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_under8_nlx
+  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_under8_nlx
+
+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_nlx_under8 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: 3
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 384
+- total_eval_batch_size: 24
+- 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": 0.9927007299270073,
+    "num_input_tokens_seen": 133693440,
+    "total_flos": 5.206772811237949e+18,
+    "train_loss": 0.5589800634804893,
+    "train_runtime": 13057.0702,
+    "train_samples_per_second": 2.516,
+    "train_steps_per_second": 0.007
+}

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_nlx_under8
+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: 1000
+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: true
+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:ab33bb741d6e8ce4d1d422ce6a88f2e14eab013fd298562e78b513883eeb9be9
+size 4980944400

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68317f4d83c42990a754a3366020ea005a95b211fc1e61a72cfab1f37174f8e5
+size 4662149984

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-00003-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-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-00003-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-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-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 +1,405 @@
+[INFO|2025-07-09 20:08:23] 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|2025-07-09 20:08:23] 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|2025-07-09 20:08:23] tokenization_utils_base.py:2034 >> loading file tokenizer.model from cache at None
+
+[INFO|2025-07-09 20:08:23] 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|2025-07-09 20:08:23] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-07-09 20:08:23] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at None
+
+[INFO|2025-07-09 20:08:23] 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|2025-07-09 20:08:23] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-07-09 20:08:24] 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|2025-07-09 20:08:25] 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|2025-07-09 20:08:25] 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|2025-07-09 20:08:26] tokenization_utils_base.py:2034 >> loading file tokenizer.model from cache at None
+
+[INFO|2025-07-09 20:08:26] 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|2025-07-09 20:08:26] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-07-09 20:08:26] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at None
+
+[INFO|2025-07-09 20:08:26] 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|2025-07-09 20:08:26] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-07-09 20:08:26] 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|2025-07-09 20:08:26] logging.py:157 >> Loading dataset Codes3_query_filtered_553474_mark_less_than_8.0.json...
+
+[INFO|2025-07-09 20:09:10] 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|2025-07-09 20:09:10] 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|2025-07-09 20:09:10] logging.py:162 >> Input length is smaller than max length. Consider increase input length.
+
+[INFO|2025-07-09 20:09:10] logging.py:157 >> Using llama3 scaling strategy and setting scaling factor to 1.0.
+
+[INFO|2025-07-09 20:09:10] logging.py:157 >> Using block diagonal attention for sequence packing without cross-attention.
+
+[INFO|2025-07-09 20:09:11] logging.py:157 >> Liger kernel has been applied to the model.
+
+[INFO|2025-07-09 20:09:11] 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|2025-07-09 20:09:11] modeling_utils.py:1582 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2025-07-09 20:09:11] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 100000,
+  "eos_token_id": 100015
+}
+
+
+[INFO|2025-07-09 20:09:14] modeling_utils.py:4888 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
+
+
+[INFO|2025-07-09 20:09:14] 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|2025-07-09 20:09:14] 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|2025-07-09 20:09:14] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 100000,
+  "eos_token_id": 100015
+}
+
+
+[INFO|2025-07-09 20:09:14] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2025-07-09 20:09:14] logging.py:157 >> Using torch SDPA for faster training and inference.
+
+[INFO|2025-07-09 20:09:14] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2025-07-09 20:09:14] logging.py:157 >> Fine-tuning method: Freeze
+
+[INFO|2025-07-09 20:09:14] logging.py:157 >> Set trainable layers: .14.,.29.
+
+[INFO|2025-07-09 20:09:14] logging.py:157 >> trainable params: 404,766,720 || all params: 6,910,365,696 || trainable%: 5.8574
+
+[INFO|2025-07-09 20:09:14] trainer.py:741 >> Using auto half precision backend
+
+[INFO|2025-07-09 20:09:14] logging.py:157 >> Found linear modules: up_proj,k_proj,gate_proj,down_proj,o_proj,q_proj,v_proj
+
+[INFO|2025-07-09 20:09:14] 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|2025-07-09 20:09:15] trainer.py:2369 >> ***** Running training *****
+
+[INFO|2025-07-09 20:09:15] trainer.py:2370 >>   Num examples = 32,858
+
+[INFO|2025-07-09 20:09:15] trainer.py:2371 >>   Num Epochs = 1
+
+[INFO|2025-07-09 20:09:15] trainer.py:2372 >>   Instantaneous batch size per device = 16
+
+[INFO|2025-07-09 20:09:15] trainer.py:2375 >>   Total train batch size (w. parallel, distributed & accumulation) = 384
+
+[INFO|2025-07-09 20:09:15] trainer.py:2376 >>   Gradient Accumulation steps = 8
+
+[INFO|2025-07-09 20:09:15] trainer.py:2377 >>   Total optimization steps = 85
+
+[INFO|2025-07-09 20:09:15] trainer.py:2378 >>   Number of trainable parameters = 404,766,720
+
+[INFO|2025-07-09 20:11:56] logging.py:157 >> {'loss': 1.2528, 'learning_rate': 4.9983e-05, 'epoch': 0.01, 'throughput': 9835.11}
+
+[INFO|2025-07-09 20:14:29] logging.py:157 >> {'loss': 1.1456, 'learning_rate': 4.9932e-05, 'epoch': 0.02, 'throughput': 10039.91}
+
+[INFO|2025-07-09 20:17:02] logging.py:157 >> {'loss': 1.0528, 'learning_rate': 4.9846e-05, 'epoch': 0.04, 'throughput': 10116.78}
+
+[INFO|2025-07-09 20:19:35] logging.py:157 >> {'loss': 0.9542, 'learning_rate': 4.9727e-05, 'epoch': 0.05, 'throughput': 10154.68}
+
+[INFO|2025-07-09 20:22:08] logging.py:157 >> {'loss': 0.8888, 'learning_rate': 4.9574e-05, 'epoch': 0.06, 'throughput': 10175.92}
+
+[INFO|2025-07-09 20:24:43] logging.py:157 >> {'loss': 0.8125, 'learning_rate': 4.9388e-05, 'epoch': 0.07, 'throughput': 10177.83}
+
+[INFO|2025-07-09 20:27:16] logging.py:157 >> {'loss': 0.7639, 'learning_rate': 4.9168e-05, 'epoch': 0.08, 'throughput': 10187.10}
+
+[INFO|2025-07-09 20:29:49] logging.py:157 >> {'loss': 0.7068, 'learning_rate': 4.8915e-05, 'epoch': 0.09, 'throughput': 10197.99}
+
+[INFO|2025-07-09 20:32:23] logging.py:157 >> {'loss': 0.6852, 'learning_rate': 4.8630e-05, 'epoch': 0.11, 'throughput': 10205.83}
+
+[INFO|2025-07-09 20:34:56] logging.py:157 >> {'loss': 0.6571, 'learning_rate': 4.8312e-05, 'epoch': 0.12, 'throughput': 10211.26}
+
+[INFO|2025-07-09 20:37:29] logging.py:157 >> {'loss': 0.6347, 'learning_rate': 4.7962e-05, 'epoch': 0.13, 'throughput': 10216.60}
+
+[INFO|2025-07-09 20:40:02] logging.py:157 >> {'loss': 0.6191, 'learning_rate': 4.7581e-05, 'epoch': 0.14, 'throughput': 10220.74}
+
+[INFO|2025-07-09 20:42:36] logging.py:157 >> {'loss': 0.5761, 'learning_rate': 4.7169e-05, 'epoch': 0.15, 'throughput': 10224.20}
+
