Upload folder using huggingface_hub

checkpoint-488/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-488/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-488/model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b86b9c5e6bfbfea6601b9c1448fbb2dcb0299dfed249ae1030c9f1eaba87c63
+size 4498420872

checkpoint-488/model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2a522e81e41f8d9db80270790810ceb15de0fcd1fe6c78663db4defc065cc5
+size 4718804768

checkpoint-488/model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50eaa2f19ac0cd91c5fc063cbd02edcfc74c6e1973462c7a2a32c91b26d30ac2
+size 4467075880

checkpoint-488/model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63eeb57f86061462a2a544afd74d8b6dc531f3ab33bd0680442e2c31a004126b
+size 4467075880

checkpoint-488/model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e38a86299c7416aca59ace38b02e531a019e7f4c19cb0e75e343ca7e0945eaf8
+size 4718804760

checkpoint-488/model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aef6c44bfca92f857ed578d96ede7ba3e10f6f298632acaf4f1a5ab1e4facf2
+size 4467075904

checkpoint-488/model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8d360481af0483210e591db639cae8cbfb62937439d9366f3eaf4c66f968538
+size 4467075904

checkpoint-488/model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b95a2c58683b36472d5de15d39b351e92e223c02e5016b16ec8494078f7eb1ad
+size 4718804800

checkpoint-488/model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f6b9d6ba3d5382429177dbbe05ef3334b8a40cefc22746417653414abc7763
+size 4467075904

checkpoint-488/model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c9e23bed8cacccc6c9aa1d3f8d6dd02c33a875530e70f86720d73cbc4225ba
+size 4467075904

checkpoint-488/model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8837170c5ce37bf94bfa502b7498c923f972e274c487a3b6254af3930c7c4b
+size 4718804800

checkpoint-488/model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3baaee3ac0a52568594e319b0e8eb89c75892949ec23b9d2bd888c0789a77ae1
+size 4467075904

checkpoint-488/model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:724d6436bd211a27aa288ebc959d0367012c1a947eaf874bf2d1ff31b31bf1c5
+size 4467075904

checkpoint-488/model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb974ff472913e52b156b6685a602f0ec6a249f69b5e35b61ce7796293826d7
+size 4718804800

checkpoint-488/model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3872634422f66579ddc5b9fcef9f0f283bc343cc34bd8455a84ce36944120e01
+size 4467075904

checkpoint-488/model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a436a927a86663b44ab8c5200c52ab45dbd8a06157ef1e73a8d1166b773c9fac
+size 4467075904

checkpoint-488/model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd7404567bdc5fe1997103a4aad1a241acfa5649299911e3f5ed79483ee5d5e
+size 4718804800

checkpoint-488/model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52b290ba916a7943a2a49f8beec1e420b28bf2926006a57ba9b49526bd63929
+size 4467075904

checkpoint-488/model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f797c71ac79728d5994816bf6ba7d8b59207a545ceb1c1cb354c672cc870aa6
+size 4467075904

checkpoint-488/model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6ad226a964de522c1fe4cef1c2345d82061c089ceb8dce413dd5e0effec709
+size 4718804800

checkpoint-488/model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b787e2453c50931037369e3bfe317360f0b1abcdec92de927df3c005a0b2f61f
+size 4467075904

checkpoint-488/model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1487ba9f845f71c172598d35cda72ba9a96e09613862dc954c37c04f4ccd4353
+size 4467075904

checkpoint-488/model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3458ff3c55fde8c8ae1aa3e5492807f436cc54348fcd604734e26c4687a425e0
+size 4718804800

checkpoint-488/model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89bbfb5e3b2fa523779ec00e47c96e66dfac3e1f49fb0b4c2f4884b22a9e773
+size 4467075904

checkpoint-488/model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e40a4268329b79e4142d94fbd907699295d3f49f7a4d40ac17e519de0980b6
+size 4467075904

checkpoint-488/model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75d4b668be5cdd900bda666c3fd1584cdebb1e8d04446c53de75fa281a5ee48
+size 4718804800

checkpoint-488/model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34c2d2260acea28f01d1b4e1447c1382c977a6347b31621e907ea2c077f6e258
+size 4467075904

checkpoint-488/model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:878fb6409a80a0ec9d7c695441288b6987594989bcbc2d22eefbbfa29640736e
+size 4467075904

checkpoint-488/model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35f5ba8fd4f9dcd0df69a5ce6e81fdaf26954015d3eb2e302410ba242bdd755
+size 3680563768

checkpoint-488/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-488/trainer_state.json

