Upload folder using huggingface_hub

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: deepseek-ai/deepseek-coder-7b-instruct-v1.5
+tags:
+- llama-factory
+- freeze
+- generated_from_trainer
+model-index:
+- name: deepseek_nsx_8_1
+  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. -->
+
+# deepseek_nsx_8_1
+
+This model is a fine-tuned version of [deepseek-ai/deepseek-coder-7b-instruct-v1.5](https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5) on the codes_nsx_over81 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 512
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.48.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9795918367346939,
+    "num_input_tokens_seen": 25165824,
+    "total_flos": 9.800984115271434e+17,
+    "train_loss": 0.7565137396256129,
+    "train_runtime": 1221.0904,
+    "train_samples_per_second": 5.136,
+    "train_steps_per_second": 0.01
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100015,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 1.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "vocab_size": 102400
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "eos_token_id": 100015,
+  "transformers_version": "4.48.2"
+}

llamaboard_config.yaml

@@ -0,0 +1,77 @@
+top.booster: liger_kernel
+top.checkpoint_path: null
+top.finetuning_type: freeze
+top.model_name: DeepSeek-Coder-7B-Instruct
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: llama3
+top.template: deepseekcoder
+train.additional_target: ''
+train.apollo_rank: 256
+train.apollo_scale: 1
+train.apollo_target: all
+train.apollo_update_interval: 200
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 16
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 4096
+train.dataset:
+- codes_nsx_over81
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.extra_args: '{}'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 2
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.learning_rate: 5e-5
+train.logging_steps: 1
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '50000000'
+train.neat_packing: true
+train.neftune_alpha: 0
+train.num_train_epochs: '1'
+train.packing: true
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to:
+- none
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 500
+train.swanlab_api_key: ''
+train.swanlab_mode: cloud
+train.swanlab_project: llamafactory
+train.swanlab_run_name: ''
+train.swanlab_workspace: ''
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_apollo: true
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.use_swanlab: false
+train.val_size: 0
+train.warmup_steps: 0

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28aba7f82f5ce656674a3e922d68c0b7bd12d2f2e6da09e47fa72eec539c53c2
+size 4987202208

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e815d13d98a67f7370ade76666bfa350f8083dea55f75a60050d05d8bb0728
+size 4980945440

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d37279dcee5098f4af1886178d9dc77c51467b6a1e8b5fd7b7f4d4e9c9335a
+size 4662148920

model.safetensors.index.json

@@ -0,0 +1,280 @@
+{
+  "metadata": {
+    "total_size": 14630264832
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

