Upload folder using huggingface_hub

README.md

@@ -0,0 +1,140 @@
+---
+license: mit
+base_model: microsoft/phi-2
+tags:
+- generated_from_trainer
+model-index:
+- name: phi-sft-out
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: microsoft/phi-2
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+trust_remote_code: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: tatsu-lab/alpaca
+    type: alpaca
+
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./phi-sft-out
+
+sequence_len: 2048
+sample_packing: false  # currently unsupported
+pad_to_sequence_len:
+
+wandb_project: phi2
+wandb_entity: oaaic
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 8
+micro_batch_size: 4
+num_epochs: 1
+optimizer: paged_adamw_8bit
+adam_beta2: 0.95
+adam_epsilon: 0.00001
+max_grad_norm: 1.0
+lr_scheduler: cosine
+learning_rate: 1e-5
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: true
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 100
+evals_per_epoch: 4
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+resize_token_embeddings_to_32x: true
+special_tokens:
+  pad_token: "<|endoftext|>"
+
+
+```
+
+</details><br>
+
+# phi-sft-out
+
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9915
+
+## 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: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 7
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 224
+- total_eval_batch_size: 28
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.4814        | 0.0   | 1    | 1.4537          |
+| 1.3529        | 0.25  | 55   | 1.3007          |
+| 1.2246        | 0.5   | 110  | 1.0940          |
+| 1.0636        | 0.75  | 165  | 0.9949          |
+| 1.0758        | 1.0   | 220  | 0.9915          |
+
+
+### Framework versions
+
+- Transformers 4.38.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.17.0
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

checkpoint-220/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "microsoft/phi-2",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": false,
+  "vocab_size": 51200
+}

checkpoint-220/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "do_sample": true,
+  "eos_token_id": 50256,
+  "transformers_version": "4.38.0.dev0"
+}

checkpoint-220/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a27f467106712ae3913c67156f8468cdc450dbb6623e5eafaf673f7b4919d9
+size 4995584848

checkpoint-220/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51fb51b33f6ec5cc80eed9035f96d56cf248499c3801c02ecc2a3fd45ebdc019
+size 563833008

checkpoint-220/model.safetensors.index.json

@@ -0,0 +1,460 @@
+{
+  "metadata": {
+    "total_size": 5559367680
+  },
+  "weight_map": {
+    "lm_head.bias": "model-00002-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.final_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

checkpoint-220/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f8ab8a3f723915816a2add7f618fb6a1c622337e5b519a9f9a30bb1f47c7940
+size 5574102019

checkpoint-220/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad0c8f4aa862e9b030759863bf5e97910ffa684c2c4397e9f57246e79abb281
+size 20663

checkpoint-220/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e5a024cf12b9a48c7ef8bb48d98d0c8d504d02cfa170952478a9c1fd11d3ea
+size 20663

checkpoint-220/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a178dfa84dcdc108f7e0ebedf5e46fb8166edfbce9a4a223bd4808766ce12695
+size 20663

checkpoint-220/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d80c01970d27fbca467cf9a6f44fa80f3ec7080628fb49ed6c89cd2189f43e
+size 20663

checkpoint-220/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4907422b26810533a39fc4028eb15b0507866bea5c5672c45206ae40c5f82caa
+size 20663

checkpoint-220/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b7eeefb7aeda23759fb5230d73bd58cf415696cbfafc101e41f295d07cf84c
+size 20663

checkpoint-220/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:783123baa6c5fbb41e2851a96c83c387b26240d8eb53bc933bc8f432e3ad7d7b
+size 20663

checkpoint-220/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e741d442a7097eedcfdd64f281d3d63b3cc1ab7b1847d36c1c51b161c2d90bc
+size 627

