70B

70B/ft_70B_gpt4_v2_lr5e-6_0/.gitattributes

@@ -0,0 +1 @@
+*.safetensor filter=lfs diff=lfs merge=lfs -text

70B/ft_70B_gpt4_v2_lr5e-6_0/README.md

@@ -0,0 +1,58 @@
+---
+base_model: /nfshome/.cache/huggingface/hub/models--meta-llama--Llama-2-70b-hf/snapshots/90052941a64de02075ca800b09fcea1bdaacb939
+tags:
+- generated_from_trainer
+datasets:
+- customized
+model-index:
+- name: ft_70B_gpt4_v2_lr5e-6_0
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# ft_70B_gpt4_v2_lr5e-6_0
+
+This model is a fine-tuned version of [/nfshome/.cache/huggingface/hub/models--meta-llama--Llama-2-70b-hf/snapshots/90052941a64de02075ca800b09fcea1bdaacb939](https://huggingface.co//nfshome/.cache/huggingface/hub/models--meta-llama--Llama-2-70b-hf/snapshots/90052941a64de02075ca800b09fcea1bdaacb939) on the customized dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 8
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.0.dev0
+- Pytorch 2.0.0+cu117
+- Datasets 2.16.1
+- Tokenizers 0.15.1

70B/ft_70B_gpt4_v2_lr5e-6_0/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.815405089325375,
+    "train_runtime": 68079.5988,
+    "train_samples": 48917,
+    "train_samples_per_second": 0.719,
+    "train_steps_per_second": 0.011
+}

70B/ft_70B_gpt4_v2_lr5e-6_0/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/nfshome/.cache/huggingface/hub/models--meta-llama--Llama-2-70b-hf/snapshots/90052941a64de02075ca800b09fcea1bdaacb939",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

70B/ft_70B_gpt4_v2_lr5e-6_0/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.38.0.dev0"
+}

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8ac09dbb8d493c0d9440f5f7c5b74bdb147a6db23972306d8e3c1e30611b3b
+size 4718660336

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8662d42937e8c4811cce11d6a08f1f9eba631f3fea884f24bb3ab7c6d3079341
+size 4664167376

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13384240d52d7795ae4d874defb11d93d9216989a934dc88d45606cd1fd310f3
+size 4999711704

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03b5506d48263d90f466944053eba8deef1a9d4f35de072d0fc5ff6e40d0791b
+size 4966157048

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4ff82ec9bb637af0b0f03aedb980ee3b5ae4b71d7902a4b9cb9341674cb753
+size 4664134408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9179e69c9254b990d35d353c37df0095f649e475270adc60e5224ecc6533c010
+size 4664167408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:723c10c09d03ad6b14fcef8c81d8f9771aabf74810c56f6fef05297329a71090
+size 4664167408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:324efa9117306c82840132940a503239d757b8a2577058ffd3c981eb048cf15b
+size 4999711728

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7edbb68c1c4a7a654fa733677c7c4e6fbe22d8eae4cd8de0d4ca0a1230db47d6
+size 4966157056

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2c58d6c90e2edf122e21f8b9a64c5ae64072ad01bb77aa1f2f0c807a35f3b96
+size 4664134408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba4edfe79c23845a91f4cd1b99e332c453b8837c9e087283f7658d6c2bc690f5
+size 4664167408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5c57ecc3567e8bbb215691f941075f6be89d3dea08225a10213301a5e8edfdb
+size 4664167408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e899604bda25be84574eea6e624ce3a2d62e310390caf0f1dfd80b60e43c3c3e
+size 4999711728

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5fd95469e858f1e55f0569db80ae87528123957d4e0c4cfa6bd600a46fa7b32
+size 4966157056

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:320ac0530cdeef56b7870cda94454029abda71fb4556465f22202ab5400dc0d7
+size 4664134408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:444e843e51fb84a5cbdf3d6699bab701e594b585f29c1e60de6984b896ef3209
+size 4664167408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3319f8ffb8b33815d2ba1066dd241cb57e224f36aeebe449f770bab2386498f6
+size 4664167408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffb40a1d39f07ed62bbe2c01d0ddc0bb28bfbde91a501a6cc119a7cc654011c
+size 4999711728

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0020661af6a6fb6dc9819a2b2cd34767c0c6ece6e83fb612dbec633f90770174
+size 4966157056

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6307586cd8dd0a79645be5e1e68d8ae65baa11f74b1662f85498846e8fe804f
+size 4664134408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d8869129734586e5c5cfd4ac0055f7566e6ac368eea7edfdb9f1aa5b58c9a9
+size 4664167408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53899b2e6c824cb738387797b84cd877f5bbeab539aef16a8db7a2fc08944068
+size 4664167408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26fc23a9381863cb593f43efad0a4db2a1aafa1b8f56a7d3485d685d21612c4a
+size 4999711728

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0abe7217424d800785a015059b7ed97b43ab5d130b97e5fff78bd9ba31cadda5
+size 4966157056

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745f75a61c612f424a587e53682c298c8b21a8ad8a9c1b84e6d8aad7b57032c7
+size 4664134408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3500f668677ea81061b2d16ea025108b43fe37c35ac8543b054896b875eeef43
+size 4664167408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c8b2bf0751418317311c90fbe9f5723a2807cb31b8c11358d669052fc9ca26f
+size 4664167408

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:709b8c4cc9dd7165a8eb7119f6a8461d590fac35ba02ac0c195de0448c3d2ff8
+size 4999711728

70B/ft_70B_gpt4_v2_lr5e-6_0/model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdaf00e8eaef6e52dd2038fd7474cf37f1a3fb6267018d1727cea215b4675e04
+size 3779151784

70B/ft_70B_gpt4_v2_lr5e-6_0/model.safetensors.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 137953296384
+  },
+  "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-00001-of-00029.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-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-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.weight": "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-00001-of-00029.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-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-00001-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.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "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.weight": "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-00012-of-00029.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.norm.weight": "model-00029-of-00029.safetensors"
+  }
+}

70B/ft_70B_gpt4_v2_lr5e-6_0/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

70B/ft_70B_gpt4_v2_lr5e-6_0/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

70B/ft_70B_gpt4_v2_lr5e-6_0/tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

70B/ft_70B_gpt4_v2_lr5e-6_0/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.815405089325375,
+    "train_runtime": 68079.5988,
+    "train_samples": 48917,
+    "train_samples_per_second": 0.719,
+    "train_steps_per_second": 0.011
+}