@@ -0,0 +1,3449 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 488,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004098360655737705,
+      "grad_norm": 4511.04541015625,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 2.2104,
+      "step": 1
+    },
+    {
+      "epoch": 0.00819672131147541,
+      "grad_norm": 402.808837890625,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 2.1402,
+      "step": 2
+    },
+    {
+      "epoch": 0.012295081967213115,
+      "grad_norm": 3.9330132007598877,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 1.8287,
+      "step": 3
+    },
+    {
+      "epoch": 0.01639344262295082,
+      "grad_norm": 84.87239074707031,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.1217,
+      "step": 4
+    },
+    {
+      "epoch": 0.020491803278688523,
+      "grad_norm": 169.44476318359375,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 2.4968,
+      "step": 5
+    },
+    {
+      "epoch": 0.02459016393442623,
+      "grad_norm": 99.3742904663086,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 2.0496,
+      "step": 6
+    },
+    {
+      "epoch": 0.028688524590163935,
+      "grad_norm": 3.963096857070923,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 1.8236,
+      "step": 7
+    },
+    {
+      "epoch": 0.03278688524590164,
+      "grad_norm": 299.411865234375,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 2.2638,
+      "step": 8
+    },
+    {
+      "epoch": 0.036885245901639344,
+      "grad_norm": 37.45259475708008,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 1.8317,
+      "step": 9
+    },
+    {
+      "epoch": 0.040983606557377046,
+      "grad_norm": 999.2122192382812,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.9443,
+      "step": 10
+    },
+    {
+      "epoch": 0.045081967213114756,
+      "grad_norm": 35.29961395263672,
+      "learning_rate": 2.2e-06,
+      "loss": 1.7157,
+      "step": 11
+    },
+    {
+      "epoch": 0.04918032786885246,
+      "grad_norm": 3.365468978881836,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.7892,
+      "step": 12
+    },
+    {
+      "epoch": 0.05327868852459016,
+      "grad_norm": 446.4648742675781,
+      "learning_rate": 2.6e-06,
+      "loss": 1.6874,
+      "step": 13
+    },
+    {
+      "epoch": 0.05737704918032787,
+      "grad_norm": 376.9467468261719,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.7135,
+      "step": 14
+    },
+    {
+      "epoch": 0.06147540983606557,
+      "grad_norm": 2.599492073059082,
+      "learning_rate": 3e-06,
+      "loss": 1.7379,
+      "step": 15
+    },
+    {
+      "epoch": 0.06557377049180328,
+      "grad_norm": 2.955031394958496,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 1.7276,
+      "step": 16
+    },
+    {
+      "epoch": 0.06967213114754098,
+      "grad_norm": 394.27630615234375,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 1.5587,
+      "step": 17
+    },
+    {
+      "epoch": 0.07377049180327869,
+      "grad_norm": 2.41615629196167,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 1.6808,
+      "step": 18
+    },
+    {
+      "epoch": 0.0778688524590164,
+      "grad_norm": 431.9937744140625,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 1.3805,
+      "step": 19
+    },
+    {
+      "epoch": 0.08196721311475409,
+      "grad_norm": 1.6226919889450073,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.6572,
+      "step": 20
+    },
+    {
+      "epoch": 0.0860655737704918,
+      "grad_norm": 13.787015914916992,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 1.4747,
+      "step": 21
+    },
+    {
+      "epoch": 0.09016393442622951,
+      "grad_norm": 8.452902793884277,
+      "learning_rate": 4.4e-06,
+      "loss": 1.2664,
+      "step": 22
+    },
+    {
+      "epoch": 0.0942622950819672,
+      "grad_norm": 1.2060812711715698,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 1.5725,
+      "step": 23
+    },
+    {
+      "epoch": 0.09836065573770492,
+      "grad_norm": 1.17067551612854,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.397,
+      "step": 24
+    },
+    {
+      "epoch": 0.10245901639344263,
+      "grad_norm": 1.1773242950439453,
+      "learning_rate": 5e-06,
+      "loss": 1.5365,
+      "step": 25
+    },
+    {
+      "epoch": 0.10655737704918032,
+      "grad_norm": 0.8914172649383545,
+      "learning_rate": 4.999942449896355e-06,
+      "loss": 1.171,
+      "step": 26
+    },
+    {
+      "epoch": 0.11065573770491803,
+      "grad_norm": 0.8337782025337219,
+      "learning_rate": 4.999769802235034e-06,
+      "loss": 1.3317,
+      "step": 27
+    },
+    {
+      "epoch": 0.11475409836065574,
+      "grad_norm": 0.8020254969596863,
+      "learning_rate": 4.999482064964746e-06,
+      "loss": 1.3156,
+      "step": 28
+    },
+    {
+      "epoch": 0.11885245901639344,
+      "grad_norm": 0.9282699227333069,
+      "learning_rate": 4.999079251332942e-06,
+      "loss": 1.4523,
+      "step": 29
+    },
+    {
+      "epoch": 0.12295081967213115,
+      "grad_norm": 0.8156635165214539,
+      "learning_rate": 4.998561379885193e-06,
+      "loss": 1.2679,
+      "step": 30
+    },
+    {
+      "epoch": 0.12704918032786885,
+      "grad_norm": 0.7708067297935486,
+      "learning_rate": 4.997928474464344e-06,
+      "loss": 1.2635,
+      "step": 31
+    },
+    {
+      "epoch": 0.13114754098360656,
+      "grad_norm": 0.8476499319076538,
+      "learning_rate": 4.997180564209414e-06,
+      "loss": 1.4239,
+      "step": 32
+    },
+    {
+      "epoch": 0.13524590163934427,
+      "grad_norm": 0.7153339982032776,
+      "learning_rate": 4.996317683554252e-06,
+      "loss": 1.2342,
+      "step": 33
+    },
+    {
+      "epoch": 0.13934426229508196,
+      "grad_norm": 0.7786403298377991,
+      "learning_rate": 4.9953398722259546e-06,
+      "loss": 1.3844,
+      "step": 34
+    },
+    {
+      "epoch": 0.14344262295081966,
+      "grad_norm": 0.8425343036651611,
+      "learning_rate": 4.994247175243038e-06,
+      "loss": 1.3856,
+      "step": 35
+    },
+    {
+      "epoch": 0.14754098360655737,
+      "grad_norm": 0.6516931653022766,
+      "learning_rate": 4.993039642913361e-06,
+      "loss": 1.0632,
+      "step": 36
+    },
+    {
+      "epoch": 0.15163934426229508,
+      "grad_norm": 0.5697762370109558,
+      "learning_rate": 4.991717330831813e-06,
+      "loss": 1.0365,
+      "step": 37
+    },
+    {
+      "epoch": 0.1557377049180328,
+      "grad_norm": 0.5697985887527466,
+      "learning_rate": 4.990280299877749e-06,
+      "loss": 1.0494,
+      "step": 38
+    },
+    {
+      "epoch": 0.1598360655737705,
+      "grad_norm": 0.6210886836051941,
+      "learning_rate": 4.988728616212197e-06,
+      "loss": 1.1787,
+      "step": 39
+    },
+    {
+      "epoch": 0.16393442622950818,
+      "grad_norm": 0.5863775610923767,
+      "learning_rate": 4.9870623512748e-06,
+      "loss": 1.1843,
+      "step": 40
+    },
+    {
+      "epoch": 0.1680327868852459,
+      "grad_norm": 0.629668116569519,
+      "learning_rate": 4.985281581780532e-06,
+      "loss": 1.3212,
+      "step": 41
+    },
+    {
+      "epoch": 0.1721311475409836,
+      "grad_norm": 0.5078697204589844,
+      "learning_rate": 4.9833863897161715e-06,
+      "loss": 0.8928,
+      "step": 42
+    },
+    {
+      "epoch": 0.1762295081967213,
+      "grad_norm": 0.5744357705116272,
+      "learning_rate": 4.9813768623365164e-06,
+      "loss": 1.1856,
+      "step": 43
+    },
+    {
+      "epoch": 0.18032786885245902,
+      "grad_norm": 0.5206721425056458,
+      "learning_rate": 4.979253092160374e-06,
+      "loss": 1.1739,
+      "step": 44
+    },
+    {
+      "epoch": 0.18442622950819673,
+      "grad_norm": 0.46724414825439453,
+      "learning_rate": 4.9770151769663e-06,
+      "loss": 1.0133,
+      "step": 45
+    },
+    {
+      "epoch": 0.1885245901639344,
+      "grad_norm": 0.629992663860321,
+      "learning_rate": 4.974663219788095e-06,
+      "loss": 1.3077,
+      "step": 46
+    },
+    {
+      "epoch": 0.19262295081967212,
+      "grad_norm": 0.3679404556751251,
+      "learning_rate": 4.972197328910063e-06,
+      "loss": 0.7106,
+      "step": 47
+    },
+    {
+      "epoch": 0.19672131147540983,
+      "grad_norm": 0.5133907198905945,
+      "learning_rate": 4.969617617862023e-06,
+      "loss": 1.1623,
+      "step": 48
+    },
+    {
+      "epoch": 0.20081967213114754,
+      "grad_norm": 0.5112882852554321,
+      "learning_rate": 4.966924205414088e-06,
+      "loss": 1.3149,
+      "step": 49
+    },
+    {
+      "epoch": 0.20491803278688525,
+      "grad_norm": 0.5100849270820618,
+      "learning_rate": 4.964117215571188e-06,
+      "loss": 1.3184,
+      "step": 50
+    },
+    {
+      "epoch": 0.20901639344262296,
+      "grad_norm": 0.49572739005088806,
+      "learning_rate": 4.9611967775673694e-06,
+      "loss": 1.139,
+      "step": 51
+    },
+    {
+      "epoch": 0.21311475409836064,
+      "grad_norm": 0.5028955340385437,
+      "learning_rate": 4.95816302585984e-06,
+      "loss": 1.1495,
+      "step": 52
+    },
+    {
+      "epoch": 0.21721311475409835,
+      "grad_norm": 0.44010698795318604,
+      "learning_rate": 4.9550161001227795e-06,
+      "loss": 1.1402,
+      "step": 53
+    },
+    {
+      "epoch": 0.22131147540983606,
+      "grad_norm": 0.461842805147171,
+      "learning_rate": 4.95175614524091e-06,
+      "loss": 1.1513,
+      "step": 54
+    },
+    {
+      "epoch": 0.22540983606557377,
+      "grad_norm": 0.40412789583206177,
+      "learning_rate": 4.9483833113028245e-06,
+      "loss": 0.8538,
+      "step": 55
+    },
+    {
+      "epoch": 0.22950819672131148,
+      "grad_norm": 0.5042741298675537,
+      "learning_rate": 4.944897753594078e-06,
+      "loss": 1.1381,
+      "step": 56
+    },
+    {
+      "epoch": 0.2336065573770492,
+      "grad_norm": 0.47176745533943176,
+      "learning_rate": 4.941299632590035e-06,
+      "loss": 1.1349,
+      "step": 57
+    },
+    {
+      "epoch": 0.23770491803278687,
+      "grad_norm": 0.41749855875968933,
+      "learning_rate": 4.937589113948485e-06,
+      "loss": 0.9905,
+      "step": 58
+    },
+    {
+      "epoch": 0.24180327868852458,
+      "grad_norm": 0.51772141456604,
+      "learning_rate": 4.933766368502015e-06,
+      "loss": 1.1436,
+      "step": 59
+    },
+    {
+      "epoch": 0.2459016393442623,
+      "grad_norm": 0.43589144945144653,
+      "learning_rate": 4.929831572250142e-06,
+      "loss": 0.98,
+      "step": 60
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.41600921750068665,
+      "learning_rate": 4.925784906351212e-06,
+      "loss": 1.1226,
+      "step": 61
+    },
+    {
+      "epoch": 0.2540983606557377,
+      "grad_norm": 0.5028397440910339,
+      "learning_rate": 4.9216265571140565e-06,
+      "loss": 1.2872,
+      "step": 62
+    },
+    {
+      "epoch": 0.2581967213114754,
+      "grad_norm": 0.4340194761753082,
+      "learning_rate": 4.917356715989421e-06,
+      "loss": 1.1263,
+      "step": 63
+    },
+    {
+      "epoch": 0.26229508196721313,
+      "grad_norm": 0.4830523729324341,
+      "learning_rate": 4.912975579561146e-06,
+      "loss": 1.2734,
+      "step": 64
+    },
+    {
+      "epoch": 0.26639344262295084,
+      "grad_norm": 0.38300302624702454,
+      "learning_rate": 4.908483349537113e-06,
+      "loss": 0.9832,
+      "step": 65
+    },
+    {
+      "epoch": 0.27049180327868855,
+      "grad_norm": 0.47147682309150696,
+      "learning_rate": 4.903880232739967e-06,
+      "loss": 1.2843,
+      "step": 66
+    },
+    {
+      "epoch": 0.27459016393442626,
+      "grad_norm": 0.4417444169521332,
+      "learning_rate": 4.899166441097586e-06,
+      "loss": 1.1331,
+      "step": 67
+    },
+    {
+      "epoch": 0.2786885245901639,
+      "grad_norm": 0.4601738452911377,
+      "learning_rate": 4.8943421916333275e-06,
+      "loss": 1.2623,
+      "step": 68
+    },
+    {
+      "epoch": 0.2827868852459016,
+      "grad_norm": 0.4713452160358429,
+      "learning_rate": 4.889407706456039e-06,
+      "loss": 1.2657,
+      "step": 69
+    },
+    {
+      "epoch": 0.28688524590163933,
+      "grad_norm": 0.4256956875324249,
+      "learning_rate": 4.884363212749825e-06,
+      "loss": 1.1085,
+      "step": 70
+    },
+    {
+      "epoch": 0.29098360655737704,
+      "grad_norm": 0.4324210584163666,
+      "learning_rate": 4.879208942763595e-06,
+      "loss": 1.1078,
+      "step": 71
+    },
+    {
