Upload 15 files

ckpt-46/README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: other
+base_model: /root/models/MMfreeLM-2.7B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: math_continue_pretrain
+  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. -->
+
+# math_continue_pretrain
+
+This model is a fine-tuned version of [/root/models/MMfreeLM-2.7B](https://huggingface.co//root/models/MMfreeLM-2.7B) on the the_stack dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.7669
+
+## 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: 2
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 256
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.5.0+cu124
+- Datasets 2.21.0
+- Tokenizers 0.20.1

ckpt-46/all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.941952506596306,
+    "eval_loss": 3.7669124603271484,
+    "eval_runtime": 7.2704,
+    "eval_samples_per_second": 92.705,
+    "eval_steps_per_second": 11.691,
+    "perplexity": 43.246333720958525,
+    "total_flos": 1.8959322667863245e+17,
+    "train_loss": 5.261244110439135,
+    "train_runtime": 307.2859,
+    "train_samples_per_second": 39.423,
+    "train_steps_per_second": 0.15
+}

ckpt-46/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/root/models/MMfreeLM-2.7B",
+  "architectures": [
+    "HGRNBitForCausalLM"
+  ],
+  "attn_mode": "fused_recurrent",
+  "bos_token_id": 1,
+  "conv_size": 4,
+  "eos_token_id": 2,
+  "expand_ratio": 1,
+  "fuse_cross_entropy": true,
+  "hidden_act": "swish",
+  "hidden_ratio": 4,
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "max_position_embeddings": 2048,
+  "model_type": "hgrn_bit",
+  "num_heads": 1,
+  "num_hidden_layers": 32,
+  "rms_norm_eps": 1e-06,
+  "share_conv_kernel": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_lower_bound": true,
+  "use_short_conv": false,
+  "vocab_size": 32000
+}

ckpt-46/eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.941952506596306,
+    "eval_loss": 3.7669124603271484,
+    "eval_runtime": 7.2704,
+    "eval_samples_per_second": 92.705,
+    "eval_steps_per_second": 11.691,
+    "perplexity": 43.246333720958525
+}

ckpt-46/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

ckpt-46/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe1a823923b917b01ce4f6191c1b48a1ab6eb0fe15eabb670e3c6636444b5bf
+size 1205075968

ckpt-46/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd11f11848bf12e8fa45b0fc5ee3eb94243e1ee7a24ab37bd5f950871c25d84
+size 428691816

ckpt-46/model.safetensors.index.json

@@ -0,0 +1,492 @@
+{
+  "metadata": {
+    "total_size": 5404715008
+  },
+  "weight_map": {
+    "lm_head.norm.weight": "model-00002-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embeddings.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.attn.f_proj.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.f_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.g_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.g_proj.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.g_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.i_proj.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.i_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.o_proj.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.f_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.f_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.g_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.g_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.g_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.i_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.i_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.o_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp_norm.weight": "model-00001-of-00002.safetensors",
+    "model.lower_bounds": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

ckpt-46/special_tokens_map.json

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

ckpt-46/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

ckpt-46/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

ckpt-46/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.941952506596306,
+    "total_flos": 1.8959322667863245e+17,
+    "train_loss": 5.261244110439135,
+    "train_runtime": 307.2859,
+    "train_samples_per_second": 39.423,
+    "train_steps_per_second": 0.15
+}

ckpt-46/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.941952506596306,
+  "eval_steps": 5000,
+  "global_step": 46,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.42216358839050133,
+      "grad_norm": 13.42656421661377,
+      "learning_rate": 9.36024704071904e-06,
+      "loss": 8.6209,
+      "step": 10
+    },
+    {
+      "epoch": 0.8443271767810027,
+      "grad_norm": 9.004769325256348,
+      "learning_rate": 6.614402023857231e-06,
+      "loss": 5.3354,
+      "step": 20
+    },
+    {
+      "epoch": 1.266490765171504,
+      "grad_norm": 6.205361843109131,
+      "learning_rate": 3.044476397549221e-06,
+      "loss": 4.18,
+      "step": 30
+    },
+    {
+      "epoch": 1.6886543535620053,
+      "grad_norm": 5.6094651222229,
+      "learning_rate": 4.727588125342669e-07,
+      "loss": 3.8146,
+      "step": 40
+    },
+    {
+      "epoch": 1.941952506596306,
+      "step": 46,
+      "total_flos": 1.8959322667863245e+17,
+      "train_loss": 5.261244110439135,
+      "train_runtime": 307.2859,
+      "train_samples_per_second": 39.423,
+      "train_steps_per_second": 0.15
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 46,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8959322667863245e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

ckpt-46/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2b53b42ae9c9b47fe7323a2c0ff45c330b32a04fc03d882e78cae25d155004
+size 6712