Upload folder using huggingface_hub

CREAM/outputs/sft/qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59/00args.json

@@ -0,0 +1,43 @@
+{
+    "epoch": 3,
+    "train_bsz": 1,
+    "eval_bsz": 2,
+    "lr": 5e-06,
+    "deepspeed": "./configs/ds_stage2.json",
+    "weight_decay": 0.01,
+    "save_eval_step_ratio": 0.999999,
+    "warmup_step_ratio": 0.1,
+    "grad_checkpointing": true,
+    "model": "qwen14b",
+    "common": {
+        "debug": false,
+        "device": "0,1,2,3,4,5,6,7",
+        "world_size": 8,
+        "rank": 0,
+        "master_address": "localhost",
+        "master_port": 41309,
+        "bf16": true,
+        "wandb_project_name": "CREAM",
+        "wandb_entity_name": "your_wandb_entity_name",
+        "run_name": "qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59",
+        "output_dir": "outputs/sft/qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59",
+        "load_args_path": null
+    },
+    "checkpoint": null,
+    "train_stage": "sft",
+    "dataset": {
+        "name": "qwen_fcs_sft",
+        "limit_size": null,
+        "max_length": 4096
+    },
+    "lora": {
+        "enable": false,
+        "alpha": 64,
+        "r": 32,
+        "dropout": 0.1
+    },
+    "dpo": {
+        "beta": 0.1,
+        "method": "original"
+    }
+}

CREAM/outputs/sft/qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59/checkpoint-5031/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
+}

CREAM/outputs/sft/qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59/checkpoint-5031/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

CREAM/outputs/sft/qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59/checkpoint-5031/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": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.2"
+}

CREAM/outputs/sft/qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59/checkpoint-5031/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1b6cb10a094f1771a0c3fe99513e019ffe17e6d3111aee0ad8e1c76be56684
+size 9941058640

CREAM/outputs/sft/qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59/checkpoint-5031/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec90605dc4b35a39fb78d16865321069dc0bf0bbd340ffb9d4751533c43aa456
+size 9909694792

CREAM/outputs/sft/qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59/checkpoint-5031/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568989e8c14e965ce96caf817393de0eec958f1831d8de82ba34635c5ecf8e84
+size 9689380560

CREAM/outputs/sft/qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59/checkpoint-5031/model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-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-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "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-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "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.bias": "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-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-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.bias": "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.bias": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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"
+  }
+}

CREAM/outputs/sft/qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59/checkpoint-5031/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
+  }
+}

CREAM/outputs/sft/qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59/checkpoint-5031/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

CREAM/outputs/sft/qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59/checkpoint-5031/trainer_state.json