+      "epoch": 0.29508196721311475,
+      "grad_norm": 0.5453669428825378,
+      "learning_rate": 4.8739451338003675e-06,
+      "loss": 1.2591,
+      "step": 72
+    },
+    {
+      "epoch": 0.29918032786885246,
+      "grad_norm": 0.5175065398216248,
+      "learning_rate": 4.868572028206342e-06,
+      "loss": 1.2617,
+      "step": 73
+    },
+    {
+      "epoch": 0.30327868852459017,
+      "grad_norm": 0.4222549498081207,
+      "learning_rate": 4.863089873359746e-06,
+      "loss": 1.1215,
+      "step": 74
+    },
+    {
+      "epoch": 0.3073770491803279,
+      "grad_norm": 0.4675232470035553,
+      "learning_rate": 4.857498921659443e-06,
+      "loss": 1.1158,
+      "step": 75
+    },
+    {
+      "epoch": 0.3114754098360656,
+      "grad_norm": 0.4866585433483124,
+      "learning_rate": 4.8517994305133135e-06,
+      "loss": 1.1089,
+      "step": 76
+    },
+    {
+      "epoch": 0.3155737704918033,
+      "grad_norm": 0.4017506241798401,
+      "learning_rate": 4.845991662326402e-06,
+      "loss": 0.9646,
+      "step": 77
+    },
+    {
+      "epoch": 0.319672131147541,
+      "grad_norm": 0.4822794497013092,
+      "learning_rate": 4.840075884488838e-06,
+      "loss": 1.0968,
+      "step": 78
+    },
+    {
+      "epoch": 0.3237704918032787,
+      "grad_norm": 0.4413742423057556,
+      "learning_rate": 4.834052369363522e-06,
+      "loss": 1.119,
+      "step": 79
+    },
+    {
+      "epoch": 0.32786885245901637,
+      "grad_norm": 0.4934443533420563,
+      "learning_rate": 4.827921394273592e-06,
+      "loss": 1.2649,
+      "step": 80
+    },
+    {
+      "epoch": 0.3319672131147541,
+      "grad_norm": 0.43795523047447205,
+      "learning_rate": 4.821683241489648e-06,
+      "loss": 1.1222,
+      "step": 81
+    },
+    {
+      "epoch": 0.3360655737704918,
+      "grad_norm": 0.4516526758670807,
+      "learning_rate": 4.815338198216762e-06,
+      "loss": 1.1335,
+      "step": 82
+    },
+    {
+      "epoch": 0.3401639344262295,
+      "grad_norm": 0.6029425263404846,
+      "learning_rate": 4.808886556581252e-06,
+      "loss": 1.2402,
+      "step": 83
+    },
+    {
+      "epoch": 0.3442622950819672,
+      "grad_norm": 0.4546549618244171,
+      "learning_rate": 4.802328613617234e-06,
+      "loss": 1.2487,
+      "step": 84
+    },
+    {
+      "epoch": 0.3483606557377049,
+      "grad_norm": 0.4653581976890564,
+      "learning_rate": 4.795664671252947e-06,
+      "loss": 1.1113,
+      "step": 85
+    },
+    {
+      "epoch": 0.3524590163934426,
+      "grad_norm": 0.5216373205184937,
+      "learning_rate": 4.788895036296848e-06,
+      "loss": 1.2333,
+      "step": 86
+    },
+    {
+      "epoch": 0.35655737704918034,
+      "grad_norm": 0.5054514408111572,
+      "learning_rate": 4.782020020423492e-06,
+      "loss": 1.2465,
+      "step": 87
+    },
+    {
+      "epoch": 0.36065573770491804,
+      "grad_norm": 0.46515244245529175,
+      "learning_rate": 4.775039940159182e-06,
+      "loss": 1.0934,
+      "step": 88
+    },
+    {
+      "epoch": 0.36475409836065575,
+      "grad_norm": 0.44310179352760315,
+      "learning_rate": 4.76795511686739e-06,
+      "loss": 1.0959,
+      "step": 89
+    },
+    {
+      "epoch": 0.36885245901639346,
+      "grad_norm": 0.4382772147655487,
+      "learning_rate": 4.760765876733967e-06,
+      "loss": 1.24,
+      "step": 90
+    },
+    {
+      "epoch": 0.3729508196721312,
+      "grad_norm": 0.4309405982494354,
+      "learning_rate": 4.753472550752128e-06,
+      "loss": 1.1033,
+      "step": 91
+    },
+    {
+      "epoch": 0.3770491803278688,
+      "grad_norm": 0.4639149606227875,
+      "learning_rate": 4.746075474707204e-06,
+      "loss": 1.2442,
+      "step": 92
+    },
+    {
+      "epoch": 0.38114754098360654,
+      "grad_norm": 0.46096235513687134,
+      "learning_rate": 4.738574989161189e-06,
+      "loss": 1.2546,
+      "step": 93
+    },
+    {
+      "epoch": 0.38524590163934425,
+      "grad_norm": 0.4685989320278168,
+      "learning_rate": 4.73097143943706e-06,
+      "loss": 1.2396,
+      "step": 94
+    },
+    {
+      "epoch": 0.38934426229508196,
+      "grad_norm": 0.4785357713699341,
+      "learning_rate": 4.723265175602877e-06,
+      "loss": 1.2363,
+      "step": 95
+    },
+    {
+      "epoch": 0.39344262295081966,
+      "grad_norm": 0.4441625475883484,
+      "learning_rate": 4.7154565524556655e-06,
+      "loss": 1.1126,
+      "step": 96
+    },
+    {
+      "epoch": 0.3975409836065574,
+      "grad_norm": 0.4569564759731293,
+      "learning_rate": 4.707545929505083e-06,
+      "loss": 1.2333,
+      "step": 97
+    },
+    {
+      "epoch": 0.4016393442622951,
+      "grad_norm": 0.4679456353187561,
+      "learning_rate": 4.699533670956866e-06,
+      "loss": 1.2431,
+      "step": 98
+    },
+    {
+      "epoch": 0.4057377049180328,
+      "grad_norm": 0.42482486367225647,
+      "learning_rate": 4.691420145696062e-06,
+      "loss": 1.2233,
+      "step": 99
+    },
+    {
+      "epoch": 0.4098360655737705,
+      "grad_norm": 0.500905454158783,
+      "learning_rate": 4.683205727270047e-06,
+      "loss": 1.0914,
+      "step": 100
+    },
+    {
+      "epoch": 0.4139344262295082,
+      "grad_norm": 0.48397594690322876,
+      "learning_rate": 4.674890793871327e-06,
+      "loss": 1.2354,
+      "step": 101
+    },
+    {
+      "epoch": 0.4180327868852459,
+      "grad_norm": 0.43638041615486145,
+      "learning_rate": 4.666475728320124e-06,
+      "loss": 1.2393,
+      "step": 102
+    },
+    {
+      "epoch": 0.42213114754098363,
+      "grad_norm": 0.4171241819858551,
+      "learning_rate": 4.657960918046755e-06,
+      "loss": 0.9597,
+      "step": 103
+    },
+    {
+      "epoch": 0.4262295081967213,
+      "grad_norm": 0.5223995447158813,
+      "learning_rate": 4.64934675507379e-06,
+      "loss": 1.2454,
+      "step": 104
+    },
+    {
+      "epoch": 0.430327868852459,
+      "grad_norm": 0.44195184111595154,
+      "learning_rate": 4.6406336359980075e-06,
+      "loss": 1.2265,
+      "step": 105
+    },
+    {
+      "epoch": 0.4344262295081967,
+      "grad_norm": 0.3648192882537842,
+      "learning_rate": 4.631821961972131e-06,
+      "loss": 0.9507,
+      "step": 106
+    },
+    {
+      "epoch": 0.4385245901639344,
+      "grad_norm": 0.4118606150150299,
+      "learning_rate": 4.622912138686364e-06,
+      "loss": 1.1188,
+      "step": 107
+    },
+    {
+      "epoch": 0.4426229508196721,
+      "grad_norm": 0.40940552949905396,
+      "learning_rate": 4.613904576349709e-06,
+      "loss": 0.9472,
+      "step": 108
+    },
+    {
+      "epoch": 0.44672131147540983,
+      "grad_norm": 0.4917749762535095,
+      "learning_rate": 4.604799689671083e-06,
+      "loss": 1.2392,
+      "step": 109
+    },
+    {
+      "epoch": 0.45081967213114754,
+      "grad_norm": 0.38426458835601807,
+      "learning_rate": 4.595597897840224e-06,
+      "loss": 0.9329,
+      "step": 110
+    },
+    {
+      "epoch": 0.45491803278688525,
+      "grad_norm": 0.4216136038303375,
+      "learning_rate": 4.58629962450839e-06,
+      "loss": 1.0911,
+      "step": 111
+    },
+    {
+      "epoch": 0.45901639344262296,
+      "grad_norm": 0.4349055290222168,
+      "learning_rate": 4.576905297768856e-06,
+      "loss": 1.1005,
+      "step": 112
+    },
+    {
+      "epoch": 0.46311475409836067,
+      "grad_norm": 0.34622690081596375,
+      "learning_rate": 4.567415350137206e-06,
+      "loss": 0.8023,
+      "step": 113
+    },
+    {
+      "epoch": 0.4672131147540984,
+      "grad_norm": 0.45868179202079773,
+      "learning_rate": 4.557830218531414e-06,
+      "loss": 1.2439,
+      "step": 114
+    },
+    {
+      "epoch": 0.4713114754098361,
+      "grad_norm": 0.4467625021934509,
+      "learning_rate": 4.548150344251735e-06,
+      "loss": 1.2263,
+      "step": 115
+    },
+    {
+      "epoch": 0.47540983606557374,
+      "grad_norm": 0.4440653622150421,
+      "learning_rate": 4.538376172960382e-06,
+      "loss": 1.0828,
+      "step": 116
+    },
+    {
+      "epoch": 0.47950819672131145,
+      "grad_norm": 0.45460832118988037,
+      "learning_rate": 4.528508154661013e-06,
+      "loss": 1.2406,
+      "step": 117
+    },
+    {
+      "epoch": 0.48360655737704916,
+      "grad_norm": 0.40908852219581604,
+      "learning_rate": 4.518546743678008e-06,
+      "loss": 1.0912,
+      "step": 118
+    },
+    {
+      "epoch": 0.48770491803278687,
+      "grad_norm": 0.4369237422943115,
+      "learning_rate": 4.508492398635556e-06,
+      "loss": 1.0774,
+      "step": 119
+    },
+    {
+      "epoch": 0.4918032786885246,
+      "grad_norm": 0.41811734437942505,
+      "learning_rate": 4.498345582436534e-06,
+      "loss": 1.0917,
+      "step": 120
+    },
+    {
+      "epoch": 0.4959016393442623,
+      "grad_norm": 0.4201302230358124,
+      "learning_rate": 4.488106762241202e-06,
+      "loss": 1.0965,
+      "step": 121
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.4195842444896698,
+      "learning_rate": 4.477776409445692e-06,
+      "loss": 1.0757,
+      "step": 122
+    },
+    {
+      "epoch": 0.5040983606557377,
+      "grad_norm": 0.37664470076560974,
+      "learning_rate": 4.4673549996603025e-06,
+      "loss": 0.9385,
+      "step": 123
+    },
+    {
+      "epoch": 0.5081967213114754,
+      "grad_norm": 0.5090377926826477,
+      "learning_rate": 4.4568430126876036e-06,
+      "loss": 1.2263,
+      "step": 124
+    },
+    {
+      "epoch": 0.5122950819672131,
+      "grad_norm": 0.41210001707077026,
+      "learning_rate": 4.446240932500349e-06,
+      "loss": 1.0886,
+      "step": 125
+    },
+    {
+      "epoch": 0.5163934426229508,
+      "grad_norm": 0.4589191675186157,
+      "learning_rate": 4.435549247219187e-06,
+      "loss": 1.232,
+      "step": 126
+    },
+    {
+      "epoch": 0.5204918032786885,
+      "grad_norm": 0.42237797379493713,
+      "learning_rate": 4.424768449090195e-06,
+      "loss": 1.0785,
+      "step": 127
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "grad_norm": 0.42833560705184937,
+      "learning_rate": 4.413899034462215e-06,
+      "loss": 1.0728,
+      "step": 128
+    },
+    {
+      "epoch": 0.5286885245901639,
+      "grad_norm": 0.4315826892852783,
+      "learning_rate": 4.402941503763996e-06,
+      "loss": 1.0867,
+      "step": 129
+    },
+    {
+      "epoch": 0.5327868852459017,
+      "grad_norm": 0.3762200176715851,
+      "learning_rate": 4.391896361481158e-06,
+      "loss": 0.9324,
+      "step": 130
+    },
+    {
+      "epoch": 0.5368852459016393,
+      "grad_norm": 0.4800119698047638,
+      "learning_rate": 4.380764116132972e-06,
+      "loss": 1.1046,
+      "step": 131
+    },
+    {
+      "epoch": 0.5409836065573771,
+      "grad_norm": 0.42680102586746216,
+      "learning_rate": 4.369545280248932e-06,
+      "loss": 1.0733,
+      "step": 132
+    },
+    {
+      "epoch": 0.5450819672131147,
+      "grad_norm": 0.49782562255859375,
+      "learning_rate": 4.358240370345177e-06,
+      "loss": 1.2342,
+      "step": 133
+    },
+    {
+      "epoch": 0.5491803278688525,
+      "grad_norm": 0.4627741873264313,
+      "learning_rate": 4.346849906900693e-06,
+      "loss": 1.2281,
+      "step": 134
+    },
+    {
+      "epoch": 0.5532786885245902,
+      "grad_norm": 0.426714688539505,
+      "learning_rate": 4.335374414333362e-06,
+      "loss": 0.9532,
+      "step": 135
+    },
+    {
+      "epoch": 0.5573770491803278,
+      "grad_norm": 0.4838584363460541,
+      "learning_rate": 4.323814420975815e-06,
+      "loss": 1.0903,
+      "step": 136
+    },
+    {
+      "epoch": 0.5614754098360656,
+      "grad_norm": 0.4934047758579254,
+      "learning_rate": 4.312170459051103e-06,
+      "loss": 1.2122,
+      "step": 137
+    },
+    {
+      "epoch": 0.5655737704918032,
+      "grad_norm": 0.4467495381832123,
+      "learning_rate": 4.300443064648198e-06,
+      "loss": 1.0822,
+      "step": 138
+    },
+    {
+      "epoch": 0.569672131147541,
+      "grad_norm": 0.4738949239253998,
+      "learning_rate": 4.288632777697313e-06,
+      "loss": 1.2296,
+      "step": 139
+    },
+    {
+      "epoch": 0.5737704918032787,
+      "grad_norm": 0.4483662545681,
+      "learning_rate": 4.276740141945035e-06,
+      "loss": 1.0718,
+      "step": 140
+    },
+    {
+      "epoch": 0.5778688524590164,
+      "grad_norm": 0.4037500321865082,
+      "learning_rate": 4.264765704929305e-06,
+      "loss": 1.082,
+      "step": 141
+    },
