Upload 22 files

.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

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
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "float32",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.50.0"
+}

llamaboard_config.yaml

@@ -0,0 +1,81 @@
+top.booster: auto
+top.checkpoint_path: null
+top.finetuning_type: full
+top.model_name: Qwen2.5-VL-7B-Instruct
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: qwen2_vl
+train.additional_target: ''
+train.apollo_rank: 16
+train.apollo_scale: 32
+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: 2
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 6000
+train.dataset:
+- critic_training_data
+- refined
+- omnisvg
+- svgen
+- llm4svg
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: '3'
+train.extra_args: '{"optim": "adamw_torch"}'
+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: 1e-4
+train.logging_steps: 21
+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: '1000000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+train.packing: false
+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: []
+train.save_steps: 5000
+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: false
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.use_swanlab: false
+train.val_size: 0.03
+train.warmup_steps: 0

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b7e68f40aa1b9e213ead8c4e71e042c8eee60b1ac43807f6e91a3bd7b01a347
+size 4968243304

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa1bfd6c37a412e18b75fbcaea4c4dc67784d5df119ffdeff77ddb12bef1312
+size 4991495816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14617c4434c1bbb749f552d889ae68aa7ae947a38e939938e3518d460f0e2b39
+size 4932751040

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eaac5aed72c32abcb07dcc0c2d2e68bda8eae4b653f6f1a557483b2090fde15
+size 1691924384

model.safetensors.index.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 16584333312
+  },
+  "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-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-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-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-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-00004-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-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-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-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-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",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

running_log.txt

@@ -0,0 +1,1037 @@
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file vocab.json
+
+[WARNING|2025-10-19 08:28:09] logging.py:329 >> Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.50, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
+
+[WARNING|2025-10-19 08:28:08] logging.py:329 >> Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.50, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file merges.txt
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file tokenizer.json
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file added_tokens.json
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file special_tokens_map.json
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file tokenizer_config.json
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file chat_template.jinja
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2323 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-10-19 08:28:08] image_processing_base.py:379 >> loading configuration file /gemini-3/space/thu/zhaozhiyuan/wfy-mptsnet/Qwen2.5-VL-7B-Instruct/preprocessor_config.json
+
+[INFO|2025-10-19 08:28:08] image_processing_base.py:379 >> loading configuration file /gemini-3/space/thu/zhaozhiyuan/wfy-mptsnet/Qwen2.5-VL-7B-Instruct/preprocessor_config.json
+
+[WARNING|2025-10-19 08:28:08] logging.py:329 >> Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.50, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
+
+[INFO|2025-10-19 08:28:08] image_processing_base.py:434 >> Image processor Qwen2VLImageProcessor {
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}
+
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file vocab.json
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file merges.txt
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file tokenizer.json
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file added_tokens.json
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file special_tokens_map.json
+
+[WARNING|2025-10-19 08:28:09] logging.py:329 >> Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.50, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
+
+[WARNING|2025-10-19 08:28:09] logging.py:329 >> Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.50, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
+
+[WARNING|2025-10-19 08:28:09] logging.py:329 >> Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.50, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
+
+[WARNING|2025-10-19 08:28:09] logging.py:329 >> Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.50, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
+
+[WARNING|2025-10-19 08:28:09] logging.py:329 >> Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.50, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file tokenizer_config.json
+
+[INFO|2025-10-19 08:28:08] tokenization_utils_base.py:2058 >> loading file chat_template.jinja
+
+[INFO|2025-10-19 08:28:09] tokenization_utils_base.py:2323 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-10-19 08:28:09] processing_utils.py:876 >> Processor Qwen2_5_VLProcessor:
+- image_processor: Qwen2VLImageProcessor {
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}
+
+- tokenizer: Qwen2TokenizerFast(name_or_path='/gemini-3/space/thu/zhaozhiyuan/wfy-mptsnet/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', '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|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
+	151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151657: AddedToken("<tool_call>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
+	151658: AddedToken("</tool_call>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
+	151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
+	151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
+	151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
+	151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
+	151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
+	151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
+}
+)
+
+{
+  "processor_class": "Qwen2_5_VLProcessor"
+}
+
+
+[INFO|2025-10-19 08:28:09] logging.py:157 >> Add <|im_end|> to stop words.
+
+[INFO|2025-10-19 08:28:09] logging.py:157 >> Loading dataset critic_training_data.json...
+
+[INFO|2025-10-19 08:28:33] logging.py:157 >> Loading dataset refined.json...
+
+[INFO|2025-10-19 08:28:57] logging.py:157 >> Loading dataset omnisvg.json...
+
+[INFO|2025-10-19 08:29:22] logging.py:157 >> Loading dataset svgen.json...
+
+[INFO|2025-10-19 08:29:51] logging.py:157 >> Loading dataset llm4svg.json...
+
+[INFO|2025-10-19 08:32:22] configuration_utils.py:697 >> loading configuration file /gemini-3/space/thu/zhaozhiyuan/wfy-mptsnet/Qwen2.5-VL-7B-Instruct/config.json
+
+[INFO|2025-10-19 08:32:22] configuration_utils.py:771 >> Model config Qwen2_5_VLConfig {
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-10-19 08:32:22] modeling_utils.py:1151 >> loading weights file /gemini-3/space/thu/zhaozhiyuan/wfy-mptsnet/Qwen2.5-VL-7B-Instruct/model.safetensors.index.json
+
+[INFO|2025-10-19 08:32:22] modeling_utils.py:3747 >> Detected DeepSpeed ZeRO-3: activating zero.init() for this model
+
+[INFO|2025-10-19 08:32:22] configuration_utils.py:1139 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151645
+}
+
+
+[INFO|2025-10-19 08:32:22] modeling_utils.py:2170 >> Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.float32.
+
+[INFO|2025-10-19 08:32:43] modeling_utils.py:4987 >> All model checkpoint weights were used when initializing Qwen2_5_VLForConditionalGeneration.
+
+
+[INFO|2025-10-19 08:32:43] modeling_utils.py:4995 >> All the weights of Qwen2_5_VLForConditionalGeneration were initialized from the model checkpoint at /gemini-3/space/thu/zhaozhiyuan/wfy-mptsnet/Qwen2.5-VL-7B-Instruct.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2_5_VLForConditionalGeneration for predictions without further training.
+
+[INFO|2025-10-19 08:32:43] configuration_utils.py:1092 >> loading configuration file /gemini-3/space/thu/zhaozhiyuan/wfy-mptsnet/Qwen2.5-VL-7B-Instruct/generation_config.json
+
+[INFO|2025-10-19 08:32:43] configuration_utils.py:1139 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06
+}
+
+
+[INFO|2025-10-19 08:32:43] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2025-10-19 08:32:43] logging.py:157 >> Using torch SDPA for faster training and inference.
+
+[INFO|2025-10-19 08:32:43] logging.py:157 >> ZeRO3 / FSDP detected, remaining trainable params in float32.
+
+[INFO|2025-10-19 08:32:43] logging.py:157 >> Fine-tuning method: Full
+
+[INFO|2025-10-19 08:32:43] logging.py:157 >> Set vision model not trainable: ['visual.patch_embed', 'visual.blocks'].
+
+[INFO|2025-10-19 08:32:43] logging.py:157 >> Set multi model projector not trainable: visual.merger.
+
+[INFO|2025-10-19 08:32:43] logging.py:157 >> trainable params: 7,615,616,512 || all params: 8,292,166,656 || trainable%: 91.8411
+
+[INFO|2025-10-19 08:32:43] trainer.py:748 >> Using auto half precision backend
+
+[INFO|2025-10-19 08:32:46] trainer.py:2409 >> ***** Running training *****
+
+[INFO|2025-10-19 08:32:46] trainer.py:2410 >>   Num examples = 296,675
+
+[INFO|2025-10-19 08:32:46] trainer.py:2411 >>   Num Epochs = 3
+
+[INFO|2025-10-19 08:32:46] trainer.py:2412 >>   Instantaneous batch size per device = 2
+
+[INFO|2025-10-19 08:32:46] trainer.py:2415 >>   Total train batch size (w. parallel, distributed & accumulation) = 128
+
+[INFO|2025-10-19 08:32:46] trainer.py:2416 >>   Gradient Accumulation steps = 8
+
+[INFO|2025-10-19 08:32:46] trainer.py:2417 >>   Total optimization steps = 6,951
+
+[INFO|2025-10-19 08:32:47] trainer.py:2418 >>   Number of trainable parameters = 7,615,616,512
+
+[INFO|2025-10-19 08:41:51] logging.py:157 >> {'loss': 1.4310, 'learning_rate': 9.9998e-05, 'epoch': 0.01, 'throughput': 9395.55}
+
+[INFO|2025-10-19 08:50:37] logging.py:157 >> {'loss': 0.5348, 'learning_rate': 9.9991e-05, 'epoch': 0.02, 'throughput': 9478.63}
+
+[INFO|2025-10-19 08:59:17] logging.py:157 >> {'loss': 0.4599, 'learning_rate': 9.9980e-05, 'epoch': 0.03, 'throughput': 9537.12}
+
+[INFO|2025-10-19 09:08:06] logging.py:157 >> {'loss': 0.4108, 'learning_rate': 9.9964e-05, 'epoch': 0.04, 'throughput': 9507.78}
+
+[INFO|2025-10-19 09:17:01] logging.py:157 >> {'loss': 0.3947, 'learning_rate': 9.9944e-05, 'epoch': 0.05, 'throughput': 9470.14}
+
+[INFO|2025-10-19 09:25:56] logging.py:157 >> {'loss': 0.3764, 'learning_rate': 9.9919e-05, 'epoch': 0.05, 'throughput': 9515.96}
+
+[INFO|2025-10-19 09:34:29] logging.py:157 >> {'loss': 0.3751, 'learning_rate': 9.9890e-05, 'epoch': 0.06, 'throughput': 9525.58}
+
+[INFO|2025-10-19 09:43:07] logging.py:157 >> {'loss': 0.3704, 'learning_rate': 9.9856e-05, 'epoch': 0.07, 'throughput': 9513.01}
+
+[INFO|2025-10-19 09:52:01] logging.py:157 >> {'loss': 0.3552, 'learning_rate': 9.9818e-05, 'epoch': 0.08, 'throughput': 9524.90}
+
+[INFO|2025-10-19 10:00:47] logging.py:157 >> {'loss': 0.3576, 'learning_rate': 9.9775e-05, 'epoch': 0.09, 'throughput': 9525.35}
+
+[INFO|2025-10-19 10:09:47] logging.py:157 >> {'loss': 0.3451, 'learning_rate': 9.9728e-05, 'epoch': 0.10, 'throughput': 9525.43}
+
+[INFO|2025-10-19 10:18:39] logging.py:157 >> {'loss': 0.3506, 'learning_rate': 9.9676e-05, 'epoch': 0.11, 'throughput': 9524.66}
+
+[INFO|2025-10-19 10:27:37] logging.py:157 >> {'loss': 0.3443, 'learning_rate': 9.9620e-05, 'epoch': 0.12, 'throughput': 9531.29}
+
+[INFO|2025-10-19 10:36:00] logging.py:157 >> {'loss': 0.3446, 'learning_rate': 9.9559e-05, 'epoch': 0.13, 'throughput': 9532.39}
+
+[INFO|2025-10-19 10:44:24] logging.py:157 >> {'loss': 0.3362, 'learning_rate': 9.9494e-05, 'epoch': 0.14, 'throughput': 9543.53}
+
+[INFO|2025-10-19 10:53:32] logging.py:157 >> {'loss': 0.3384, 'learning_rate': 9.9425e-05, 'epoch': 0.14, 'throughput': 9528.67}
+
+[INFO|2025-10-19 11:02:31] logging.py:157 >> {'loss': 0.3315, 'learning_rate': 9.9351e-05, 'epoch': 0.15, 'throughput': 9534.93}
+
+[INFO|2025-10-19 11:11:12] logging.py:157 >> {'loss': 0.3300, 'learning_rate': 9.9272e-05, 'epoch': 0.16, 'throughput': 9542.47}
+
+[INFO|2025-10-19 11:20:21] logging.py:157 >> {'loss': 0.3296, 'learning_rate': 9.9189e-05, 'epoch': 0.17, 'throughput': 9530.71}
+
+[INFO|2025-10-19 11:29:10] logging.py:157 >> {'loss': 0.3315, 'learning_rate': 9.9102e-05, 'epoch': 0.18, 'throughput': 9530.11}
+
+[INFO|2025-10-19 11:38:03] logging.py:157 >> {'loss': 0.3530, 'learning_rate': 9.9010e-05, 'epoch': 0.19, 'throughput': 9524.36}
+
+[INFO|2025-10-19 11:47:11] logging.py:157 >> {'loss': 0.3414, 'learning_rate': 9.8914e-05, 'epoch': 0.20, 'throughput': 9514.36}
+
+[INFO|2025-10-19 11:56:09] logging.py:157 >> {'loss': 0.3224, 'learning_rate': 9.8813e-05, 'epoch': 0.21, 'throughput': 9515.30}
+
+[INFO|2025-10-19 12:05:15] logging.py:157 >> {'loss': 0.3212, 'learning_rate': 9.8708e-05, 'epoch': 0.22, 'throughput': 9511.06}
+
+[INFO|2025-10-19 12:14:07] logging.py:157 >> {'loss': 0.3213, 'learning_rate': 9.8599e-05, 'epoch': 0.23, 'throughput': 9509.05}
+
+[INFO|2025-10-19 12:22:40] logging.py:157 >> {'loss': 0.3198, 'learning_rate': 9.8485e-05, 'epoch': 0.24, 'throughput': 9514.22}
+
+[INFO|2025-10-19 12:31:22] logging.py:157 >> {'loss': 0.3149, 'learning_rate': 9.8367e-05, 'epoch': 0.24, 'throughput': 9518.41}
+
+[INFO|2025-10-19 12:40:35] logging.py:157 >> {'loss': 0.3169, 'learning_rate': 9.8245e-05, 'epoch': 0.25, 'throughput': 9510.51}
+
+[INFO|2025-10-19 12:49:33] logging.py:157 >> {'loss': 0.3142, 'learning_rate': 9.8118e-05, 'epoch': 0.26, 'throughput': 9501.43}
+
+[INFO|2025-10-19 12:58:19] logging.py:157 >> {'loss': 0.3097, 'learning_rate': 9.7987e-05, 'epoch': 0.27, 'throughput': 9499.35}
+
+[INFO|2025-10-19 13:07:12] logging.py:157 >> {'loss': 0.3116, 'learning_rate': 9.7851e-05, 'epoch': 0.28, 'throughput': 9500.56}
+
+[INFO|2025-10-19 13:16:12] logging.py:157 >> {'loss': 0.3086, 'learning_rate': 9.7712e-05, 'epoch': 0.29, 'throughput': 9499.14}
+
+[INFO|2025-10-19 13:25:17] logging.py:157 >> {'loss': 0.3057, 'learning_rate': 9.7567e-05, 'epoch': 0.30, 'throughput': 9491.21}
+
+[INFO|2025-10-19 13:34:03] logging.py:157 >> {'loss': 0.3017, 'learning_rate': 9.7419e-05, 'epoch': 0.31, 'throughput': 9494.90}
+
+[INFO|2025-10-19 13:43:13] logging.py:157 >> {'loss': 0.3066, 'learning_rate': 9.7266e-05, 'epoch': 0.32, 'throughput': 9489.84}
+
+[INFO|2025-10-19 13:52:17] logging.py:157 >> {'loss': 0.2996, 'learning_rate': 9.7110e-05, 'epoch': 0.33, 'throughput': 9490.92}
+
+[INFO|2025-10-19 14:01:12] logging.py:157 >> {'loss': 0.2972, 'learning_rate': 9.6948e-05, 'epoch': 0.34, 'throughput': 9489.46}
+
+[INFO|2025-10-19 14:10:12] logging.py:157 >> {'loss': 0.2984, 'learning_rate': 9.6783e-05, 'epoch': 0.34, 'throughput': 9487.66}
+
+[INFO|2025-10-19 14:18:52] logging.py:157 >> {'loss': 0.2957, 'learning_rate': 9.6614e-05, 'epoch': 0.35, 'throughput': 9493.32}
+
+[INFO|2025-10-19 14:28:01] logging.py:157 >> {'loss': 0.2926, 'learning_rate': 9.6440e-05, 'epoch': 0.36, 'throughput': 9491.78}
+
+[INFO|2025-10-19 14:36:47] logging.py:157 >> {'loss': 0.2909, 'learning_rate': 9.6262e-05, 'epoch': 0.37, 'throughput': 9494.44}
+
+[INFO|2025-10-19 14:45:41] logging.py:157 >> {'loss': 0.2954, 'learning_rate': 9.6080e-05, 'epoch': 0.38, 'throughput': 9492.66}
+
+[INFO|2025-10-19 14:54:34] logging.py:157 >> {'loss': 0.2912, 'learning_rate': 9.5893e-05, 'epoch': 0.39, 'throughput': 9497.80}
+
+[INFO|2025-10-19 15:03:25] logging.py:157 >> {'loss': 0.2928, 'learning_rate': 9.5703e-05, 'epoch': 0.40, 'throughput': 9498.61}
+
+[INFO|2025-10-19 15:11:44] logging.py:157 >> {'loss': 0.2920, 'learning_rate': 9.5508e-05, 'epoch': 0.41, 'throughput': 9506.77}
+
+[INFO|2025-10-19 15:20:51] logging.py:157 >> {'loss': 0.2920, 'learning_rate': 9.5310e-05, 'epoch': 0.42, 'throughput': 9502.21}
+
+[INFO|2025-10-19 15:29:38] logging.py:157 >> {'loss': 0.2959, 'learning_rate': 9.5107e-05, 'epoch': 0.43, 'throughput': 9500.11}
+
+[INFO|2025-10-19 15:38:41] logging.py:157 >> {'loss': 0.2884, 'learning_rate': 9.4900e-05, 'epoch': 0.43, 'throughput': 9497.19}
+
+[INFO|2025-10-19 15:47:33] logging.py:157 >> {'loss': 0.2878, 'learning_rate': 9.4690e-05, 'epoch': 0.44, 'throughput': 9494.35}
+
+[INFO|2025-10-19 15:56:42] logging.py:157 >> {'loss': 0.2908, 'learning_rate': 9.4475e-05, 'epoch': 0.45, 'throughput': 9490.15}
+
+[INFO|2025-10-19 16:06:06] logging.py:157 >> {'loss': 0.2796, 'learning_rate': 9.4256e-05, 'epoch': 0.46, 'throughput': 9485.80}
+
+[INFO|2025-10-19 16:15:10] logging.py:157 >> {'loss': 0.2858, 'learning_rate': 9.4033e-05, 'epoch': 0.47, 'throughput': 9484.86}
+
+[INFO|2025-10-19 16:23:56] logging.py:157 >> {'loss': 0.2876, 'learning_rate': 9.3806e-05, 'epoch': 0.48, 'throughput': 9486.71}
+
+[INFO|2025-10-19 16:33:11] logging.py:157 >> {'loss': 0.2814, 'learning_rate': 9.3575e-05, 'epoch': 0.49, 'throughput': 9486.33}
+
+[INFO|2025-10-19 16:42:03] logging.py:157 >> {'loss': 0.2804, 'learning_rate': 9.3341e-05, 'epoch': 0.50, 'throughput': 9491.48}
+
+[INFO|2025-10-19 16:51:06] logging.py:157 >> {'loss': 0.2863, 'learning_rate': 9.3102e-05, 'epoch': 0.51, 'throughput': 9490.65}
+
+[INFO|2025-10-19 16:59:50] logging.py:157 >> {'loss': 0.2851, 'learning_rate': 9.2860e-05, 'epoch': 0.52, 'throughput': 9494.69}
+
+[INFO|2025-10-19 17:08:35] logging.py:157 >> {'loss': 0.2798, 'learning_rate': 9.2613e-05, 'epoch': 0.53, 'throughput': 9497.76}
+
+[INFO|2025-10-19 17:17:38] logging.py:157 >> {'loss': 0.2728, 'learning_rate': 9.2363e-05, 'epoch': 0.53, 'throughput': 9497.60}
+
+[INFO|2025-10-19 17:26:07] logging.py:157 >> {'loss': 0.2756, 'learning_rate': 9.2109e-05, 'epoch': 0.54, 'throughput': 9500.30}
+
+[INFO|2025-10-19 17:34:57] logging.py:157 >> {'loss': 0.2747, 'learning_rate': 9.1851e-05, 'epoch': 0.55, 'throughput': 9501.41}
+
+[INFO|2025-10-19 17:43:50] logging.py:157 >> {'loss': 0.2772, 'learning_rate': 9.1590e-05, 'epoch': 0.56, 'throughput': 9503.01}
+
+[INFO|2025-10-19 17:52:25] logging.py:157 >> {'loss': 0.2785, 'learning_rate': 9.1325e-05, 'epoch': 0.57, 'throughput': 9508.07}
+
+[INFO|2025-10-19 18:01:25] logging.py:157 >> {'loss': 0.2755, 'learning_rate': 9.1056e-05, 'epoch': 0.58, 'throughput': 9509.96}
+
+[INFO|2025-10-19 18:10:33] logging.py:157 >> {'loss': 0.2708, 'learning_rate': 9.0783e-05, 'epoch': 0.59, 'throughput': 9506.81}
+
+[INFO|2025-10-19 18:19:36] logging.py:157 >> {'loss': 0.2729, 'learning_rate': 9.0507e-05, 'epoch': 0.60, 'throughput': 9504.96}
+
+[INFO|2025-10-19 18:28:32] logging.py:157 >> {'loss': 0.2754, 'learning_rate': 9.0227e-05, 'epoch': 0.61, 'throughput': 9505.70}
+
+[INFO|2025-10-19 18:37:36] logging.py:157 >> {'loss': 0.2742, 'learning_rate': 8.9943e-05, 'epoch': 0.62, 'throughput': 9500.81}
+
+[INFO|2025-10-19 18:46:09] logging.py:157 >> {'loss': 0.2703, 'learning_rate': 8.9656e-05, 'epoch': 0.63, 'throughput': 9503.01}
+
+[INFO|2025-10-19 18:54:51] logging.py:157 >> {'loss': 0.2756, 'learning_rate': 8.9365e-05, 'epoch': 0.63, 'throughput': 9502.95}
+
+[INFO|2025-10-19 19:04:00] logging.py:157 >> {'loss': 0.2698, 'learning_rate': 8.9070e-05, 'epoch': 0.64, 'throughput': 9501.97}
+
+[INFO|2025-10-19 19:13:03] logging.py:157 >> {'loss': 0.2716, 'learning_rate': 8.8773e-05, 'epoch': 0.65, 'throughput': 9499.40}
+
+[INFO|2025-10-19 19:22:00] logging.py:157 >> {'loss': 0.2682, 'learning_rate': 8.8471e-05, 'epoch': 0.66, 'throughput': 9498.48}
+
+[INFO|2025-10-19 19:30:38] logging.py:157 >> {'loss': 0.2695, 'learning_rate': 8.8166e-05, 'epoch': 0.67, 'throughput': 9500.35}
+
+[INFO|2025-10-19 19:39:20] logging.py:157 >> {'loss': 0.2706, 'learning_rate': 8.7858e-05, 'epoch': 0.68, 'throughput': 9502.46}
+
+[INFO|2025-10-19 19:48:19] logging.py:157 >> {'loss': 0.2704, 'learning_rate': 8.7546e-05, 'epoch': 0.69, 'throughput': 9503.27}
+
+[INFO|2025-10-19 19:57:01] logging.py:157 >> {'loss': 0.2707, 'learning_rate': 8.7231e-05, 'epoch': 0.70, 'throughput': 9504.39}
+
+[INFO|2025-10-19 20:06:09] logging.py:157 >> {'loss': 0.2653, 'learning_rate': 8.6913e-05, 'epoch': 0.71, 'throughput': 9503.23}
+
+[INFO|2025-10-19 20:14:45] logging.py:157 >> {'loss': 0.2649, 'learning_rate': 8.6591e-05, 'epoch': 0.72, 'throughput': 9507.46}
+
+[INFO|2025-10-19 20:23:37] logging.py:157 >> {'loss': 0.2652, 'learning_rate': 8.6266e-05, 'epoch': 0.72, 'throughput': 9507.43}
+
+[INFO|2025-10-19 20:32:21] logging.py:157 >> {'loss': 0.2638, 'learning_rate': 8.5938e-05, 'epoch': 0.73, 'throughput': 9507.28}
+
+[INFO|2025-10-19 20:41:00] logging.py:157 >> {'loss': 0.2685, 'learning_rate': 8.5606e-05, 'epoch': 0.74, 'throughput': 9510.67}
+
+[INFO|2025-10-19 20:49:36] logging.py:157 >> {'loss': 0.2584, 'learning_rate': 8.5271e-05, 'epoch': 0.75, 'throughput': 9511.61}
+