70B/ft_70B_gpt4_v2_lr5e-6_0/trainer_state.json

@@ -0,0 +1,4620 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50.0,
+  "global_step": 765,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 1.1945,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.248277861430049e-07,
+      "loss": 1.182,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.2496555722860098e-06,
+      "loss": 1.19,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.8744833584290148e-06,
+      "loss": 1.176,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4993111445720197e-06,
+      "loss": 1.1374,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.1241389307150244e-06,
+      "loss": 1.165,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.7489667168580295e-06,
+      "loss": 1.1013,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.373794503001035e-06,
+      "loss": 1.0501,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-06,
+      "loss": 1.0721,
+      "step": 9
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.99997891923933e-06,
+      "loss": 0.9498,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.999915677312839e-06,
+      "loss": 0.9165,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.999810275287077e-06,
+      "loss": 0.9485,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9996627149396075e-06,
+      "loss": 0.906,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.999472998758979e-06,
+      "loss": 0.8926,
+      "step": 14
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.99924112994468e-06,
+      "loss": 0.8937,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.998967112407087e-06,
+      "loss": 0.8994,
+      "step": 16
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9986509507673986e-06,
+      "loss": 0.8768,
+      "step": 17
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.998292650357558e-06,
+      "loss": 0.8871,
+      "step": 18
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.99789221722016e-06,
+      "loss": 0.9122,
+      "step": 19
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.997449658108354e-06,
+      "loss": 0.8588,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.996964980485725e-06,
+      "loss": 0.8706,
+      "step": 21
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.996438192526173e-06,
+      "loss": 0.8988,
+      "step": 22
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.995869303113768e-06,
+      "loss": 0.9065,
+      "step": 23
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.995258321842611e-06,
+      "loss": 0.9069,
+      "step": 24
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.994605259016658e-06,
+      "loss": 0.8923,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.993910125649561e-06,
+      "loss": 0.8726,
+      "step": 26
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.99317293346447e-06,
+      "loss": 0.8234,
+      "step": 27
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.992393694893844e-06,
+      "loss": 0.8859,
+      "step": 28
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.991572423079236e-06,
+      "loss": 0.8919,
+      "step": 29
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.990709131871074e-06,
+      "loss": 0.8541,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.989803835828426e-06,
+      "loss": 0.8407,
+      "step": 31
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.988856550218755e-06,
+      "loss": 0.8568,
+      "step": 32
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.987867291017662e-06,
+      "loss": 0.8741,
+      "step": 33
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.986836074908616e-06,
+      "loss": 0.8312,
+      "step": 34
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.985762919282674e-06,
+      "loss": 0.8424,
+      "step": 35
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.984647842238185e-06,
+      "loss": 0.8613,
+      "step": 36
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.983490862580486e-06,
+      "loss": 0.8548,
+      "step": 37
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.982291999821587e-06,
+      "loss": 0.8567,
+      "step": 38
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.98105127417984e-06,
+      "loss": 0.8602,
+      "step": 39
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.979768706579595e-06,
+      "loss": 0.8817,
+      "step": 40
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.978444318650855e-06,
+      "loss": 0.8299,
+      "step": 41
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.977078132728901e-06,
+      "loss": 0.8838,
+      "step": 42
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.975670171853926e-06,
+      "loss": 0.8837,
+      "step": 43
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9742204597706386e-06,
+      "loss": 0.8531,
+      "step": 44
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.972729020927866e-06,
+      "loss": 0.8366,
+      "step": 45
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9711958804781385e-06,
+      "loss": 0.8635,
+      "step": 46
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.969621064277271e-06,
+      "loss": 0.8756,
+      "step": 47
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.968004598883923e-06,
+      "loss": 0.8553,
+      "step": 48
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.966346511559149e-06,
+      "loss": 0.8263,
+      "step": 49
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.964646830265944e-06,
+      "loss": 0.8609,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.962905583668766e-06,
+      "loss": 0.8367,
+      "step": 51
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.961122801133059e-06,
+      "loss": 0.872,
+      "step": 52
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9592985127247525e-06,
+      "loss": 0.845,
+      "step": 53
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.957432749209755e-06,
+      "loss": 0.8254,
+      "step": 54
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.955525542053438e-06,
+      "loss": 0.8759,
+      "step": 55
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.953576923420105e-06,
+      "loss": 0.8704,
+      "step": 56
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9515869261724444e-06,
+      "loss": 0.8489,
+      "step": 57
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.949555583870983e-06,
+      "loss": 0.8762,
+      "step": 58
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.9474829307735115e-06,
+      "loss": 0.8042,
+      "step": 59
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.9453690018345144e-06,
+      "loss": 0.83,
+      "step": 60
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.943213832704575e-06,
+      "loss": 0.8321,
+      "step": 61
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.941017459729778e-06,
+      "loss": 0.8162,
+      "step": 62
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.938779919951092e-06,
+      "loss": 0.8619,
+      "step": 63
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.936501251103751e-06,
+      "loss": 0.8518,
+      "step": 64
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.934181491616613e-06,
+      "loss": 0.8212,
+      "step": 65
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.9318206806115125e-06,
+      "loss": 0.8061,
+      "step": 66
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.929418857902603e-06,
+      "loss": 0.8626,
+      "step": 67
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.926976063995687e-06,
+      "loss": 0.8434,
+      "step": 68
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.9244923400875245e-06,
+      "loss": 0.8621,
+      "step": 69
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.921967728065147e-06,
+      "loss": 0.8088,
+      "step": 70
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.91940227050515e-06,
+      "loss": 0.8554,
+      "step": 71
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.916796010672969e-06,
+      "loss": 0.8375,
+      "step": 72
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.914148992522157e-06,
+      "loss": 0.838,
+      "step": 73
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.911461260693639e-06,
+      "loss": 0.8748,
+      "step": 74
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.908732860514958e-06,
+      "loss": 0.8368,
+      "step": 75
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.905963837999518e-06,
+      "loss": 0.8333,
+      "step": 76
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.903154239845798e-06,
+      "loss": 0.8484,
+      "step": 77
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.90030411343657e-06,
+      "loss": 0.8648,
+      "step": 78
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.897413506838103e-06,
+      "loss": 0.8299,
+      "step": 79
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.894482468799344e-06,
+      "loss": 0.8596,
+      "step": 80
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.891511048751102e-06,
+      "loss": 0.8589,
+      "step": 81
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.888499296805214e-06,
+      "loss": 0.8463,
+      "step": 82
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.8854472637536966e-06,
+      "loss": 0.8647,
+      "step": 83
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.882355001067892e-06,
+      "loss": 0.8378,
+      "step": 84
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.8792225608976e-06,
+      "loss": 0.8364,
+      "step": 85
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.8760499960702005e-06,
+      "loss": 0.8515,
+      "step": 86
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.8728373600897535e-06,
+      "loss": 0.8375,
+      "step": 87
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.869584707136109e-06,
+      "loss": 0.8338,
+      "step": 88
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.8662920920639866e-06,
+      "loss": 0.8454,
+      "step": 89
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.86295957040205e-06,
+      "loss": 0.8555,
+      "step": 90
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.8595871983519705e-06,
+      "loss": 0.8456,
+      "step": 91
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.856175032787485e-06,
+      "loss": 0.829,
+      "step": 92
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.852723131253429e-06,
+      "loss": 0.8181,
+      "step": 93
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.849231551964771e-06,
+      "loss": 0.8806,
+      "step": 94
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.845700353805629e-06,
+      "loss": 0.8187,
+      "step": 95
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.842129596328277e-06,
+      "loss": 0.7919,
+      "step": 96
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.838519339752143e-06,
+      "loss": 0.817,
+      "step": 97
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.834869644962789e-06,
+      "loss": 0.8448,
+      "step": 98
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.83118057351089e-06,
+      "loss": 0.8296,
+      "step": 99
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.827452187611192e-06,
+      "loss": 0.8281,
+      "step": 100
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.823684550141464e-06,
+      "loss": 0.8399,
+      "step": 101
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.819877724641437e-06,
+      "loss": 0.8505,
+      "step": 102
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.8160317753117326e-06,
+      "loss": 0.8776,
+      "step": 103
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.81214676701278e-06,
+      "loss": 0.8624,
+      "step": 104
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.808222765263724e-06,
+      "loss": 0.8449,
+      "step": 105
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.8042598362413175e-06,
+      "loss": 0.8485,
+      "step": 106
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.800258046778809e-06,
+      "loss": 0.7915,
+      "step": 107
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.796217464364808e-06,
+      "loss": 0.8309,
+      "step": 108
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.792138157142158e-06,
+      "loss": 0.8201,
+      "step": 109
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.788020193906776e-06,
+      "loss": 0.8607,
+      "step": 110
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.783863644106502e-06,
+      "loss": 0.8454,
+      "step": 111
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.779668577839921e-06,
+      "loss": 0.8202,
+      "step": 112
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.775435065855183e-06,