+    {
+      "epoch": 0.5819672131147541,
+      "grad_norm": 0.39695730805397034,
+      "learning_rate": 4.252710017954191e-06,
+      "loss": 0.9265,
+      "step": 142
+    },
+    {
+      "epoch": 0.5860655737704918,
+      "grad_norm": 0.5003882050514221,
+      "learning_rate": 4.240573636064525e-06,
+      "loss": 1.2273,
+      "step": 143
+    },
+    {
+      "epoch": 0.5901639344262295,
+      "grad_norm": 0.4882379174232483,
+      "learning_rate": 4.228357118020332e-06,
+      "loss": 1.2261,
+      "step": 144
+    },
+    {
+      "epoch": 0.5942622950819673,
+      "grad_norm": 0.41904476284980774,
+      "learning_rate": 4.216061026271119e-06,
+      "loss": 1.1018,
+      "step": 145
+    },
+    {
+      "epoch": 0.5983606557377049,
+      "grad_norm": 0.4707728624343872,
+      "learning_rate": 4.203685926929968e-06,
+      "loss": 1.2294,
+      "step": 146
+    },
+    {
+      "epoch": 0.6024590163934426,
+      "grad_norm": 0.40794438123703003,
+      "learning_rate": 4.191232389747477e-06,
+      "loss": 1.0856,
+      "step": 147
+    },
+    {
+      "epoch": 0.6065573770491803,
+      "grad_norm": 0.4550691246986389,
+      "learning_rate": 4.178700988085534e-06,
+      "loss": 1.2273,
+      "step": 148
+    },
+    {
+      "epoch": 0.610655737704918,
+      "grad_norm": 0.40126630663871765,
+      "learning_rate": 4.166092298890909e-06,
+      "loss": 0.9451,
+      "step": 149
+    },
+    {
+      "epoch": 0.6147540983606558,
+      "grad_norm": 0.4168899655342102,
+      "learning_rate": 4.1534069026686975e-06,
+      "loss": 1.0871,
+      "step": 150
+    },
+    {
+      "epoch": 0.6188524590163934,
+      "grad_norm": 0.4449077248573303,
+      "learning_rate": 4.140645383455593e-06,
+      "loss": 0.9748,
+      "step": 151
+    },
+    {
+      "epoch": 0.6229508196721312,
+      "grad_norm": 0.5277643799781799,
+      "learning_rate": 4.127808328793e-06,
+      "loss": 1.2301,
+      "step": 152
+    },
+    {
+      "epoch": 0.6270491803278688,
+      "grad_norm": 0.4093081057071686,
+      "learning_rate": 4.114896329699979e-06,
+      "loss": 1.0789,
+      "step": 153
+    },
+    {
+      "epoch": 0.6311475409836066,
+      "grad_norm": 0.4493444859981537,
+      "learning_rate": 4.101909980646037e-06,
+      "loss": 1.2096,
+      "step": 154
+    },
+    {
+      "epoch": 0.6352459016393442,
+      "grad_norm": 0.40696650743484497,
+      "learning_rate": 4.088849879523763e-06,
+      "loss": 1.073,
+      "step": 155
+    },
+    {
+      "epoch": 0.639344262295082,
+      "grad_norm": 0.4298895299434662,
+      "learning_rate": 4.075716627621295e-06,
+      "loss": 1.0768,
+      "step": 156
+    },
+    {
+      "epoch": 0.6434426229508197,
+      "grad_norm": 0.544258713722229,
+      "learning_rate": 4.062510829594641e-06,
+      "loss": 1.2106,
+      "step": 157
+    },
+    {
+      "epoch": 0.6475409836065574,
+      "grad_norm": 0.4137495458126068,
+      "learning_rate": 4.049233093439834e-06,
+      "loss": 1.0738,
+      "step": 158
+    },
+    {
+      "epoch": 0.6516393442622951,
+      "grad_norm": 0.34983235597610474,
+      "learning_rate": 4.035884030464951e-06,
+      "loss": 0.9393,
+      "step": 159
+    },
+    {
+      "epoch": 0.6557377049180327,
+      "grad_norm": 0.475832998752594,
+      "learning_rate": 4.022464255261956e-06,
+      "loss": 1.0725,
+      "step": 160
+    },
+    {
+      "epoch": 0.6598360655737705,
+      "grad_norm": 0.38982298970222473,
+      "learning_rate": 4.008974385678412e-06,
+      "loss": 0.9301,
+      "step": 161
+    },
+    {
+      "epoch": 0.6639344262295082,
+      "grad_norm": 0.41842958331108093,
+      "learning_rate": 3.995415042789034e-06,
+      "loss": 0.9552,
+      "step": 162
+    },
+    {
+      "epoch": 0.6680327868852459,
+      "grad_norm": 0.3715745806694031,
+      "learning_rate": 3.9817868508670925e-06,
+      "loss": 0.9586,
+      "step": 163
+    },
+    {
+      "epoch": 0.6721311475409836,
+      "grad_norm": 0.39996999502182007,
+      "learning_rate": 3.9680904373556735e-06,
+      "loss": 1.0737,
+      "step": 164
+    },
+    {
+      "epoch": 0.6762295081967213,
+      "grad_norm": 0.41154536604881287,
+      "learning_rate": 3.954326432838792e-06,
+      "loss": 0.9275,
+      "step": 165
+    },
+    {
+      "epoch": 0.680327868852459,
+      "grad_norm": 0.4771071970462799,
+      "learning_rate": 3.940495471012355e-06,
+      "loss": 1.2166,
+      "step": 166
+    },
+    {
+      "epoch": 0.6844262295081968,
+      "grad_norm": 0.4488621652126312,
+      "learning_rate": 3.926598188654993e-06,
+      "loss": 1.2164,
+      "step": 167
+    },
+    {
+      "epoch": 0.6885245901639344,
+      "grad_norm": 0.3757840096950531,
+      "learning_rate": 3.912635225598739e-06,
+      "loss": 0.922,
+      "step": 168
+    },
+    {
+      "epoch": 0.6926229508196722,
+      "grad_norm": 0.4264204800128937,
+      "learning_rate": 3.898607224699568e-06,
+      "loss": 1.072,
+      "step": 169
+    },
+    {
+      "epoch": 0.6967213114754098,
+      "grad_norm": 0.4652060270309448,
+      "learning_rate": 3.884514831807805e-06,
+      "loss": 1.212,
+      "step": 170
+    },
+    {
+      "epoch": 0.7008196721311475,
+      "grad_norm": 0.455747127532959,
+      "learning_rate": 3.870358695738389e-06,
+      "loss": 1.2155,
+      "step": 171
+    },
+    {
+      "epoch": 0.7049180327868853,
+      "grad_norm": 0.4523256719112396,
+      "learning_rate": 3.856139468240996e-06,
+      "loss": 1.221,
+      "step": 172
+    },
+    {
+      "epoch": 0.7090163934426229,
+      "grad_norm": 0.44244229793548584,
+      "learning_rate": 3.841857803970039e-06,
+      "loss": 1.2092,
+      "step": 173
+    },
+    {
+      "epoch": 0.7131147540983607,
+      "grad_norm": 0.4393782913684845,
+      "learning_rate": 3.827514360454529e-06,
+      "loss": 1.0785,
+      "step": 174
+    },
+    {
+      "epoch": 0.7172131147540983,
+      "grad_norm": 0.4734303057193756,
+      "learning_rate": 3.813109798067789e-06,
+      "loss": 1.2032,
+      "step": 175
+    },
+    {
+      "epoch": 0.7213114754098361,
+      "grad_norm": 0.4356328845024109,
+      "learning_rate": 3.79864477999707e-06,
+      "loss": 1.0952,
+      "step": 176
+    },
+    {
+      "epoch": 0.7254098360655737,
+      "grad_norm": 0.5063803791999817,
+      "learning_rate": 3.7841199722130016e-06,
+      "loss": 1.0747,
+      "step": 177
+    },
+    {
+      "epoch": 0.7295081967213115,
+      "grad_norm": 0.37222030758857727,
+      "learning_rate": 3.7695360434389385e-06,
+      "loss": 0.945,
+      "step": 178
+    },
+    {
+      "epoch": 0.7336065573770492,
+      "grad_norm": 0.44854214787483215,
+      "learning_rate": 3.754893665120171e-06,
+      "loss": 1.0643,
+      "step": 179
+    },
+    {
+      "epoch": 0.7377049180327869,
+      "grad_norm": 0.47099798917770386,
+      "learning_rate": 3.7401935113930115e-06,
+      "loss": 1.0674,
+      "step": 180
+    },
+    {
+      "epoch": 0.7418032786885246,
+      "grad_norm": 0.40957486629486084,
+      "learning_rate": 3.7254362590537555e-06,
+      "loss": 1.0806,
+      "step": 181
+    },
+    {
+      "epoch": 0.7459016393442623,
+      "grad_norm": 0.44317427277565,
+      "learning_rate": 3.7106225875275257e-06,
+      "loss": 1.0747,
+      "step": 182
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.43721142411231995,
+      "learning_rate": 3.695753178836986e-06,
+      "loss": 1.217,
+      "step": 183
+    },
+    {
+      "epoch": 0.7540983606557377,
+      "grad_norm": 0.4011574685573578,
+      "learning_rate": 3.680828717570946e-06,
+      "loss": 1.0657,
+      "step": 184
+    },
+    {
+      "epoch": 0.7581967213114754,
+      "grad_norm": 0.43174558877944946,
+      "learning_rate": 3.6658498908528394e-06,
+      "loss": 1.2118,
+      "step": 185
+    },
+    {
+      "epoch": 0.7622950819672131,
+      "grad_norm": 0.4041191041469574,
+      "learning_rate": 3.6508173883090915e-06,
+      "loss": 1.0715,
+      "step": 186
+    },
+    {
+      "epoch": 0.7663934426229508,
+      "grad_norm": 0.40428057312965393,
+      "learning_rate": 3.635731902037364e-06,
+      "loss": 1.07,
+      "step": 187
+    },
+    {
+      "epoch": 0.7704918032786885,
+      "grad_norm": 0.434089720249176,
+      "learning_rate": 3.6205941265746976e-06,
+      "loss": 1.0573,
+      "step": 188
+    },
+    {
+      "epoch": 0.7745901639344263,
+      "grad_norm": 0.43966200947761536,
+      "learning_rate": 3.6054047588655287e-06,
+      "loss": 1.2011,
+      "step": 189
+    },
+    {
+      "epoch": 0.7786885245901639,
+      "grad_norm": 0.37951526045799255,
+      "learning_rate": 3.5901644982296058e-06,
+      "loss": 0.928,
+      "step": 190
+    },
+    {
+      "epoch": 0.7827868852459017,
+      "grad_norm": 0.40477126836776733,
+      "learning_rate": 3.5748740463297926e-06,
+      "loss": 1.0996,
+      "step": 191
+    },
+    {
+      "epoch": 0.7868852459016393,
+      "grad_norm": 0.4541768431663513,
+      "learning_rate": 3.5595341071397627e-06,
+      "loss": 1.2099,
+      "step": 192
+    },
+    {
+      "epoch": 0.7909836065573771,
+      "grad_norm": 0.4461807310581207,
+      "learning_rate": 3.5441453869115885e-06,
+      "loss": 1.2206,
+      "step": 193
+    },
+    {
+      "epoch": 0.7950819672131147,
+      "grad_norm": 0.393301784992218,
+      "learning_rate": 3.5287085941432246e-06,
+      "loss": 1.0643,
+      "step": 194
+    },
+    {
+      "epoch": 0.7991803278688525,
+      "grad_norm": 0.41351836919784546,
+      "learning_rate": 3.51322443954589e-06,
+      "loss": 1.2166,
+      "step": 195
+    },
+    {
+      "epoch": 0.8032786885245902,
+      "grad_norm": 0.4048912525177002,
+      "learning_rate": 3.4976936360113475e-06,
+      "loss": 1.0686,
+      "step": 196
+    },
+    {
+      "epoch": 0.8073770491803278,
+      "grad_norm": 0.41161829233169556,
+      "learning_rate": 3.4821168985790776e-06,
+      "loss": 1.0661,
+      "step": 197
+    },
+    {
+      "epoch": 0.8114754098360656,
+      "grad_norm": 0.4504454433917999,
+      "learning_rate": 3.4664949444033648e-06,
+      "loss": 1.0658,
+      "step": 198
+    },
+    {
+      "epoch": 0.8155737704918032,
+      "grad_norm": 0.45676442980766296,
+      "learning_rate": 3.4508284927202733e-06,
+      "loss": 1.2081,
+      "step": 199
+    },
+    {
+      "epoch": 0.819672131147541,
+      "grad_norm": 0.37078866362571716,
+      "learning_rate": 3.4351182648145388e-06,
+      "loss": 0.9318,
+      "step": 200
+    },
+    {
+      "epoch": 0.8237704918032787,
+      "grad_norm": 0.373999685049057,
+      "learning_rate": 3.4193649839863563e-06,
+      "loss": 0.9257,
+      "step": 201
+    },
+    {
+      "epoch": 0.8278688524590164,
+      "grad_norm": 0.4319070279598236,
+      "learning_rate": 3.4035693755180817e-06,
+      "loss": 1.2125,
+      "step": 202
+    },
+    {
+      "epoch": 0.8319672131147541,
+      "grad_norm": 0.4047754108905792,
+      "learning_rate": 3.387732166640837e-06,
+      "loss": 1.0657,
+      "step": 203
+    },
+    {
+      "epoch": 0.8360655737704918,
+      "grad_norm": 0.3999074697494507,
+      "learning_rate": 3.3718540865010348e-06,
+      "loss": 1.0561,
+      "step": 204
+    },
+    {
+      "epoch": 0.8401639344262295,
+      "grad_norm": 0.439710795879364,
+      "learning_rate": 3.355935866126798e-06,
+      "loss": 1.2163,
+      "step": 205
+    },
+    {
+      "epoch": 0.8442622950819673,
+      "grad_norm": 0.4157400131225586,
+      "learning_rate": 3.3399782383943153e-06,
+      "loss": 1.084,
+      "step": 206
+    },
+    {
+      "epoch": 0.8483606557377049,
+      "grad_norm": 0.36068040132522583,
+      "learning_rate": 3.3239819379940896e-06,
+      "loss": 0.9286,
+      "step": 207
+    },
+    {
+      "epoch": 0.8524590163934426,
+      "grad_norm": 0.47732654213905334,
+      "learning_rate": 3.3079477013971173e-06,
+      "loss": 1.215,
+      "step": 208
+    },
+    {
+      "epoch": 0.8565573770491803,
+      "grad_norm": 0.42468348145484924,
+      "learning_rate": 3.2918762668209815e-06,
+      "loss": 1.2141,
+      "step": 209
+    },
+    {
+      "epoch": 0.860655737704918,
+      "grad_norm": 0.40056779980659485,
+      "learning_rate": 3.275768374195862e-06,
+      "loss": 1.0908,
+      "step": 210
+    },
+    {
+      "epoch": 0.8647540983606558,
+      "grad_norm": 0.4349064826965332,
+      "learning_rate": 3.2596247651304715e-06,