+[INFO|2025-07-09 20:45:09] logging.py:157 >> {'loss': 0.5772, 'learning_rate': 4.6727e-05, 'epoch': 0.16, 'throughput': 10227.13}
+
+[INFO|2025-07-09 20:47:42] logging.py:157 >> {'loss': 0.5579, 'learning_rate': 4.6255e-05, 'epoch': 0.18, 'throughput': 10229.70}
+
+[INFO|2025-07-09 20:50:15] logging.py:157 >> {'loss': 0.5674, 'learning_rate': 4.5755e-05, 'epoch': 0.19, 'throughput': 10233.46}
+
+[INFO|2025-07-09 20:52:48] logging.py:157 >> {'loss': 0.5767, 'learning_rate': 4.5225e-05, 'epoch': 0.20, 'throughput': 10235.03}
+
+[INFO|2025-07-09 20:55:21] logging.py:157 >> {'loss': 0.5559, 'learning_rate': 4.4669e-05, 'epoch': 0.21, 'throughput': 10236.83}
+
+[INFO|2025-07-09 20:57:55] logging.py:157 >> {'loss': 0.5603, 'learning_rate': 4.4085e-05, 'epoch': 0.22, 'throughput': 10238.16}
+
+[INFO|2025-07-09 21:00:28] logging.py:157 >> {'loss': 0.5541, 'learning_rate': 4.3475e-05, 'epoch': 0.23, 'throughput': 10239.41}
+
+[INFO|2025-07-09 21:03:01] logging.py:157 >> {'loss': 0.5358, 'learning_rate': 4.2840e-05, 'epoch': 0.25, 'throughput': 10240.84}
+
+[INFO|2025-07-09 21:05:34] logging.py:157 >> {'loss': 0.5290, 'learning_rate': 4.2181e-05, 'epoch': 0.26, 'throughput': 10242.63}
+
+[INFO|2025-07-09 21:08:07] logging.py:157 >> {'loss': 0.5391, 'learning_rate': 4.1498e-05, 'epoch': 0.27, 'throughput': 10243.79}
+
+[INFO|2025-07-09 21:10:40] logging.py:157 >> {'loss': 0.5368, 'learning_rate': 4.0793e-05, 'epoch': 0.28, 'throughput': 10244.74}
+
+[INFO|2025-07-09 21:13:14] logging.py:157 >> {'loss': 0.5226, 'learning_rate': 4.0066e-05, 'epoch': 0.29, 'throughput': 10245.36}
+
+[INFO|2025-07-09 21:15:47] logging.py:157 >> {'loss': 0.5181, 'learning_rate': 3.9318e-05, 'epoch': 0.30, 'throughput': 10245.84}
+
+[INFO|2025-07-09 21:18:20] logging.py:157 >> {'loss': 0.5368, 'learning_rate': 3.8551e-05, 'epoch': 0.32, 'throughput': 10246.61}
+
+[INFO|2025-07-09 21:20:53] logging.py:157 >> {'loss': 0.5143, 'learning_rate': 3.7766e-05, 'epoch': 0.33, 'throughput': 10247.05}
+
+[INFO|2025-07-09 21:23:27] logging.py:157 >> {'loss': 0.5084, 'learning_rate': 3.6963e-05, 'epoch': 0.34, 'throughput': 10247.38}
+
+[INFO|2025-07-09 21:26:00] logging.py:157 >> {'loss': 0.5026, 'learning_rate': 3.6143e-05, 'epoch': 0.35, 'throughput': 10247.73}
+
+[INFO|2025-07-09 21:28:33] logging.py:157 >> {'loss': 0.5300, 'learning_rate': 3.5309e-05, 'epoch': 0.36, 'throughput': 10248.10}
+
+[INFO|2025-07-09 21:31:07] logging.py:157 >> {'loss': 0.5320, 'learning_rate': 3.4460e-05, 'epoch': 0.37, 'throughput': 10248.71}
+
+[INFO|2025-07-09 21:33:40] logging.py:157 >> {'loss': 0.5257, 'learning_rate': 3.3599e-05, 'epoch': 0.39, 'throughput': 10248.92}
+
+[INFO|2025-07-09 21:36:13] logging.py:157 >> {'loss': 0.5078, 'learning_rate': 3.2725e-05, 'epoch': 0.40, 'throughput': 10249.40}
+
+[INFO|2025-07-09 21:38:46] logging.py:157 >> {'loss': 0.5012, 'learning_rate': 3.1842e-05, 'epoch': 0.41, 'throughput': 10249.82}
+
+[INFO|2025-07-09 21:41:20] logging.py:157 >> {'loss': 0.5117, 'learning_rate': 3.0948e-05, 'epoch': 0.42, 'throughput': 10250.03}
+
+[INFO|2025-07-09 21:43:53] logging.py:157 >> {'loss': 0.5160, 'learning_rate': 3.0047e-05, 'epoch': 0.43, 'throughput': 10250.39}
+
+[INFO|2025-07-09 21:46:26] logging.py:157 >> {'loss': 0.5189, 'learning_rate': 2.9139e-05, 'epoch': 0.44, 'throughput': 10250.64}
+
+[INFO|2025-07-09 21:49:00] logging.py:157 >> {'loss': 0.4973, 'learning_rate': 2.8225e-05, 'epoch': 0.46, 'throughput': 10251.16}
+
+[INFO|2025-07-09 21:51:33] logging.py:157 >> {'loss': 0.4942, 'learning_rate': 2.7307e-05, 'epoch': 0.47, 'throughput': 10251.77}
+
+[INFO|2025-07-09 21:54:06] logging.py:157 >> {'loss': 0.5069, 'learning_rate': 2.6385e-05, 'epoch': 0.48, 'throughput': 10252.24}
+
+[INFO|2025-07-09 21:56:39] logging.py:157 >> {'loss': 0.5218, 'learning_rate': 2.5462e-05, 'epoch': 0.49, 'throughput': 10252.43}
+
+[INFO|2025-07-09 21:59:12] logging.py:157 >> {'loss': 0.5003, 'learning_rate': 2.4538e-05, 'epoch': 0.50, 'throughput': 10252.63}
+
+[INFO|2025-07-09 22:01:45] logging.py:157 >> {'loss': 0.4997, 'learning_rate': 2.3615e-05, 'epoch': 0.51, 'throughput': 10253.02}
+
+[INFO|2025-07-09 22:04:19] logging.py:157 >> {'loss': 0.5045, 'learning_rate': 2.2693e-05, 'epoch': 0.53, 'throughput': 10253.25}
+
+[INFO|2025-07-09 22:06:52] logging.py:157 >> {'loss': 0.4972, 'learning_rate': 2.1775e-05, 'epoch': 0.54, 'throughput': 10253.46}
+
+[INFO|2025-07-09 22:09:25] logging.py:157 >> {'loss': 0.5174, 'learning_rate': 2.0861e-05, 'epoch': 0.55, 'throughput': 10253.76}
+
+[INFO|2025-07-09 22:11:58] logging.py:157 >> {'loss': 0.5086, 'learning_rate': 1.9953e-05, 'epoch': 0.56, 'throughput': 10254.17}
+
+[INFO|2025-07-09 22:14:32] logging.py:157 >> {'loss': 0.4988, 'learning_rate': 1.9052e-05, 'epoch': 0.57, 'throughput': 10254.33}
+
+[INFO|2025-07-09 22:17:05] logging.py:157 >> {'loss': 0.5047, 'learning_rate': 1.8158e-05, 'epoch': 0.58, 'throughput': 10254.36}
+
+[INFO|2025-07-09 22:19:38] logging.py:157 >> {'loss': 0.4977, 'learning_rate': 1.7275e-05, 'epoch': 0.60, 'throughput': 10254.39}
+
+[INFO|2025-07-09 22:22:11] logging.py:157 >> {'loss': 0.4775, 'learning_rate': 1.6401e-05, 'epoch': 0.61, 'throughput': 10254.65}
+
+[INFO|2025-07-09 22:24:45] logging.py:157 >> {'loss': 0.5190, 'learning_rate': 1.5540e-05, 'epoch': 0.62, 'throughput': 10254.75}
+
+[INFO|2025-07-09 22:27:18] logging.py:157 >> {'loss': 0.5102, 'learning_rate': 1.4691e-05, 'epoch': 0.63, 'throughput': 10254.76}
+
+[INFO|2025-07-09 22:29:51] logging.py:157 >> {'loss': 0.4705, 'learning_rate': 1.3857e-05, 'epoch': 0.64, 'throughput': 10254.79}
+
+[INFO|2025-07-09 22:32:25] logging.py:157 >> {'loss': 0.4965, 'learning_rate': 1.3037e-05, 'epoch': 0.65, 'throughput': 10254.68}
+
+[INFO|2025-07-09 22:34:58] logging.py:157 >> {'loss': 0.5030, 'learning_rate': 1.2234e-05, 'epoch': 0.67, 'throughput': 10254.63}
+
+[INFO|2025-07-09 22:37:32] logging.py:157 >> {'loss': 0.4921, 'learning_rate': 1.1449e-05, 'epoch': 0.68, 'throughput': 10254.63}
+
+[INFO|2025-07-09 22:40:05] logging.py:157 >> {'loss': 0.5042, 'learning_rate': 1.0682e-05, 'epoch': 0.69, 'throughput': 10254.57}
+
+[INFO|2025-07-09 22:42:38] logging.py:157 >> {'loss': 0.5145, 'learning_rate': 9.9341e-06, 'epoch': 0.70, 'throughput': 10254.68}
+
+[INFO|2025-07-09 22:45:12] logging.py:157 >> {'loss': 0.4897, 'learning_rate': 9.2072e-06, 'epoch': 0.71, 'throughput': 10254.77}
+
+[INFO|2025-07-09 22:47:45] logging.py:157 >> {'loss': 0.5033, 'learning_rate': 8.5019e-06, 'epoch': 0.72, 'throughput': 10254.85}
+
+[INFO|2025-07-09 22:50:18] logging.py:157 >> {'loss': 0.4730, 'learning_rate': 7.8191e-06, 'epoch': 0.74, 'throughput': 10254.95}
+
+[INFO|2025-07-09 22:52:52] logging.py:157 >> {'loss': 0.5298, 'learning_rate': 7.1597e-06, 'epoch': 0.75, 'throughput': 10255.10}
+
+[INFO|2025-07-09 22:55:25] logging.py:157 >> {'loss': 0.4685, 'learning_rate': 6.5248e-06, 'epoch': 0.76, 'throughput': 10255.23}
+
+[INFO|2025-07-09 22:57:58] logging.py:157 >> {'loss': 0.4931, 'learning_rate': 5.9150e-06, 'epoch': 0.77, 'throughput': 10255.33}
+
+[INFO|2025-07-09 23:00:31] logging.py:157 >> {'loss': 0.4957, 'learning_rate': 5.3314e-06, 'epoch': 0.78, 'throughput': 10255.52}
+
+[INFO|2025-07-09 23:03:04] logging.py:157 >> {'loss': 0.4924, 'learning_rate': 4.7746e-06, 'epoch': 0.79, 'throughput': 10255.76}
+
+[INFO|2025-07-09 23:05:38] logging.py:157 >> {'loss': 0.5041, 'learning_rate': 4.2454e-06, 'epoch': 0.81, 'throughput': 10255.93}
+
+[INFO|2025-07-09 23:08:11] logging.py:157 >> {'loss': 0.4948, 'learning_rate': 3.7446e-06, 'epoch': 0.82, 'throughput': 10256.07}
+
