111206055,
+      "learning_rate": 2.131471032134067e-06,
+      "loss": 1.0479,
+      "step": 300
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.3805724084377289,
+      "learning_rate": 2.115910946133105e-06,
+      "loss": 1.049,
+      "step": 301
+    },
+    {
+      "epoch": 1.1466540104413858,
+      "grad_norm": 0.38618871569633484,
+      "learning_rate": 2.10036608414528e-06,
+      "loss": 1.0566,
+      "step": 302
+    },
+    {
+      "epoch": 1.1504508780256288,
+      "grad_norm": 0.32153603434562683,
+      "learning_rate": 2.084837062317241e-06,
+      "loss": 0.7648,
+      "step": 303
+    },
+    {
+      "epoch": 1.1542477456098719,
+      "grad_norm": 0.4316171109676361,
+      "learning_rate": 2.0693244961677834e-06,
+      "loss": 1.183,
+      "step": 304
+    },
+    {
+      "epoch": 1.158044613194115,
+      "grad_norm": 0.3866140842437744,
+      "learning_rate": 2.0538290005634564e-06,
+      "loss": 1.1986,
+      "step": 305
+    },
+    {
+      "epoch": 1.161841480778358,
+      "grad_norm": 0.41327404975891113,
+      "learning_rate": 2.0383511896941894e-06,
+      "loss": 1.1974,
+      "step": 306
+    },
+    {
+      "epoch": 1.165638348362601,
+      "grad_norm": 0.37834978103637695,
+      "learning_rate": 2.0228916770489466e-06,
+      "loss": 1.0443,
+      "step": 307
+    },
+    {
+      "epoch": 1.169435215946844,
+      "grad_norm": 0.41474854946136475,
+      "learning_rate": 2.0074510753914113e-06,
+      "loss": 1.1803,
+      "step": 308
+    },
+    {
+      "epoch": 1.1732320835310868,
+      "grad_norm": 0.3727324306964874,
+      "learning_rate": 1.9920299967356995e-06,
+      "loss": 1.055,
+      "step": 309
+    },
+    {
+      "epoch": 1.1770289511153298,
+      "grad_norm": 0.40379658341407776,
+      "learning_rate": 1.9766290523220997e-06,
+      "loss": 1.2038,
+      "step": 310
+    },
+    {
+      "epoch": 1.1808258186995728,
+      "grad_norm": 0.39679378271102905,
+      "learning_rate": 1.9612488525928453e-06,
+      "loss": 1.1826,
+      "step": 311
+    },
+    {
+      "epoch": 1.1846226862838158,
+      "grad_norm": 0.4498043954372406,
+      "learning_rate": 1.94589000716792e-06,
+      "loss": 1.1875,
+      "step": 312
+    },
+    {
+      "epoch": 1.1884195538680589,
+      "grad_norm": 0.41798946261405945,
+      "learning_rate": 1.9305531248208948e-06,
+      "loss": 1.1847,
+      "step": 313
+    },
+    {
+      "epoch": 1.1922164214523019,
+      "grad_norm": 0.42096462845802307,
+      "learning_rate": 1.9152388134547944e-06,
+      "loss": 1.059,
+      "step": 314
+    },
+    {
+      "epoch": 1.196013289036545,
+      "grad_norm": 0.3939502537250519,
+      "learning_rate": 1.8999476800780087e-06,
+      "loss": 1.0457,
+      "step": 315
+    },
+    {
+      "epoch": 1.199810156620788,
+      "grad_norm": 0.44725000858306885,
+      "learning_rate": 1.8846803307802263e-06,
+      "loss": 1.1939,
+      "step": 316
+    },
+    {
+      "epoch": 1.2036070242050307,
+      "grad_norm": 0.3450300097465515,
+      "learning_rate": 1.8694373707084148e-06,
+      "loss": 0.9045,
+      "step": 317
+    },
+    {
+      "epoch": 1.2074038917892738,
+      "grad_norm": 0.4713125228881836,
+      "learning_rate": 1.854219404042834e-06,
+      "loss": 1.1848,
+      "step": 318
+    },
+    {
+      "epoch": 1.2112007593735168,
+      "grad_norm": 0.33273351192474365,
+      "learning_rate": 1.8390270339730892e-06,
+      "loss": 0.7687,
+      "step": 319
+    },
+    {
+      "epoch": 1.2149976269577598,
+      "grad_norm": 0.35393235087394714,
+      "learning_rate": 1.82386086267422e-06,
+      "loss": 0.9687,
+      "step": 320
+    },
+    {
+      "epoch": 1.2187944945420028,
+      "grad_norm": 0.35949307680130005,
+      "learning_rate": 1.8087214912828343e-06,
+      "loss": 0.9033,
+      "step": 321
+    },
+    {
+      "epoch": 1.2225913621262459,
+      "grad_norm": 0.42038631439208984,
+      "learning_rate": 1.793609519873282e-06,
+      "loss": 1.1888,
+      "step": 322
+    },
+    {
+      "epoch": 1.2263882297104889,
+      "grad_norm": 0.4522581696510315,
+      "learning_rate": 1.7785255474338675e-06,
+      "loss": 1.188,
+      "step": 323
+    },
+    {
+      "epoch": 1.230185097294732,
+      "grad_norm": 0.3686380386352539,
+      "learning_rate": 1.763470171843109e-06,
+      "loss": 1.0683,
+      "step": 324
+    },
+    {
+      "epoch": 1.233981964878975,
+      "grad_norm": 0.4130842685699463,
+      "learning_rate": 1.748443989846042e-06,
+      "loss": 1.1772,
+      "step": 325
+    },
+    {
+      "epoch": 1.237778832463218,
+      "grad_norm": 0.3096576929092407,
+      "learning_rate": 1.7334475970305639e-06,
+      "loss": 0.767,
+      "step": 326
+    },
+    {
+      "epoch": 1.2415757000474608,
+      "grad_norm": 0.3671686351299286,
+      "learning_rate": 1.718481587803828e-06,
+      "loss": 0.9131,
+      "step": 327
+    },
+    {
+      "epoch": 1.2453725676317038,
+      "grad_norm": 0.4213862717151642,
+      "learning_rate": 1.7035465553686839e-06,
+      "loss": 1.1863,
+      "step": 328
+    },