+      "loss": 0.8395,
+      "step": 113
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.77116317954881e-06,
+      "loss": 0.8288,
+      "step": 114
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.766852990964492e-06,
+      "loss": 0.845,
+      "step": 115
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.762504572791873e-06,
+      "loss": 0.838,
+      "step": 116
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.7581179983653224e-06,
+      "loss": 0.8471,
+      "step": 117
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.753693341662702e-06,
+      "loss": 0.8008,
+      "step": 118
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.749230677304113e-06,
+      "loss": 0.8276,
+      "step": 119
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.7447300805506455e-06,
+      "loss": 0.8417,
+      "step": 120
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.7401916273031e-06,
+      "loss": 0.8343,
+      "step": 121
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.7356153941007145e-06,
+      "loss": 0.8042,
+      "step": 122
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.73100145811987e-06,
+      "loss": 0.8382,
+      "step": 123
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.726349897172791e-06,
+      "loss": 0.8674,
+      "step": 124
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.721660789706232e-06,
+      "loss": 0.832,
+      "step": 125
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.716934214800155e-06,
+      "loss": 0.8485,
+      "step": 126
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.712170252166395e-06,
+      "loss": 0.8158,
+      "step": 127
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.707368982147318e-06,
+      "loss": 0.8644,
+      "step": 128
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.702530485714462e-06,
+      "loss": 0.8013,
+      "step": 129
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.697654844467175e-06,
+      "loss": 0.8645,
+      "step": 130
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.69274214063124e-06,
+      "loss": 0.8323,
+      "step": 131
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.687792457057482e-06,
+      "loss": 0.8711,
+      "step": 132
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.682805877220378e-06,
+      "loss": 0.8018,
+      "step": 133
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.677782485216644e-06,
+      "loss": 0.8008,
+      "step": 134
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.672722365763821e-06,
+      "loss": 0.851,
+      "step": 135
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.667625604198842e-06,
+      "loss": 0.7952,
+      "step": 136
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.662492286476595e-06,
+      "loss": 0.8096,
+      "step": 137
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.657322499168475e-06,
+      "loss": 0.831,
+      "step": 138
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.65211632946092e-06,
+      "loss": 0.8212,
+      "step": 139
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.646873865153945e-06,
+      "loss": 0.836,
+      "step": 140
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.641595194659657e-06,
+      "loss": 0.8814,
+      "step": 141
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.63628040700077e-06,
+      "loss": 0.8538,
+      "step": 142
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.630929591809095e-06,
+      "loss": 0.8167,
+      "step": 143
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.625542839324036e-06,
+      "loss": 0.846,
+      "step": 144
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.620120240391065e-06,
+      "loss": 0.8205,
+      "step": 145
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.614661886460191e-06,
+      "loss": 0.8368,
+      "step": 146
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.609167869584416e-06,
+      "loss": 0.8294,
+      "step": 147
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.6036382824181836e-06,
+      "loss": 0.7892,
+      "step": 148
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.598073218215817e-06,
+      "loss": 0.8182,
+      "step": 149
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.5924727708299455e-06,
+      "loss": 0.8369,
+      "step": 150
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.586837034709921e-06,
+      "loss": 0.7774,
+      "step": 151
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.581166104900228e-06,
+      "loss": 0.7848,
+      "step": 152
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.575460077038877e-06,
+      "loss": 0.8288,
+      "step": 153
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.569719047355795e-06,
+      "loss": 0.8462,
+      "step": 154
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.5639431126712e-06,
+      "loss": 0.8378,
+      "step": 155
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.5581323703939685e-06,
+      "loss": 0.8403,
+      "step": 156
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.552286918519996e-06,
+      "loss": 0.8077,
+      "step": 157
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.5464068556305375e-06,
+      "loss": 0.8302,
+      "step": 158
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.540492280890555e-06,
+      "loss": 0.8225,
+      "step": 159
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.534543294047033e-06,
+      "loss": 0.8083,
+      "step": 160
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.528559995427309e-06,
+      "loss": 0.8533,
+      "step": 161
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 0.8346,
+      "step": 162
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.516490867060156e-06,
+      "loss": 0.8138,
+      "step": 163
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.5104052408538545e-06,
+      "loss": 0.8099,
+      "step": 164
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.504285709950167e-06,
+      "loss": 0.8357,
+      "step": 165
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.498132377552587e-06,
+      "loss": 0.8205,
+      "step": 166
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.491945347434656e-06,
+      "loss": 0.8092,
+      "step": 167
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.485724723938215e-06,
+      "loss": 0.8317,
+      "step": 168
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.479470611971646e-06,
+      "loss": 0.8113,
+      "step": 169
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.473183117008096e-06,
+      "loss": 0.8496,
+      "step": 170
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.4668623450837085e-06,
+      "loss": 0.8133,
+      "step": 171
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.460508402795827e-06,
+      "loss": 0.8362,
+      "step": 172
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.4541213973012005e-06,
+      "loss": 0.8375,
+      "step": 173
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.447701436314177e-06,
+      "loss": 0.8382,
+      "step": 174
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.441248628104884e-06,
+      "loss": 0.8115,
+      "step": 175
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.434763081497407e-06,
+      "loss": 0.852,
+      "step": 176
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.428244905867952e-06,
+      "loss": 0.8178,
+      "step": 177
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.421694211142998e-06,
+      "loss": 0.7956,
+      "step": 178
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.415111107797445e-06,
+      "loss": 0.8136,
+      "step": 179
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.408495706852758e-06,
+      "loss": 0.8172,
+      "step": 180
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.401848119875082e-06,
+      "loss": 0.8155,
+      "step": 181
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.395168458973368e-06,
+      "loss": 0.8158,
+      "step": 182
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.388456836797484e-06,
+      "loss": 0.832,
+      "step": 183
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.381713366536312e-06,
+      "loss": 0.8181,
+      "step": 184
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.374938161915835e-06,
+      "loss": 0.8279,
+      "step": 185
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.368131337197228e-06,
+      "loss": 0.7963,
+      "step": 186
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.361293007174925e-06,
+      "loss": 0.8024,
+      "step": 187
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.354423287174686e-06,
+      "loss": 0.8524,
+      "step": 188
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.3475222930516484e-06,
+      "loss": 0.8607,
+      "step": 189
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.340590141188377e-06,
+      "loss": 0.8288,
+      "step": 190
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.333626948492898e-06,
+      "loss": 0.8373,
+      "step": 191
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.326632832396733e-06,
+      "loss": 0.8355,
+      "step": 192
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.319607910852911e-06,
+      "loss": 0.8051,
+      "step": 193
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.3125523023339825e-06,
+      "loss": 0.8142,
+      "step": 194
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.305466125830023e-06,
+      "loss": 0.8446,
+      "step": 195
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.2983495008466285e-06,
+      "loss": 0.7987,
+      "step": 196
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.29120254740289e-06,
+      "loss": 0.7929,
+      "step": 197
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.284025386029381e-06,
+      "loss": 0.865,
+      "step": 198
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.276818137766118e-06,
+      "loss": 0.8197,
+      "step": 199
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.269580924160523e-06,
+      "loss": 0.8342,
+      "step": 200
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.262313867265369e-06,
+      "loss": 0.7934,
+      "step": 201
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.255017089636725e-06,
+      "loss": 0.777,
+      "step": 202
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.24769071433189e-06,
+      "loss": 0.8043,
+      "step": 203
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.240334864907317e-06,
+      "loss": 0.8276,
+      "step": 204
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.232949665416526e-06,
+      "loss": 0.8216,
+      "step": 205
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.225535240408014e-06,
+      "loss": 0.8428,
+      "step": 206
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.218091714923157e-06,
+      "loss": 0.8584,
+      "step": 207
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.210619214494099e-06,
+      "loss": 0.8278,
+      "step": 208
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.203117865141635e-06,
+      "loss": 0.8667,
+      "step": 209
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.195587793373085e-06,
+      "loss": 0.8868,
+      "step": 210
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.188029126180161e-06,
+      "loss": 0.8361,
+      "step": 211
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.180441991036827e-06,
+      "loss": 0.8336,
+      "step": 212
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.172826515897146e-06,
+      "loss": 0.7853,
+      "step": 213
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.165182829193126e-06,
+      "loss": 0.8026,
+      "step": 214
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.15751105983255e-06,
+      "loss": 0.812,
+      "step": 215
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.149811337196808e-06,
+      "loss": 0.8051,
+      "step": 216
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.142083791138703e-06,
+      "loss": 0.8076,
+      "step": 217
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.134328551980278e-06,
+      "loss": 0.8372,
+      "step": 218
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.126545750510605e-06,
+      "loss": 0.8308,
+      "step": 219
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.118735517983584e-06,
+      "loss": 0.8027,
+      "step": 220
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.110897986115729e-06,
+      "loss": 0.8262,
+      "step": 221
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.1030332870839466e-06,
+      "loss": 0.8086,
+      "step": 222
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.0951415535233065e-06,