+[INFO|2025-07-09 23:10:44] logging.py:157 >> {'loss': 0.5085, 'learning_rate': 3.2728e-06, 'epoch': 0.83, 'throughput': 10256.08}
+
+[INFO|2025-07-09 23:13:17] logging.py:157 >> {'loss': 0.5152, 'learning_rate': 2.8307e-06, 'epoch': 0.84, 'throughput': 10256.66}
+
+[INFO|2025-07-09 23:15:50] logging.py:157 >> {'loss': 0.4905, 'learning_rate': 2.4188e-06, 'epoch': 0.85, 'throughput': 10256.64}
+
+[INFO|2025-07-09 23:18:24] logging.py:157 >> {'loss': 0.5023, 'learning_rate': 2.0378e-06, 'epoch': 0.86, 'throughput': 10256.67}
+
+[INFO|2025-07-09 23:20:57] logging.py:157 >> {'loss': 0.4993, 'learning_rate': 1.6882e-06, 'epoch': 0.88, 'throughput': 10256.80}
+
+[INFO|2025-07-09 23:23:30] logging.py:157 >> {'loss': 0.4810, 'learning_rate': 1.3704e-06, 'epoch': 0.89, 'throughput': 10256.78}
+
+[INFO|2025-07-09 23:26:04] logging.py:157 >> {'loss': 0.4806, 'learning_rate': 1.0849e-06, 'epoch': 0.90, 'throughput': 10256.76}
+
+[INFO|2025-07-09 23:28:37] logging.py:157 >> {'loss': 0.4915, 'learning_rate': 8.3204e-07, 'epoch': 0.91, 'throughput': 10256.95}
+
+[INFO|2025-07-09 23:31:10] logging.py:157 >> {'loss': 0.4937, 'learning_rate': 6.1220e-07, 'epoch': 0.92, 'throughput': 10256.91}
+
+[INFO|2025-07-09 23:33:43] logging.py:157 >> {'loss': 0.5152, 'learning_rate': 4.2567e-07, 'epoch': 0.93, 'throughput': 10256.86}
+
+[INFO|2025-07-09 23:36:17] logging.py:157 >> {'loss': 0.4832, 'learning_rate': 2.7271e-07, 'epoch': 0.95, 'throughput': 10257.04}
+
+[INFO|2025-07-09 23:38:50] logging.py:157 >> {'loss': 0.4975, 'learning_rate': 1.5352e-07, 'epoch': 0.96, 'throughput': 10257.12}
+
+[INFO|2025-07-09 23:41:23] logging.py:157 >> {'loss': 0.4887, 'learning_rate': 6.8271e-08, 'epoch': 0.97, 'throughput': 10257.16}
+
+[INFO|2025-07-09 23:43:56] logging.py:157 >> {'loss': 0.4905, 'learning_rate': 1.7073e-08, 'epoch': 0.98, 'throughput': 10257.17}
+
+[INFO|2025-07-09 23:46:30] logging.py:157 >> {'loss': 0.5088, 'learning_rate': 0.0000e+00, 'epoch': 0.99, 'throughput': 10257.11}
+
+[INFO|2025-07-09 23:46:30] trainer.py:3910 >> Saving model checkpoint to saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_under8_nlx/checkpoint-85
+
+[INFO|2025-07-09 23:46:30] configuration_utils.py:420 >> Configuration saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_under8_nlx/checkpoint-85/config.json
+
+[INFO|2025-07-09 23:46:30] configuration_utils.py:909 >> Configuration saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_under8_nlx/checkpoint-85/generation_config.json
+
+[INFO|2025-07-09 23:46:51] 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_under8_nlx/checkpoint-85/model.safetensors.index.json.
+
+[INFO|2025-07-09 23:46:51] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_under8_nlx/checkpoint-85/tokenizer_config.json
+
+[INFO|2025-07-09 23:46:51] tokenization_utils_base.py:2500 >> Special tokens file saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_under8_nlx/checkpoint-85/special_tokens_map.json
+
+[INFO|2025-07-09 23:46:52] trainer.py:2643 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-07-09 23:46:52] trainer.py:3910 >> Saving model checkpoint to saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_under8_nlx
+
+[INFO|2025-07-09 23:46:52] configuration_utils.py:420 >> Configuration saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_under8_nlx/config.json
+
+[INFO|2025-07-09 23:46:52] configuration_utils.py:909 >> Configuration saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_under8_nlx/generation_config.json
+
+[INFO|2025-07-09 23:47:16] 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_under8_nlx/model.safetensors.index.json.
+
+[INFO|2025-07-09 23:47:16] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_under8_nlx/tokenizer_config.json
+
+[INFO|2025-07-09 23:47:16] tokenization_utils_base.py:2500 >> Special tokens file saved in saves/DeepSeek-Coder-7B-Instruct/freeze/deepseek_under8_nlx/special_tokens_map.json
+
+[WARNING|2025-07-09 23:47:16] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2025-07-09 23:47:16] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2025-07-09 23:47:16] 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": 0.9927007299270073,
+    "num_input_tokens_seen": 133693440,
+    "total_flos": 5.206772811237949e+18,
+    "train_loss": 0.5589800634804893,
+    "train_runtime": 13057.0702,
+    "train_samples_per_second": 2.516,
+    "train_steps_per_second": 0.007
+}

trainer_log.jsonl

@@ -0,0 +1,86 @@
+{"current_steps": 1, "total_steps": 85, "loss": 1.2528, "lr": 4.998292650357558e-05, "epoch": 0.01167883211678832, "percentage": 1.18, "elapsed_time": "0:02:39", "remaining_time": "3:43:53", "throughput": 9835.11, "total_tokens": 1572864}
+{"current_steps": 2, "total_steps": 85, "loss": 1.1456, "lr": 4.993172933464471e-05, "epoch": 0.02335766423357664, "percentage": 2.35, "elapsed_time": "0:05:13", "remaining_time": "3:36:42", "throughput": 10039.91, "total_tokens": 3145728}
+{"current_steps": 3, "total_steps": 85, "loss": 1.0528, "lr": 4.984647842238185e-05, "epoch": 0.035036496350364967, "percentage": 3.53, "elapsed_time": "0:07:46", "remaining_time": "3:32:28", "throughput": 10116.78, "total_tokens": 4718592}
+{"current_steps": 4, "total_steps": 85, "loss": 0.9542, "lr": 4.972729020927865e-05, "epoch": 0.04671532846715328, "percentage": 4.71, "elapsed_time": "0:10:19", "remaining_time": "3:29:06", "throughput": 10154.68, "total_tokens": 6291456}
+{"current_steps": 5, "total_steps": 85, "loss": 0.8888, "lr": 4.957432749209755e-05, "epoch": 0.058394160583941604, "percentage": 5.88, "elapsed_time": "0:12:52", "remaining_time": "3:26:05", "throughput": 10175.92, "total_tokens": 7864320}
+{"current_steps": 6, "total_steps": 85, "loss": 0.8125, "lr": 4.938779919951092e-05, "epoch": 0.07007299270072993, "percentage": 7.06, "elapsed_time": "0:15:27", "remaining_time": "3:23:28", "throughput": 10177.83, "total_tokens": 9437184}
+{"current_steps": 7, "total_steps": 85, "loss": 0.7639, "lr": 4.916796010672969e-05, "epoch": 0.08175182481751825, "percentage": 8.24, "elapsed_time": "0:18:00", "remaining_time": "3:20:43", "throughput": 10187.1, "total_tokens": 11010048}
+{"current_steps": 8, "total_steps": 85, "loss": 0.7068, "lr": 4.891511048751102e-05, "epoch": 0.09343065693430656, "percentage": 9.41, "elapsed_time": "0:20:33", "remaining_time": "3:17:55", "throughput": 10197.99, "total_tokens": 12582912}
+{"current_steps": 9, "total_steps": 85, "loss": 0.6852, "lr": 4.862959570402049e-05, "epoch": 0.10510948905109489, "percentage": 10.59, "elapsed_time": "0:23:07", "remaining_time": "3:15:12", "throughput": 10205.83, "total_tokens": 14155776}
+{"current_steps": 10, "total_steps": 85, "loss": 0.6571, "lr": 4.8311805735108894e-05, "epoch": 0.11678832116788321, "percentage": 11.76, "elapsed_time": "0:25:40", "remaining_time": "3:12:32", "throughput": 10211.26, "total_tokens": 15728640}
+{"current_steps": 11, "total_steps": 85, "loss": 0.6347, "lr": 4.796217464364808e-05, "epoch": 0.12846715328467154, "percentage": 12.94, "elapsed_time": "0:28:13", "remaining_time": "3:09:52", "throughput": 10216.6, "total_tokens": 17301504}
+{"current_steps": 12, "total_steps": 85, "loss": 0.6191, "lr": 4.758117998365322e-05, "epoch": 0.14014598540145987, "percentage": 14.12, "elapsed_time": "0:30:46", "remaining_time": "3:07:13", "throughput": 10220.74, "total_tokens": 18874368}
+{"current_steps": 13, "total_steps": 85, "loss": 0.5761, "lr": 4.716934214800155e-05, "epoch": 0.15182481751824817, "percentage": 15.29, "elapsed_time": "0:33:19", "remaining_time": "3:04:36", "throughput": 10224.2, "total_tokens": 20447232}
