Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- llama-factory
+- freeze
+- generated_from_trainer
+model-index:
+- name: qwen_under8_nsx
+  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. -->
+
+# qwen_under8_nsx
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the codes_nsx_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

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9943502824858758,
+    "num_input_tokens_seen": 69206016,
+    "total_flos": 2.9359762154685727e+18,
+    "train_loss": 0.8689587211067026,
+    "train_runtime": 6937.0161,
+    "train_samples_per_second": 2.448,
+    "train_steps_per_second": 0.006
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 1.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 32768,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "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: Qwen2.5-Coder-7B-Instruct
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: llama3
+top.template: qwen
+train.additional_target: ''
+train.apollo_rank: 256
+train.apollo_scale: 1
+train.apollo_target: all
+train.apollo_update_interval: 200
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 16
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 4096
+train.dataset:
+- codes_nsx_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-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b6f069918b07c064cbba8ae4f00f529aa9bbf84b7cdfcb7fc2694a40f6aa8ef
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ce54ed2faa3e2bae0852f9b859e4dd63c98b468b4db1f87c936a3c748854cb
+size 4932749648

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dfa76babe05a3ca6b3a27ffb1b6d837e5a2cf6d5985a49c938ebaa5450ac3ca
+size 4991480296

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c93799b124f07f5b80b2057eb05fbf1ced98323a3df545595904ec2757774006
+size 1361612328

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 16163464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

running_log.txt

@@ -0,0 +1,286 @@
+[INFO|2025-07-08 10:09:20] configuration_utils.py:696 >> loading configuration file config.json from cache at /home/kiho/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B-Instruct/snapshots/c03e6d358207e414f1eca0bb1891e29f1db0e242/config.json
+
+[INFO|2025-07-08 10:09:20] configuration_utils.py:768 >> Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-07-08 10:09:20] tokenization_utils_base.py:2034 >> loading file vocab.json from cache at /home/kiho/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B-Instruct/snapshots/c03e6d358207e414f1eca0bb1891e29f1db0e242/vocab.json
+
+[INFO|2025-07-08 10:09:20] tokenization_utils_base.py:2034 >> loading file merges.txt from cache at /home/kiho/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B-Instruct/snapshots/c03e6d358207e414f1eca0bb1891e29f1db0e242/merges.txt
+
+[INFO|2025-07-08 10:09:20] tokenization_utils_base.py:2034 >> loading file tokenizer.json from cache at /home/kiho/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B-Instruct/snapshots/c03e6d358207e414f1eca0bb1891e29f1db0e242/tokenizer.json
+
+[INFO|2025-07-08 10:09:20] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-07-08 10:09:20] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at None
+
+[INFO|2025-07-08 10:09:20] tokenization_utils_base.py:2034 >> loading file tokenizer_config.json from cache at /home/kiho/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B-Instruct/snapshots/c03e6d358207e414f1eca0bb1891e29f1db0e242/tokenizer_config.json
+
+[INFO|2025-07-08 10:09:20] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-07-08 10:09:20] 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|2025-07-08 10:09:20] logging.py:157 >> Add <|im_end|> to stop words.
+
+[INFO|2025-07-08 10:09:20] logging.py:157 >> Loading dataset Codes3_query_filtered_553474_mark_less_than_8.0.json...
+
+[INFO|2025-07-08 10:09:48] configuration_utils.py:696 >> loading configuration file config.json from cache at /home/kiho/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B-Instruct/snapshots/c03e6d358207e414f1eca0bb1891e29f1db0e242/config.json
+
+[INFO|2025-07-08 10:09:48] configuration_utils.py:768 >> Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[WARNING|2025-07-08 10:09:48] logging.py:162 >> Input length is smaller than max length. Consider increase input length.
+
+[INFO|2025-07-08 10:09:48] logging.py:157 >> Using llama3 scaling strategy and setting scaling factor to 1.0.
+
+[INFO|2025-07-08 10:09:48] logging.py:157 >> Using block diagonal attention for sequence packing without cross-attention.
+
+[INFO|2025-07-08 10:09:48] logging.py:157 >> Liger kernel has been applied to the model.
+
+[INFO|2025-07-08 10:09:48] modeling_utils.py:3904 >> loading weights file model.safetensors from cache at /home/kiho/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B-Instruct/snapshots/c03e6d358207e414f1eca0bb1891e29f1db0e242/model.safetensors.index.json
+
+[INFO|2025-07-08 10:09:48] modeling_utils.py:1582 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2025-07-08 10:09:48] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151645
+}
+
+
+[INFO|2025-07-08 10:09:53] modeling_utils.py:4888 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.
+
+
+[INFO|2025-07-08 10:09:53] modeling_utils.py:4896 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-Coder-7B-Instruct.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.
+
+[INFO|2025-07-08 10:09:53] configuration_utils.py:1095 >> loading configuration file generation_config.json from cache at /home/kiho/.cache/huggingface/hub/models--Qwen--Qwen2.5-Coder-7B-Instruct/snapshots/c03e6d358207e414f1eca0bb1891e29f1db0e242/generation_config.json
+
+[INFO|2025-07-08 10:09:53] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8
+}
+
+
+[INFO|2025-07-08 10:09:53] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2025-07-08 10:09:53] logging.py:157 >> Using torch SDPA for faster training and inference.
+
+[INFO|2025-07-08 10:09:53] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2025-07-08 10:09:53] logging.py:157 >> Fine-tuning method: Freeze
+
+[INFO|2025-07-08 10:09:53] logging.py:157 >> Set trainable layers: .13.,.27.