+    {
+      "epoch": 1.2491694352159468,
+      "grad_norm": 0.3827097713947296,
+      "learning_rate": 1.688643091700164e-06,
+      "loss": 1.0456,
+      "step": 329
+    },
+    {
+      "epoch": 1.2529663028001898,
+      "grad_norm": 0.3981434106826782,
+      "learning_rate": 1.6737717875220177e-06,
+      "loss": 1.0414,
+      "step": 330
+    },
+    {
+      "epoch": 1.2567631703844329,
+      "grad_norm": 0.3808799982070923,
+      "learning_rate": 1.6589332322833035e-06,
+      "loss": 1.0457,
+      "step": 331
+    },
+    {
+      "epoch": 1.2605600379686759,
+      "grad_norm": 0.39812132716178894,
+      "learning_rate": 1.6441280141350169e-06,
+      "loss": 1.0624,
+      "step": 332
+    },
+    {
+      "epoch": 1.264356905552919,
+      "grad_norm": 0.3926783502101898,
+      "learning_rate": 1.6293567199067827e-06,
+      "loss": 1.1868,
+      "step": 333
+    },
+    {
+      "epoch": 1.2681537731371617,
+      "grad_norm": 0.42180249094963074,
+      "learning_rate": 1.6146199350835956e-06,
+      "loss": 1.1785,
+      "step": 334
+    },
+    {
+      "epoch": 1.2719506407214047,
+      "grad_norm": 0.3862990736961365,
+      "learning_rate": 1.5999182437826111e-06,
+      "loss": 1.0557,
+      "step": 335
+    },
+    {
+      "epoch": 1.2757475083056478,
+      "grad_norm": 0.33035123348236084,
+      "learning_rate": 1.5852522287299946e-06,
+      "loss": 0.9202,
+      "step": 336
+    },
+    {
+      "epoch": 1.2795443758898908,
+      "grad_norm": 0.3912082612514496,
+      "learning_rate": 1.5706224712378237e-06,
+      "loss": 1.0578,
+      "step": 337
+    },
+    {
+      "epoch": 1.2833412434741338,
+      "grad_norm": 0.368190199136734,
+      "learning_rate": 1.5560295511810465e-06,
+      "loss": 1.0456,
+      "step": 338
+    },
+    {
+      "epoch": 1.2871381110583768,
+      "grad_norm": 0.3697574734687805,
+      "learning_rate": 1.5414740469744986e-06,
+      "loss": 1.0412,
+      "step": 339
+    },
+    {
+      "epoch": 1.2909349786426199,
+      "grad_norm": 0.3395715057849884,
+      "learning_rate": 1.5269565355499738e-06,
+      "loss": 0.9436,
+      "step": 340
+    },
+    {
+      "epoch": 1.2947318462268629,
+      "grad_norm": 0.38877978920936584,
+      "learning_rate": 1.5124775923333604e-06,
+      "loss": 1.0565,
+      "step": 341
+    },
+    {
+      "epoch": 1.298528713811106,
+      "grad_norm": 0.3653126060962677,
+      "learning_rate": 1.4980377912218291e-06,
+      "loss": 1.0534,
+      "step": 342
+    },
+    {
+      "epoch": 1.302325581395349,
+      "grad_norm": 0.403150737285614,
+      "learning_rate": 1.4836377045610903e-06,
+      "loss": 1.063,
+      "step": 343
+    },
+    {
+      "epoch": 1.306122448979592,
+      "grad_norm": 0.3969637155532837,
+      "learning_rate": 1.4692779031227032e-06,
+      "loss": 1.1949,
+      "step": 344
+    },
+    {
+      "epoch": 1.3099193165638348,
+      "grad_norm": 0.3859919607639313,
+      "learning_rate": 1.4549589560814558e-06,
+      "loss": 1.0345,
+      "step": 345
+    },
+    {
+      "epoch": 1.3137161841480778,
+      "grad_norm": 0.3501088321208954,
+      "learning_rate": 1.440681430992803e-06,
+      "loss": 1.0387,
+      "step": 346
+    },
+    {
+      "epoch": 1.3175130517323208,
+      "grad_norm": 0.38995981216430664,
+      "learning_rate": 1.4264458937703717e-06,
+      "loss": 1.0632,
+      "step": 347
+    },
+    {
+      "epoch": 1.3213099193165638,
+      "grad_norm": 0.3388945460319519,
+      "learning_rate": 1.4122529086635312e-06,
+      "loss": 0.9119,
+      "step": 348
+    },
+    {
+      "epoch": 1.3251067869008069,
+      "grad_norm": 0.37815216183662415,
+      "learning_rate": 1.398103038235022e-06,
+      "loss": 1.1801,
+      "step": 349
+    },
+    {
+      "epoch": 1.3289036544850499,
+      "grad_norm": 0.3603959381580353,
+      "learning_rate": 1.3839968433386659e-06,
+      "loss": 1.0401,
+      "step": 350
+    },
+    {
+      "epoch": 1.332700522069293,
+      "grad_norm": 0.4169382154941559,
+      "learning_rate": 1.3699348830971316e-06,
+      "loss": 1.1889,
+      "step": 351
+    },
+    {
+      "epoch": 1.3364973896535357,
+      "grad_norm": 0.4009808599948883,
+      "learning_rate": 1.3559177148797698e-06,
+      "loss": 1.1802,
+      "step": 352
+    },
+    {
+      "epoch": 1.3402942572377787,
+      "grad_norm": 0.3702283203601837,
+      "learning_rate": 1.3419458942805274e-06,
+      "loss": 0.9253,
+      "step": 353
+    },
+    {
+      "epoch": 1.3440911248220218,
+      "grad_norm": 0.3447802662849426,
+      "learning_rate": 1.3280199750959233e-06,
+      "loss": 0.9254,
+      "step": 354
+    },
+    {
+      "epoch": 1.3478879924062648,
+      "grad_norm": 0.40221476554870605,
+      "learning_rate": 1.314140509303093e-06,
+      "loss": 1.0729,
+      "step": 355
+    },
+    {
+      "epoch": 1.3516848599905078,
+      "grad_norm": 0.40008315443992615,
+      "learning_rate": 1.3003080470379176e-06,
+      "loss": 1.1839,
+      "step": 356
+    },
+    {
+      "epoch": 1.3554817275747508,
+      "grad_norm": 0.4559074640274048,