+      "loss": 1.2033,
+      "step": 211
+    },
+    {
+      "epoch": 0.8688524590163934,
+      "grad_norm": 0.4414246082305908,
+      "learning_rate": 3.2434461828779096e-06,
+      "loss": 1.0881,
+      "step": 212
+    },
+    {
+      "epoch": 0.8729508196721312,
+      "grad_norm": 0.421542763710022,
+      "learning_rate": 3.227233372301444e-06,
+      "loss": 1.0671,
+      "step": 213
+    },
+    {
+      "epoch": 0.8770491803278688,
+      "grad_norm": 0.4388136863708496,
+      "learning_rate": 3.2109870798402186e-06,
+      "loss": 1.0648,
+      "step": 214
+    },
+    {
+      "epoch": 0.8811475409836066,
+      "grad_norm": 0.38112929463386536,
+      "learning_rate": 3.194708053474885e-06,
+      "loss": 0.9222,
+      "step": 215
+    },
+    {
+      "epoch": 0.8852459016393442,
+      "grad_norm": 0.42555421590805054,
+      "learning_rate": 3.1783970426931686e-06,
+      "loss": 1.0613,
+      "step": 216
+    },
+    {
+      "epoch": 0.889344262295082,
+      "grad_norm": 0.45528554916381836,
+      "learning_rate": 3.1620547984553563e-06,
+      "loss": 1.206,
+      "step": 217
+    },
+    {
+      "epoch": 0.8934426229508197,
+      "grad_norm": 0.4099060893058777,
+      "learning_rate": 3.1456820731597283e-06,
+      "loss": 1.0603,
+      "step": 218
+    },
+    {
+      "epoch": 0.8975409836065574,
+      "grad_norm": 0.4148857593536377,
+      "learning_rate": 3.129279620607915e-06,
+      "loss": 1.0768,
+      "step": 219
+    },
+    {
+      "epoch": 0.9016393442622951,
+      "grad_norm": 0.3957928419113159,
+      "learning_rate": 3.1128481959701916e-06,
+      "loss": 1.0694,
+      "step": 220
+    },
+    {
+      "epoch": 0.9057377049180327,
+      "grad_norm": 0.3965204060077667,
+      "learning_rate": 3.096388555750711e-06,
+      "loss": 1.066,
+      "step": 221
+    },
+    {
+      "epoch": 0.9098360655737705,
+      "grad_norm": 0.43010538816452026,
+      "learning_rate": 3.0799014577526735e-06,
+      "loss": 1.2038,
+      "step": 222
+    },
+    {
+      "epoch": 0.9139344262295082,
+      "grad_norm": 0.4200957119464874,
+      "learning_rate": 3.063387661043438e-06,
+      "loss": 1.0688,
+      "step": 223
+    },
+    {
+      "epoch": 0.9180327868852459,
+      "grad_norm": 0.40668630599975586,
+      "learning_rate": 3.0468479259195753e-06,
+      "loss": 1.0627,
+      "step": 224
+    },
+    {
+      "epoch": 0.9221311475409836,
+      "grad_norm": 0.26530569791793823,
+      "learning_rate": 3.0302830138718605e-06,
+      "loss": 0.5103,
+      "step": 225
+    },
+    {
+      "epoch": 0.9262295081967213,
+      "grad_norm": 0.44774329662323,
+      "learning_rate": 3.0136936875502175e-06,
+      "loss": 1.2042,
+      "step": 226
+    },
+    {
+      "epoch": 0.930327868852459,
+      "grad_norm": 0.34162765741348267,
+      "learning_rate": 2.9970807107286078e-06,
+      "loss": 0.7947,
+      "step": 227
+    },
+    {
+      "epoch": 0.9344262295081968,
+      "grad_norm": 0.46961259841918945,
+      "learning_rate": 2.9804448482698595e-06,
+      "loss": 1.1955,
+      "step": 228
+    },
+    {
+      "epoch": 0.9385245901639344,
+      "grad_norm": 0.4084847569465637,
+      "learning_rate": 2.9637868660904613e-06,
+      "loss": 1.0717,
+      "step": 229
+    },
+    {
+      "epoch": 0.9426229508196722,
+      "grad_norm": 0.42072829604148865,
+      "learning_rate": 2.947107531125292e-06,
+      "loss": 1.2051,
+      "step": 230
+    },
+    {
+      "epoch": 0.9467213114754098,
+      "grad_norm": 0.43697723746299744,
+      "learning_rate": 2.9304076112923175e-06,
+      "loss": 1.2038,
+      "step": 231
+    },
+    {
+      "epoch": 0.9508196721311475,
+      "grad_norm": 0.42760905623435974,
+      "learning_rate": 2.9136878754572317e-06,
+      "loss": 1.2073,
+      "step": 232
+    },
+    {
+      "epoch": 0.9549180327868853,
+      "grad_norm": 0.44690465927124023,
+      "learning_rate": 2.896949093398059e-06,
+      "loss": 1.2163,
+      "step": 233
+    },
+    {
+      "epoch": 0.9590163934426229,
+      "grad_norm": 0.4078381061553955,
+      "learning_rate": 2.8801920357697132e-06,
+      "loss": 1.0642,
+      "step": 234
+    },
+    {
+      "epoch": 0.9631147540983607,
+      "grad_norm": 0.442238450050354,
+      "learning_rate": 2.8634174740685165e-06,
+      "loss": 1.1923,
+      "step": 235
+    },
+    {
+      "epoch": 0.9672131147540983,
+      "grad_norm": 0.37964820861816406,
+      "learning_rate": 2.8466261805966797e-06,
+      "loss": 1.0788,
+      "step": 236
+    },
+    {
+      "epoch": 0.9713114754098361,
+      "grad_norm": 0.4121408462524414,
+      "learning_rate": 2.8298189284267492e-06,
+      "loss": 1.0854,
+      "step": 237
+    },
+    {
+      "epoch": 0.9754098360655737,
+      "grad_norm": 0.357814759016037,
+      "learning_rate": 2.8129964913660056e-06,
+      "loss": 0.9302,
+      "step": 238
+    },
+    {
+      "epoch": 0.9795081967213115,
+      "grad_norm": 0.42910444736480713,
+      "learning_rate": 2.796159643920847e-06,
+      "loss": 1.2106,
+      "step": 239
+    },
+    {
+      "epoch": 0.9836065573770492,
+      "grad_norm": 0.4574357569217682,
+      "learning_rate": 2.7793091612611266e-06,
+      "loss": 1.2081,
+      "step": 240
+    },
+    {
+      "epoch": 0.9877049180327869,
+      "grad_norm": 0.3818189799785614,
+      "learning_rate": 2.762445819184463e-06,
+      "loss": 0.9782,
+      "step": 241
+    },
+    {
+      "epoch": 0.9918032786885246,
+      "grad_norm": 0.3787913918495178,
+      "learning_rate": 2.7455703940805228e-06,
+      "loss": 1.0491,
+      "step": 242
+    },
+    {
+      "epoch": 0.9959016393442623,
+      "grad_norm": 0.3858451545238495,
+      "learning_rate": 2.7286836628952775e-06,
+      "loss": 0.9493,
+      "step": 243
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.40878915786743164,
+      "learning_rate": 2.7117864030952306e-06,
+      "loss": 1.0745,
+      "step": 244
+    },
+    {
+      "epoch": 1.0040983606557377,
+      "grad_norm": 0.4115857481956482,
+      "learning_rate": 2.694879392631625e-06,
+      "loss": 1.1877,
+      "step": 245
+    },
+    {
+      "epoch": 1.0081967213114753,
+      "grad_norm": 0.40796780586242676,
+      "learning_rate": 2.677963409904624e-06,
+      "loss": 1.1999,
+      "step": 246
+    },
+    {
+      "epoch": 1.0122950819672132,
+      "grad_norm": 0.34583404660224915,
+      "learning_rate": 2.6610392337274754e-06,
+      "loss": 0.9231,
+      "step": 247
+    },
+    {
+      "epoch": 1.0163934426229508,
+      "grad_norm": 0.4206702411174774,
+      "learning_rate": 2.644107643290653e-06,
+      "loss": 1.1912,
+      "step": 248
+    },
+    {
+      "epoch": 1.0204918032786885,
+      "grad_norm": 0.3856116831302643,
+      "learning_rate": 2.6271694181259854e-06,
+      "loss": 1.051,
+      "step": 249
+    },
+    {
+      "epoch": 1.0245901639344261,
+      "grad_norm": 0.36935338377952576,
+      "learning_rate": 2.6102253380707626e-06,
+      "loss": 0.9188,
+      "step": 250
+    },
+    {
+      "epoch": 1.028688524590164,
+      "grad_norm": 0.4281650483608246,
+      "learning_rate": 2.5932761832318354e-06,
+      "loss": 1.19,
+      "step": 251
+    },
+    {
+      "epoch": 1.0327868852459017,
+      "grad_norm": 0.3120673596858978,
+      "learning_rate": 2.5763227339496984e-06,
+      "loss": 0.7811,
+      "step": 252
+    },
+    {
+      "epoch": 1.0368852459016393,
+      "grad_norm": 0.35444319248199463,
+      "learning_rate": 2.5593657707625615e-06,
+      "loss": 0.9101,
+      "step": 253
+    },
+    {
+      "epoch": 1.040983606557377,
+      "grad_norm": 0.41338273882865906,
+      "learning_rate": 2.5424060743704158e-06,
+      "loss": 1.1917,
+      "step": 254
+    },
+    {
+      "epoch": 1.0450819672131149,
+      "grad_norm": 0.39441365003585815,
+      "learning_rate": 2.5254444255990917e-06,
+      "loss": 1.1841,
+      "step": 255
+    },
+    {
+      "epoch": 1.0491803278688525,
+      "grad_norm": 0.38659295439720154,
+      "learning_rate": 2.508481605364302e-06,
+      "loss": 1.0622,
+      "step": 256
+    },
+    {
+      "epoch": 1.0532786885245902,
+      "grad_norm": 0.3723162114620209,
+      "learning_rate": 2.491518394635699e-06,
+      "loss": 1.0711,
+      "step": 257
+    },
+    {
+      "epoch": 1.0573770491803278,
+      "grad_norm": 0.38122040033340454,
+      "learning_rate": 2.4745555744009096e-06,
+      "loss": 1.0615,
+      "step": 258
+    },
+    {
+      "epoch": 1.0614754098360655,
+      "grad_norm": 0.38536080718040466,
+      "learning_rate": 2.4575939256295846e-06,
+      "loss": 1.0613,
+      "step": 259
+    },
+    {
+      "epoch": 1.0655737704918034,
+      "grad_norm": 0.4175841510295868,
+      "learning_rate": 2.44063422923744e-06,
+      "loss": 1.1848,
+      "step": 260
+    },
+    {
+      "epoch": 1.069672131147541,
+      "grad_norm": 0.3640967607498169,
+      "learning_rate": 2.423677266050303e-06,
+      "loss": 0.9144,
+      "step": 261
+    },
+    {
+      "epoch": 1.0737704918032787,
+      "grad_norm": 0.40630045533180237,
+      "learning_rate": 2.4067238167681655e-06,
+      "loss": 1.1783,
+      "step": 262
+    },
+    {
+      "epoch": 1.0778688524590163,
+      "grad_norm": 0.41707780957221985,
+      "learning_rate": 2.389774661929238e-06,
+      "loss": 1.1887,
+      "step": 263
+    },
+    {
+      "epoch": 1.0819672131147542,
+      "grad_norm": 0.4203328490257263,
+      "learning_rate": 2.3728305818740154e-06,
+      "loss": 1.1921,
+      "step": 264
+    },
+    {
+      "epoch": 1.0860655737704918,
+      "grad_norm": 0.3672391176223755,
+      "learning_rate": 2.355892356709347e-06,
+      "loss": 1.0485,
+      "step": 265
+    },
+    {
+      "epoch": 1.0901639344262295,
+      "grad_norm": 0.40844452381134033,
+      "learning_rate": 2.338960766272526e-06,
+      "loss": 1.1886,
+      "step": 266
+    },
+    {
+      "epoch": 1.0942622950819672,
+      "grad_norm": 0.38421133160591125,
+      "learning_rate": 2.3220365900953767e-06,
+      "loss": 1.0558,
+      "step": 267
+    },
+    {
+      "epoch": 1.098360655737705,
+      "grad_norm": 0.41264253854751587,
+      "learning_rate": 2.3051206073683755e-06,
+      "loss": 1.0627,
+      "step": 268
+    },
+    {
+      "epoch": 1.1024590163934427,
+      "grad_norm": 0.42893290519714355,
+      "learning_rate": 2.2882135969047703e-06,
+      "loss": 1.1924,
+      "step": 269
+    },
+    {
+      "epoch": 1.1065573770491803,
+      "grad_norm": 0.4517589807510376,
+      "learning_rate": 2.2713163371047234e-06,
+      "loss": 1.1954,
+      "step": 270
+    },
+    {
+      "epoch": 1.110655737704918,
+      "grad_norm": 0.43190959095954895,
+      "learning_rate": 2.2544296059194777e-06,
+      "loss": 1.1875,
+      "step": 271
+    },
+    {
+      "epoch": 1.1147540983606556,
+      "grad_norm": 0.3956393599510193,
+      "learning_rate": 2.237554180815538e-06,
+      "loss": 1.0555,
+      "step": 272
+    },
+    {
+      "epoch": 1.1188524590163935,
+      "grad_norm": 0.39499905705451965,
+      "learning_rate": 2.220690838738874e-06,
+      "loss": 1.0675,
+      "step": 273
+    },
+    {
+      "epoch": 1.1229508196721312,
+      "grad_norm": 0.4274572730064392,
+      "learning_rate": 2.203840356079154e-06,
+      "loss": 1.196,
+      "step": 274
+    },
+    {
+      "epoch": 1.1270491803278688,
+      "grad_norm": 0.4216081202030182,
+      "learning_rate": 2.1870035086339957e-06,
+      "loss": 1.1903,
+      "step": 275
+    },
+    {
+      "epoch": 1.1311475409836065,
+      "grad_norm": 0.39377495646476746,
+      "learning_rate": 2.170181071573252e-06,
+      "loss": 1.0438,
+      "step": 276
+    },
+    {
+      "epoch": 1.1352459016393444,
+      "grad_norm": 0.42385077476501465,
+      "learning_rate": 2.1533738194033207e-06,
+      "loss": 1.0567,
+      "step": 277
+    },
+    {
+      "epoch": 1.139344262295082,
+      "grad_norm": 0.3978115916252136,
+      "learning_rate": 2.1365825259314843e-06,
+      "loss": 1.0567,
+      "step": 278
+    },
+    {
+      "epoch": 1.1434426229508197,
+      "grad_norm": 0.3592003881931305,
+      "learning_rate": 2.119807964230287e-06,
+      "loss": 0.9136,
+      "step": 279
+    },
+    {
+      "epoch": 1.1475409836065573,
+      "grad_norm": 0.37734466791152954,
+      "learning_rate": 2.1030509066019412e-06,
+      "loss": 1.0529,
+      "step": 280
+    },
+    {
+      "epoch": 1.151639344262295,
+      "grad_norm": 0.35755643248558044,