+
+[INFO|2025-07-08 10:09:53] logging.py:157 >> trainable params: 466,115,584 || all params: 7,615,616,512 || trainable%: 6.1205
+
+[INFO|2025-07-08 10:09:53] trainer.py:741 >> Using auto half precision backend
+
+[INFO|2025-07-08 10:09:53] logging.py:157 >> Found linear modules: down_proj,k_proj,o_proj,up_proj,q_proj,v_proj,gate_proj
+
+[INFO|2025-07-08 10:09:53] 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|2025-07-08 10:09:54] trainer.py:2369 >> ***** Running training *****
+
+[INFO|2025-07-08 10:09:54] trainer.py:2370 >>   Num examples = 16,981
+
+[INFO|2025-07-08 10:09:54] trainer.py:2371 >>   Num Epochs = 1
+
+[INFO|2025-07-08 10:09:54] trainer.py:2372 >>   Instantaneous batch size per device = 16
+
+[INFO|2025-07-08 10:09:54] trainer.py:2375 >>   Total train batch size (w. parallel, distributed & accumulation) = 384
+
+[INFO|2025-07-08 10:09:54] trainer.py:2376 >>   Gradient Accumulation steps = 8
+
+[INFO|2025-07-08 10:09:54] trainer.py:2377 >>   Total optimization steps = 44
+
+[INFO|2025-07-08 10:09:54] trainer.py:2378 >>   Number of trainable parameters = 466,115,584
+
+[INFO|2025-07-08 10:12:41] logging.py:157 >> {'loss': 1.1536, 'learning_rate': 4.9936e-05, 'epoch': 0.02, 'throughput': 9464.56}
+
+[INFO|2025-07-08 10:15:17] logging.py:157 >> {'loss': 1.1215, 'learning_rate': 4.9746e-05, 'epoch': 0.05, 'throughput': 9756.96}
+
+[INFO|2025-07-08 10:17:54] logging.py:157 >> {'loss': 1.0725, 'learning_rate': 4.9429e-05, 'epoch': 0.07, 'throughput': 9852.97}
+
+[INFO|2025-07-08 10:20:32] logging.py:157 >> {'loss': 1.0047, 'learning_rate': 4.8987e-05, 'epoch': 0.09, 'throughput': 9867.27}
+
+[INFO|2025-07-08 10:23:09] logging.py:157 >> {'loss': 0.9418, 'learning_rate': 4.8424e-05, 'epoch': 0.11, 'throughput': 9897.39}
+
+[INFO|2025-07-08 10:25:47] logging.py:157 >> {'loss': 0.9885, 'learning_rate': 4.7741e-05, 'epoch': 0.14, 'throughput': 9908.82}
+
+[INFO|2025-07-08 10:28:25] logging.py:157 >> {'loss': 0.9354, 'learning_rate': 4.6942e-05, 'epoch': 0.16, 'throughput': 9918.69}
+
+[INFO|2025-07-08 10:31:01] logging.py:157 >> {'loss': 0.8844, 'learning_rate': 4.6031e-05, 'epoch': 0.18, 'throughput': 9935.83}
+
+[INFO|2025-07-08 10:33:39] logging.py:157 >> {'loss': 0.9354, 'learning_rate': 4.5014e-05, 'epoch': 0.20, 'throughput': 9938.21}
+
+[INFO|2025-07-08 10:36:15] logging.py:157 >> {'loss': 0.9176, 'learning_rate': 4.3894e-05, 'epoch': 0.23, 'throughput': 9950.66}
+
+[INFO|2025-07-08 10:38:59] logging.py:157 >> {'loss': 0.8972, 'learning_rate': 4.2678e-05, 'epoch': 0.25, 'throughput': 9919.94}
+
+[INFO|2025-07-08 10:41:37] logging.py:157 >> {'loss': 0.8788, 'learning_rate': 4.1372e-05, 'epoch': 0.27, 'throughput': 9921.44}
+
+[INFO|2025-07-08 10:44:13] logging.py:157 >> {'loss': 0.8609, 'learning_rate': 3.9982e-05, 'epoch': 0.29, 'throughput': 9931.94}
+
+[INFO|2025-07-08 10:46:50] logging.py:157 >> {'loss': 0.8719, 'learning_rate': 3.8516e-05, 'epoch': 0.32, 'throughput': 9940.78}
+
+[INFO|2025-07-08 10:49:26] logging.py:157 >> {'loss': 0.8662, 'learning_rate': 3.6981e-05, 'epoch': 0.34, 'throughput': 9948.22}
+
+[INFO|2025-07-08 10:52:04] logging.py:157 >> {'loss': 0.8663, 'learning_rate': 3.5385e-05, 'epoch': 0.36, 'throughput': 9950.11}
+
+[INFO|2025-07-08 10:54:41] logging.py:157 >> {'loss': 0.8709, 'learning_rate': 3.3737e-05, 'epoch': 0.38, 'throughput': 9955.21}
+
+[INFO|2025-07-08 10:57:21] logging.py:157 >> {'loss': 0.8467, 'learning_rate': 3.2043e-05, 'epoch': 0.41, 'throughput': 9948.37}
+
+[INFO|2025-07-08 10:59:58] logging.py:157 >> {'loss': 0.8586, 'learning_rate': 3.0314e-05, 'epoch': 0.43, 'throughput': 9951.73}
+
+[INFO|2025-07-08 11:02:34] logging.py:157 >> {'loss': 0.8146, 'learning_rate': 2.8558e-05, 'epoch': 0.45, 'throughput': 9958.64}
+