+[INFO|2025-10-19 20:58:33] logging.py:157 >> {'loss': 0.2607, 'learning_rate': 8.4933e-05, 'epoch': 0.76, 'throughput': 9511.41}
+
+[INFO|2025-10-19 21:07:10] logging.py:157 >> {'loss': 0.2652, 'learning_rate': 8.4592e-05, 'epoch': 0.77, 'throughput': 9511.99}
+
+[INFO|2025-10-19 21:15:56] logging.py:157 >> {'loss': 0.2604, 'learning_rate': 8.4248e-05, 'epoch': 0.78, 'throughput': 9513.64}
+
+[INFO|2025-10-19 21:24:38] logging.py:157 >> {'loss': 0.2603, 'learning_rate': 8.3901e-05, 'epoch': 0.79, 'throughput': 9515.83}
+
+[INFO|2025-10-19 21:34:06] logging.py:157 >> {'loss': 0.2576, 'learning_rate': 8.3550e-05, 'epoch': 0.80, 'throughput': 9511.18}
+
+[INFO|2025-10-19 21:43:04] logging.py:157 >> {'loss': 0.2622, 'learning_rate': 8.3197e-05, 'epoch': 0.81, 'throughput': 9511.76}
+
+[INFO|2025-10-19 21:51:57] logging.py:157 >> {'loss': 0.2587, 'learning_rate': 8.2841e-05, 'epoch': 0.82, 'throughput': 9511.99}
+
+[INFO|2025-10-19 22:01:15] logging.py:157 >> {'loss': 0.2575, 'learning_rate': 8.2481e-05, 'epoch': 0.82, 'throughput': 9511.08}
+
+[INFO|2025-10-19 22:10:20] logging.py:157 >> {'loss': 0.2573, 'learning_rate': 8.2119e-05, 'epoch': 0.83, 'throughput': 9509.35}
+
+[INFO|2025-10-19 22:19:20] logging.py:157 >> {'loss': 0.2600, 'learning_rate': 8.1754e-05, 'epoch': 0.84, 'throughput': 9508.08}
+
+[INFO|2025-10-19 22:28:30] logging.py:157 >> {'loss': 0.2571, 'learning_rate': 8.1386e-05, 'epoch': 0.85, 'throughput': 9505.71}
+
+[INFO|2025-10-19 22:37:09] logging.py:157 >> {'loss': 0.2510, 'learning_rate': 8.1015e-05, 'epoch': 0.86, 'throughput': 9507.90}
+
+[INFO|2025-10-19 22:46:00] logging.py:157 >> {'loss': 0.2614, 'learning_rate': 8.0642e-05, 'epoch': 0.87, 'throughput': 9507.12}
+
+[INFO|2025-10-19 22:55:24] logging.py:157 >> {'loss': 0.2528, 'learning_rate': 8.0265e-05, 'epoch': 0.88, 'throughput': 9504.87}
+
+[INFO|2025-10-19 23:03:49] logging.py:157 >> {'loss': 0.2571, 'learning_rate': 7.9886e-05, 'epoch': 0.89, 'throughput': 9508.31}
+
+[INFO|2025-10-19 23:12:48] logging.py:157 >> {'loss': 0.2547, 'learning_rate': 7.9504e-05, 'epoch': 0.90, 'throughput': 9508.57}
+
+[INFO|2025-10-19 23:21:42] logging.py:157 >> {'loss': 0.2538, 'learning_rate': 7.9120e-05, 'epoch': 0.91, 'throughput': 9507.51}
+
+[INFO|2025-10-19 23:30:30] logging.py:157 >> {'loss': 0.2551, 'learning_rate': 7.8733e-05, 'epoch': 0.92, 'throughput': 9506.69}
+
+[INFO|2025-10-19 23:39:42] logging.py:157 >> {'loss': 0.2515, 'learning_rate': 7.8343e-05, 'epoch': 0.92, 'throughput': 9503.49}
+
+[INFO|2025-10-19 23:48:36] logging.py:157 >> {'loss': 0.2526, 'learning_rate': 7.7951e-05, 'epoch': 0.93, 'throughput': 9503.75}
+
+[INFO|2025-10-19 23:57:34] logging.py:157 >> {'loss': 0.2482, 'learning_rate': 7.7556e-05, 'epoch': 0.94, 'throughput': 9504.35}
+
+[INFO|2025-10-20 00:06:42] logging.py:157 >> {'loss': 0.2516, 'learning_rate': 7.7159e-05, 'epoch': 0.95, 'throughput': 9502.88}
+
+[INFO|2025-10-20 00:15:05] logging.py:157 >> {'loss': 0.2493, 'learning_rate': 7.6759e-05, 'epoch': 0.96, 'throughput': 9505.71}
+
+[INFO|2025-10-20 00:23:54] logging.py:157 >> {'loss': 0.2465, 'learning_rate': 7.6357e-05, 'epoch': 0.97, 'throughput': 9508.14}
+
+[INFO|2025-10-20 00:32:41] logging.py:157 >> {'loss': 0.2486, 'learning_rate': 7.5953e-05, 'epoch': 0.98, 'throughput': 9508.27}
+
+[INFO|2025-10-20 00:41:47] logging.py:157 >> {'loss': 0.2472, 'learning_rate': 7.5546e-05, 'epoch': 0.99, 'throughput': 9507.12}
+
+[INFO|2025-10-20 00:50:40] logging.py:157 >> {'loss': 0.2471, 'learning_rate': 7.5137e-05, 'epoch': 1.00, 'throughput': 9506.69}
+
+[INFO|2025-10-20 01:00:01] logging.py:157 >> {'loss': 0.2361, 'learning_rate': 7.4726e-05, 'epoch': 1.01, 'throughput': 9504.55}
+
+[INFO|2025-10-20 01:08:47] logging.py:157 >> {'loss': 0.2170, 'learning_rate': 7.4312e-05, 'epoch': 1.02, 'throughput': 9504.99}
+
+[INFO|2025-10-20 01:17:18] logging.py:157 >> {'loss': 0.2145, 'learning_rate': 7.3896e-05, 'epoch': 1.02, 'throughput': 9506.33}
+
+[INFO|2025-10-20 01:26:16] logging.py:157 >> {'loss': 0.2179, 'learning_rate': 7.3478e-05, 'epoch': 1.03, 'throughput': 9504.64}
+
+[INFO|2025-10-20 01:34:49] logging.py:157 >> {'loss': 0.2098, 'learning_rate': 7.3058e-05, 'epoch': 1.04, 'throughput': 9506.20}
+
+[INFO|2025-10-20 01:43:41] logging.py:157 >> {'loss': 0.2174, 'learning_rate': 7.2636e-05, 'epoch': 1.05, 'throughput': 9505.78}
+
+[INFO|2025-10-20 01:52:29] logging.py:157 >> {'loss': 0.2187, 'learning_rate': 7.2212e-05, 'epoch': 1.06, 'throughput': 9506.65}
+
+[INFO|2025-10-20 02:01:32] logging.py:157 >> {'loss': 0.2162, 'learning_rate': 7.1786e-05, 'epoch': 1.07, 'throughput': 9506.10}
+
+[INFO|2025-10-20 02:10:19] logging.py:157 >> {'loss': 0.2202, 'learning_rate': 7.1358e-05, 'epoch': 1.08, 'throughput': 9505.76}
+
+[INFO|2025-10-20 02:19:23] logging.py:157 >> {'loss': 0.2237, 'learning_rate': 7.0928e-05, 'epoch': 1.09, 'throughput': 9504.97}
+
+[INFO|2025-10-20 02:27:59] logging.py:157 >> {'loss': 0.2199, 'learning_rate': 7.0496e-05, 'epoch': 1.10, 'throughput': 9505.35}
+
+[INFO|2025-10-20 02:37:16] logging.py:157 >> {'loss': 0.2189, 'learning_rate': 7.0062e-05, 'epoch': 1.11, 'throughput': 9501.61}
+
+[INFO|2025-10-20 02:46:26] logging.py:157 >> {'loss': 0.2163, 'learning_rate': 6.9626e-05, 'epoch': 1.11, 'throughput': 9501.64}
+
+[INFO|2025-10-20 02:55:16] logging.py:157 >> {'loss': 0.2157, 'learning_rate': 6.9189e-05, 'epoch': 1.12, 'throughput': 9502.18}
+
+[INFO|2025-10-20 03:04:29] logging.py:157 >> {'loss': 0.2141, 'learning_rate': 6.8750e-05, 'epoch': 1.13, 'throughput': 9499.47}
+
+[INFO|2025-10-20 03:12:55] logging.py:157 >> {'loss': 0.2185, 'learning_rate': 6.8309e-05, 'epoch': 1.14, 'throughput': 9502.37}
+
+[INFO|2025-10-20 03:21:51] logging.py:157 >> {'loss': 0.2125, 'learning_rate': 6.7867e-05, 'epoch': 1.15, 'throughput': 9502.47}
+
+[INFO|2025-10-20 03:30:50] logging.py:157 >> {'loss': 0.2138, 'learning_rate': 6.7423e-05, 'epoch': 1.16, 'throughput': 9501.96}
+
+[INFO|2025-10-20 03:39:45] logging.py:157 >> {'loss': 0.2152, 'learning_rate': 6.6977e-05, 'epoch': 1.17, 'throughput': 9502.59}
+
+[INFO|2025-10-20 03:48:29] logging.py:157 >> {'loss': 0.2125, 'learning_rate': 6.6530e-05, 'epoch': 1.18, 'throughput': 9503.45}
+
+[INFO|2025-10-20 03:57:37] logging.py:157 >> {'loss': 0.2123, 'learning_rate': 6.6081e-05, 'epoch': 1.19, 'throughput': 9502.01}
+
+[INFO|2025-10-20 04:06:37] logging.py:157 >> {'loss': 0.2101, 'learning_rate': 6.5631e-05, 'epoch': 1.20, 'throughput': 9500.47}
+
+[INFO|2025-10-20 04:15:30] logging.py:157 >> {'loss': 0.2090, 'learning_rate': 6.5180e-05, 'epoch': 1.21, 'throughput': 9501.47}
+
+[INFO|2025-10-20 04:24:12] logging.py:157 >> {'loss': 0.2122, 'learning_rate': 6.4727e-05, 'epoch': 1.21, 'throughput': 9501.91}
+
+[INFO|2025-10-20 04:33:14] logging.py:157 >> {'loss': 0.2093, 'learning_rate': 6.4273e-05, 'epoch': 1.22, 'throughput': 9500.84}
+
+[INFO|2025-10-20 04:41:55] logging.py:157 >> {'loss': 0.2114, 'learning_rate': 6.3817e-05, 'epoch': 1.23, 'throughput': 9501.80}
+
+[INFO|2025-10-20 04:50:50] logging.py:157 >> {'loss': 0.2111, 'learning_rate': 6.3361e-05, 'epoch': 1.24, 'throughput': 9501.17}
+
+[INFO|2025-10-20 04:59:36] logging.py:157 >> {'loss': 0.2086, 'learning_rate': 6.2903e-05, 'epoch': 1.25, 'throughput': 9501.16}
+
+[INFO|2025-10-20 05:08:27] logging.py:157 >> {'loss': 0.2095, 'learning_rate': 6.2444e-05, 'epoch': 1.26, 'throughput': 9501.00}
+
+[INFO|2025-10-20 05:17:03] logging.py:157 >> {'loss': 0.2083, 'learning_rate': 6.1984e-05, 'epoch': 1.27, 'throughput': 9502.81}
+
+[INFO|2025-10-20 05:25:43] logging.py:157 >> {'loss': 0.2088, 'learning_rate': 6.1522e-05, 'epoch': 1.28, 'throughput': 9504.07}
+
+[INFO|2025-10-20 05:34:38] logging.py:157 >> {'loss': 0.2118, 'learning_rate': 6.1060e-05, 'epoch': 1.29, 'throughput': 9503.94}
+
+[INFO|2025-10-20 05:43:25] logging.py:157 >> {'loss': 0.2058, 'learning_rate': 6.0597e-05, 'epoch': 1.30, 'throughput': 9504.75}
+
+[INFO|2025-10-20 05:52:28] logging.py:157 >> {'loss': 0.2065, 'learning_rate': 6.0132e-05, 'epoch': 1.31, 'throughput': 9504.80}
+
+[INFO|2025-10-20 06:01:14] logging.py:157 >> {'loss': 0.2070, 'learning_rate': 5.9667e-05, 'epoch': 1.31, 'throughput': 9504.25}
+
+[INFO|2025-10-20 06:10:19] logging.py:157 >> {'loss': 0.2049, 'learning_rate': 5.9201e-05, 'epoch': 1.32, 'throughput': 9502.94}
+
+[INFO|2025-10-20 06:19:34] logging.py:157 >> {'loss': 0.2080, 'learning_rate': 5.8734e-05, 'epoch': 1.33, 'throughput': 9499.75}
+
+[INFO|2025-10-20 06:28:22] logging.py:157 >> {'loss': 0.2047, 'learning_rate': 5.8267e-05, 'epoch': 1.34, 'throughput': 9499.82}
+
+[INFO|2025-10-20 06:37:17] logging.py:157 >> {'loss': 0.2022, 'learning_rate': 5.7798e-05, 'epoch': 1.35, 'throughput': 9498.47}
+
+[INFO|2025-10-20 06:46:48] logging.py:157 >> {'loss': 0.2073, 'learning_rate': 5.7329e-05, 'epoch': 1.36, 'throughput': 9494.01}
+
+[INFO|2025-10-20 06:55:58] logging.py:157 >> {'loss': 0.2056, 'learning_rate': 5.6859e-05, 'epoch': 1.37, 'throughput': 9492.45}
+
+[INFO|2025-10-20 07:04:26] logging.py:157 >> {'loss': 0.2056, 'learning_rate': 5.6389e-05, 'epoch': 1.38, 'throughput': 9494.77}
+
+[INFO|2025-10-20 07:13:31] logging.py:157 >> {'loss': 0.2037, 'learning_rate': 5.5918e-05, 'epoch': 1.39, 'throughput': 9494.81}
+
+[INFO|2025-10-20 07:22:03] logging.py:157 >> {'loss': 0.2042, 'learning_rate': 5.5447e-05, 'epoch': 1.40, 'throughput': 9496.67}
+
+[INFO|2025-10-20 07:31:07] logging.py:157 >> {'loss': 0.2011, 'learning_rate': 5.4975e-05, 'epoch': 1.40, 'throughput': 9496.92}
+
+[INFO|2025-10-20 07:40:10] logging.py:157 >> {'loss': 0.2015, 'learning_rate': 5.4502e-05, 'epoch': 1.41, 'throughput': 9495.35}
+
+[INFO|2025-10-20 07:49:28] logging.py:157 >> {'loss': 0.2005, 'learning_rate': 5.4029e-05, 'epoch': 1.42, 'throughput': 9493.13}
+
+[INFO|2025-10-20 07:58:08] logging.py:157 >> {'loss': 0.2052, 'learning_rate': 5.3556e-05, 'epoch': 1.43, 'throughput': 9493.86}
+
+[INFO|2025-10-20 08:06:44] logging.py:157 >> {'loss': 0.2042, 'learning_rate': 5.3083e-05, 'epoch': 1.44, 'throughput': 9495.07}
+
+[INFO|2025-10-20 08:15:42] logging.py:157 >> {'loss': 0.1984, 'learning_rate': 5.2609e-05, 'epoch': 1.45, 'throughput': 9493.99}
+
+[INFO|2025-10-20 08:24:50] logging.py:157 >> {'loss': 0.2038, 'learning_rate': 5.2135e-05, 'epoch': 1.46, 'throughput': 9492.20}
+
+[INFO|2025-10-20 08:33:47] logging.py:157 >> {'loss': 0.2012, 'learning_rate': 5.1661e-05, 'epoch': 1.47, 'throughput': 9492.22}
+
+[INFO|2025-10-20 08:42:27] logging.py:157 >> {'loss': 0.1987, 'learning_rate': 5.1186e-05, 'epoch': 1.48, 'throughput': 9492.76}
+
+[INFO|2025-10-20 08:51:30] logging.py:157 >> {'loss': 0.1986, 'learning_rate': 5.0712e-05, 'epoch': 1.49, 'throughput': 9491.54}
+
+[INFO|2025-10-20 09:00:19] logging.py:157 >> {'loss': 0.1987, 'learning_rate': 5.0237e-05, 'epoch': 1.50, 'throughput': 9491.31}
+
+[INFO|2025-10-20 09:08:54] logging.py:157 >> {'loss': 0.1952, 'learning_rate': 4.9763e-05, 'epoch': 1.50, 'throughput': 9493.38}
+
+[INFO|2025-10-20 09:17:40] logging.py:157 >> {'loss': 0.1957, 'learning_rate': 4.9288e-05, 'epoch': 1.51, 'throughput': 9494.32}
+
+[INFO|2025-10-20 09:26:33] logging.py:157 >> {'loss': 0.1957, 'learning_rate': 4.8814e-05, 'epoch': 1.52, 'throughput': 9495.01}
+
+[INFO|2025-10-20 09:35:27] logging.py:157 >> {'loss': 0.1970, 'learning_rate': 4.8339e-05, 'epoch': 1.53, 'throughput': 9494.56}
+
+[INFO|2025-10-20 09:43:58] logging.py:157 >> {'loss': 0.1957, 'learning_rate': 4.7865e-05, 'epoch': 1.54, 'throughput': 9495.47}
+
+[INFO|2025-10-20 09:52:47] logging.py:157 >> {'loss': 0.1926, 'learning_rate': 4.7391e-05, 'epoch': 1.55, 'throughput': 9496.47}
+
+[INFO|2025-10-20 10:01:54] logging.py:157 >> {'loss': 0.1934, 'learning_rate': 4.6917e-05, 'epoch': 1.56, 'throughput': 9496.66}
+
+[INFO|2025-10-20 10:10:48] logging.py:157 >> {'loss': 0.1961, 'learning_rate': 4.6444e-05, 'epoch': 1.57, 'throughput': 9496.52}
+
+[INFO|2025-10-20 10:19:52] logging.py:157 >> {'loss': 0.1902, 'learning_rate': 4.5971e-05, 'epoch': 1.58, 'throughput': 9496.01}
+
+[INFO|2025-10-20 10:28:51] logging.py:157 >> {'loss': 0.1971, 'learning_rate': 4.5498e-05, 'epoch': 1.59, 'throughput': 9495.37}
+
+[INFO|2025-10-20 10:37:40] logging.py:157 >> {'loss': 0.1952, 'learning_rate': 4.5025e-05, 'epoch': 1.59, 'throughput': 9495.50}
+
+[INFO|2025-10-20 10:46:19] logging.py:157 >> {'loss': 0.1908, 'learning_rate': 4.4553e-05, 'epoch': 1.60, 'throughput': 9496.69}
+
+[INFO|2025-10-20 10:55:21] logging.py:157 >> {'loss': 0.1945, 'learning_rate': 4.4082e-05, 'epoch': 1.61, 'throughput': 9496.20}
+
+[INFO|2025-10-20 11:04:17] logging.py:157 >> {'loss': 0.1911, 'learning_rate': 4.3611e-05, 'epoch': 1.62, 'throughput': 9496.70}
+
+[INFO|2025-10-20 11:13:15] logging.py:157 >> {'loss': 0.1930, 'learning_rate': 4.3141e-05, 'epoch': 1.63, 'throughput': 9496.86}
+
+[INFO|2025-10-20 11:22:03] logging.py:157 >> {'loss': 0.1898, 'learning_rate': 4.2671e-05, 'epoch': 1.64, 'throughput': 9498.11}
+
+[INFO|2025-10-20 11:30:38] logging.py:157 >> {'loss': 0.1852, 'learning_rate': 4.2202e-05, 'epoch': 1.65, 'throughput': 9500.27}
+
+[INFO|2025-10-20 11:39:38] logging.py:157 >> {'loss': 0.1863, 'learning_rate': 4.1733e-05, 'epoch': 1.66, 'throughput': 9499.96}
+
+[INFO|2025-10-20 11:48:37] logging.py:157 >> {'loss': 0.1882, 'learning_rate': 4.1266e-05, 'epoch': 1.67, 'throughput': 9498.96}
+
+[INFO|2025-10-20 11:57:24] logging.py:157 >> {'loss': 0.1893, 'learning_rate': 4.0799e-05, 'epoch': 1.68, 'throughput': 9500.06}
+
+[INFO|2025-10-20 12:06:33] logging.py:157 >> {'loss': 0.1885, 'learning_rate': 4.0333e-05, 'epoch': 1.69, 'throughput': 9499.68}
+
+[INFO|2025-10-20 12:15:46] logging.py:157 >> {'loss': 0.1883, 'learning_rate': 3.9868e-05, 'epoch': 1.69, 'throughput': 9499.21}
+
+[INFO|2025-10-20 12:24:39] logging.py:157 >> {'loss': 0.1871, 'learning_rate': 3.9403e-05, 'epoch': 1.70, 'throughput': 9499.01}
+
+[INFO|2025-10-20 12:33:32] logging.py:157 >> {'loss': 0.1853, 'learning_rate': 3.8940e-05, 'epoch': 1.71, 'throughput': 9498.79}
+
+[INFO|2025-10-20 12:42:17] logging.py:157 >> {'loss': 0.1862, 'learning_rate': 3.8478e-05, 'epoch': 1.72, 'throughput': 9499.53}
+
+[INFO|2025-10-20 12:51:21] logging.py:157 >> {'loss': 0.1913, 'learning_rate': 3.8016e-05, 'epoch': 1.73, 'throughput': 9498.33}
+
+[INFO|2025-10-20 13:00:21] logging.py:157 >> {'loss': 0.1908, 'learning_rate': 3.7556e-05, 'epoch': 1.74, 'throughput': 9498.07}
+
+[INFO|2025-10-20 13:09:43] logging.py:157 >> {'loss': 0.1839, 'learning_rate': 3.7097e-05, 'epoch': 1.75, 'throughput': 9496.29}
+
+[INFO|2025-10-20 13:18:59] logging.py:157 >> {'loss': 0.1869, 'learning_rate': 3.6639e-05, 'epoch': 1.76, 'throughput': 9495.72}
+
+[INFO|2025-10-20 13:27:58] logging.py:157 >> {'loss': 0.1884, 'learning_rate': 3.6183e-05, 'epoch': 1.77, 'throughput': 9494.70}
+
+[INFO|2025-10-20 13:37:11] logging.py:157 >> {'loss': 0.1863, 'learning_rate': 3.5727e-05, 'epoch': 1.78, 'throughput': 9492.68}
+
+[INFO|2025-10-20 13:45:49] logging.py:157 >> {'loss': 0.1884, 'learning_rate': 3.5273e-05, 'epoch': 1.79, 'throughput': 9493.64}
+
+[INFO|2025-10-20 13:54:26] logging.py:157 >> {'loss': 0.1815, 'learning_rate': 3.4820e-05, 'epoch': 1.79, 'throughput': 9494.28}
+
+[INFO|2025-10-20 14:03:24] logging.py:157 >> {'loss': 0.1798, 'learning_rate': 3.4369e-05, 'epoch': 1.80, 'throughput': 9493.88}
+
+[INFO|2025-10-20 14:11:55] logging.py:157 >> {'loss': 0.1797, 'learning_rate': 3.3919e-05, 'epoch': 1.81, 'throughput': 9495.04}
+
+[INFO|2025-10-20 14:20:35] logging.py:157 >> {'loss': 0.1773, 'learning_rate': 3.3470e-05, 'epoch': 1.82, 'throughput': 9495.33}
+
+[INFO|2025-10-20 14:29:27] logging.py:157 >> {'loss': 0.1828, 'learning_rate': 3.3023e-05, 'epoch': 1.83, 'throughput': 9494.34}
+
+[INFO|2025-10-20 14:38:22] logging.py:157 >> {'loss': 0.1800, 'learning_rate': 3.2577e-05, 'epoch': 1.84, 'throughput': 9494.06}
+
+[INFO|2025-10-20 14:47:18] logging.py:157 >> {'loss': 0.1825, 'learning_rate': 3.2133e-05, 'epoch': 1.85, 'throughput': 9493.51}
+
+[INFO|2025-10-20 14:56:14] logging.py:157 >> {'loss': 0.1776, 'learning_rate': 3.1691e-05, 'epoch': 1.86, 'throughput': 9493.01}
+
+[INFO|2025-10-20 15:05:18] logging.py:157 >> {'loss': 0.1768, 'learning_rate': 3.1250e-05, 'epoch': 1.87, 'throughput': 9493.04}
+
+[INFO|2025-10-20 15:14:21] logging.py:157 >> {'loss': 0.1778, 'learning_rate': 3.0811e-05, 'epoch': 1.88, 'throughput': 9492.18}
+
+[INFO|2025-10-20 15:23:32] logging.py:157 >> {'loss': 0.1788, 'learning_rate': 3.0374e-05, 'epoch': 1.88, 'throughput': 9491.15}
+
+[INFO|2025-10-20 15:32:43] logging.py:157 >> {'loss': 0.1760, 'learning_rate': 2.9938e-05, 'epoch': 1.89, 'throughput': 9490.66}
+
+[INFO|2025-10-20 15:41:43] logging.py:157 >> {'loss': 0.1783, 'learning_rate': 2.9504e-05, 'epoch': 1.90, 'throughput': 9490.01}
+
+[INFO|2025-10-20 15:50:49] logging.py:157 >> {'loss': 0.1780, 'learning_rate': 2.9072e-05, 'epoch': 1.91, 'throughput': 9488.58}
+
+[INFO|2025-10-20 15:59:52] logging.py:157 >> {'loss': 0.1759, 'learning_rate': 2.8642e-05, 'epoch': 1.92, 'throughput': 9488.29}
+
+[INFO|2025-10-20 16:08:51] logging.py:157 >> {'loss': 0.1769, 'learning_rate': 2.8214e-05, 'epoch': 1.93, 'throughput': 9487.56}
+
+[INFO|2025-10-20 16:17:39] logging.py:157 >> {'loss': 0.1761, 'learning_rate': 2.7788e-05, 'epoch': 1.94, 'throughput': 9488.08}
+
+[INFO|2025-10-20 16:26:37] logging.py:157 >> {'loss': 0.1762, 'learning_rate': 2.7364e-05, 'epoch': 1.95, 'throughput': 9488.56}
+
+[INFO|2025-10-20 16:35:36] logging.py:157 >> {'loss': 0.1715, 'learning_rate': 2.6942e-05, 'epoch': 1.96, 'throughput': 9489.02}
+
+[INFO|2025-10-20 16:44:11] logging.py:157 >> {'loss': 0.1728, 'learning_rate': 2.6522e-05, 'epoch': 1.97, 'throughput': 9489.67}
+
+[INFO|2025-10-20 16:53:22] logging.py:157 >> {'loss': 0.1750, 'learning_rate': 2.6104e-05, 'epoch': 1.98, 'throughput': 9488.69}
+
+[INFO|2025-10-20 17:02:13] logging.py:157 >> {'loss': 0.1736, 'learning_rate': 2.5688e-05, 'epoch': 1.98, 'throughput': 9489.47}
+
+[INFO|2025-10-20 17:11:21] logging.py:157 >> {'loss': 0.1704, 'learning_rate': 2.5274e-05, 'epoch': 1.99, 'throughput': 9489.29}
+
+[INFO|2025-10-20 17:20:16] logging.py:157 >> {'loss': 0.1548, 'learning_rate': 2.4863e-05, 'epoch': 2.00, 'throughput': 9490.07}
+
+[INFO|2025-10-20 17:29:16] logging.py:157 >> {'loss': 0.1188, 'learning_rate': 2.4454e-05, 'epoch': 2.01, 'throughput': 9489.70}
+
+[INFO|2025-10-20 17:38:27] logging.py:157 >> {'loss': 0.1176, 'learning_rate': 2.4047e-05, 'epoch': 2.02, 'throughput': 9490.21}
+
+[INFO|2025-10-20 17:47:24] logging.py:157 >> {'loss': 0.1166, 'learning_rate': 2.3643e-05, 'epoch': 2.03, 'throughput': 9489.93}
+
+[INFO|2025-10-20 17:56:19] logging.py:157 >> {'loss': 0.1129, 'learning_rate': 2.3241e-05, 'epoch': 2.04, 'throughput': 9489.27}
+
+[INFO|2025-10-20 18:05:04] logging.py:157 >> {'loss': 0.1122, 'learning_rate': 2.2841e-05, 'epoch': 2.05, 'throughput': 9490.08}
+
+[INFO|2025-10-20 18:13:56] logging.py:157 >> {'loss': 0.1145, 'learning_rate': 2.2444e-05, 'epoch': 2.06, 'throughput': 9490.09}
+
+[INFO|2025-10-20 18:22:51] logging.py:157 >> {'loss': 0.1153, 'learning_rate': 2.2049e-05, 'epoch': 2.07, 'throughput': 9490.25}
+
+[INFO|2025-10-20 18:31:59] logging.py:157 >> {'loss': 0.1152, 'learning_rate': 2.1657e-05, 'epoch': 2.08, 'throughput': 9489.42}
+
+[INFO|2025-10-20 18:40:42] logging.py:157 >> {'loss': 0.1148, 'learning_rate': 2.1267e-05, 'epoch': 2.08, 'throughput': 9489.77}
+
+[INFO|2025-10-20 18:50:03] logging.py:157 >> {'loss': 0.1119, 'learning_rate': 2.0880e-05, 'epoch': 2.09, 'throughput': 9488.55}
+
+[INFO|2025-10-20 18:59:08] logging.py:157 >> {'loss': 0.1101, 'learning_rate': 2.0496e-05, 'epoch': 2.10, 'throughput': 9487.59}
+
+[INFO|2025-10-20 19:08:09] logging.py:157 >> {'loss': 0.1139, 'learning_rate': 2.0114e-05, 'epoch': 2.11, 'throughput': 9487.45}
+
+[INFO|2025-10-20 19:16:41] logging.py:157 >> {'loss': 0.1116, 'learning_rate': 1.9735e-05, 'epoch': 2.12, 'throughput': 9489.64}
+
+[INFO|2025-10-20 19:25:49] logging.py:157 >> {'loss': 0.1120, 'learning_rate': 1.9358e-05, 'epoch': 2.13, 'throughput': 9489.09}
+
+[INFO|2025-10-20 19:34:50] logging.py:157 >> {'loss': 0.1106, 'learning_rate': 1.8985e-05, 'epoch': 2.14, 'throughput': 9488.78}
+
+[INFO|2025-10-20 19:43:50] logging.py:157 >> {'loss': 0.1124, 'learning_rate': 1.8614e-05, 'epoch': 2.15, 'throughput': 9488.59}
+
+[INFO|2025-10-20 19:52:41] logging.py:157 >> {'loss': 0.1136, 'learning_rate': 1.8246e-05, 'epoch': 2.16, 'throughput': 9488.83}
+
+[INFO|2025-10-20 19:53:28] trainer.py:4289 >> 
+***** Running Evaluation *****
+
+[INFO|2025-10-20 19:53:28] trainer.py:4291 >>   Num examples = 9176
+
+[INFO|2025-10-20 19:53:28] trainer.py:4294 >>   Batch size = 2
+
+[INFO|2025-10-20 20:02:26] trainer.py:3966 >> Saving model checkpoint to saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-5000
+
+[INFO|2025-10-20 20:02:26] configuration_utils.py:423 >> Configuration saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-5000/config.json
+
+[INFO|2025-10-20 20:02:26] configuration_utils.py:908 >> Configuration saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-5000/generation_config.json
+
+[INFO|2025-10-20 20:09:40] modeling_utils.py:3594 >> 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-VL-7B-Instruct/full/all_stage_123/checkpoint-5000/model.safetensors.index.json.