running_log.txt

@@ -0,0 +1,259 @@
+[INFO|2025-05-29 22:52:47] configuration_utils.py:696 >> loading configuration file config.json from cache at /home/kiho/.cache/huggingface/hub/models--deepseek-ai--deepseek-coder-7b-instruct-v1.5/snapshots/2a050a4c59d687a85324d32e147517992117ed30/config.json
+
+[INFO|2025-05-29 22:52:47] configuration_utils.py:768 >> Model config LlamaConfig {
+  "_name_or_path": "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100015,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "vocab_size": 102400
+}
+
+
+[INFO|2025-05-29 22:52:47] tokenization_utils_base.py:2034 >> loading file tokenizer.model from cache at None
+
+[INFO|2025-05-29 22:52:47] tokenization_utils_base.py:2034 >> loading file tokenizer.json from cache at /home/kiho/.cache/huggingface/hub/models--deepseek-ai--deepseek-coder-7b-instruct-v1.5/snapshots/2a050a4c59d687a85324d32e147517992117ed30/tokenizer.json
+
+[INFO|2025-05-29 22:52:47] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-05-29 22:52:47] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at None
+
+[INFO|2025-05-29 22:52:47] tokenization_utils_base.py:2034 >> loading file tokenizer_config.json from cache at /home/kiho/.cache/huggingface/hub/models--deepseek-ai--deepseek-coder-7b-instruct-v1.5/snapshots/2a050a4c59d687a85324d32e147517992117ed30/tokenizer_config.json
+
+[INFO|2025-05-29 22:52:47] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-05-29 22:52:47] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-05-29 22:52:48] configuration_utils.py:696 >> loading configuration file config.json from cache at /home/kiho/.cache/huggingface/hub/models--deepseek-ai--deepseek-coder-7b-instruct-v1.5/snapshots/2a050a4c59d687a85324d32e147517992117ed30/config.json
+
+[INFO|2025-05-29 22:52:48] configuration_utils.py:768 >> Model config LlamaConfig {
+  "_name_or_path": "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100015,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "vocab_size": 102400
+}
+
+
+[INFO|2025-05-29 22:52:49] tokenization_utils_base.py:2034 >> loading file tokenizer.model from cache at None
+
+[INFO|2025-05-29 22:52:49] tokenization_utils_base.py:2034 >> loading file tokenizer.json from cache at /home/kiho/.cache/huggingface/hub/models--deepseek-ai--deepseek-coder-7b-instruct-v1.5/snapshots/2a050a4c59d687a85324d32e147517992117ed30/tokenizer.json
+
+[INFO|2025-05-29 22:52:49] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-05-29 22:52:49] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at None
+
+[INFO|2025-05-29 22:52:49] tokenization_utils_base.py:2034 >> loading file tokenizer_config.json from cache at /home/kiho/.cache/huggingface/hub/models--deepseek-ai--deepseek-coder-7b-instruct-v1.5/snapshots/2a050a4c59d687a85324d32e147517992117ed30/tokenizer_config.json
+
+[INFO|2025-05-29 22:52:49] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-05-29 22:52:49] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-05-29 22:52:49] logging.py:157 >> Loading dataset Codes_query_filtered_330k_ns_over8_1.json...
+
+[INFO|2025-05-29 22:53:02] configuration_utils.py:696 >> loading configuration file config.json from cache at /home/kiho/.cache/huggingface/hub/models--deepseek-ai--deepseek-coder-7b-instruct-v1.5/snapshots/2a050a4c59d687a85324d32e147517992117ed30/config.json
+
+[INFO|2025-05-29 22:53:02] configuration_utils.py:768 >> Model config LlamaConfig {
+  "_name_or_path": "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100015,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "vocab_size": 102400
+}
+
+
+[WARNING|2025-05-29 22:53:02] logging.py:162 >> Input length is smaller than max length. Consider increase input length.
+
+[INFO|2025-05-29 22:53:02] logging.py:157 >> Using llama3 scaling strategy and setting scaling factor to 1.0.
+
+[INFO|2025-05-29 22:53:02] logging.py:157 >> Using block diagonal attention for sequence packing without cross-attention.
+
+[INFO|2025-05-29 22:53:02] logging.py:157 >> Liger kernel has been applied to the model.
+
+[INFO|2025-05-29 22:53:02] modeling_utils.py:3904 >> loading weights file model.safetensors from cache at /home/kiho/.cache/huggingface/hub/models--deepseek-ai--deepseek-coder-7b-instruct-v1.5/snapshots/2a050a4c59d687a85324d32e147517992117ed30/model.safetensors.index.json
+
+[INFO|2025-05-29 22:53:02] modeling_utils.py:1582 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2025-05-29 22:53:02] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 100000,
+  "eos_token_id": 100015
+}
+
+
+[INFO|2025-05-29 22:53:11] modeling_utils.py:4888 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
+
+
+[INFO|2025-05-29 22:53:11] modeling_utils.py:4896 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at deepseek-ai/deepseek-coder-7b-instruct-v1.5.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
+
+[INFO|2025-05-29 22:53:11] configuration_utils.py:1095 >> loading configuration file generation_config.json from cache at /home/kiho/.cache/huggingface/hub/models--deepseek-ai--deepseek-coder-7b-instruct-v1.5/snapshots/2a050a4c59d687a85324d32e147517992117ed30/generation_config.json
+
+[INFO|2025-05-29 22:53:11] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 100000,
+  "eos_token_id": 100015
+}
+
+
+[INFO|2025-05-29 22:53:11] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2025-05-29 22:53:11] logging.py:157 >> Using torch SDPA for faster training and inference.
+
+[INFO|2025-05-29 22:53:11] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2025-05-29 22:53:11] logging.py:157 >> Fine-tuning method: Freeze
+
+[INFO|2025-05-29 22:53:11] logging.py:157 >> Set trainable layers: .28.,.29.
+
+[INFO|2025-05-29 22:53:11] logging.py:157 >> trainable params: 404,766,720 || all params: 6,910,365,696 || trainable%: 5.8574
+
+[INFO|2025-05-29 22:53:11] trainer.py:741 >> Using auto half precision backend
+
+[INFO|2025-05-29 22:53:11] logging.py:157 >> Found linear modules: down_proj,gate_proj,o_proj,k_proj,up_proj,q_proj,v_proj
+