+[INFO|2025-07-08 11:05:10] logging.py:157 >> {'loss': 0.8188, 'learning_rate': 2.6783e-05, 'epoch': 0.47, 'throughput': 9963.10}
+
+[INFO|2025-07-08 11:07:46] logging.py:157 >> {'loss': 0.8239, 'learning_rate': 2.5000e-05, 'epoch': 0.50, 'throughput': 9968.54}
+
+[INFO|2025-07-08 11:10:26] logging.py:157 >> {'loss': 0.8436, 'learning_rate': 2.3217e-05, 'epoch': 0.52, 'throughput': 9962.09}
+
+[INFO|2025-07-08 11:13:02] logging.py:157 >> {'loss': 0.8271, 'learning_rate': 2.1442e-05, 'epoch': 0.54, 'throughput': 9967.19}
+
+[INFO|2025-07-08 11:15:40] logging.py:157 >> {'loss': 0.8421, 'learning_rate': 1.9686e-05, 'epoch': 0.56, 'throughput': 9967.45}
+
+[INFO|2025-07-08 11:18:16] logging.py:157 >> {'loss': 0.8239, 'learning_rate': 1.7957e-05, 'epoch': 0.59, 'throughput': 9971.21}
+
+[INFO|2025-07-08 11:20:52] logging.py:157 >> {'loss': 0.8005, 'learning_rate': 1.6263e-05, 'epoch': 0.61, 'throughput': 9974.62}
+
+[INFO|2025-07-08 11:23:29] logging.py:157 >> {'loss': 0.8360, 'learning_rate': 1.4615e-05, 'epoch': 0.63, 'throughput': 9976.73}
+
+[INFO|2025-07-08 11:26:06] logging.py:157 >> {'loss': 0.8231, 'learning_rate': 1.3019e-05, 'epoch': 0.66, 'throughput': 9977.25}
+
+[INFO|2025-07-08 11:28:43] logging.py:157 >> {'loss': 0.7963, 'learning_rate': 1.1484e-05, 'epoch': 0.68, 'throughput': 9978.92}
+
+[INFO|2025-07-08 11:31:19] logging.py:157 >> {'loss': 0.8199, 'learning_rate': 1.0018e-05, 'epoch': 0.70, 'throughput': 9982.42}
+
+[INFO|2025-07-08 11:33:56] logging.py:157 >> {'loss': 0.8411, 'learning_rate': 8.6285e-06, 'epoch': 0.72, 'throughput': 9984.05}
+
+[INFO|2025-07-08 11:36:34] logging.py:157 >> {'loss': 0.8219, 'learning_rate': 7.3223e-06, 'epoch': 0.75, 'throughput': 9983.50}
+
+[INFO|2025-07-08 11:39:09] logging.py:157 >> {'loss': 0.8057, 'learning_rate': 6.1063e-06, 'epoch': 0.77, 'throughput': 9987.10}
+
+[INFO|2025-07-08 11:41:46] logging.py:157 >> {'loss': 0.8147, 'learning_rate': 4.9865e-06, 'epoch': 0.79, 'throughput': 9988.07}
+
+[INFO|2025-07-08 11:44:22] logging.py:157 >> {'loss': 0.8138, 'learning_rate': 3.9687e-06, 'epoch': 0.81, 'throughput': 9990.56}
+
+[INFO|2025-07-08 11:46:59] logging.py:157 >> {'loss': 0.8135, 'learning_rate': 3.0580e-06, 'epoch': 0.84, 'throughput': 9991.17}
+
+[INFO|2025-07-08 11:49:35] logging.py:157 >> {'loss': 0.8158, 'learning_rate': 2.2592e-06, 'epoch': 0.86, 'throughput': 9993.85}
+
+[INFO|2025-07-08 11:52:14] logging.py:157 >> {'loss': 0.8087, 'learning_rate': 1.5763e-06, 'epoch': 0.88, 'throughput': 9991.63}
+
+[INFO|2025-07-08 11:54:51] logging.py:157 >> {'loss': 0.8183, 'learning_rate': 1.0127e-06, 'epoch': 0.90, 'throughput': 9993.15}
+
+[INFO|2025-07-08 11:57:25] logging.py:157 >> {'loss': 0.8280, 'learning_rate': 5.7133e-07, 'epoch': 0.93, 'throughput': 9997.39}
+
+[INFO|2025-07-08 11:59:59] logging.py:157 >> {'loss': 0.8196, 'learning_rate': 2.5446e-07, 'epoch': 0.95, 'throughput': 10002.91}
+
+[INFO|2025-07-08 12:02:33] logging.py:157 >> {'loss': 0.7919, 'learning_rate': 6.3697e-08, 'epoch': 0.97, 'throughput': 10008.14}
+
+[INFO|2025-07-08 12:05:07] logging.py:157 >> {'loss': 0.7989, 'learning_rate': 0.0000e+00, 'epoch': 0.99, 'throughput': 10012.24}
+
+[INFO|2025-07-08 12:05:07] trainer.py:3910 >> Saving model checkpoint to saves/Qwen2.5-Coder-7B-Instruct/freeze/qwen_under8_nsx/checkpoint-44
+
+[INFO|2025-07-08 12:05:07] configuration_utils.py:420 >> Configuration saved in saves/Qwen2.5-Coder-7B-Instruct/freeze/qwen_under8_nsx/checkpoint-44/config.json
+
+[INFO|2025-07-08 12:05:07] configuration_utils.py:909 >> Configuration saved in saves/Qwen2.5-Coder-7B-Instruct/freeze/qwen_under8_nsx/checkpoint-44/generation_config.json
+
+[INFO|2025-07-08 12:05:30] modeling_utils.py:2996 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at saves/Qwen2.5-Coder-7B-Instruct/freeze/qwen_under8_nsx/checkpoint-44/model.safetensors.index.json.