+
+[INFO|2025-10-20 20:09:40] tokenization_utils_base.py:2510 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-5000/tokenizer_config.json
+
+[INFO|2025-10-20 20:09:40] tokenization_utils_base.py:2519 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-5000/special_tokens_map.json
+
+[INFO|2025-10-20 20:14:49] image_processing_base.py:261 >> Image processor saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-5000/preprocessor_config.json
+
+[INFO|2025-10-20 20:14:49] tokenization_utils_base.py:2510 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-5000/tokenizer_config.json
+
+[INFO|2025-10-20 20:14:49] tokenization_utils_base.py:2519 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-5000/special_tokens_map.json
+
+[INFO|2025-10-20 20:14:49] processing_utils.py:638 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-5000/chat_template.json
+
+[INFO|2025-10-20 20:22:41] logging.py:157 >> {'loss': 0.1102, 'learning_rate': 1.7881e-05, 'epoch': 2.17, 'throughput': 9394.81}
+
+[INFO|2025-10-20 20:31:44] logging.py:157 >> {'loss': 0.1130, 'learning_rate': 1.7519e-05, 'epoch': 2.18, 'throughput': 9394.59}
+
+[INFO|2025-10-20 20:40:35] logging.py:157 >> {'loss': 0.1104, 'learning_rate': 1.7159e-05, 'epoch': 2.18, 'throughput': 9394.84}
+
+[INFO|2025-10-20 20:49:22] logging.py:157 >> {'loss': 0.1152, 'learning_rate': 1.6803e-05, 'epoch': 2.19, 'throughput': 9395.21}
+
+[INFO|2025-10-20 20:57:59] logging.py:157 >> {'loss': 0.1097, 'learning_rate': 1.6450e-05, 'epoch': 2.20, 'throughput': 9396.50}
+
+[INFO|2025-10-20 21:06:50] logging.py:157 >> {'loss': 0.1111, 'learning_rate': 1.6099e-05, 'epoch': 2.21, 'throughput': 9396.54}
+
+[INFO|2025-10-20 21:15:45] logging.py:157 >> {'loss': 0.1104, 'learning_rate': 1.5752e-05, 'epoch': 2.22, 'throughput': 9396.81}
+
+[INFO|2025-10-20 21:24:38] logging.py:157 >> {'loss': 0.1075, 'learning_rate': 1.5408e-05, 'epoch': 2.23, 'throughput': 9397.25}
+
+[INFO|2025-10-20 21:33:34] logging.py:157 >> {'loss': 0.1093, 'learning_rate': 1.5067e-05, 'epoch': 2.24, 'throughput': 9397.23}
+
+[INFO|2025-10-20 21:42:37] logging.py:157 >> {'loss': 0.1126, 'learning_rate': 1.4729e-05, 'epoch': 2.25, 'throughput': 9397.67}
+
+[INFO|2025-10-20 21:51:20] logging.py:157 >> {'loss': 0.1064, 'learning_rate': 1.4394e-05, 'epoch': 2.26, 'throughput': 9398.27}
+
+[INFO|2025-10-20 22:00:12] logging.py:157 >> {'loss': 0.1096, 'learning_rate': 1.4062e-05, 'epoch': 2.27, 'throughput': 9398.52}
+
+[INFO|2025-10-20 22:09:09] logging.py:157 >> {'loss': 0.1089, 'learning_rate': 1.3734e-05, 'epoch': 2.27, 'throughput': 9398.21}
+
+[INFO|2025-10-20 22:17:32] logging.py:157 >> {'loss': 0.1093, 'learning_rate': 1.3409e-05, 'epoch': 2.28, 'throughput': 9399.94}
+
+[INFO|2025-10-20 22:26:21] logging.py:157 >> {'loss': 0.1064, 'learning_rate': 1.3087e-05, 'epoch': 2.29, 'throughput': 9400.36}
+
+[INFO|2025-10-20 22:35:22] logging.py:157 >> {'loss': 0.1103, 'learning_rate': 1.2769e-05, 'epoch': 2.30, 'throughput': 9400.86}
+
+[INFO|2025-10-20 22:44:04] logging.py:157 >> {'loss': 0.1077, 'learning_rate': 1.2454e-05, 'epoch': 2.31, 'throughput': 9401.43}
+
+[INFO|2025-10-20 22:52:55] logging.py:157 >> {'loss': 0.1051, 'learning_rate': 1.2142e-05, 'epoch': 2.32, 'throughput': 9402.42}
+
+[INFO|2025-10-20 23:02:06] logging.py:157 >> {'loss': 0.1063, 'learning_rate': 1.1834e-05, 'epoch': 2.33, 'throughput': 9402.19}
+
+[INFO|2025-10-20 23:10:53] logging.py:157 >> {'loss': 0.1073, 'learning_rate': 1.1529e-05, 'epoch': 2.34, 'throughput': 9402.65}
+
+[INFO|2025-10-20 23:19:56] logging.py:157 >> {'loss': 0.1076, 'learning_rate': 1.1227e-05, 'epoch': 2.35, 'throughput': 9402.88}
+
+[INFO|2025-10-20 23:28:32] logging.py:157 >> {'loss': 0.1049, 'learning_rate': 1.0930e-05, 'epoch': 2.36, 'throughput': 9403.97}
+
+[INFO|2025-10-20 23:37:11] logging.py:157 >> {'loss': 0.1038, 'learning_rate': 1.0635e-05, 'epoch': 2.37, 'throughput': 9404.57}
+
+[INFO|2025-10-20 23:46:14] logging.py:157 >> {'loss': 0.1049, 'learning_rate': 1.0344e-05, 'epoch': 2.37, 'throughput': 9404.62}
+
+[INFO|2025-10-20 23:55:18] logging.py:157 >> {'loss': 0.1026, 'learning_rate': 1.0057e-05, 'epoch': 2.38, 'throughput': 9404.53}
+
+[INFO|2025-10-21 00:04:01] logging.py:157 >> {'loss': 0.1061, 'learning_rate': 9.7735e-06, 'epoch': 2.39, 'throughput': 9405.00}
+
+[INFO|2025-10-21 00:12:43] logging.py:157 >> {'loss': 0.1078, 'learning_rate': 9.4934e-06, 'epoch': 2.40, 'throughput': 9405.66}
+
+[INFO|2025-10-21 00:22:04] logging.py:157 >> {'loss': 0.1021, 'learning_rate': 9.2171e-06, 'epoch': 2.41, 'throughput': 9404.52}
+
+[INFO|2025-10-21 00:31:08] logging.py:157 >> {'loss': 0.1050, 'learning_rate': 8.9443e-06, 'epoch': 2.42, 'throughput': 9404.23}
+
+[INFO|2025-10-21 00:40:06] logging.py:157 >> {'loss': 0.1039, 'learning_rate': 8.6753e-06, 'epoch': 2.43, 'throughput': 9404.10}
+
+[INFO|2025-10-21 00:48:47] logging.py:157 >> {'loss': 0.1026, 'learning_rate': 8.4100e-06, 'epoch': 2.44, 'throughput': 9404.46}
+
+[INFO|2025-10-21 00:57:41] logging.py:157 >> {'loss': 0.1046, 'learning_rate': 8.1485e-06, 'epoch': 2.45, 'throughput': 9405.18}
+
+[INFO|2025-10-21 01:06:27] logging.py:157 >> {'loss': 0.1062, 'learning_rate': 7.8907e-06, 'epoch': 2.46, 'throughput': 9405.68}
+
+[INFO|2025-10-21 01:14:52] logging.py:157 >> {'loss': 0.1005, 'learning_rate': 7.6368e-06, 'epoch': 2.47, 'throughput': 9407.14}
+
+[INFO|2025-10-21 01:23:49] logging.py:157 >> {'loss': 0.1008, 'learning_rate': 7.3866e-06, 'epoch': 2.47, 'throughput': 9407.69}
+
+[INFO|2025-10-21 01:32:54] logging.py:157 >> {'loss': 0.1012, 'learning_rate': 7.1403e-06, 'epoch': 2.48, 'throughput': 9407.74}
+
+[INFO|2025-10-21 01:41:45] logging.py:157 >> {'loss': 0.1004, 'learning_rate': 6.8978e-06, 'epoch': 2.49, 'throughput': 9408.87}
+
+[INFO|2025-10-21 01:50:52] logging.py:157 >> {'loss': 0.1058, 'learning_rate': 6.6592e-06, 'epoch': 2.50, 'throughput': 9409.14}
+
+[INFO|2025-10-21 01:59:29] logging.py:157 >> {'loss': 0.0996, 'learning_rate': 6.4246e-06, 'epoch': 2.51, 'throughput': 9410.56}
+
+[INFO|2025-10-21 02:08:18] logging.py:157 >> {'loss': 0.0980, 'learning_rate': 6.1938e-06, 'epoch': 2.52, 'throughput': 9411.15}
+
+[INFO|2025-10-21 02:17:08] logging.py:157 >> {'loss': 0.1053, 'learning_rate': 5.9670e-06, 'epoch': 2.53, 'throughput': 9411.73}
+
+[INFO|2025-10-21 02:26:00] logging.py:157 >> {'loss': 0.1021, 'learning_rate': 5.7442e-06, 'epoch': 2.54, 'throughput': 9412.46}
+
+[INFO|2025-10-21 02:34:44] logging.py:157 >> {'loss': 0.1003, 'learning_rate': 5.5253e-06, 'epoch': 2.55, 'throughput': 9413.49}
+
+[INFO|2025-10-21 02:43:21] logging.py:157 >> {'loss': 0.1039, 'learning_rate': 5.3105e-06, 'epoch': 2.56, 'throughput': 9413.93}
+
+[INFO|2025-10-21 02:52:07] logging.py:157 >> {'loss': 0.1034, 'learning_rate': 5.0997e-06, 'epoch': 2.56, 'throughput': 9414.81}
+
+[INFO|2025-10-21 03:01:16] logging.py:157 >> {'loss': 0.1025, 'learning_rate': 4.8929e-06, 'epoch': 2.57, 'throughput': 9415.33}
+
+[INFO|2025-10-21 03:10:08] logging.py:157 >> {'loss': 0.1041, 'learning_rate': 4.6902e-06, 'epoch': 2.58, 'throughput': 9415.61}
+
+[INFO|2025-10-21 03:19:13] logging.py:157 >> {'loss': 0.1035, 'learning_rate': 4.4916e-06, 'epoch': 2.59, 'throughput': 9415.24}
+
+[INFO|2025-10-21 03:28:15] logging.py:157 >> {'loss': 0.1020, 'learning_rate': 4.2970e-06, 'epoch': 2.60, 'throughput': 9415.55}
+
+[INFO|2025-10-21 03:37:01] logging.py:157 >> {'loss': 0.0968, 'learning_rate': 4.1066e-06, 'epoch': 2.61, 'throughput': 9416.74}
+
+[INFO|2025-10-21 03:46:20] logging.py:157 >> {'loss': 0.1025, 'learning_rate': 3.9203e-06, 'epoch': 2.62, 'throughput': 9416.50}
+
+[INFO|2025-10-21 03:55:19] logging.py:157 >> {'loss': 0.0992, 'learning_rate': 3.7382e-06, 'epoch': 2.63, 'throughput': 9417.01}
+
+[INFO|2025-10-21 04:04:01] logging.py:157 >> {'loss': 0.1014, 'learning_rate': 3.5603e-06, 'epoch': 2.64, 'throughput': 9417.49}
+
+[INFO|2025-10-21 04:13:07] logging.py:157 >> {'loss': 0.0970, 'learning_rate': 3.3865e-06, 'epoch': 2.65, 'throughput': 9416.80}
+
+[INFO|2025-10-21 04:21:34] logging.py:157 >> {'loss': 0.1011, 'learning_rate': 3.2169e-06, 'epoch': 2.66, 'throughput': 9417.61}
+
+[INFO|2025-10-21 04:30:30] logging.py:157 >> {'loss': 0.1003, 'learning_rate': 3.0515e-06, 'epoch': 2.66, 'throughput': 9418.35}
+
+[INFO|2025-10-21 04:39:21] logging.py:157 >> {'loss': 0.1011, 'learning_rate': 2.8904e-06, 'epoch': 2.67, 'throughput': 9419.24}
+
+[INFO|2025-10-21 04:48:13] logging.py:157 >> {'loss': 0.0992, 'learning_rate': 2.7335e-06, 'epoch': 2.68, 'throughput': 9418.86}
+
+[INFO|2025-10-21 04:57:13] logging.py:157 >> {'loss': 0.0985, 'learning_rate': 2.5809e-06, 'epoch': 2.69, 'throughput': 9418.72}
+
+[INFO|2025-10-21 05:06:03] logging.py:157 >> {'loss': 0.0999, 'learning_rate': 2.4325e-06, 'epoch': 2.70, 'throughput': 9419.01}
+
+[INFO|2025-10-21 05:14:56] logging.py:157 >> {'loss': 0.1015, 'learning_rate': 2.2885e-06, 'epoch': 2.71, 'throughput': 9419.26}
+
+[INFO|2025-10-21 05:23:49] logging.py:157 >> {'loss': 0.0952, 'learning_rate': 2.1487e-06, 'epoch': 2.72, 'throughput': 9418.88}
+
+[INFO|2025-10-21 05:32:51] logging.py:157 >> {'loss': 0.1014, 'learning_rate': 2.0132e-06, 'epoch': 2.73, 'throughput': 9418.79}
+
+[INFO|2025-10-21 05:42:05] logging.py:157 >> {'loss': 0.0962, 'learning_rate': 1.8821e-06, 'epoch': 2.74, 'throughput': 9418.29}
+
+[INFO|2025-10-21 05:51:14] logging.py:157 >> {'loss': 0.0984, 'learning_rate': 1.7553e-06, 'epoch': 2.75, 'throughput': 9417.96}
+
+[INFO|2025-10-21 05:59:46] logging.py:157 >> {'loss': 0.0996, 'learning_rate': 1.6328e-06, 'epoch': 2.76, 'throughput': 9418.90}
+
+[INFO|2025-10-21 06:08:27] logging.py:157 >> {'loss': 0.0980, 'learning_rate': 1.5147e-06, 'epoch': 2.76, 'throughput': 9419.80}
+
+[INFO|2025-10-21 06:17:49] logging.py:157 >> {'loss': 0.0979, 'learning_rate': 1.4010e-06, 'epoch': 2.77, 'throughput': 9419.54}
+
+[INFO|2025-10-21 06:26:53] logging.py:157 >> {'loss': 0.0960, 'learning_rate': 1.2916e-06, 'epoch': 2.78, 'throughput': 9419.30}
+
+[INFO|2025-10-21 06:35:34] logging.py:157 >> {'loss': 0.0995, 'learning_rate': 1.1866e-06, 'epoch': 2.79, 'throughput': 9419.37}
+
+[INFO|2025-10-21 06:44:22] logging.py:157 >> {'loss': 0.0979, 'learning_rate': 1.0861e-06, 'epoch': 2.80, 'throughput': 9419.58}
+
+[INFO|2025-10-21 06:53:12] logging.py:157 >> {'loss': 0.0944, 'learning_rate': 9.8988e-07, 'epoch': 2.81, 'throughput': 9419.64}
+
+[INFO|2025-10-21 07:01:56] logging.py:157 >> {'loss': 0.0949, 'learning_rate': 8.9813e-07, 'epoch': 2.82, 'throughput': 9420.47}
+
+[INFO|2025-10-21 07:11:06] logging.py:157 >> {'loss': 0.0959, 'learning_rate': 8.1080e-07, 'epoch': 2.83, 'throughput': 9420.22}
+
+[INFO|2025-10-21 07:20:02] logging.py:157 >> {'loss': 0.0995, 'learning_rate': 7.2790e-07, 'epoch': 2.84, 'throughput': 9420.29}
+
+[INFO|2025-10-21 07:28:41] logging.py:157 >> {'loss': 0.0973, 'learning_rate': 6.4944e-07, 'epoch': 2.85, 'throughput': 9421.16}
+
+[INFO|2025-10-21 07:37:33] logging.py:157 >> {'loss': 0.0992, 'learning_rate': 5.7543e-07, 'epoch': 2.85, 'throughput': 9421.50}
+
+[INFO|2025-10-21 07:46:42] logging.py:157 >> {'loss': 0.0978, 'learning_rate': 5.0586e-07, 'epoch': 2.86, 'throughput': 9421.29}
+
+[INFO|2025-10-21 07:55:32] logging.py:157 >> {'loss': 0.0963, 'learning_rate': 4.4076e-07, 'epoch': 2.87, 'throughput': 9421.46}
+
+[INFO|2025-10-21 08:04:53] logging.py:157 >> {'loss': 0.0932, 'learning_rate': 3.8012e-07, 'epoch': 2.88, 'throughput': 9420.75}
+
+[INFO|2025-10-21 08:13:35] logging.py:157 >> {'loss': 0.0980, 'learning_rate': 3.2395e-07, 'epoch': 2.89, 'throughput': 9421.03}
+
+[INFO|2025-10-21 08:22:02] logging.py:157 >> {'loss': 0.0990, 'learning_rate': 2.7225e-07, 'epoch': 2.90, 'throughput': 9422.17}
+
+[INFO|2025-10-21 08:31:18] logging.py:157 >> {'loss': 0.0974, 'learning_rate': 2.2504e-07, 'epoch': 2.91, 'throughput': 9421.85}
+
+[INFO|2025-10-21 08:39:56] logging.py:157 >> {'loss': 0.0995, 'learning_rate': 1.8231e-07, 'epoch': 2.92, 'throughput': 9422.72}
+
+[INFO|2025-10-21 08:49:10] logging.py:157 >> {'loss': 0.0955, 'learning_rate': 1.4406e-07, 'epoch': 2.93, 'throughput': 9422.15}
+
+[INFO|2025-10-21 08:57:45] logging.py:157 >> {'loss': 0.0950, 'learning_rate': 1.1031e-07, 'epoch': 2.94, 'throughput': 9422.79}
+
+[INFO|2025-10-21 09:06:43] logging.py:157 >> {'loss': 0.0995, 'learning_rate': 8.1053e-08, 'epoch': 2.95, 'throughput': 9422.90}
+
+[INFO|2025-10-21 09:15:28] logging.py:157 >> {'loss': 0.0976, 'learning_rate': 5.6291e-08, 'epoch': 2.95, 'throughput': 9423.33}
+
+[INFO|2025-10-21 09:24:09] logging.py:157 >> {'loss': 0.0955, 'learning_rate': 3.6029e-08, 'epoch': 2.96, 'throughput': 9423.84}
+
+[INFO|2025-10-21 09:32:53] logging.py:157 >> {'loss': 0.0979, 'learning_rate': 2.0267e-08, 'epoch': 2.97, 'throughput': 9424.10}
+
+[INFO|2025-10-21 09:41:43] logging.py:157 >> {'loss': 0.0999, 'learning_rate': 9.0080e-09, 'epoch': 2.98, 'throughput': 9425.00}
+
+[INFO|2025-10-21 09:50:56] logging.py:157 >> {'loss': 0.0990, 'learning_rate': 2.2521e-09, 'epoch': 2.99, 'throughput': 9424.34}
+
+[INFO|2025-10-21 10:00:15] logging.py:157 >> {'loss': 0.0971, 'learning_rate': 0.0000e+00, 'epoch': 3.00, 'throughput': 9423.59}
+
+[INFO|2025-10-21 10:00:23] trainer.py:3966 >> Saving model checkpoint to saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-6951
+
+[INFO|2025-10-21 10:00:23] configuration_utils.py:423 >> Configuration saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-6951/config.json
+
+[INFO|2025-10-21 10:00:23] configuration_utils.py:908 >> Configuration saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-6951/generation_config.json
+
+[INFO|2025-10-21 10:07:28] modeling_utils.py:3594 >> 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-VL-7B-Instruct/full/all_stage_123/checkpoint-6951/model.safetensors.index.json.
+
+[INFO|2025-10-21 10:07:28] tokenization_utils_base.py:2510 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-6951/tokenizer_config.json
+
+[INFO|2025-10-21 10:07:28] tokenization_utils_base.py:2519 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-6951/special_tokens_map.json
+
+[INFO|2025-10-21 10:12:28] image_processing_base.py:261 >> Image processor saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-6951/preprocessor_config.json
+
+[INFO|2025-10-21 10:12:28] tokenization_utils_base.py:2510 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-6951/tokenizer_config.json
+
+[INFO|2025-10-21 10:12:28] tokenization_utils_base.py:2519 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-6951/special_tokens_map.json
+
+[INFO|2025-10-21 10:12:29] processing_utils.py:638 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/checkpoint-6951/chat_template.json
+
+[INFO|2025-10-21 10:12:29] trainer.py:2665 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-10-21 10:12:29] image_processing_base.py:261 >> Image processor saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/preprocessor_config.json
+
+[INFO|2025-10-21 10:12:29] tokenization_utils_base.py:2510 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/tokenizer_config.json
+
+[INFO|2025-10-21 10:12:29] tokenization_utils_base.py:2519 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/special_tokens_map.json
+
+[INFO|2025-10-21 10:12:30] processing_utils.py:638 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/chat_template.json
+
+[INFO|2025-10-21 10:12:37] trainer.py:3966 >> Saving model checkpoint to saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123
+
+[INFO|2025-10-21 10:12:37] configuration_utils.py:423 >> Configuration saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/config.json
+
+[INFO|2025-10-21 10:12:37] configuration_utils.py:908 >> Configuration saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/generation_config.json
+
+[INFO|2025-10-21 10:19:32] modeling_utils.py:3594 >> 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-VL-7B-Instruct/full/all_stage_123/model.safetensors.index.json.
