Add astrollama-70b-chat

README.md

@@ -1,3 +1,58 @@
 ---
-license: mit
+base_model: output_models/abot-70b_epoch-1
+tags:
+- generated_from_trainer
+datasets:
+- customized
+model-index:
+- name: abot-70b_chat
+  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. -->
+
+# abot-70b_chat
+
+This model is a fine-tuned version of [output_models/abot-70b_epoch-1](https://huggingface.co/output_models/abot-70b_epoch-1) 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: 2e-05
+- train_batch_size: 6
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 48
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.008456783521743,
+    "train_runtime": 75047.9043,
+    "train_samples": 25188,
+    "train_samples_per_second": 0.336,
+    "train_steps_per_second": 0.007
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "output_models/abot-70b_epoch-1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "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": "4.33.3",
+  "use_cache": false,
+  "vocab_size": 32000
+}

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": "4.33.3"
+}

pytorch_model-00001-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5db29118ac14cce79617b06fc19e15f0126024235e6bb22c994f113fbf8e171
+size 9852601804

pytorch_model-00002-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b4eeb1b288020206677d3f450d543ee7e2aeae3026ca095a2573ac13fceb599
+size 9798109380

pytorch_model-00003-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a815856abfb77884ef6594a8f9ea607e23cc7747930021266c78031c2edb874
+size 9965880502

pytorch_model-00004-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60f72779360b00b42f11f1be04827fd969c7254fc8f6c2939636b8994589d37
+size 9798075916

pytorch_model-00005-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d0571830855a2394f4b3658aec75bf294db26c10ab3b31390a6717fe965be6
+size 9798109360

pytorch_model-00006-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d039cbb94c03f0d5837e99fd5dd0184cbc93f422d1389b45cea93788f59b5c8
+size 9798109444

pytorch_model-00007-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e9a91fc35b50d6c540092a11cecf511c88e0f991aa93b57035f4dbbed25129c
+size 9965880502

pytorch_model-00008-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf74bd5388ad2f1bf45b8b53f58eb95f32b8e2288c2350f005eed8260f1aa9c7
+size 9798075916

pytorch_model-00009-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a2781df5adff73ce32d631d7c663c8ce9e3f10a537b7e8c37b76464dcdc640
+size 9798109360

pytorch_model-00010-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87cf99609db80ca0353503455379d8bdd798dd7fd2582641a62dc35ae736a6f
+size 9798109444

pytorch_model-00011-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58378d3e31f25ad59f4151e464202b6d16dcaf45e0ed779561c767c03859a6a
+size 9965880502

pytorch_model-00012-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fca98344147d919b25827281190e899dfe784c36b73ddef38431e50e08662de
+size 9798075916

pytorch_model-00013-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c368feca8fcd043a0c2675fddc9e0d43d2209f8acf9d5811cd7706f1dc5ec22d
+size 9798109360

pytorch_model-00014-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25dda728bf69b80a51c0aad413158ffb1667ddbd6f78d2a776145d6550f08a3b
+size 9496134826

pytorch_model-00015-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ae02d41617cb006a3dc46adb077577e6018e9a9759d6fefaaf1a871c7b6c6d
+size 524289413

pytorch_model.bin.index.json

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

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
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.008456783521743,
+    "train_runtime": 75047.9043,
+    "train_samples": 25188,
+    "train_samples_per_second": 0.336,
+    "train_steps_per_second": 0.007
+}