+
+[INFO|2025-07-08 12:05:30] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves/Qwen2.5-Coder-7B-Instruct/freeze/qwen_under8_nsx/checkpoint-44/tokenizer_config.json
+
+[INFO|2025-07-08 12:05:30] tokenization_utils_base.py:2500 >> Special tokens file saved in saves/Qwen2.5-Coder-7B-Instruct/freeze/qwen_under8_nsx/checkpoint-44/special_tokens_map.json
+
+[INFO|2025-07-08 12:05:31] trainer.py:2643 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-07-08 12:05:31] trainer.py:3910 >> Saving model checkpoint to saves/Qwen2.5-Coder-7B-Instruct/freeze/qwen_under8_nsx
+
+[INFO|2025-07-08 12:05:31] configuration_utils.py:420 >> Configuration saved in saves/Qwen2.5-Coder-7B-Instruct/freeze/qwen_under8_nsx/config.json
+
+[INFO|2025-07-08 12:05:31] configuration_utils.py:909 >> Configuration saved in saves/Qwen2.5-Coder-7B-Instruct/freeze/qwen_under8_nsx/generation_config.json
+
+[INFO|2025-07-08 12:05:54] modeling_utils.py:2996 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at saves/Qwen2.5-Coder-7B-Instruct/freeze/qwen_under8_nsx/model.safetensors.index.json.
+
+[INFO|2025-07-08 12:05:54] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves/Qwen2.5-Coder-7B-Instruct/freeze/qwen_under8_nsx/tokenizer_config.json
+
+[INFO|2025-07-08 12:05:54] tokenization_utils_base.py:2500 >> Special tokens file saved in saves/Qwen2.5-Coder-7B-Instruct/freeze/qwen_under8_nsx/special_tokens_map.json
+
+[WARNING|2025-07-08 12:05:55] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2025-07-08 12:05:55] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2025-07-08 12:05:55] 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 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9943502824858758,
+    "num_input_tokens_seen": 69206016,
+    "total_flos": 2.9359762154685727e+18,
+    "train_loss": 0.8689587211067026,
+    "train_runtime": 6937.0161,
+    "train_samples_per_second": 2.448,
+    "train_steps_per_second": 0.006
+}

trainer_log.jsonl

@@ -0,0 +1,45 @@
+{"current_steps": 1, "total_steps": 44, "loss": 1.1536, "lr": 4.993630286525634e-05, "epoch": 0.022598870056497175, "percentage": 2.27, "elapsed_time": "0:02:46", "remaining_time": "1:59:05", "throughput": 9464.56, "total_tokens": 1572864}
+{"current_steps": 2, "total_steps": 44, "loss": 1.1215, "lr": 4.9745536047023324e-05, "epoch": 0.04519774011299435, "percentage": 4.55, "elapsed_time": "0:05:22", "remaining_time": "1:52:50", "throughput": 9756.96, "total_tokens": 3145728}
+{"current_steps": 3, "total_steps": 44, "loss": 1.0725, "lr": 4.942867164927899e-05, "epoch": 0.06779661016949153, "percentage": 6.82, "elapsed_time": "0:07:58", "remaining_time": "1:49:04", "throughput": 9852.97, "total_tokens": 4718592}
+{"current_steps": 4, "total_steps": 44, "loss": 1.0047, "lr": 4.898732434036244e-05, "epoch": 0.0903954802259887, "percentage": 9.09, "elapsed_time": "0:10:37", "remaining_time": "1:46:16", "throughput": 9867.27, "total_tokens": 6291456}
+{"current_steps": 5, "total_steps": 44, "loss": 0.9418, "lr": 4.842374312499405e-05, "epoch": 0.11299435028248588, "percentage": 11.36, "elapsed_time": "0:13:14", "remaining_time": "1:43:17", "throughput": 9897.39, "total_tokens": 7864320}
+{"current_steps": 6, "total_steps": 44, "loss": 0.9885, "lr": 4.774079988386296e-05, "epoch": 0.13559322033898305, "percentage": 13.64, "elapsed_time": "0:15:52", "remaining_time": "1:40:31", "throughput": 9908.82, "total_tokens": 9437184}
+{"current_steps": 7, "total_steps": 44, "loss": 0.9354, "lr": 4.6941974739181395e-05, "epoch": 0.15819209039548024, "percentage": 15.91, "elapsed_time": "0:18:30", "remaining_time": "1:37:47", "throughput": 9918.69, "total_tokens": 11010048}
+{"current_steps": 8, "total_steps": 44, "loss": 0.8844, "lr": 4.6031338320779534e-05, "epoch": 0.1807909604519774, "percentage": 18.18, "elapsed_time": "0:21:06", "remaining_time": "1:34:58", "throughput": 9935.83, "total_tokens": 12582912}
+{"current_steps": 9, "total_steps": 44, "loss": 0.9354, "lr": 4.5013531023109014e-05, "epoch": 0.2033898305084746, "percentage": 20.45, "elapsed_time": "0:23:44", "remaining_time": "1:32:19", "throughput": 9938.21, "total_tokens": 14155776}
+{"current_steps": 10, "total_steps": 44, "loss": 0.9176, "lr": 4.389373935885646e-05, "epoch": 0.22598870056497175, "percentage": 22.73, "elapsed_time": "0:26:20", "remaining_time": "1:29:34", "throughput": 9950.66, "total_tokens": 15728640}
+{"current_steps": 11, "total_steps": 44, "loss": 0.8972, "lr": 4.267766952966369e-05, "epoch": 0.24858757062146894, "percentage": 25.0, "elapsed_time": "0:29:04", "remaining_time": "1:27:12", "throughput": 9919.94, "total_tokens": 17301504}