+      "loss": 0.8224,
+      "step": 223
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.087222918524807e-06,
+      "loss": 0.8143,
+      "step": 224
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.079277515633127e-06,
+      "loss": 0.7967,
+      "step": 225
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.0713054788443776e-06,
+      "loss": 0.7993,
+      "step": 226
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.063306942603835e-06,
+      "loss": 0.8084,
+      "step": 227
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.055282041803685e-06,
+      "loss": 0.7965,
+      "step": 228
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.0472309117807365e-06,
+      "loss": 0.8619,
+      "step": 229
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.039153688314146e-06,
+      "loss": 0.8266,
+      "step": 230
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.031050507623125e-06,
+      "loss": 0.8131,
+      "step": 231
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.022921506364645e-06,
+      "loss": 0.7845,
+      "step": 232
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.014766821631128e-06,
+      "loss": 0.8106,
+      "step": 233
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.006586590948141e-06,
+      "loss": 0.8314,
+      "step": 234
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.998380952272073e-06,
+      "loss": 0.7866,
+      "step": 235
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.990150043987806e-06,
+      "loss": 0.8343,
+      "step": 236
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.981894004906388e-06,
+      "loss": 0.8457,
+      "step": 237
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.973612974262685e-06,
+      "loss": 0.8325,
+      "step": 238
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.965307091713036e-06,
+      "loss": 0.8388,
+      "step": 239
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.956976497332903e-06,
+      "loss": 0.7935,
+      "step": 240
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.948621331614495e-06,
+      "loss": 0.8157,
+      "step": 241
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.9402417354644115e-06,
+      "loss": 0.7983,
+      "step": 242
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.9318378502012636e-06,
+      "loss": 0.839,
+      "step": 243
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.923409817553284e-06,
+      "loss": 0.8337,
+      "step": 244
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.914957779655946e-06,
+      "loss": 0.8095,
+      "step": 245
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.906481879049559e-06,
+      "loss": 0.8282,
+      "step": 246
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.897982258676868e-06,
+      "loss": 0.8364,
+      "step": 247
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.8894590618806435e-06,
+      "loss": 0.8322,
+      "step": 248
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.880912432401265e-06,
+      "loss": 0.7784,
+      "step": 249
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.872342514374291e-06,
+      "loss": 0.8187,
+      "step": 250
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.863749452328035e-06,
+      "loss": 0.8118,
+      "step": 251
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.855133391181124e-06,
+      "loss": 0.8569,
+      "step": 252
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.846494476240057e-06,
+      "loss": 0.8101,
+      "step": 253
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.837832853196751e-06,
+      "loss": 0.8226,
+      "step": 254
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.8291486681260904e-06,
+      "loss": 0.7769,
+      "step": 255
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.820442067483456e-06,
+      "loss": 0.8081,
+      "step": 256
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.811713198102258e-06,
+      "loss": 0.822,
+      "step": 257
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.802962207191463e-06,
+      "loss": 0.8241,
+      "step": 258
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.794189242333107e-06,
+      "loss": 0.8604,
+      "step": 259
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.785394451479806e-06,
+      "loss": 0.8081,
+      "step": 260
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.7765779829522674e-06,
+      "loss": 0.8098,
+      "step": 261
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.7677399854367806e-06,
+      "loss": 0.8141,
+      "step": 262
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.7588806079827147e-06,
+      "loss": 0.8068,
+      "step": 263
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.8101,
+      "step": 264
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.7410983112566162e-06,
+      "loss": 0.8287,
+      "step": 265
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.7321756918760587e-06,
+      "loss": 0.8201,
+      "step": 266
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.7232322923348097e-06,
+      "loss": 0.8342,
+      "step": 267
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.7142682634598016e-06,
+      "loss": 0.841,
+      "step": 268
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.7052837564258728e-06,
+      "loss": 0.8426,
+      "step": 269
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.696278922753217e-06,
+      "loss": 0.8281,
+      "step": 270
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.6872539143048287e-06,
+      "loss": 0.8053,
+      "step": 271
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.678208883283943e-06,
+      "loss": 0.7817,
+      "step": 272
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.6691439822314672e-06,
+      "loss": 0.8208,
+      "step": 273
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.660059364023409e-06,
+      "loss": 0.8426,
+      "step": 274
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.6509551818682975e-06,
+      "loss": 0.8492,
+      "step": 275
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.641831589304602e-06,
+      "loss": 0.8054,
+      "step": 276
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.6326887401981386e-06,
+      "loss": 0.7877,
+      "step": 277
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.6235267887394774e-06,
+      "loss": 0.8353,
+      "step": 278
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.6143458894413463e-06,
+      "loss": 0.7823,
+      "step": 279
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.605146197136015e-06,
+      "loss": 0.7971,
+      "step": 280
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.595927866972694e-06,
+      "loss": 0.8226,
+      "step": 281
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.5866910544149126e-06,
+      "loss": 0.7827,
+      "step": 282
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.577435915237899e-06,
+      "loss": 0.8317,
+      "step": 283
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.5681626055259526e-06,
+      "loss": 0.8149,
+      "step": 284
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.5588712816698106e-06,
+      "loss": 0.8205,
+      "step": 285
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.549562100364014e-06,
+      "loss": 0.8395,
+      "step": 286
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.5402352186042602e-06,
+      "loss": 0.7887,
+      "step": 287
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.530890793684759e-06,
+      "loss": 0.8167,
+      "step": 288
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.521528983195579e-06,
+      "loss": 0.8056,
+      "step": 289
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.5121499450199896e-06,
+      "loss": 0.8141,
+      "step": 290
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.5027538373317975e-06,
+      "loss": 0.8096,
+      "step": 291
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.4933408185926805e-06,
+      "loss": 0.8188,
+      "step": 292
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.4839110475495153e-06,
+      "loss": 0.8192,
+      "step": 293
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.4744646832316985e-06,
+      "loss": 0.8132,
+      "step": 294
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.465001884948468e-06,
+      "loss": 0.8057,
+      "step": 295
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.45552281228621e-06,
+      "loss": 0.7761,
+      "step": 296
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.446027625105776e-06,
+      "loss": 0.8422,
+      "step": 297
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.436516483539781e-06,
+      "loss": 0.8408,
+      "step": 298
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.4269895479899023e-06,
+      "loss": 0.834,
+      "step": 299
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.4174469791241805e-06,
+      "loss": 0.8248,
+      "step": 300
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.4078889378743036e-06,
+      "loss": 0.8201,
+      "step": 301
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.3983155854328942e-06,
+      "loss": 0.8063,
+      "step": 302
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.388727083250795e-06,
+      "loss": 0.7891,
+      "step": 303
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.379123593034342e-06,
+      "loss": 0.7877,
+      "step": 304
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.369505276742638e-06,
+      "loss": 0.8189,
+      "step": 305
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.359872296584821e-06,
+      "loss": 0.8174,
+      "step": 306
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.350224815017331e-06,
+      "loss": 0.7867,
+      "step": 307
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.3405629947411687e-06,
+      "loss": 0.8269,
+      "step": 308
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.3308869986991493e-06,
+      "loss": 0.8414,
+      "step": 309
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.32119699007316e-06,
+      "loss": 0.8241,
+      "step": 310
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.311493132281402e-06,
+      "loss": 0.8067,
+      "step": 311
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.3017755889756382e-06,
+      "loss": 0.7725,
+      "step": 312
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.292044524038433e-06,
+      "loss": 0.8223,
+      "step": 313
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.2823001015803863e-06,
+      "loss": 0.8154,
+      "step": 314
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 0.7919,
+      "step": 315
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.2627718416677484e-06,
+      "loss": 0.7962,
+      "step": 316
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.2529883335496163e-06,
+      "loss": 0.794,
+      "step": 317
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.243192126578007e-06,
+      "loss": 0.8045,
+      "step": 318
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.2333833859621155e-06,
+      "loss": 0.8122,
+      "step": 319
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.223562277122513e-06,
+      "loss": 0.8068,
+      "step": 320
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.213728965688356e-06,
+      "loss": 0.8036,
+      "step": 321
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.2038836174945907e-06,
+      "loss": 0.8126,
+      "step": 322
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.194026398579162e-06,
+      "loss": 0.8097,
+      "step": 323
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.1841574751802075e-06,
+      "loss": 0.7985,
+      "step": 324
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.1742770137332567e-06,
+      "loss": 0.7947,
+      "step": 325
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.1643851808684258e-06,
+      "loss": 0.8361,
+      "step": 326
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.1544821434076013e-06,
+      "loss": 0.8421,
+      "step": 327
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.144568068361634e-06,
+      "loss": 0.8546,
+      "step": 328
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.1346431229275205e-06,
+      "loss": 0.8186,
+      "step": 329
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.124707474485577e-06,
+      "loss": 0.826,
+      "step": 330
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.1147612905966286e-06,
+      "loss": 0.8362,
+      "step": 331
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.1048047389991697e-06,
+      "loss": 0.8166,
+      "step": 332
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.094837987606547e-06,