trainer_state.json

@@ -0,0 +1,3178 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 15.0,
+  "global_step": 525,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.25e-06,
+      "loss": 1.2013,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.5e-06,
+      "loss": 1.2758,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.3713,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-06,
+      "loss": 1.2094,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.25e-06,
+      "loss": 1.1364,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.2654,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.1074,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1e-05,
+      "loss": 1.2926,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.125e-05,
+      "loss": 1.0516,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.25e-05,
+      "loss": 1.0722,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.375e-05,
+      "loss": 1.1681,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.0346,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.6250000000000002e-05,
+      "loss": 1.2024,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 1.093,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 1.012,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 1.2205,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9999809527270053e-05,
+      "loss": 0.925,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.999923811633618e-05,
+      "loss": 1.0383,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9998285788966027e-05,
+      "loss": 1.0327,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999695258143807e-05,
+      "loss": 1.058,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999523854454024e-05,
+      "loss": 1.1077,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9993143743568e-05,
+      "loss": 0.9494,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999066825832184e-05,
+      "loss": 1.0373,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998781218310425e-05,
+      "loss": 1.1996,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9984575626716113e-05,
+      "loss": 0.899,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9980958712452577e-05,
+      "loss": 1.0654,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9976961578098352e-05,
+      "loss": 1.1306,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9972584375922453e-05,
+      "loss": 1.0501,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9967827272672407e-05,
+      "loss": 1.0959,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.996269044956791e-05,
+      "loss": 1.0585,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.99571741022939e-05,
+      "loss": 0.9487,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9951278440993128e-05,
+      "loss": 1.03,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9945003690258127e-05,
+      "loss": 1.1106,
+      "step": 33
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.993835008912268e-05,
+      "loss": 0.9199,
+      "step": 34
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9931317891052707e-05,
+      "loss": 1.0684,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9923907363936593e-05,
+      "loss": 0.9362,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.991611879007501e-05,
+      "loss": 1.0414,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.990795246617014e-05,
+      "loss": 1.161,
+      "step": 38
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9899408703314383e-05,
+      "loss": 0.9178,
+      "step": 39
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.989048782697851e-05,
+      "loss": 1.0846,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9881190176999255e-05,
+      "loss": 0.9939,
+      "step": 41
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9871516107566366e-05,
+      "loss": 0.9798,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.986146598720913e-05,
+      "loss": 1.0917,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.985104019878233e-05,
+      "loss": 0.8748,
+      "step": 44
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9840239139451622e-05,
+      "loss": 1.0609,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.982906322067847e-05,
+      "loss": 1.0462,
+      "step": 46
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9817512868204425e-05,
+      "loss": 0.9416,
+      "step": 47
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.980558852203492e-05,
+      "loss": 1.0883,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9793290636422503e-05,
+      "loss": 1.0643,
+      "step": 49
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9780619679849552e-05,
+      "loss": 1.1065,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.97675761350104e-05,
+      "loss": 0.932,
+      "step": 51
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9754160498792964e-05,
+      "loss": 0.9377,
+      "step": 52
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.974037328225982e-05,
+      "loss": 1.061,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9726215010628717e-05,
+      "loss": 1.049,
+      "step": 54
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.971168622325259e-05,
+      "loss": 0.9426,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9696787473598993e-05,
+      "loss": 0.9608,
+      "step": 56
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.968151932922903e-05,
+      "loss": 1.0438,
+      "step": 57
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9665882371775735e-05,
+      "loss": 1.0972,
+      "step": 58
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.96498771969219e-05,
+      "loss": 1.062,
+      "step": 59
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.963350441437739e-05,
+      "loss": 1.0511,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9616764647855924e-05,
+      "loss": 1.0602,
+      "step": 61
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9599658535051312e-05,
+      "loss": 1.111,
+      "step": 62
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9582186727613152e-05,
+      "loss": 0.9868,
+      "step": 63
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9564349891122017e-05,
+      "loss": 0.9718,
+      "step": 64
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9546148705064097e-05,
+      "loss": 1.0348,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9527583862805303e-05,
+      "loss": 0.9947,
+      "step": 66
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9508656071564883e-05,
+      "loss": 0.9132,
+      "step": 67
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9489366052388443e-05,
+      "loss": 1.1411,
+      "step": 68
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.946971454012051e-05,
+      "loss": 0.8929,
+      "step": 69
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9449702283376516e-05,
+      "loss": 0.9863,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9429330044514305e-05,
+      "loss": 0.9028,
+      "step": 71
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9408598599605062e-05,
+      "loss": 1.0009,
+      "step": 72
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.938750873840377e-05,
+      "loss": 1.0323,
+      "step": 73
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9366061264319112e-05,
+      "loss": 1.205,
+      "step": 74
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.934425699438288e-05,
+      "loss": 1.0304,
+      "step": 75
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9322096759218838e-05,
+      "loss": 1.0166,
+      "step": 76
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9299581403011082e-05,
+      "loss": 0.9792,
+      "step": 77
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9276711783471888e-05,
+      "loss": 1.0663,
+      "step": 78
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9253488771809024e-05,
+      "loss": 1.0008,
+      "step": 79
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.922991325269258e-05,
+      "loss": 1.035,
+      "step": 80
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.920598612422125e-05,
+      "loss": 1.0196,
+      "step": 81
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9181708297888133e-05,
+      "loss": 0.9973,
+      "step": 82
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9157080698546e-05,
+      "loss": 1.0891,
+      "step": 83
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9132104264372065e-05,
+      "loss": 1.1233,
+      "step": 84