+{"current_steps": 14, "total_steps": 85, "loss": 0.5772, "lr": 4.672722365763821e-05, "epoch": 0.1635036496350365, "percentage": 16.47, "elapsed_time": "0:35:53", "remaining_time": "3:01:59", "throughput": 10227.13, "total_tokens": 22020096}
+{"current_steps": 15, "total_steps": 85, "loss": 0.5579, "lr": 4.625542839324036e-05, "epoch": 0.17518248175182483, "percentage": 17.65, "elapsed_time": "0:38:26", "remaining_time": "2:59:22", "throughput": 10229.7, "total_tokens": 23592960}
+{"current_steps": 16, "total_steps": 85, "loss": 0.5674, "lr": 4.575460077038877e-05, "epoch": 0.18686131386861313, "percentage": 18.82, "elapsed_time": "0:40:59", "remaining_time": "2:56:45", "throughput": 10233.46, "total_tokens": 25165824}
+{"current_steps": 17, "total_steps": 85, "loss": 0.5767, "lr": 4.522542485937369e-05, "epoch": 0.19854014598540146, "percentage": 20.0, "elapsed_time": "0:43:32", "remaining_time": "2:54:09", "throughput": 10235.03, "total_tokens": 26738688}
+{"current_steps": 18, "total_steps": 85, "loss": 0.5559, "lr": 4.4668623450837085e-05, "epoch": 0.21021897810218979, "percentage": 21.18, "elapsed_time": "0:46:05", "remaining_time": "2:51:34", "throughput": 10236.83, "total_tokens": 28311552}
+{"current_steps": 19, "total_steps": 85, "loss": 0.5603, "lr": 4.408495706852758e-05, "epoch": 0.22189781021897811, "percentage": 22.35, "elapsed_time": "0:48:38", "remaining_time": "2:48:59", "throughput": 10238.16, "total_tokens": 29884416}
+{"current_steps": 20, "total_steps": 85, "loss": 0.5541, "lr": 4.347522293051648e-05, "epoch": 0.23357664233576642, "percentage": 23.53, "elapsed_time": "0:51:12", "remaining_time": "2:46:24", "throughput": 10239.41, "total_tokens": 31457280}
+{"current_steps": 21, "total_steps": 85, "loss": 0.5358, "lr": 4.284025386029381e-05, "epoch": 0.24525547445255474, "percentage": 24.71, "elapsed_time": "0:53:45", "remaining_time": "2:43:49", "throughput": 10240.84, "total_tokens": 33030144}
+{"current_steps": 22, "total_steps": 85, "loss": 0.529, "lr": 4.218091714923157e-05, "epoch": 0.2569343065693431, "percentage": 25.88, "elapsed_time": "0:56:18", "remaining_time": "2:41:14", "throughput": 10242.63, "total_tokens": 34603008}
+{"current_steps": 23, "total_steps": 85, "loss": 0.5391, "lr": 4.149811337196807e-05, "epoch": 0.2686131386861314, "percentage": 27.06, "elapsed_time": "0:58:51", "remaining_time": "2:38:39", "throughput": 10243.79, "total_tokens": 36175872}
+{"current_steps": 24, "total_steps": 85, "loss": 0.5368, "lr": 4.079277515633127e-05, "epoch": 0.28029197080291973, "percentage": 28.24, "elapsed_time": "1:01:24", "remaining_time": "2:36:05", "throughput": 10244.74, "total_tokens": 37748736}
+{"current_steps": 25, "total_steps": 85, "loss": 0.5226, "lr": 4.0065865909481417e-05, "epoch": 0.291970802919708, "percentage": 29.41, "elapsed_time": "1:03:57", "remaining_time": "2:33:31", "throughput": 10245.36, "total_tokens": 39321600}
+{"current_steps": 26, "total_steps": 85, "loss": 0.5181, "lr": 3.931837850201263e-05, "epoch": 0.30364963503649633, "percentage": 30.59, "elapsed_time": "1:06:31", "remaining_time": "2:30:57", "throughput": 10245.84, "total_tokens": 40894464}
+{"current_steps": 27, "total_steps": 85, "loss": 0.5368, "lr": 3.855133391181124e-05, "epoch": 0.31532846715328466, "percentage": 31.76, "elapsed_time": "1:09:04", "remaining_time": "2:28:23", "throughput": 10246.61, "total_tokens": 42467328}
+{"current_steps": 28, "total_steps": 85, "loss": 0.5143, "lr": 3.7765779829522675e-05, "epoch": 0.327007299270073, "percentage": 32.94, "elapsed_time": "1:11:37", "remaining_time": "2:25:49", "throughput": 10247.05, "total_tokens": 44040192}
+{"current_steps": 29, "total_steps": 85, "loss": 0.5084, "lr": 3.696278922753216e-05, "epoch": 0.3386861313868613, "percentage": 34.12, "elapsed_time": "1:14:11", "remaining_time": "2:23:15", "throughput": 10247.38, "total_tokens": 45613056}
+{"current_steps": 30, "total_steps": 85, "loss": 0.5026, "lr": 3.6143458894413465e-05, "epoch": 0.35036496350364965, "percentage": 35.29, "elapsed_time": "1:16:44", "remaining_time": "2:20:41", "throughput": 10247.73, "total_tokens": 47185920}
+{"current_steps": 31, "total_steps": 85, "loss": 0.53, "lr": 3.5308907936847594e-05, "epoch": 0.362043795620438, "percentage": 36.47, "elapsed_time": "1:19:17", "remaining_time": "2:18:07", "throughput": 10248.1, "total_tokens": 48758784}
+{"current_steps": 32, "total_steps": 85, "loss": 0.532, "lr": 3.446027625105776e-05, "epoch": 0.37372262773722625, "percentage": 37.65, "elapsed_time": "1:21:51", "remaining_time": "2:15:33", "throughput": 10248.71, "total_tokens": 50331648}
+{"current_steps": 33, "total_steps": 85, "loss": 0.5257, "lr": 3.3598722965848204e-05, "epoch": 0.3854014598540146, "percentage": 38.82, "elapsed_time": "1:24:24", "remaining_time": "2:13:00", "throughput": 10248.92, "total_tokens": 51904512}
+{"current_steps": 34, "total_steps": 85, "loss": 0.5078, "lr": 3.272542485937369e-05, "epoch": 0.3970802919708029, "percentage": 40.0, "elapsed_time": "1:26:57", "remaining_time": "2:10:26", "throughput": 10249.4, "total_tokens": 53477376}
+{"current_steps": 35, "total_steps": 85, "loss": 0.5012, "lr": 3.1841574751802076e-05, "epoch": 0.40875912408759124, "percentage": 41.18, "elapsed_time": "1:29:30", "remaining_time": "2:07:52", "throughput": 10249.82, "total_tokens": 55050240}
+{"current_steps": 36, "total_steps": 85, "loss": 0.5117, "lr": 3.094837987606547e-05, "epoch": 0.42043795620437957, "percentage": 42.35, "elapsed_time": "1:32:04", "remaining_time": "2:05:19", "throughput": 10250.03, "total_tokens": 56623104}
+{"current_steps": 37, "total_steps": 85, "loss": 0.516, "lr": 3.0047060228925256e-05, "epoch": 0.4321167883211679, "percentage": 43.53, "elapsed_time": "1:34:37", "remaining_time": "2:02:45", "throughput": 10250.39, "total_tokens": 58195968}
+{"current_steps": 38, "total_steps": 85, "loss": 0.5189, "lr": 2.913884690460325e-05, "epoch": 0.44379562043795623, "percentage": 44.71, "elapsed_time": "1:37:10", "remaining_time": "2:00:11", "throughput": 10250.64, "total_tokens": 59768832}
+{"current_steps": 39, "total_steps": 85, "loss": 0.4973, "lr": 2.8224980413255086e-05, "epoch": 0.4554744525547445, "percentage": 45.88, "elapsed_time": "1:39:43", "remaining_time": "1:57:37", "throughput": 10251.16, "total_tokens": 61341696}
+{"current_steps": 40, "total_steps": 85, "loss": 0.4942, "lr": 2.7306708986582553e-05, "epoch": 0.46715328467153283, "percentage": 47.06, "elapsed_time": "1:42:16", "remaining_time": "1:55:04", "throughput": 10251.77, "total_tokens": 62914560}
+{"current_steps": 41, "total_steps": 85, "loss": 0.5069, "lr": 2.638528687289925e-05, "epoch": 0.47883211678832116, "percentage": 48.24, "elapsed_time": "1:44:50", "remaining_time": "1:52:30", "throughput": 10252.24, "total_tokens": 64487424}
+{"current_steps": 42, "total_steps": 85, "loss": 0.5218, "lr": 2.5461972623978247e-05, "epoch": 0.4905109489051095, "percentage": 49.41, "elapsed_time": "1:47:23", "remaining_time": "1:49:56", "throughput": 10252.43, "total_tokens": 66060288}
+{"current_steps": 43, "total_steps": 85, "loss": 0.5003, "lr": 2.453802737602176e-05, "epoch": 0.5021897810218978, "percentage": 50.59, "elapsed_time": "1:49:56", "remaining_time": "1:47:23", "throughput": 10252.63, "total_tokens": 67633152}
+{"current_steps": 44, "total_steps": 85, "loss": 0.4997, "lr": 2.361471312710075e-05, "epoch": 0.5138686131386861, "percentage": 51.76, "elapsed_time": "1:52:29", "remaining_time": "1:44:49", "throughput": 10253.02, "total_tokens": 69206016}