+      "learning_rate": 2.0863121245427683e-06,
+      "loss": 0.9093,
+      "step": 281
+    },
+    {
+      "epoch": 1.1557377049180328,
+      "grad_norm": 0.3943209946155548,
+      "learning_rate": 2.0695923887076824e-06,
+      "loss": 1.0582,
+      "step": 282
+    },
+    {
+      "epoch": 1.1598360655737705,
+      "grad_norm": 0.42525431513786316,
+      "learning_rate": 2.0528924688747094e-06,
+      "loss": 1.1881,
+      "step": 283
+    },
+    {
+      "epoch": 1.1639344262295082,
+      "grad_norm": 0.40409737825393677,
+      "learning_rate": 2.0362131339095404e-06,
+      "loss": 1.1971,
+      "step": 284
+    },
+    {
+      "epoch": 1.1680327868852458,
+      "grad_norm": 0.3922713100910187,
+      "learning_rate": 2.0195551517301413e-06,
+      "loss": 1.0495,
+      "step": 285
+    },
+    {
+      "epoch": 1.1721311475409837,
+      "grad_norm": 0.40771782398223877,
+      "learning_rate": 2.0029192892713926e-06,
+      "loss": 1.0463,
+      "step": 286
+    },
+    {
+      "epoch": 1.1762295081967213,
+      "grad_norm": 0.36359649896621704,
+      "learning_rate": 1.986306312449783e-06,
+      "loss": 0.9164,
+      "step": 287
+    },
+    {
+      "epoch": 1.180327868852459,
+      "grad_norm": 0.4061618447303772,
+      "learning_rate": 1.9697169861281404e-06,
+      "loss": 1.044,
+      "step": 288
+    },
+    {
+      "epoch": 1.1844262295081966,
+      "grad_norm": 0.41950753331184387,
+      "learning_rate": 1.953152074080425e-06,
+      "loss": 1.0598,
+      "step": 289
+    },
+    {
+      "epoch": 1.1885245901639343,
+      "grad_norm": 0.44499605894088745,
+      "learning_rate": 1.936612338956562e-06,
+      "loss": 1.1791,
+      "step": 290
+    },
+    {
+      "epoch": 1.1926229508196722,
+      "grad_norm": 0.38169240951538086,
+      "learning_rate": 1.9200985422473265e-06,
+      "loss": 1.0692,
+      "step": 291
+    },
+    {
+      "epoch": 1.1967213114754098,
+      "grad_norm": 0.3613937199115753,
+      "learning_rate": 1.9036114442492901e-06,
+      "loss": 0.9741,
+      "step": 292
+    },
+    {
+      "epoch": 1.2008196721311475,
+      "grad_norm": 0.35592231154441833,
+      "learning_rate": 1.8871518040298092e-06,
+      "loss": 0.9079,
+      "step": 293
+    },
+    {
+      "epoch": 1.2049180327868854,
+      "grad_norm": 0.38903704285621643,
+      "learning_rate": 1.870720379392086e-06,
+      "loss": 1.0629,
+      "step": 294
+    },
+    {
+      "epoch": 1.209016393442623,
+      "grad_norm": 0.3940332233905792,
+      "learning_rate": 1.8543179268402728e-06,
+      "loss": 1.0465,
+      "step": 295
+    },
+    {
+      "epoch": 1.2131147540983607,
+      "grad_norm": 0.3513702154159546,
+      "learning_rate": 1.8379452015446445e-06,
+      "loss": 0.9417,
+      "step": 296
+    },
+    {
+      "epoch": 1.2172131147540983,
+      "grad_norm": 0.40110501646995544,
+      "learning_rate": 1.8216029573068316e-06,
+      "loss": 1.1848,
+      "step": 297
+    },
+    {
+      "epoch": 1.221311475409836,
+      "grad_norm": 0.4220271110534668,
+      "learning_rate": 1.8052919465251146e-06,
+      "loss": 1.1923,
+      "step": 298
+    },
+    {
+      "epoch": 1.2254098360655739,
+      "grad_norm": 0.41311049461364746,
+      "learning_rate": 1.7890129201597818e-06,
+      "loss": 1.2026,
+      "step": 299
+    },
+    {
+      "epoch": 1.2295081967213115,
+      "grad_norm": 0.3664914071559906,
+      "learning_rate": 1.772766627698556e-06,
+      "loss": 1.0687,
+      "step": 300
+    },
+    {
+      "epoch": 1.2336065573770492,
+      "grad_norm": 0.3773500323295593,
+      "learning_rate": 1.7565538171220919e-06,
+      "loss": 1.0548,
+      "step": 301
+    },
+    {
+      "epoch": 1.2377049180327868,
+      "grad_norm": 0.38285502791404724,
+      "learning_rate": 1.7403752348695296e-06,
+      "loss": 1.0563,
+      "step": 302
+    },
+    {
+      "epoch": 1.2418032786885247,
+      "grad_norm": 0.3447133004665375,
+      "learning_rate": 1.7242316258041392e-06,
+      "loss": 0.7965,
+      "step": 303
+    },
+    {
+      "epoch": 1.2459016393442623,
+      "grad_norm": 0.3942312002182007,
+      "learning_rate": 1.7081237331790196e-06,
+      "loss": 1.1774,
+      "step": 304
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.4133829176425934,
+      "learning_rate": 1.6920522986028832e-06,
+      "loss": 1.1979,
+      "step": 305
+    },
+    {
+      "epoch": 1.2540983606557377,
+      "grad_norm": 0.3958912193775177,
+      "learning_rate": 1.6760180620059108e-06,
+      "loss": 1.1947,
+      "step": 306
+    },
+    {
+      "epoch": 1.2581967213114753,
+      "grad_norm": 0.38137897849082947,
+      "learning_rate": 1.6600217616056847e-06,
+      "loss": 1.0567,
+      "step": 307
+    },
+    {
+      "epoch": 1.2622950819672132,
+      "grad_norm": 0.40342697501182556,
+      "learning_rate": 1.6440641338732017e-06,
+      "loss": 1.1894,
+      "step": 308
+    },
+    {
+      "epoch": 1.2663934426229508,
+      "grad_norm": 0.35720932483673096,
+      "learning_rate": 1.6281459134989667e-06,
+      "loss": 1.0529,
+      "step": 309
+    },
+    {
+      "epoch": 1.2704918032786885,
+      "grad_norm": 0.4097684919834137,
+      "learning_rate": 1.6122678333591635e-06,
+      "loss": 1.1959,
+      "step": 310
+    },
+    {
+      "epoch": 1.2745901639344264,
+      "grad_norm": 0.43254339694976807,
+      "learning_rate": 1.59643062448192e-06,
+      "loss": 1.1799,
+      "step": 311
+    },
+    {
+      "epoch": 1.278688524590164,
+      "grad_norm": 0.39682623744010925,
+      "learning_rate": 1.5806350160136446e-06,
+      "loss": 1.1929,
+      "step": 312
+    },
+    {
+      "epoch": 1.2827868852459017,
+      "grad_norm": 0.4308740794658661,
+      "learning_rate": 1.564881735185462e-06,
+      "loss": 1.2046,
+      "step": 313
+    },
+    {
+      "epoch": 1.2868852459016393,
+      "grad_norm": 0.36684301495552063,
+      "learning_rate": 1.5491715072797273e-06,
+      "loss": 1.0479,
+      "step": 314
+    },
+    {
+      "epoch": 1.290983606557377,
+      "grad_norm": 0.3774110972881317,
+      "learning_rate": 1.533505055596636e-06,
+      "loss": 1.0506,
+      "step": 315
+    },
+    {
+      "epoch": 1.2950819672131146,
+      "grad_norm": 0.3854641914367676,
+      "learning_rate": 1.5178831014209228e-06,
+      "loss": 1.1967,
+      "step": 316
+    },
+    {
+      "epoch": 1.2991803278688525,
+      "grad_norm": 0.36282190680503845,
+      "learning_rate": 1.5023063639886534e-06,
+      "loss": 0.9287,
+      "step": 317
+    },
+    {
+      "epoch": 1.3032786885245902,
+      "grad_norm": 0.4137556850910187,
+      "learning_rate": 1.4867755604541106e-06,
+      "loss": 1.1855,
+      "step": 318
+    },
+    {
+      "epoch": 1.3073770491803278,
+      "grad_norm": 0.32083621621131897,
+      "learning_rate": 1.4712914058567764e-06,
+      "loss": 0.7922,
+      "step": 319
+    },
+    {
+      "epoch": 1.3114754098360657,
+      "grad_norm": 0.386574387550354,
+      "learning_rate": 1.4558546130884124e-06,
+      "loss": 0.9356,
+      "step": 320
+    },
+    {
+      "epoch": 1.3155737704918034,
+      "grad_norm": 0.3629494309425354,
+      "learning_rate": 1.440465892860237e-06,
+      "loss": 0.9098,
+      "step": 321
+    },
+    {
+      "epoch": 1.319672131147541,
+      "grad_norm": 0.42711344361305237,
+      "learning_rate": 1.4251259536702078e-06,
+      "loss": 1.1856,
+      "step": 322
+    },
+    {
+      "epoch": 1.3237704918032787,
+      "grad_norm": 0.412729412317276,
+      "learning_rate": 1.4098355017703953e-06,
+      "loss": 1.1909,
+      "step": 323
+    },
+    {
+      "epoch": 1.3278688524590163,
+      "grad_norm": 0.379153311252594,
+      "learning_rate": 1.3945952411344721e-06,
+      "loss": 1.044,
+      "step": 324
+    },
+    {
+      "epoch": 1.331967213114754,
+      "grad_norm": 0.39480680227279663,
+      "learning_rate": 1.3794058734253032e-06,
+      "loss": 1.1911,
+      "step": 325
+    },
+    {
+      "epoch": 1.3360655737704918,
+      "grad_norm": 0.341774582862854,
+      "learning_rate": 1.3642680979626358e-06,
+      "loss": 0.788,
+      "step": 326
+    },
+    {
+      "epoch": 1.3401639344262295,
+      "grad_norm": 0.35537952184677124,
+      "learning_rate": 1.3491826116909102e-06,
+      "loss": 0.9082,
+      "step": 327
+    },
+    {
+      "epoch": 1.3442622950819672,
+      "grad_norm": 0.39688992500305176,
+      "learning_rate": 1.334150109147161e-06,
+      "loss": 1.1879,
+      "step": 328
+    },
+    {
+      "epoch": 1.348360655737705,
+      "grad_norm": 0.36747315526008606,
+      "learning_rate": 1.319171282429055e-06,
+      "loss": 1.0536,
+      "step": 329
+    },
+    {
+      "epoch": 1.3524590163934427,
+      "grad_norm": 0.3777834475040436,
+      "learning_rate": 1.3042468211630151e-06,
+      "loss": 1.0795,
+      "step": 330
+    },
+    {
+      "epoch": 1.3565573770491803,
+      "grad_norm": 0.3840106129646301,
+      "learning_rate": 1.289377412472475e-06,
+      "loss": 1.0563,
+      "step": 331
+    },
+    {
+      "epoch": 1.360655737704918,
+      "grad_norm": 0.38249310851097107,
+      "learning_rate": 1.2745637409462447e-06,
+      "loss": 1.054,
+      "step": 332
+    },
+    {
+      "epoch": 1.3647540983606556,
+      "grad_norm": 0.41104790568351746,
+      "learning_rate": 1.2598064886069883e-06,
+      "loss": 1.194,
+      "step": 333
+    },
+    {
+      "epoch": 1.3688524590163935,
+      "grad_norm": 0.4032827317714691,
+      "learning_rate": 1.245106334879829e-06,
+      "loss": 1.1931,
+      "step": 334
+    },
+    {
+      "epoch": 1.3729508196721312,
+      "grad_norm": 0.34885475039482117,
+      "learning_rate": 1.2304639565610622e-06,
+      "loss": 1.0484,
+      "step": 335
+    },
+    {
+      "epoch": 1.3770491803278688,
+      "grad_norm": 0.35111573338508606,
+      "learning_rate": 1.2158800277869999e-06,
+      "loss": 0.9173,
+      "step": 336
+    },
+    {
+      "epoch": 1.3811475409836065,
+      "grad_norm": 0.39559832215309143,
+      "learning_rate": 1.2013552200029308e-06,
+      "loss": 1.0561,
+      "step": 337
+    },
+    {
+      "epoch": 1.3852459016393444,
+      "grad_norm": 0.3728807866573334,
+      "learning_rate": 1.1868902019322118e-06,
+      "loss": 1.0634,
+      "step": 338
+    },
+    {
+      "epoch": 1.389344262295082,
+      "grad_norm": 0.36476659774780273,
+      "learning_rate": 1.1724856395454732e-06,
+      "loss": 1.0531,
+      "step": 339
+    },
+    {
+      "epoch": 1.3934426229508197,
+      "grad_norm": 0.3505764603614807,
+      "learning_rate": 1.1581421960299606e-06,
+      "loss": 0.9267,
+      "step": 340
+    },
+    {
+      "epoch": 1.3975409836065573,
+      "grad_norm": 0.3615562319755554,
+      "learning_rate": 1.1438605317590049e-06,
+      "loss": 1.052,
+      "step": 341
+    },
+    {
+      "epoch": 1.401639344262295,
+      "grad_norm": 0.3582325577735901,
+      "learning_rate": 1.1296413042616115e-06,
+      "loss": 1.0543,
+      "step": 342
+    },
+    {
+      "epoch": 1.4057377049180328,
+      "grad_norm": 0.3774518072605133,
+      "learning_rate": 1.1154851681921947e-06,
+      "loss": 1.0565,
+      "step": 343
+    },
+    {
+      "epoch": 1.4098360655737705,
+      "grad_norm": 0.40019941329956055,
+      "learning_rate": 1.1013927753004325e-06,
+      "loss": 1.189,
+      "step": 344
+    },
+    {
+      "epoch": 1.4139344262295082,
+      "grad_norm": 0.3798370063304901,
+      "learning_rate": 1.087364774401262e-06,
+      "loss": 1.0464,
+      "step": 345
+    },
+    {
+      "epoch": 1.418032786885246,
+      "grad_norm": 0.39250487089157104,
+      "learning_rate": 1.0734018113450076e-06,
+      "loss": 1.0502,
+      "step": 346
+    },
+    {
+      "epoch": 1.4221311475409837,
+      "grad_norm": 0.3554217517375946,
+      "learning_rate": 1.0595045289876454e-06,
+      "loss": 1.0605,
+      "step": 347
+    },
+    {
+      "epoch": 1.4262295081967213,
+      "grad_norm": 0.3500226140022278,
+      "learning_rate": 1.0456735671612092e-06,
+      "loss": 0.9104,
+      "step": 348
+    },
+    {
+      "epoch": 1.430327868852459,
+      "grad_norm": 0.3931366801261902,
+      "learning_rate": 1.0319095626443263e-06,
+      "loss": 1.1878,
+      "step": 349
+    },
+    {
+      "epoch": 1.4344262295081966,
+      "grad_norm": 0.3775804042816162,
+      "learning_rate": 1.0182131491329077e-06,
+      "loss": 1.0624,
+      "step": 350