+[INFO|2025-05-29 22:53:11] logging.py:157 >> Using APOLLO optimizer with args: {'rank': 256, 'proj': 'random', 'proj_type': 'std', 'update_proj_gap': 200, 'scale': 1, 'scale_type': 'channel', 'scale_front': False}.
+
+[INFO|2025-05-29 22:53:11] trainer.py:2369 >> ***** Running training *****
+
+[INFO|2025-05-29 22:53:11] trainer.py:2370 >>   Num examples = 6,272
+
+[INFO|2025-05-29 22:53:11] trainer.py:2371 >>   Num Epochs = 1
+
+[INFO|2025-05-29 22:53:11] trainer.py:2372 >>   Instantaneous batch size per device = 16
+
+[INFO|2025-05-29 22:53:11] trainer.py:2375 >>   Total train batch size (w. parallel, distributed & accumulation) = 512
+
+[INFO|2025-05-29 22:53:11] trainer.py:2376 >>   Gradient Accumulation steps = 8
+
+[INFO|2025-05-29 22:53:11] trainer.py:2377 >>   Total optimization steps = 12
+
+[INFO|2025-05-29 22:53:11] trainer.py:2378 >>   Number of trainable parameters = 404,766,720
+
+[INFO|2025-05-29 22:54:58] logging.py:157 >> {'loss': 0.8480, 'learning_rate': 4.9148e-05, 'epoch': 0.08, 'throughput': 19880.44}
+
+[INFO|2025-05-29 22:56:38] logging.py:157 >> {'loss': 0.8111, 'learning_rate': 4.6651e-05, 'epoch': 0.16, 'throughput': 20427.48}
+
+[INFO|2025-05-29 22:58:17] logging.py:157 >> {'loss': 0.7984, 'learning_rate': 4.2678e-05, 'epoch': 0.24, 'throughput': 20649.67}
+
+[INFO|2025-05-29 22:59:56] logging.py:157 >> {'loss': 0.7649, 'learning_rate': 3.7500e-05, 'epoch': 0.33, 'throughput': 20755.74}
+
+[INFO|2025-05-29 23:01:36] logging.py:157 >> {'loss': 0.7687, 'learning_rate': 3.1470e-05, 'epoch': 0.41, 'throughput': 20825.02}
+
+[INFO|2025-05-29 23:03:15] logging.py:157 >> {'loss': 0.7696, 'learning_rate': 2.5000e-05, 'epoch': 0.49, 'throughput': 20874.16}
+
+[INFO|2025-05-29 23:04:54] logging.py:157 >> {'loss': 0.7488, 'learning_rate': 1.8530e-05, 'epoch': 0.57, 'throughput': 20909.51}
+
+[INFO|2025-05-29 23:06:34] logging.py:157 >> {'loss': 0.7368, 'learning_rate': 1.2500e-05, 'epoch': 0.65, 'throughput': 20931.46}
+
+[INFO|2025-05-29 23:08:13] logging.py:157 >> {'loss': 0.7088, 'learning_rate': 7.3223e-06, 'epoch': 0.73, 'throughput': 20947.01}
+
+[INFO|2025-05-29 23:09:53] logging.py:157 >> {'loss': 0.7054, 'learning_rate': 3.3494e-06, 'epoch': 0.82, 'throughput': 20961.84}
+
+[INFO|2025-05-29 23:11:32] logging.py:157 >> {'loss': 0.7032, 'learning_rate': 8.5185e-07, 'epoch': 0.90, 'throughput': 20974.14}
+
+[INFO|2025-05-29 23:13:11] logging.py:157 >> {'loss': 0.7144, 'learning_rate': 0.0000e+00, 'epoch': 0.98, 'throughput': 20986.53}
+
+[INFO|2025-05-29 23:13:11] trainer.py:3910 >> Saving model checkpoint to saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_nsx_8_1/checkpoint-12
+
+[INFO|2025-05-29 23:13:11] configuration_utils.py:420 >> Configuration saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_nsx_8_1/checkpoint-12/config.json
+
+[INFO|2025-05-29 23:13:11] configuration_utils.py:909 >> Configuration saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_nsx_8_1/checkpoint-12/generation_config.json
+
+[INFO|2025-05-29 23:13:32] modeling_utils.py:2996 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 3 checkpoint shards. You can find where each parameters has been saved in the index located at saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_nsx_8_1/checkpoint-12/model.safetensors.index.json.
+
+[INFO|2025-05-29 23:13:32] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_nsx_8_1/checkpoint-12/tokenizer_config.json
+
+[INFO|2025-05-29 23:13:32] tokenization_utils_base.py:2500 >> Special tokens file saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_nsx_8_1/checkpoint-12/special_tokens_map.json
+
+[INFO|2025-05-29 23:13:32] trainer.py:2643 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-05-29 23:13:32] trainer.py:3910 >> Saving model checkpoint to saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_nsx_8_1
+
+[INFO|2025-05-29 23:13:32] configuration_utils.py:420 >> Configuration saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_nsx_8_1/config.json
+
+[INFO|2025-05-29 23:13:32] configuration_utils.py:909 >> Configuration saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_nsx_8_1/generation_config.json
+
+[INFO|2025-05-29 23:13:53] modeling_utils.py:2996 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 3 checkpoint shards. You can find where each parameters has been saved in the index located at saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_nsx_8_1/model.safetensors.index.json.
+
+[INFO|2025-05-29 23:13:53] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_nsx_8_1/tokenizer_config.json
+
+[INFO|2025-05-29 23:13:53] tokenization_utils_base.py:2500 >> Special tokens file saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_nsx_8_1/special_tokens_map.json
+
+[WARNING|2025-05-29 23:13:54] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2025-05-29 23:13:54] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2025-05-29 23:13:54] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,149 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100003": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100004": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100006": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100007": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100008": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100009": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100010": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100011": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100012": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100013": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100014": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100015": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set ns.found = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9795918367346939,
+    "num_input_tokens_seen": 25165824,
+    "total_flos": 9.800984115271434e+17,
+    "train_loss": 0.7565137396256129,
+    "train_runtime": 1221.0904,
+    "train_samples_per_second": 5.136,
+    "train_steps_per_second": 0.01
+}