+
+[INFO|2025-10-21 10:19:32] tokenization_utils_base.py:2510 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/tokenizer_config.json
+
+[INFO|2025-10-21 10:19:32] tokenization_utils_base.py:2519 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123/special_tokens_map.json
+
+[WARNING|2025-10-21 10:19:34] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2025-10-21 10:19:34] trainer.py:4289 >> 
+***** Running Evaluation *****
+
+[INFO|2025-10-21 10:19:34] trainer.py:4291 >>   Num examples = 9176
+
+[INFO|2025-10-21 10:19:34] trainer.py:4294 >>   Batch size = 2
+
+[INFO|2025-10-21 10:28:27] 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 +1,210 @@
+{
+  "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": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 6000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.9996224990562474,
+    "num_input_tokens_seen": 1677860944,
+    "total_flos": 8545808136798208.0,
+    "train_loss": 0.2019795169591595,
+    "train_runtime": 178782.2648,
+    "train_samples_per_second": 4.978,
+    "train_steps_per_second": 0.039
+}

trainer_log.jsonl

@@ -0,0 +1,333 @@
+{"current_steps": 21, "total_steps": 6951, "loss": 1.431, "lr": 9.999774793715127e-05, "epoch": 0.009060022650056626, "percentage": 0.3, "elapsed_time": "0:09:04", "remaining_time": "2 days, 1:56:17", "throughput": 9395.55, "total_tokens": 5118512}
+{"current_steps": 42, "total_steps": 6951, "loss": 0.5348, "lr": 9.99909919514765e-05, "epoch": 0.01812004530011325, "percentage": 0.6, "elapsed_time": "0:17:50", "remaining_time": "2 days, 0:56:01", "throughput": 9478.63, "total_tokens": 10150592}
+{"current_steps": 63, "total_steps": 6951, "loss": 0.4599, "lr": 9.997973265157192e-05, "epoch": 0.027180067950169876, "percentage": 0.91, "elapsed_time": "0:26:30", "remaining_time": "2 days, 0:18:38", "throughput": 9537.12, "total_tokens": 15170896}
+{"current_steps": 84, "total_steps": 6951, "loss": 0.4108, "lr": 9.996397105170353e-05, "epoch": 0.0362400906002265, "percentage": 1.21, "elapsed_time": "0:35:19", "remaining_time": "2 days, 0:08:22", "throughput": 9507.78, "total_tokens": 20155632}
+{"current_steps": 105, "total_steps": 6951, "loss": 0.3947, "lr": 9.994370857171588e-05, "epoch": 0.045300113250283124, "percentage": 1.51, "elapsed_time": "0:44:14", "remaining_time": "2 days, 0:04:12", "throughput": 9470.14, "total_tokens": 25135440}
+{"current_steps": 126, "total_steps": 6951, "loss": 0.3764, "lr": 9.991894703690414e-05, "epoch": 0.05436013590033975, "percentage": 1.81, "elapsed_time": "0:53:09", "remaining_time": "1 day, 23:58:59", "throughput": 9515.96, "total_tokens": 30346784}
+{"current_steps": 147, "total_steps": 6951, "loss": 0.3751, "lr": 9.988968867784958e-05, "epoch": 0.06342015855039637, "percentage": 2.11, "elapsed_time": "1:01:42", "remaining_time": "1 day, 23:36:18", "throughput": 9525.58, "total_tokens": 35269664}
+{"current_steps": 168, "total_steps": 6951, "loss": 0.3704, "lr": 9.985593613021872e-05, "epoch": 0.072480181200453, "percentage": 2.42, "elapsed_time": "1:10:20", "remaining_time": "1 day, 23:20:11", "throughput": 9513.01, "total_tokens": 40151792}
+{"current_steps": 189, "total_steps": 6951, "loss": 0.3552, "lr": 9.981769243452595e-05, "epoch": 0.08154020385050963, "percentage": 2.72, "elapsed_time": "1:19:14", "remaining_time": "1 day, 23:14:54", "throughput": 9524.9, "total_tokens": 45283312}
+{"current_steps": 210, "total_steps": 6951, "loss": 0.3576, "lr": 9.977496103585949e-05, "epoch": 0.09060022650056625, "percentage": 3.02, "elapsed_time": "1:28:00", "remaining_time": "1 day, 23:05:05", "throughput": 9525.35, "total_tokens": 50298912}
+{"current_steps": 231, "total_steps": 6951, "loss": 0.3451, "lr": 9.972774578357117e-05, "epoch": 0.09966024915062288, "percentage": 3.32, "elapsed_time": "1:37:00", "remaining_time": "1 day, 23:02:12", "throughput": 9525.43, "total_tokens": 55445792}
+{"current_steps": 252, "total_steps": 6951, "loss": 0.3506, "lr": 9.96760509309296e-05, "epoch": 0.1087202718006795, "percentage": 3.63, "elapsed_time": "1:45:52", "remaining_time": "1 day, 22:54:33", "throughput": 9524.66, "total_tokens": 60506496}
+{"current_steps": 273, "total_steps": 6951, "loss": 0.3443, "lr": 9.961988113473708e-05, "epoch": 0.11778029445073612, "percentage": 3.93, "elapsed_time": "1:54:50", "remaining_time": "1 day, 22:49:19", "throughput": 9531.29, "total_tokens": 65678096}
+{"current_steps": 294, "total_steps": 6951, "loss": 0.3446, "lr": 9.955924145491005e-05, "epoch": 0.12684031710079274, "percentage": 4.23, "elapsed_time": "2:03:13", "remaining_time": "1 day, 22:30:12", "throughput": 9532.39, "total_tokens": 70478688}
+{"current_steps": 315, "total_steps": 6951, "loss": 0.3362, "lr": 9.94941373540233e-05, "epoch": 0.13590033975084936, "percentage": 4.53, "elapsed_time": "2:11:37", "remaining_time": "1 day, 22:13:01", "throughput": 9543.53, "total_tokens": 75373536}
+{"current_steps": 336, "total_steps": 6951, "loss": 0.3384, "lr": 9.942457469681794e-05, "epoch": 0.144960362400906, "percentage": 4.83, "elapsed_time": "2:20:45", "remaining_time": "1 day, 22:11:15", "throughput": 9528.67, "total_tokens": 80476704}
+{"current_steps": 357, "total_steps": 6951, "loss": 0.3315, "lr": 9.935055974967299e-05, "epoch": 0.15402038505096263, "percentage": 5.14, "elapsed_time": "2:29:44", "remaining_time": "1 day, 22:05:57", "throughput": 9534.93, "total_tokens": 85670800}
+{"current_steps": 378, "total_steps": 6951, "loss": 0.33, "lr": 9.927209918004095e-05, "epoch": 0.16308040770101925, "percentage": 5.44, "elapsed_time": "2:38:25", "remaining_time": "1 day, 21:54:52", "throughput": 9542.47, "total_tokens": 90707040}
+{"current_steps": 399, "total_steps": 6951, "loss": 0.3296, "lr": 9.918920005584719e-05, "epoch": 0.17214043035107587, "percentage": 5.74, "elapsed_time": "2:47:34", "remaining_time": "1 day, 21:51:41", "throughput": 9530.71, "total_tokens": 95824496}
+{"current_steps": 420, "total_steps": 6951, "loss": 0.3315, "lr": 9.910186984485321e-05, "epoch": 0.1812004530011325, "percentage": 6.04, "elapsed_time": "2:56:23", "remaining_time": "1 day, 21:42:53", "throughput": 9530.11, "total_tokens": 100862224}
+{"current_steps": 441, "total_steps": 6951, "loss": 0.353, "lr": 9.901011641398398e-05, "epoch": 0.19026047565118911, "percentage": 6.34, "elapsed_time": "3:05:16", "remaining_time": "1 day, 21:34:59", "throughput": 9524.36, "total_tokens": 105876656}
+{"current_steps": 462, "total_steps": 6951, "loss": 0.3414, "lr": 9.89139480286192e-05, "epoch": 0.19932049830124576, "percentage": 6.65, "elapsed_time": "3:14:24", "remaining_time": "1 day, 21:30:34", "throughput": 9514.36, "total_tokens": 110980864}
+{"current_steps": 483, "total_steps": 6951, "loss": 0.3224, "lr": 9.881337335184878e-05, "epoch": 0.20838052095130238, "percentage": 6.95, "elapsed_time": "3:23:22", "remaining_time": "1 day, 21:23:33", "throughput": 9515.3, "total_tokens": 116114800}
+{"current_steps": 504, "total_steps": 6951, "loss": 0.3212, "lr": 9.870840144369246e-05, "epoch": 0.217440543601359, "percentage": 7.25, "elapsed_time": "3:32:28", "remaining_time": "1 day, 21:17:59", "throughput": 9511.06, "total_tokens": 121255744}
+{"current_steps": 525, "total_steps": 6951, "loss": 0.3213, "lr": 9.859904176028362e-05, "epoch": 0.22650056625141562, "percentage": 7.55, "elapsed_time": "3:41:20", "remaining_time": "1 day, 21:09:18", "throughput": 9509.05, "total_tokens": 126288608}
+{"current_steps": 546, "total_steps": 6951, "loss": 0.3198, "lr": 9.848530415301747e-05, "epoch": 0.23556058890147225, "percentage": 7.85, "elapsed_time": "3:49:53", "remaining_time": "1 day, 20:56:47", "throughput": 9514.22, "total_tokens": 131233488}
+{"current_steps": 567, "total_steps": 6951, "loss": 0.3149, "lr": 9.836719886766356e-05, "epoch": 0.24462061155152887, "percentage": 8.16, "elapsed_time": "3:58:35", "remaining_time": "1 day, 20:46:18", "throughput": 9518.41, "total_tokens": 136257888}
+{"current_steps": 588, "total_steps": 6951, "loss": 0.3169, "lr": 9.824473654344297e-05, "epoch": 0.2536806342015855, "percentage": 8.46, "elapsed_time": "4:07:48", "remaining_time": "1 day, 20:41:36", "throughput": 9510.51, "total_tokens": 141405120}
+{"current_steps": 609, "total_steps": 6951, "loss": 0.3142, "lr": 9.811792821206969e-05, "epoch": 0.2627406568516421, "percentage": 8.76, "elapsed_time": "4:16:46", "remaining_time": "1 day, 20:33:56", "throughput": 9501.43, "total_tokens": 146380496}
+{"current_steps": 630, "total_steps": 6951, "loss": 0.3097, "lr": 9.7986785296757e-05, "epoch": 0.2718006795016987, "percentage": 9.06, "elapsed_time": "4:25:32", "remaining_time": "1 day, 20:24:11", "throughput": 9499.35, "total_tokens": 151344048}
+{"current_steps": 651, "total_steps": 6951, "loss": 0.3116, "lr": 9.785131961118844e-05, "epoch": 0.2808607021517554, "percentage": 9.37, "elapsed_time": "4:34:25", "remaining_time": "1 day, 20:15:47", "throughput": 9500.56, "total_tokens": 156435136}
+{"current_steps": 672, "total_steps": 6951, "loss": 0.3086, "lr": 9.771154335845345e-05, "epoch": 0.289920724801812, "percentage": 9.67, "elapsed_time": "4:43:25", "remaining_time": "1 day, 20:08:13", "throughput": 9499.14, "total_tokens": 161536224}
+{"current_steps": 693, "total_steps": 6951, "loss": 0.3057, "lr": 9.756746912994832e-05, "epoch": 0.29898074745186864, "percentage": 9.97, "elapsed_time": "4:52:30", "remaining_time": "1 day, 20:01:24", "throughput": 9491.21, "total_tokens": 166573984}
+{"current_steps": 714, "total_steps": 6951, "loss": 0.3017, "lr": 9.741910990424174e-05, "epoch": 0.30804077010192527, "percentage": 10.27, "elapsed_time": "5:01:16", "remaining_time": "1 day, 19:51:46", "throughput": 9494.9, "total_tokens": 171638000}
+{"current_steps": 735, "total_steps": 6951, "loss": 0.3066, "lr": 9.726647904590571e-05, "epoch": 0.3171007927519819, "percentage": 10.57, "elapsed_time": "5:10:26", "remaining_time": "1 day, 19:45:29", "throughput": 9489.84, "total_tokens": 176765648}
+{"current_steps": 756, "total_steps": 6951, "loss": 0.2996, "lr": 9.710959030431167e-05, "epoch": 0.3261608154020385, "percentage": 10.88, "elapsed_time": "5:19:30", "remaining_time": "1 day, 19:38:14", "throughput": 9490.92, "total_tokens": 181949360}
+{"current_steps": 777, "total_steps": 6951, "loss": 0.2972, "lr": 9.694845781239187e-05, "epoch": 0.3352208380520951, "percentage": 11.18, "elapsed_time": "5:28:25", "remaining_time": "1 day, 19:29:35", "throughput": 9489.46, "total_tokens": 186990096}
+{"current_steps": 798, "total_steps": 6951, "loss": 0.2984, "lr": 9.678309608536626e-05, "epoch": 0.34428086070215175, "percentage": 11.48, "elapsed_time": "5:37:25", "remaining_time": "1 day, 19:21:44", "throughput": 9487.66, "total_tokens": 192083856}
+{"current_steps": 819, "total_steps": 6951, "loss": 0.2957, "lr": 9.661352001943493e-05, "epoch": 0.35334088335220837, "percentage": 11.78, "elapsed_time": "5:46:05", "remaining_time": "1 day, 19:11:15", "throughput": 9493.32, "total_tokens": 197134448}
+{"current_steps": 840, "total_steps": 6951, "loss": 0.2926, "lr": 9.64397448904362e-05, "epoch": 0.362400906002265, "percentage": 12.08, "elapsed_time": "5:55:14", "remaining_time": "1 day, 19:04:21", "throughput": 9491.78, "total_tokens": 202310368}
+{"current_steps": 861, "total_steps": 6951, "loss": 0.2909, "lr": 9.626178635247054e-05, "epoch": 0.3714609286523216, "percentage": 12.39, "elapsed_time": "6:04:00", "remaining_time": "1 day, 18:54:38", "throughput": 9494.44, "total_tokens": 207359840}
+{"current_steps": 882, "total_steps": 6951, "loss": 0.2954, "lr": 9.607966043649046e-05, "epoch": 0.38052095130237823, "percentage": 12.69, "elapsed_time": "6:12:54", "remaining_time": "1 day, 18:45:59", "throughput": 9492.66, "total_tokens": 212395664}
+{"current_steps": 903, "total_steps": 6951, "loss": 0.2912, "lr": 9.589338354885629e-05, "epoch": 0.3895809739524349, "percentage": 12.99, "elapsed_time": "6:21:47", "remaining_time": "1 day, 18:37:06", "throughput": 9497.8, "total_tokens": 217570640}
+{"current_steps": 924, "total_steps": 6951, "loss": 0.2928, "lr": 9.570297246985837e-05, "epoch": 0.3986409966024915, "percentage": 13.29, "elapsed_time": "6:30:38", "remaining_time": "1 day, 18:28:00", "throughput": 9498.61, "total_tokens": 222629712}
+{"current_steps": 945, "total_steps": 6951, "loss": 0.292, "lr": 9.550844435220539e-05, "epoch": 0.40770101925254815, "percentage": 13.6, "elapsed_time": "6:38:57", "remaining_time": "1 day, 18:15:34", "throughput": 9506.77, "total_tokens": 227565744}
+{"current_steps": 966, "total_steps": 6951, "loss": 0.292, "lr": 9.530981671947923e-05, "epoch": 0.41676104190260477, "percentage": 13.9, "elapsed_time": "6:48:04", "remaining_time": "1 day, 18:08:16", "throughput": 9502.21, "total_tokens": 232655712}
+{"current_steps": 987, "total_steps": 6951, "loss": 0.2959, "lr": 9.510710746455636e-05, "epoch": 0.4258210645526614, "percentage": 14.2, "elapsed_time": "6:56:51", "remaining_time": "1 day, 17:58:52", "throughput": 9500.11, "total_tokens": 237611056}
+{"current_steps": 1008, "total_steps": 6951, "loss": 0.2884, "lr": 9.490033484799608e-05, "epoch": 0.434881087202718, "percentage": 14.5, "elapsed_time": "7:05:54", "remaining_time": "1 day, 17:51:03", "throughput": 9497.19, "total_tokens": 242693136}
+{"current_steps": 1029, "total_steps": 6951, "loss": 0.2878, "lr": 9.468951749639551e-05, "epoch": 0.44394110985277463, "percentage": 14.8, "elapsed_time": "7:14:46", "remaining_time": "1 day, 17:42:12", "throughput": 9494.35, "total_tokens": 247677488}
+{"current_steps": 1050, "total_steps": 6951, "loss": 0.2908, "lr": 9.447467440071164e-05, "epoch": 0.45300113250283125, "percentage": 15.11, "elapsed_time": "7:23:55", "remaining_time": "1 day, 17:34:48", "throughput": 9490.15, "total_tokens": 252770384}
+{"current_steps": 1071, "total_steps": 6951, "loss": 0.2796, "lr": 9.425582491455067e-05, "epoch": 0.46206115515288787, "percentage": 15.41, "elapsed_time": "7:33:19", "remaining_time": "1 day, 17:28:50", "throughput": 9485.8, "total_tokens": 258009696}
+{"current_steps": 1092, "total_steps": 6951, "loss": 0.2858, "lr": 9.403298875242448e-05, "epoch": 0.4711211778029445, "percentage": 15.71, "elapsed_time": "7:42:23", "remaining_time": "1 day, 17:20:57", "throughput": 9484.86, "total_tokens": 263147728}
+{"current_steps": 1113, "total_steps": 6951, "loss": 0.2876, "lr": 9.380618598797473e-05, "epoch": 0.4801812004530011, "percentage": 16.01, "elapsed_time": "7:51:09", "remaining_time": "1 day, 17:11:21", "throughput": 9486.71, "total_tokens": 268184080}
+{"current_steps": 1134, "total_steps": 6951, "loss": 0.2814, "lr": 9.357543705216465e-05, "epoch": 0.48924122310305773, "percentage": 16.31, "elapsed_time": "8:00:24", "remaining_time": "1 day, 17:04:21", "throughput": 9486.33, "total_tokens": 273442768}
+{"current_steps": 1155, "total_steps": 6951, "loss": 0.2804, "lr": 9.334076273143843e-05, "epoch": 0.4983012457531144, "percentage": 16.62, "elapsed_time": "8:09:16", "remaining_time": "1 day, 16:55:18", "throughput": 9491.48, "total_tokens": 278640624}
+{"current_steps": 1176, "total_steps": 6951, "loss": 0.2863, "lr": 9.310218416584886e-05, "epoch": 0.507361268403171, "percentage": 16.92, "elapsed_time": "8:18:19", "remaining_time": "1 day, 16:47:09", "throughput": 9490.65, "total_tokens": 283769424}
+{"current_steps": 1197, "total_steps": 6951, "loss": 0.2851, "lr": 9.28597228471529e-05, "epoch": 0.5164212910532276, "percentage": 17.22, "elapsed_time": "8:27:03", "remaining_time": "1 day, 16:37:28", "throughput": 9494.69, "total_tokens": 288866448}
+{"current_steps": 1218, "total_steps": 6951, "loss": 0.2798, "lr": 9.26134006168757e-05, "epoch": 0.5254813137032842, "percentage": 17.52, "elapsed_time": "8:35:48", "remaining_time": "1 day, 16:27:52", "throughput": 9497.76, "total_tokens": 293944576}
+{"current_steps": 1239, "total_steps": 6951, "loss": 0.2728, "lr": 9.236323966434295e-05, "epoch": 0.5345413363533409, "percentage": 17.82, "elapsed_time": "8:44:51", "remaining_time": "1 day, 16:19:39", "throughput": 9497.6, "total_tokens": 299090032}
+{"current_steps": 1260, "total_steps": 6951, "loss": 0.2756, "lr": 9.210926252468219e-05, "epoch": 0.5436013590033975, "percentage": 18.13, "elapsed_time": "8:53:20", "remaining_time": "1 day, 16:08:56", "throughput": 9500.3, "total_tokens": 304016304}
+{"current_steps": 1281, "total_steps": 6951, "loss": 0.2747, "lr": 9.185149207679263e-05, "epoch": 0.5526613816534541, "percentage": 18.43, "elapsed_time": "9:02:10", "remaining_time": "1 day, 15:59:46", "throughput": 9501.41, "total_tokens": 309084016}
+{"current_steps": 1302, "total_steps": 6951, "loss": 0.2772, "lr": 9.158995154128425e-05, "epoch": 0.5617214043035108, "percentage": 18.73, "elapsed_time": "9:11:03", "remaining_time": "1 day, 15:50:52", "throughput": 9503.01, "total_tokens": 314201696}
+{"current_steps": 1323, "total_steps": 6951, "loss": 0.2785, "lr": 9.132466447838597e-05, "epoch": 0.5707814269535674, "percentage": 19.03, "elapsed_time": "9:19:38", "remaining_time": "1 day, 15:40:41", "throughput": 9508.07, "total_tokens": 319266256}
+{"current_steps": 1344, "total_steps": 6951, "loss": 0.2755, "lr": 9.105565478582334e-05, "epoch": 0.579841449603624, "percentage": 19.34, "elapsed_time": "9:28:38", "remaining_time": "1 day, 15:32:19", "throughput": 9509.96, "total_tokens": 324468352}
+{"current_steps": 1365, "total_steps": 6951, "loss": 0.2708, "lr": 9.078294669666576e-05, "epoch": 0.5889014722536806, "percentage": 19.64, "elapsed_time": "9:37:46", "remaining_time": "1 day, 15:24:25", "throughput": 9506.81, "total_tokens": 329566736}
+{"current_steps": 1386, "total_steps": 6951, "loss": 0.2729, "lr": 9.050656477714346e-05, "epoch": 0.5979614949037373, "percentage": 19.94, "elapsed_time": "9:46:49", "remaining_time": "1 day, 15:16:10", "throughput": 9504.96, "total_tokens": 334661888}
+{"current_steps": 1407, "total_steps": 6951, "loss": 0.2754, "lr": 9.022653392443454e-05, "epoch": 0.6070215175537939, "percentage": 20.24, "elapsed_time": "9:55:45", "remaining_time": "1 day, 15:07:27", "throughput": 9505.7, "total_tokens": 339784976}
+{"current_steps": 1428, "total_steps": 6951, "loss": 0.2742, "lr": 8.994287936442225e-05, "epoch": 0.6160815402038505, "percentage": 20.54, "elapsed_time": "10:04:49", "remaining_time": "1 day, 14:59:13", "throughput": 9500.81, "total_tokens": 344776544}
+{"current_steps": 1449, "total_steps": 6951, "loss": 0.2703, "lr": 8.96556266494224e-05, "epoch": 0.6251415628539071, "percentage": 20.85, "elapsed_time": "10:13:22", "remaining_time": "1 day, 14:49:01", "throughput": 9503.01, "total_tokens": 349731168}
+{"current_steps": 1470, "total_steps": 6951, "loss": 0.2756, "lr": 8.936480165588173e-05, "epoch": 0.6342015855039638, "percentage": 21.15, "elapsed_time": "10:22:04", "remaining_time": "1 day, 14:39:27", "throughput": 9502.95, "total_tokens": 354694544}
+{"current_steps": 1491, "total_steps": 6951, "loss": 0.2698, "lr": 8.907043058204674e-05, "epoch": 0.6432616081540203, "percentage": 21.45, "elapsed_time": "10:31:13", "remaining_time": "1 day, 14:31:31", "throughput": 9501.97, "total_tokens": 359871984}
+{"current_steps": 1512, "total_steps": 6951, "loss": 0.2716, "lr": 8.877253994560382e-05, "epoch": 0.652321630804077, "percentage": 21.75, "elapsed_time": "10:40:16", "remaining_time": "1 day, 14:23:14", "throughput": 9499.4, "total_tokens": 364937440}
+{"current_steps": 1533, "total_steps": 6951, "loss": 0.2682, "lr": 8.847115658129039e-05, "epoch": 0.6613816534541337, "percentage": 22.05, "elapsed_time": "10:49:13", "remaining_time": "1 day, 14:14:29", "throughput": 9498.48, "total_tokens": 369994848}
+{"current_steps": 1554, "total_steps": 6951, "loss": 0.2695, "lr": 8.816630763847755e-05, "epoch": 0.6704416761041903, "percentage": 22.36, "elapsed_time": "10:57:51", "remaining_time": "1 day, 14:04:43", "throughput": 9500.35, "total_tokens": 374992544}
+{"current_steps": 1575, "total_steps": 6951, "loss": 0.2706, "lr": 8.785802057872446e-05, "epoch": 0.6795016987542469, "percentage": 22.66, "elapsed_time": "11:06:33", "remaining_time": "1 day, 13:55:11", "throughput": 9502.46, "total_tokens": 380038624}
+{"current_steps": 1596, "total_steps": 6951, "loss": 0.2704, "lr": 8.754632317330447e-05, "epoch": 0.6885617214043035, "percentage": 22.96, "elapsed_time": "11:15:32", "remaining_time": "1 day, 13:46:38", "throughput": 9503.27, "total_tokens": 385195792}
+{"current_steps": 1617, "total_steps": 6951, "loss": 0.2707, "lr": 8.723124350070347e-05, "epoch": 0.6976217440543602, "percentage": 23.26, "elapsed_time": "11:24:14", "remaining_time": "1 day, 13:37:05", "throughput": 9504.39, "total_tokens": 390195296}
+{"current_steps": 1638, "total_steps": 6951, "loss": 0.2653, "lr": 8.691280994409043e-05, "epoch": 0.7066817667044167, "percentage": 23.56, "elapsed_time": "11:33:22", "remaining_time": "1 day, 13:28:59", "throughput": 9503.23, "total_tokens": 395353440}
+{"current_steps": 1659, "total_steps": 6951, "loss": 0.2649, "lr": 8.659105118876068e-05, "epoch": 0.7157417893544734, "percentage": 23.87, "elapsed_time": "11:41:58", "remaining_time": "1 day, 13:19:14", "throughput": 9507.46, "total_tokens": 400444080}
+{"current_steps": 1680, "total_steps": 6951, "loss": 0.2652, "lr": 8.626599621955179e-05, "epoch": 0.72480181200453, "percentage": 24.17, "elapsed_time": "11:50:50", "remaining_time": "1 day, 13:10:14", "throughput": 9507.43, "total_tokens": 405492112}
+{"current_steps": 1701, "total_steps": 6951, "loss": 0.2638, "lr": 8.593767431823255e-05, "epoch": 0.7338618346545867, "percentage": 24.47, "elapsed_time": "11:59:34", "remaining_time": "1 day, 13:00:53", "throughput": 9507.28, "total_tokens": 410467584}
+{"current_steps": 1722, "total_steps": 6951, "loss": 0.2685, "lr": 8.56061150608652e-05, "epoch": 0.7429218573046432, "percentage": 24.77, "elapsed_time": "12:08:13", "remaining_time": "1 day, 12:51:17", "throughput": 9510.67, "total_tokens": 415550320}
+{"current_steps": 1743, "total_steps": 6951, "loss": 0.2584, "lr": 8.527134831514117e-05, "epoch": 0.7519818799546999, "percentage": 25.08, "elapsed_time": "12:16:49", "remaining_time": "1 day, 12:41:35", "throughput": 9511.61, "total_tokens": 420503712}