+      "learning_rate": 1.2865231365732136e-06,
+      "loss": 1.184,
+      "step": 357
+    },
+    {
+      "epoch": 1.3592785951589939,
+      "grad_norm": 0.3520359694957733,
+      "learning_rate": 1.2727863242970007e-06,
+      "loss": 0.9056,
+      "step": 358
+    },
+    {
+      "epoch": 1.3630754627432369,
+      "grad_norm": 0.39236965775489807,
+      "learning_rate": 1.2590981546908481e-06,
+      "loss": 1.1798,
+      "step": 359
+    },
+    {
+      "epoch": 1.36687233032748,
+      "grad_norm": 0.39921608567237854,
+      "learning_rate": 1.245459170308292e-06,
+      "loss": 1.1876,
+      "step": 360
+    },
+    {
+      "epoch": 1.370669197911723,
+      "grad_norm": 0.32645294070243835,
+      "learning_rate": 1.2318699117533264e-06,
+      "loss": 0.9214,
+      "step": 361
+    },
+    {
+      "epoch": 1.374466065495966,
+      "grad_norm": 0.3884054720401764,
+      "learning_rate": 1.2183309176589822e-06,
+      "loss": 1.1828,
+      "step": 362
+    },
+    {
+      "epoch": 1.3782629330802088,
+      "grad_norm": 0.3472171425819397,
+      "learning_rate": 1.2048427246659738e-06,
+      "loss": 0.9014,
+      "step": 363
+    },
+    {
+      "epoch": 1.3820598006644518,
+      "grad_norm": 0.34238362312316895,
+      "learning_rate": 1.1914058674014264e-06,
+      "loss": 0.9166,
+      "step": 364
+    },
+    {
+      "epoch": 1.3858566682486948,
+      "grad_norm": 0.4093136489391327,
+      "learning_rate": 1.17802087845769e-06,
+      "loss": 1.1757,
+      "step": 365
+    },
+    {
+      "epoch": 1.3896535358329378,
+      "grad_norm": 0.4089086949825287,
+      "learning_rate": 1.164688288371227e-06,
+      "loss": 1.1898,
+      "step": 366
+    },
+    {
+      "epoch": 1.3934504034171808,
+      "grad_norm": 0.36652591824531555,
+      "learning_rate": 1.1514086256015803e-06,
+      "loss": 1.0574,
+      "step": 367
+    },
+    {
+      "epoch": 1.3972472710014239,
+      "grad_norm": 0.3458910584449768,
+      "learning_rate": 1.138182416510434e-06,
+      "loss": 1.0404,
+      "step": 368
+    },
+    {
+      "epoch": 1.401044138585667,
+      "grad_norm": 0.403898149728775,
+      "learning_rate": 1.1250101853407427e-06,
+      "loss": 1.185,
+      "step": 369
+    },
+    {
+      "epoch": 1.4048410061699097,
+      "grad_norm": 0.38953447341918945,
+      "learning_rate": 1.1118924541959573e-06,
+      "loss": 1.1767,
+      "step": 370
+    },
+    {
+      "epoch": 1.4086378737541527,
+      "grad_norm": 0.41569021344184875,
+      "learning_rate": 1.09882974301933e-06,
+      "loss": 1.1867,
+      "step": 371
+    },
+    {
+      "epoch": 1.4124347413383957,
+      "grad_norm": 0.3661198019981384,
+      "learning_rate": 1.0858225695733006e-06,
+      "loss": 1.0516,
+      "step": 372
+    },
+    {
+      "epoch": 1.4162316089226388,
+      "grad_norm": 0.40183043479919434,
+      "learning_rate": 1.072871449418982e-06,
+      "loss": 1.0376,
+      "step": 373
+    },
+    {
+      "epoch": 1.4200284765068818,
+      "grad_norm": 0.3806290030479431,
+      "learning_rate": 1.0599768958957193e-06,
+      "loss": 1.0473,
+      "step": 374
+    },
+    {
+      "epoch": 1.4238253440911248,
+      "grad_norm": 0.3974708616733551,
+      "learning_rate": 1.0471394201007435e-06,
+      "loss": 1.1799,
+      "step": 375
+    },
+    {
+      "epoch": 1.4276222116753678,
+      "grad_norm": 0.37168920040130615,
+      "learning_rate": 1.0343595308689156e-06,
+      "loss": 1.0478,
+      "step": 376
+    },
+    {
+      "epoch": 1.4314190792596109,
+      "grad_norm": 0.36702632904052734,
+      "learning_rate": 1.021637734752557e-06,
+      "loss": 1.0368,
+      "step": 377
+    },
+    {
+      "epoch": 1.435215946843854,
+      "grad_norm": 0.36013931035995483,
+      "learning_rate": 1.0089745360013685e-06,
+      "loss": 1.0488,
+      "step": 378
+    },
+    {
+      "epoch": 1.439012814428097,
+      "grad_norm": 0.39848053455352783,
+      "learning_rate": 9.963704365424494e-07,
+      "loss": 1.0501,
+      "step": 379
+    },
+    {
+      "epoch": 1.44280968201234,
+      "grad_norm": 0.3630136549472809,
+      "learning_rate": 9.838259359603987e-07,
+      "loss": 1.0455,
+      "step": 380
+    },
+    {
+      "epoch": 1.4466065495965827,
+      "grad_norm": 0.38877931237220764,
+      "learning_rate": 9.713415314775122e-07,
+      "loss": 1.1887,
+      "step": 381
+    },
+    {
+      "epoch": 1.4504034171808258,
+      "grad_norm": 0.3823590874671936,
+      "learning_rate": 9.589177179340775e-07,
+      "loss": 1.1795,
+      "step": 382
+    },
+    {
+      "epoch": 1.4542002847650688,
+      "grad_norm": 0.31407251954078674,
+      "learning_rate": 9.465549877687602e-07,
+      "loss": 0.8088,
+      "step": 383
+    },
+    {
+      "epoch": 1.4579971523493118,
+      "grad_norm": 0.3785543143749237,
+      "learning_rate": 9.342538309990804e-07,
+      "loss": 1.0545,
+      "step": 384
+    },
+    {
+      "epoch": 1.4617940199335548,
+      "grad_norm": 0.3719753921031952,
+      "learning_rate": 9.220147352019965e-07,
+      "loss": 1.1924,