trainer_log.jsonl

@@ -0,0 +1,13 @@
+{"current_steps": 1, "total_steps": 12, "loss": 0.848, "lr": 4.914814565722671e-05, "epoch": 0.08163265306122448, "percentage": 8.33, "elapsed_time": "0:01:45", "remaining_time": "0:19:20", "throughput": 19880.44, "total_tokens": 2097152}
+{"current_steps": 2, "total_steps": 12, "loss": 0.8111, "lr": 4.665063509461097e-05, "epoch": 0.16326530612244897, "percentage": 16.67, "elapsed_time": "0:03:25", "remaining_time": "0:17:06", "throughput": 20427.48, "total_tokens": 4194304}
+{"current_steps": 3, "total_steps": 12, "loss": 0.7984, "lr": 4.267766952966369e-05, "epoch": 0.24489795918367346, "percentage": 25.0, "elapsed_time": "0:05:04", "remaining_time": "0:15:14", "throughput": 20649.67, "total_tokens": 6291456}
+{"current_steps": 4, "total_steps": 12, "loss": 0.7649, "lr": 3.7500000000000003e-05, "epoch": 0.32653061224489793, "percentage": 33.33, "elapsed_time": "0:06:44", "remaining_time": "0:13:28", "throughput": 20755.74, "total_tokens": 8388608}
+{"current_steps": 5, "total_steps": 12, "loss": 0.7687, "lr": 3.147047612756302e-05, "epoch": 0.40816326530612246, "percentage": 41.67, "elapsed_time": "0:08:23", "remaining_time": "0:11:44", "throughput": 20825.02, "total_tokens": 10485760}
+{"current_steps": 6, "total_steps": 12, "loss": 0.7696, "lr": 2.5e-05, "epoch": 0.4897959183673469, "percentage": 50.0, "elapsed_time": "0:10:02", "remaining_time": "0:10:02", "throughput": 20874.16, "total_tokens": 12582912}
+{"current_steps": 7, "total_steps": 12, "loss": 0.7488, "lr": 1.852952387243698e-05, "epoch": 0.5714285714285714, "percentage": 58.33, "elapsed_time": "0:11:42", "remaining_time": "0:08:21", "throughput": 20909.51, "total_tokens": 14680064}
+{"current_steps": 8, "total_steps": 12, "loss": 0.7368, "lr": 1.2500000000000006e-05, "epoch": 0.6530612244897959, "percentage": 66.67, "elapsed_time": "0:13:21", "remaining_time": "0:06:40", "throughput": 20931.46, "total_tokens": 16777216}
+{"current_steps": 9, "total_steps": 12, "loss": 0.7088, "lr": 7.3223304703363135e-06, "epoch": 0.7346938775510204, "percentage": 75.0, "elapsed_time": "0:15:01", "remaining_time": "0:05:00", "throughput": 20947.01, "total_tokens": 18874368}
+{"current_steps": 10, "total_steps": 12, "loss": 0.7054, "lr": 3.3493649053890326e-06, "epoch": 0.8163265306122449, "percentage": 83.33, "elapsed_time": "0:16:40", "remaining_time": "0:03:20", "throughput": 20961.84, "total_tokens": 20971520}
+{"current_steps": 11, "total_steps": 12, "loss": 0.7032, "lr": 8.51854342773295e-07, "epoch": 0.8979591836734694, "percentage": 91.67, "elapsed_time": "0:18:19", "remaining_time": "0:01:39", "throughput": 20974.14, "total_tokens": 23068672}
+{"current_steps": 12, "total_steps": 12, "loss": 0.7144, "lr": 0.0, "epoch": 0.9795918367346939, "percentage": 100.0, "elapsed_time": "0:19:59", "remaining_time": "0:00:00", "throughput": 20986.53, "total_tokens": 25165824}
+{"current_steps": 12, "total_steps": 12, "epoch": 0.9795918367346939, "percentage": 100.0, "elapsed_time": "0:20:20", "remaining_time": "0:00:00", "throughput": 20626.1, "total_tokens": 25165824}