+{"current_steps": 1764, "total_steps": 6951, "loss": 0.2607, "lr": 8.493340423769053e-05, "epoch": 0.7610419026047565, "percentage": 25.38, "elapsed_time": "12:25:46", "remaining_time": "1 day, 12:32:56", "throughput": 9511.41, "total_tokens": 425602800}
+{"current_steps": 1785, "total_steps": 6951, "loss": 0.2652, "lr": 8.459231327136532e-05, "epoch": 0.7701019252548131, "percentage": 25.68, "elapsed_time": "12:34:23", "remaining_time": "1 day, 12:23:18", "throughput": 9511.99, "total_tokens": 430546320}
+{"current_steps": 1806, "total_steps": 6951, "loss": 0.2604, "lr": 8.42481061424973e-05, "epoch": 0.7791619479048698, "percentage": 25.98, "elapsed_time": "12:43:09", "remaining_time": "1 day, 12:14:07", "throughput": 9513.64, "total_tokens": 435625600}
+{"current_steps": 1827, "total_steps": 6951, "loss": 0.2603, "lr": 8.390081385812993e-05, "epoch": 0.7882219705549264, "percentage": 26.28, "elapsed_time": "12:51:51", "remaining_time": "1 day, 12:04:45", "throughput": 9515.83, "total_tokens": 440695024}
+{"current_steps": 1848, "total_steps": 6951, "loss": 0.2576, "lr": 8.355046770322528e-05, "epoch": 0.797281993204983, "percentage": 26.59, "elapsed_time": "13:01:19", "remaining_time": "1 day, 11:57:30", "throughput": 9511.18, "total_tokens": 445877360}
+{"current_steps": 1869, "total_steps": 6951, "loss": 0.2622, "lr": 8.319709923784573e-05, "epoch": 0.8063420158550396, "percentage": 26.89, "elapsed_time": "13:10:17", "remaining_time": "1 day, 11:48:52", "throughput": 9511.76, "total_tokens": 451021040}
+{"current_steps": 1890, "total_steps": 6951, "loss": 0.2587, "lr": 8.284074029431099e-05, "epoch": 0.8154020385050963, "percentage": 27.19, "elapsed_time": "13:19:10", "remaining_time": "1 day, 11:39:59", "throughput": 9511.99, "total_tokens": 456101872}
+{"current_steps": 1911, "total_steps": 6951, "loss": 0.2575, "lr": 8.248142297433057e-05, "epoch": 0.8244620611551529, "percentage": 27.49, "elapsed_time": "13:28:28", "remaining_time": "1 day, 11:32:13", "throughput": 9511.08, "total_tokens": 461365920}
+{"current_steps": 1932, "total_steps": 6951, "loss": 0.2573, "lr": 8.211917964611196e-05, "epoch": 0.8335220838052095, "percentage": 27.79, "elapsed_time": "13:37:33", "remaining_time": "1 day, 11:23:52", "throughput": 9509.35, "total_tokens": 466466096}
+{"current_steps": 1953, "total_steps": 6951, "loss": 0.26, "lr": 8.175404294144482e-05, "epoch": 0.8425821064552661, "percentage": 28.1, "elapsed_time": "13:46:33", "remaining_time": "1 day, 11:15:17", "throughput": 9508.08, "total_tokens": 471541104}
+{"current_steps": 1974, "total_steps": 6951, "loss": 0.2571, "lr": 8.138604575276143e-05, "epoch": 0.8516421291053228, "percentage": 28.4, "elapsed_time": "13:55:43", "remaining_time": "1 day, 11:07:04", "throughput": 9505.71, "total_tokens": 476646096}
+{"current_steps": 1995, "total_steps": 6951, "loss": 0.251, "lr": 8.10152212301737e-05, "epoch": 0.8607021517553793, "percentage": 28.7, "elapsed_time": "14:04:22", "remaining_time": "1 day, 10:57:36", "throughput": 9507.9, "total_tokens": 481695200}
+{"current_steps": 2016, "total_steps": 6951, "loss": 0.2614, "lr": 8.064160277848682e-05, "epoch": 0.869762174405436, "percentage": 29.0, "elapsed_time": "14:13:13", "remaining_time": "1 day, 10:48:38", "throughput": 9507.12, "total_tokens": 486706656}
+{"current_steps": 2037, "total_steps": 6951, "loss": 0.2528, "lr": 8.026522405419023e-05, "epoch": 0.8788221970554927, "percentage": 29.31, "elapsed_time": "14:22:37", "remaining_time": "1 day, 10:40:57", "throughput": 9504.87, "total_tokens": 491943424}
+{"current_steps": 2058, "total_steps": 6951, "loss": 0.2571, "lr": 7.988611896242559e-05, "epoch": 0.8878822197055493, "percentage": 29.61, "elapsed_time": "14:31:02", "remaining_time": "1 day, 10:30:56", "throughput": 9508.31, "total_tokens": 496925888}
+{"current_steps": 2079, "total_steps": 6951, "loss": 0.2547, "lr": 7.950432165393259e-05, "epoch": 0.8969422423556059, "percentage": 29.91, "elapsed_time": "14:40:01", "remaining_time": "1 day, 10:22:16", "throughput": 9508.57, "total_tokens": 502065216}
+{"current_steps": 2100, "total_steps": 6951, "loss": 0.2538, "lr": 7.911986652197262e-05, "epoch": 0.9060022650056625, "percentage": 30.21, "elapsed_time": "14:48:55", "remaining_time": "1 day, 10:13:25", "throughput": 9507.51, "total_tokens": 507089616}
+{"current_steps": 2121, "total_steps": 6951, "loss": 0.2551, "lr": 7.873278819923048e-05, "epoch": 0.9150622876557192, "percentage": 30.51, "elapsed_time": "14:57:43", "remaining_time": "1 day, 10:04:18", "throughput": 9506.69, "total_tokens": 512060336}
+{"current_steps": 2142, "total_steps": 6951, "loss": 0.2515, "lr": 7.834312155469456e-05, "epoch": 0.9241223103057757, "percentage": 30.82, "elapsed_time": "15:06:55", "remaining_time": "1 day, 9:56:07", "throughput": 9503.49, "total_tokens": 517133680}
+{"current_steps": 2163, "total_steps": 6951, "loss": 0.2526, "lr": 7.79509016905158e-05, "epoch": 0.9331823329558324, "percentage": 31.12, "elapsed_time": "15:15:49", "remaining_time": "1 day, 9:47:16", "throughput": 9503.75, "total_tokens": 522229616}
+{"current_steps": 2184, "total_steps": 6951, "loss": 0.2482, "lr": 7.755616393884561e-05, "epoch": 0.942242355605889, "percentage": 31.42, "elapsed_time": "15:24:47", "remaining_time": "1 day, 9:38:31", "throughput": 9504.35, "total_tokens": 527368864}
+{"current_steps": 2205, "total_steps": 6951, "loss": 0.2516, "lr": 7.715894385865299e-05, "epoch": 0.9513023782559457, "percentage": 31.72, "elapsed_time": "15:33:55", "remaining_time": "1 day, 9:30:09", "throughput": 9502.88, "total_tokens": 532499712}
+{"current_steps": 2226, "total_steps": 6951, "loss": 0.2493, "lr": 7.675927723252134e-05, "epoch": 0.9603624009060022, "percentage": 32.02, "elapsed_time": "15:42:18", "remaining_time": "1 day, 9:20:10", "throughput": 9505.71, "total_tokens": 537438224}
+{"current_steps": 2247, "total_steps": 6951, "loss": 0.2465, "lr": 7.635720006342512e-05, "epoch": 0.9694224235560589, "percentage": 32.33, "elapsed_time": "15:51:07", "remaining_time": "1 day, 9:11:07", "throughput": 9508.14, "total_tokens": 542603472}
+{"current_steps": 2268, "total_steps": 6951, "loss": 0.2486, "lr": 7.595274857148652e-05, "epoch": 0.9784824462061155, "percentage": 32.63, "elapsed_time": "15:59:54", "remaining_time": "1 day, 9:02:01", "throughput": 9508.27, "total_tokens": 547622688}
+{"current_steps": 2289, "total_steps": 6951, "loss": 0.2472, "lr": 7.554595919071268e-05, "epoch": 0.9875424688561721, "percentage": 32.93, "elapsed_time": "16:09:00", "remaining_time": "1 day, 8:53:35", "throughput": 9507.12, "total_tokens": 552751232}
+{"current_steps": 2310, "total_steps": 6951, "loss": 0.2471, "lr": 7.513686856571368e-05, "epoch": 0.9966024915062288, "percentage": 33.23, "elapsed_time": "16:17:53", "remaining_time": "1 day, 8:44:39", "throughput": 9506.69, "total_tokens": 557786736}
+{"current_steps": 2331, "total_steps": 6951, "loss": 0.2361, "lr": 7.472551354840145e-05, "epoch": 1.0060400151000377, "percentage": 33.53, "elapsed_time": "16:27:14", "remaining_time": "1 day, 8:36:40", "throughput": 9504.55, "total_tokens": 562993712}
+{"current_steps": 2352, "total_steps": 6951, "loss": 0.217, "lr": 7.431193119467008e-05, "epoch": 1.0151000377500943, "percentage": 33.84, "elapsed_time": "16:36:00", "remaining_time": "1 day, 8:27:32", "throughput": 9504.99, "total_tokens": 568021744}
+{"current_steps": 2373, "total_steps": 6951, "loss": 0.2145, "lr": 7.389615876105774e-05, "epoch": 1.024160060400151, "percentage": 34.14, "elapsed_time": "16:44:31", "remaining_time": "1 day, 8:17:55", "throughput": 9506.33, "total_tokens": 572956608}
+{"current_steps": 2394, "total_steps": 6951, "loss": 0.2179, "lr": 7.347823370139042e-05, "epoch": 1.0332200830502076, "percentage": 34.44, "elapsed_time": "16:53:29", "remaining_time": "1 day, 8:09:11", "throughput": 9504.64, "total_tokens": 577973792}
+{"current_steps": 2415, "total_steps": 6951, "loss": 0.2098, "lr": 7.30581936634082e-05, "epoch": 1.0422801057002642, "percentage": 34.74, "elapsed_time": "17:02:02", "remaining_time": "1 day, 7:59:40", "throughput": 9506.2, "total_tokens": 582948368}
+{"current_steps": 2436, "total_steps": 6951, "loss": 0.2174, "lr": 7.263607648537364e-05, "epoch": 1.051340128350321, "percentage": 35.05, "elapsed_time": "17:10:54", "remaining_time": "1 day, 7:50:43", "throughput": 9505.78, "total_tokens": 587973936}
+{"current_steps": 2457, "total_steps": 6951, "loss": 0.2187, "lr": 7.221192019266332e-05, "epoch": 1.0604001510003775, "percentage": 35.35, "elapsed_time": "17:19:42", "remaining_time": "1 day, 7:41:41", "throughput": 9506.65, "total_tokens": 593048624}
+{"current_steps": 2478, "total_steps": 6951, "loss": 0.2162, "lr": 7.178576299434238e-05, "epoch": 1.069460173650434, "percentage": 35.65, "elapsed_time": "17:28:45", "remaining_time": "1 day, 7:33:05", "throughput": 9506.1, "total_tokens": 598171840}
+{"current_steps": 2499, "total_steps": 6951, "loss": 0.2202, "lr": 7.135764327972261e-05, "epoch": 1.0785201963004907, "percentage": 35.95, "elapsed_time": "17:37:32", "remaining_time": "1 day, 7:24:02", "throughput": 9505.76, "total_tokens": 603168000}
+{"current_steps": 2520, "total_steps": 6951, "loss": 0.2237, "lr": 7.092759961490415e-05, "epoch": 1.0875802189505475, "percentage": 36.25, "elapsed_time": "17:46:36", "remaining_time": "1 day, 7:15:26", "throughput": 9504.97, "total_tokens": 608280544}
+{"current_steps": 2541, "total_steps": 6951, "loss": 0.2199, "lr": 7.049567073930143e-05, "epoch": 1.096640241600604, "percentage": 36.56, "elapsed_time": "17:55:12", "remaining_time": "1 day, 7:06:04", "throughput": 9505.35, "total_tokens": 613215280}
+{"current_steps": 2562, "total_steps": 6951, "loss": 0.2189, "lr": 7.006189556215345e-05, "epoch": 1.1057002642506606, "percentage": 36.86, "elapsed_time": "18:04:29", "remaining_time": "1 day, 6:57:50", "throughput": 9501.61, "total_tokens": 618261984}
+{"current_steps": 2583, "total_steps": 6951, "loss": 0.2163, "lr": 6.962631315901861e-05, "epoch": 1.1147602869007172, "percentage": 37.16, "elapsed_time": "18:13:39", "remaining_time": "1 day, 6:49:26", "throughput": 9501.64, "total_tokens": 623492320}
+{"current_steps": 2604, "total_steps": 6951, "loss": 0.2157, "lr": 6.918896276825485e-05, "epoch": 1.123820309550774, "percentage": 37.46, "elapsed_time": "18:22:29", "remaining_time": "1 day, 6:40:26", "throughput": 9502.18, "total_tokens": 628563152}
+{"current_steps": 2625, "total_steps": 6951, "loss": 0.2141, "lr": 6.874988378748483e-05, "epoch": 1.1328803322008305, "percentage": 37.76, "elapsed_time": "18:31:42", "remaining_time": "1 day, 6:32:05", "throughput": 9499.47, "total_tokens": 633639472}
+{"current_steps": 2646, "total_steps": 6951, "loss": 0.2185, "lr": 6.830911577004698e-05, "epoch": 1.141940354850887, "percentage": 38.07, "elapsed_time": "18:40:08", "remaining_time": "1 day, 6:22:27", "throughput": 9502.37, "total_tokens": 638639648}
+{"current_steps": 2667, "total_steps": 6951, "loss": 0.2125, "lr": 6.786669842143236e-05, "epoch": 1.1510003775009436, "percentage": 38.37, "elapsed_time": "18:49:04", "remaining_time": "1 day, 6:13:38", "throughput": 9502.47, "total_tokens": 643743632}
+{"current_steps": 2688, "total_steps": 6951, "loss": 0.2138, "lr": 6.742267159570795e-05, "epoch": 1.1600604001510004, "percentage": 38.67, "elapsed_time": "18:58:03", "remaining_time": "1 day, 6:04:52", "throughput": 9501.96, "total_tokens": 648823584}
+{"current_steps": 2709, "total_steps": 6951, "loss": 0.2152, "lr": 6.697707529192648e-05, "epoch": 1.169120422801057, "percentage": 38.97, "elapsed_time": "19:06:58", "remaining_time": "1 day, 5:56:01", "throughput": 9502.59, "total_tokens": 653949232}
+{"current_steps": 2730, "total_steps": 6951, "loss": 0.2125, "lr": 6.652994965052319e-05, "epoch": 1.1781804454511136, "percentage": 39.27, "elapsed_time": "19:15:42", "remaining_time": "1 day, 5:46:54", "throughput": 9503.45, "total_tokens": 658996016}
+{"current_steps": 2751, "total_steps": 6951, "loss": 0.2123, "lr": 6.608133494969994e-05, "epoch": 1.1872404681011703, "percentage": 39.58, "elapsed_time": "19:24:50", "remaining_time": "1 day, 5:38:23", "throughput": 9502.01, "total_tokens": 664102304}
+{"current_steps": 2772, "total_steps": 6951, "loss": 0.2101, "lr": 6.563127160179671e-05, "epoch": 1.196300490751227, "percentage": 39.88, "elapsed_time": "19:33:50", "remaining_time": "1 day, 5:29:39", "throughput": 9500.47, "total_tokens": 669123584}
+{"current_steps": 2793, "total_steps": 6951, "loss": 0.209, "lr": 6.517980014965139e-05, "epoch": 1.2053605134012835, "percentage": 40.18, "elapsed_time": "19:42:43", "remaining_time": "1 day, 5:20:44", "throughput": 9501.47, "total_tokens": 674256592}
+{"current_steps": 2814, "total_steps": 6951, "loss": 0.2122, "lr": 6.472696126294732e-05, "epoch": 1.21442053605134, "percentage": 40.48, "elapsed_time": "19:51:25", "remaining_time": "1 day, 5:11:34", "throughput": 9501.91, "total_tokens": 679248208}
+{"current_steps": 2835, "total_steps": 6951, "loss": 0.2093, "lr": 6.427279573454985e-05, "epoch": 1.2234805587013968, "percentage": 40.79, "elapsed_time": "20:00:27", "remaining_time": "1 day, 5:02:53", "throughput": 9500.84, "total_tokens": 684325632}
+{"current_steps": 2856, "total_steps": 6951, "loss": 0.2114, "lr": 6.381734447683152e-05, "epoch": 1.2325405813514534, "percentage": 41.09, "elapsed_time": "20:09:08", "remaining_time": "1 day, 4:53:41", "throughput": 9501.8, "total_tokens": 689336736}
+{"current_steps": 2877, "total_steps": 6951, "loss": 0.2111, "lr": 6.33606485179866e-05, "epoch": 1.24160060400151, "percentage": 41.39, "elapsed_time": "20:18:03", "remaining_time": "1 day, 4:44:51", "throughput": 9501.17, "total_tokens": 694382688}
+{"current_steps": 2898, "total_steps": 6951, "loss": 0.2086, "lr": 6.290274899833517e-05, "epoch": 1.2506606266515665, "percentage": 41.69, "elapsed_time": "20:26:49", "remaining_time": "1 day, 4:35:46", "throughput": 9501.16, "total_tokens": 699371792}
+{"current_steps": 2919, "total_steps": 6951, "loss": 0.2095, "lr": 6.244368716661713e-05, "epoch": 1.2597206493016233, "percentage": 41.99, "elapsed_time": "20:35:40", "remaining_time": "1 day, 4:26:49", "throughput": 9501.0, "total_tokens": 704404624}
+{"current_steps": 2940, "total_steps": 6951, "loss": 0.2083, "lr": 6.198350437627632e-05, "epoch": 1.2687806719516799, "percentage": 42.3, "elapsed_time": "20:44:16", "remaining_time": "1 day, 4:17:33", "throughput": 9502.81, "total_tokens": 709451392}
+{"current_steps": 2961, "total_steps": 6951, "loss": 0.2088, "lr": 6.152224208173533e-05, "epoch": 1.2778406946017364, "percentage": 42.6, "elapsed_time": "20:52:56", "remaining_time": "1 day, 4:08:22", "throughput": 9504.07, "total_tokens": 714486848}
+{"current_steps": 2982, "total_steps": 6951, "loss": 0.2118, "lr": 6.10599418346613e-05, "epoch": 1.2869007172517932, "percentage": 42.9, "elapsed_time": "21:01:51", "remaining_time": "1 day, 3:59:30", "throughput": 9503.94, "total_tokens": 719556448}
+{"current_steps": 3003, "total_steps": 6951, "loss": 0.2058, "lr": 6.059664528022266e-05, "epoch": 1.2959607399018498, "percentage": 43.2, "elapsed_time": "21:10:38", "remaining_time": "1 day, 3:50:29", "throughput": 9504.75, "total_tokens": 724625472}
+{"current_steps": 3024, "total_steps": 6951, "loss": 0.2065, "lr": 6.0132394153337755e-05, "epoch": 1.3050207625519064, "percentage": 43.5, "elapsed_time": "21:19:41", "remaining_time": "1 day, 3:41:49", "throughput": 9504.8, "total_tokens": 729794320}
+{"current_steps": 3045, "total_steps": 6951, "loss": 0.207, "lr": 5.9667230274915174e-05, "epoch": 1.3140807852019631, "percentage": 43.81, "elapsed_time": "21:28:27", "remaining_time": "1 day, 3:32:47", "throughput": 9504.25, "total_tokens": 734753392}
+{"current_steps": 3066, "total_steps": 6951, "loss": 0.2049, "lr": 5.920119554808651e-05, "epoch": 1.3231408078520197, "percentage": 44.11, "elapsed_time": "21:37:32", "remaining_time": "1 day, 3:24:08", "throughput": 9502.94, "total_tokens": 739827088}
+{"current_steps": 3087, "total_steps": 6951, "loss": 0.208, "lr": 5.873433195443152e-05, "epoch": 1.3322008305020763, "percentage": 44.41, "elapsed_time": "21:46:47", "remaining_time": "1 day, 3:15:42", "throughput": 9499.75, "total_tokens": 744847184}
+{"current_steps": 3108, "total_steps": 6951, "loss": 0.2047, "lr": 5.82666815501964e-05, "epoch": 1.3412608531521328, "percentage": 44.71, "elapsed_time": "21:55:35", "remaining_time": "1 day, 3:06:42", "throughput": 9499.82, "total_tokens": 749874880}
+{"current_steps": 3129, "total_steps": 6951, "loss": 0.2022, "lr": 5.779828646250521e-05, "epoch": 1.3503208758021894, "percentage": 45.02, "elapsed_time": "22:04:30", "remaining_time": "1 day, 2:57:51", "throughput": 9498.47, "total_tokens": 754848400}
+{"current_steps": 3150, "total_steps": 6951, "loss": 0.2073, "lr": 5.7329188885565e-05, "epoch": 1.3593808984522462, "percentage": 45.32, "elapsed_time": "22:14:01", "remaining_time": "1 day, 2:49:43", "throughput": 9494.01, "total_tokens": 759913728}
+{"current_steps": 3171, "total_steps": 6951, "loss": 0.2056, "lr": 5.6859431076864755e-05, "epoch": 1.3684409211023028, "percentage": 45.62, "elapsed_time": "22:23:11", "remaining_time": "1 day, 2:41:09", "throughput": 9492.45, "total_tokens": 765009632}
+{"current_steps": 3192, "total_steps": 6951, "loss": 0.2056, "lr": 5.6389055353368826e-05, "epoch": 1.3775009437523593, "percentage": 45.92, "elapsed_time": "22:31:39", "remaining_time": "1 day, 2:31:44", "throughput": 9494.77, "total_tokens": 770016704}
+{"current_steps": 3213, "total_steps": 6951, "loss": 0.2037, "lr": 5.591810408770493e-05, "epoch": 1.386560966402416, "percentage": 46.22, "elapsed_time": "22:40:44", "remaining_time": "1 day, 2:23:04", "throughput": 9494.81, "total_tokens": 775197264}
+{"current_steps": 3234, "total_steps": 6951, "loss": 0.2042, "lr": 5.544661970434696e-05, "epoch": 1.3956209890524727, "percentage": 46.53, "elapsed_time": "22:49:16", "remaining_time": "1 day, 2:13:46", "throughput": 9496.67, "total_tokens": 780209328}
+{"current_steps": 3255, "total_steps": 6951, "loss": 0.2011, "lr": 5.497464467579351e-05, "epoch": 1.4046810117025292, "percentage": 46.83, "elapsed_time": "22:58:20", "remaining_time": "1 day, 2:05:05", "throughput": 9496.92, "total_tokens": 785402112}
+{"current_steps": 3276, "total_steps": 6951, "loss": 0.2015, "lr": 5.450222151874166e-05, "epoch": 1.4137410343525858, "percentage": 47.13, "elapsed_time": "23:07:23", "remaining_time": "1 day, 1:56:22", "throughput": 9495.35, "total_tokens": 790429216}
+{"current_steps": 3297, "total_steps": 6951, "loss": 0.2005, "lr": 5.402939279025705e-05, "epoch": 1.4228010570026426, "percentage": 47.43, "elapsed_time": "23:16:41", "remaining_time": "1 day, 1:47:56", "throughput": 9493.13, "total_tokens": 795543264}
+{"current_steps": 3318, "total_steps": 6951, "loss": 0.2052, "lr": 5.355620108394018e-05, "epoch": 1.4318610796526992, "percentage": 47.73, "elapsed_time": "23:25:21", "remaining_time": "1 day, 1:38:46", "throughput": 9493.86, "total_tokens": 800533200}
+{"current_steps": 3339, "total_steps": 6951, "loss": 0.2042, "lr": 5.308268902608958e-05, "epoch": 1.4409211023027557, "percentage": 48.04, "elapsed_time": "23:33:57", "remaining_time": "1 day, 1:29:34", "throughput": 9495.07, "total_tokens": 805542720}
+{"current_steps": 3360, "total_steps": 6951, "loss": 0.1984, "lr": 5.2608899271861765e-05, "epoch": 1.4499811249528123, "percentage": 48.34, "elapsed_time": "23:42:55", "remaining_time": "1 day, 1:20:44", "throughput": 9493.99, "total_tokens": 810549376}
+{"current_steps": 3381, "total_steps": 6951, "loss": 0.2038, "lr": 5.213487450142892e-05, "epoch": 1.459041147602869, "percentage": 48.64, "elapsed_time": "23:52:03", "remaining_time": "1 day, 1:12:06", "throughput": 9492.2, "total_tokens": 815599232}
+{"current_steps": 3402, "total_steps": 6951, "loss": 0.2012, "lr": 5.166065741613402e-05, "epoch": 1.4681011702529256, "percentage": 48.94, "elapsed_time": "1 day, 0:01:00", "remaining_time": "1 day, 1:03:16", "throughput": 9492.22, "total_tokens": 820700608}
+{"current_steps": 3423, "total_steps": 6951, "loss": 0.1987, "lr": 5.118629073464424e-05, "epoch": 1.4771611929029822, "percentage": 49.24, "elapsed_time": "1 day, 0:09:40", "remaining_time": "1 day, 0:54:08", "throughput": 9492.76, "total_tokens": 825686176}
+{"current_steps": 3444, "total_steps": 6951, "loss": 0.1986, "lr": 5.071181718910283e-05, "epoch": 1.486221215553039, "percentage": 49.55, "elapsed_time": "1 day, 0:18:43", "remaining_time": "1 day, 0:45:24", "throughput": 9491.54, "total_tokens": 830730000}
+{"current_steps": 3465, "total_steps": 6951, "loss": 0.1987, "lr": 5.023727952127954e-05, "epoch": 1.4952812382030956, "percentage": 49.85, "elapsed_time": "1 day, 0:27:32", "remaining_time": "1 day, 0:36:26", "throughput": 9491.31, "total_tokens": 835738032}
+{"current_steps": 3486, "total_steps": 6951, "loss": 0.1952, "lr": 4.976272047872046e-05, "epoch": 1.5043412608531521, "percentage": 50.15, "elapsed_time": "1 day, 0:36:07", "remaining_time": "1 day, 0:27:14", "throughput": 9493.38, "total_tokens": 840806528}
+{"current_steps": 3507, "total_steps": 6951, "loss": 0.1957, "lr": 4.9288182810897184e-05, "epoch": 1.513401283503209, "percentage": 50.45, "elapsed_time": "1 day, 0:44:53", "remaining_time": "1 day, 0:18:12", "throughput": 9494.32, "total_tokens": 845877808}
+{"current_steps": 3528, "total_steps": 6951, "loss": 0.1957, "lr": 4.8813709265355766e-05, "epoch": 1.5224613061532652, "percentage": 50.76, "elapsed_time": "1 day, 0:53:46", "remaining_time": "1 day, 0:09:18", "throughput": 9495.01, "total_tokens": 851002432}
+{"current_steps": 3549, "total_steps": 6951, "loss": 0.197, "lr": 4.8339342583866005e-05, "epoch": 1.531521328803322, "percentage": 51.06, "elapsed_time": "1 day, 1:02:40", "remaining_time": "1 day, 0:00:26", "throughput": 9494.56, "total_tokens": 856037440}
+{"current_steps": 3570, "total_steps": 6951, "loss": 0.1957, "lr": 4.7865125498571086e-05, "epoch": 1.5405813514533786, "percentage": 51.36, "elapsed_time": "1 day, 1:11:11", "remaining_time": "23:51:11", "throughput": 9495.47, "total_tokens": 860972624}