+{"current_steps": 12, "total_steps": 44, "loss": 0.8788, "lr": 4.137151834863213e-05, "epoch": 0.2711864406779661, "percentage": 27.27, "elapsed_time": "0:31:42", "remaining_time": "1:24:33", "throughput": 9921.44, "total_tokens": 18874368}
+{"current_steps": 13, "total_steps": 44, "loss": 0.8609, "lr": 3.9981941662783674e-05, "epoch": 0.2937853107344633, "percentage": 29.55, "elapsed_time": "0:34:18", "remaining_time": "1:21:49", "throughput": 9931.94, "total_tokens": 20447232}
+{"current_steps": 14, "total_steps": 44, "loss": 0.8719, "lr": 3.851602043638994e-05, "epoch": 0.3163841807909605, "percentage": 31.82, "elapsed_time": "0:36:55", "remaining_time": "1:19:06", "throughput": 9940.78, "total_tokens": 22020096}
+{"current_steps": 15, "total_steps": 44, "loss": 0.8662, "lr": 3.6981224668001424e-05, "epoch": 0.3389830508474576, "percentage": 34.09, "elapsed_time": "0:39:31", "remaining_time": "1:16:25", "throughput": 9948.22, "total_tokens": 23592960}
+{"current_steps": 16, "total_steps": 44, "loss": 0.8663, "lr": 3.5385375325047166e-05, "epoch": 0.3615819209039548, "percentage": 36.36, "elapsed_time": "0:42:09", "remaining_time": "1:13:46", "throughput": 9950.11, "total_tokens": 25165824}
+{"current_steps": 17, "total_steps": 44, "loss": 0.8709, "lr": 3.3736604489977466e-05, "epoch": 0.384180790960452, "percentage": 38.64, "elapsed_time": "0:44:45", "remaining_time": "1:11:05", "throughput": 9955.21, "total_tokens": 26738688}
+{"current_steps": 18, "total_steps": 44, "loss": 0.8467, "lr": 3.2043313921035743e-05, "epoch": 0.4067796610169492, "percentage": 40.91, "elapsed_time": "0:47:25", "remaining_time": "1:08:30", "throughput": 9948.37, "total_tokens": 28311552}
+{"current_steps": 19, "total_steps": 44, "loss": 0.8586, "lr": 3.0314132238824415e-05, "epoch": 0.4293785310734463, "percentage": 43.18, "elapsed_time": "0:50:02", "remaining_time": "1:05:51", "throughput": 9951.73, "total_tokens": 29884416}
+{"current_steps": 20, "total_steps": 44, "loss": 0.8146, "lr": 2.8557870956832132e-05, "epoch": 0.4519774011299435, "percentage": 45.45, "elapsed_time": "0:52:38", "remaining_time": "1:03:10", "throughput": 9958.64, "total_tokens": 31457280}
+{"current_steps": 21, "total_steps": 44, "loss": 0.8188, "lr": 2.6783479579980807e-05, "epoch": 0.4745762711864407, "percentage": 47.73, "elapsed_time": "0:55:15", "remaining_time": "1:00:30", "throughput": 9963.1, "total_tokens": 33030144}
+{"current_steps": 22, "total_steps": 44, "loss": 0.8239, "lr": 2.5e-05, "epoch": 0.4971751412429379, "percentage": 50.0, "elapsed_time": "0:57:51", "remaining_time": "0:57:51", "throughput": 9968.54, "total_tokens": 34603008}
+{"current_steps": 23, "total_steps": 44, "loss": 0.8436, "lr": 2.3216520420019195e-05, "epoch": 0.519774011299435, "percentage": 52.27, "elapsed_time": "1:00:31", "remaining_time": "0:55:15", "throughput": 9962.09, "total_tokens": 36175872}
+{"current_steps": 24, "total_steps": 44, "loss": 0.8271, "lr": 2.1442129043167874e-05, "epoch": 0.5423728813559322, "percentage": 54.55, "elapsed_time": "1:03:07", "remaining_time": "0:52:36", "throughput": 9967.19, "total_tokens": 37748736}
+{"current_steps": 25, "total_steps": 44, "loss": 0.8421, "lr": 1.9685867761175584e-05, "epoch": 0.5649717514124294, "percentage": 56.82, "elapsed_time": "1:05:45", "remaining_time": "0:49:58", "throughput": 9967.45, "total_tokens": 39321600}
+{"current_steps": 26, "total_steps": 44, "loss": 0.8239, "lr": 1.795668607896426e-05, "epoch": 0.5875706214689266, "percentage": 59.09, "elapsed_time": "1:08:21", "remaining_time": "0:47:19", "throughput": 9971.21, "total_tokens": 40894464}
+{"current_steps": 27, "total_steps": 44, "loss": 0.8005, "lr": 1.6263395510022543e-05, "epoch": 0.6101694915254238, "percentage": 61.36, "elapsed_time": "1:10:57", "remaining_time": "0:44:40", "throughput": 9974.62, "total_tokens": 42467328}
+{"current_steps": 28, "total_steps": 44, "loss": 0.836, "lr": 1.4614624674952842e-05, "epoch": 0.632768361581921, "percentage": 63.64, "elapsed_time": "1:13:34", "remaining_time": "0:42:02", "throughput": 9976.73, "total_tokens": 44040192}
+{"current_steps": 29, "total_steps": 44, "loss": 0.8231, "lr": 1.301877533199859e-05, "epoch": 0.655367231638418, "percentage": 65.91, "elapsed_time": "1:16:11", "remaining_time": "0:39:24", "throughput": 9977.25, "total_tokens": 45613056}
+{"current_steps": 30, "total_steps": 44, "loss": 0.7963, "lr": 1.148397956361007e-05, "epoch": 0.6779661016949152, "percentage": 68.18, "elapsed_time": "1:18:48", "remaining_time": "0:36:46", "throughput": 9978.92, "total_tokens": 47185920}
+{"current_steps": 31, "total_steps": 44, "loss": 0.8199, "lr": 1.0018058337216327e-05, "epoch": 0.7005649717514124, "percentage": 70.45, "elapsed_time": "1:21:24", "remaining_time": "0:34:08", "throughput": 9982.42, "total_tokens": 48758784}