@@ -0,0 +1,1139 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 5031,
+  "global_step": 5031,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 12.40677261352539,
+      "learning_rate": 9.920634920634921e-09,
+      "loss": 1.4787,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 9.015302658081055,
+      "learning_rate": 3.174603174603175e-07,
+      "loss": 1.7169,
+      "step": 32
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 21.63365364074707,
+      "learning_rate": 6.34920634920635e-07,
+      "loss": 1.4059,
+      "step": 64
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.4237022399902344,
+      "learning_rate": 9.523809523809525e-07,
+      "loss": 0.589,
+      "step": 96
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.1732497215270996,
+      "learning_rate": 1.26984126984127e-06,
+      "loss": 0.396,
+      "step": 128
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.178024172782898,
+      "learning_rate": 1.5873015873015873e-06,
+      "loss": 0.3483,
+      "step": 160
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.1424766778945923,
+      "learning_rate": 1.904761904761905e-06,
+      "loss": 0.3438,
+      "step": 192
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.9893178939819336,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.3315,
+      "step": 224
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.9395055174827576,
+      "learning_rate": 2.53968253968254e-06,
+      "loss": 0.3232,
+      "step": 256
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.9525547623634338,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.3059,
+      "step": 288
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.028775930404663,
+      "learning_rate": 3.1746031746031746e-06,
+      "loss": 0.2904,
+      "step": 320
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.9500004053115845,
+      "learning_rate": 3.492063492063492e-06,
+      "loss": 0.2866,
+      "step": 352
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.8986429572105408,
+      "learning_rate": 3.80952380952381e-06,
+      "loss": 0.2761,
+      "step": 384
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.8961861729621887,
+      "learning_rate": 4.126984126984127e-06,
+      "loss": 0.2771,
+      "step": 416
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.9038839936256409,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.294,
+      "step": 448
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.213515281677246,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.2824,
+      "step": 480
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.015212059020996,
+      "learning_rate": 4.999961472783987e-06,
+      "loss": 0.2762,
+      "step": 512
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8547834753990173,
+      "learning_rate": 4.9990368789722524e-06,
+      "loss": 0.2642,
+      "step": 544
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.1258083581924438,
+      "learning_rate": 4.996879936689864e-06,
+      "loss": 0.2691,
+      "step": 576
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.846869707107544,
+      "learning_rate": 4.993491709588402e-06,
+      "loss": 0.2583,
+      "step": 608
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.0405147075653076,
+      "learning_rate": 4.988873868502148e-06,
+      "loss": 0.264,
+      "step": 640
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.035718321800232,
+      "learning_rate": 4.983028690624146e-06,
+      "loss": 0.2544,
+      "step": 672
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.9199182987213135,
+      "learning_rate": 4.975959058383255e-06,
+      "loss": 0.262,
+      "step": 704
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.7455497980117798,
+      "learning_rate": 4.967668458022737e-06,
+      "loss": 0.256,
+      "step": 736
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.8655063509941101,
+      "learning_rate": 4.958160977881089e-06,
+      "loss": 0.2689,
+      "step": 768
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.9442307353019714,
+      "learning_rate": 4.947441306375959e-06,
+      "loss": 0.2605,
+      "step": 800
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.1555304527282715,
+      "learning_rate": 4.935514729692157e-06,
+      "loss": 0.2622,
+      "step": 832
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.1373685598373413,
+      "learning_rate": 4.922387129174876e-06,
+      "loss": 0.2684,
+      "step": 864
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.9241792559623718,
+      "learning_rate": 4.908064978429431e-06,
+      "loss": 0.2557,
+      "step": 896
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.0020250082015991,
+      "learning_rate": 4.892555340128932e-06,
+      "loss": 0.2628,
+      "step": 928
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.6900858283042908,
+      "learning_rate": 4.875865862531474e-06,
+      "loss": 0.2463,
+      "step": 960
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.920263409614563,
+      "learning_rate": 4.858004775708557e-06,
+      "loss": 0.2489,
+      "step": 992