+{"current_steps": 3591, "total_steps": 6951, "loss": 0.1926, "lr": 4.739110072813823e-05, "epoch": 1.5496413741034352, "percentage": 51.66, "elapsed_time": "1 day, 1:20:00", "remaining_time": "23:42:13", "throughput": 9496.47, "total_tokens": 866078128}
+{"current_steps": 3612, "total_steps": 6951, "loss": 0.1934, "lr": 4.6917310973910425e-05, "epoch": 1.558701396753492, "percentage": 51.96, "elapsed_time": "1 day, 1:29:07", "remaining_time": "23:33:32", "throughput": 9496.66, "total_tokens": 871290720}
+{"current_steps": 3633, "total_steps": 6951, "loss": 0.1961, "lr": 4.6443798916059836e-05, "epoch": 1.5677614194035485, "percentage": 52.27, "elapsed_time": "1 day, 1:38:01", "remaining_time": "23:24:40", "throughput": 9496.52, "total_tokens": 876353920}
+{"current_steps": 3654, "total_steps": 6951, "loss": 0.1902, "lr": 4.597060720974298e-05, "epoch": 1.576821442053605, "percentage": 52.57, "elapsed_time": "1 day, 1:47:05", "remaining_time": "23:15:56", "throughput": 9496.01, "total_tokens": 881469536}
+{"current_steps": 3675, "total_steps": 6951, "loss": 0.1971, "lr": 4.549777848125833e-05, "epoch": 1.5858814647036619, "percentage": 52.87, "elapsed_time": "1 day, 1:56:04", "remaining_time": "23:07:07", "throughput": 9495.37, "total_tokens": 886532048}
+{"current_steps": 3696, "total_steps": 6951, "loss": 0.1952, "lr": 4.50253553242065e-05, "epoch": 1.5949414873537184, "percentage": 53.17, "elapsed_time": "1 day, 2:04:53", "remaining_time": "22:58:10", "throughput": 9495.5, "total_tokens": 891565152}
+{"current_steps": 3717, "total_steps": 6951, "loss": 0.1908, "lr": 4.4553380295653053e-05, "epoch": 1.604001510003775, "percentage": 53.47, "elapsed_time": "1 day, 2:13:32", "remaining_time": "22:49:03", "throughput": 9496.69, "total_tokens": 896603568}
+{"current_steps": 3738, "total_steps": 6951, "loss": 0.1945, "lr": 4.40818959122951e-05, "epoch": 1.6130615326538318, "percentage": 53.78, "elapsed_time": "1 day, 2:22:34", "remaining_time": "22:40:17", "throughput": 9496.2, "total_tokens": 901703264}
+{"current_steps": 3759, "total_steps": 6951, "loss": 0.1911, "lr": 4.361094464663118e-05, "epoch": 1.6221215553038881, "percentage": 54.08, "elapsed_time": "1 day, 2:31:30", "remaining_time": "22:31:27", "throughput": 9496.7, "total_tokens": 906846256}
+{"current_steps": 3780, "total_steps": 6951, "loss": 0.193, "lr": 4.3140568923135264e-05, "epoch": 1.631181577953945, "percentage": 54.38, "elapsed_time": "1 day, 2:40:27", "remaining_time": "22:22:36", "throughput": 9496.86, "total_tokens": 911964272}
+{"current_steps": 3801, "total_steps": 6951, "loss": 0.1898, "lr": 4.267081111443501e-05, "epoch": 1.6402416006040015, "percentage": 54.68, "elapsed_time": "1 day, 2:49:16", "remaining_time": "22:13:39", "throughput": 9498.11, "total_tokens": 917101840}
+{"current_steps": 3822, "total_steps": 6951, "loss": 0.1852, "lr": 4.22017135374948e-05, "epoch": 1.649301623254058, "percentage": 54.98, "elapsed_time": "1 day, 2:57:51", "remaining_time": "22:04:30", "throughput": 9500.27, "total_tokens": 922205664}
+{"current_steps": 3843, "total_steps": 6951, "loss": 0.1863, "lr": 4.1733318449803624e-05, "epoch": 1.6583616459041148, "percentage": 55.29, "elapsed_time": "1 day, 3:06:51", "remaining_time": "21:55:42", "throughput": 9499.96, "total_tokens": 927302560}
+{"current_steps": 3864, "total_steps": 6951, "loss": 0.1882, "lr": 4.1265668045568495e-05, "epoch": 1.6674216685541714, "percentage": 55.59, "elapsed_time": "1 day, 3:15:50", "remaining_time": "21:46:53", "throughput": 9498.96, "total_tokens": 932325424}
+{"current_steps": 3885, "total_steps": 6951, "loss": 0.1893, "lr": 4.079880445191351e-05, "epoch": 1.676481691204228, "percentage": 55.89, "elapsed_time": "1 day, 3:24:37", "remaining_time": "21:37:54", "throughput": 9500.06, "total_tokens": 937438464}
+{"current_steps": 3906, "total_steps": 6951, "loss": 0.1885, "lr": 4.033276972508484e-05, "epoch": 1.6855417138542848, "percentage": 56.19, "elapsed_time": "1 day, 3:33:46", "remaining_time": "21:29:13", "throughput": 9499.68, "total_tokens": 942617840}
+{"current_steps": 3927, "total_steps": 6951, "loss": 0.1883, "lr": 3.9867605846662256e-05, "epoch": 1.6946017365043413, "percentage": 56.5, "elapsed_time": "1 day, 3:42:59", "remaining_time": "21:20:35", "throughput": 9499.21, "total_tokens": 947823200}
+{"current_steps": 3948, "total_steps": 6951, "loss": 0.1871, "lr": 3.940335471977734e-05, "epoch": 1.7036617591543979, "percentage": 56.8, "elapsed_time": "1 day, 3:51:52", "remaining_time": "21:11:41", "throughput": 9499.01, "total_tokens": 952872784}
+{"current_steps": 3969, "total_steps": 6951, "loss": 0.1853, "lr": 3.89400581653387e-05, "epoch": 1.7127217818044547, "percentage": 57.1, "elapsed_time": "1 day, 4:00:45", "remaining_time": "21:02:47", "throughput": 9498.79, "total_tokens": 957908608}
+{"current_steps": 3990, "total_steps": 6951, "loss": 0.1862, "lr": 3.847775791826468e-05, "epoch": 1.721781804454511, "percentage": 57.4, "elapsed_time": "1 day, 4:09:30", "remaining_time": "20:53:47", "throughput": 9499.53, "total_tokens": 962972208}
+{"current_steps": 4011, "total_steps": 6951, "loss": 0.1913, "lr": 3.801649562372371e-05, "epoch": 1.7308418271045678, "percentage": 57.7, "elapsed_time": "1 day, 4:18:34", "remaining_time": "20:45:01", "throughput": 9498.33, "total_tokens": 968020256}
+{"current_steps": 4032, "total_steps": 6951, "loss": 0.1908, "lr": 3.755631283338287e-05, "epoch": 1.7399018497546244, "percentage": 58.01, "elapsed_time": "1 day, 4:27:34", "remaining_time": "20:36:12", "throughput": 9498.07, "total_tokens": 973116912}
+{"current_steps": 4053, "total_steps": 6951, "loss": 0.1839, "lr": 3.709725100166482e-05, "epoch": 1.748961872404681, "percentage": 58.31, "elapsed_time": "1 day, 4:36:56", "remaining_time": "20:27:39", "throughput": 9496.29, "total_tokens": 978276224}
+{"current_steps": 4074, "total_steps": 6951, "loss": 0.1869, "lr": 3.663935148201341e-05, "epoch": 1.7580218950547377, "percentage": 58.61, "elapsed_time": "1 day, 4:46:12", "remaining_time": "20:19:01", "throughput": 9495.72, "total_tokens": 983499184}
+{"current_steps": 4095, "total_steps": 6951, "loss": 0.1884, "lr": 3.618265552316849e-05, "epoch": 1.7670819177047943, "percentage": 58.91, "elapsed_time": "1 day, 4:55:11", "remaining_time": "20:10:11", "throughput": 9494.7, "total_tokens": 988511216}
+{"current_steps": 4116, "total_steps": 6951, "loss": 0.1863, "lr": 3.572720426545017e-05, "epoch": 1.7761419403548508, "percentage": 59.21, "elapsed_time": "1 day, 5:04:24", "remaining_time": "20:01:30", "throughput": 9492.68, "total_tokens": 993542272}
+{"current_steps": 4137, "total_steps": 6951, "loss": 0.1884, "lr": 3.5273038737052675e-05, "epoch": 1.7852019630049076, "percentage": 59.52, "elapsed_time": "1 day, 5:13:02", "remaining_time": "19:52:25", "throughput": 9493.64, "total_tokens": 998561584}
+{"current_steps": 4158, "total_steps": 6951, "loss": 0.1815, "lr": 3.482019985034861e-05, "epoch": 1.794261985654964, "percentage": 59.82, "elapsed_time": "1 day, 5:21:39", "remaining_time": "19:43:19", "throughput": 9494.28, "total_tokens": 1003535696}
+{"current_steps": 4179, "total_steps": 6951, "loss": 0.1798, "lr": 3.43687283982033e-05, "epoch": 1.8033220083050208, "percentage": 60.12, "elapsed_time": "1 day, 5:30:37", "remaining_time": "19:34:29", "throughput": 9493.88, "total_tokens": 1008610432}
+{"current_steps": 4200, "total_steps": 6951, "loss": 0.1797, "lr": 3.391866505030009e-05, "epoch": 1.8123820309550775, "percentage": 60.42, "elapsed_time": "1 day, 5:39:08", "remaining_time": "19:25:20", "throughput": 9495.04, "total_tokens": 1013577840}
+{"current_steps": 4221, "total_steps": 6951, "loss": 0.1773, "lr": 3.347005034947681e-05, "epoch": 1.821442053605134, "percentage": 60.73, "elapsed_time": "1 day, 5:47:48", "remaining_time": "19:16:17", "throughput": 9495.33, "total_tokens": 1018549888}
+{"current_steps": 4242, "total_steps": 6951, "loss": 0.1828, "lr": 3.3022924708073524e-05, "epoch": 1.8305020762551907, "percentage": 61.03, "elapsed_time": "1 day, 5:56:40", "remaining_time": "19:07:23", "throughput": 9494.34, "total_tokens": 1023498368}
+{"current_steps": 4263, "total_steps": 6951, "loss": 0.18, "lr": 3.257732840429206e-05, "epoch": 1.8395620989052472, "percentage": 61.33, "elapsed_time": "1 day, 6:05:35", "remaining_time": "18:58:30", "throughput": 9494.06, "total_tokens": 1028542992}
+{"current_steps": 4284, "total_steps": 6951, "loss": 0.1825, "lr": 3.2133301578567646e-05, "epoch": 1.8486221215553038, "percentage": 61.63, "elapsed_time": "1 day, 6:14:31", "remaining_time": "18:49:37", "throughput": 9493.51, "total_tokens": 1033574288}
+{"current_steps": 4305, "total_steps": 6951, "loss": 0.1776, "lr": 3.169088422995304e-05, "epoch": 1.8576821442053606, "percentage": 61.93, "elapsed_time": "1 day, 6:23:27", "remaining_time": "18:40:45", "throughput": 9493.01, "total_tokens": 1038606208}
+{"current_steps": 4326, "total_steps": 6951, "loss": 0.1768, "lr": 3.125011621251516e-05, "epoch": 1.8667421668554172, "percentage": 62.24, "elapsed_time": "1 day, 6:32:31", "remaining_time": "18:31:57", "throughput": 9493.04, "total_tokens": 1043770704}
+{"current_steps": 4347, "total_steps": 6951, "loss": 0.1778, "lr": 3.081103723174515e-05, "epoch": 1.8758021895054737, "percentage": 62.54, "elapsed_time": "1 day, 6:41:34", "remaining_time": "18:23:09", "throughput": 9492.18, "total_tokens": 1048829664}
+{"current_steps": 4368, "total_steps": 6951, "loss": 0.1788, "lr": 3.0373686840981397e-05, "epoch": 1.8848622121555305, "percentage": 62.84, "elapsed_time": "1 day, 6:50:45", "remaining_time": "18:14:26", "throughput": 9491.15, "total_tokens": 1053950224}
+{"current_steps": 4389, "total_steps": 6951, "loss": 0.176, "lr": 2.9938104437846572e-05, "epoch": 1.8939222348055869, "percentage": 63.14, "elapsed_time": "1 day, 6:59:56", "remaining_time": "18:05:42", "throughput": 9490.66, "total_tokens": 1059119888}
+{"current_steps": 4410, "total_steps": 6951, "loss": 0.1783, "lr": 2.950432926069857e-05, "epoch": 1.9029822574556436, "percentage": 63.44, "elapsed_time": "1 day, 7:08:56", "remaining_time": "17:56:52", "throughput": 9490.01, "total_tokens": 1064177088}
+{"current_steps": 4431, "total_steps": 6951, "loss": 0.178, "lr": 2.9072400385095865e-05, "epoch": 1.9120422801057002, "percentage": 63.75, "elapsed_time": "1 day, 7:18:02", "remaining_time": "17:48:05", "throughput": 9488.58, "total_tokens": 1069200928}
+{"current_steps": 4452, "total_steps": 6951, "loss": 0.1759, "lr": 2.864235672027741e-05, "epoch": 1.9211023027557568, "percentage": 64.05, "elapsed_time": "1 day, 7:27:05", "remaining_time": "17:39:15", "throughput": 9488.29, "total_tokens": 1074313840}
+{"current_steps": 4473, "total_steps": 6951, "loss": 0.1769, "lr": 2.8214237005657627e-05, "epoch": 1.9301623254058136, "percentage": 64.35, "elapsed_time": "1 day, 7:36:04", "remaining_time": "17:30:24", "throughput": 9487.56, "total_tokens": 1079348080}
+{"current_steps": 4494, "total_steps": 6951, "loss": 0.1761, "lr": 2.7788079807336692e-05, "epoch": 1.9392223480558701, "percentage": 64.65, "elapsed_time": "1 day, 7:44:52", "remaining_time": "17:21:26", "throughput": 9488.08, "total_tokens": 1084415072}
+{"current_steps": 4515, "total_steps": 6951, "loss": 0.1762, "lr": 2.7363923514626367e-05, "epoch": 1.9482823707059267, "percentage": 64.95, "elapsed_time": "1 day, 7:53:50", "remaining_time": "17:12:35", "throughput": 9488.56, "total_tokens": 1089576528}
+{"current_steps": 4536, "total_steps": 6951, "loss": 0.1715, "lr": 2.6941806336591808e-05, "epoch": 1.9573423933559835, "percentage": 65.26, "elapsed_time": "1 day, 8:02:49", "remaining_time": "17:03:43", "throughput": 9489.02, "total_tokens": 1094741664}
+{"current_steps": 4557, "total_steps": 6951, "loss": 0.1728, "lr": 2.6521766298609584e-05, "epoch": 1.96640241600604, "percentage": 65.56, "elapsed_time": "1 day, 8:11:24", "remaining_time": "16:54:39", "throughput": 9489.67, "total_tokens": 1099708896}
+{"current_steps": 4578, "total_steps": 6951, "loss": 0.175, "lr": 2.610384123894229e-05, "epoch": 1.9754624386560966, "percentage": 65.86, "elapsed_time": "1 day, 8:20:35", "remaining_time": "16:45:54", "throughput": 9488.69, "total_tokens": 1104824512}
+{"current_steps": 4599, "total_steps": 6951, "loss": 0.1736, "lr": 2.568806880532991e-05, "epoch": 1.9845224613061534, "percentage": 66.16, "elapsed_time": "1 day, 8:29:26", "remaining_time": "16:36:58", "throughput": 9489.47, "total_tokens": 1109954160}
+{"current_steps": 4620, "total_steps": 6951, "loss": 0.1704, "lr": 2.5274486451598565e-05, "epoch": 1.9935824839562097, "percentage": 66.47, "elapsed_time": "1 day, 8:38:34", "remaining_time": "16:28:11", "throughput": 9489.29, "total_tokens": 1115130992}
+{"current_steps": 4641, "total_steps": 6951, "loss": 0.1548, "lr": 2.4863131434286342e-05, "epoch": 2.003020007550019, "percentage": 66.77, "elapsed_time": "1 day, 8:47:29", "remaining_time": "16:19:17", "throughput": 9490.07, "total_tokens": 1120294784}
+{"current_steps": 4662, "total_steps": 6951, "loss": 0.1188, "lr": 2.4454040809287342e-05, "epoch": 2.0120800302000754, "percentage": 67.07, "elapsed_time": "1 day, 8:56:29", "remaining_time": "16:10:26", "throughput": 9489.7, "total_tokens": 1125375728}
+{"current_steps": 4683, "total_steps": 6951, "loss": 0.1176, "lr": 2.4047251428513485e-05, "epoch": 2.021140052850132, "percentage": 67.37, "elapsed_time": "1 day, 9:05:40", "remaining_time": "16:01:40", "throughput": 9490.21, "total_tokens": 1130663488}
+{"current_steps": 4704, "total_steps": 6951, "loss": 0.1166, "lr": 2.364279993657487e-05, "epoch": 2.0302000755001886, "percentage": 67.67, "elapsed_time": "1 day, 9:14:37", "remaining_time": "15:52:47", "throughput": 9489.93, "total_tokens": 1135729856}
+{"current_steps": 4725, "total_steps": 6951, "loss": 0.1129, "lr": 2.3240722767478657e-05, "epoch": 2.0392600981502453, "percentage": 67.98, "elapsed_time": "1 day, 9:23:32", "remaining_time": "15:43:53", "throughput": 9489.27, "total_tokens": 1140728768}
+{"current_steps": 4746, "total_steps": 6951, "loss": 0.1122, "lr": 2.2841056141347038e-05, "epoch": 2.048320120800302, "percentage": 68.28, "elapsed_time": "1 day, 9:32:17", "remaining_time": "15:34:54", "throughput": 9490.08, "total_tokens": 1145810672}
+{"current_steps": 4767, "total_steps": 6951, "loss": 0.1145, "lr": 2.2443836061154415e-05, "epoch": 2.0573801434503585, "percentage": 68.58, "elapsed_time": "1 day, 9:41:09", "remaining_time": "15:25:59", "throughput": 9490.09, "total_tokens": 1150862064}
+{"current_steps": 4788, "total_steps": 6951, "loss": 0.1153, "lr": 2.2049098309484195e-05, "epoch": 2.0664401661004153, "percentage": 68.88, "elapsed_time": "1 day, 9:50:04", "remaining_time": "15:17:05", "throughput": 9490.25, "total_tokens": 1155954544}
+{"current_steps": 4809, "total_steps": 6951, "loss": 0.1152, "lr": 2.1656878445305447e-05, "epoch": 2.075500188750472, "percentage": 69.18, "elapsed_time": "1 day, 9:59:12", "remaining_time": "15:08:17", "throughput": 9489.42, "total_tokens": 1161054256}
+{"current_steps": 4830, "total_steps": 6951, "loss": 0.1148, "lr": 2.1267211800769528e-05, "epoch": 2.0845602114005284, "percentage": 69.49, "elapsed_time": "1 day, 10:07:55", "remaining_time": "14:59:18", "throughput": 9489.77, "total_tokens": 1166056688}
+{"current_steps": 4851, "total_steps": 6951, "loss": 0.1119, "lr": 2.088013347802738e-05, "epoch": 2.093620234050585, "percentage": 69.79, "elapsed_time": "1 day, 10:17:16", "remaining_time": "14:50:35", "throughput": 9488.55, "total_tokens": 1171231104}
+{"current_steps": 4872, "total_steps": 6951, "loss": 0.1101, "lr": 2.0495678346067414e-05, "epoch": 2.102680256700642, "percentage": 70.09, "elapsed_time": "1 day, 10:26:21", "remaining_time": "14:41:45", "throughput": 9487.59, "total_tokens": 1176284976}
+{"current_steps": 4893, "total_steps": 6951, "loss": 0.1139, "lr": 2.011388103757442e-05, "epoch": 2.1117402793506983, "percentage": 70.39, "elapsed_time": "1 day, 10:35:22", "remaining_time": "14:32:54", "throughput": 9487.45, "total_tokens": 1181400944}
+{"current_steps": 4914, "total_steps": 6951, "loss": 0.1116, "lr": 1.973477594580977e-05, "epoch": 2.120800302000755, "percentage": 70.69, "elapsed_time": "1 day, 10:43:54", "remaining_time": "14:23:50", "throughput": 9489.64, "total_tokens": 1186527776}
+{"current_steps": 4935, "total_steps": 6951, "loss": 0.112, "lr": 1.9358397221513176e-05, "epoch": 2.1298603246508114, "percentage": 71.0, "elapsed_time": "1 day, 10:53:02", "remaining_time": "14:15:01", "throughput": 9489.09, "total_tokens": 1191661680}
+{"current_steps": 4956, "total_steps": 6951, "loss": 0.1106, "lr": 1.8984778769826316e-05, "epoch": 2.138920347300868, "percentage": 71.3, "elapsed_time": "1 day, 11:02:03", "remaining_time": "14:06:10", "throughput": 9488.78, "total_tokens": 1196759648}
+{"current_steps": 4977, "total_steps": 6951, "loss": 0.1124, "lr": 1.8613954247238586e-05, "epoch": 2.147980369950925, "percentage": 71.6, "elapsed_time": "1 day, 11:11:03", "remaining_time": "13:57:17", "throughput": 9488.59, "total_tokens": 1201857104}
+{"current_steps": 4998, "total_steps": 6951, "loss": 0.1136, "lr": 1.82459570585552e-05, "epoch": 2.1570403926009813, "percentage": 71.9, "elapsed_time": "1 day, 11:19:54", "remaining_time": "13:48:22", "throughput": 9488.83, "total_tokens": 1206927520}
+{"current_steps": 5000, "total_steps": 6951, "eval_loss": 0.19485081732273102, "epoch": 2.157903251900987, "percentage": 71.93, "elapsed_time": "1 day, 11:29:30", "remaining_time": "13:50:56", "throughput": 9449.62, "total_tokens": 1207385424}
+{"current_steps": 5019, "total_steps": 6951, "loss": 0.1102, "lr": 1.7880820353888056e-05, "epoch": 2.166100415251038, "percentage": 72.21, "elapsed_time": "1 day, 11:49:54", "remaining_time": "13:47:34", "throughput": 9394.81, "total_tokens": 1211875824}
+{"current_steps": 5040, "total_steps": 6951, "loss": 0.113, "lr": 1.751857702566944e-05, "epoch": 2.175160437901095, "percentage": 72.51, "elapsed_time": "1 day, 11:58:57", "remaining_time": "13:38:36", "throughput": 9394.59, "total_tokens": 1216954688}
+{"current_steps": 5061, "total_steps": 6951, "loss": 0.1104, "lr": 1.7159259705689e-05, "epoch": 2.1842204605511513, "percentage": 72.81, "elapsed_time": "1 day, 12:07:48", "remaining_time": "13:29:33", "throughput": 9394.84, "total_tokens": 1221976560}
+{"current_steps": 5082, "total_steps": 6951, "loss": 0.1152, "lr": 1.6802900762154267e-05, "epoch": 2.193280483201208, "percentage": 73.11, "elapsed_time": "1 day, 12:16:35", "remaining_time": "13:20:29", "throughput": 9395.21, "total_tokens": 1226975776}
+{"current_steps": 5103, "total_steps": 6951, "loss": 0.1097, "lr": 1.644953229677474e-05, "epoch": 2.2023405058512644, "percentage": 73.41, "elapsed_time": "1 day, 12:25:12", "remaining_time": "13:11:21", "throughput": 9396.5, "total_tokens": 1231998784}
+{"current_steps": 5124, "total_steps": 6951, "loss": 0.1111, "lr": 1.609918614187009e-05, "epoch": 2.211400528501321, "percentage": 73.72, "elapsed_time": "1 day, 12:34:03", "remaining_time": "13:02:18", "throughput": 9396.54, "total_tokens": 1236990864}
+{"current_steps": 5145, "total_steps": 6951, "loss": 0.1104, "lr": 1.575189385750271e-05, "epoch": 2.220460551151378, "percentage": 74.02, "elapsed_time": "1 day, 12:42:57", "remaining_time": "12:53:17", "throughput": 9396.81, "total_tokens": 1242051280}
+{"current_steps": 5166, "total_steps": 6951, "loss": 0.1075, "lr": 1.540768672863468e-05, "epoch": 2.2295205738014343, "percentage": 74.32, "elapsed_time": "1 day, 12:51:51", "remaining_time": "12:44:15", "throughput": 9397.25, "total_tokens": 1247127040}
+{"current_steps": 5187, "total_steps": 6951, "loss": 0.1093, "lr": 1.5066595762309477e-05, "epoch": 2.238580596451491, "percentage": 74.62, "elapsed_time": "1 day, 13:00:47", "remaining_time": "12:35:14", "throughput": 9397.23, "total_tokens": 1252158672}
+{"current_steps": 5208, "total_steps": 6951, "loss": 0.1126, "lr": 1.4728651684858834e-05, "epoch": 2.247640619101548, "percentage": 74.92, "elapsed_time": "1 day, 13:09:50", "remaining_time": "12:26:16", "throughput": 9397.67, "total_tokens": 1257321184}
+{"current_steps": 5229, "total_steps": 6951, "loss": 0.1064, "lr": 1.4393884939134833e-05, "epoch": 2.2567006417516042, "percentage": 75.23, "elapsed_time": "1 day, 13:18:33", "remaining_time": "12:17:11", "throughput": 9398.27, "total_tokens": 1262315984}
+{"current_steps": 5250, "total_steps": 6951, "loss": 0.1096, "lr": 1.4062325681767469e-05, "epoch": 2.265760664401661, "percentage": 75.53, "elapsed_time": "1 day, 13:27:25", "remaining_time": "12:08:10", "throughput": 9398.52, "total_tokens": 1267351616}
+{"current_steps": 5271, "total_steps": 6951, "loss": 0.1089, "lr": 1.3734003780448218e-05, "epoch": 2.274820687051718, "percentage": 75.83, "elapsed_time": "1 day, 13:36:22", "remaining_time": "11:59:09", "throughput": 9398.21, "total_tokens": 1272350592}
+{"current_steps": 5292, "total_steps": 6951, "loss": 0.1093, "lr": 1.340894881123932e-05, "epoch": 2.283880709701774, "percentage": 76.13, "elapsed_time": "1 day, 13:44:45", "remaining_time": "11:49:58", "throughput": 9399.94, "total_tokens": 1277314160}
+{"current_steps": 5313, "total_steps": 6951, "loss": 0.1064, "lr": 1.308719005590957e-05, "epoch": 2.292940732351831, "percentage": 76.44, "elapsed_time": "1 day, 13:53:34", "remaining_time": "11:40:56", "throughput": 9400.36, "total_tokens": 1282348896}
+{"current_steps": 5334, "total_steps": 6951, "loss": 0.1103, "lr": 1.276875649929654e-05, "epoch": 2.3020007550018873, "percentage": 76.74, "elapsed_time": "1 day, 14:02:35", "remaining_time": "11:31:58", "throughput": 9400.86, "total_tokens": 1287503120}
+{"current_steps": 5355, "total_steps": 6951, "loss": 0.1077, "lr": 1.2453676826695532e-05, "epoch": 2.311060777651944, "percentage": 77.04, "elapsed_time": "1 day, 14:11:17", "remaining_time": "11:22:53", "throughput": 9401.43, "total_tokens": 1292488224}
+{"current_steps": 5376, "total_steps": 6951, "loss": 0.1051, "lr": 1.2141979421275545e-05, "epoch": 2.320120800302001, "percentage": 77.34, "elapsed_time": "1 day, 14:20:08", "remaining_time": "11:13:52", "throughput": 9402.42, "total_tokens": 1297613792}