checkpoint-220/trainer_state.json

@@ -0,0 +1,1381 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9971671388101983,
+  "eval_steps": 55,
+  "global_step": 220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 1.4814,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 1.4537283182144165,
+      "eval_runtime": 5.2647,
+      "eval_samples_per_second": 494.046,
+      "eval_steps_per_second": 17.665,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 1.3904,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 1.5035,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.5594,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.3623,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 1.4823,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 1.3817,
+      "step": 7
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.4402,
+      "step": 8
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 1.3728,
+      "step": 9
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.5025,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1e-06,
+      "loss": 1.4032,
+      "step": 11
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.3889,
+      "step": 12
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3e-06,
+      "loss": 1.6009,
+      "step": 13
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 1.4421,
+      "step": 14
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5e-06,
+      "loss": 1.5008,
+      "step": 15
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.5311,
+      "step": 16
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 1.3308,
+      "step": 17
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 1.3582,
+      "step": 18
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 1.5426,
+      "step": 19
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.3096,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 1.4453,
+      "step": 21
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.2e-06,
+      "loss": 1.5165,
+      "step": 22
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 1.3552,
+      "step": 23
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.3963,
+      "step": 24
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.5e-06,
+      "loss": 1.3657,
+      "step": 25
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.6e-06,
+      "loss": 1.4383,
+      "step": 26
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 1.4539,
+      "step": 27
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.3158,
+      "step": 28
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.9e-06,
+      "loss": 1.4113,
+      "step": 29
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3e-06,
+      "loss": 1.4426,
+      "step": 30
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 1.3938,
+      "step": 31
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 1.3704,
+      "step": 32
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 1.4268,
+      "step": 33
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 1.3662,
+      "step": 34
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.5e-06,
+      "loss": 1.4189,
+      "step": 35
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 1.3602,
+      "step": 36
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.7e-06,
+      "loss": 1.2845,
+      "step": 37
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 1.4432,
+      "step": 38
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 1.412,
+      "step": 39
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.396,
+      "step": 40
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.1e-06,
+      "loss": 1.3463,
+      "step": 41
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 1.3552,
+      "step": 42
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.3e-06,
+      "loss": 1.3606,
+      "step": 43
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.4e-06,
+      "loss": 1.33,
+      "step": 44
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.5e-06,
+      "loss": 1.3242,
+      "step": 45
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 1.3012,
+      "step": 46
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.7e-06,
+      "loss": 1.3414,
+      "step": 47
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.4236,
+      "step": 48
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 1.3572,
+      "step": 49
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 5e-06,
+      "loss": 1.4086,
+      "step": 50
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 5.1e-06,
+      "loss": 1.2868,
+      "step": 51
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 5.2e-06,
+      "loss": 1.2877,
+      "step": 52
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 5.300000000000001e-06,
+      "loss": 1.2699,
+      "step": 53
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 5.400000000000001e-06,
+      "loss": 1.3287,
+      "step": 54
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 1.3529,
+      "step": 55
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.300736904144287,
+      "eval_runtime": 5.7333,
+      "eval_samples_per_second": 453.669,
+      "eval_steps_per_second": 16.221,
+      "step": 55
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 1.2862,
+      "step": 56
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 5.7e-06,
+      "loss": 1.3115,
+      "step": 57
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 5.8e-06,
+      "loss": 1.3377,
+      "step": 58
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 5.9e-06,
+      "loss": 1.3842,
+      "step": 59
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 6e-06,
+      "loss": 1.38,
+      "step": 60
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 6.1e-06,
+      "loss": 1.3856,
+      "step": 61
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 6.200000000000001e-06,
+      "loss": 1.2891,
+      "step": 62
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 6.300000000000001e-06,
+      "loss": 1.2762,
+      "step": 63
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 1.356,
+      "step": 64
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 1.3018,