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9795918367346939,
+  "eval_steps": 500,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08163265306122448,
+      "grad_norm": 0.5826467275619507,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.848,
+      "num_input_tokens_seen": 2097152,
+      "step": 1
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 0.5116532444953918,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.8111,
+      "num_input_tokens_seen": 4194304,
+      "step": 2
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 0.46351540088653564,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.7984,
+      "num_input_tokens_seen": 6291456,
+      "step": 3
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.39698782563209534,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.7649,
+      "num_input_tokens_seen": 8388608,
+      "step": 4
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 0.3687557578086853,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 0.7687,
+      "num_input_tokens_seen": 10485760,
+      "step": 5
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 0.3421611785888672,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7696,
+      "num_input_tokens_seen": 12582912,
+      "step": 6
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.3205947279930115,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 0.7488,
+      "num_input_tokens_seen": 14680064,
+      "step": 7
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 0.2887260913848877,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.7368,
+      "num_input_tokens_seen": 16777216,
+      "step": 8
+    },
+    {
+      "epoch": 0.7346938775510204,
+      "grad_norm": 0.3012808561325073,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.7088,
+      "num_input_tokens_seen": 18874368,
+      "step": 9
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.3112427592277527,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.7054,
+      "num_input_tokens_seen": 20971520,
+      "step": 10
+    },
+    {
+      "epoch": 0.8979591836734694,
+      "grad_norm": 0.29755619168281555,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 0.7032,
+      "num_input_tokens_seen": 23068672,
+      "step": 11
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 0.30344462394714355,
+      "learning_rate": 0.0,
+      "loss": 0.7144,
+      "num_input_tokens_seen": 25165824,
+      "step": 12
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "num_input_tokens_seen": 25165824,
+      "step": 12,
+      "total_flos": 9.800984115271434e+17,
+      "train_loss": 0.7565137396256129,
+      "train_runtime": 1221.0904,
+      "train_samples_per_second": 5.136,
+      "train_steps_per_second": 0.01
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 12,
+  "num_input_tokens_seen": 25165824,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.800984115271434e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f8b77590e8f79fc02f78a48259c2e8ebd4d92de94debe9fdb2a985d8788b984
+size 5688

training_args.yaml

@@ -0,0 +1,38 @@
+apollo_rank: 256
+apollo_scale: 1
+apollo_target: all
+apollo_update_interval: 200
+bf16: true
+cutoff_len: 4096
+dataset: codes_nsx_over81
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+enable_liger_kernel: true
+finetuning_type: freeze
+flash_attn: auto
+freeze_trainable_layers: 2
+freeze_trainable_modules: all
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 5.0e-05
+logging_steps: 1
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 50000000
+model_name_or_path: deepseek-ai/deepseek-coder-7b-instruct-v1.5
+neat_packing: true
+num_train_epochs: 1.0
+output_dir: saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_nsx_8_1
+packing: true
+per_device_train_batch_size: 16
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+rope_scaling: llama3
+save_steps: 500
+stage: sft
+template: deepseekcoder
+trust_remote_code: true
+use_apollo: true
+warmup_steps: 0