Upload model weights

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+library_name: transformers
+base_model: meta-llama/Meta-Llama-3-8B
+tags:
+- generated_from_trainer
+datasets:
+- vicgalle/alpaca-gpt4
+model-index:
+- name: 1e-5_bnoniid_layer
+  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. -->
+
+# 1e-5_bnoniid_layer
+
+This model is a fine-tuned version of [/data/public_models/Meta-Llama-3-8B](https://huggingface.co//data/public_models/Meta-Llama-3-8B) on the vicgalle/alpaca-gpt4 default dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 8.78925141040004e-07
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.7222487440041828,
+    "eval_bleu": 0.0,
+    "eval_loss": 1.0461024045944214,
+    "eval_rougeL": 0.5729727886517084,
+    "eval_runtime": 17.5083,
+    "eval_samples": 86,
+    "eval_samples_per_second": 4.912,
+    "eval_steps_per_second": 0.628,
+    "perplexity": 2.846534827668364,
+    "total_flos": 2213292344868864.0,
+    "train_loss": 1.0366925398508708,
+    "train_runtime": 6.9379,
+    "train_samples": 801,
+    "train_samples_per_second": 6.919,
+    "train_steps_per_second": 1.73
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/data/public_models/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "seed": 42,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

config.txt

@@ -0,0 +1 @@
+--model_name_or_path /data/public_models/Meta-Llama-3-8B --output_dir /data/yujia_wang/fedmoe_llama/moe/checkpoints_moe/Meta-Llama-3-8B/vicgalle/alpaca-gpt4/1e-5_bnoniid_layer --dataset_name vicgalle/alpaca-gpt4 --dataset_config_name default --per_device_train_batch_size 1 --per_device_eval_batch_size 8 --num_train_epochs 1 --overwrite_output_dir --do_train True --do_eval --seed 42 --dataloader_num_workers 16 --disable_tqdm False --save_strategy no --evaluation_strategy epoch --load_best_model_at_end True --learning_rate 1e-5 --notes layer --split_strategy bnoniid --num_rounds 32 --num_clients 10 --sample_clients 10 --max_gate_samples 50 --max_train_samples 60000 --gradient_accumulation_steps 4

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.7222487440041828,
+    "eval_bleu": 0.0,
+    "eval_loss": 1.0461024045944214,
+    "eval_rougeL": 0.5729727886517084,
+    "eval_runtime": 17.5083,
+    "eval_samples": 86,
+    "eval_samples_per_second": 4.912,
+    "eval_steps_per_second": 0.628,
+    "perplexity": 2.846534827668364
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a98eef4d6bc7347fe04011febbe014b6aac521bfa3023c0ea7a9dbfdca12604
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53a097e81f9b4b2df139991437bc2b2839f206ed4a195b8bd86a2817c8b40215
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb4f7e15394ca110d603102b5dbd365b263f27e5eb7752a24bb118d9ee294e0
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc34e6bdf2da9e35f0d93b5c333c870f3677dc43dc3a91ea3a8ad28a1fe1acb
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

runs/Jan10_18-28-27_compute-permanent-node-326/events.out.tfevents.1736533711.compute-permanent-node-326.3512784.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c488ddf1796378eef02493f49dc7822f13eca3958b250ba7d6b83b19cf3459
+size 5746

runs/Jan10_18-28-43_compute-permanent-node-326/events.out.tfevents.1736533723.compute-permanent-node-326.3512784.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0f9429586934b0288b0d05dc7977775da0f490d3f810ece4014b836fb332ce
+size 5746

runs/Jan10_18-28-55_compute-permanent-node-326/events.out.tfevents.1736533735.compute-permanent-node-326.3512784.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff1f9ef9e76d7458359aace090c935e071e94f41eacfb445c47dce38945e8fcd
+size 5746

runs/Jan10_18-29-11_compute-permanent-node-326/events.out.tfevents.1736533751.compute-permanent-node-326.3512784.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2236ba8a1e42c5b43ec7376c438b250347462d9a2d40022c5a176a75d66a93f2
+size 5746

runs/Jan10_18-29-13_compute-permanent-node-326/events.out.tfevents.1736533753.compute-permanent-node-326.3512784.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f4b3b82dbb534be4c5e0012791f45859c5f852ae53683df3ca4162df9325e3
+size 5746