+      "step": 65
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 6.600000000000001e-06,
+      "loss": 1.3118,
+      "step": 66
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 6.700000000000001e-06,
+      "loss": 1.3355,
+      "step": 67
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.2342,
+      "step": 68
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 6.9e-06,
+      "loss": 1.3015,
+      "step": 69
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7e-06,
+      "loss": 1.2471,
+      "step": 70
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7.100000000000001e-06,
+      "loss": 1.2873,
+      "step": 71
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 1.2805,
+      "step": 72
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.3e-06,
+      "loss": 1.2326,
+      "step": 73
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.4e-06,
+      "loss": 1.238,
+      "step": 74
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.3337,
+      "step": 75
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 1.3518,
+      "step": 76
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.7e-06,
+      "loss": 1.2328,
+      "step": 77
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.2552,
+      "step": 78
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 7.9e-06,
+      "loss": 1.2211,
+      "step": 79
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.2458,
+      "step": 80
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.1e-06,
+      "loss": 1.1735,
+      "step": 81
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.2e-06,
+      "loss": 1.1613,
+      "step": 82
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.3e-06,
+      "loss": 1.2147,
+      "step": 83
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 1.2297,
+      "step": 84
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 8.5e-06,
+      "loss": 1.2053,
+      "step": 85
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 8.6e-06,
+      "loss": 1.2524,
+      "step": 86
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 8.700000000000001e-06,
+      "loss": 1.2613,
+      "step": 87
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.8e-06,
+      "loss": 1.1453,
+      "step": 88
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.900000000000001e-06,
+      "loss": 1.2025,
+      "step": 89
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9e-06,
+      "loss": 1.1106,
+      "step": 90
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.100000000000001e-06,
+      "loss": 1.1556,
+      "step": 91
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 1.2154,
+      "step": 92
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.3e-06,
+      "loss": 1.1388,
+      "step": 93
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.4e-06,
+      "loss": 1.1614,
+      "step": 94
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.5e-06,
+      "loss": 1.1671,
+      "step": 95
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.1532,
+      "step": 96
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.7e-06,
+      "loss": 1.1536,
+      "step": 97
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.1557,
+      "step": 98
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.9e-06,
+      "loss": 1.1084,
+      "step": 99
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1e-05,
+      "loss": 1.1748,
+      "step": 100
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.998286624877786e-06,
+      "loss": 1.1997,
+      "step": 101
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.993147673772869e-06,
+      "loss": 1.0219,
+      "step": 102
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.984586668665641e-06,
+      "loss": 1.1311,
+      "step": 103
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.972609476841368e-06,
+      "loss": 1.0767,
+      "step": 104
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.957224306869053e-06,
+      "loss": 1.0199,
+      "step": 105
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.938441702975689e-06,
+      "loss": 1.2051,
+      "step": 106
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.916274537819774e-06,
+      "loss": 1.1329,
+      "step": 107
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 1.2139,
+      "step": 108
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.861849601988384e-06,
+      "loss": 1.2148,
+      "step": 109
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.829629131445342e-06,
+      "loss": 1.2246,
+      "step": 110
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.0940097570419312,
+      "eval_runtime": 5.4854,
+      "eval_samples_per_second": 474.171,
+      "eval_steps_per_second": 16.954,
+      "step": 110
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.794098674340966e-06,
+      "loss": 1.191,
+      "step": 111
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 1.1356,
+      "step": 112
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.713207455460893e-06,
+      "loss": 1.0826,
+      "step": 113
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.667902132486009e-06,
+      "loss": 1.2344,
+      "step": 114
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 1.205,
+      "step": 115
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.567727288213005e-06,
+      "loss": 1.1462,
+      "step": 116
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.512926421749305e-06,
+      "loss": 1.1341,
+      "step": 117
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.45503262094184e-06,
+      "loss": 1.1104,
+      "step": 118
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.394085563309827e-06,
+      "loss": 1.1868,
+      "step": 119
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 1.0813,
+      "step": 120
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.263200821770462e-06,
+      "loss": 1.1324,
+      "step": 121
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.193352839727122e-06,
+      "loss": 1.1167,
+      "step": 122
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.120630943110078e-06,