+{"current_steps": 45, "total_steps": 85, "loss": 0.5045, "lr": 2.2693291013417453e-05, "epoch": 0.5255474452554745, "percentage": 52.94, "elapsed_time": "1:55:03", "remaining_time": "1:42:16", "throughput": 10253.25, "total_tokens": 70778880}
+{"current_steps": 46, "total_steps": 85, "loss": 0.4972, "lr": 2.1775019586744923e-05, "epoch": 0.5372262773722628, "percentage": 54.12, "elapsed_time": "1:57:36", "remaining_time": "1:39:42", "throughput": 10253.46, "total_tokens": 72351744}
+{"current_steps": 47, "total_steps": 85, "loss": 0.5174, "lr": 2.0861153095396748e-05, "epoch": 0.5489051094890511, "percentage": 55.29, "elapsed_time": "2:00:09", "remaining_time": "1:37:08", "throughput": 10253.76, "total_tokens": 73924608}
+{"current_steps": 48, "total_steps": 85, "loss": 0.5086, "lr": 1.995293977107475e-05, "epoch": 0.5605839416058395, "percentage": 56.47, "elapsed_time": "2:02:42", "remaining_time": "1:34:35", "throughput": 10254.17, "total_tokens": 75497472}
+{"current_steps": 49, "total_steps": 85, "loss": 0.4988, "lr": 1.9051620123934537e-05, "epoch": 0.5722627737226277, "percentage": 57.65, "elapsed_time": "2:05:15", "remaining_time": "1:32:01", "throughput": 10254.33, "total_tokens": 77070336}
+{"current_steps": 50, "total_steps": 85, "loss": 0.5047, "lr": 1.815842524819793e-05, "epoch": 0.583941605839416, "percentage": 58.82, "elapsed_time": "2:07:49", "remaining_time": "1:29:28", "throughput": 10254.36, "total_tokens": 78643200}
+{"current_steps": 51, "total_steps": 85, "loss": 0.4977, "lr": 1.7274575140626318e-05, "epoch": 0.5956204379562043, "percentage": 60.0, "elapsed_time": "2:10:22", "remaining_time": "1:26:55", "throughput": 10254.39, "total_tokens": 80216064}
+{"current_steps": 52, "total_steps": 85, "loss": 0.4775, "lr": 1.6401277034151798e-05, "epoch": 0.6072992700729927, "percentage": 61.18, "elapsed_time": "2:12:55", "remaining_time": "1:24:21", "throughput": 10254.65, "total_tokens": 81788928}
+{"current_steps": 53, "total_steps": 85, "loss": 0.519, "lr": 1.5539723748942245e-05, "epoch": 0.618978102189781, "percentage": 62.35, "elapsed_time": "2:15:29", "remaining_time": "1:21:48", "throughput": 10254.75, "total_tokens": 83361792}
+{"current_steps": 54, "total_steps": 85, "loss": 0.5102, "lr": 1.4691092063152417e-05, "epoch": 0.6306569343065693, "percentage": 63.53, "elapsed_time": "2:18:02", "remaining_time": "1:19:14", "throughput": 10254.76, "total_tokens": 84934656}
+{"current_steps": 55, "total_steps": 85, "loss": 0.4705, "lr": 1.3856541105586545e-05, "epoch": 0.6423357664233577, "percentage": 64.71, "elapsed_time": "2:20:35", "remaining_time": "1:16:41", "throughput": 10254.79, "total_tokens": 86507520}
+{"current_steps": 56, "total_steps": 85, "loss": 0.4965, "lr": 1.303721077246784e-05, "epoch": 0.654014598540146, "percentage": 65.88, "elapsed_time": "2:23:09", "remaining_time": "1:14:08", "throughput": 10254.68, "total_tokens": 88080384}
+{"current_steps": 57, "total_steps": 85, "loss": 0.503, "lr": 1.223422017047733e-05, "epoch": 0.6656934306569343, "percentage": 67.06, "elapsed_time": "2:25:42", "remaining_time": "1:11:34", "throughput": 10254.63, "total_tokens": 89653248}
+{"current_steps": 58, "total_steps": 85, "loss": 0.4921, "lr": 1.1448666088188764e-05, "epoch": 0.6773722627737226, "percentage": 68.24, "elapsed_time": "2:28:16", "remaining_time": "1:09:01", "throughput": 10254.63, "total_tokens": 91226112}
+{"current_steps": 59, "total_steps": 85, "loss": 0.5042, "lr": 1.068162149798737e-05, "epoch": 0.689051094890511, "percentage": 69.41, "elapsed_time": "2:30:49", "remaining_time": "1:06:27", "throughput": 10254.57, "total_tokens": 92798976}
+{"current_steps": 60, "total_steps": 85, "loss": 0.5145, "lr": 9.934134090518593e-06, "epoch": 0.7007299270072993, "percentage": 70.59, "elapsed_time": "2:33:22", "remaining_time": "1:03:54", "throughput": 10254.68, "total_tokens": 94371840}
+{"current_steps": 61, "total_steps": 85, "loss": 0.4897, "lr": 9.207224843668732e-06, "epoch": 0.7124087591240876, "percentage": 71.76, "elapsed_time": "2:35:56", "remaining_time": "1:01:21", "throughput": 10254.77, "total_tokens": 95944704}
+{"current_steps": 62, "total_steps": 85, "loss": 0.5033, "lr": 8.50188662803194e-06, "epoch": 0.724087591240876, "percentage": 72.94, "elapsed_time": "2:38:29", "remaining_time": "0:58:47", "throughput": 10254.85, "total_tokens": 97517568}
+{"current_steps": 63, "total_steps": 85, "loss": 0.473, "lr": 7.819082850768434e-06, "epoch": 0.7357664233576642, "percentage": 74.12, "elapsed_time": "2:41:02", "remaining_time": "0:56:14", "throughput": 10254.95, "total_tokens": 99090432}
+{"current_steps": 64, "total_steps": 85, "loss": 0.5298, "lr": 7.159746139706194e-06, "epoch": 0.7474452554744525, "percentage": 75.29, "elapsed_time": "2:43:35", "remaining_time": "0:53:40", "throughput": 10255.1, "total_tokens": 100663296}
+{"current_steps": 65, "total_steps": 85, "loss": 0.4685, "lr": 6.524777069483526e-06, "epoch": 0.7591240875912408, "percentage": 76.47, "elapsed_time": "2:46:09", "remaining_time": "0:51:07", "throughput": 10255.23, "total_tokens": 102236160}
+{"current_steps": 66, "total_steps": 85, "loss": 0.4931, "lr": 5.915042931472425e-06, "epoch": 0.7708029197080292, "percentage": 77.65, "elapsed_time": "2:48:42", "remaining_time": "0:48:34", "throughput": 10255.33, "total_tokens": 103809024}
+{"current_steps": 67, "total_steps": 85, "loss": 0.4957, "lr": 5.33137654916292e-06, "epoch": 0.7824817518248175, "percentage": 78.82, "elapsed_time": "2:51:15", "remaining_time": "0:46:00", "throughput": 10255.52, "total_tokens": 105381888}
+{"current_steps": 68, "total_steps": 85, "loss": 0.4924, "lr": 4.7745751406263165e-06, "epoch": 0.7941605839416058, "percentage": 80.0, "elapsed_time": "2:53:48", "remaining_time": "0:43:27", "throughput": 10255.76, "total_tokens": 106954752}
+{"current_steps": 69, "total_steps": 85, "loss": 0.5041, "lr": 4.245399229611238e-06, "epoch": 0.8058394160583942, "percentage": 81.18, "elapsed_time": "2:56:21", "remaining_time": "0:40:53", "throughput": 10255.93, "total_tokens": 108527616}
+{"current_steps": 70, "total_steps": 85, "loss": 0.4948, "lr": 3.7445716067596503e-06, "epoch": 0.8175182481751825, "percentage": 82.35, "elapsed_time": "2:58:55", "remaining_time": "0:38:20", "throughput": 10256.07, "total_tokens": 110100480}
+{"current_steps": 71, "total_steps": 85, "loss": 0.5085, "lr": 3.2727763423617913e-06, "epoch": 0.8291970802919708, "percentage": 83.53, "elapsed_time": "3:01:28", "remaining_time": "0:35:47", "throughput": 10256.08, "total_tokens": 111673344}
+{"current_steps": 72, "total_steps": 85, "loss": 0.5152, "lr": 2.8306578519984527e-06, "epoch": 0.8408759124087591, "percentage": 84.71, "elapsed_time": "3:04:01", "remaining_time": "0:33:13", "throughput": 10256.66, "total_tokens": 113246208}
+{"current_steps": 73, "total_steps": 85, "loss": 0.4905, "lr": 2.418820016346779e-06, "epoch": 0.8525547445255475, "percentage": 85.88, "elapsed_time": "3:06:34", "remaining_time": "0:30:40", "throughput": 10256.64, "total_tokens": 114819072}
+{"current_steps": 74, "total_steps": 85, "loss": 0.5023, "lr": 2.0378253563519247e-06, "epoch": 0.8642335766423358, "percentage": 87.06, "elapsed_time": "3:09:07", "remaining_time": "0:28:06", "throughput": 10256.67, "total_tokens": 116391936}
+{"current_steps": 75, "total_steps": 85, "loss": 0.4993, "lr": 1.6881942648911076e-06, "epoch": 0.8759124087591241, "percentage": 88.24, "elapsed_time": "3:11:41", "remaining_time": "0:25:33", "throughput": 10256.8, "total_tokens": 117964800}