+      "step": 385
+    },
+    {
+      "epoch": 1.4655908875177979,
+      "grad_norm": 0.3974050283432007,
+      "learning_rate": 9.098381854945762e-07,
+      "loss": 1.0512,
+      "step": 386
+    },
+    {
+      "epoch": 1.469387755102041,
+      "grad_norm": 0.380188912153244,
+      "learning_rate": 8.977246645147655e-07,
+      "loss": 1.1842,
+      "step": 387
+    },
+    {
+      "epoch": 1.4731846226862837,
+      "grad_norm": 0.33522146940231323,
+      "learning_rate": 8.856746524022647e-07,
+      "loss": 0.9293,
+      "step": 388
+    },
+    {
+      "epoch": 1.4769814902705267,
+      "grad_norm": 0.34948912262916565,
+      "learning_rate": 8.736886267794911e-07,
+      "loss": 1.0576,
+      "step": 389
+    },
+    {
+      "epoch": 1.4807783578547697,
+      "grad_norm": 0.3386431336402893,
+      "learning_rate": 8.617670627326503e-07,
+      "loss": 0.9029,
+      "step": 390
+    },
+    {
+      "epoch": 1.4845752254390128,
+      "grad_norm": 0.32754087448120117,
+      "learning_rate": 8.49910432792907e-07,
+      "loss": 0.9201,
+      "step": 391
+    },
+    {
+      "epoch": 1.4883720930232558,
+      "grad_norm": 0.38169023394584656,
+      "learning_rate": 8.381192069176539e-07,
+      "loss": 1.1824,
+      "step": 392
+    },
+    {
+      "epoch": 1.4921689606074988,
+      "grad_norm": 0.3721928596496582,
+      "learning_rate": 8.263938524718812e-07,
+      "loss": 1.0526,
+      "step": 393
+    },
+    {
+      "epoch": 1.4959658281917418,
+      "grad_norm": 0.3896506130695343,
+      "learning_rate": 8.147348342096579e-07,
+      "loss": 1.1811,
+      "step": 394
+    },
+    {
+      "epoch": 1.4997626957759849,
+      "grad_norm": 0.3741244375705719,
+      "learning_rate": 8.031426142557061e-07,
+      "loss": 1.0512,
+      "step": 395
+    },
+    {
+      "epoch": 1.503559563360228,
+      "grad_norm": 0.3273400366306305,
+      "learning_rate": 7.916176520870836e-07,
+      "loss": 0.905,
+      "step": 396
+    },
+    {
+      "epoch": 1.507356430944471,
+      "grad_norm": 0.3622443675994873,
+      "learning_rate": 7.80160404514975e-07,
+      "loss": 1.0561,
+      "step": 397
+    },
+    {
+      "epoch": 1.511153298528714,
+      "grad_norm": 0.3936561048030853,
+      "learning_rate": 7.687713256665835e-07,
+      "loss": 1.1887,
+      "step": 398
+    },
+    {
+      "epoch": 1.514950166112957,
+      "grad_norm": 0.37885287404060364,
+      "learning_rate": 7.574508669671288e-07,
+      "loss": 1.185,
+      "step": 399
+    },
+    {
+      "epoch": 1.5187470336971998,
+      "grad_norm": 0.36686670780181885,
+      "learning_rate": 7.46199477121958e-07,
+      "loss": 1.1886,
+      "step": 400
+    },
+    {
+      "epoch": 1.5225439012814428,
+      "grad_norm": 0.3786951005458832,
+      "learning_rate": 7.350176020987585e-07,
+      "loss": 1.1841,
+      "step": 401
+    },
+    {
+      "epoch": 1.5263407688656858,
+      "grad_norm": 0.3833267390727997,
+      "learning_rate": 7.239056851098785e-07,
+      "loss": 1.191,
+      "step": 402
+    },
+    {
+      "epoch": 1.5301376364499288,
+      "grad_norm": 0.2992788553237915,
+      "learning_rate": 7.128641665947658e-07,
+      "loss": 0.7744,
+      "step": 403
+    },
+    {
+      "epoch": 1.5339345040341716,
+      "grad_norm": 0.379607230424881,
+      "learning_rate": 7.018934842025058e-07,
+      "loss": 1.1837,
+      "step": 404
+    },
+    {
+      "epoch": 1.5377313716184147,
+      "grad_norm": 0.3761638104915619,
+      "learning_rate": 6.90994072774473e-07,
+      "loss": 1.0384,
+      "step": 405
+    },
+    {
+      "epoch": 1.5415282392026577,
+      "grad_norm": 0.405567467212677,
+      "learning_rate": 6.801663643271012e-07,
+      "loss": 1.1853,
+      "step": 406
+    },
+    {
+      "epoch": 1.5453251067869007,
+      "grad_norm": 0.3884119987487793,
+      "learning_rate": 6.69410788034755e-07,
+      "loss": 1.1932,
+      "step": 407
+    },
+    {
+      "epoch": 1.5491219743711437,
+      "grad_norm": 0.35525161027908325,
+      "learning_rate": 6.587277702127196e-07,
+      "loss": 1.0483,
+      "step": 408
+    },
+    {
+      "epoch": 1.5529188419553868,
+      "grad_norm": 0.3150971829891205,
+      "learning_rate": 6.481177343003043e-07,
+      "loss": 0.9127,
+      "step": 409
+    },
+    {
+      "epoch": 1.5567157095396298,
+      "grad_norm": 0.39407217502593994,
+      "learning_rate": 6.375811008440591e-07,
+      "loss": 1.179,
+      "step": 410
+    },
+    {
+      "epoch": 1.5605125771238728,
+      "grad_norm": 0.402775377035141,
+      "learning_rate": 6.271182874811024e-07,
+      "loss": 1.0475,
+      "step": 411
+    },
+    {
+      "epoch": 1.5643094447081158,
+      "grad_norm": 0.3489883840084076,
+      "learning_rate": 6.167297089225713e-07,
+      "loss": 0.9048,
+      "step": 412
+    },
+    {
+      "epoch": 1.5681063122923589,
+      "grad_norm": 0.35091614723205566,
+      "learning_rate": 6.064157769371823e-07,
+      "loss": 1.0413,
+      "step": 413
+    },
+    {
+      "epoch": 1.5719031798766019,
+      "grad_norm": 0.35318344831466675,