+      "loss": 0.7894,
+      "step": 333
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.084861204504122e-06,
+      "loss": 0.8057,
+      "step": 334
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.0748745579464347e-06,
+      "loss": 0.7673,
+      "step": 335
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.0648782163543696e-06,
+      "loss": 0.8209,
+      "step": 336
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.0548723483123157e-06,
+      "loss": 0.8393,
+      "step": 337
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.0448571225653195e-06,
+      "loss": 0.7976,
+      "step": 338
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.034832708016244e-06,
+      "loss": 0.7856,
+      "step": 339
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.0247992737229147e-06,
+      "loss": 0.824,
+      "step": 340
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.014756988895274e-06,
+      "loss": 0.8249,
+      "step": 341
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.004706022892526e-06,
+      "loss": 0.8216,
+      "step": 342
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.994646545220275e-06,
+      "loss": 0.7927,
+      "step": 343
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.9845787255276753e-06,
+      "loss": 0.819,
+      "step": 344
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.9745027336045644e-06,
+      "loss": 0.8057,
+      "step": 345
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.964418739378603e-06,
+      "loss": 0.7633,
+      "step": 346
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.9543269129124036e-06,
+      "loss": 0.8107,
+      "step": 347
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.9442274244006725e-06,
+      "loss": 0.8245,
+      "step": 348
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.9341204441673267e-06,
+      "loss": 0.8095,
+      "step": 349
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.9240061426626325e-06,
+      "loss": 0.8083,
+      "step": 350
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.913884690460325e-06,
+      "loss": 0.8008,
+      "step": 351
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.903756258254734e-06,
+      "loss": 0.7911,
+      "step": 352
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.8936210168579047e-06,
+      "loss": 0.8193,
+      "step": 353
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.883479137196714e-06,
+      "loss": 0.7829,
+      "step": 354
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.8733307903099926e-06,
+      "loss": 0.8018,
+      "step": 355
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.8631761473456377e-06,
+      "loss": 0.8133,
+      "step": 356
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.853015379557729e-06,
+      "loss": 0.8132,
+      "step": 357
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.842848658303636e-06,
+      "loss": 0.7818,
+      "step": 358
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.8326761550411353e-06,
+      "loss": 0.8541,
+      "step": 359
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.822498041325509e-06,
+      "loss": 0.8267,
+      "step": 360
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.8123144888066623e-06,
+      "loss": 0.8041,
+      "step": 361
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.802125669226222e-06,
+      "loss": 0.8177,
+      "step": 362
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.7919317544146405e-06,
+      "loss": 0.7828,
+      "step": 363
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.7817329162883033e-06,
+      "loss": 0.7763,
+      "step": 364
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.77152932684662e-06,
+      "loss": 0.793,
+      "step": 365
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.7613211581691347e-06,
+      "loss": 0.7748,
+      "step": 366
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.7511085824126133e-06,
+      "loss": 0.7777,
+      "step": 367
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.74089177180815e-06,
+      "loss": 0.8215,
+      "step": 368
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.730670898658255e-06,
+      "loss": 0.8063,
+      "step": 369
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.7204461353339546e-06,
+      "loss": 0.801,
+      "step": 370
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.710217654271878e-06,
+      "loss": 0.8928,
+      "step": 371
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.6999856279713537e-06,
+      "loss": 0.8004,
+      "step": 372
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.689750228991503e-06,
+      "loss": 0.7836,
+      "step": 373
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.679511629948319e-06,
+      "loss": 0.808,
+      "step": 374
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.669270003511769e-06,
+      "loss": 0.8275,
+      "step": 375
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.6590255224028725e-06,
+      "loss": 0.8203,
+      "step": 376
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.648778359390794e-06,
+      "loss": 0.8104,
+      "step": 377
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.6385286872899248e-06,
+      "loss": 0.8118,
+      "step": 378
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.6282766789569746e-06,
+      "loss": 0.8055,
+      "step": 379
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.618022507288049e-06,
+      "loss": 0.8368,
+      "step": 380
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.6077663452157398e-06,
+      "loss": 0.7884,
+      "step": 381
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.5975083657062043e-06,
+      "loss": 0.8231,
+      "step": 382
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.5872487417562527e-06,
+      "loss": 0.786,
+      "step": 383
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.5769876463904258e-06,
+      "loss": 0.7857,
+      "step": 384
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.566725252658081e-06,
+      "loss": 0.8088,
+      "step": 385
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.5564617336304708e-06,
+      "loss": 0.8089,
+      "step": 386
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.546197262397825e-06,
+      "loss": 0.7817,
+      "step": 387
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.535932012066434e-06,
+      "loss": 0.8521,
+      "step": 388
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.525666155755725e-06,
+      "loss": 0.8011,
+      "step": 389
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.515399866595348e-06,
+      "loss": 0.7946,
+      "step": 390
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.5051333177222476e-06,
+      "loss": 0.8317,
+      "step": 391
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.494866682277754e-06,
+      "loss": 0.7809,
+      "step": 392
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.4846001334046537e-06,
+      "loss": 0.7891,
+      "step": 393
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.474333844244275e-06,
+      "loss": 0.8117,
+      "step": 394
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.464067987933567e-06,
+      "loss": 0.8039,
+      "step": 395
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.4538027376021754e-06,
+      "loss": 0.8015,
+      "step": 396
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.4435382663695305e-06,
+      "loss": 0.7922,
+      "step": 397
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.4332747473419193e-06,
+      "loss": 0.8315,
+      "step": 398
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.4230123536095746e-06,
+      "loss": 0.813,
+      "step": 399
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.4127512582437477e-06,
+      "loss": 0.8176,
+      "step": 400
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.4024916342937966e-06,
+      "loss": 0.7881,
+      "step": 401
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.392233654784261e-06,
+      "loss": 0.7757,
+      "step": 402
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.3819774927119523e-06,
+      "loss": 0.8139,
+      "step": 403
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.371723321043026e-06,
+      "loss": 0.8229,
+      "step": 404
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.3614713127100752e-06,
+      "loss": 0.7965,
+      "step": 405
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.351221640609207e-06,
+      "loss": 0.8069,
+      "step": 406
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.340974477597128e-06,
+      "loss": 0.8112,
+      "step": 407
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.3307299964882314e-06,
+      "loss": 0.8149,
+      "step": 408
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.3204883700516813e-06,
+      "loss": 0.8327,
+      "step": 409
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.3102497710084984e-06,
+      "loss": 0.7966,
+      "step": 410
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.3000143720286463e-06,
+      "loss": 0.7934,
+      "step": 411
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.2897823457281234e-06,
+      "loss": 0.8279,
+      "step": 412
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.2795538646660462e-06,
+      "loss": 0.7736,
+      "step": 413
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.269329101341745e-06,
+      "loss": 0.7782,
+      "step": 414
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.2591082281918507e-06,
+      "loss": 0.8168,
+      "step": 415
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.2488914175873867e-06,
+      "loss": 0.7841,
+      "step": 416
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.238678841830867e-06,
+      "loss": 0.8293,
+      "step": 417
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.2284706731533805e-06,
+      "loss": 0.8175,
+      "step": 418
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.2182670837116975e-06,
+      "loss": 0.7573,
+      "step": 419
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.208068245585359e-06,
+      "loss": 0.7953,
+      "step": 420
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1978743307737794e-06,
+      "loss": 0.7975,
+      "step": 421
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1876855111933385e-06,
+      "loss": 0.8089,
+      "step": 422
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1775019586744924e-06,
+      "loss": 0.8124,
+      "step": 423
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1673238449588664e-06,
+      "loss": 0.8046,
+      "step": 424
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.1571513416963643e-06,
+      "loss": 0.7934,
+      "step": 425
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.1469846204422715e-06,
+      "loss": 0.7767,
+      "step": 426
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.1368238526543623e-06,
+      "loss": 0.8247,
+      "step": 427
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.1266692096900086e-06,
+      "loss": 0.7744,
+      "step": 428
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.1165208628032867e-06,
+      "loss": 0.7913,
+      "step": 429
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.106378983142096e-06,
+      "loss": 0.813,
+      "step": 430
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.096243741745266e-06,
+      "loss": 0.7798,
+      "step": 431
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.0861153095396754e-06,
+      "loss": 0.7871,
+      "step": 432
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.0759938573373683e-06,
+      "loss": 0.7988,
+      "step": 433
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.065879555832675e-06,
+      "loss": 0.7684,
+      "step": 434
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.055772575599329e-06,
+      "loss": 0.7971,
+      "step": 435
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.0456730870875964e-06,
+      "loss": 0.8171,
+      "step": 436
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.035581260621398e-06,
+      "loss": 0.8026,
+      "step": 437
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.0254972663954356e-06,
+      "loss": 0.7951,
+      "step": 438
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.015421274472325e-06,
+      "loss": 0.8099,
+      "step": 439
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.005353454779725e-06,
+      "loss": 0.7973,
+      "step": 440
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.995293977107475e-06,
+      "loss": 0.7882,
+      "step": 441
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.9852430111047254e-06,