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.9031669497489929,
+      "learning_rate": 4.838980887486594e-06,
+      "loss": 0.257,
+      "step": 1024
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.060744047164917,
+      "learning_rate": 4.818803579103514e-06,
+      "loss": 0.2517,
+      "step": 1056
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.8569713234901428,
+      "learning_rate": 4.7974828005826e-06,
+      "loss": 0.2581,
+      "step": 1088
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.8791570067405701,
+      "learning_rate": 4.775029065825837e-06,
+      "loss": 0.2584,
+      "step": 1120
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.9484251737594604,
+      "learning_rate": 4.751453447429199e-06,
+      "loss": 0.2482,
+      "step": 1152
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.9309147596359253,
+      "learning_rate": 4.72676757122243e-06,
+      "loss": 0.2465,
+      "step": 1184
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.9173675179481506,
+      "learning_rate": 4.700983610536002e-06,
+      "loss": 0.247,
+      "step": 1216
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.8396390676498413,
+      "learning_rate": 4.674114280198089e-06,
+      "loss": 0.2486,
+      "step": 1248
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.020650863647461,
+      "learning_rate": 4.646172830264516e-06,
+      "loss": 0.2443,
+      "step": 1280
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.7430787086486816,
+      "learning_rate": 4.617173039484759e-06,
+      "loss": 0.2387,
+      "step": 1312
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7960339188575745,
+      "learning_rate": 4.58712920850725e-06,
+      "loss": 0.2338,
+      "step": 1344
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.9160335063934326,
+      "learning_rate": 4.556056152827294e-06,
+      "loss": 0.2535,
+      "step": 1376
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.887413740158081,
+      "learning_rate": 4.523969195481128e-06,
+      "loss": 0.2509,
+      "step": 1408
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.9703641533851624,
+      "learning_rate": 4.49088415948967e-06,
+      "loss": 0.2504,
+      "step": 1440
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.0379596948623657,
+      "learning_rate": 4.4568173600557285e-06,
+      "loss": 0.2543,
+      "step": 1472
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.8071537017822266,
+      "learning_rate": 4.421785596518494e-06,
+      "loss": 0.2525,
+      "step": 1504
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.7581356763839722,
+      "learning_rate": 4.385806144069296e-06,
+      "loss": 0.2462,
+      "step": 1536
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.007126808166504,
+      "learning_rate": 4.348896745232692e-06,
+      "loss": 0.2464,
+      "step": 1568
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.8424175381660461,
+      "learning_rate": 4.311075601117116e-06,
+      "loss": 0.2429,
+      "step": 1600
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.9869457483291626,
+      "learning_rate": 4.27236136243937e-06,
+      "loss": 0.2427,
+      "step": 1632
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.7949284911155701,
+      "learning_rate": 4.232773120327411e-06,
+      "loss": 0.2415,
+      "step": 1664
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.8421123027801514,
+      "learning_rate": 4.1923303969059545e-06,
+      "loss": 0.2368,
+      "step": 1696
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.8088740110397339,
+      "learning_rate": 4.151053135669545e-06,
+      "loss": 0.2067,
+      "step": 1728
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.98466557264328,
+      "learning_rate": 4.108961691647828e-06,
+      "loss": 0.2265,
+      "step": 1760
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.844094455242157,
+      "learning_rate": 4.066076821367889e-06,
+      "loss": 0.2084,
+      "step": 1792
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.9722954630851746,
+      "learning_rate": 4.022419672618602e-06,
+      "loss": 0.2071,
+      "step": 1824
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 1.104019045829773,
+      "learning_rate": 3.978011774022031e-06,
+      "loss": 0.2064,
+      "step": 1856
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.8978186845779419,
+      "learning_rate": 3.9328750244170385e-06,
+      "loss": 0.2133,
+      "step": 1888
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.9305084347724915,
+      "learning_rate": 3.88703168206032e-06,
+      "loss": 0.2138,
+      "step": 1920
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.919377326965332,
+      "learning_rate": 3.840504353650209e-06,
+      "loss": 0.2153,
+      "step": 1952
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 1.0230509042739868,
+      "learning_rate": 3.7933159831786424e-06,
+      "loss": 0.2164,
+      "step": 1984
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.9514108300209045,
+      "learning_rate": 3.745489840616816e-06,
+      "loss": 0.218,
+      "step": 2016
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 1.2104793787002563,