+      "learning_rate": 5.961769003349077e-07,
+      "loss": 1.0326,
+      "step": 414
+    },
+    {
+      "epoch": 1.575700047460845,
+      "grad_norm": 0.3418586850166321,
+      "learning_rate": 5.860134849507765e-07,
+      "loss": 0.9169,
+      "step": 415
+    },
+    {
+      "epoch": 1.579496915045088,
+      "grad_norm": 0.35626721382141113,
+      "learning_rate": 5.759259336287851e-07,
+      "loss": 1.0404,
+      "step": 416
+    },
+    {
+      "epoch": 1.583293782629331,
+      "grad_norm": 0.3962875306606293,
+      "learning_rate": 5.659146462059292e-07,
+      "loss": 1.1874,
+      "step": 417
+    },
+    {
+      "epoch": 1.5870906502135738,
+      "grad_norm": 0.3754862844944,
+      "learning_rate": 5.559800194963591e-07,
+      "loss": 1.1858,
+      "step": 418
+    },
+    {
+      "epoch": 1.5908875177978168,
+      "grad_norm": 0.37421101331710815,
+      "learning_rate": 5.46122447275649e-07,
+      "loss": 1.1813,
+      "step": 419
+    },
+    {
+      "epoch": 1.5946843853820598,
+      "grad_norm": 0.3670285642147064,
+      "learning_rate": 5.363423202651876e-07,
+      "loss": 1.0544,
+      "step": 420
+    },
+    {
+      "epoch": 1.5984812529663028,
+      "grad_norm": 0.42034921050071716,
+      "learning_rate": 5.266400261166951e-07,
+      "loss": 1.1884,
+      "step": 421
+    },
+    {
+      "epoch": 1.6022781205505456,
+      "grad_norm": 0.3546159565448761,
+      "learning_rate": 5.170159493968549e-07,
+      "loss": 1.1814,
+      "step": 422
+    },
+    {
+      "epoch": 1.6060749881347887,
+      "grad_norm": 0.3211246728897095,
+      "learning_rate": 5.074704715720711e-07,
+      "loss": 0.9178,
+      "step": 423
+    },
+    {
+      "epoch": 1.6098718557190317,
+      "grad_norm": 0.3514634370803833,
+      "learning_rate": 4.980039709933492e-07,
+      "loss": 0.913,
+      "step": 424
+    },
+    {
+      "epoch": 1.6136687233032747,
+      "grad_norm": 0.4017420709133148,
+      "learning_rate": 4.886168228813007e-07,
+      "loss": 1.1828,
+      "step": 425
+    },
+    {
+      "epoch": 1.6174655908875177,
+      "grad_norm": 0.3313949406147003,
+      "learning_rate": 4.793093993112663e-07,
+      "loss": 0.9082,
+      "step": 426
+    },
+    {
+      "epoch": 1.6212624584717608,
+      "grad_norm": 0.33639460802078247,
+      "learning_rate": 4.700820691985739e-07,
+      "loss": 0.9069,
+      "step": 427
+    },
+    {
+      "epoch": 1.6250593260560038,
+      "grad_norm": 0.3237963616847992,
+      "learning_rate": 4.6093519828391025e-07,
+      "loss": 0.894,
+      "step": 428
+    },
+    {
+      "epoch": 1.6288561936402468,
+      "grad_norm": 0.3815336525440216,
+      "learning_rate": 4.51869149118829e-07,
+      "loss": 1.1764,
+      "step": 429
+    },
+    {
+      "epoch": 1.6326530612244898,
+      "grad_norm": 0.36702704429626465,
+      "learning_rate": 4.428842810513784e-07,
+      "loss": 1.1678,
+      "step": 430
+    },
+    {
+      "epoch": 1.6364499288087329,
+      "grad_norm": 0.3530699610710144,
+      "learning_rate": 4.3398095021185557e-07,
+      "loss": 1.1782,
+      "step": 431
+    },
+    {
+      "epoch": 1.6402467963929759,
+      "grad_norm": 0.33500173687934875,
+      "learning_rate": 4.251595094986957e-07,
+      "loss": 1.0625,
+      "step": 432
+    },
+    {
+      "epoch": 1.644043663977219,
+      "grad_norm": 0.37163975834846497,
+      "learning_rate": 4.1642030856448104e-07,
+      "loss": 1.1739,
+      "step": 433
+    },
+    {
+      "epoch": 1.647840531561462,
+      "grad_norm": 0.37387996912002563,
+      "learning_rate": 4.077636938020807e-07,
+      "loss": 1.0592,
+      "step": 434
+    },
+    {
+      "epoch": 1.651637399145705,
+      "grad_norm": 0.3629416823387146,
+      "learning_rate": 3.991900083309241e-07,
+      "loss": 1.1718,
+      "step": 435
+    },
+    {
+      "epoch": 1.6554342667299478,
+      "grad_norm": 0.3603303134441376,
+      "learning_rate": 3.906995919833997e-07,
+      "loss": 1.0432,
+      "step": 436
+    },
+    {
+      "epoch": 1.6592311343141908,
+      "grad_norm": 0.31616950035095215,
+      "learning_rate": 3.8229278129138293e-07,
+      "loss": 0.9182,
+      "step": 437
+    },
+    {
+      "epoch": 1.6630280018984338,
+      "grad_norm": 0.3574075698852539,
+      "learning_rate": 3.739699094729002e-07,
+      "loss": 1.0423,
+      "step": 438
+    },
+    {
+      "epoch": 1.6668248694826768,
+      "grad_norm": 0.33015620708465576,
+      "learning_rate": 3.6573130641892053e-07,
+      "loss": 0.8927,
+      "step": 439
+    },
+    {
+      "epoch": 1.6706217370669196,
+      "grad_norm": 0.32390230894088745,
+      "learning_rate": 3.575772986802775e-07,
+      "loss": 0.9272,
+      "step": 440
+    },
+    {
+      "epoch": 1.6744186046511627,
+      "grad_norm": 0.37338370084762573,
+      "learning_rate": 3.4950820945472945e-07,
+      "loss": 1.1717,
+      "step": 441
+    },
+    {
+      "epoch": 1.6782154722354057,
+      "grad_norm": 0.35633939504623413,
+      "learning_rate": 3.4152435857414676e-07,
+      "loss": 1.1792,
+      "step": 442
+    },