+{"current_steps": 5397, "total_steps": 6951, "loss": 0.1063, "lr": 1.1833692361522459e-05, "epoch": 2.329180822952057, "percentage": 77.64, "elapsed_time": "1 day, 14:29:19", "remaining_time": "11:04:56", "throughput": 9402.19, "total_tokens": 1302765200}
+{"current_steps": 5418, "total_steps": 6951, "loss": 0.1073, "lr": 1.1528843418709622e-05, "epoch": 2.338240845602114, "percentage": 77.95, "elapsed_time": "1 day, 14:38:06", "remaining_time": "10:55:53", "throughput": 9402.65, "total_tokens": 1307780896}
+{"current_steps": 5439, "total_steps": 6951, "loss": 0.1076, "lr": 1.1227460054396177e-05, "epoch": 2.3473008682521708, "percentage": 78.25, "elapsed_time": "1 day, 14:47:09", "remaining_time": "10:46:55", "throughput": 9402.88, "total_tokens": 1312916864}
+{"current_steps": 5460, "total_steps": 6951, "loss": 0.1049, "lr": 1.0929569417953278e-05, "epoch": 2.356360890902227, "percentage": 78.55, "elapsed_time": "1 day, 14:55:45", "remaining_time": "10:37:50", "throughput": 9403.97, "total_tokens": 1317924528}
+{"current_steps": 5481, "total_steps": 6951, "loss": 0.1038, "lr": 1.0635198344118296e-05, "epoch": 2.365420913552284, "percentage": 78.85, "elapsed_time": "1 day, 15:04:24", "remaining_time": "10:28:46", "throughput": 9404.57, "total_tokens": 1322892896}
+{"current_steps": 5502, "total_steps": 6951, "loss": 0.1049, "lr": 1.034437335057762e-05, "epoch": 2.3744809362023407, "percentage": 79.15, "elapsed_time": "1 day, 15:13:27", "remaining_time": "10:19:48", "throughput": 9404.62, "total_tokens": 1328000960}
+{"current_steps": 5523, "total_steps": 6951, "loss": 0.1026, "lr": 1.005712063557776e-05, "epoch": 2.383540958852397, "percentage": 79.46, "elapsed_time": "1 day, 15:22:31", "remaining_time": "10:10:50", "throughput": 9404.53, "total_tokens": 1333104928}
+{"current_steps": 5544, "total_steps": 6951, "loss": 0.1061, "lr": 9.773466075565457e-06, "epoch": 2.392600981502454, "percentage": 79.76, "elapsed_time": "1 day, 15:31:14", "remaining_time": "10:01:47", "throughput": 9405.0, "total_tokens": 1338094928}
+{"current_steps": 5565, "total_steps": 6951, "loss": 0.1078, "lr": 9.493435222856556e-06, "epoch": 2.40166100415251, "percentage": 80.06, "elapsed_time": "1 day, 15:39:56", "remaining_time": "9:52:44", "throughput": 9405.66, "total_tokens": 1343094352}
+{"current_steps": 5586, "total_steps": 6951, "loss": 0.1021, "lr": 9.21705330333426e-06, "epoch": 2.410721026802567, "percentage": 80.36, "elapsed_time": "1 day, 15:49:17", "remaining_time": "9:43:50", "throughput": 9404.52, "total_tokens": 1348209008}
+{"current_steps": 5607, "total_steps": 6951, "loss": 0.105, "lr": 8.944345214176675e-06, "epoch": 2.4197810494526237, "percentage": 80.66, "elapsed_time": "1 day, 15:58:21", "remaining_time": "9:34:53", "throughput": 9404.23, "total_tokens": 1353281712}
+{"current_steps": 5628, "total_steps": 6951, "loss": 0.1039, "lr": 8.675335521614036e-06, "epoch": 2.42884107210268, "percentage": 80.97, "elapsed_time": "1 day, 16:07:19", "remaining_time": "9:25:54", "throughput": 9404.1, "total_tokens": 1358325728}
+{"current_steps": 5649, "total_steps": 6951, "loss": 0.1026, "lr": 8.410048458715763e-06, "epoch": 2.437901094752737, "percentage": 81.27, "elapsed_time": "1 day, 16:16:00", "remaining_time": "9:16:50", "throughput": 9404.46, "total_tokens": 1363274864}
+{"current_steps": 5670, "total_steps": 6951, "loss": 0.1046, "lr": 8.148507923207377e-06, "epoch": 2.4469611174027937, "percentage": 81.57, "elapsed_time": "1 day, 16:24:54", "remaining_time": "9:07:50", "throughput": 9405.18, "total_tokens": 1368398176}
+{"current_steps": 5691, "total_steps": 6951, "loss": 0.1062, "lr": 7.890737475317817e-06, "epoch": 2.45602114005285, "percentage": 81.87, "elapsed_time": "1 day, 16:33:40", "remaining_time": "8:58:49", "throughput": 9405.68, "total_tokens": 1373421664}
+{"current_steps": 5712, "total_steps": 6951, "loss": 0.1005, "lr": 7.636760335657056e-06, "epoch": 2.465081162702907, "percentage": 82.18, "elapsed_time": "1 day, 16:42:05", "remaining_time": "8:49:43", "throughput": 9407.14, "total_tokens": 1378386688}
+{"current_steps": 5733, "total_steps": 6951, "loss": 0.1008, "lr": 7.38659938312432e-06, "epoch": 2.4741411853529636, "percentage": 82.48, "elapsed_time": "1 day, 16:51:02", "remaining_time": "8:40:43", "throughput": 9407.69, "total_tokens": 1383515360}
+{"current_steps": 5754, "total_steps": 6951, "loss": 0.1012, "lr": 7.140277152847103e-06, "epoch": 2.48320120800302, "percentage": 82.78, "elapsed_time": "1 day, 17:00:07", "remaining_time": "8:31:46", "throughput": 9407.74, "total_tokens": 1388651712}
+{"current_steps": 5775, "total_steps": 6951, "loss": 0.1004, "lr": 6.89781583415115e-06, "epoch": 2.4922612306530767, "percentage": 83.08, "elapsed_time": "1 day, 17:08:58", "remaining_time": "8:22:46", "throughput": 9408.87, "total_tokens": 1393819168}
+{"current_steps": 5796, "total_steps": 6951, "loss": 0.1058, "lr": 6.659237268561569e-06, "epoch": 2.501321253303133, "percentage": 83.38, "elapsed_time": "1 day, 17:18:05", "remaining_time": "8:13:49", "throughput": 9409.14, "total_tokens": 1399005008}
+{"current_steps": 5817, "total_steps": 6951, "loss": 0.0996, "lr": 6.424562947835367e-06, "epoch": 2.51038127595319, "percentage": 83.69, "elapsed_time": "1 day, 17:26:42", "remaining_time": "8:04:46", "throughput": 9410.56, "total_tokens": 1404075040}
+{"current_steps": 5838, "total_steps": 6951, "loss": 0.098, "lr": 6.193814012025278e-06, "epoch": 2.5194412986032466, "percentage": 83.99, "elapsed_time": "1 day, 17:35:31", "remaining_time": "7:55:45", "throughput": 9411.15, "total_tokens": 1409145760}
+{"current_steps": 5859, "total_steps": 6951, "loss": 0.1053, "lr": 5.967011247575532e-06, "epoch": 2.5285013212533034, "percentage": 84.29, "elapsed_time": "1 day, 17:44:21", "remaining_time": "7:46:45", "throughput": 9411.73, "total_tokens": 1414225568}
+{"current_steps": 5880, "total_steps": 6951, "loss": 0.1021, "lr": 5.744175085449338e-06, "epoch": 2.5375613439033597, "percentage": 84.59, "elapsed_time": "1 day, 17:53:13", "remaining_time": "7:37:45", "throughput": 9412.46, "total_tokens": 1419339216}
+{"current_steps": 5901, "total_steps": 6951, "loss": 0.1003, "lr": 5.525325599288356e-06, "epoch": 2.5466213665534165, "percentage": 84.89, "elapsed_time": "1 day, 18:01:57", "remaining_time": "7:28:44", "throughput": 9413.49, "total_tokens": 1424423024}
+{"current_steps": 5922, "total_steps": 6951, "loss": 0.1039, "lr": 5.310482503604497e-06, "epoch": 2.555681389203473, "percentage": 85.2, "elapsed_time": "1 day, 18:10:34", "remaining_time": "7:19:42", "throughput": 9413.93, "total_tokens": 1429360512}
+{"current_steps": 5943, "total_steps": 6951, "loss": 0.1034, "lr": 5.09966515200393e-06, "epoch": 2.5647414118535297, "percentage": 85.5, "elapsed_time": "1 day, 18:19:20", "remaining_time": "7:10:42", "throughput": 9414.81, "total_tokens": 1434443216}
+{"current_steps": 5964, "total_steps": 6951, "loss": 0.1025, "lr": 4.892892535443655e-06, "epoch": 2.5738014345035864, "percentage": 85.8, "elapsed_time": "1 day, 18:28:29", "remaining_time": "7:01:45", "throughput": 9415.33, "total_tokens": 1439693152}
+{"current_steps": 5985, "total_steps": 6951, "loss": 0.1041, "lr": 4.690183280520777e-06, "epoch": 2.582861457153643, "percentage": 86.1, "elapsed_time": "1 day, 18:37:21", "remaining_time": "6:52:45", "throughput": 9415.61, "total_tokens": 1444742640}
+{"current_steps": 6006, "total_steps": 6951, "loss": 0.1035, "lr": 4.491555647794609e-06, "epoch": 2.5919214798036996, "percentage": 86.4, "elapsed_time": "1 day, 18:46:26", "remaining_time": "6:43:48", "throughput": 9415.24, "total_tokens": 1449817024}
+{"current_steps": 6027, "total_steps": 6951, "loss": 0.102, "lr": 4.297027530141634e-06, "epoch": 2.600981502453756, "percentage": 86.71, "elapsed_time": "1 day, 18:55:28", "remaining_time": "6:34:50", "throughput": 9415.55, "total_tokens": 1454966656}
+{"current_steps": 6048, "total_steps": 6951, "loss": 0.0968, "lr": 4.106616451143719e-06, "epoch": 2.6100415251038127, "percentage": 87.01, "elapsed_time": "1 day, 19:04:14", "remaining_time": "6:25:50", "throughput": 9416.74, "total_tokens": 1460107904}
+{"current_steps": 6069, "total_steps": 6951, "loss": 0.1025, "lr": 3.9203395635095615e-06, "epoch": 2.6191015477538695, "percentage": 87.31, "elapsed_time": "1 day, 19:13:33", "remaining_time": "6:16:55", "throughput": 9416.5, "total_tokens": 1465329712}
+{"current_steps": 6090, "total_steps": 6951, "loss": 0.0992, "lr": 3.7382136475294592e-06, "epoch": 2.6281615704039263, "percentage": 87.61, "elapsed_time": "1 day, 19:22:32", "remaining_time": "6:07:56", "throughput": 9417.01, "total_tokens": 1470486400}
+{"current_steps": 6111, "total_steps": 6951, "loss": 0.1014, "lr": 3.5602551095638094e-06, "epoch": 2.6372215930539826, "percentage": 87.92, "elapsed_time": "1 day, 19:31:14", "remaining_time": "5:58:56", "throughput": 9417.49, "total_tokens": 1475481216}
+{"current_steps": 6132, "total_steps": 6951, "loss": 0.097, "lr": 3.386479980565077e-06, "epoch": 2.6462816157040394, "percentage": 88.22, "elapsed_time": "1 day, 19:40:20", "remaining_time": "5:49:58", "throughput": 9416.8, "total_tokens": 1480509520}
+{"current_steps": 6153, "total_steps": 6951, "loss": 0.1011, "lr": 3.2169039146337455e-06, "epoch": 2.6553416383540958, "percentage": 88.52, "elapsed_time": "1 day, 19:48:47", "remaining_time": "5:40:56", "throughput": 9417.61, "total_tokens": 1485415168}
+{"current_steps": 6174, "total_steps": 6951, "loss": 0.1003, "lr": 3.0515421876081364e-06, "epoch": 2.6644016610041525, "percentage": 88.82, "elapsed_time": "1 day, 19:57:43", "remaining_time": "5:31:57", "throughput": 9418.35, "total_tokens": 1490580288}
+{"current_steps": 6195, "total_steps": 6951, "loss": 0.1011, "lr": 2.8904096956883396e-06, "epoch": 2.6734616836542093, "percentage": 89.12, "elapsed_time": "1 day, 20:06:34", "remaining_time": "5:22:58", "throughput": 9419.24, "total_tokens": 1495724928}
+{"current_steps": 6216, "total_steps": 6951, "loss": 0.0992, "lr": 2.733520954094304e-06, "epoch": 2.6825217063042657, "percentage": 89.43, "elapsed_time": "1 day, 20:15:26", "remaining_time": "5:13:59", "throughput": 9418.86, "total_tokens": 1500671568}
+{"current_steps": 6237, "total_steps": 6951, "loss": 0.0985, "lr": 2.580890095758276e-06, "epoch": 2.6915817289543225, "percentage": 89.73, "elapsed_time": "1 day, 20:24:26", "remaining_time": "5:05:01", "throughput": 9418.72, "total_tokens": 1505736848}
+{"current_steps": 6258, "total_steps": 6951, "loss": 0.0999, "lr": 2.4325308700516804e-06, "epoch": 2.700641751604379, "percentage": 90.03, "elapsed_time": "1 day, 20:33:16", "remaining_time": "4:56:01", "throughput": 9419.01, "total_tokens": 1510772384}
+{"current_steps": 6279, "total_steps": 6951, "loss": 0.1015, "lr": 2.288456641546549e-06, "epoch": 2.7097017742544356, "percentage": 90.33, "elapsed_time": "1 day, 20:42:09", "remaining_time": "4:47:03", "throughput": 9419.26, "total_tokens": 1515840336}
+{"current_steps": 6300, "total_steps": 6951, "loss": 0.0952, "lr": 2.1486803888115802e-06, "epoch": 2.7187617969044924, "percentage": 90.63, "elapsed_time": "1 day, 20:51:02", "remaining_time": "4:38:04", "throughput": 9418.88, "total_tokens": 1520795728}
+{"current_steps": 6321, "total_steps": 6951, "loss": 0.1014, "lr": 2.013214703242994e-06, "epoch": 2.7278218195545487, "percentage": 90.94, "elapsed_time": "1 day, 21:00:04", "remaining_time": "4:29:06", "throughput": 9418.79, "total_tokens": 1525885232}
+{"current_steps": 6342, "total_steps": 6951, "loss": 0.0962, "lr": 1.8820717879303175e-06, "epoch": 2.7368818422046055, "percentage": 91.24, "elapsed_time": "1 day, 21:09:18", "remaining_time": "4:20:09", "throughput": 9418.29, "total_tokens": 1531020736}
+{"current_steps": 6363, "total_steps": 6951, "loss": 0.0984, "lr": 1.7552634565570325e-06, "epoch": 2.7459418648546623, "percentage": 91.54, "elapsed_time": "1 day, 21:18:27", "remaining_time": "4:11:12", "throughput": 9417.96, "total_tokens": 1536139280}
+{"current_steps": 6384, "total_steps": 6951, "loss": 0.0996, "lr": 1.6328011323364313e-06, "epoch": 2.7550018875047186, "percentage": 91.84, "elapsed_time": "1 day, 21:26:59", "remaining_time": "4:02:12", "throughput": 9418.9, "total_tokens": 1541119392}
+{"current_steps": 6405, "total_steps": 6951, "loss": 0.098, "lr": 1.5146958469825445e-06, "epoch": 2.7640619101547754, "percentage": 92.15, "elapsed_time": "1 day, 21:35:40", "remaining_time": "3:53:12", "throughput": 9419.8, "total_tokens": 1546172016}
+{"current_steps": 6426, "total_steps": 6951, "loss": 0.0979, "lr": 1.4009582397163879e-06, "epoch": 2.773121932804832, "percentage": 92.45, "elapsed_time": "1 day, 21:45:02", "remaining_time": "3:44:16", "throughput": 9419.54, "total_tokens": 1551424800}
+{"current_steps": 6447, "total_steps": 6951, "loss": 0.096, "lr": 1.2915985563075383e-06, "epoch": 2.7821819554548886, "percentage": 92.75, "elapsed_time": "1 day, 21:54:06", "remaining_time": "3:35:18", "throughput": 9419.3, "total_tokens": 1556510032}
+{"current_steps": 6468, "total_steps": 6951, "loss": 0.0995, "lr": 1.1866266481512234e-06, "epoch": 2.7912419781049453, "percentage": 93.05, "elapsed_time": "1 day, 22:02:47", "remaining_time": "3:26:18", "throughput": 9419.37, "total_tokens": 1561425840}
+{"current_steps": 6489, "total_steps": 6951, "loss": 0.0979, "lr": 1.0860519713808082e-06, "epoch": 2.8003020007550017, "percentage": 93.35, "elapsed_time": "1 day, 22:11:35", "remaining_time": "3:17:19", "throughput": 9419.58, "total_tokens": 1566437584}
+{"current_steps": 6510, "total_steps": 6951, "loss": 0.0944, "lr": 9.898835860160271e-07, "epoch": 2.8093620234050585, "percentage": 93.66, "elapsed_time": "1 day, 22:20:25", "remaining_time": "3:08:21", "throughput": 9419.64, "total_tokens": 1571433728}
+{"current_steps": 6531, "total_steps": 6951, "loss": 0.0949, "lr": 8.981301551467924e-07, "epoch": 2.8184220460551153, "percentage": 93.96, "elapsed_time": "1 day, 22:29:09", "remaining_time": "2:59:22", "throughput": 9420.47, "total_tokens": 1576510304}
+{"current_steps": 6552, "total_steps": 6951, "loss": 0.0959, "lr": 8.10799944152818e-07, "epoch": 2.8274820687051716, "percentage": 94.26, "elapsed_time": "1 day, 22:38:19", "remaining_time": "2:50:24", "throughput": 9420.22, "total_tokens": 1581652480}
+{"current_steps": 6573, "total_steps": 6951, "loss": 0.0995, "lr": 7.279008199590543e-07, "epoch": 2.8365420913552284, "percentage": 94.56, "elapsed_time": "1 day, 22:47:15", "remaining_time": "2:41:26", "throughput": 9420.29, "total_tokens": 1586710928}
+{"current_steps": 6594, "total_steps": 6951, "loss": 0.0973, "lr": 6.494402503270158e-07, "epoch": 2.845602114005285, "percentage": 94.86, "elapsed_time": "1 day, 22:55:54", "remaining_time": "2:32:27", "throughput": 9421.16, "total_tokens": 1591751872}
+{"current_steps": 6615, "total_steps": 6951, "loss": 0.0992, "lr": 5.754253031820588e-07, "epoch": 2.8546621366553415, "percentage": 95.17, "elapsed_time": "1 day, 23:04:46", "remaining_time": "2:23:28", "throughput": 9421.5, "total_tokens": 1596817344}
+{"current_steps": 6636, "total_steps": 6951, "loss": 0.0978, "lr": 5.058626459766902e-07, "epoch": 2.8637221593053983, "percentage": 95.47, "elapsed_time": "1 day, 23:13:55", "remaining_time": "2:14:31", "throughput": 9421.29, "total_tokens": 1601955280}
+{"current_steps": 6657, "total_steps": 6951, "loss": 0.0963, "lr": 4.407585450899587e-07, "epoch": 2.872782181955455, "percentage": 95.77, "elapsed_time": "1 day, 23:22:45", "remaining_time": "2:05:32", "throughput": 9421.46, "total_tokens": 1606977888}
+{"current_steps": 6678, "total_steps": 6951, "loss": 0.0932, "lr": 3.8011886526292395e-07, "epoch": 2.8818422046055114, "percentage": 96.07, "elapsed_time": "1 day, 23:32:06", "remaining_time": "1:56:35", "throughput": 9420.75, "total_tokens": 1612137088}
+{"current_steps": 6699, "total_steps": 6951, "loss": 0.098, "lr": 3.2394906907040056e-07, "epoch": 2.8909022272555682, "percentage": 96.37, "elapsed_time": "1 day, 23:40:48", "remaining_time": "1:47:36", "throughput": 9421.03, "total_tokens": 1617105760}
+{"current_steps": 6720, "total_steps": 6951, "loss": 0.099, "lr": 2.7225421642883554e-07, "epoch": 2.8999622499056246, "percentage": 96.68, "elapsed_time": "1 day, 23:49:15", "remaining_time": "1:38:37", "throughput": 9422.17, "total_tokens": 1622079712}
+{"current_steps": 6741, "total_steps": 6951, "loss": 0.0974, "lr": 2.250389641405115e-07, "epoch": 2.9090222725556814, "percentage": 96.98, "elapsed_time": "1 day, 23:58:31", "remaining_time": "1:29:40", "throughput": 9421.85, "total_tokens": 1627262208}
+{"current_steps": 6762, "total_steps": 6951, "loss": 0.0995, "lr": 1.823075654740547e-07, "epoch": 2.918082295205738, "percentage": 97.28, "elapsed_time": "2 days, 0:07:09", "remaining_time": "1:20:41", "throughput": 9422.72, "total_tokens": 1632293744}
+{"current_steps": 6783, "total_steps": 6951, "loss": 0.0955, "lr": 1.4406386978128018e-07, "epoch": 2.9271423178557945, "percentage": 97.58, "elapsed_time": "2 days, 0:16:23", "remaining_time": "1:11:44", "throughput": 9422.15, "total_tokens": 1637413856}
+{"current_steps": 6804, "total_steps": 6951, "loss": 0.095, "lr": 1.1031132215043594e-07, "epoch": 2.9362023405058513, "percentage": 97.89, "elapsed_time": "2 days, 0:24:58", "remaining_time": "1:02:45", "throughput": 9422.79, "total_tokens": 1642376144}
+{"current_steps": 6825, "total_steps": 6951, "loss": 0.0995, "lr": 8.105296309586785e-08, "epoch": 2.9452623631559076, "percentage": 98.19, "elapsed_time": "2 days, 0:33:56", "remaining_time": "0:53:47", "throughput": 9422.9, "total_tokens": 1647471008}
+{"current_steps": 6846, "total_steps": 6951, "loss": 0.0976, "lr": 5.629142828411094e-08, "epoch": 2.9543223858059644, "percentage": 98.49, "elapsed_time": "2 days, 0:42:41", "remaining_time": "0:44:49", "throughput": 9423.33, "total_tokens": 1652489696}
+{"current_steps": 6867, "total_steps": 6951, "loss": 0.0955, "lr": 3.602894829647374e-08, "epoch": 2.963382408456021, "percentage": 98.79, "elapsed_time": "2 days, 0:51:22", "remaining_time": "0:35:51", "throughput": 9423.84, "total_tokens": 1657488848}
+{"current_steps": 6888, "total_steps": 6951, "loss": 0.0979, "lr": 2.0267348428087974e-08, "epoch": 2.972442431106078, "percentage": 99.09, "elapsed_time": "2 days, 1:00:06", "remaining_time": "0:26:53", "throughput": 9424.1, "total_tokens": 1662468816}
+{"current_steps": 6909, "total_steps": 6951, "loss": 0.0999, "lr": 9.008048523501122e-09, "epoch": 2.9815024537561343, "percentage": 99.4, "elapsed_time": "2 days, 1:08:56", "remaining_time": "0:17:55", "throughput": 9425.0, "total_tokens": 1667627776}
+{"current_steps": 6930, "total_steps": 6951, "loss": 0.099, "lr": 2.252062848745462e-09, "epoch": 2.990562476406191, "percentage": 99.7, "elapsed_time": "2 days, 1:18:09", "remaining_time": "0:08:57", "throughput": 9424.34, "total_tokens": 1672724048}
+{"current_steps": 6951, "total_steps": 6951, "loss": 0.0971, "lr": 0.0, "epoch": 2.9996224990562474, "percentage": 100.0, "elapsed_time": "2 days, 1:27:28", "remaining_time": "0:00:00", "throughput": 9423.59, "total_tokens": 1677860944}
+{"current_steps": 6951, "total_steps": 6951, "epoch": 2.9996224990562474, "percentage": 100.0, "elapsed_time": "2 days, 1:39:42", "remaining_time": "0:00:00", "throughput": 9384.94, "total_tokens": 1677860944}

trainer_state.json

@@ -0,0 +1,2701 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9996224990562474,
+  "eval_steps": 5000,
+  "global_step": 6951,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009060022650056626,
+      "grad_norm": 2.6664810047066947,
+      "learning_rate": 9.999774793715127e-05,
+      "loss": 1.431,
+      "num_input_tokens_seen": 5118512,
+      "step": 21
+    },
+    {
+      "epoch": 0.01812004530011325,
+      "grad_norm": 0.8152880359374859,
+      "learning_rate": 9.99909919514765e-05,
+      "loss": 0.5348,
+      "num_input_tokens_seen": 10150592,
+      "step": 42
+    },
+    {
+      "epoch": 0.027180067950169876,
+      "grad_norm": 0.6315786850545617,
+      "learning_rate": 9.997973265157192e-05,
+      "loss": 0.4599,
+      "num_input_tokens_seen": 15170896,
+      "step": 63
+    },
+    {
+      "epoch": 0.0362400906002265,
+      "grad_norm": 0.4538892840989214,
+      "learning_rate": 9.996397105170353e-05,
+      "loss": 0.4108,
+      "num_input_tokens_seen": 20155632,
+      "step": 84
+    },
+    {
+      "epoch": 0.045300113250283124,
+      "grad_norm": 0.4720911162561318,
+      "learning_rate": 9.994370857171588e-05,
+      "loss": 0.3947,
+      "num_input_tokens_seen": 25135440,
+      "step": 105
+    },
+    {
+      "epoch": 0.05436013590033975,
+      "grad_norm": 0.4622888476742547,
+      "learning_rate": 9.991894703690414e-05,
+      "loss": 0.3764,
+      "num_input_tokens_seen": 30346784,
+      "step": 126
+    },
+    {
+      "epoch": 0.06342015855039637,
+      "grad_norm": 0.4173513485950873,
+      "learning_rate": 9.988968867784958e-05,
+      "loss": 0.3751,
+      "num_input_tokens_seen": 35269664,
+      "step": 147
+    },
+    {
+      "epoch": 0.072480181200453,
+      "grad_norm": 0.39249341716348773,
+      "learning_rate": 9.985593613021872e-05,
+      "loss": 0.3704,
+      "num_input_tokens_seen": 40151792,
+      "step": 168
+    },
+    {
+      "epoch": 0.08154020385050963,
+      "grad_norm": 0.3080363284417135,
+      "learning_rate": 9.981769243452595e-05,
+      "loss": 0.3552,
+      "num_input_tokens_seen": 45283312,
+      "step": 189
+    },
+    {
+      "epoch": 0.09060022650056625,
+      "grad_norm": 0.3747998358734097,
+      "learning_rate": 9.977496103585949e-05,
+      "loss": 0.3576,
+      "num_input_tokens_seen": 50298912,
+      "step": 210
+    },
+    {
+      "epoch": 0.09966024915062288,
+      "grad_norm": 0.2975791185912304,
+      "learning_rate": 9.972774578357117e-05,
+      "loss": 0.3451,
+      "num_input_tokens_seen": 55445792,
+      "step": 231
+    },
+    {
+      "epoch": 0.1087202718006795,
+      "grad_norm": 0.3172928529259604,
+      "learning_rate": 9.96760509309296e-05,
+      "loss": 0.3506,