+      "learning_rate": 3.6970495104400677e-06,
+      "loss": 0.2205,
+      "step": 2048
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.9711910486221313,
+      "learning_rate": 3.648018879997686e-06,
+      "loss": 0.2136,
+      "step": 2080
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.9941205382347107,
+      "learning_rate": 3.5984221277333527e-06,
+      "loss": 0.2087,
+      "step": 2112
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.9926620125770569,
+      "learning_rate": 3.5482837112620473e-06,
+      "loss": 0.2156,
+      "step": 2144
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.8572381734848022,
+      "learning_rate": 3.4976283553092744e-06,
+      "loss": 0.2101,
+      "step": 2176
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.978687047958374,
+      "learning_rate": 3.4464810395185776e-06,
+      "loss": 0.2091,
+      "step": 2208
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.8880535364151001,
+      "learning_rate": 3.3948669861333427e-06,
+      "loss": 0.2077,
+      "step": 2240
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.8167008757591248,
+      "learning_rate": 3.34281164755897e-06,
+      "loss": 0.2098,
+      "step": 2272
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 1.0977202653884888,
+      "learning_rate": 3.2903406938115463e-06,
+      "loss": 0.2167,
+      "step": 2304
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.8238468170166016,
+      "learning_rate": 3.2374799998592017e-06,
+      "loss": 0.2121,
+      "step": 2336
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.9441167712211609,
+      "learning_rate": 3.1842556328624097e-06,
+      "loss": 0.212,
+      "step": 2368
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.7314653396606445,
+      "learning_rate": 3.1306938393194993e-06,
+      "loss": 0.2067,
+      "step": 2400
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.9368041753768921,
+      "learning_rate": 3.076821032123739e-06,
+      "loss": 0.2116,
+      "step": 2432
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 1.0334727764129639,
+      "learning_rate": 3.022663777538362e-06,
+      "loss": 0.2118,
+      "step": 2464
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.9771775603294373,
+      "learning_rate": 2.968248782095965e-06,
+      "loss": 0.221,
+      "step": 2496
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.8788793087005615,
+      "learning_rate": 2.9136028794287248e-06,
+      "loss": 0.2117,
+      "step": 2528
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.798906683921814,
+      "learning_rate": 2.8587530170359563e-06,
+      "loss": 0.2091,
+      "step": 2560
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.8745276927947998,
+      "learning_rate": 2.8037262429955014e-06,
+      "loss": 0.2198,
+      "step": 2592
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.9228450059890747,
+      "learning_rate": 2.748549692625533e-06,
+      "loss": 0.2169,
+      "step": 2624
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.8804572820663452,
+      "learning_rate": 2.6932505751033284e-06,
+      "loss": 0.2116,
+      "step": 2656
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.7888917922973633,
+      "learning_rate": 2.6378561600476282e-06,
+      "loss": 0.2051,
+      "step": 2688
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.9026584625244141,
+      "learning_rate": 2.582393764071185e-06,
+      "loss": 0.205,
+      "step": 2720
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.7188759446144104,
+      "learning_rate": 2.5268907373101374e-06,
+      "loss": 0.2189,
+      "step": 2752
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.7976438999176025,
+      "learning_rate": 2.4713744499368618e-06,
+      "loss": 0.2153,
+      "step": 2784
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.9571369886398315,
+      "learning_rate": 2.415872278662926e-06,
+      "loss": 0.2187,
+      "step": 2816
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.9056606888771057,
+      "learning_rate": 2.3604115932388416e-06,
+      "loss": 0.216,
+      "step": 2848
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.9621754288673401,
+      "learning_rate": 2.305019742957222e-06,
+      "loss": 0.203,
+      "step": 2880
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.7014433145523071,
+      "learning_rate": 2.2497240431660573e-06,
+      "loss": 0.204,
+      "step": 2912
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.7371328473091125,
+      "learning_rate": 2.1945517617987016e-06,
+      "loss": 0.2042,
+      "step": 2944
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.8532301187515259,
+      "learning_rate": 2.1395301059272638e-06,
+      "loss": 0.2045,
+      "step": 2976
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.8193667531013489,
+      "learning_rate": 2.084686208345995e-06,
+      "loss": 0.2087,
+      "step": 3008
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.8078427910804749,
+      "learning_rate": 2.0300471141913156e-06,
+      "loss": 0.22,
+      "step": 3040
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.7181941866874695,