+    {
+      "epoch": 1.6820123398196487,
+      "grad_norm": 0.35473427176475525,
+      "learning_rate": 3.3362606249183446e-07,
+      "loss": 1.0391,
+      "step": 443
+    },
+    {
+      "epoch": 1.6858092074038917,
+      "grad_norm": 0.36706259846687317,
+      "learning_rate": 3.2581363426998966e-07,
+      "loss": 1.0463,
+      "step": 444
+    },
+    {
+      "epoch": 1.6896060749881348,
+      "grad_norm": 0.3562609553337097,
+      "learning_rate": 3.18087383567294e-07,
+      "loss": 1.0515,
+      "step": 445
+    },
+    {
+      "epoch": 1.6934029425723778,
+      "grad_norm": 0.35783901810646057,
+      "learning_rate": 3.1044761662663933e-07,
+      "loss": 1.0449,
+      "step": 446
+    },
+    {
+      "epoch": 1.6971998101566208,
+      "grad_norm": 0.3588060736656189,
+      "learning_rate": 3.0289463626298585e-07,
+      "loss": 1.1823,
+      "step": 447
+    },
+    {
+      "epoch": 1.7009966777408638,
+      "grad_norm": 0.35698550939559937,
+      "learning_rate": 2.9542874185136545e-07,
+      "loss": 1.1792,
+      "step": 448
+    },
+    {
+      "epoch": 1.7047935453251069,
+      "grad_norm": 0.37660661339759827,
+      "learning_rate": 2.880502293150117e-07,
+      "loss": 1.1868,
+      "step": 449
+    },
+    {
+      "epoch": 1.7085904129093499,
+      "grad_norm": 0.38808876276016235,
+      "learning_rate": 2.8075939111362915e-07,
+      "loss": 1.1823,
+      "step": 450
+    },
+    {
+      "epoch": 1.712387280493593,
+      "grad_norm": 0.35739246010780334,
+      "learning_rate": 2.7355651623180574e-07,
+      "loss": 1.1793,
+      "step": 451
+    },
+    {
+      "epoch": 1.716184148077836,
+      "grad_norm": 0.3609924018383026,
+      "learning_rate": 2.6644189016755415e-07,
+      "loss": 1.0662,
+      "step": 452
+    },
+    {
+      "epoch": 1.719981015662079,
+      "grad_norm": 0.3684343099594116,
+      "learning_rate": 2.5941579492099853e-07,
+      "loss": 1.1712,
+      "step": 453
+    },
+    {
+      "epoch": 1.7237778832463218,
+      "grad_norm": 0.3490484952926636,
+      "learning_rate": 2.524785089831955e-07,
+      "loss": 1.0555,
+      "step": 454
+    },
+    {
+      "epoch": 1.7275747508305648,
+      "grad_norm": 0.32522618770599365,
+      "learning_rate": 2.456303073250943e-07,
+      "loss": 0.9226,
+      "step": 455
+    },
+    {
+      "epoch": 1.7313716184148078,
+      "grad_norm": 0.38961344957351685,
+      "learning_rate": 2.388714613866422e-07,
+      "loss": 1.1842,
+      "step": 456
+    },
+    {
+      "epoch": 1.7351684859990508,
+      "grad_norm": 0.35974937677383423,
+      "learning_rate": 2.3220223906602113e-07,
+      "loss": 1.0626,
+      "step": 457
+    },
+    {
+      "epoch": 1.7389653535832936,
+      "grad_norm": 0.3246191143989563,
+      "learning_rate": 2.2562290470903082e-07,
+      "loss": 0.9113,
+      "step": 458
+    },
+    {
+      "epoch": 1.7427622211675367,
+      "grad_norm": 0.3299662172794342,
+      "learning_rate": 2.191337190986112e-07,
+      "loss": 0.9153,
+      "step": 459
+    },
+    {
+      "epoch": 1.7465590887517797,
+      "grad_norm": 0.38010498881340027,
+      "learning_rate": 2.1273493944450634e-07,
+      "loss": 1.1955,
+      "step": 460
+    },
+    {
+      "epoch": 1.7503559563360227,
+      "grad_norm": 0.38703298568725586,
+      "learning_rate": 2.06426819373067e-07,
+      "loss": 1.1757,
+      "step": 461
+    },
+    {
+      "epoch": 1.7541528239202657,
+      "grad_norm": 0.294664204120636,
+      "learning_rate": 2.0020960891720147e-07,
+      "loss": 0.7584,
+      "step": 462
+    },
+    {
+      "epoch": 1.7579496915045087,
+      "grad_norm": 0.3676691949367523,
+      "learning_rate": 1.9408355450646234e-07,
+      "loss": 1.1826,
+      "step": 463
+    },
+    {
+      "epoch": 1.7617465590887518,
+      "grad_norm": 0.36037302017211914,
+      "learning_rate": 1.8804889895727872e-07,
+      "loss": 1.046,
+      "step": 464
+    },
+    {
+      "epoch": 1.7655434266729948,
+      "grad_norm": 0.3599529266357422,
+      "learning_rate": 1.821058814633339e-07,
+      "loss": 1.0328,
+      "step": 465
+    },
+    {
+      "epoch": 1.7693402942572378,
+      "grad_norm": 0.32030507922172546,
+      "learning_rate": 1.762547375860832e-07,
+      "loss": 0.9193,
+      "step": 466
+    },
+    {
+      "epoch": 1.7731371618414808,
+      "grad_norm": 0.4202202558517456,
+      "learning_rate": 1.7049569924541653e-07,
+      "loss": 1.1895,
+      "step": 467
+    },
+    {
+      "epoch": 1.7769340294257239,
+      "grad_norm": 0.35407963395118713,
+      "learning_rate": 1.6482899471046726e-07,
+      "loss": 1.0546,
+      "step": 468
+    },
+    {
+      "epoch": 1.780730897009967,
+      "grad_norm": 0.3341258466243744,
+      "learning_rate": 1.5925484859056372e-07,
+      "loss": 1.0506,
+      "step": 469
+    },
+    {
+      "epoch": 1.78452776459421,
+      "grad_norm": 0.3770039677619934,
+      "learning_rate": 1.5377348182632536e-07,
+      "loss": 1.1839,
+      "step": 470
+    },
+    {
+      "epoch": 1.7883246321784527,
+      "grad_norm": 0.3668918311595917,