+      "loss": 0.7845,
+      "step": 442
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.9752007262770857e-06,
+      "loss": 0.8045,
+      "step": 443
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.9651672919837566e-06,
+      "loss": 0.796,
+      "step": 444
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.955142877434681e-06,
+      "loss": 0.7914,
+      "step": 445
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.9451276516876847e-06,
+      "loss": 0.7394,
+      "step": 446
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.935121783645631e-06,
+      "loss": 0.7839,
+      "step": 447
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.9251254420535665e-06,
+      "loss": 0.8198,
+      "step": 448
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.915138795495879e-06,
+      "loss": 0.7775,
+      "step": 449
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.9051620123934534e-06,
+      "loss": 0.8106,
+      "step": 450
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8951952610008307e-06,
+      "loss": 0.7796,
+      "step": 451
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.885238709403373e-06,
+      "loss": 0.7512,
+      "step": 452
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8752925255144234e-06,
+      "loss": 0.7846,
+      "step": 453
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8653568770724812e-06,
+      "loss": 0.7954,
+      "step": 454
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8554319316383661e-06,
+      "loss": 0.8306,
+      "step": 455
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8455178565923997e-06,
+      "loss": 0.8121,
+      "step": 456
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8356148191315753e-06,
+      "loss": 0.8274,
+      "step": 457
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.825722986266743e-06,
+      "loss": 0.7845,
+      "step": 458
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8158425248197936e-06,
+      "loss": 0.7751,
+      "step": 459
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8059736014208388e-06,
+      "loss": 0.7951,
+      "step": 460
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.7961163825054101e-06,
+      "loss": 0.8067,
+      "step": 461
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.7862710343116451e-06,
+      "loss": 0.8046,
+      "step": 462
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.7764377228774877e-06,
+      "loss": 0.8111,
+      "step": 463
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.766616614037885e-06,
+      "loss": 0.812,
+      "step": 464
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.756807873421994e-06,
+      "loss": 0.828,
+      "step": 465
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.747011666450384e-06,
+      "loss": 0.792,
+      "step": 466
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.737228158332252e-06,
+      "loss": 0.8158,
+      "step": 467
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.7274575140626318e-06,
+      "loss": 0.8035,
+      "step": 468
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.7176998984196141e-06,
+      "loss": 0.8222,
+      "step": 469
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.707955475961568e-06,
+      "loss": 0.8273,
+      "step": 470
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.698224411024362e-06,
+      "loss": 0.779,
+      "step": 471
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6885068677185989e-06,
+      "loss": 0.8354,
+      "step": 472
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6788030099268407e-06,
+      "loss": 0.7926,
+      "step": 473
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6691130013008514e-06,
+      "loss": 0.8091,
+      "step": 474
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6594370052588321e-06,
+      "loss": 0.7789,
+      "step": 475
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6497751849826699e-06,
+      "loss": 0.7857,
+      "step": 476
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6401277034151798e-06,
+      "loss": 0.8094,
+      "step": 477
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6304947232573637e-06,
+      "loss": 0.7974,
+      "step": 478
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.6208764069656584e-06,
+      "loss": 0.8269,
+      "step": 479
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.611272916749205e-06,
+      "loss": 0.8063,
+      "step": 480
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.6016844145671062e-06,
+      "loss": 0.777,
+      "step": 481
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.5921110621256972e-06,
+      "loss": 0.8234,
+      "step": 482
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.5825530208758206e-06,
+      "loss": 0.7793,
+      "step": 483
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.5730104520100984e-06,
+      "loss": 0.7956,
+      "step": 484
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.5634835164602206e-06,
+      "loss": 0.8179,
+      "step": 485
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5539723748942246e-06,
+      "loss": 0.7822,
+      "step": 486
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.544477187713791e-06,
+      "loss": 0.7967,
+      "step": 487
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.534998115051533e-06,
+      "loss": 0.7751,
+      "step": 488
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5255353167683023e-06,
+      "loss": 0.8109,
+      "step": 489
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5160889524504857e-06,
+      "loss": 0.8081,
+      "step": 490
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.50665918140732e-06,
+      "loss": 0.7911,
+      "step": 491
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.4972461626682033e-06,
+      "loss": 0.8349,
+      "step": 492
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.487850054980011e-06,
+      "loss": 0.7894,
+      "step": 493
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.4784710168044215e-06,
+      "loss": 0.8186,
+      "step": 494
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.4691092063152413e-06,
+      "loss": 0.8063,
+      "step": 495
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.459764781395741e-06,
+      "loss": 0.8237,
+      "step": 496
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.4504378996359867e-06,
+      "loss": 0.8075,
+      "step": 497
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.4411287183301892e-06,
+      "loss": 0.7954,
+      "step": 498
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.4318373944740485e-06,
+      "loss": 0.7963,
+      "step": 499
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.4225640847621015e-06,
+      "loss": 0.814,
+      "step": 500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.4133089455850878e-06,
+      "loss": 0.7669,
+      "step": 501
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.4040721330273063e-06,
+      "loss": 0.8231,
+      "step": 502
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.394853802863986e-06,
+      "loss": 0.8323,
+      "step": 503
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.3856541105586545e-06,
+      "loss": 0.7884,
+      "step": 504
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.3764732112605234e-06,
+      "loss": 0.7727,
+      "step": 505
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.367311259801863e-06,
+      "loss": 0.8102,
+      "step": 506
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.3581684106953987e-06,
+      "loss": 0.8012,
+      "step": 507
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.3490448181317025e-06,
+      "loss": 0.8001,
+      "step": 508
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.3399406359765921e-06,
+      "loss": 0.8122,
+      "step": 509
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.3308560177685334e-06,
+      "loss": 0.7582,
+      "step": 510
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.3217911167160575e-06,
+      "loss": 0.8061,
+      "step": 511
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.3127460856951724e-06,
+      "loss": 0.8169,
+      "step": 512
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.303721077246784e-06,
+      "loss": 0.7983,
+      "step": 513
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.2947162435741278e-06,
+      "loss": 0.8256,
+      "step": 514
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.2857317365401988e-06,
+      "loss": 0.7945,
+      "step": 515
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.2767677076651913e-06,
+      "loss": 0.7725,
+      "step": 516
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.2678243081239421e-06,
+      "loss": 0.7832,
+      "step": 517
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.2589016887433846e-06,
+      "loss": 0.7915,
+      "step": 518
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.8055,
+      "step": 519
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.2411193920172866e-06,
+      "loss": 0.7581,
+      "step": 520
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.2322600145632194e-06,
+      "loss": 0.8076,
+      "step": 521
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.2234220170477324e-06,
+      "loss": 0.8401,
+      "step": 522
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.2146055485201943e-06,
+      "loss": 0.8178,
+      "step": 523
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.205810757666894e-06,
+      "loss": 0.7968,
+      "step": 524
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.197037792808538e-06,
+      "loss": 0.8016,
+      "step": 525
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.188286801897743e-06,
+      "loss": 0.8182,
+      "step": 526
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.1795579325165448e-06,
+      "loss": 0.7649,
+      "step": 527
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.1708513318739096e-06,
+      "loss": 0.769,
+      "step": 528
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.1621671468032495e-06,
+      "loss": 0.798,
+      "step": 529
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.153505523759944e-06,
+      "loss": 0.7675,
+      "step": 530
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.1448666088188776e-06,
+      "loss": 0.8087,
+      "step": 531
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.1362505476719662e-06,
+      "loss": 0.7884,
+      "step": 532
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.1276574856257097e-06,
+      "loss": 0.8001,
+      "step": 533
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.1190875675987355e-06,
+      "loss": 0.7813,
+      "step": 534
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.1105409381193563e-06,
+      "loss": 0.7958,
+      "step": 535
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.1020177413231334e-06,
+      "loss": 0.7589,
+      "step": 536
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.0935181209504422e-06,
+      "loss": 0.7825,
+      "step": 537
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.0850422203440555e-06,
+      "loss": 0.8153,
+      "step": 538
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.0765901824467167e-06,
+      "loss": 0.8181,
+      "step": 539
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.068162149798737e-06,
+      "loss": 0.791,
+      "step": 540
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.0597582645355883e-06,
+      "loss": 0.7811,
+      "step": 541
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.0513786683855062e-06,
+      "loss": 0.7889,
+      "step": 542
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.0430235026670979e-06,
+      "loss": 0.8002,
+      "step": 543
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.0346929082869632e-06,
+      "loss": 0.8045,
+      "step": 544
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.0263870257373162e-06,
+      "loss": 0.8224,
+      "step": 545
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.0181059950936131e-06,
+      "loss": 0.7853,
+      "step": 546
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.0098499560121943e-06,
+      "loss": 0.7737,
+      "step": 547
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.0016190477279274e-06,
+      "loss": 0.7547,
+      "step": 548
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.934134090518593e-07,
+      "loss": 0.8131,
+      "step": 549
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.852331783688722e-07,
+      "loss": 0.8139,
+      "step": 550
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.770784936353564e-07,
+      "loss": 0.7874,
+      "step": 551