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.910677994683225e-05,
+      "loss": 0.9175,
+      "step": 85
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9081108710644933e-05,
+      "loss": 1.0085,
+      "step": 86
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9055091533744204e-05,
+      "loss": 1.0296,
+      "step": 87
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9028729407242598e-05,
+      "loss": 0.9736,
+      "step": 88
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9002023335393366e-05,
+      "loss": 1.0423,
+      "step": 89
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.897497433555218e-05,
+      "loss": 1.0293,
+      "step": 90
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.894758343813842e-05,
+      "loss": 0.9725,
+      "step": 91
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8919851686595875e-05,
+      "loss": 1.0399,
+      "step": 92
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8891780137353036e-05,
+      "loss": 1.0698,
+      "step": 93
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8863369859782824e-05,
+      "loss": 1.0414,
+      "step": 94
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.883462193616187e-05,
+      "loss": 1.0559,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8805537461629266e-05,
+      "loss": 1.0205,
+      "step": 96
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8776117544144866e-05,
+      "loss": 1.0146,
+      "step": 97
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8746363304447073e-05,
+      "loss": 1.0369,
+      "step": 98
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8716275876010135e-05,
+      "loss": 1.1089,
+      "step": 99
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8685856405000984e-05,
+      "loss": 1.0616,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.865510605023555e-05,
+      "loss": 1.1595,
+      "step": 101
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8624025983134643e-05,
+      "loss": 0.9224,
+      "step": 102
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8592617387679304e-05,
+      "loss": 0.9449,
+      "step": 103
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8560881460365726e-05,
+      "loss": 0.9947,
+      "step": 104
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8528819410159638e-05,
+      "loss": 0.9683,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8496432458450297e-05,
+      "loss": 1.0687,
+      "step": 106
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8463721839003917e-05,
+      "loss": 0.9345,
+      "step": 107
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8430688797916702e-05,
+      "loss": 0.9944,
+      "step": 108
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8397334593567347e-05,
+      "loss": 0.9834,
+      "step": 109
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.836366049656913e-05,
+      "loss": 0.9557,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8329667789721487e-05,
+      "loss": 0.9486,
+      "step": 111
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8295357767961144e-05,
+      "loss": 0.9461,
+      "step": 112
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8260731738312817e-05,
+      "loss": 1.0935,
+      "step": 113
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8225791019839375e-05,
+      "loss": 0.9832,
+      "step": 114
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8190536943591627e-05,
+      "loss": 1.1332,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8154970852557604e-05,
+      "loss": 0.9484,
+      "step": 116
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.811909410161139e-05,
+      "loss": 0.9992,
+      "step": 117
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8082908057461534e-05,
+      "loss": 0.9772,
+      "step": 118
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8046414098598947e-05,
+      "loss": 1.0294,
+      "step": 119
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8009613615244438e-05,
+      "loss": 1.0607,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.79725080092957e-05,
+      "loss": 0.9284,
+      "step": 121
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.793509869427395e-05,
+      "loss": 1.3684,
+      "step": 122
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7897387095270058e-05,
+      "loss": 1.0456,
+      "step": 123
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.785937464889027e-05,
+      "loss": 1.0026,
+      "step": 124
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.782106280320147e-05,
+      "loss": 0.903,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7782453017676025e-05,
+      "loss": 0.9958,
+      "step": 126
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7743546763136187e-05,
+      "loss": 0.9393,
+      "step": 127
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7704345521698057e-05,
+      "loss": 1.011,
+      "step": 128
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.766485078671514e-05,
+      "loss": 0.9844,
+      "step": 129
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7625064062721414e-05,
+      "loss": 0.9095,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7584986865374084e-05,
+      "loss": 1.069,
+      "step": 131
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.754462072139578e-05,
+      "loss": 1.0297,
+      "step": 132
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7503967168516426e-05,
+      "loss": 0.9506,
+      "step": 133
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.746302775541467e-05,
+      "loss": 1.0637,
+      "step": 134
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7421804041658867e-05,
+      "loss": 0.9747,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.738029759764767e-05,
+      "loss": 1.0646,
+      "step": 136
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7338510004550225e-05,
+      "loss": 0.903,
+      "step": 137
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7296442854245915e-05,
+      "loss": 1.0498,
+      "step": 138
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7254097749263735e-05,
+      "loss": 0.9385,
+      "step": 139
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.721147630272123e-05,
+      "loss": 0.9959,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7168580138263064e-05,
+      "loss": 1.195,
+      "step": 141
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7125410889999135e-05,
+      "loss": 0.9948,
+      "step": 142
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7081970202442363e-05,
+      "loss": 0.9771,
+      "step": 143
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.703825973044602e-05,
+      "loss": 1.0914,
+      "step": 144
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.699428113914069e-05,
+      "loss": 1.1004,
+      "step": 145
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.695003610387084e-05,
+      "loss": 0.9474,
+      "step": 146
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6905526310131e-05,
+      "loss": 0.9924,
+      "step": 147
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.686075345350156e-05,
+      "loss": 0.8992,
+      "step": 148
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.681571923958416e-05,
+      "loss": 1.0628,
+      "step": 149
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6770425383936734e-05,
+      "loss": 0.9987,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6724873612008155e-05,
+      "loss": 0.9921,
+      "step": 151
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6679065659072486e-05,
+      "loss": 0.9219,
+      "step": 152
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6633003270162903e-05,
+      "loss": 1.0066,
+      "step": 153
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6586688200005193e-05,
+      "loss": 0.9523,
+      "step": 154
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.654012221295093e-05,
+      "loss": 0.9338,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.649330708291025e-05,
+      "loss": 1.1743,
+      "step": 156
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6446244593284277e-05,
+      "loss": 0.9423,
+      "step": 157
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6398936536897182e-05,
+      "loss": 1.0983,
+      "step": 158
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6351384715927897e-05,
+      "loss": 1.0577,
+      "step": 159
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6303590941841457e-05,
+      "loss": 1.0107,
+      "step": 160