+      "loss": 1.056,
+      "step": 123
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 1.1708,
+      "step": 124
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.966766701456177e-06,
+      "loss": 1.1312,
+      "step": 125
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.885729807284855e-06,
+      "loss": 1.1008,
+      "step": 126
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.802029828000157e-06,
+      "loss": 1.0592,
+      "step": 127
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.715724127386971e-06,
+      "loss": 1.0699,
+      "step": 128
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.626871855061438e-06,
+      "loss": 1.0373,
+      "step": 129
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 1.1162,
+      "step": 130
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.44177287846877e-06,
+      "loss": 1.0207,
+      "step": 131
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.345653031794292e-06,
+      "loss": 1.2075,
+      "step": 132
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.247240241650918e-06,
+      "loss": 1.0471,
+      "step": 133
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.146601955249187e-06,
+      "loss": 1.1402,
+      "step": 134
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.043807145043604e-06,
+      "loss": 1.0375,
+      "step": 135
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 1.0273,
+      "step": 136
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.832031184624165e-06,
+      "loss": 1.046,
+      "step": 137
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.723195175075136e-06,
+      "loss": 1.1205,
+      "step": 138
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.612492823579744e-06,
+      "loss": 1.1016,
+      "step": 139
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.1173,
+      "step": 140
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.3857938012980425e-06,
+      "loss": 1.0941,
+      "step": 141
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.269952498697734e-06,
+      "loss": 1.1158,
+      "step": 142
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.1525554840414765e-06,
+      "loss": 1.061,
+      "step": 143
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.033683215379002e-06,
+      "loss": 1.1158,
+      "step": 144
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 1.1206,
+      "step": 145
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.7918397477265e-06,
+      "loss": 1.1196,
+      "step": 146
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.669034296168855e-06,
+      "loss": 1.1284,
+      "step": 147
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 1.0504,
+      "step": 148
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.420076723519615e-06,
+      "loss": 1.1095,
+      "step": 149
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.294095225512604e-06,
+      "loss": 1.154,
+      "step": 150
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.1672268192795285e-06,
+      "loss": 1.0097,
+      "step": 151
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.039558454088796e-06,
+      "loss": 0.997,
+      "step": 152
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.911177627460739e-06,
+      "loss": 1.0522,
+      "step": 153
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.782172325201155e-06,
+      "loss": 1.0514,
+      "step": 154
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.65263096110026e-06,
+      "loss": 1.0633,
+      "step": 155
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.522642316338268e-06,
+      "loss": 1.0988,
+      "step": 156
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.392295478639226e-06,
+      "loss": 1.1034,
+      "step": 157
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.2616797812147205e-06,
+      "loss": 1.1069,
+      "step": 158
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.130884741539367e-06,
+      "loss": 1.142,
+      "step": 159
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5e-06,
+      "loss": 1.0829,
+      "step": 160
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.869115258460636e-06,
+      "loss": 1.0947,
+      "step": 161
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.738320218785281e-06,
+      "loss": 1.0733,
+      "step": 162
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.6077045213607765e-06,
+      "loss": 1.1207,
+      "step": 163
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.477357683661734e-06,
+      "loss": 1.1621,
+      "step": 164
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.347369038899744e-06,
+      "loss": 1.0636,
+      "step": 165
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.9949154853820801,
+      "eval_runtime": 5.4121,
+      "eval_samples_per_second": 480.59,
+      "eval_steps_per_second": 17.184,
+      "step": 165
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.217827674798845e-06,
+      "loss": 1.0529,
+      "step": 166
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.088822372539263e-06,
+      "loss": 1.0638,
+      "step": 167
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.960441545911205e-06,
+      "loss": 1.0807,
+      "step": 168
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.832773180720475e-06,
+      "loss": 1.0677,
+      "step": 169
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.705904774487396e-06,
+      "loss": 1.0897,
+      "step": 170
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.579923276480387e-06,
+      "loss": 1.0828,
+      "step": 171
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 1.0671,
+      "step": 172
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.330965703831146e-06,
+      "loss": 1.0613,
+      "step": 173
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.2081602522734987e-06,
+      "loss": 1.1383,
+      "step": 174
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 1.1004,
+      "step": 175
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.966316784621e-06,
+      "loss": 1.048,
+      "step": 176
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.8474445159585235e-06,