+      "learning_rate": 1.4838511168090707e-07,
+      "loss": 1.1741,
+      "step": 471
+    },
+    {
+      "epoch": 1.7921214997626957,
+      "grad_norm": 0.3690701425075531,
+      "learning_rate": 1.4308995173138828e-07,
+      "loss": 1.1862,
+      "step": 472
+    },
+    {
+      "epoch": 1.7959183673469388,
+      "grad_norm": 0.33050721883773804,
+      "learning_rate": 1.3788821186030338e-07,
+      "loss": 1.0628,
+      "step": 473
+    },
+    {
+      "epoch": 1.7997152349311818,
+      "grad_norm": 0.35489219427108765,
+      "learning_rate": 1.3278009824732763e-07,
+      "loss": 1.0405,
+      "step": 474
+    },
+    {
+      "epoch": 1.8035121025154248,
+      "grad_norm": 0.3431392014026642,
+      "learning_rate": 1.2776581336110234e-07,
+      "loss": 1.0425,
+      "step": 475
+    },
+    {
+      "epoch": 1.8073089700996676,
+      "grad_norm": 0.35951146483421326,
+      "learning_rate": 1.2284555595120901e-07,
+      "loss": 1.192,
+      "step": 476
+    },
+    {
+      "epoch": 1.8111058376839106,
+      "grad_norm": 0.34095799922943115,
+      "learning_rate": 1.1801952104029347e-07,
+      "loss": 0.9311,
+      "step": 477
+    },
+    {
+      "epoch": 1.8149027052681537,
+      "grad_norm": 0.36434096097946167,
+      "learning_rate": 1.1328789991633532e-07,
+      "loss": 1.1809,
+      "step": 478
+    },
+    {
+      "epoch": 1.8186995728523967,
+      "grad_norm": 0.35194143652915955,
+      "learning_rate": 1.0865088012506408e-07,
+      "loss": 1.0538,
+      "step": 479
+    },
+    {
+      "epoch": 1.8224964404366397,
+      "grad_norm": 0.3786377012729645,
+      "learning_rate": 1.0410864546252841e-07,
+      "loss": 1.1839,
+      "step": 480
+    },
+    {
+      "epoch": 1.8262933080208827,
+      "grad_norm": 0.3330764174461365,
+      "learning_rate": 9.966137596780945e-08,
+      "loss": 1.0354,
+      "step": 481
+    },
+    {
+      "epoch": 1.8300901756051258,
+      "grad_norm": 0.33103281259536743,
+      "learning_rate": 9.530924791588319e-08,
+      "loss": 0.956,
+      "step": 482
+    },
+    {
+      "epoch": 1.8338870431893688,
+      "grad_norm": 0.34974756836891174,
+      "learning_rate": 9.10524338106375e-08,
+      "loss": 1.1761,
+      "step": 483
+    },
+    {
+      "epoch": 1.8376839107736118,
+      "grad_norm": 0.3340107202529907,
+      "learning_rate": 8.689110237803056e-08,
+      "loss": 1.0462,
+      "step": 484
+    },
+    {
+      "epoch": 1.8414807783578548,
+      "grad_norm": 0.337950199842453,
+      "learning_rate": 8.282541855940546e-08,
+      "loss": 1.0587,
+      "step": 485
+    },
+    {
+      "epoch": 1.8452776459420979,
+      "grad_norm": 0.34110939502716064,
+      "learning_rate": 7.885554350495206e-08,
+      "loss": 1.1823,
+      "step": 486
+    },
+    {
+      "epoch": 1.849074513526341,
+      "grad_norm": 0.3682970702648163,
+      "learning_rate": 7.498163456731878e-08,
+      "loss": 1.1863,
+      "step": 487
+    },
+    {
+      "epoch": 1.852871381110584,
+      "grad_norm": 0.3614114820957184,
+      "learning_rate": 7.120384529537672e-08,
+      "loss": 1.1923,
+      "step": 488
+    },
+    {
+      "epoch": 1.8566682486948267,
+      "grad_norm": 1.5183669328689575,
+      "learning_rate": 6.752232542813319e-08,
+      "loss": 0.5159,
+      "step": 489
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 1.4683269262313843,
+      "learning_rate": 6.393722088879534e-08,
+      "loss": 0.504,
+      "step": 490
+    },
+    {
+      "epoch": 1.8642619838633128,
+      "grad_norm": 1.4609661102294922,
+      "learning_rate": 6.044867377898806e-08,
+      "loss": 0.5112,
+      "step": 491
+    },
+    {
+      "epoch": 1.8680588514475558,
+      "grad_norm": 1.6301960945129395,
+      "learning_rate": 5.7056822373121324e-08,
+      "loss": 0.5463,
+      "step": 492
+    },
+    {
+      "epoch": 1.8718557190317988,
+      "grad_norm": 1.419601321220398,
+      "learning_rate": 5.3761801112907356e-08,
+      "loss": 0.4816,
+      "step": 493
+    },
+    {
+      "epoch": 1.8756525866160416,
+      "grad_norm": 1.1993861198425293,
+      "learning_rate": 5.0563740602034284e-08,
+      "loss": 0.418,
+      "step": 494
+    },
+    {
+      "epoch": 1.8794494542002846,
+      "grad_norm": 1.2279670238494873,
+      "learning_rate": 4.746276760098867e-08,
+      "loss": 0.4118,
+      "step": 495
+    },
+    {
+      "epoch": 1.8832463217845277,
+      "grad_norm": 0.9904822111129761,
+      "learning_rate": 4.44590050220306e-08,
+      "loss": 0.3383,
+      "step": 496
+    },
+    {
+      "epoch": 1.8870431893687707,
+      "grad_norm": 1.4921010732650757,
+      "learning_rate": 4.155257192432205e-08,
+      "loss": 0.5024,
+      "step": 497
+    },
+    {
+      "epoch": 1.8908400569530137,
+      "grad_norm": 1.2175933122634888,
+      "learning_rate": 3.874358350920843e-08,
+      "loss": 0.4521,
+      "step": 498
+    },
+    {
+      "epoch": 1.8946369245372567,
+      "grad_norm": 0.9808973670005798,
+      "learning_rate": 3.603215111565139e-08,
+      "loss": 0.3847,
+      "step": 499
+    },
+    {