+      "learning_rate": 1.9756397676050603e-06,
+      "loss": 0.2017,
+      "step": 3072
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.8528056740760803,
+      "learning_rate": 1.9214909984475344e-06,
+      "loss": 0.206,
+      "step": 3104
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.8406049013137817,
+      "learning_rate": 1.8676275090669178e-06,
+      "loss": 0.2147,
+      "step": 3136
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.9283360242843628,
+      "learning_rate": 1.8140758611315562e-06,
+      "loss": 0.2045,
+      "step": 3168
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.7418608665466309,
+      "learning_rate": 1.7608624625316207e-06,
+      "loss": 0.2144,
+      "step": 3200
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.8113357424736023,
+      "learning_rate": 1.7080135543566034e-06,
+      "loss": 0.2157,
+      "step": 3232
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 1.008221983909607,
+      "learning_rate": 1.6555551979550621e-06,
+      "loss": 0.2159,
+      "step": 3264
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.8102164268493652,
+      "learning_rate": 1.603513262083009e-06,
+      "loss": 0.2176,
+      "step": 3296
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.764071524143219,
+      "learning_rate": 1.5519134101472627e-06,
+      "loss": 0.2046,
+      "step": 3328
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7320986390113831,
+      "learning_rate": 1.5007810875500719e-06,
+      "loss": 0.1989,
+      "step": 3360
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.7520262002944946,
+      "learning_rate": 1.4501415091412385e-06,
+      "loss": 0.1718,
+      "step": 3392
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.875102162361145,
+      "learning_rate": 1.4000196467839367e-06,
+      "loss": 0.1714,
+      "step": 3424
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 0.8077968955039978,
+      "learning_rate": 1.3504402170403509e-06,
+      "loss": 0.1641,
+      "step": 3456
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.8814091086387634,
+      "learning_rate": 1.3014276689832144e-06,
+      "loss": 0.161,
+      "step": 3488
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.7426602244377136,
+      "learning_rate": 1.253006172139258e-06,
+      "loss": 0.1713,
+      "step": 3520
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.957939088344574,
+      "learning_rate": 1.2051996045704989e-06,
+      "loss": 0.1608,
+      "step": 3552
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 0.8715665936470032,
+      "learning_rate": 1.1580315410992724e-06,
+      "loss": 0.1604,
+      "step": 3584
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.8994800448417664,
+      "learning_rate": 1.1115252416827916e-06,
+      "loss": 0.1624,
+      "step": 3616
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.7915408611297607,
+      "learning_rate": 1.0657036399429844e-06,
+      "loss": 0.1645,
+      "step": 3648
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 0.7938965559005737,
+      "learning_rate": 1.0205893318572454e-06,
+      "loss": 0.1629,
+      "step": 3680
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.8025040626525879,
+      "learning_rate": 9.76204564615699e-07,
+      "loss": 0.1647,
+      "step": 3712
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 0.8651378750801086,
+      "learning_rate": 9.325712256504544e-07,
+      "loss": 0.1738,
+      "step": 3744
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.9058112502098083,
+      "learning_rate": 8.897108318422751e-07,
+      "loss": 0.1645,
+      "step": 3776
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 1.1461430788040161,
+      "learning_rate": 8.476445189099666e-07,
+      "loss": 0.1648,
+      "step": 3808
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 0.7564007639884949,
+      "learning_rate": 8.063930309877368e-07,
+      "loss": 0.1661,
+      "step": 3840
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 0.8938281536102295,
+      "learning_rate": 7.659767103956531e-07,
+      "loss": 0.1569,
+      "step": 3872
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 0.9898664951324463,
+      "learning_rate": 7.264154876082489e-07,
+      "loss": 0.1665,
+      "step": 3904
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.9588989019393921,
+      "learning_rate": 6.877288714262176e-07,
+      "loss": 0.1712,
+      "step": 3936
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 0.8905143141746521,
+      "learning_rate": 6.499359393560526e-07,
+      "loss": 0.1668,
+      "step": 3968
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 0.8382207751274109,
+      "learning_rate": 6.130553282023682e-07,
+      "loss": 0.1638,
+      "step": 4000
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.8408306241035461,
+      "learning_rate": 5.771052248775455e-07,
+      "loss": 0.1707,
+      "step": 4032
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.8187743425369263,
+      "learning_rate": 5.421033574332285e-07,
+      "loss": 0.1654,
+      "step": 4064
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.7513293027877808,