+    },
+    {
+      "epoch": 1.4385245901639343,
+      "grad_norm": 0.4001830220222473,
+      "learning_rate": 1.004584957210967e-06,
+      "loss": 1.1765,
+      "step": 351
+    },
+    {
+      "epoch": 1.4426229508196722,
+      "grad_norm": 0.41710567474365234,
+      "learning_rate": 9.910256143215882e-07,
+      "loss": 1.1916,
+      "step": 352
+    },
+    {
+      "epoch": 1.4467213114754098,
+      "grad_norm": 0.33517131209373474,
+      "learning_rate": 9.775357447380457e-07,
+      "loss": 0.9161,
+      "step": 353
+    },
+    {
+      "epoch": 1.4508196721311475,
+      "grad_norm": 0.34202972054481506,
+      "learning_rate": 9.6411596953505e-07,
+      "loss": 0.9116,
+      "step": 354
+    },
+    {
+      "epoch": 1.4549180327868854,
+      "grad_norm": 0.36201608180999756,
+      "learning_rate": 9.507669065601663e-07,
+      "loss": 1.0389,
+      "step": 355
+    },
+    {
+      "epoch": 1.459016393442623,
+      "grad_norm": 0.4313637912273407,
+      "learning_rate": 9.374891704053596e-07,
+      "loss": 1.1823,
+      "step": 356
+    },
+    {
+      "epoch": 1.4631147540983607,
+      "grad_norm": 0.41889068484306335,
+      "learning_rate": 9.242833723787051e-07,
+      "loss": 1.1872,
+      "step": 357
+    },
+    {
+      "epoch": 1.4672131147540983,
+      "grad_norm": 0.34125325083732605,
+      "learning_rate": 9.111501204762368e-07,
+      "loss": 0.9146,
+      "step": 358
+    },
+    {
+      "epoch": 1.471311475409836,
+      "grad_norm": 0.3865812122821808,
+      "learning_rate": 8.980900193539632e-07,
+      "loss": 1.1993,
+      "step": 359
+    },
+    {
+      "epoch": 1.4754098360655736,
+      "grad_norm": 0.37811699509620667,
+      "learning_rate": 8.851036703000223e-07,
+      "loss": 1.1905,
+      "step": 360
+    },
+    {
+      "epoch": 1.4795081967213115,
+      "grad_norm": 0.3557872772216797,
+      "learning_rate": 8.72191671207e-07,
+      "loss": 0.9251,
+      "step": 361
+    },
+    {
+      "epoch": 1.4836065573770492,
+      "grad_norm": 0.40049198269844055,
+      "learning_rate": 8.593546165444078e-07,
+      "loss": 1.188,
+      "step": 362
+    },
+    {
+      "epoch": 1.4877049180327868,
+      "grad_norm": 0.35006624460220337,
+      "learning_rate": 8.465930973313033e-07,
+      "loss": 0.9116,
+      "step": 363
+    },
+    {
+      "epoch": 1.4918032786885247,
+      "grad_norm": 0.3427639305591583,
+      "learning_rate": 8.339077011090921e-07,
+      "loss": 0.9215,
+      "step": 364
+    },
+    {
+      "epoch": 1.4959016393442623,
+      "grad_norm": 0.38232627511024475,
+      "learning_rate": 8.212990119144662e-07,
+      "loss": 1.1955,
+      "step": 365
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.4133051037788391,
+      "learning_rate": 8.08767610252523e-07,
+      "loss": 1.1938,
+      "step": 366
+    },
+    {
+      "epoch": 1.5040983606557377,
+      "grad_norm": 0.35854944586753845,
+      "learning_rate": 7.963140730700337e-07,
+      "loss": 1.0445,
+      "step": 367
+    },
+    {
+      "epoch": 1.5081967213114753,
+      "grad_norm": 0.3624001741409302,
+      "learning_rate": 7.839389737288816e-07,
+      "loss": 1.0562,
+      "step": 368
+    },
+    {
+      "epoch": 1.512295081967213,
+      "grad_norm": 0.4092054069042206,
+      "learning_rate": 7.716428819796681e-07,
+      "loss": 1.1936,
+      "step": 369
+    },
+    {
+      "epoch": 1.5163934426229508,
+      "grad_norm": 0.4036654829978943,
+      "learning_rate": 7.594263639354757e-07,
+      "loss": 1.1953,
+      "step": 370
+    },
+    {
+      "epoch": 1.5204918032786885,
+      "grad_norm": 0.3745408058166504,
+      "learning_rate": 7.472899820458099e-07,
+      "loss": 1.1882,
+      "step": 371
+    },
+    {
+      "epoch": 1.5245901639344264,
+      "grad_norm": 0.4146348536014557,
+      "learning_rate": 7.352342950706964e-07,
+      "loss": 1.0546,
+      "step": 372
+    },
+    {
+      "epoch": 1.528688524590164,
+      "grad_norm": 0.34985482692718506,
+      "learning_rate": 7.232598580549652e-07,
+      "loss": 1.0361,
+      "step": 373
+    },
+    {
+      "epoch": 1.5327868852459017,
+      "grad_norm": 0.38958367705345154,
+      "learning_rate": 7.113672223026879e-07,
+      "loss": 1.0618,
+      "step": 374
+    },
+    {
+      "epoch": 1.5368852459016393,
+      "grad_norm": 0.3797606825828552,
+      "learning_rate": 6.995569353518025e-07,
+      "loss": 1.1985,
+      "step": 375
+    },
+    {
+      "epoch": 1.540983606557377,
+      "grad_norm": 0.38366222381591797,
+      "learning_rate": 6.878295409488986e-07,
+      "loss": 1.0515,
+      "step": 376
+    },
+    {
+      "epoch": 1.5450819672131146,
+      "grad_norm": 0.36375316977500916,
+      "learning_rate": 6.761855790241858e-07,
+      "loss": 1.0462,
+      "step": 377
+    },
+    {
+      "epoch": 1.5491803278688525,
+      "grad_norm": 0.3730354607105255,
+      "learning_rate": 6.646255856666383e-07,
+      "loss": 1.051,
+      "step": 378
+    },
+    {
+      "epoch": 1.5532786885245902,
+      "grad_norm": 0.4092353880405426,
+      "learning_rate": 6.531500930993081e-07,
+      "loss": 1.044,
+      "step": 379
+    },
+    {
+      "epoch": 1.5573770491803278,
+      "grad_norm": 0.34410029649734497,
+      "learning_rate": 6.417596296548243e-07,
+      "loss": 1.0541,
+      "step": 380
+    },
+    {
+      "epoch": 1.5614754098360657,
+      "grad_norm": 0.39041340351104736,
+      "learning_rate": 6.304547197510677e-07,
+      "loss": 1.1804,
+      "step": 381
+    },
+    {
+      "epoch": 1.5655737704918034,
+      "grad_norm": 0.35463252663612366,
+      "learning_rate": 6.192358838670293e-07,
+      "loss": 1.1851,
+      "step": 382
+    },
+    {
+      "epoch": 1.569672131147541,
+      "grad_norm": 0.3231685161590576,
+      "learning_rate": 6.081036385188424e-07,
+      "loss": 0.7895,
+      "step": 383
+    },
+    {
+      "epoch": 1.5737704918032787,
+      "grad_norm": 0.36696764826774597,
+      "learning_rate": 5.970584962360052e-07,
+      "loss": 1.0495,
+      "step": 384
+    },
+    {
+      "epoch": 1.5778688524590163,
+      "grad_norm": 0.3678134083747864,
+      "learning_rate": 5.861009655377859e-07,
+      "loss": 1.1852,
+      "step": 385
+    },
+    {
+      "epoch": 1.581967213114754,
+      "grad_norm": 0.35735976696014404,
+      "learning_rate": 5.752315509098044e-07,
+      "loss": 1.0428,
+      "step": 386
+    },
+    {
+      "epoch": 1.5860655737704918,
+      "grad_norm": 0.4014861285686493,
+      "learning_rate": 5.644507527808135e-07,
+      "loss": 1.1817,
+      "step": 387
+    },
+    {
+      "epoch": 1.5901639344262295,
+      "grad_norm": 0.3189600706100464,
+      "learning_rate": 5.537590674996521e-07,
+      "loss": 0.9228,
+      "step": 388
+    },
+    {
+      "epoch": 1.5942622950819674,
+      "grad_norm": 0.3636609613895416,
+      "learning_rate": 5.431569873123965e-07,
+      "loss": 1.0466,
+      "step": 389
+    },
+    {
+      "epoch": 1.598360655737705,
+      "grad_norm": 0.33342039585113525,
+      "learning_rate": 5.326450003396977e-07,
+      "loss": 0.9119,
+      "step": 390
+    },
+    {
+      "epoch": 1.6024590163934427,
+      "grad_norm": 0.31864428520202637,
+      "learning_rate": 5.222235905543083e-07,
+      "loss": 0.9298,
+      "step": 391
+    },
+    {
+      "epoch": 1.6065573770491803,
+      "grad_norm": 0.38250261545181274,
+      "learning_rate": 5.118932377587984e-07,
+      "loss": 1.1875,
+      "step": 392
+    },
+    {
+      "epoch": 1.610655737704918,
+      "grad_norm": 0.36248064041137695,
+      "learning_rate": 5.016544175634669e-07,
+      "loss": 1.0468,
+      "step": 393
+    },
+    {
+      "epoch": 1.6147540983606556,
+      "grad_norm": 0.39731329679489136,
+      "learning_rate": 4.915076013644454e-07,
+      "loss": 1.196,
+      "step": 394
+    },
+    {
+      "epoch": 1.6188524590163933,
+      "grad_norm": 0.3571957051753998,
+      "learning_rate": 4.814532563219921e-07,
+      "loss": 1.0512,
+      "step": 395
+    },
+    {
+      "epoch": 1.6229508196721312,
+      "grad_norm": 0.34423011541366577,
+      "learning_rate": 4.714918453389875e-07,
+      "loss": 0.9108,
+      "step": 396
+    },
+    {
+      "epoch": 1.6270491803278688,
+      "grad_norm": 0.3421591520309448,
+      "learning_rate": 4.6162382703961836e-07,
+      "loss": 1.0536,
+      "step": 397
+    },
+    {
+      "epoch": 1.6311475409836067,
+      "grad_norm": 0.3798050284385681,
+      "learning_rate": 4.51849655748266e-07,
+      "loss": 1.188,
+      "step": 398
+    },
+    {
+      "epoch": 1.6352459016393444,
+      "grad_norm": 0.36641448736190796,
+      "learning_rate": 4.421697814685869e-07,
+      "loss": 1.1898,
+      "step": 399
+    },
+    {
+      "epoch": 1.639344262295082,
+      "grad_norm": 0.3719433844089508,
+      "learning_rate": 4.325846498627945e-07,
+      "loss": 1.1861,
+      "step": 400
+    },
+    {
+      "epoch": 1.6434426229508197,
+      "grad_norm": 0.35947632789611816,
+      "learning_rate": 4.230947022311441e-07,
+      "loss": 1.1754,
+      "step": 401
+    },
+    {
+      "epoch": 1.6475409836065573,
+      "grad_norm": 0.44209569692611694,
+      "learning_rate": 4.137003754916105e-07,
+      "loss": 1.189,
+      "step": 402
+    },
+    {
+      "epoch": 1.651639344262295,
+      "grad_norm": 0.2977343797683716,
+      "learning_rate": 4.044021021597769e-07,
+      "loss": 0.7746,
+      "step": 403
+    },
+    {
+      "epoch": 1.6557377049180326,
+      "grad_norm": 0.3610956370830536,
+      "learning_rate": 3.952003103289179e-07,
+      "loss": 1.1821,
+      "step": 404
+    },
+    {
+      "epoch": 1.6598360655737705,
+      "grad_norm": 0.37780749797821045,
+      "learning_rate": 3.8609542365029146e-07,
+      "loss": 1.0457,
+      "step": 405
+    },
+    {
+      "epoch": 1.6639344262295082,
+      "grad_norm": 0.38885119557380676,
+      "learning_rate": 3.770878613136372e-07,
+      "loss": 1.1997,
+      "step": 406
+    },
+    {
+      "epoch": 1.668032786885246,
+      "grad_norm": 0.3951539397239685,
+      "learning_rate": 3.681780380278696e-07,
+      "loss": 1.1919,
+      "step": 407
+    },
+    {
+      "epoch": 1.6721311475409837,
+      "grad_norm": 0.3688086271286011,
+      "learning_rate": 3.5936636400199313e-07,
+      "loss": 1.0473,
+      "step": 408
+    },
+    {
+      "epoch": 1.6762295081967213,
+      "grad_norm": 0.3443498909473419,
+      "learning_rate": 3.506532449262098e-07,
+      "loss": 0.9097,
+      "step": 409
+    },
+    {
+      "epoch": 1.680327868852459,
+      "grad_norm": 0.37763506174087524,
+      "learning_rate": 3.4203908195324486e-07,
+      "loss": 1.1979,
+      "step": 410
+    },
+    {
+      "epoch": 1.6844262295081966,
+      "grad_norm": 0.34643036127090454,
+      "learning_rate": 3.3352427167987536e-07,
+      "loss": 1.0504,
+      "step": 411
+    },
+    {
+      "epoch": 1.6885245901639343,
+      "grad_norm": 0.33650776743888855,
+      "learning_rate": 3.2510920612867284e-07,
+      "loss": 0.9052,
+      "step": 412
+    },
+    {
+      "epoch": 1.6926229508196722,
+      "grad_norm": 0.35390788316726685,
+      "learning_rate": 3.1679427272995304e-07,
+      "loss": 1.0437,
+      "step": 413
+    },
+    {
+      "epoch": 1.6967213114754098,
+      "grad_norm": 0.3367477357387543,
+      "learning_rate": 3.0857985430393837e-07,
+      "loss": 1.0315,
+      "step": 414
+    },
+    {
+      "epoch": 1.7008196721311475,
+      "grad_norm": 0.35534176230430603,
+      "learning_rate": 3.004663290431348e-07,
+      "loss": 0.9072,
+      "step": 415
+    },
+    {
+      "epoch": 1.7049180327868854,
+      "grad_norm": 0.3314175307750702,
+      "learning_rate": 2.924540704949175e-07,
+      "loss": 1.045,
+      "step": 416
+    },
+    {
+      "epoch": 1.709016393442623,
+      "grad_norm": 0.3758045434951782,
+      "learning_rate": 2.845434475443351e-07,
+      "loss": 1.1899,
+      "step": 417
+    },
+    {
+      "epoch": 1.7131147540983607,
+      "grad_norm": 0.35300490260124207,
+      "learning_rate": 2.767348243971235e-07,
+      "loss": 1.1793,
+      "step": 418
+    },
+    {
+      "epoch": 1.7172131147540983,
+      "grad_norm": 0.3697493374347687,
+      "learning_rate": 2.6902856056294057e-07,
+      "loss": 1.2013,
+      "step": 419
+    },
+    {
+      "epoch": 1.721311475409836,
+      "grad_norm": 0.3522683084011078,
+      "learning_rate": 2.6142501083881195e-07,
+      "loss": 1.0652,