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.625555703531998e-05,
+      "loss": 1.0051,
+      "step": 161
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6207284826193334e-05,
+      "loss": 0.9868,
+      "step": 162
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6158776153369406e-05,
+      "loss": 1.0838,
+      "step": 163
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.611003286476406e-05,
+      "loss": 0.9899,
+      "step": 164
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6061056817230754e-05,
+      "loss": 1.0625,
+      "step": 165
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6011849876489777e-05,
+      "loss": 1.0744,
+      "step": 166
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.59624139170572e-05,
+      "loss": 1.2099,
+      "step": 167
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5912750822173446e-05,
+      "loss": 0.9299,
+      "step": 168
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5862862483731574e-05,
+      "loss": 0.956,
+      "step": 169
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5812750802205187e-05,
+      "loss": 1.04,
+      "step": 170
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.576241768657604e-05,
+      "loss": 1.2019,
+      "step": 171
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.571186505426132e-05,
+      "loss": 0.8532,
+      "step": 172
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.56610948310406e-05,
+      "loss": 0.9586,
+      "step": 173
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5610108950982494e-05,
+      "loss": 1.1052,
+      "step": 174
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5558909356370944e-05,
+      "loss": 1.1066,
+      "step": 175
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5507497997631267e-05,
+      "loss": 0.9839,
+      "step": 176
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.545587683325583e-05,
+      "loss": 1.0389,
+      "step": 177
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.540404782972946e-05,
+      "loss": 0.9958,
+      "step": 178
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.535201296145451e-05,
+      "loss": 1.0568,
+      "step": 179
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.529977421067566e-05,
+      "loss": 0.9631,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5247333567404407e-05,
+      "loss": 1.0225,
+      "step": 181
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5194693029343249e-05,
+      "loss": 1.0099,
+      "step": 182
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5141854601809583e-05,
+      "loss": 0.931,
+      "step": 183
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5088820297659314e-05,
+      "loss": 1.1087,
+      "step": 184
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5035592137210188e-05,
+      "loss": 1.0107,
+      "step": 185
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.4982172148164804e-05,
+      "loss": 0.9999,
+      "step": 186
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4928562365533393e-05,
+      "loss": 0.927,
+      "step": 187
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4874764831556285e-05,
+      "loss": 0.9624,
+      "step": 188
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4820781595626116e-05,
+      "loss": 0.9271,
+      "step": 189
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4766614714209748e-05,
+      "loss": 1.0568,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4712266250769932e-05,
+      "loss": 0.9526,
+      "step": 191
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4657738275686711e-05,
+      "loss": 0.9525,
+      "step": 192
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.460303286617854e-05,
+      "loss": 1.0047,
+      "step": 193
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4548152106223157e-05,
+      "loss": 1.0844,
+      "step": 194
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4493098086478196e-05,
+      "loss": 1.0315,
+      "step": 195
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4437872904201542e-05,
+      "loss": 0.9944,
+      "step": 196
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4382478663171449e-05,
+      "loss": 0.9606,
+      "step": 197
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4326917473606368e-05,
+      "loss": 1.1036,
+      "step": 198
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4271191452084598e-05,
+      "loss": 0.9404,
+      "step": 199
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4215302721463624e-05,
+      "loss": 1.0934,
+      "step": 200
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4159253410799272e-05,
+      "loss": 0.9587,
+      "step": 201
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4103045655264576e-05,
+      "loss": 1.1526,
+      "step": 202
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4046681596068468e-05,
+      "loss": 0.9883,
+      "step": 203
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3990163380374195e-05,
+      "loss": 1.003,
+      "step": 204
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3933493161217521e-05,
+      "loss": 0.9472,
+      "step": 205
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.387667309742472e-05,
+      "loss": 0.949,
+      "step": 206
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3819705353530322e-05,
+      "loss": 1.0019,
+      "step": 207
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3762592099694666e-05,
+      "loss": 1.1014,
+      "step": 208
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3705335511621229e-05,
+      "loss": 1.0855,
+      "step": 209
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3647937770473739e-05,
+      "loss": 1.0694,
+      "step": 210
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3590401062793084e-05,
+      "loss": 0.9958,
+      "step": 211
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3532727580414018e-05,
+      "loss": 1.0537,
+      "step": 212
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3474919520381673e-05,
+      "loss": 1.0812,
+      "step": 213
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3416979084867851e-05,
+      "loss": 0.9856,
+      "step": 214
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3358908481087133e-05,
+      "loss": 0.9998,
+      "step": 215
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.330070992121281e-05,
+      "loss": 1.0072,
+      "step": 216
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3242385622292593e-05,
+      "loss": 0.9522,
+      "step": 217
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3183937806164174e-05,
+      "loss": 1.2482,
+      "step": 218
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3125368699370567e-05,
+      "loss": 0.999,
+      "step": 219
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3066680533075312e-05,
+      "loss": 0.9447,
+      "step": 220
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3007875542977448e-05,
+      "loss": 1.0508,
+      "step": 221
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2948955969226384e-05,
+      "loss": 1.1029,
+      "step": 222
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2889924056336531e-05,
+      "loss": 1.0036,
+      "step": 223
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2830782053101807e-05,
+      "loss": 1.0508,
+      "step": 224
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2771532212509974e-05,
+      "loss": 1.1378,
+      "step": 225
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2712176791656807e-05,
+      "loss": 1.0185,
+      "step": 226
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2652718051660122e-05,
+      "loss": 1.1234,
+      "step": 227
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.259315825757362e-05,
+      "loss": 1.0036,
+      "step": 228
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2533499678300618e-05,
+      "loss": 1.0508,
+      "step": 229
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2473744586507606e-05,
+      "loss": 1.1163,
+      "step": 230
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2413895258537676e-05,
+      "loss": 1.0512,
+      "step": 231
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2353953974323807e-05,
+      "loss": 0.9337,
+      "step": 232
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2293923017302004e-05,
+      "loss": 1.0446,
+      "step": 233
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.223380467432432e-05,
+      "loss": 0.9448,
+      "step": 234