runs/Jan10_18-29-22_compute-permanent-node-326/events.out.tfevents.1736533762.compute-permanent-node-326.3512784.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df97f704c0cbddfa084027482cca94378ddb01be393139807ff7d70e1acc7fe1
+size 5746

runs/Jan10_18-30-42_compute-permanent-node-326/events.out.tfevents.1736533842.compute-permanent-node-326.3512784.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e43e7272fe5d25fab44c5c9d35ca3d162bcbaf8d6a97c11d1c3dcd6ff08bf5f6
+size 5746

runs/Jan10_18-31-15_compute-permanent-node-326/events.out.tfevents.1736533875.compute-permanent-node-326.3512784.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81eb105b75f1645b545fe1d8521b85917a58a71a76d99aa1c1caeaa1f229dae
+size 5746

runs/Jan10_18-31-52_compute-permanent-node-326/events.out.tfevents.1736533912.compute-permanent-node-326.3512784.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcdf2cef81742ac5a654f6cb5c50f60d3434e89421fe46b4cf7e7c217307c1dc
+size 5746

runs/Jan10_18-32-11_compute-permanent-node-326/events.out.tfevents.1736533931.compute-permanent-node-326.3512784.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fee39a70a223adaf3ee769d66bf4e0385c480a0360a0ab39b7026864e7541d8
+size 5746

runs/Jan10_18-32-37_compute-permanent-node-326/events.out.tfevents.1736533957.compute-permanent-node-326.3512784.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec01671cf8aef051daed49ea5ef1c0c87250865dc7b68ebc24f44381d7186dd
+size 5746

runs/Jan10_18-32-44_compute-permanent-node-326/events.out.tfevents.1736533964.compute-permanent-node-326.3512784.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ae147e2c41baf2664d69e51ee94012676e52f34fcbca2a8e2e97d16b58c59d
+size 5746

runs/Jan10_18-32-58_compute-permanent-node-326/events.out.tfevents.1736533978.compute-permanent-node-326.3512784.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e066a0d1c367704456e35d6c24331b2f04d8bca53267226c3498869f929f53c
+size 5746

runs/Jan10_18-33-15_compute-permanent-node-326/events.out.tfevents.1736533996.compute-permanent-node-326.3512784.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e1ccb6e84be9248ebb62ea99071610862da71449dcbd32445f9c1a2578995b
+size 5746

runs/Jan10_18-33-18_compute-permanent-node-326/events.out.tfevents.1736533998.compute-permanent-node-326.3512784.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da81edfb9cde173e0b83e7246f9e9bb04ed5abe8ad63e81bc5362291bf429146
+size 5746

runs/Jan10_18-33-28_compute-permanent-node-326/events.out.tfevents.1736534009.compute-permanent-node-326.3512784.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8268a1b1dd69cda0240350a7a8d6a1d7bec896673bbd500c21dba5bc851981aa
+size 5746

runs/Jan10_18-34-58_compute-permanent-node-326/events.out.tfevents.1736534098.compute-permanent-node-326.3512784.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f231572aeb381cfddf7573ec30634651ae5569452e840c4353451d7a48a3370c
+size 5746

runs/Jan10_18-35-34_compute-permanent-node-326/events.out.tfevents.1736534134.compute-permanent-node-326.3512784.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb30b9fe5c44516f894533a95ec115f2bcd860e61ff86594e9997afaaae42ea
+size 5746

runs/Jan10_18-36-16_compute-permanent-node-326/events.out.tfevents.1736534176.compute-permanent-node-326.3512784.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b3eeed3d256daa7f80cba82c7a59e9767cc395e86fa06b8d06ecde02371309
+size 5746

runs/Jan10_18-36-37_compute-permanent-node-326/events.out.tfevents.1736534197.compute-permanent-node-326.3512784.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5cb8509a0b50c28ab5666edb69abeeb50b9348e08cb5a0ac64661fc581ad98
+size 5746

runs/Jan10_18-37-07_compute-permanent-node-326/events.out.tfevents.1736534227.compute-permanent-node-326.3512784.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc64a95b96283ffa7336a2738e2ccbb6113f661b4ecab9cdc33202416132fa5
+size 5746

runs/Jan10_18-37-13_compute-permanent-node-326/events.out.tfevents.1736534233.compute-permanent-node-326.3512784.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28a43b0896b5e1ad854cf6cb3d2ebd096d5d9f794cdec404de1c16bc10bc186
+size 5746