+      "learning_rate": 5.080669863181037e-07,
+      "loss": 0.1632,
+      "step": 4096
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.8408425450325012,
+      "learning_rate": 4.750128958662645e-07,
+      "loss": 0.1616,
+      "step": 4128
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.7690516114234924,
+      "learning_rate": 4.4295738602036673e-07,
+      "loss": 0.1619,
+      "step": 4160
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.934533417224884,
+      "learning_rate": 4.1191626429364086e-07,
+      "loss": 0.1617,
+      "step": 4192
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.8874086141586304,
+      "learning_rate": 3.81904837974752e-07,
+      "loss": 0.1594,
+      "step": 4224
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.85221928358078,
+      "learning_rate": 3.5293790657932094e-07,
+      "loss": 0.1628,
+      "step": 4256
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.9865897297859192,
+      "learning_rate": 3.2502975455184853e-07,
+      "loss": 0.1683,
+      "step": 4288
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 0.9407656192779541,
+      "learning_rate": 2.9819414422163797e-07,
+      "loss": 0.1683,
+      "step": 4320
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.8901329636573792,
+      "learning_rate": 2.72444309016186e-07,
+      "loss": 0.1622,
+      "step": 4352
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 0.9479309320449829,
+      "learning_rate": 2.477929469353918e-07,
+      "loss": 0.1647,
+      "step": 4384
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.8797332048416138,
+      "learning_rate": 2.242522142897971e-07,
+      "loss": 0.1649,
+      "step": 4416
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.8541396260261536,
+      "learning_rate": 2.018337197059575e-07,
+      "loss": 0.1655,
+      "step": 4448
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 1.0476915836334229,
+      "learning_rate": 1.805485184018832e-07,
+      "loss": 0.1581,
+      "step": 4480
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 0.8131563067436218,
+      "learning_rate": 1.6040710673539072e-07,
+      "loss": 0.1657,
+      "step": 4512
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 0.7551488280296326,
+      "learning_rate": 1.4141941702803473e-07,
+      "loss": 0.1683,
+      "step": 4544
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 0.8537065386772156,
+      "learning_rate": 1.235948126671957e-07,
+      "loss": 0.1647,
+      "step": 4576
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.87921142578125,
+      "learning_rate": 1.0694208348871304e-07,
+      "loss": 0.1631,
+      "step": 4608
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 0.8241755962371826,
+      "learning_rate": 9.14694414423617e-08,
+      "loss": 0.1659,
+      "step": 4640
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 0.9495503306388855,
+      "learning_rate": 7.718451654229686e-08,
+      "loss": 0.1638,
+      "step": 4672
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.9258249402046204,
+      "learning_rate": 6.40943531044727e-08,
+      "loss": 0.1669,
+      "step": 4704
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.8805275559425354,
+      "learning_rate": 5.220540627287968e-08,
+      "loss": 0.1685,
+      "step": 4736
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.9998162388801575,
+      "learning_rate": 4.152353883632665e-08,
+      "loss": 0.1627,
+      "step": 4768
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.8057408332824707,
+      "learning_rate": 3.2054018337324965e-08,
+      "loss": 0.1632,
+      "step": 4800
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.8954938054084778,
+      "learning_rate": 2.380151447451129e-08,
+      "loss": 0.1638,
+      "step": 4832
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 1.0400339365005493,
+      "learning_rate": 1.6770096799879343e-08,
+      "loss": 0.1658,
+      "step": 4864
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.8406778573989868,
+      "learning_rate": 1.0963232711966309e-08,
+      "loss": 0.1639,
+      "step": 4896
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 0.8733680248260498,
+      "learning_rate": 6.383785745975313e-09,
+      "loss": 0.1606,
+      "step": 4928
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.8817850947380066,
+      "learning_rate": 3.03401416168414e-09,
+      "loss": 0.1649,
+      "step": 4960
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 0.925607442855835,
+      "learning_rate": 9.155698298279892e-10,
+      "loss": 0.1609,
+      "step": 4992
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8764336705207825,
+      "learning_rate": 2.9497417516899384e-11,
+      "loss": 0.1662,
+      "step": 5024
+    }
+  ],
+  "logging_steps": 32,
+  "max_steps": 5031,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 5031,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

CREAM/outputs/sft/qwen_fcs_sft-lora_None-ckpt_None-25-10-05-18_51_59/checkpoint-5031/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ba8c557dea04b869a0ad42b91d7ca977e9e7045c6a37bca7700ab7371fac17f
+size 6584