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.217360123557174e-05,
+      "loss": 0.9856,
+      "step": 235
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.211331499446693e-05,
+      "loss": 0.9578,
+      "step": 236
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2052948247586872e-05,
+      "loss": 0.8096,
+      "step": 237
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1992503294575385e-05,
+      "loss": 0.9109,
+      "step": 238
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1931982438055506e-05,
+      "loss": 1.014,
+      "step": 239
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1871387983541789e-05,
+      "loss": 1.0129,
+      "step": 240
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1810722239352468e-05,
+      "loss": 0.9497,
+      "step": 241
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1749987516521523e-05,
+      "loss": 0.9578,
+      "step": 242
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1689186128710654e-05,
+      "loss": 1.0114,
+      "step": 243
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1628320392121118e-05,
+      "loss": 1.0635,
+      "step": 244
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.156739262540552e-05,
+      "loss": 0.9527,
+      "step": 245
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.150640514957947e-05,
+      "loss": 1.0139,
+      "step": 246
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1445360287933165e-05,
+      "loss": 0.9126,
+      "step": 247
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1384260365942905e-05,
+      "loss": 0.9579,
+      "step": 248
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1323107711182474e-05,
+      "loss": 0.8946,
+      "step": 249
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1261904653234486e-05,
+      "loss": 1.0059,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1200653523601652e-05,
+      "loss": 0.9798,
+      "step": 251
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1139356655617945e-05,
+      "loss": 0.9536,
+      "step": 252
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1078016384359725e-05,
+      "loss": 1.0603,
+      "step": 253
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1016635046556773e-05,
+      "loss": 0.9435,
+      "step": 254
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0955214980503284e-05,
+      "loss": 0.9584,
+      "step": 255
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0893758525968789e-05,
+      "loss": 1.0198,
+      "step": 256
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0832268024109025e-05,
+      "loss": 0.9559,
+      "step": 257
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0770745817376741e-05,
+      "loss": 0.9561,
+      "step": 258
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0709194249432471e-05,
+      "loss": 0.8537,
+      "step": 259
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0647615665055251e-05,
+      "loss": 1.0372,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0586012410053293e-05,
+      "loss": 1.1696,
+      "step": 261
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0524386831174629e-05,
+      "loss": 1.0219,
+      "step": 262
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0462741276017711e-05,
+      "loss": 0.9949,
+      "step": 263
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0401078092941972e-05,
+      "loss": 0.886,
+      "step": 264
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0339399630978373e-05,
+      "loss": 1.2172,
+      "step": 265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0277708239739925e-05,
+      "loss": 0.9929,
+      "step": 266
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.021600626933217e-05,
+      "loss": 0.9677,
+      "step": 267
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0154296070263649e-05,
+      "loss": 0.9792,
+      "step": 268
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0092579993356386e-05,
+      "loss": 1.0348,
+      "step": 269
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0030860389656306e-05,
+      "loss": 1.0046,
+      "step": 270
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.969139610343696e-06,
+      "loss": 1.1282,
+      "step": 271
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.907420006643619e-06,
+      "loss": 1.0213,
+      "step": 272
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.845703929736351e-06,
+      "loss": 1.0319,
+      "step": 273
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.783993730667833e-06,
+      "loss": 0.9653,
+      "step": 274
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.722291760260077e-06,
+      "loss": 1.1236,
+      "step": 275
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.66060036902163e-06,
+      "loss": 1.0243,
+      "step": 276
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.598921907058033e-06,
+      "loss": 0.9902,
+      "step": 277
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.53725872398229e-06,
+      "loss": 0.9274,
+      "step": 278
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.475613168825374e-06,
+      "loss": 1.215,
+      "step": 279
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.41398758994671e-06,
+      "loss": 0.9316,
+      "step": 280
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.352384334944754e-06,
+      "loss": 1.0422,
+      "step": 281
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.290805750567532e-06,
+      "loss": 1.1358,
+      "step": 282
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.22925418262326e-06,
+      "loss": 0.9926,
+      "step": 283
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.167731975890977e-06,
+      "loss": 0.9155,
+      "step": 284
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.106241474031213e-06,
+      "loss": 0.9292,
+      "step": 285
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.04478501949672e-06,
+      "loss": 0.9266,
+      "step": 286
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.983364953443227e-06,
+      "loss": 1.0313,
+      "step": 287
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.921983615640277e-06,
+      "loss": 1.0648,
+      "step": 288
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.860643344382057e-06,
+      "loss": 1.0713,
+      "step": 289
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.799346476398351e-06,
+      "loss": 0.8234,
+      "step": 290
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.738095346765519e-06,
+      "loss": 0.9235,
+      "step": 291
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.676892288817531e-06,
+      "loss": 1.0543,
+      "step": 292
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.615739634057098e-06,
+      "loss": 1.0305,
+      "step": 293
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.554639712066837e-06,
+      "loss": 1.0071,
+      "step": 294
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.493594850420537e-06,
+      "loss": 0.9926,
+      "step": 295
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.432607374594484e-06,
+      "loss": 0.9834,
+      "step": 296
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.371679607878884e-06,
+      "loss": 0.9733,
+      "step": 297
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.310813871289349e-06,
+      "loss": 1.0198,
+      "step": 298
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.250012483478478e-06,
+      "loss": 0.8944,
+      "step": 299
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.189277760647537e-06,
+      "loss": 1.0853,
+      "step": 300
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.128612016458214e-06,
+      "loss": 0.9688,
+      "step": 301
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.0680175619445e-06,
+      "loss": 1.0182,
+      "step": 302
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.00749670542462e-06,
+      "loss": 1.0056,
+      "step": 303
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.947051752413131e-06,
+      "loss": 1.0006,
+      "step": 304
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.886685005533073e-06,
+      "loss": 1.0194,
+      "step": 305
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.826398764428261e-06,
+      "loss": 0.9406,
+      "step": 306
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.766195325675681e-06,
+      "loss": 0.7382,
+      "step": 307
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.706076982698e-06,
+      "loss": 1.205,
+      "step": 308