+      "loss": 1.083,
+      "step": 177
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.7300475013022666e-06,
+      "loss": 1.0262,
+      "step": 178
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.614206198701958e-06,
+      "loss": 1.076,
+      "step": 179
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 1.1453,
+      "step": 180
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.387507176420256e-06,
+      "loss": 1.0674,
+      "step": 181
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.2768048249248648e-06,
+      "loss": 1.0622,
+      "step": 182
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.1679688153758373e-06,
+      "loss": 1.0837,
+      "step": 183
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 1.1283,
+      "step": 184
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.956192854956397e-06,
+      "loss": 1.0808,
+      "step": 185
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.8533980447508138e-06,
+      "loss": 1.1307,
+      "step": 186
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.7527597583490825e-06,
+      "loss": 0.9674,
+      "step": 187
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6543469682057105e-06,
+      "loss": 1.0615,
+      "step": 188
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.5582271215312294e-06,
+      "loss": 1.1103,
+      "step": 189
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 1.1133,
+      "step": 190
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.373128144938563e-06,
+      "loss": 1.0925,
+      "step": 191
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2842758726130283e-06,
+      "loss": 1.081,
+      "step": 192
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.1979701719998454e-06,
+      "loss": 1.0841,
+      "step": 193
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.1142701927151456e-06,
+      "loss": 1.1522,
+      "step": 194
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.0332332985438248e-06,
+      "loss": 1.1564,
+      "step": 195
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 1.0965,
+      "step": 196
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.793690568899216e-07,
+      "loss": 1.1434,
+      "step": 197
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.066471602728804e-07,
+      "loss": 1.0312,
+      "step": 198
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.367991782295392e-07,
+      "loss": 1.1378,
+      "step": 199
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 1.0707,
+      "step": 200
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.059144366901737e-07,
+      "loss": 1.0679,
+      "step": 201
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.449673790581611e-07,
+      "loss": 1.107,
+      "step": 202
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.87073578250698e-07,
+      "loss": 0.9918,
+      "step": 203
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.322727117869951e-07,
+      "loss": 1.0946,
+      "step": 204
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 1.0381,
+      "step": 205
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.320978675139919e-07,
+      "loss": 1.0833,
+      "step": 206
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.867925445391079e-07,
+      "loss": 1.0792,
+      "step": 207
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 1.1722,
+      "step": 208
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.0590132565903475e-07,
+      "loss": 1.0136,
+      "step": 209
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.7037086855465902e-07,
+      "loss": 1.1095,
+      "step": 210
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.3815039801161723e-07,
+      "loss": 1.1202,
+      "step": 211
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0926199633097156e-07,
+      "loss": 1.0463,
+      "step": 212
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 8.372546218022747e-08,
+      "loss": 1.0762,
+      "step": 213
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 6.15582970243117e-08,
+      "loss": 1.0496,
+      "step": 214
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.2775693130948094e-08,
+      "loss": 1.0197,
+      "step": 215
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.7390523158633552e-08,
+      "loss": 1.0559,
+      "step": 216
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.541333133436018e-08,
+      "loss": 1.1146,
+      "step": 217
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.852326227130835e-09,
+      "loss": 1.0802,
+      "step": 218
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.7133751222137007e-09,
+      "loss": 1.0113,
+      "step": 219
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 1.0758,
+      "step": 220
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9915103912353516,
+      "eval_runtime": 5.4164,
+      "eval_samples_per_second": 480.209,
+      "eval_steps_per_second": 17.17,
+      "step": 220
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.589146774667264e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-220/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a071201f35d85c9533abf1329186376dd48210d74609a49ae5d04d0d0aeb4a8
+size 4923

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "microsoft/phi-2",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": false,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "do_sample": true,
+  "eos_token_id": 50256,
+  "transformers_version": "4.38.0.dev0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a260a602acd097c8bdb3294c3633263c9dedf4eb8fb6e95afba741c244bf71e8
+size 4995685160

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ab5c8c7d4898e69a02d1d03bcba536988c0fcb88ba0c4fe212cca336a8b83e
+size 563839915

pytorch_model.bin.index.json

@@ -0,0 +1,460 @@
+{
+  "metadata": {
+    "total_size": 5559367680
+  },
+  "weight_map": {
+    "lm_head.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.final_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.final_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,324 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}