+{"current_steps": 76, "total_steps": 85, "loss": 0.481, "lr": 1.3704042959795132e-06, "epoch": 0.8875912408759125, "percentage": 89.41, "elapsed_time": "3:14:14", "remaining_time": "0:23:00", "throughput": 10256.78, "total_tokens": 119537664}
+{"current_steps": 77, "total_steps": 85, "loss": 0.4806, "lr": 1.0848895124889818e-06, "epoch": 0.8992700729927007, "percentage": 90.59, "elapsed_time": "3:16:47", "remaining_time": "0:20:26", "throughput": 10256.76, "total_tokens": 121110528}
+{"current_steps": 78, "total_steps": 85, "loss": 0.4915, "lr": 8.320398932703144e-07, "epoch": 0.910948905109489, "percentage": 91.76, "elapsed_time": "3:19:20", "remaining_time": "0:17:53", "throughput": 10256.95, "total_tokens": 122683392}
+{"current_steps": 79, "total_steps": 85, "loss": 0.4937, "lr": 6.122008004890851e-07, "epoch": 0.9226277372262773, "percentage": 92.94, "elapsed_time": "3:21:54", "remaining_time": "0:15:20", "throughput": 10256.91, "total_tokens": 124256256}
+{"current_steps": 80, "total_steps": 85, "loss": 0.5152, "lr": 4.256725079024554e-07, "epoch": 0.9343065693430657, "percentage": 94.12, "elapsed_time": "3:24:27", "remaining_time": "0:12:46", "throughput": 10256.86, "total_tokens": 125829120}
+{"current_steps": 81, "total_steps": 85, "loss": 0.4832, "lr": 2.7270979072135104e-07, "epoch": 0.945985401459854, "percentage": 95.29, "elapsed_time": "3:27:00", "remaining_time": "0:10:13", "throughput": 10257.04, "total_tokens": 127401984}
+{"current_steps": 82, "total_steps": 85, "loss": 0.4975, "lr": 1.5352157761815977e-07, "epoch": 0.9576642335766423, "percentage": 96.47, "elapsed_time": "3:29:34", "remaining_time": "0:07:40", "throughput": 10257.12, "total_tokens": 128974848}
+{"current_steps": 83, "total_steps": 85, "loss": 0.4887, "lr": 6.827066535529946e-08, "epoch": 0.9693430656934306, "percentage": 97.65, "elapsed_time": "3:32:07", "remaining_time": "0:05:06", "throughput": 10257.16, "total_tokens": 130547712}
+{"current_steps": 84, "total_steps": 85, "loss": 0.4905, "lr": 1.7073496424427348e-08, "epoch": 0.981021897810219, "percentage": 98.82, "elapsed_time": "3:34:40", "remaining_time": "0:02:33", "throughput": 10257.17, "total_tokens": 132120576}
+{"current_steps": 85, "total_steps": 85, "loss": 0.5088, "lr": 0.0, "epoch": 0.9927007299270073, "percentage": 100.0, "elapsed_time": "3:37:14", "remaining_time": "0:00:00", "throughput": 10257.11, "total_tokens": 133693440}
+{"current_steps": 85, "total_steps": 85, "epoch": 0.9927007299270073, "percentage": 100.0, "elapsed_time": "3:37:36", "remaining_time": "0:00:00", "throughput": 10239.97, "total_tokens": 133693440}

trainer_state.json

@@ -0,0 +1,723 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9927007299270073,
+  "eval_steps": 500,
+  "global_step": 85,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01167883211678832,
+      "grad_norm": 2.102217674255371,
+      "learning_rate": 4.998292650357558e-05,
+      "loss": 1.2528,
+      "num_input_tokens_seen": 1572864,
+      "step": 1
+    },
+    {
+      "epoch": 0.02335766423357664,
+      "grad_norm": 1.8151874542236328,
+      "learning_rate": 4.993172933464471e-05,
+      "loss": 1.1456,
+      "num_input_tokens_seen": 3145728,
+      "step": 2
+    },
+    {
+      "epoch": 0.035036496350364967,
+      "grad_norm": 1.6563794612884521,
+      "learning_rate": 4.984647842238185e-05,
+      "loss": 1.0528,
+      "num_input_tokens_seen": 4718592,
+      "step": 3
+    },
+    {
+      "epoch": 0.04671532846715328,
+      "grad_norm": 1.4128868579864502,
+      "learning_rate": 4.972729020927865e-05,
+      "loss": 0.9542,
+      "num_input_tokens_seen": 6291456,
+      "step": 4
+    },
+    {
+      "epoch": 0.058394160583941604,
+      "grad_norm": 1.3149222135543823,
+      "learning_rate": 4.957432749209755e-05,
+      "loss": 0.8888,
+      "num_input_tokens_seen": 7864320,
+      "step": 5
+    },
+    {
+      "epoch": 0.07007299270072993,
+      "grad_norm": 1.1523312330245972,
+      "learning_rate": 4.938779919951092e-05,
+      "loss": 0.8125,
+      "num_input_tokens_seen": 9437184,
+      "step": 6
+    },
+    {
+      "epoch": 0.08175182481751825,
+      "grad_norm": 1.0558948516845703,
+      "learning_rate": 4.916796010672969e-05,
+      "loss": 0.7639,
+      "num_input_tokens_seen": 11010048,
+      "step": 7
+    },
+    {
+      "epoch": 0.09343065693430656,
+      "grad_norm": 0.9993464350700378,
+      "learning_rate": 4.891511048751102e-05,
+      "loss": 0.7068,
+      "num_input_tokens_seen": 12582912,
+      "step": 8
+    },
+    {
+      "epoch": 0.10510948905109489,
+      "grad_norm": 0.7277781367301941,
+      "learning_rate": 4.862959570402049e-05,
+      "loss": 0.6852,
+      "num_input_tokens_seen": 14155776,
+      "step": 9
+    },
+    {
+      "epoch": 0.11678832116788321,
+      "grad_norm": 0.33135032653808594,
+      "learning_rate": 4.8311805735108894e-05,
+      "loss": 0.6571,
+      "num_input_tokens_seen": 15728640,
+      "step": 10
+    },
+    {
+      "epoch": 0.12846715328467154,
+      "grad_norm": 0.24875016510486603,
+      "learning_rate": 4.796217464364808e-05,
+      "loss": 0.6347,
+      "num_input_tokens_seen": 17301504,
+      "step": 11
+    },
+    {
+      "epoch": 0.14014598540145987,
+      "grad_norm": 0.219735249876976,
+      "learning_rate": 4.758117998365322e-05,
+      "loss": 0.6191,
+      "num_input_tokens_seen": 18874368,
+      "step": 12
+    },
+    {
+      "epoch": 0.15182481751824817,
+      "grad_norm": 0.20399349927902222,
+      "learning_rate": 4.716934214800155e-05,
+      "loss": 0.5761,
+      "num_input_tokens_seen": 20447232,
+      "step": 13
+    },
+    {
+      "epoch": 0.1635036496350365,
+      "grad_norm": 0.18108128011226654,
+      "learning_rate": 4.672722365763821e-05,
+      "loss": 0.5772,
+      "num_input_tokens_seen": 22020096,
+      "step": 14
+    },
+    {
+      "epoch": 0.17518248175182483,
+      "grad_norm": 0.15887582302093506,
+      "learning_rate": 4.625542839324036e-05,
+      "loss": 0.5579,
+      "num_input_tokens_seen": 23592960,
+      "step": 15
+    },
+    {
+      "epoch": 0.18686131386861313,
+      "grad_norm": 0.1574232280254364,
+      "learning_rate": 4.575460077038877e-05,
+      "loss": 0.5674,
+      "num_input_tokens_seen": 25165824,
+      "step": 16
+    },
+    {
+      "epoch": 0.19854014598540146,
+      "grad_norm": 0.1397695690393448,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.5767,
+      "num_input_tokens_seen": 26738688,
+      "step": 17
+    },
+    {
+      "epoch": 0.21021897810218979,
+      "grad_norm": 0.12465737760066986,
+      "learning_rate": 4.4668623450837085e-05,
+      "loss": 0.5559,
+      "num_input_tokens_seen": 28311552,
+      "step": 18
+    },
+    {
+      "epoch": 0.22189781021897811,
+      "grad_norm": 0.10970822721719742,
+      "learning_rate": 4.408495706852758e-05,
+      "loss": 0.5603,
+      "num_input_tokens_seen": 29884416,
+      "step": 19
+    },
+    {
+      "epoch": 0.23357664233576642,
+      "grad_norm": 0.10278748720884323,
+      "learning_rate": 4.347522293051648e-05,
+      "loss": 0.5541,
+      "num_input_tokens_seen": 31457280,
+      "step": 20
+    },
+    {
+      "epoch": 0.24525547445255474,
+      "grad_norm": 0.09158932417631149,
+      "learning_rate": 4.284025386029381e-05,
+      "loss": 0.5358,
+      "num_input_tokens_seen": 33030144,
+      "step": 21
+    },
+    {
+      "epoch": 0.2569343065693431,
+      "grad_norm": 0.09265461564064026,
+      "learning_rate": 4.218091714923157e-05,
+      "loss": 0.529,