+{"current_steps": 32, "total_steps": 44, "loss": 0.8411, "lr": 8.628481651367876e-06, "epoch": 0.7231638418079096, "percentage": 72.73, "elapsed_time": "1:24:01", "remaining_time": "0:31:30", "throughput": 9984.05, "total_tokens": 50331648}
+{"current_steps": 33, "total_steps": 44, "loss": 0.8219, "lr": 7.3223304703363135e-06, "epoch": 0.7457627118644068, "percentage": 75.0, "elapsed_time": "1:26:39", "remaining_time": "0:28:53", "throughput": 9983.5, "total_tokens": 51904512}
+{"current_steps": 34, "total_steps": 44, "loss": 0.8057, "lr": 6.106260641143546e-06, "epoch": 0.768361581920904, "percentage": 77.27, "elapsed_time": "1:29:14", "remaining_time": "0:26:14", "throughput": 9987.1, "total_tokens": 53477376}
+{"current_steps": 35, "total_steps": 44, "loss": 0.8147, "lr": 4.986468976890993e-06, "epoch": 0.7909604519774012, "percentage": 79.55, "elapsed_time": "1:31:51", "remaining_time": "0:23:37", "throughput": 9988.07, "total_tokens": 55050240}
+{"current_steps": 36, "total_steps": 44, "loss": 0.8138, "lr": 3.968661679220468e-06, "epoch": 0.8135593220338984, "percentage": 81.82, "elapsed_time": "1:34:27", "remaining_time": "0:20:59", "throughput": 9990.56, "total_tokens": 56623104}
+{"current_steps": 37, "total_steps": 44, "loss": 0.8135, "lr": 3.058025260818609e-06, "epoch": 0.8361581920903954, "percentage": 84.09, "elapsed_time": "1:37:04", "remaining_time": "0:18:21", "throughput": 9991.17, "total_tokens": 58195968}
+{"current_steps": 38, "total_steps": 44, "loss": 0.8158, "lr": 2.2592001161370392e-06, "epoch": 0.8587570621468926, "percentage": 86.36, "elapsed_time": "1:39:40", "remaining_time": "0:15:44", "throughput": 9993.85, "total_tokens": 59768832}
+{"current_steps": 39, "total_steps": 44, "loss": 0.8087, "lr": 1.5762568750059604e-06, "epoch": 0.8813559322033898, "percentage": 88.64, "elapsed_time": "1:42:19", "remaining_time": "0:13:07", "throughput": 9991.63, "total_tokens": 61341696}
+{"current_steps": 40, "total_steps": 44, "loss": 0.8183, "lr": 1.0126756596375686e-06, "epoch": 0.903954802259887, "percentage": 90.91, "elapsed_time": "1:44:55", "remaining_time": "0:10:29", "throughput": 9993.15, "total_tokens": 62914560}
+{"current_steps": 41, "total_steps": 44, "loss": 0.828, "lr": 5.713283507210148e-07, "epoch": 0.9265536723163842, "percentage": 93.18, "elapsed_time": "1:47:30", "remaining_time": "0:07:51", "throughput": 9997.39, "total_tokens": 64487424}
+{"current_steps": 42, "total_steps": 44, "loss": 0.8196, "lr": 2.544639529766829e-07, "epoch": 0.9491525423728814, "percentage": 95.45, "elapsed_time": "1:50:04", "remaining_time": "0:05:14", "throughput": 10002.91, "total_tokens": 66060288}
+{"current_steps": 43, "total_steps": 44, "loss": 0.7919, "lr": 6.369713474366212e-08, "epoch": 0.9717514124293786, "percentage": 97.73, "elapsed_time": "1:52:37", "remaining_time": "0:02:37", "throughput": 10008.14, "total_tokens": 67633152}
+{"current_steps": 44, "total_steps": 44, "loss": 0.7989, "lr": 0.0, "epoch": 0.9943502824858758, "percentage": 100.0, "elapsed_time": "1:55:12", "remaining_time": "0:00:00", "throughput": 10012.24, "total_tokens": 69206016}
+{"current_steps": 44, "total_steps": 44, "epoch": 0.9943502824858758, "percentage": 100.0, "elapsed_time": "1:55:35", "remaining_time": "0:00:00", "throughput": 9977.96, "total_tokens": 69206016}

trainer_state.json

@@ -0,0 +1,395 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9943502824858758,
+  "eval_steps": 500,
+  "global_step": 44,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022598870056497175,
+      "grad_norm": 1.389330267906189,
+      "learning_rate": 4.993630286525634e-05,
+      "loss": 1.1536,
+      "num_input_tokens_seen": 1572864,
+      "step": 1
+    },
+    {
+      "epoch": 0.04519774011299435,
+      "grad_norm": 1.1050268411636353,
+      "learning_rate": 4.9745536047023324e-05,
+      "loss": 1.1215,
+      "num_input_tokens_seen": 3145728,
+      "step": 2
+    },
+    {
+      "epoch": 0.06779661016949153,
+      "grad_norm": 0.8083967566490173,
+      "learning_rate": 4.942867164927899e-05,
+      "loss": 1.0725,
+      "num_input_tokens_seen": 4718592,
+      "step": 3
+    },
+    {
+      "epoch": 0.0903954802259887,
+      "grad_norm": 0.5546463131904602,
+      "learning_rate": 4.898732434036244e-05,
+      "loss": 1.0047,
+      "num_input_tokens_seen": 6291456,
+      "step": 4
+    },
+    {
+      "epoch": 0.11299435028248588,
+      "grad_norm": 0.3899783194065094,
+      "learning_rate": 4.842374312499405e-05,
+      "loss": 0.9418,
+      "num_input_tokens_seen": 7864320,
+      "step": 5
+    },
+    {
+      "epoch": 0.13559322033898305,
+      "grad_norm": 0.36992546916007996,