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.646046025676198e-06,
+      "loss": 0.9854,
+      "step": 309
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.586104741462326e-06,
+      "loss": 0.9266,
+      "step": 310
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.526255413492396e-06,
+      "loss": 0.9455,
+      "step": 311
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.4665003216993835e-06,
+      "loss": 0.8424,
+      "step": 312
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.40684174242638e-06,
+      "loss": 1.0366,
+      "step": 313
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.34728194833988e-06,
+      "loss": 1.1087,
+      "step": 314
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.287823208343192e-06,
+      "loss": 1.0448,
+      "step": 315
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.2284677874900285e-06,
+      "loss": 1.0783,
+      "step": 316
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.169217946898197e-06,
+      "loss": 1.1065,
+      "step": 317
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.110075943663473e-06,
+      "loss": 0.9442,
+      "step": 318
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.051044030773619e-06,
+      "loss": 1.1005,
+      "step": 319
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.9921244570225536e-06,
+      "loss": 1.0234,
+      "step": 320
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.933319466924693e-06,
+      "loss": 1.0285,
+      "step": 321
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.874631300629435e-06,
+      "loss": 0.9707,
+      "step": 322
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.81606219383583e-06,
+      "loss": 0.9826,
+      "step": 323
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.757614377707409e-06,
+      "loss": 0.8997,
+      "step": 324
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.699290078787193e-06,
+      "loss": 1.0546,
+      "step": 325
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.6410915189128675e-06,
+      "loss": 1.138,
+      "step": 326
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.5830209151321525e-06,
+      "loss": 1.1151,
+      "step": 327
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.525080479618331e-06,
+      "loss": 1.1214,
+      "step": 328
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.467272419585984e-06,
+      "loss": 0.9674,
+      "step": 329
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.40959893720692e-06,
+      "loss": 1.0787,
+      "step": 330
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.352062229526266e-06,
+      "loss": 0.9351,
+      "step": 331
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.294664488378777e-06,
+      "loss": 1.0169,
+      "step": 332
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.237407900305334e-06,
+      "loss": 0.9301,
+      "step": 333
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.18029464646968e-06,
+      "loss": 0.9611,
+      "step": 334
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.123326902575282e-06,
+      "loss": 1.0809,
+      "step": 335
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.06650683878248e-06,
+      "loss": 1.0369,
+      "step": 336
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.0098366196258095e-06,
+      "loss": 0.9603,
+      "step": 337
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.953318403931533e-06,
+      "loss": 1.018,
+      "step": 338
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.896954344735426e-06,
+      "loss": 0.9963,
+      "step": 339
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.840746589200732e-06,
+      "loss": 0.9803,
+      "step": 340
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.78469727853638e-06,
+      "loss": 0.9496,
+      "step": 341
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.728808547915405e-06,
+      "loss": 0.9574,
+      "step": 342
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.673082526393634e-06,
+      "loss": 1.0413,
+      "step": 343
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.617521336828556e-06,
+      "loss": 1.0234,
+      "step": 344
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.5621270957984575e-06,
+      "loss": 0.9281,
+      "step": 345
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.506901913521808e-06,
+      "loss": 0.9141,
+      "step": 346
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.451847893776845e-06,
+      "loss": 1.0553,
+      "step": 347
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.396967133821461e-06,
+      "loss": 1.0136,
+      "step": 348
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.342261724313292e-06,
+      "loss": 0.8781,
+      "step": 349
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.287733749230071e-06,
+      "loss": 1.0005,
+      "step": 350
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.233385285790258e-06,
+      "loss": 1.0315,
+      "step": 351
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.179218404373886e-06,
+      "loss": 0.9875,
+      "step": 352
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.125235168443714e-06,
+      "loss": 1.0762,
+      "step": 353
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.0714376344666095e-06,
+      "loss": 0.9883,
+      "step": 354
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.017827851835199e-06,
+      "loss": 1.0402,
+      "step": 355
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.964407862789817e-06,
+      "loss": 0.9832,
+      "step": 356
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.9111797023406884e-06,
+      "loss": 1.064,
+      "step": 357
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.8581453981904205e-06,
+      "loss": 0.8565,
+      "step": 358
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.8053069706567555e-06,
+      "loss": 0.9622,
+      "step": 359
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.752666432595596e-06,
+      "loss": 0.9257,
+      "step": 360
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.700225789324343e-06,
+      "loss": 1.0264,
+      "step": 361
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.647987038545496e-06,
+      "loss": 0.9795,
+      "step": 362
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.595952170270542e-06,
+      "loss": 1.1062,
+      "step": 363
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.5441231667441724e-06,
+      "loss": 0.878,
+      "step": 364
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.492502002368738e-06,
+      "loss": 1.1202,
+      "step": 365
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.441090643629057e-06,
+      "loss": 0.9125,
+      "step": 366
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.389891049017511e-06,
+      "loss": 0.9245,
+      "step": 367
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.3389051689594e-06,
+      "loss": 0.8584,
+      "step": 368
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.288134945738684e-06,
+      "loss": 0.9324,
+      "step": 369
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.2375823134239624e-06,
+      "loss": 0.9386,
+      "step": 370
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.1872491977948125e-06,
+      "loss": 1.072,
+      "step": 371
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.1371375162684255e-06,
+      "loss": 1.0002,
+      "step": 372
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.087249177826553e-06,
+      "loss": 1.0169,
+      "step": 373
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.037586082942805e-06,
+      "loss": 0.9317,
+      "step": 374
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.988150123510224e-06,
+      "loss": 1.0668,
+      "step": 375
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.9389431827692455e-06,
+      "loss": 1.1167,
+      "step": 376
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.88996713523594e-06,
+      "loss": 0.9246,
+      "step": 377
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.841223846630599e-06,
+      "loss": 1.3171,
+      "step": 378
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7927151738066693e-06,
+      "loss": 1.092,
+      "step": 379
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7444429646800206e-06,
+      "loss": 0.9919,
+      "step": 380
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.696409058158544e-06,
+      "loss": 0.9269,
+      "step": 381
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6486152840721046e-06,