+      "num_input_tokens_seen": 34603008,
+      "step": 22
+    },
+    {
+      "epoch": 0.2686131386861314,
+      "grad_norm": 0.08593211323022842,
+      "learning_rate": 4.149811337196807e-05,
+      "loss": 0.5391,
+      "num_input_tokens_seen": 36175872,
+      "step": 23
+    },
+    {
+      "epoch": 0.28029197080291973,
+      "grad_norm": 0.07743365317583084,
+      "learning_rate": 4.079277515633127e-05,
+      "loss": 0.5368,
+      "num_input_tokens_seen": 37748736,
+      "step": 24
+    },
+    {
+      "epoch": 0.291970802919708,
+      "grad_norm": 0.08235425502061844,
+      "learning_rate": 4.0065865909481417e-05,
+      "loss": 0.5226,
+      "num_input_tokens_seen": 39321600,
+      "step": 25
+    },
+    {
+      "epoch": 0.30364963503649633,
+      "grad_norm": 0.07797503471374512,
+      "learning_rate": 3.931837850201263e-05,
+      "loss": 0.5181,
+      "num_input_tokens_seen": 40894464,
+      "step": 26
+    },
+    {
+      "epoch": 0.31532846715328466,
+      "grad_norm": 0.07740040868520737,
+      "learning_rate": 3.855133391181124e-05,
+      "loss": 0.5368,
+      "num_input_tokens_seen": 42467328,
+      "step": 27
+    },
+    {
+      "epoch": 0.327007299270073,
+      "grad_norm": 0.07796761393547058,
+      "learning_rate": 3.7765779829522675e-05,
+      "loss": 0.5143,
+      "num_input_tokens_seen": 44040192,
+      "step": 28
+    },
+    {
+      "epoch": 0.3386861313868613,
+      "grad_norm": 0.06905554234981537,
+      "learning_rate": 3.696278922753216e-05,
+      "loss": 0.5084,
+      "num_input_tokens_seen": 45613056,
+      "step": 29
+    },
+    {
+      "epoch": 0.35036496350364965,
+      "grad_norm": 0.07220657169818878,
+      "learning_rate": 3.6143458894413465e-05,
+      "loss": 0.5026,
+      "num_input_tokens_seen": 47185920,
+      "step": 30
+    },
+    {
+      "epoch": 0.362043795620438,
+      "grad_norm": 0.0667012482881546,
+      "learning_rate": 3.5308907936847594e-05,
+      "loss": 0.53,
+      "num_input_tokens_seen": 48758784,
+      "step": 31
+    },
+    {
+      "epoch": 0.37372262773722625,
+      "grad_norm": 0.06964272260665894,
+      "learning_rate": 3.446027625105776e-05,
+      "loss": 0.532,
+      "num_input_tokens_seen": 50331648,
+      "step": 32
+    },
+    {
+      "epoch": 0.3854014598540146,
+      "grad_norm": 0.06804265826940536,
+      "learning_rate": 3.3598722965848204e-05,
+      "loss": 0.5257,
+      "num_input_tokens_seen": 51904512,
+      "step": 33
+    },
+    {
+      "epoch": 0.3970802919708029,
+      "grad_norm": 0.06633932888507843,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.5078,
+      "num_input_tokens_seen": 53477376,
+      "step": 34
+    },
+    {
+      "epoch": 0.40875912408759124,
+      "grad_norm": 0.06411036849021912,
+      "learning_rate": 3.1841574751802076e-05,
+      "loss": 0.5012,
+      "num_input_tokens_seen": 55050240,
+      "step": 35
+    },
+    {
+      "epoch": 0.42043795620437957,
+      "grad_norm": 0.06728877872228622,
+      "learning_rate": 3.094837987606547e-05,
+      "loss": 0.5117,
+      "num_input_tokens_seen": 56623104,
+      "step": 36
+    },
+    {
+      "epoch": 0.4321167883211679,
+      "grad_norm": 0.06455469876527786,
+      "learning_rate": 3.0047060228925256e-05,
+      "loss": 0.516,
+      "num_input_tokens_seen": 58195968,
+      "step": 37
+    },
+    {
+      "epoch": 0.44379562043795623,
+      "grad_norm": 0.06497868150472641,
+      "learning_rate": 2.913884690460325e-05,
+      "loss": 0.5189,
+      "num_input_tokens_seen": 59768832,
+      "step": 38
+    },
+    {
+      "epoch": 0.4554744525547445,
+      "grad_norm": 0.062144387513399124,
+      "learning_rate": 2.8224980413255086e-05,
+      "loss": 0.4973,
+      "num_input_tokens_seen": 61341696,
+      "step": 39
+    },
+    {
+      "epoch": 0.46715328467153283,
+      "grad_norm": 0.064272440969944,
+      "learning_rate": 2.7306708986582553e-05,
+      "loss": 0.4942,
+      "num_input_tokens_seen": 62914560,
+      "step": 40
+    },
+    {
+      "epoch": 0.47883211678832116,
+      "grad_norm": 0.06099522113800049,
+      "learning_rate": 2.638528687289925e-05,
+      "loss": 0.5069,
+      "num_input_tokens_seen": 64487424,
+      "step": 41
+    },
+    {
+      "epoch": 0.4905109489051095,
+      "grad_norm": 0.06261651962995529,
+      "learning_rate": 2.5461972623978247e-05,
+      "loss": 0.5218,
+      "num_input_tokens_seen": 66060288,
+      "step": 42
+    },
+    {
+      "epoch": 0.5021897810218978,
+      "grad_norm": 0.059084702283144,
+      "learning_rate": 2.453802737602176e-05,
+      "loss": 0.5003,
+      "num_input_tokens_seen": 67633152,
+      "step": 43
+    },
+    {
+      "epoch": 0.5138686131386861,
+      "grad_norm": 0.05868009477853775,
+      "learning_rate": 2.361471312710075e-05,
+      "loss": 0.4997,
+      "num_input_tokens_seen": 69206016,
+      "step": 44
+    },
+    {
+      "epoch": 0.5255474452554745,
+      "grad_norm": 0.05527840927243233,
+      "learning_rate": 2.2693291013417453e-05,
+      "loss": 0.5045,
+      "num_input_tokens_seen": 70778880,
+      "step": 45
+    },
+    {
+      "epoch": 0.5372262773722628,
+      "grad_norm": 0.05962590128183365,
+      "learning_rate": 2.1775019586744923e-05,
+      "loss": 0.4972,
+      "num_input_tokens_seen": 72351744,
+      "step": 46
+    },
+    {
+      "epoch": 0.5489051094890511,
+      "grad_norm": 0.05784057453274727,
+      "learning_rate": 2.0861153095396748e-05,
+      "loss": 0.5174,
+      "num_input_tokens_seen": 73924608,
+      "step": 47
+    },
+    {
+      "epoch": 0.5605839416058395,
+      "grad_norm": 0.0580497644841671,
+      "learning_rate": 1.995293977107475e-05,
+      "loss": 0.5086,
+      "num_input_tokens_seen": 75497472,
+      "step": 48
+    },
+    {
+      "epoch": 0.5722627737226277,
+      "grad_norm": 0.05789309740066528,
+      "learning_rate": 1.9051620123934537e-05,
+      "loss": 0.4988,
+      "num_input_tokens_seen": 77070336,
+      "step": 49
+    },
+    {
+      "epoch": 0.583941605839416,
+      "grad_norm": 0.05743095278739929,
+      "learning_rate": 1.815842524819793e-05,
+      "loss": 0.5047,
+      "num_input_tokens_seen": 78643200,
+      "step": 50
+    },
+    {
+      "epoch": 0.5956204379562043,
+      "grad_norm": 0.05637204647064209,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.4977,
+      "num_input_tokens_seen": 80216064,
+      "step": 51
+    },
+    {
+      "epoch": 0.6072992700729927,
+      "grad_norm": 0.054249729961156845,
+      "learning_rate": 1.6401277034151798e-05,
+      "loss": 0.4775,
+      "num_input_tokens_seen": 81788928,
+      "step": 52
+    },
+    {
+      "epoch": 0.618978102189781,
+      "grad_norm": 0.05614548176527023,
+      "learning_rate": 1.5539723748942245e-05,
+      "loss": 0.519,
+      "num_input_tokens_seen": 83361792,
+      "step": 53
+    },
+    {
+      "epoch": 0.6306569343065693,
+      "grad_norm": 0.05785420536994934,
+      "learning_rate": 1.4691092063152417e-05,
+      "loss": 0.5102,
+      "num_input_tokens_seen": 84934656,
+      "step": 54
+    },
+    {
+      "epoch": 0.6423357664233577,
+      "grad_norm": 0.05397043377161026,
+      "learning_rate": 1.3856541105586545e-05,
+      "loss": 0.4705,
+      "num_input_tokens_seen": 86507520,
+      "step": 55
+    },
+    {
+      "epoch": 0.654014598540146,
+      "grad_norm": 0.05297677591443062,
+      "learning_rate": 1.303721077246784e-05,
+      "loss": 0.4965,
+      "num_input_tokens_seen": 88080384,