+      "learning_rate": 4.774079988386296e-05,
+      "loss": 0.9885,
+      "num_input_tokens_seen": 9437184,
+      "step": 6
+    },
+    {
+      "epoch": 0.15819209039548024,
+      "grad_norm": 0.2956640124320984,
+      "learning_rate": 4.6941974739181395e-05,
+      "loss": 0.9354,
+      "num_input_tokens_seen": 11010048,
+      "step": 7
+    },
+    {
+      "epoch": 0.1807909604519774,
+      "grad_norm": 0.2466004639863968,
+      "learning_rate": 4.6031338320779534e-05,
+      "loss": 0.8844,
+      "num_input_tokens_seen": 12582912,
+      "step": 8
+    },
+    {
+      "epoch": 0.2033898305084746,
+      "grad_norm": 0.25577887892723083,
+      "learning_rate": 4.5013531023109014e-05,
+      "loss": 0.9354,
+      "num_input_tokens_seen": 14155776,
+      "step": 9
+    },
+    {
+      "epoch": 0.22598870056497175,
+      "grad_norm": 0.24122916162014008,
+      "learning_rate": 4.389373935885646e-05,
+      "loss": 0.9176,
+      "num_input_tokens_seen": 15728640,
+      "step": 10
+    },
+    {
+      "epoch": 0.24858757062146894,
+      "grad_norm": 0.20128831267356873,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.8972,
+      "num_input_tokens_seen": 17301504,
+      "step": 11
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 0.1990034431219101,
+      "learning_rate": 4.137151834863213e-05,
+      "loss": 0.8788,
+      "num_input_tokens_seen": 18874368,
+      "step": 12
+    },
+    {
+      "epoch": 0.2937853107344633,
+      "grad_norm": 0.18727582693099976,
+      "learning_rate": 3.9981941662783674e-05,
+      "loss": 0.8609,
+      "num_input_tokens_seen": 20447232,
+      "step": 13
+    },
+    {
+      "epoch": 0.3163841807909605,
+      "grad_norm": 0.183744877576828,
+      "learning_rate": 3.851602043638994e-05,
+      "loss": 0.8719,
+      "num_input_tokens_seen": 22020096,
+      "step": 14
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "grad_norm": 0.19635234773159027,
+      "learning_rate": 3.6981224668001424e-05,
+      "loss": 0.8662,
+      "num_input_tokens_seen": 23592960,
+      "step": 15
+    },
+    {
+      "epoch": 0.3615819209039548,
+      "grad_norm": 0.18947215378284454,
+      "learning_rate": 3.5385375325047166e-05,
+      "loss": 0.8663,
+      "num_input_tokens_seen": 25165824,
+      "step": 16
+    },
+    {
+      "epoch": 0.384180790960452,
+      "grad_norm": 0.18483321368694305,
+      "learning_rate": 3.3736604489977466e-05,
+      "loss": 0.8709,
+      "num_input_tokens_seen": 26738688,
+      "step": 17
+    },
+    {
+      "epoch": 0.4067796610169492,
+      "grad_norm": 0.16091912984848022,
+      "learning_rate": 3.2043313921035743e-05,
+      "loss": 0.8467,
+      "num_input_tokens_seen": 28311552,
+      "step": 18
+    },
+    {
+      "epoch": 0.4293785310734463,
+      "grad_norm": 0.15878094732761383,
+      "learning_rate": 3.0314132238824415e-05,
+      "loss": 0.8586,
+      "num_input_tokens_seen": 29884416,
+      "step": 19
+    },
+    {
+      "epoch": 0.4519774011299435,
+      "grad_norm": 0.16434833407402039,
+      "learning_rate": 2.8557870956832132e-05,
+      "loss": 0.8146,
+      "num_input_tokens_seen": 31457280,
+      "step": 20
+    },
+    {
+      "epoch": 0.4745762711864407,
+      "grad_norm": 0.1497550904750824,
+      "learning_rate": 2.6783479579980807e-05,
+      "loss": 0.8188,
+      "num_input_tokens_seen": 33030144,
+      "step": 21
+    },
+    {
+      "epoch": 0.4971751412429379,
+      "grad_norm": 0.1458846926689148,
+      "learning_rate": 2.5e-05,
+      "loss": 0.8239,
+      "num_input_tokens_seen": 34603008,
+      "step": 22
+    },
+    {
+      "epoch": 0.519774011299435,
+      "grad_norm": 0.13780465722084045,
+      "learning_rate": 2.3216520420019195e-05,
+      "loss": 0.8436,
+      "num_input_tokens_seen": 36175872,
+      "step": 23
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 0.1300361305475235,
+      "learning_rate": 2.1442129043167874e-05,
+      "loss": 0.8271,
+      "num_input_tokens_seen": 37748736,
+      "step": 24
+    },
+    {
+      "epoch": 0.5649717514124294,
+      "grad_norm": 0.13375268876552582,
+      "learning_rate": 1.9685867761175584e-05,
+      "loss": 0.8421,
+      "num_input_tokens_seen": 39321600,
+      "step": 25
+    },
+    {
+      "epoch": 0.5875706214689266,
+      "grad_norm": 0.12455960363149643,
+      "learning_rate": 1.795668607896426e-05,
+      "loss": 0.8239,
+      "num_input_tokens_seen": 40894464,
+      "step": 26
+    },
+    {
+      "epoch": 0.6101694915254238,
+      "grad_norm": 0.11861604452133179,
+      "learning_rate": 1.6263395510022543e-05,
+      "loss": 0.8005,
+      "num_input_tokens_seen": 42467328,
+      "step": 27