+      "epoch": 1.8984337921214998,
+      "grad_norm": 1.0177325010299683,
+      "learning_rate": 3.341838221581656e-08,
+      "loss": 0.433,
+      "step": 500
+    },
+    {
+      "epoch": 1.9022306597057428,
+      "grad_norm": 1.1320708990097046,
+      "learning_rate": 3.090238041081328e-08,
+      "loss": 0.4865,
+      "step": 501
+    },
+    {
+      "epoch": 1.9060275272899858,
+      "grad_norm": 0.8693588972091675,
+      "learning_rate": 2.848424542658823e-08,
+      "loss": 0.3843,
+      "step": 502
+    },
+    {
+      "epoch": 1.9098243948742288,
+      "grad_norm": 1.0695801973342896,
+      "learning_rate": 2.6164073109972986e-08,
+      "loss": 0.4924,
+      "step": 503
+    },
+    {
+      "epoch": 1.9136212624584719,
+      "grad_norm": 1.0257716178894043,
+      "learning_rate": 2.3941955424884312e-08,
+      "loss": 0.4785,
+      "step": 504
+    },
+    {
+      "epoch": 1.9174181300427149,
+      "grad_norm": 0.8927969932556152,
+      "learning_rate": 2.1817980448679553e-08,
+      "loss": 0.4477,
+      "step": 505
+    },
+    {
+      "epoch": 1.921214997626958,
+      "grad_norm": 0.960476815700531,
+      "learning_rate": 1.979223236866501e-08,
+      "loss": 0.484,
+      "step": 506
+    },
+    {
+      "epoch": 1.9250118652112007,
+      "grad_norm": 0.8209058046340942,
+      "learning_rate": 1.7864791478760245e-08,
+      "loss": 0.4217,
+      "step": 507
+    },
+    {
+      "epoch": 1.9288087327954437,
+      "grad_norm": 0.815679669380188,
+      "learning_rate": 1.603573417631371e-08,
+      "loss": 0.4293,
+      "step": 508
+    },
+    {
+      "epoch": 1.9326056003796868,
+      "grad_norm": 0.9071650505065918,
+      "learning_rate": 1.4305132959075706e-08,
+      "loss": 0.4821,
+      "step": 509
+    },
+    {
+      "epoch": 1.9364024679639298,
+      "grad_norm": 0.9293763637542725,
+      "learning_rate": 1.2673056422325413e-08,
+      "loss": 0.4737,
+      "step": 510
+    },
+    {
+      "epoch": 1.9401993355481728,
+      "grad_norm": 0.8001239895820618,
+      "learning_rate": 1.1139569256150285e-08,
+      "loss": 0.4284,
+      "step": 511
+    },
+    {
+      "epoch": 1.9439962031324156,
+      "grad_norm": 0.7981712222099304,
+      "learning_rate": 9.704732242883374e-09,
+      "loss": 0.4344,
+      "step": 512
+    },
+    {
+      "epoch": 1.9477930707166586,
+      "grad_norm": 0.5713729858398438,
+      "learning_rate": 8.368602254693603e-09,
+      "loss": 0.3397,
+      "step": 513
+    },
+    {
+      "epoch": 1.9515899383009017,
+      "grad_norm": 0.7548425197601318,
+      "learning_rate": 7.131232251331721e-09,
+      "loss": 0.4207,
+      "step": 514
+    },
+    {
+      "epoch": 1.9553868058851447,
+      "grad_norm": 0.6806543469429016,
+      "learning_rate": 5.992671278030327e-09,
+      "loss": 0.4099,
+      "step": 515
+    },
+    {
+      "epoch": 1.9591836734693877,
+      "grad_norm": 0.836120069026947,
+      "learning_rate": 4.952964463561805e-09,
+      "loss": 0.4671,
+      "step": 516
+    },
+    {
+      "epoch": 1.9629805410536307,
+      "grad_norm": 0.662464439868927,
+      "learning_rate": 4.012153018446984e-09,
+      "loss": 0.3776,
+      "step": 517
+    },
+    {
+      "epoch": 1.9667774086378738,
+      "grad_norm": 0.7680605053901672,
+      "learning_rate": 3.170274233324222e-09,
+      "loss": 0.4336,
+      "step": 518
+    },
+    {
+      "epoch": 1.9705742762221168,
+      "grad_norm": 0.7456918954849243,
+      "learning_rate": 2.4273614774691923e-09,
+      "loss": 0.4209,
+      "step": 519
+    },
+    {
+      "epoch": 1.9743711438063598,
+      "grad_norm": 0.7245385050773621,
+      "learning_rate": 1.7834441974740047e-09,
+      "loss": 0.4,
+      "step": 520
+    },
+    {
+      "epoch": 1.9781680113906028,
+      "grad_norm": 0.6544315814971924,
+      "learning_rate": 1.2385479160784141e-09,
+      "loss": 0.3741,
+      "step": 521
+    },
+    {
+      "epoch": 1.9819648789748459,
+      "grad_norm": 0.721889317035675,
+      "learning_rate": 7.926942311597962e-10,
+      "loss": 0.4156,
+      "step": 522
+    },
+    {
+      "epoch": 1.9857617465590889,
+      "grad_norm": 0.8772999048233032,
+      "learning_rate": 4.4590081487577706e-10,
+      "loss": 0.4664,
+      "step": 523
+    },
+    {
+      "epoch": 1.989558614143332,
+      "grad_norm": 0.8888481855392456,
+      "learning_rate": 1.9818141296451544e-10,
+      "loss": 0.4626,
+      "step": 524
+    },
+    {
+      "epoch": 1.9933554817275747,
+      "grad_norm": 0.7575893998146057,
+      "learning_rate": 4.954584419930575e-11,
+      "loss": 0.4245,
+      "step": 525
+    },
+    {
+      "epoch": 1.9971523493118177,
+      "grad_norm": 0.878999650478363,
+      "learning_rate": 0.0,
+      "loss": 0.4739,
+      "step": 526
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 526,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6538932878717747e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-526/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66c2f09cdfe4b739ffb9f91aaae33dcd93a75b26b1c8fda5ddbe3a91ce174d5
+size 5816