+      "step": 56
+    },
+    {
+      "epoch": 0.6656934306569343,
+      "grad_norm": 0.05379556864500046,
+      "learning_rate": 1.223422017047733e-05,
+      "loss": 0.503,
+      "num_input_tokens_seen": 89653248,
+      "step": 57
+    },
+    {
+      "epoch": 0.6773722627737226,
+      "grad_norm": 0.058262865990400314,
+      "learning_rate": 1.1448666088188764e-05,
+      "loss": 0.4921,
+      "num_input_tokens_seen": 91226112,
+      "step": 58
+    },
+    {
+      "epoch": 0.689051094890511,
+      "grad_norm": 0.05684163048863411,
+      "learning_rate": 1.068162149798737e-05,
+      "loss": 0.5042,
+      "num_input_tokens_seen": 92798976,
+      "step": 59
+    },
+    {
+      "epoch": 0.7007299270072993,
+      "grad_norm": 0.053847264498472214,
+      "learning_rate": 9.934134090518593e-06,
+      "loss": 0.5145,
+      "num_input_tokens_seen": 94371840,
+      "step": 60
+    },
+    {
+      "epoch": 0.7124087591240876,
+      "grad_norm": 0.05480194464325905,
+      "learning_rate": 9.207224843668732e-06,
+      "loss": 0.4897,
+      "num_input_tokens_seen": 95944704,
+      "step": 61
+    },
+    {
+      "epoch": 0.724087591240876,
+      "grad_norm": 0.05290277674794197,
+      "learning_rate": 8.50188662803194e-06,
+      "loss": 0.5033,
+      "num_input_tokens_seen": 97517568,
+      "step": 62
+    },
+    {
+      "epoch": 0.7357664233576642,
+      "grad_norm": 0.05715763568878174,
+      "learning_rate": 7.819082850768434e-06,
+      "loss": 0.473,
+      "num_input_tokens_seen": 99090432,
+      "step": 63
+    },
+    {
+      "epoch": 0.7474452554744525,
+      "grad_norm": 0.060164712369441986,
+      "learning_rate": 7.159746139706194e-06,
+      "loss": 0.5298,
+      "num_input_tokens_seen": 100663296,
+      "step": 64
+    },
+    {
+      "epoch": 0.7591240875912408,
+      "grad_norm": 0.058020610362291336,
+      "learning_rate": 6.524777069483526e-06,
+      "loss": 0.4685,
+      "num_input_tokens_seen": 102236160,
+      "step": 65
+    },
+    {
+      "epoch": 0.7708029197080292,
+      "grad_norm": 0.05399800464510918,
+      "learning_rate": 5.915042931472425e-06,
+      "loss": 0.4931,
+      "num_input_tokens_seen": 103809024,
+      "step": 66
+    },
+    {
+      "epoch": 0.7824817518248175,
+      "grad_norm": 0.05629091337323189,
+      "learning_rate": 5.33137654916292e-06,
+      "loss": 0.4957,
+      "num_input_tokens_seen": 105381888,
+      "step": 67
+    },
+    {
+      "epoch": 0.7941605839416058,
+      "grad_norm": 0.05569099634885788,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.4924,
+      "num_input_tokens_seen": 106954752,
+      "step": 68
+    },
+    {
+      "epoch": 0.8058394160583942,
+      "grad_norm": 0.05562946945428848,
+      "learning_rate": 4.245399229611238e-06,
+      "loss": 0.5041,
+      "num_input_tokens_seen": 108527616,
+      "step": 69
+    },
+    {
+      "epoch": 0.8175182481751825,
+      "grad_norm": 0.05801980197429657,
+      "learning_rate": 3.7445716067596503e-06,
+      "loss": 0.4948,
+      "num_input_tokens_seen": 110100480,
+      "step": 70
+    },
+    {
+      "epoch": 0.8291970802919708,
+      "grad_norm": 0.058106038719415665,
+      "learning_rate": 3.2727763423617913e-06,
+      "loss": 0.5085,
+      "num_input_tokens_seen": 111673344,
+      "step": 71
+    },
+    {
+      "epoch": 0.8408759124087591,
+      "grad_norm": 0.052898507565259933,
+      "learning_rate": 2.8306578519984527e-06,
+      "loss": 0.5152,
+      "num_input_tokens_seen": 113246208,
+      "step": 72
+    },
+    {
+      "epoch": 0.8525547445255475,
+      "grad_norm": 0.05265094339847565,
+      "learning_rate": 2.418820016346779e-06,
+      "loss": 0.4905,
+      "num_input_tokens_seen": 114819072,
+      "step": 73
+    },
+    {
+      "epoch": 0.8642335766423358,
+      "grad_norm": 0.054221879690885544,
+      "learning_rate": 2.0378253563519247e-06,
+      "loss": 0.5023,
+      "num_input_tokens_seen": 116391936,
+      "step": 74
+    },
+    {
+      "epoch": 0.8759124087591241,
+      "grad_norm": 0.0557856447994709,
+      "learning_rate": 1.6881942648911076e-06,
+      "loss": 0.4993,
+      "num_input_tokens_seen": 117964800,
+      "step": 75
+    },
+    {
+      "epoch": 0.8875912408759125,
+      "grad_norm": 0.05209067091345787,
+      "learning_rate": 1.3704042959795132e-06,
+      "loss": 0.481,
+      "num_input_tokens_seen": 119537664,
+      "step": 76
+    },
+    {
+      "epoch": 0.8992700729927007,
+      "grad_norm": 0.05373719707131386,
+      "learning_rate": 1.0848895124889818e-06,
+      "loss": 0.4806,
+      "num_input_tokens_seen": 121110528,
+      "step": 77
+    },
+    {
+      "epoch": 0.910948905109489,
+      "grad_norm": 0.055330030620098114,
+      "learning_rate": 8.320398932703144e-07,
+      "loss": 0.4915,
+      "num_input_tokens_seen": 122683392,
+      "step": 78
+    },
+    {
+      "epoch": 0.9226277372262773,
+      "grad_norm": 0.05640307813882828,
+      "learning_rate": 6.122008004890851e-07,
+      "loss": 0.4937,
+      "num_input_tokens_seen": 124256256,
+      "step": 79
+    },
+    {
+      "epoch": 0.9343065693430657,
+      "grad_norm": 0.05659601837396622,
+      "learning_rate": 4.256725079024554e-07,
+      "loss": 0.5152,
+      "num_input_tokens_seen": 125829120,
+      "step": 80
+    },
+    {
+      "epoch": 0.945985401459854,
+      "grad_norm": 0.05199190601706505,
+      "learning_rate": 2.7270979072135104e-07,
+      "loss": 0.4832,
+      "num_input_tokens_seen": 127401984,
+      "step": 81
+    },
+    {
+      "epoch": 0.9576642335766423,
+      "grad_norm": 0.05153407156467438,
+      "learning_rate": 1.5352157761815977e-07,
+      "loss": 0.4975,
+      "num_input_tokens_seen": 128974848,
+      "step": 82
+    },
+    {
+      "epoch": 0.9693430656934306,
+      "grad_norm": 0.05456986650824547,
+      "learning_rate": 6.827066535529946e-08,
+      "loss": 0.4887,
+      "num_input_tokens_seen": 130547712,
+      "step": 83
+    },
+    {
+      "epoch": 0.981021897810219,
+      "grad_norm": 0.057446081191301346,
+      "learning_rate": 1.7073496424427348e-08,
+      "loss": 0.4905,
+      "num_input_tokens_seen": 132120576,
+      "step": 84
+    },
+    {
+      "epoch": 0.9927007299270073,
+      "grad_norm": 0.05915559083223343,
+      "learning_rate": 0.0,
+      "loss": 0.5088,
+      "num_input_tokens_seen": 133693440,
+      "step": 85
+    },
+    {
+      "epoch": 0.9927007299270073,
+      "num_input_tokens_seen": 133693440,
+      "step": 85,
+      "total_flos": 5.206772811237949e+18,
+      "train_loss": 0.5589800634804893,
+      "train_runtime": 13057.0702,
+      "train_samples_per_second": 2.516,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 85,
+  "num_input_tokens_seen": 133693440,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.206772811237949e+18,
+  "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 sha256:9dfe9b9f31fd962583f6b7768605329d948c74f32677992d80a611eb33aaa2f5
+size 5688

training_args.yaml

@@ -0,0 +1,39 @@
+apollo_rank: 256
+apollo_scale: 1
+apollo_target: all
+apollo_update_interval: 200
+bf16: true
+cutoff_len: 4096
+dataset: codes_nlx_under8
+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_under8_nlx
+packing: true
+per_device_train_batch_size: 16
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+rope_scaling: llama3
+save_steps: 1000
+stage: sft
+template: deepseekcoder
+trust_remote_code: true
+use_apollo: true
+use_llama_pro: true
+warmup_steps: 0