+    },
+    {
+      "epoch": 0.632768361581921,
+      "grad_norm": 0.1256602257490158,
+      "learning_rate": 1.4614624674952842e-05,
+      "loss": 0.836,
+      "num_input_tokens_seen": 44040192,
+      "step": 28
+    },
+    {
+      "epoch": 0.655367231638418,
+      "grad_norm": 0.12941180169582367,
+      "learning_rate": 1.301877533199859e-05,
+      "loss": 0.8231,
+      "num_input_tokens_seen": 45613056,
+      "step": 29
+    },
+    {
+      "epoch": 0.6779661016949152,
+      "grad_norm": 0.1277913600206375,
+      "learning_rate": 1.148397956361007e-05,
+      "loss": 0.7963,
+      "num_input_tokens_seen": 47185920,
+      "step": 30
+    },
+    {
+      "epoch": 0.7005649717514124,
+      "grad_norm": 0.12341845035552979,
+      "learning_rate": 1.0018058337216327e-05,
+      "loss": 0.8199,
+      "num_input_tokens_seen": 48758784,
+      "step": 31
+    },
+    {
+      "epoch": 0.7231638418079096,
+      "grad_norm": 0.12854008376598358,
+      "learning_rate": 8.628481651367876e-06,
+      "loss": 0.8411,
+      "num_input_tokens_seen": 50331648,
+      "step": 32
+    },
+    {
+      "epoch": 0.7457627118644068,
+      "grad_norm": 0.12963342666625977,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.8219,
+      "num_input_tokens_seen": 51904512,
+      "step": 33
+    },
+    {
+      "epoch": 0.768361581920904,
+      "grad_norm": 0.12576307356357574,
+      "learning_rate": 6.106260641143546e-06,
+      "loss": 0.8057,
+      "num_input_tokens_seen": 53477376,
+      "step": 34
+    },
+    {
+      "epoch": 0.7909604519774012,
+      "grad_norm": 0.12176015228033066,
+      "learning_rate": 4.986468976890993e-06,
+      "loss": 0.8147,
+      "num_input_tokens_seen": 55050240,
+      "step": 35
+    },
+    {
+      "epoch": 0.8135593220338984,
+      "grad_norm": 0.12038470059633255,
+      "learning_rate": 3.968661679220468e-06,
+      "loss": 0.8138,
+      "num_input_tokens_seen": 56623104,
+      "step": 36
+    },
+    {
+      "epoch": 0.8361581920903954,
+      "grad_norm": 0.12175320088863373,
+      "learning_rate": 3.058025260818609e-06,
+      "loss": 0.8135,
+      "num_input_tokens_seen": 58195968,
+      "step": 37
+    },
+    {
+      "epoch": 0.8587570621468926,
+      "grad_norm": 0.11917068809270859,
+      "learning_rate": 2.2592001161370392e-06,
+      "loss": 0.8158,
+      "num_input_tokens_seen": 59768832,
+      "step": 38
+    },
+    {
+      "epoch": 0.8813559322033898,
+      "grad_norm": 0.11807029694318771,
+      "learning_rate": 1.5762568750059604e-06,
+      "loss": 0.8087,
+      "num_input_tokens_seen": 61341696,
+      "step": 39
+    },
+    {
+      "epoch": 0.903954802259887,
+      "grad_norm": 0.12152665853500366,
+      "learning_rate": 1.0126756596375686e-06,
+      "loss": 0.8183,
+      "num_input_tokens_seen": 62914560,
+      "step": 40
+    },
+    {
+      "epoch": 0.9265536723163842,
+      "grad_norm": 0.1269780844449997,
+      "learning_rate": 5.713283507210148e-07,
+      "loss": 0.828,
+      "num_input_tokens_seen": 64487424,
+      "step": 41
+    },
+    {
+      "epoch": 0.9491525423728814,
+      "grad_norm": 0.12324244529008865,
+      "learning_rate": 2.544639529766829e-07,
+      "loss": 0.8196,
+      "num_input_tokens_seen": 66060288,
+      "step": 42
+    },
+    {
+      "epoch": 0.9717514124293786,
+      "grad_norm": 0.11345086246728897,
+      "learning_rate": 6.369713474366212e-08,
+      "loss": 0.7919,
+      "num_input_tokens_seen": 67633152,
+      "step": 43
+    },
+    {
+      "epoch": 0.9943502824858758,
+      "grad_norm": 0.11618965864181519,
+      "learning_rate": 0.0,
+      "loss": 0.7989,
+      "num_input_tokens_seen": 69206016,
+      "step": 44
+    },
+    {
+      "epoch": 0.9943502824858758,
+      "num_input_tokens_seen": 69206016,
+      "step": 44,
+      "total_flos": 2.9359762154685727e+18,
+      "train_loss": 0.8689587211067026,
+      "train_runtime": 6937.0161,
+      "train_samples_per_second": 2.448,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 44,
+  "num_input_tokens_seen": 69206016,
+  "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": 2.9359762154685727e+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 sha256:9391951953814b84cc445237bb0ecc801d98372b8195ce4af9dc72a463a296db
+size 5624

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_nsx_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: Qwen/Qwen2.5-Coder-7B-Instruct
+neat_packing: true
+num_train_epochs: 1.0
+output_dir: saves/Qwen2.5-Coder-7B-Instruct/freeze/qwen_under8_nsx
+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: qwen
+trust_remote_code: true
+use_apollo: true
+use_llama_pro: true
+warmup_steps: 0