+      "loss": 1.0242,
+      "step": 382
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.601063463102823e-06,
+      "loss": 1.0446,
+      "step": 383
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.553755406715724e-06,
+      "loss": 0.9833,
+      "step": 384
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.506692917089751e-06,
+      "loss": 1.0029,
+      "step": 385
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.4598777870490717e-06,
+      "loss": 0.9458,
+      "step": 386
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.4133117999948086e-06,
+      "loss": 1.0084,
+      "step": 387
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.366996729837102e-06,
+      "loss": 1.0454,
+      "step": 388
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.320934340927513e-06,
+      "loss": 1.0022,
+      "step": 389
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.275126387991847e-06,
+      "loss": 1.0804,
+      "step": 390
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.229574616063268e-06,
+      "loss": 1.0618,
+      "step": 391
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.184280760415843e-06,
+      "loss": 0.8866,
+      "step": 392
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1392465464984455e-06,
+      "loss": 1.0266,
+      "step": 393
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.094473689869002e-06,
+      "loss": 1.0078,
+      "step": 394
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0499638961291623e-06,
+      "loss": 0.9705,
+      "step": 395
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0057188608593146e-06,
+      "loss": 0.9405,
+      "step": 396
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.961740269553981e-06,
+      "loss": 1.0097,
+      "step": 397
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9180297975576368e-06,
+      "loss": 1.1537,
+      "step": 398
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8745891100008683e-06,
+      "loss": 0.967,
+      "step": 399
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8314198617369403e-06,
+      "loss": 0.8564,
+      "step": 400
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.7885236972787733e-06,
+      "loss": 0.919,
+      "step": 401
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7459022507362687e-06,
+      "loss": 1.0236,
+      "step": 402
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7035571457540865e-06,
+      "loss": 0.964,
+      "step": 403
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6614899954497797e-06,
+      "loss": 1.0324,
+      "step": 404
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.619702402352332e-06,
+      "loss": 0.9101,
+      "step": 405
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5781959583411375e-06,
+      "loss": 0.9287,
+      "step": 406
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.536972244585331e-06,
+      "loss": 1.0566,
+      "step": 407
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4960328314835746e-06,
+      "loss": 0.9279,
+      "step": 408
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.455379278604226e-06,
+      "loss": 1.021,
+      "step": 409
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.41501313462592e-06,
+      "loss": 0.8296,
+      "step": 410
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3749359372785884e-06,
+      "loss": 0.9509,
+      "step": 411
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3351492132848665e-06,
+      "loss": 0.9372,
+      "step": 412
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.295654478301942e-06,
+      "loss": 1.0208,
+      "step": 413
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.256453236863815e-06,
+      "loss": 1.0768,
+      "step": 414
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.217546982323977e-06,
+      "loss": 1.0822,
+      "step": 415
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.178937196798534e-06,
+      "loss": 1.0618,
+      "step": 416
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.140625351109733e-06,
+      "loss": 1.0208,
+      "step": 417
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.1026129047299436e-06,
+      "loss": 0.8305,
+      "step": 418
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.064901305726055e-06,
+      "loss": 1.0297,
+      "step": 419
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0274919907043033e-06,
+      "loss": 0.9256,
+      "step": 420
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.990386384755565e-06,
+      "loss": 0.9384,
+      "step": 421
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9535859014010525e-06,
+      "loss": 0.9526,
+      "step": 422
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.9170919425384695e-06,
+      "loss": 1.1685,
+      "step": 423
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.880905898388612e-06,
+      "loss": 0.8731,
+      "step": 424
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8450291474423999e-06,
+      "loss": 0.9038,
+      "step": 425
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8094630564083737e-06,
+      "loss": 0.9914,
+      "step": 426
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7742089801606278e-06,
+      "loss": 0.9217,
+      "step": 427
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7392682616871836e-06,
+      "loss": 0.9949,
+      "step": 428
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7046422320388556e-06,
+      "loss": 1.0348,
+      "step": 429
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6703322102785168e-06,
+      "loss": 0.8882,
+      "step": 430
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6363395034308704e-06,
+      "loss": 0.9555,
+      "step": 431
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6026654064326553e-06,
+      "loss": 1.0105,
+      "step": 432
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5693112020833012e-06,
+      "loss": 1.0233,
+      "step": 433
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5362781609960853e-06,
+      "loss": 0.8375,
+      "step": 434
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5035675415497064e-06,
+      "loss": 0.9687,
+      "step": 435
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.471180589840363e-06,
+      "loss": 1.0763,
+      "step": 436
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4391185396342787e-06,
+      "loss": 0.8356,
+      "step": 437
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4073826123206946e-06,
+      "loss": 1.0506,
+      "step": 438
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.375974016865359e-06,
+      "loss": 1.0625,
+      "step": 439
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3448939497644508e-06,
+      "loss": 0.9615,
+      "step": 440
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3141435949990188e-06,
+      "loss": 0.9799,
+      "step": 441
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2837241239898669e-06,
+      "loss": 1.0765,
+      "step": 442
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.253636695552931e-06,
+      "loss": 1.0043,
+      "step": 443
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2238824558551365e-06,
+      "loss": 1.0117,
+      "step": 444
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1944625383707377e-06,
+      "loss": 0.8158,
+      "step": 445
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.165378063838133e-06,
+      "loss": 0.9406,
+      "step": 446
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1366301402171775e-06,
+      "loss": 1.0382,
+      "step": 447
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1082198626469687e-06,
+      "loss": 0.9529,
+      "step": 448
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.080148313404127e-06,
+      "loss": 0.9811,
+      "step": 449
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0524165618615845e-06,
+      "loss": 0.8795,
+      "step": 450
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0250256644478196e-06,
+      "loss": 0.9581,
+      "step": 451
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.979766646066368e-07,
+      "loss": 0.9823,
+      "step": 452
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.71270592757404e-07,
+      "loss": 0.9371,
+      "step": 453
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.449084662557984e-07,
+      "loss": 0.9674,
+      "step": 454
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.188912893550694e-07,
+      "loss": 0.9306,
+      "step": 455