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.689494923768756e-07,
+      "loss": 0.7849,
+      "step": 552
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.608463116858544e-07,
+      "loss": 0.805,
+      "step": 553
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.527690882192636e-07,
+      "loss": 0.7928,
+      "step": 554
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.447179581963148e-07,
+      "loss": 0.8057,
+      "step": 555
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.366930573961649e-07,
+      "loss": 0.8258,
+      "step": 556
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.286945211556231e-07,
+      "loss": 0.7561,
+      "step": 557
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.207224843668733e-07,
+      "loss": 0.794,
+      "step": 558
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.127770814751933e-07,
+      "loss": 0.7662,
+      "step": 559
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.048584464766938e-07,
+      "loss": 0.7949,
+      "step": 560
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.96966712916054e-07,
+      "loss": 0.793,
+      "step": 561
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.891020138842718e-07,
+      "loss": 0.7779,
+      "step": 562
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.81264482016416e-07,
+      "loss": 0.7798,
+      "step": 563
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.734542494893947e-07,
+      "loss": 0.8056,
+      "step": 564
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.65671448019722e-07,
+      "loss": 0.7898,
+      "step": 565
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.579162088612974e-07,
+      "loss": 0.7723,
+      "step": 566
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.501886628031941e-07,
+      "loss": 0.7705,
+      "step": 567
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.424889401674505e-07,
+      "loss": 0.7892,
+      "step": 568
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.348171708068748e-07,
+      "loss": 0.773,
+      "step": 569
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.271734841028545e-07,
+      "loss": 0.832,
+      "step": 570
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.195580089631741e-07,
+      "loss": 0.7984,
+      "step": 571
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.119708738198395e-07,
+      "loss": 0.7448,
+      "step": 572
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.044122066269159e-07,
+      "loss": 0.7497,
+      "step": 573
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.968821348583652e-07,
+      "loss": 0.7794,
+      "step": 574
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.89380785505901e-07,
+      "loss": 0.7857,
+      "step": 575
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.819082850768433e-07,
+      "loss": 0.7799,
+      "step": 576
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.744647595919869e-07,
+      "loss": 0.8092,
+      "step": 577
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.670503345834757e-07,
+      "loss": 0.7905,
+      "step": 578
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.596651350926837e-07,
+      "loss": 0.77,
+      "step": 579
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.523092856681105e-07,
+      "loss": 0.7962,
+      "step": 580
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.44982910363276e-07,
+      "loss": 0.8031,
+      "step": 581
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.376861327346325e-07,
+      "loss": 0.8029,
+      "step": 582
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.304190758394775e-07,
+      "loss": 0.7673,
+      "step": 583
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.231818622338824e-07,
+      "loss": 0.7838,
+      "step": 584
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.159746139706194e-07,
+      "loss": 0.7944,
+      "step": 585
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.087974525971103e-07,
+      "loss": 0.8111,
+      "step": 586
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.016504991533727e-07,
+      "loss": 0.77,
+      "step": 587
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.94533874169977e-07,
+      "loss": 0.7893,
+      "step": 588
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.874476976660185e-07,
+      "loss": 0.7789,
+      "step": 589
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.803920891470897e-07,
+      "loss": 0.7778,
+      "step": 590
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.733671676032674e-07,
+      "loss": 0.8004,
+      "step": 591
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.663730515071019e-07,
+      "loss": 0.7951,
+      "step": 592
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.594098588116243e-07,
+      "loss": 0.7855,
+      "step": 593
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.524777069483526e-07,
+      "loss": 0.7906,
+      "step": 594
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.455767128253148e-07,
+      "loss": 0.801,
+      "step": 595
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.38706992825075e-07,
+      "loss": 0.766,
+      "step": 596
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.318686628027723e-07,
+      "loss": 0.8051,
+      "step": 597
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.250618380841661e-07,
+      "loss": 0.8199,
+      "step": 598
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.182866334636889e-07,
+      "loss": 0.7891,
+      "step": 599
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.115431632025162e-07,
+      "loss": 0.7971,
+      "step": 600
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 6.048315410266326e-07,
+      "loss": 0.7983,
+      "step": 601
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.981518801249192e-07,
+      "loss": 0.8151,
+      "step": 602
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.915042931472426e-07,
+      "loss": 0.7969,
+      "step": 603
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.848888922025553e-07,
+      "loss": 0.8007,
+      "step": 604
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.783057888570034e-07,
+      "loss": 0.7817,
+      "step": 605
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.717550941320491e-07,
+      "loss": 0.7754,
+      "step": 606
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.65236918502593e-07,
+      "loss": 0.783,
+      "step": 607
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.587513718951165e-07,
+      "loss": 0.8016,
+      "step": 608
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.522985636858238e-07,
+      "loss": 0.7854,
+      "step": 609
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.458786026988e-07,
+      "loss": 0.7976,
+      "step": 610
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.394915972041739e-07,
+      "loss": 0.7798,
+      "step": 611
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.33137654916292e-07,
+      "loss": 0.7446,
+      "step": 612
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.268168829919046e-07,
+      "loss": 0.7807,
+      "step": 613
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.205293880283552e-07,
+      "loss": 0.7988,
+      "step": 614
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.14275276061785e-07,
+      "loss": 0.8045,
+      "step": 615
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 5.080546525653443e-07,
+      "loss": 0.8085,
+      "step": 616
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 5.018676224474139e-07,
+      "loss": 0.7984,
+      "step": 617
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.957142900498335e-07,
+      "loss": 0.8185,
+      "step": 618
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.895947591461456e-07,
+      "loss": 0.7901,
+      "step": 619
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.835091329398442e-07,
+      "loss": 0.8083,
+      "step": 620
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.774575140626317e-07,
+      "loss": 0.8104,
+      "step": 621
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.714400045726919e-07,
+      "loss": 0.7603,
+      "step": 622
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.6545670595296686e-07,
+      "loss": 0.7979,
+      "step": 623
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.5950771910944603e-07,
+      "loss": 0.7999,
+      "step": 624
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.5359314436946275e-07,
+      "loss": 0.7954,
+      "step": 625
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.477130814800054e-07,
+      "loss": 0.7987,
+      "step": 626
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.418676296060323e-07,
+      "loss": 0.7664,
+      "step": 627
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.3605688732880097e-07,
+      "loss": 0.7597,
+      "step": 628
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.302809526442053e-07,
+      "loss": 0.8077,
+      "step": 629
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.2453992296112384e-07,
+      "loss": 0.8146,
+      "step": 630
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.188338950997728e-07,
+      "loss": 0.7753,
+      "step": 631
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.1316296529007955e-07,
+      "loss": 0.8016,
+      "step": 632
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.075272291700558e-07,
+      "loss": 0.7614,
+      "step": 633
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.019267817841835e-07,
+      "loss": 0.8069,
+      "step": 634
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.963617175818171e-07,
+      "loss": 0.7683,
+      "step": 635
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.908321304155846e-07,
+      "loss": 0.8056,
+      "step": 636
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.853381135398093e-07,
+      "loss": 0.8418,
+      "step": 637
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.798797596089351e-07,
+      "loss": 0.7794,
+      "step": 638
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.744571606759645e-07,
+      "loss": 0.8237,
+      "step": 639
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.6907040819090604e-07,
+      "loss": 0.7927,
+      "step": 640
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.63719592999231e-07,
+      "loss": 0.7847,
+      "step": 641
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.5840480534034355e-07,
+      "loss": 0.7701,
+      "step": 642
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.531261348460563e-07,
+      "loss": 0.7898,
+      "step": 643
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.4788367053908087e-07,
+      "loss": 0.8017,
+      "step": 644
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.4267750083152587e-07,
+      "loss": 0.7854,
+      "step": 645
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.375077135234056e-07,
+      "loss": 0.8245,
+      "step": 646
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.323743958011588e-07,
+      "loss": 0.827,
+      "step": 647
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.272776342361797e-07,
+      "loss": 0.7868,
+      "step": 648
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.2221751478335615e-07,
+      "loss": 0.7913,
+      "step": 649
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.171941227796227e-07,
+      "loss": 0.8071,
+      "step": 650
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.122075429425184e-07,
+      "loss": 0.7679,
+      "step": 651
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.072578593687606e-07,
+      "loss": 0.8103,
+      "step": 652
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.0234515553282523e-07,
+      "loss": 0.8137,
+      "step": 653
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.9746951428553884e-07,
+      "loss": 0.8366,
+      "step": 654
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.926310178526831e-07,
+      "loss": 0.7944,
+      "step": 655
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.8782974783360534e-07,
+      "loss": 0.7825,
+      "step": 656
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.8306578519984526e-07,
+      "loss": 0.783,
+      "step": 657
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.783392102937682e-07,
+      "loss": 0.7991,
+      "step": 658
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.7365010282720954e-07,
+      "loss": 0.8074,
+      "step": 659
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.6899854188013054e-07,
+      "loss": 0.7877,
+      "step": 660
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.643846058992866e-07,
