Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: other
+base_model: 01-ai/Yi-34B
+tags:
+- generated_from_trainer
+model-index:
+- name: yi_4k_paged_optimizer
+  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. -->
+
+# yi_4k_paged_optimizer
+
+This model is a fine-tuned version of [01-ai/Yi-34B](https://huggingface.co/01-ai/Yi-34B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5581
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- 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: 0.1
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.2057        | 0.99  | 31   | 0.9855          |
+| 0.5676        | 1.98  | 62   | 0.5699          |
+| 0.5608        | 2.98  | 93   | 0.5596          |
+| 0.5576        | 3.97  | 124  | 0.5581          |
+
+
+### Framework versions
+
+- Transformers 4.36.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.97,
+    "eval_loss": 0.5581246018409729,
+    "eval_runtime": 79.6437,
+    "eval_samples": 110,
+    "eval_samples_per_second": 1.381,
+    "eval_steps_per_second": 0.176,
+    "train_loss": 0.8594164925236856,
+    "train_runtime": 9510.8221,
+    "train_samples": 995,
+    "train_samples_per_second": 0.418,
+    "train_steps_per_second": 0.013
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "01-ai/Yi-34B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.0",
+  "use_cache": false,
+  "vocab_size": 64000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.97,
+    "eval_loss": 0.5581246018409729,
+    "eval_runtime": 79.6437,
+    "eval_samples": 110,
+    "eval_samples_per_second": 1.381,
+    "eval_steps_per_second": 0.176
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.0"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ac0e8586c07b14c23f9f956f63cc7a23d8179024274dba60a570a90ecc67c9
+size 4793130760

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd2d52d0d74407ee10f3a9926a75e317b3b8f72a9800521af8fd78fdc41a2bea
+size 4756459720

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aab3318816ea951d0693ea25c8c17c49aa242f0ad53de7f54dfdcd4331896b3
+size 4991370136

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f2a57596b23b9cc89a47f34cb61c805cda5dc175245dfc4e697aa2deaf0f0de
+size 4756459760

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9438f58d8f3a3ce7b19affdb25e8b747e91574d5e18982e215f3ff568c06dd43
+size 4756459760

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5694f9c57fbb4d177316d59bb4cbada434dabe578f209f5db361ee8366dca428
+size 4991370160

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522b115ebfab75069365aef2b6dc1d9a8ef82f1818a893f2a99426479871936e
+size 4756459760

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca461a29ff4ca39a364260de433ef47bdbb3003c2de9d4f1c0f994f1ab2c3c79
+size 4756459760

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d713ad5ab7571af59acada3bbaf436458cc8d356359d38c07f2446340976373
+size 4991370160

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bde8a5083290833b51cad997ee052724795ede8b1b0954f9307a75955ccf9bad
+size 4756459760

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b7bf39d9cabb2b6eeebf46d00375da3a217e188103abba6281b79acab47e045
+size 4756459760

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb5c30a8aadd61613e2e9e1c1992caf318fc22b08a5bcc47db11b189d5ccbc5f
+size 4991370160

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2e10a23b3ecb5fedf1c70609919fe36f841215433f3354856d5475a294b7ce4
+size 4756459760

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c9300edb74f953173318220c38eae846e55517ba646f96a370d38a03c882900
+size 4756459760

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:773e5c46300d731d83de2d766be923603916eb44a42d604cfd8a825b6185acb6
+size 1211148856

model.safetensors.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 68777834496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00015-of-00015.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.norm.weight": "model-00015-of-00015.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '### Input:\n' + message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ '### Instruction:' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '\n### Response:\n'  + message['content'] }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '### Response:' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.97,
+    "train_loss": 0.8594164925236856,
+    "train_runtime": 9510.8221,
+    "train_samples": 995,
+    "train_samples_per_second": 0.418,
+    "train_steps_per_second": 0.013
+}

trainer_state.json

@@ -0,0 +1,206 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.968,
+  "eval_steps": 500,
+  "global_step": 124,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9230769230769231e-07,
+      "loss": 1.9369,
+      "step": 5
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.8461538461538463e-07,
+      "loss": 1.9166,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.995995873155957e-07,
+      "loss": 1.8806,
+      "step": 15
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.951096619903317e-07,
+      "loss": 1.7313,
+      "step": 20
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.85719361365271e-07,
+      "loss": 1.5518,
+      "step": 25
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.7161642180652463e-07,
+      "loss": 1.2057,
+      "step": 30
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 0.9854549169540405,
+      "eval_runtime": 79.0664,
+      "eval_samples_per_second": 1.391,
+      "eval_steps_per_second": 0.177,
+      "step": 31
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.5308279750597144e-07,
+      "loss": 0.9383,
+      "step": 35
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.3048902348863106e-07,
+      "loss": 0.6736,
+      "step": 40
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 4.042868076603638e-07,
+      "loss": 0.6114,
+      "step": 45
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 3.75e-07,
+      "loss": 0.5736,
+      "step": 50
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.4321411944507714e-07,
+      "loss": 0.5836,
+      "step": 55
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 3.095646478557912e-07,
+      "loss": 0.5676,
+      "step": 60
+    },
+    {
+      "epoch": 1.98,
+      "eval_loss": 0.569873571395874,
+      "eval_runtime": 79.9371,
+      "eval_samples_per_second": 1.376,
+      "eval_steps_per_second": 0.175,
+      "step": 62
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2.747243250910625e-07,
+      "loss": 0.5831,
+      "step": 65
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 2.3938969920096296e-07,
+      "loss": 0.5583,
+      "step": 70
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.0426720063190333e-07,
+      "loss": 0.5599,
+      "step": 75
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.7005901885718867e-07,
+      "loss": 0.5424,
+      "step": 80
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.3744906379558164e-07,
+      "loss": 0.5574,
+      "step": 85
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 1.0708929268538034e-07,
+      "loss": 0.5608,
+      "step": 90
+    },
+    {
+      "epoch": 2.98,
+      "eval_loss": 0.5596022605895996,
+      "eval_runtime": 80.1059,
+      "eval_samples_per_second": 1.373,
+      "eval_steps_per_second": 0.175,
+      "step": 93
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 7.958667577511683e-08,
+      "loss": 0.5648,
+      "step": 95
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 5.5491061420390174e-08,
+      "loss": 0.551,
+      "step": 100
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 3.528418319489348e-08,
+      "loss": 0.5471,
+      "step": 105
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 1.9370028791882847e-08,
+      "loss": 0.5572,
+      "step": 110
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 8.066763266625282e-09,
+      "loss": 0.5416,
+      "step": 115
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 1.6003680950742726e-09,
+      "loss": 0.5576,
+      "step": 120
+    },
+    {
+      "epoch": 3.97,
+      "eval_loss": 0.5581246018409729,
+      "eval_runtime": 79.6401,
+      "eval_samples_per_second": 1.381,
+      "eval_steps_per_second": 0.176,
+      "step": 124
+    },
+    {
+      "epoch": 3.97,
+      "step": 124,
+      "total_flos": 23406615330816.0,
+      "train_loss": 0.8594164925236856,
+      "train_runtime": 9510.8221,
+      "train_samples_per_second": 0.418,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 124,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 23406615330816.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de46b7bcd2163c0d2be3c4dc434518dec2bb737f0a547f8dcc8f6878a58d839c
+size 5371