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.932200531677537e-07,
+      "loss": 1.1018,
+      "step": 456
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.678957356279372e-07,
+      "loss": 0.8571,
+      "step": 457
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.429193014540015e-07,
+      "loss": 1.0098,
+      "step": 458
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.182917021118664e-07,
+      "loss": 0.8574,
+      "step": 459
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.940138757787507e-07,
+      "loss": 1.0129,
+      "step": 460
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.700867473074225e-07,
+      "loss": 1.109,
+      "step": 461
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.46511228190977e-07,
+      "loss": 0.8979,
+      "step": 462
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.232882165281141e-07,
+      "loss": 0.9884,
+      "step": 463
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.004185969889188e-07,
+      "loss": 1.1263,
+      "step": 464
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.779032407811636e-07,
+      "loss": 1.164,
+      "step": 465
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.557430056171221e-07,
+      "loss": 0.8073,
+      "step": 466
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.339387356808912e-07,
+      "loss": 1.0606,
+      "step": 467
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.124912615962341e-07,
+      "loss": 1.0234,
+      "step": 468
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.914014003949408e-07,
+      "loss": 1.0694,
+      "step": 469
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.706699554856965e-07,
+      "loss": 1.0804,
+      "step": 470
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.502977166234857e-07,
+      "loss": 0.9358,
+      "step": 471
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.302854598794938e-07,
+      "loss": 1.0226,
+      "step": 472
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.106339476115596e-07,
+      "loss": 1.0955,
+      "step": 473
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.913439284351207e-07,
+      "loss": 0.9492,
+      "step": 474
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.7241613719469784e-07,
+      "loss": 0.8924,
+      "step": 475
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.538512949359075e-07,
+      "loss": 0.9072,
+      "step": 476
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.356501088779841e-07,
+      "loss": 0.9692,
+      "step": 477
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.1781327238684775e-07,
+      "loss": 0.9852,
+      "step": 478
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.003414649486892e-07,
+      "loss": 0.8978,
+      "step": 479
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.832353521440768e-07,
+      "loss": 0.9217,
+      "step": 480
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.6649558562261377e-07,
+      "loss": 1.0179,
+      "step": 481
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.5012280307810344e-07,
+      "loss": 0.8973,
+      "step": 482
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.341176282242653e-07,
+      "loss": 0.9245,
+      "step": 483
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.184806707709698e-07,
+      "loss": 0.8216,
+      "step": 484
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.0321252640100883e-07,
+      "loss": 1.0511,
+      "step": 485
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.8831377674741203e-07,
+      "loss": 0.9983,
+      "step": 486
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.737849893712841e-07,
+      "loss": 0.945,
+      "step": 487
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.5962671774018234e-07,
+      "loss": 1.023,
+      "step": 488
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.458395012070369e-07,
+      "loss": 1.0748,
+      "step": 489
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.3242386498960267e-07,
+      "loss": 0.9754,
+      "step": 490
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.1938032015044964e-07,
+      "loss": 0.9531,
+      "step": 491
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.067093635774975e-07,
+      "loss": 0.9747,
+      "step": 492
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9441147796508408e-07,
+      "loss": 1.0484,
+      "step": 493
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8248713179557788e-07,
+      "loss": 0.9075,
+      "step": 494
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.7093677932153218e-07,
+      "loss": 1.0215,
+      "step": 495
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5976086054838024e-07,
+      "loss": 0.9313,
+      "step": 496
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.4895980121767627e-07,
+      "loss": 0.9872,
+      "step": 497
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3853401279086853e-07,
+      "loss": 1.0439,
+      "step": 498
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2848389243363514e-07,
+      "loss": 0.8577,
+      "step": 499
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1880982300074839e-07,
+      "loss": 1.0613,
+      "step": 500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0951217302148986e-07,
+      "loss": 1.048,
+      "step": 501
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0059129668561707e-07,
+      "loss": 0.9441,
+      "step": 502
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.204753382986097e-08,
+      "loss": 0.9795,
+      "step": 503
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.388120992499083e-08,
+      "loss": 1.0613,
+      "step": 504
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.609263606340622e-08,
+      "loss": 0.8849,
+      "step": 505
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.868210894729333e-08,
+      "loss": 0.9591,
+      "step": 506
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 6.164991087731831e-08,
+      "loss": 0.898,
+      "step": 507
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.4996309741873755e-08,
+      "loss": 0.8596,
+      "step": 508
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.8721559006873473e-08,
+      "loss": 1.0341,
+      "step": 509
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.2825897706100237e-08,
+      "loss": 1.0509,
+      "step": 510
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.730955043209083e-08,
+      "loss": 1.0373,
+      "step": 511
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.2172727327594024e-08,
+      "loss": 1.1891,
+      "step": 512
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.7415624077551383e-08,
+      "loss": 0.9783,
+      "step": 513
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.3038421901651064e-08,
+      "loss": 0.9968,
+      "step": 514
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.9041287547424404e-08,
+      "loss": 0.7965,
+      "step": 515
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5424373283889904e-08,
+      "loss": 0.9412,
+      "step": 516
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.2187816895752324e-08,
+      "loss": 1.0623,
+      "step": 517
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.3317416781602e-09,
+      "loss": 1.092,
+      "step": 518
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.856256432000719e-09,
+      "loss": 1.0168,
+      "step": 519
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.761455459760811e-09,
+      "loss": 0.9015,
+      "step": 520
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.0474185619333573e-09,
+      "loss": 0.891,
+      "step": 521
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.7142110339740669e-09,
+      "loss": 1.0192,
+      "step": 522
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.618836638190186e-10,
+      "loss": 0.9934,
+      "step": 523
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.904727299473219e-10,
+      "loss": 0.9555,
+      "step": 524
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 1.0071,
+      "step": 525
+    },
+    {
+      "epoch": 1.0,
+      "step": 525,
+      "total_flos": 408411124531200.0,
+      "train_loss": 1.008456783521743,
+      "train_runtime": 75047.9043,
+      "train_samples_per_second": 0.336,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 525,
+  "num_train_epochs": 1,
+  "save_steps": 400,
+  "total_flos": 408411124531200.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a8863c39c2acf6593998cb3e18152c9a1405c0379daeefefed8074235e9fa0
+size 6648