+      "step": 420
+    },
+    {
+      "epoch": 1.7254098360655736,
+      "grad_norm": 0.37219488620758057,
+      "learning_rate": 2.539245252927969e-07,
+      "loss": 1.1923,
+      "step": 421
+    },
+    {
+      "epoch": 1.7295081967213115,
+      "grad_norm": 0.3900905251502991,
+      "learning_rate": 2.4652744924787253e-07,
+      "loss": 1.1957,
+      "step": 422
+    },
+    {
+      "epoch": 1.7336065573770492,
+      "grad_norm": 0.334423303604126,
+      "learning_rate": 2.3923412326603307e-07,
+      "loss": 0.9102,
+      "step": 423
+    },
+    {
+      "epoch": 1.737704918032787,
+      "grad_norm": 0.3214561641216278,
+      "learning_rate": 2.3204488313261136e-07,
+      "loss": 0.926,
+      "step": 424
+    },
+    {
+      "epoch": 1.7418032786885247,
+      "grad_norm": 0.36900636553764343,
+      "learning_rate": 2.2496005984081887e-07,
+      "loss": 1.1893,
+      "step": 425
+    },
+    {
+      "epoch": 1.7459016393442623,
+      "grad_norm": 0.3153081238269806,
+      "learning_rate": 2.1797997957650807e-07,
+      "loss": 0.907,
+      "step": 426
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.3328554630279541,
+      "learning_rate": 2.1110496370315258e-07,
+      "loss": 0.9161,
+      "step": 427
+    },
+    {
+      "epoch": 1.7540983606557377,
+      "grad_norm": 0.3190460801124573,
+      "learning_rate": 2.0433532874705369e-07,
+      "loss": 0.9164,
+      "step": 428
+    },
+    {
+      "epoch": 1.7581967213114753,
+      "grad_norm": 0.3754616379737854,
+      "learning_rate": 1.9767138638276616e-07,
+      "loss": 1.1885,
+      "step": 429
+    },
+    {
+      "epoch": 1.762295081967213,
+      "grad_norm": 0.36980029940605164,
+      "learning_rate": 1.911134434187481e-07,
+      "loss": 1.1848,
+      "step": 430
+    },
+    {
+      "epoch": 1.7663934426229508,
+      "grad_norm": 0.37450385093688965,
+      "learning_rate": 1.8466180178323856e-07,
+      "loss": 1.1975,
+      "step": 431
+    },
+    {
+      "epoch": 1.7704918032786885,
+      "grad_norm": 0.3627603054046631,
+      "learning_rate": 1.7831675851035264e-07,
+      "loss": 1.0433,
+      "step": 432
+    },
+    {
+      "epoch": 1.7745901639344264,
+      "grad_norm": 0.37861618399620056,
+      "learning_rate": 1.7207860572640872e-07,
+      "loss": 1.1866,
+      "step": 433
+    },
+    {
+      "epoch": 1.778688524590164,
+      "grad_norm": 0.33325180411338806,
+      "learning_rate": 1.6594763063647822e-07,
+      "loss": 1.0378,
+      "step": 434
+    },
+    {
+      "epoch": 1.7827868852459017,
+      "grad_norm": 0.35680869221687317,
+      "learning_rate": 1.5992411551116304e-07,
+      "loss": 1.1838,
+      "step": 435
+    },
+    {
+      "epoch": 1.7868852459016393,
+      "grad_norm": 0.3443697690963745,
+      "learning_rate": 1.5400833767359847e-07,
+      "loss": 1.0466,
+      "step": 436
+    },
+    {
+      "epoch": 1.790983606557377,
+      "grad_norm": 0.32265111804008484,
+      "learning_rate": 1.482005694866867e-07,
+      "loss": 0.9085,
+      "step": 437
+    },
+    {
+      "epoch": 1.7950819672131146,
+      "grad_norm": 0.3619065582752228,
+      "learning_rate": 1.4250107834055725e-07,
+      "loss": 1.0399,
+      "step": 438
+    },
+    {
+      "epoch": 1.7991803278688525,
+      "grad_norm": 0.34738269448280334,
+      "learning_rate": 1.369101266402545e-07,
+      "loss": 0.9015,
+      "step": 439
+    },
+    {
+      "epoch": 1.8032786885245902,
+      "grad_norm": 0.33382171392440796,
+      "learning_rate": 1.3142797179365868e-07,
+      "loss": 0.9155,
+      "step": 440
+    },
+    {
+      "epoch": 1.8073770491803278,
+      "grad_norm": 0.36321792006492615,
+      "learning_rate": 1.2605486619963276e-07,
+      "loss": 1.193,
+      "step": 441
+    },
+    {
+      "epoch": 1.8114754098360657,
+      "grad_norm": 0.3667308986186981,
+      "learning_rate": 1.207910572364046e-07,
+      "loss": 1.173,
+      "step": 442
+    },
+    {
+      "epoch": 1.8155737704918034,
+      "grad_norm": 0.3402903974056244,
+      "learning_rate": 1.1563678725017513e-07,
+      "loss": 1.0647,
+      "step": 443
+    },
+    {
+      "epoch": 1.819672131147541,
+      "grad_norm": 0.34336400032043457,
+      "learning_rate": 1.1059229354396128e-07,
+      "loss": 1.0459,
+      "step": 444
+    },
+    {
+      "epoch": 1.8237704918032787,
+      "grad_norm": 0.3510723412036896,
+      "learning_rate": 1.056578083666726e-07,
+      "loss": 1.0441,
+      "step": 445
+    },
+    {
+      "epoch": 1.8278688524590163,
+      "grad_norm": 0.3598317801952362,
+      "learning_rate": 1.008335589024148e-07,
+      "loss": 1.0563,
+      "step": 446
+    },
+    {
+      "epoch": 1.831967213114754,
+      "grad_norm": 0.3661951422691345,
+      "learning_rate": 9.611976726003392e-08,
+      "loss": 1.1879,
+      "step": 447
+    },
+    {
+      "epoch": 1.8360655737704918,
+      "grad_norm": 0.3591423034667969,
+      "learning_rate": 9.151665046288727e-08,
+      "loss": 1.1889,
+      "step": 448
+    },
+    {
+      "epoch": 1.8401639344262295,
+      "grad_norm": 0.37362557649612427,
+      "learning_rate": 8.702442043885512e-08,
+      "loss": 1.1838,
+      "step": 449
+    },
+    {
+      "epoch": 1.8442622950819674,
+      "grad_norm": 0.35810065269470215,
+      "learning_rate": 8.264328401057897e-08,
+      "loss": 1.1907,
+      "step": 450
+    },
+    {
+      "epoch": 1.848360655737705,
+      "grad_norm": 0.36946335434913635,
+      "learning_rate": 7.837344288594395e-08,
+      "loss": 1.1866,
+      "step": 451
+    },
+    {
+      "epoch": 1.8524590163934427,
+      "grad_norm": 0.346340537071228,
+      "learning_rate": 7.421509364878927e-08,
+      "loss": 1.0539,
+      "step": 452
+    },
+    {
+      "epoch": 1.8565573770491803,
+      "grad_norm": 0.3482150733470917,
+      "learning_rate": 7.016842774985821e-08,
+      "loss": 1.1901,
+      "step": 453
+    },
+    {
+      "epoch": 1.860655737704918,
+      "grad_norm": 0.33978191018104553,
+      "learning_rate": 6.623363149798529e-08,
+      "loss": 1.0597,
+      "step": 454
+    },
+    {
+      "epoch": 1.8647540983606556,
+      "grad_norm": 0.32557353377342224,
+      "learning_rate": 6.241088605151518e-08,
+      "loss": 0.9112,
+      "step": 455
+    },
+    {
+      "epoch": 1.8688524590163933,
+      "grad_norm": 0.3608950674533844,
+      "learning_rate": 5.870036740996565e-08,
+      "loss": 1.1979,
+      "step": 456
+    },
+    {
+      "epoch": 1.8729508196721312,
+      "grad_norm": 0.3571400046348572,
+      "learning_rate": 5.5102246405922823e-08,
+      "loss": 1.0464,
+      "step": 457
+    },
+    {
+      "epoch": 1.8770491803278688,
+      "grad_norm": 0.33007898926734924,
+      "learning_rate": 5.161668869717584e-08,
+      "loss": 0.92,
+      "step": 458
+    },
+    {
+      "epoch": 1.8811475409836067,
+      "grad_norm": 0.30745700001716614,
+      "learning_rate": 4.824385475909049e-08,
+      "loss": 0.908,
+      "step": 459
+    },
+    {
+      "epoch": 1.8852459016393444,
+      "grad_norm": 0.3910124897956848,
+      "learning_rate": 4.49838998772209e-08,
+      "loss": 1.1883,
+      "step": 460
+    },
+    {
+      "epoch": 1.889344262295082,
+      "grad_norm": 0.35443976521492004,
+      "learning_rate": 4.183697414016058e-08,
+      "loss": 1.198,
+      "step": 461
+    },
+    {
+      "epoch": 1.8934426229508197,
+      "grad_norm": 0.2877008616924286,
+      "learning_rate": 3.8803222432630685e-08,
+      "loss": 0.7777,
+      "step": 462
+    },
+    {
+      "epoch": 1.8975409836065573,
+      "grad_norm": 0.3574839234352112,
+      "learning_rate": 3.5882784428812324e-08,
+      "loss": 1.1775,
+      "step": 463
+    },
+    {
+      "epoch": 1.901639344262295,
+      "grad_norm": 0.34388306736946106,
+      "learning_rate": 3.3075794585912534e-08,
+      "loss": 1.0463,
+      "step": 464
+    },
+    {
+      "epoch": 1.9057377049180326,
+      "grad_norm": 0.3502333164215088,
+      "learning_rate": 3.038238213797673e-08,
+      "loss": 1.0559,
+      "step": 465
+    },
+    {
+      "epoch": 1.9098360655737705,
+      "grad_norm": 0.33753618597984314,
+      "learning_rate": 2.7802671089937338e-08,
+      "loss": 0.9013,
+      "step": 466
+    },
+    {
+      "epoch": 1.9139344262295082,
+      "grad_norm": 0.3773573338985443,
+      "learning_rate": 2.5336780211905055e-08,
+      "loss": 1.1903,
+      "step": 467
+    },
+    {
+      "epoch": 1.918032786885246,
+      "grad_norm": 0.3575388491153717,
+      "learning_rate": 2.2984823033700142e-08,
+      "loss": 1.0461,
+      "step": 468
+    },
+    {
+      "epoch": 1.9221311475409837,
+      "grad_norm": 0.3283044099807739,
+      "learning_rate": 2.0746907839626075e-08,
+      "loss": 1.0457,
+      "step": 469
+    },
+    {
+      "epoch": 1.9262295081967213,
+      "grad_norm": 0.36623239517211914,
+      "learning_rate": 1.862313766348406e-08,
+      "loss": 1.1883,
+      "step": 470
+    },
+    {
+      "epoch": 1.930327868852459,
+      "grad_norm": 0.5590834617614746,
+      "learning_rate": 1.6613610283828797e-08,
+      "loss": 1.1851,
+      "step": 471
+    },
+    {
+      "epoch": 1.9344262295081966,
+      "grad_norm": 0.3764868378639221,
+      "learning_rate": 1.4718418219468178e-08,
+      "loss": 1.1829,
+      "step": 472
+    },
+    {
+      "epoch": 1.9385245901639343,
+      "grad_norm": 0.33510729670524597,
+      "learning_rate": 1.2937648725201424e-08,
+      "loss": 1.0685,
+      "step": 473
+    },
+    {
+      "epoch": 1.9426229508196722,
+      "grad_norm": 0.34146928787231445,
+      "learning_rate": 1.127138378780368e-08,
+      "loss": 1.0389,
+      "step": 474
+    },
+    {
+      "epoch": 1.9467213114754098,
+      "grad_norm": 0.33086708188056946,
+      "learning_rate": 9.719700122250985e-09,
+      "loss": 1.0417,
+      "step": 475
+    },
+    {
+      "epoch": 1.9508196721311475,
+      "grad_norm": 0.38524767756462097,
+      "learning_rate": 8.282669168188095e-09,
+      "loss": 1.1932,
+      "step": 476
+    },
+    {
+      "epoch": 1.9549180327868854,
+      "grad_norm": 0.3176893889904022,
+      "learning_rate": 6.960357086639169e-09,
+      "loss": 0.9165,
+      "step": 477
+    },
+    {
+      "epoch": 1.959016393442623,
+      "grad_norm": 0.40208250284194946,
+      "learning_rate": 5.752824756961872e-09,
+      "loss": 1.1892,
+      "step": 478
+    },
+    {
+      "epoch": 1.9631147540983607,
+      "grad_norm": 0.3620227575302124,
+      "learning_rate": 4.660127774045175e-09,
+      "loss": 1.0402,
+      "step": 479
+    },
+    {
+      "epoch": 1.9672131147540983,
+      "grad_norm": 0.3547709882259369,
+      "learning_rate": 3.682316445748346e-09,
+      "loss": 1.1752,
+      "step": 480
+    },
+    {
+      "epoch": 1.971311475409836,
+      "grad_norm": 0.3593614101409912,
+      "learning_rate": 2.819435790586411e-09,
+      "loss": 1.074,
+      "step": 481
+    },
+    {
+      "epoch": 1.9754098360655736,
+      "grad_norm": 0.3166957497596741,
+      "learning_rate": 2.0715255356559826e-09,
+      "loss": 0.9169,
+      "step": 482
+    },
+    {
+      "epoch": 1.9795081967213115,
+      "grad_norm": 0.3417866826057434,
+      "learning_rate": 1.4386201148072766e-09,
+      "loss": 1.1867,
+      "step": 483
+    },
+    {
+      "epoch": 1.9836065573770492,
+      "grad_norm": 0.3376613259315491,
+      "learning_rate": 9.20748667058713e-10,
+      "loss": 1.0687,
+      "step": 484
+    },
+    {
+      "epoch": 1.987704918032787,
+      "grad_norm": 0.332938015460968,
+      "learning_rate": 5.179350352541024e-10,
+      "loss": 1.0354,
+      "step": 485
+    },
+    {
+      "epoch": 1.9918032786885247,
+      "grad_norm": 0.3657640218734741,
+      "learning_rate": 2.301977649668552e-10,
+      "loss": 1.1871,
+      "step": 486
+    },
+    {
+      "epoch": 1.9959016393442623,
+      "grad_norm": 0.3668140769004822,
+      "learning_rate": 5.755010364455471e-11,
+      "loss": 1.1814,
+      "step": 487
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.36807963252067566,
+      "learning_rate": 0.0,
+      "loss": 1.177,
+      "step": 488
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 488,
+  "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": 1.5344105028163994e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-488/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1442da29a240f20215228cffff3361298a33ab5abeefe41f06e0ac3cf92d4f74
+size 5752