runs/Jan10_18-37-24_compute-permanent-node-326/events.out.tfevents.1736534244.compute-permanent-node-326.3512784.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee2d4eb97ab0f6e3a74422c1c54160a1935a62b5b135ef464e9346b28b688c7
+size 5746

runs/Jan10_18-37-37_compute-permanent-node-326/events.out.tfevents.1736534258.compute-permanent-node-326.3512784.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbcdd22ac6f4d92100c3636a75b4f7856f3d7ba94eb3809d6c9c3f0cbd73127d
+size 5746

runs/Jan10_18-37-40_compute-permanent-node-326/events.out.tfevents.1736534260.compute-permanent-node-326.3512784.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0697dc4dc5c0a38b87c1937f31a13f8232a41300e6f752331f7d97001c26532
+size 5746

runs/Jan10_18-37-48_compute-permanent-node-326/events.out.tfevents.1736534268.compute-permanent-node-326.3512784.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4226dba5b56459147d0bfc85bd88b6186db6ed2adae5bf3788ae916ca0a3e806
+size 5746

runs/Jan10_18-38-55_compute-permanent-node-326/events.out.tfevents.1736534336.compute-permanent-node-326.3512784.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:304e3e2357f3b6b6e86d85911552bfece191c65ba2942ccc3f5e3f871be7fbc3
+size 5746

runs/Jan10_18-39-23_compute-permanent-node-326/events.out.tfevents.1736534363.compute-permanent-node-326.3512784.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672b1e0dd6ed17d0c9931b93d6620e1f391ad2f04a02cc098546b9f8ac385737
+size 5746

runs/Jan10_18-39-55_compute-permanent-node-326/events.out.tfevents.1736534395.compute-permanent-node-326.3512784.28

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7013d8f54cc763cd0b21747dc7fb010b4130c48ec8dd67bba60b62ffc7e0d01
+size 5746

runs/Jan10_18-40-11_compute-permanent-node-326/events.out.tfevents.1736534411.compute-permanent-node-326.3512784.29

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e89625b133ac63402bef2bc5e793d133079975f02389613e47cb21a4fc0edfba
+size 5746

runs/Jan10_18-40-36_compute-permanent-node-326/events.out.tfevents.1736534436.compute-permanent-node-326.3512784.30

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3e6c946f9bacbdb3937d4c1c3b7e56402d3c087da441c4e6733b65f1e22722
+size 5730

runs/Jan10_18-40-42_compute-permanent-node-326/events.out.tfevents.1736534442.compute-permanent-node-326.3512784.31

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06945b1ff1c5f673fff012a2f48af42d08f556fa44f5c3e944abc4076912427d
+size 5730

runs/Jan10_18-40-53_compute-permanent-node-326/events.out.tfevents.1736534453.compute-permanent-node-326.3512784.32

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b391b57fed4f108f48aede737dc8d8356cd9544a7a57c45e4bef23b6baccb934
+size 5730

runs/Jan10_18-41-07_compute-permanent-node-326/events.out.tfevents.1736534468.compute-permanent-node-326.3512784.33

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac1a08c8833bb27d7cb249fda2fd839c072571bf9c826f905110d5699301f9f
+size 5730

runs/Jan10_18-41-10_compute-permanent-node-326/events.out.tfevents.1736534470.compute-permanent-node-326.3512784.34

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae9422d876e0d58666767a8c6dc7d69b7c0cfe1493d3e7ca58d8e5aec84ab5a9
+size 5730

runs/Jan10_18-41-18_compute-permanent-node-326/events.out.tfevents.1736534478.compute-permanent-node-326.3512784.35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b2de21efb962af839045b44c16a393006638fba85e47df8e7201299b1cd3587
+size 5730

runs/Jan10_18-42-29_compute-permanent-node-326/events.out.tfevents.1736534549.compute-permanent-node-326.3512784.36

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0179dd370cc0bcdb36b845fab705b3dd01672fa00d5b8dd9e5afb16f3f170bf6
+size 5730

runs/Jan10_18-42-57_compute-permanent-node-326/events.out.tfevents.1736534578.compute-permanent-node-326.3512784.37

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb2c275de48ac527d39674e5d9c083428ebba7ad0f2bfd23f053d362416cb526
+size 5730