+      "loss": 0.7795,
+      "step": 661
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.598083726969003e-07,
+      "loss": 0.7968,
+      "step": 662
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.552699194493549e-07,
+      "loss": 0.7787,
+      "step": 663
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.5076932269588684e-07,
+      "loss": 0.8009,
+      "step": 664
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.463066583372989e-07,
+      "loss": 0.8041,
+      "step": 665
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.418820016346776e-07,
+      "loss": 0.8068,
+      "step": 666
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.3749542720812757e-07,
+      "loss": 0.7713,
+      "step": 667
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.3314700903550897e-07,
+      "loss": 0.786,
+      "step": 668
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.2883682045119093e-07,
+      "loss": 0.7479,
+      "step": 669
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.2456493414481778e-07,
+      "loss": 0.8023,
+      "step": 670
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.2033142216007913e-07,
+      "loss": 0.7763,
+      "step": 671
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.1613635589349812e-07,
+      "loss": 0.7793,
+      "step": 672
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.1197980609322377e-07,
+      "loss": 0.8387,
+      "step": 673
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.07861842857843e-07,
+      "loss": 0.7965,
+      "step": 674
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.0378253563519273e-07,
+      "loss": 0.7708,
+      "step": 675
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.997419532211925e-07,
+      "loss": 0.7493,
+      "step": 676
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.9574016375868282e-07,
+      "loss": 0.7833,
+      "step": 677
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.9177723473627647e-07,
+      "loss": 0.823,
+      "step": 678
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.8785323298722098e-07,
+      "loss": 0.769,
+      "step": 679
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.8396822468826876e-07,
+      "loss": 0.7869,
+      "step": 680
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.8012227535856326e-07,
+      "loss": 0.7885,
+      "step": 681
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.7631544985853623e-07,
+      "loss": 0.7844,
+      "step": 682
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.725478123888083e-07,
+      "loss": 0.7763,
+      "step": 683
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6881942648911047e-07,
+      "loss": 0.7964,
+      "step": 684
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6513035503721187e-07,
+      "loss": 0.7894,
+      "step": 685
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.614806602478583e-07,
+      "loss": 0.774,
+      "step": 686
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.5787040367172379e-07,
+      "loss": 0.8107,
+      "step": 687
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.542996461943713e-07,
+      "loss": 0.7907,
+      "step": 688
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.507684480352292e-07,
+      "loss": 0.7691,
+      "step": 689
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.4727686874657116e-07,
+      "loss": 0.7821,
+      "step": 690
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.4382496721251556e-07,
+      "loss": 0.7807,
+      "step": 691
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.4041280164802967e-07,
+      "loss": 0.8025,
+      "step": 692
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.3704042959795132e-07,
+      "loss": 0.7967,
+      "step": 693
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.3370790793601403e-07,
+      "loss": 0.8285,
+      "step": 694
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.3041529286389078e-07,
+      "loss": 0.7722,
+      "step": 695
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.2716263991024712e-07,
+      "loss": 0.7876,
+      "step": 696
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.2395000392980083e-07,
+      "loss": 0.8149,
+      "step": 697
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.2077743910239998e-07,
+      "loss": 0.7717,
+      "step": 698
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1764499893210879e-07,
+      "loss": 0.7895,
+      "step": 699
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.145527362463042e-07,
+      "loss": 0.7778,
+      "step": 700
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.1150070319478679e-07,
+      "loss": 0.8254,
+      "step": 701
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.0848895124889847e-07,
+      "loss": 0.7743,
+      "step": 702
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.0551753120065621e-07,
+      "loss": 0.7628,
+      "step": 703
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.0258649316189722e-07,
+      "loss": 0.7787,
+      "step": 704
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.969588656342982e-08,
+      "loss": 0.7832,
+      "step": 705
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.684576015420277e-08,
+      "loss": 0.8013,
+      "step": 706
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.40361620004826e-08,
+      "loss": 0.7997,
+      "step": 707
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 9.12671394850423e-08,
+      "loss": 0.7971,
+      "step": 708
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 8.853873930636248e-08,
+      "loss": 0.7795,
+      "step": 709
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 8.585100747784348e-08,
+      "loss": 0.784,
+      "step": 710
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 8.320398932703145e-08,
+      "loss": 0.7575,
+      "step": 711
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 8.059772949485068e-08,
+      "loss": 0.7954,
+      "step": 712
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.803227193485336e-08,
+      "loss": 0.8266,
+      "step": 713
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.550765991247627e-08,
+      "loss": 0.7929,
+      "step": 714
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.30239360043139e-08,
+      "loss": 0.8073,
+      "step": 715
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 7.058114209739702e-08,
+      "loss": 0.8262,
+      "step": 716
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 6.817931938848805e-08,
+      "loss": 0.7818,
+      "step": 717
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 6.581850838338816e-08,
+      "loss": 0.8052,
+      "step": 718
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 6.349874889624963e-08,
+      "loss": 0.8023,
+      "step": 719
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 6.12200800489085e-08,
+      "loss": 0.7622,
+      "step": 720
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.898254027022265e-08,
+      "loss": 0.8362,
+      "step": 721
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.678616729542535e-08,
+      "loss": 0.7673,
+      "step": 722
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 5.463099816548606e-08,
+      "loss": 0.7847,
+      "step": 723
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 5.2517069226488694e-08,
+      "loss": 0.8266,
+      "step": 724
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 5.044441612901768e-08,
+      "loss": 0.7812,
+      "step": 725
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.841307382755567e-08,
+      "loss": 0.7823,
+      "step": 726
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.6423076579895646e-08,
+      "loss": 0.7864,
+      "step": 727
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.447445794656197e-08,
+      "loss": 0.7993,
+      "step": 728
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.256725079024554e-08,
+      "loss": 0.7637,
+      "step": 729
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.070148727524814e-08,
+      "loss": 0.8043,
+      "step": 730
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.887719886694091e-08,
+      "loss": 0.7794,
+      "step": 731
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.709441633123367e-08,
+      "loss": 0.7911,
+      "step": 732
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.535316973405645e-08,
+      "loss": 0.7691,
+      "step": 733
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.3653488440851255e-08,
+      "loss": 0.8012,
+      "step": 734
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.199540111607724e-08,
+      "loss": 0.7939,
+      "step": 735
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.0378935722729095e-08,
+      "loss": 0.7788,
+      "step": 736
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.8804119521862183e-08,
+      "loss": 0.8145,
+      "step": 737
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.7270979072135106e-08,
+      "loss": 0.7804,
+      "step": 738
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.5779540229361744e-08,
+      "loss": 0.8001,
+      "step": 739
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.4329828146074096e-08,
+      "loss": 0.814,
+      "step": 740
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.2921867271099296e-08,
+      "loss": 0.8008,
+      "step": 741
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.1555681349146318e-08,
+      "loss": 0.7683,
+      "step": 742
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.0231293420405194e-08,
+      "loss": 0.7887,
+      "step": 743
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.8948725820160663e-08,
+      "loss": 0.7837,
+      "step": 744
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.770800017841301e-08,
+      "loss": 0.783,
+      "step": 745
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.650913741951421e-08,
+      "loss": 0.7938,
+      "step": 746
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.53521577618157e-08,
+      "loss": 0.7762,
+      "step": 747
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.4237080717326712e-08,
+      "loss": 0.7761,
+      "step": 748
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.3163925091384532e-08,
+      "loss": 0.8096,
+      "step": 749
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.2132708982338925e-08,
+      "loss": 0.8229,
+      "step": 750
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.1143449781245985e-08,
+      "loss": 0.7754,
+      "step": 751
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0196164171574762e-08,
+      "loss": 0.801,
+      "step": 752
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.290868128926378e-09,
+      "loss": 0.8087,
+      "step": 753
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 8.427576920763681e-09,
+      "loss": 0.8389,
+      "step": 754
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.606305106155898e-09,
+      "loss": 0.7898,
+      "step": 755
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.827066535529947e-09,
+      "loss": 0.7743,
+      "step": 756
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.089874350439229e-09,
+      "loss": 0.8121,
+      "step": 757
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.394740983341862e-09,
+      "loss": 0.795,
+      "step": 758
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.74167815738974e-09,
+      "loss": 0.8057,
+      "step": 759
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.130696886231744e-09,
+      "loss": 0.8175,
+      "step": 760
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.561807473827783e-09,
+      "loss": 0.8185,
+      "step": 761
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.035019514275039e-09,
+      "loss": 0.791,
+      "step": 762
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5503418916467127e-09,
+      "loss": 0.7795,
+      "step": 763
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.1077827798404728e-09,
+      "loss": 0.7878,
+      "step": 764
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.707349642442735e-09,
+      "loss": 0.74,
+      "step": 765
+    },
+    {
+      "epoch": 1.0,
+      "step": 765,
+      "total_flos": 198371117629440.0,
+      "train_loss": 0.815405089325375,
+      "train_runtime": 68079.5988,
+      "train_samples_per_second": 0.719,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 765,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 198371117629440.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

70B/ft_70B_gpt4_v2_lr5e-6_0/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb57e9097f0a4a8bd51d0e168b7c268716da7c95c209482ef74c0dcf7ca48c13
+size 6459