+      "num_input_tokens_seen": 60506496,
+      "step": 252
+    },
+    {
+      "epoch": 0.11778029445073612,
+      "grad_norm": 0.3304680645103982,
+      "learning_rate": 9.961988113473708e-05,
+      "loss": 0.3443,
+      "num_input_tokens_seen": 65678096,
+      "step": 273
+    },
+    {
+      "epoch": 0.12684031710079274,
+      "grad_norm": 0.2929759270178528,
+      "learning_rate": 9.955924145491005e-05,
+      "loss": 0.3446,
+      "num_input_tokens_seen": 70478688,
+      "step": 294
+    },
+    {
+      "epoch": 0.13590033975084936,
+      "grad_norm": 0.2809492487037724,
+      "learning_rate": 9.94941373540233e-05,
+      "loss": 0.3362,
+      "num_input_tokens_seen": 75373536,
+      "step": 315
+    },
+    {
+      "epoch": 0.144960362400906,
+      "grad_norm": 0.38609616986912937,
+      "learning_rate": 9.942457469681794e-05,
+      "loss": 0.3384,
+      "num_input_tokens_seen": 80476704,
+      "step": 336
+    },
+    {
+      "epoch": 0.15402038505096263,
+      "grad_norm": 0.24129947470960447,
+      "learning_rate": 9.935055974967299e-05,
+      "loss": 0.3315,
+      "num_input_tokens_seen": 85670800,
+      "step": 357
+    },
+    {
+      "epoch": 0.16308040770101925,
+      "grad_norm": 0.22875446286948012,
+      "learning_rate": 9.927209918004095e-05,
+      "loss": 0.33,
+      "num_input_tokens_seen": 90707040,
+      "step": 378
+    },
+    {
+      "epoch": 0.17214043035107587,
+      "grad_norm": 0.26219955903132913,
+      "learning_rate": 9.918920005584719e-05,
+      "loss": 0.3296,
+      "num_input_tokens_seen": 95824496,
+      "step": 399
+    },
+    {
+      "epoch": 0.1812004530011325,
+      "grad_norm": 0.6217611528853424,
+      "learning_rate": 9.910186984485321e-05,
+      "loss": 0.3315,
+      "num_input_tokens_seen": 100862224,
+      "step": 420
+    },
+    {
+      "epoch": 0.19026047565118911,
+      "grad_norm": 0.5343386676193482,
+      "learning_rate": 9.901011641398398e-05,
+      "loss": 0.353,
+      "num_input_tokens_seen": 105876656,
+      "step": 441
+    },
+    {
+      "epoch": 0.19932049830124576,
+      "grad_norm": 0.29271392356860787,
+      "learning_rate": 9.89139480286192e-05,
+      "loss": 0.3414,
+      "num_input_tokens_seen": 110980864,
+      "step": 462
+    },
+    {
+      "epoch": 0.20838052095130238,
+      "grad_norm": 0.2662936598921738,
+      "learning_rate": 9.881337335184878e-05,
+      "loss": 0.3224,
+      "num_input_tokens_seen": 116114800,
+      "step": 483
+    },
+    {
+      "epoch": 0.217440543601359,
+      "grad_norm": 0.3006863273182064,
+      "learning_rate": 9.870840144369246e-05,
+      "loss": 0.3212,
+      "num_input_tokens_seen": 121255744,
+      "step": 504
+    },
+    {
+      "epoch": 0.22650056625141562,
+      "grad_norm": 0.28557101475631624,
+      "learning_rate": 9.859904176028362e-05,
+      "loss": 0.3213,
+      "num_input_tokens_seen": 126288608,
+      "step": 525
+    },
+    {
+      "epoch": 0.23556058890147225,
+      "grad_norm": 0.30204169829965893,
+      "learning_rate": 9.848530415301747e-05,
+      "loss": 0.3198,
+      "num_input_tokens_seen": 131233488,
+      "step": 546
+    },
+    {
+      "epoch": 0.24462061155152887,
+      "grad_norm": 0.22788149212961117,
+      "learning_rate": 9.836719886766356e-05,
+      "loss": 0.3149,
+      "num_input_tokens_seen": 136257888,
+      "step": 567
+    },
+    {
+      "epoch": 0.2536806342015855,
+      "grad_norm": 0.25388452332747136,
+      "learning_rate": 9.824473654344297e-05,
+      "loss": 0.3169,
+      "num_input_tokens_seen": 141405120,
+      "step": 588
+    },
+    {
+      "epoch": 0.2627406568516421,
+      "grad_norm": 0.22932388019266456,
+      "learning_rate": 9.811792821206969e-05,
+      "loss": 0.3142,
+      "num_input_tokens_seen": 146380496,
+      "step": 609
+    },
+    {
+      "epoch": 0.2718006795016987,
+      "grad_norm": 0.21316227582275912,
+      "learning_rate": 9.7986785296757e-05,
+      "loss": 0.3097,
+      "num_input_tokens_seen": 151344048,
+      "step": 630
+    },
+    {
+      "epoch": 0.2808607021517554,
+      "grad_norm": 0.2055839569031328,
+      "learning_rate": 9.785131961118844e-05,
+      "loss": 0.3116,
+      "num_input_tokens_seen": 156435136,
+      "step": 651
+    },
+    {
+      "epoch": 0.289920724801812,
+      "grad_norm": 0.2441799648084251,
+      "learning_rate": 9.771154335845345e-05,
+      "loss": 0.3086,
+      "num_input_tokens_seen": 161536224,
+      "step": 672
+    },
+    {
+      "epoch": 0.29898074745186864,
+      "grad_norm": 0.20481810635702893,
+      "learning_rate": 9.756746912994832e-05,
+      "loss": 0.3057,
+      "num_input_tokens_seen": 166573984,
+      "step": 693
+    },
+    {
+      "epoch": 0.30804077010192527,
+      "grad_norm": 0.2592126104806373,
+      "learning_rate": 9.741910990424174e-05,
+      "loss": 0.3017,
+      "num_input_tokens_seen": 171638000,
+      "step": 714
+    },
+    {
+      "epoch": 0.3171007927519819,
+      "grad_norm": 0.25174137308280303,
+      "learning_rate": 9.726647904590571e-05,
+      "loss": 0.3066,
+      "num_input_tokens_seen": 176765648,
+      "step": 735
+    },
+    {
+      "epoch": 0.3261608154020385,
+      "grad_norm": 0.20855236580529835,
+      "learning_rate": 9.710959030431167e-05,
+      "loss": 0.2996,
+      "num_input_tokens_seen": 181949360,
+      "step": 756
+    },
+    {
+      "epoch": 0.3352208380520951,
+      "grad_norm": 0.23697815659002952,
+      "learning_rate": 9.694845781239187e-05,
+      "loss": 0.2972,
+      "num_input_tokens_seen": 186990096,
+      "step": 777
+    },
+    {
+      "epoch": 0.34428086070215175,
+      "grad_norm": 0.2492979898134609,
+      "learning_rate": 9.678309608536626e-05,
+      "loss": 0.2984,
+      "num_input_tokens_seen": 192083856,
+      "step": 798
+    },
+    {
+      "epoch": 0.35334088335220837,
+      "grad_norm": 0.23816573617268064,
+      "learning_rate": 9.661352001943493e-05,
+      "loss": 0.2957,
+      "num_input_tokens_seen": 197134448,
+      "step": 819
+    },
+    {
+      "epoch": 0.362400906002265,
+      "grad_norm": 0.20467034048790322,
+      "learning_rate": 9.64397448904362e-05,
+      "loss": 0.2926,
+      "num_input_tokens_seen": 202310368,
+      "step": 840
+    },
+    {
+      "epoch": 0.3714609286523216,
+      "grad_norm": 0.17904927666050605,
+      "learning_rate": 9.626178635247054e-05,
+      "loss": 0.2909,
+      "num_input_tokens_seen": 207359840,
+      "step": 861
+    },
+    {
+      "epoch": 0.38052095130237823,
+      "grad_norm": 0.248985929697072,
+      "learning_rate": 9.607966043649046e-05,
+      "loss": 0.2954,
+      "num_input_tokens_seen": 212395664,
+      "step": 882
+    },
+    {
+      "epoch": 0.3895809739524349,
+      "grad_norm": 0.17735947921966527,
+      "learning_rate": 9.589338354885629e-05,
+      "loss": 0.2912,
+      "num_input_tokens_seen": 217570640,
+      "step": 903
+    },
+    {
+      "epoch": 0.3986409966024915,
+      "grad_norm": 0.2653024856558906,
+      "learning_rate": 9.570297246985837e-05,
+      "loss": 0.2928,
+      "num_input_tokens_seen": 222629712,
+      "step": 924
+    },
+    {
+      "epoch": 0.40770101925254815,
+      "grad_norm": 0.21684716629964057,
+      "learning_rate": 9.550844435220539e-05,
+      "loss": 0.292,
+      "num_input_tokens_seen": 227565744,
+      "step": 945
+    },
+    {
+      "epoch": 0.41676104190260477,
+      "grad_norm": 0.19831973070913392,
+      "learning_rate": 9.530981671947923e-05,
+      "loss": 0.292,
+      "num_input_tokens_seen": 232655712,
+      "step": 966
+    },
+    {
+      "epoch": 0.4258210645526614,
+      "grad_norm": 0.2039591338730108,
+      "learning_rate": 9.510710746455636e-05,
+      "loss": 0.2959,
+      "num_input_tokens_seen": 237611056,
+      "step": 987
+    },
+    {
+      "epoch": 0.434881087202718,
+      "grad_norm": 0.20635917697106,
+      "learning_rate": 9.490033484799608e-05,
+      "loss": 0.2884,
+      "num_input_tokens_seen": 242693136,
+      "step": 1008
+    },
+    {
+      "epoch": 0.44394110985277463,
+      "grad_norm": 0.21178513822087988,
+      "learning_rate": 9.468951749639551e-05,
+      "loss": 0.2878,
+      "num_input_tokens_seen": 247677488,
+      "step": 1029
+    },
+    {
+      "epoch": 0.45300113250283125,
+      "grad_norm": 0.24393748334345636,
+      "learning_rate": 9.447467440071164e-05,
+      "loss": 0.2908,
+      "num_input_tokens_seen": 252770384,
+      "step": 1050
+    },
+    {
+      "epoch": 0.46206115515288787,
+      "grad_norm": 0.19345581725168481,
+      "learning_rate": 9.425582491455067e-05,
+      "loss": 0.2796,
+      "num_input_tokens_seen": 258009696,
+      "step": 1071
+    },
+    {
+      "epoch": 0.4711211778029445,
+      "grad_norm": 0.17550447436524724,
+      "learning_rate": 9.403298875242448e-05,
+      "loss": 0.2858,
+      "num_input_tokens_seen": 263147728,
+      "step": 1092
+    },
+    {
+      "epoch": 0.4801812004530011,
+      "grad_norm": 0.1873327110291133,
+      "learning_rate": 9.380618598797473e-05,
+      "loss": 0.2876,
+      "num_input_tokens_seen": 268184080,
+      "step": 1113
+    },
+    {
+      "epoch": 0.48924122310305773,
+      "grad_norm": 0.2326284547666313,
+      "learning_rate": 9.357543705216465e-05,
+      "loss": 0.2814,
+      "num_input_tokens_seen": 273442768,
+      "step": 1134
+    },
+    {
+      "epoch": 0.4983012457531144,
+      "grad_norm": 0.1606625392823979,
+      "learning_rate": 9.334076273143843e-05,
+      "loss": 0.2804,
+      "num_input_tokens_seen": 278640624,
+      "step": 1155
+    },
+    {
+      "epoch": 0.507361268403171,
+      "grad_norm": 0.174300515580659,
+      "learning_rate": 9.310218416584886e-05,
+      "loss": 0.2863,
+      "num_input_tokens_seen": 283769424,
+      "step": 1176
+    },
+    {
+      "epoch": 0.5164212910532276,
+      "grad_norm": 0.18523825539113345,
+      "learning_rate": 9.28597228471529e-05,
+      "loss": 0.2851,
+      "num_input_tokens_seen": 288866448,
+      "step": 1197
+    },
+    {
+      "epoch": 0.5254813137032842,
+      "grad_norm": 0.29288899462077944,
+      "learning_rate": 9.26134006168757e-05,
+      "loss": 0.2798,
+      "num_input_tokens_seen": 293944576,
+      "step": 1218
+    },
+    {
+      "epoch": 0.5345413363533409,
+      "grad_norm": 0.21677248351508627,
+      "learning_rate": 9.236323966434295e-05,
+      "loss": 0.2728,
+      "num_input_tokens_seen": 299090032,
+      "step": 1239
+    },
+    {
+      "epoch": 0.5436013590033975,
+      "grad_norm": 0.17425284816339717,
+      "learning_rate": 9.210926252468219e-05,
+      "loss": 0.2756,
+      "num_input_tokens_seen": 304016304,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5526613816534541,
+      "grad_norm": 0.19722321188451059,
+      "learning_rate": 9.185149207679263e-05,
+      "loss": 0.2747,
+      "num_input_tokens_seen": 309084016,
+      "step": 1281
+    },
+    {
+      "epoch": 0.5617214043035108,
+      "grad_norm": 0.15927450699962342,
+      "learning_rate": 9.158995154128425e-05,
+      "loss": 0.2772,
+      "num_input_tokens_seen": 314201696,
+      "step": 1302
+    },
+    {
+      "epoch": 0.5707814269535674,
+      "grad_norm": 0.144121234319095,
+      "learning_rate": 9.132466447838597e-05,
+      "loss": 0.2785,
+      "num_input_tokens_seen": 319266256,
+      "step": 1323
+    },
+    {
+      "epoch": 0.579841449603624,
+      "grad_norm": 0.20014275331573014,
+      "learning_rate": 9.105565478582334e-05,
+      "loss": 0.2755,
+      "num_input_tokens_seen": 324468352,
+      "step": 1344
+    },
+    {
+      "epoch": 0.5889014722536806,
+      "grad_norm": 0.1763537829210326,
+      "learning_rate": 9.078294669666576e-05,
+      "loss": 0.2708,
+      "num_input_tokens_seen": 329566736,
+      "step": 1365
+    },
+    {
+      "epoch": 0.5979614949037373,
+      "grad_norm": 0.20344878470372835,
+      "learning_rate": 9.050656477714346e-05,
+      "loss": 0.2729,
+      "num_input_tokens_seen": 334661888,
+      "step": 1386
+    },
+    {
+      "epoch": 0.6070215175537939,
+      "grad_norm": 0.16201525012659232,
+      "learning_rate": 9.022653392443454e-05,
+      "loss": 0.2754,
+      "num_input_tokens_seen": 339784976,
+      "step": 1407
+    },
+    {
+      "epoch": 0.6160815402038505,
+      "grad_norm": 0.17086654725622255,
+      "learning_rate": 8.994287936442225e-05,
+      "loss": 0.2742,
+      "num_input_tokens_seen": 344776544,
+      "step": 1428
+    },
+    {
+      "epoch": 0.6251415628539071,
+      "grad_norm": 0.17370971449213884,
+      "learning_rate": 8.96556266494224e-05,
+      "loss": 0.2703,
+      "num_input_tokens_seen": 349731168,
+      "step": 1449
+    },
+    {
+      "epoch": 0.6342015855039638,
+      "grad_norm": 0.1759254965690454,
+      "learning_rate": 8.936480165588173e-05,
+      "loss": 0.2756,
+      "num_input_tokens_seen": 354694544,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6432616081540203,
+      "grad_norm": 0.1884165927777844,
+      "learning_rate": 8.907043058204674e-05,
+      "loss": 0.2698,
+      "num_input_tokens_seen": 359871984,
+      "step": 1491
+    },
+    {
+      "epoch": 0.652321630804077,
+      "grad_norm": 0.18427306909901323,
+      "learning_rate": 8.877253994560382e-05,
+      "loss": 0.2716,
+      "num_input_tokens_seen": 364937440,
+      "step": 1512
+    },
+    {
+      "epoch": 0.6613816534541337,
+      "grad_norm": 0.20911376204072243,
+      "learning_rate": 8.847115658129039e-05,
+      "loss": 0.2682,
+      "num_input_tokens_seen": 369994848,
+      "step": 1533
+    },
+    {
+      "epoch": 0.6704416761041903,
+      "grad_norm": 0.20741042143522315,
+      "learning_rate": 8.816630763847755e-05,
+      "loss": 0.2695,
+      "num_input_tokens_seen": 374992544,
+      "step": 1554
+    },
+    {
+      "epoch": 0.6795016987542469,
+      "grad_norm": 0.1643283959081191,
+      "learning_rate": 8.785802057872446e-05,
+      "loss": 0.2706,
+      "num_input_tokens_seen": 380038624,
+      "step": 1575
+    },
+    {
+      "epoch": 0.6885617214043035,
+      "grad_norm": 0.20102992236744546,
+      "learning_rate": 8.754632317330447e-05,
+      "loss": 0.2704,
+      "num_input_tokens_seen": 385195792,
+      "step": 1596
+    },
+    {
+      "epoch": 0.6976217440543602,
+      "grad_norm": 0.18834807757879243,
+      "learning_rate": 8.723124350070347e-05,
+      "loss": 0.2707,
+      "num_input_tokens_seen": 390195296,
+      "step": 1617
+    },
+    {
+      "epoch": 0.7066817667044167,
+      "grad_norm": 0.15261075530832655,
+      "learning_rate": 8.691280994409043e-05,
+      "loss": 0.2653,
+      "num_input_tokens_seen": 395353440,
+      "step": 1638
+    },
+    {
+      "epoch": 0.7157417893544734,
+      "grad_norm": 0.20682506960801342,
+      "learning_rate": 8.659105118876068e-05,
+      "loss": 0.2649,
+      "num_input_tokens_seen": 400444080,
+      "step": 1659
+    },
+    {
+      "epoch": 0.72480181200453,
+      "grad_norm": 0.21733357068498219,
+      "learning_rate": 8.626599621955179e-05,
+      "loss": 0.2652,
+      "num_input_tokens_seen": 405492112,
+      "step": 1680
+    },
+    {
+      "epoch": 0.7338618346545867,
+      "grad_norm": 0.18286757761891814,
+      "learning_rate": 8.593767431823255e-05,
+      "loss": 0.2638,
+      "num_input_tokens_seen": 410467584,
+      "step": 1701
+    },
+    {
+      "epoch": 0.7429218573046432,
+      "grad_norm": 0.16764027437130122,
+      "learning_rate": 8.56061150608652e-05,
+      "loss": 0.2685,
+      "num_input_tokens_seen": 415550320,
+      "step": 1722
+    },
+    {
+      "epoch": 0.7519818799546999,
+      "grad_norm": 0.17921646972994934,
+      "learning_rate": 8.527134831514117e-05,
+      "loss": 0.2584,
+      "num_input_tokens_seen": 420503712,
+      "step": 1743
+    },
+    {
+      "epoch": 0.7610419026047565,
+      "grad_norm": 0.19062465197166928,
+      "learning_rate": 8.493340423769053e-05,
+      "loss": 0.2607,
+      "num_input_tokens_seen": 425602800,
+      "step": 1764
+    },
+    {
+      "epoch": 0.7701019252548131,
+      "grad_norm": 0.19476076523413036,
+      "learning_rate": 8.459231327136532e-05,
+      "loss": 0.2652,
+      "num_input_tokens_seen": 430546320,
+      "step": 1785
+    },
+    {
+      "epoch": 0.7791619479048698,
+      "grad_norm": 0.18756178702354967,
+      "learning_rate": 8.42481061424973e-05,
+      "loss": 0.2604,
+      "num_input_tokens_seen": 435625600,
+      "step": 1806
+    },
+    {
+      "epoch": 0.7882219705549264,
+      "grad_norm": 0.16871375853816825,
+      "learning_rate": 8.390081385812993e-05,
+      "loss": 0.2603,
+      "num_input_tokens_seen": 440695024,
+      "step": 1827
+    },
+    {
+      "epoch": 0.797281993204983,
+      "grad_norm": 0.1669594920851862,
+      "learning_rate": 8.355046770322528e-05,
+      "loss": 0.2576,
+      "num_input_tokens_seen": 445877360,
+      "step": 1848
+    },
+    {
+      "epoch": 0.8063420158550396,
+      "grad_norm": 0.20147791313721689,
+      "learning_rate": 8.319709923784573e-05,
+      "loss": 0.2622,
+      "num_input_tokens_seen": 451021040,
+      "step": 1869
+    },
+    {
+      "epoch": 0.8154020385050963,
+      "grad_norm": 0.17108850294819108,
+      "learning_rate": 8.284074029431099e-05,
+      "loss": 0.2587,
+      "num_input_tokens_seen": 456101872,
+      "step": 1890
+    },
+    {
+      "epoch": 0.8244620611551529,
+      "grad_norm": 0.18516681989871883,
+      "learning_rate": 8.248142297433057e-05,
+      "loss": 0.2575,
+      "num_input_tokens_seen": 461365920,
+      "step": 1911
+    },
+    {
+      "epoch": 0.8335220838052095,
+      "grad_norm": 0.20285356102658042,
+      "learning_rate": 8.211917964611196e-05,
+      "loss": 0.2573,
+      "num_input_tokens_seen": 466466096,
+      "step": 1932
+    },
+    {
+      "epoch": 0.8425821064552661,
+      "grad_norm": 0.207923488217522,
+      "learning_rate": 8.175404294144482e-05,
+      "loss": 0.26,
+      "num_input_tokens_seen": 471541104,
+      "step": 1953
+    },
+    {
+      "epoch": 0.8516421291053228,
+      "grad_norm": 0.19850908270608497,
+      "learning_rate": 8.138604575276143e-05,
+      "loss": 0.2571,
+      "num_input_tokens_seen": 476646096,
+      "step": 1974
+    },
+    {
+      "epoch": 0.8607021517553793,
+      "grad_norm": 0.1821198820367163,
+      "learning_rate": 8.10152212301737e-05,
+      "loss": 0.251,
+      "num_input_tokens_seen": 481695200,
+      "step": 1995
+    },
+    {
+      "epoch": 0.869762174405436,
+      "grad_norm": 0.1623421619904062,
+      "learning_rate": 8.064160277848682e-05,
+      "loss": 0.2614,
+      "num_input_tokens_seen": 486706656,
+      "step": 2016
+    },
+    {
+      "epoch": 0.8788221970554927,
+      "grad_norm": 0.1774308248272562,
+      "learning_rate": 8.026522405419023e-05,
+      "loss": 0.2528,
+      "num_input_tokens_seen": 491943424,
+      "step": 2037
+    },
+    {
+      "epoch": 0.8878822197055493,
+      "grad_norm": 0.21003241654174584,
+      "learning_rate": 7.988611896242559e-05,
+      "loss": 0.2571,
+      "num_input_tokens_seen": 496925888,
+      "step": 2058
+    },
+    {
+      "epoch": 0.8969422423556059,
+      "grad_norm": 0.20014809740395048,
+      "learning_rate": 7.950432165393259e-05,
+      "loss": 0.2547,
+      "num_input_tokens_seen": 502065216,
+      "step": 2079
+    },
+    {
+      "epoch": 0.9060022650056625,
+      "grad_norm": 0.17154274701388803,
+      "learning_rate": 7.911986652197262e-05,
+      "loss": 0.2538,
+      "num_input_tokens_seen": 507089616,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9150622876557192,
+      "grad_norm": 0.17929198920009218,
+      "learning_rate": 7.873278819923048e-05,
+      "loss": 0.2551,
+      "num_input_tokens_seen": 512060336,
+      "step": 2121
+    },
+    {
+      "epoch": 0.9241223103057757,
+      "grad_norm": 0.16398954046091754,
+      "learning_rate": 7.834312155469456e-05,
+      "loss": 0.2515,
+      "num_input_tokens_seen": 517133680,
+      "step": 2142
+    },
+    {
+      "epoch": 0.9331823329558324,
+      "grad_norm": 0.17469600332499013,
+      "learning_rate": 7.79509016905158e-05,
+      "loss": 0.2526,
+      "num_input_tokens_seen": 522229616,
+      "step": 2163
+    },
+    {
+      "epoch": 0.942242355605889,
+      "grad_norm": 0.15900929966723312,
+      "learning_rate": 7.755616393884561e-05,
+      "loss": 0.2482,
+      "num_input_tokens_seen": 527368864,
+      "step": 2184
+    },
+    {
+      "epoch": 0.9513023782559457,
+      "grad_norm": 0.18254122861853214,
+      "learning_rate": 7.715894385865299e-05,
+      "loss": 0.2516,
+      "num_input_tokens_seen": 532499712,
+      "step": 2205
+    },
+    {
+      "epoch": 0.9603624009060022,
+      "grad_norm": 0.19001641667974054,
+      "learning_rate": 7.675927723252134e-05,
+      "loss": 0.2493,
+      "num_input_tokens_seen": 537438224,
+      "step": 2226
+    },
+    {
+      "epoch": 0.9694224235560589,
+      "grad_norm": 0.16454856189702688,
+      "learning_rate": 7.635720006342512e-05,
+      "loss": 0.2465,
+      "num_input_tokens_seen": 542603472,
+      "step": 2247
+    },
+    {
+      "epoch": 0.9784824462061155,
+      "grad_norm": 0.18435585737458549,
+      "learning_rate": 7.595274857148652e-05,
+      "loss": 0.2486,
+      "num_input_tokens_seen": 547622688,
+      "step": 2268
+    },
+    {
+      "epoch": 0.9875424688561721,
+      "grad_norm": 0.16595693704140477,
+      "learning_rate": 7.554595919071268e-05,
+      "loss": 0.2472,
+      "num_input_tokens_seen": 552751232,
+      "step": 2289
+    },
+    {
+      "epoch": 0.9966024915062288,
+      "grad_norm": 0.16765543588823353,
+      "learning_rate": 7.513686856571368e-05,
+      "loss": 0.2471,
+      "num_input_tokens_seen": 557786736,
+      "step": 2310
+    },
+    {
+      "epoch": 1.0060400151000377,
+      "grad_norm": 0.17133389174596797,
+      "learning_rate": 7.472551354840145e-05,
+      "loss": 0.2361,
+      "num_input_tokens_seen": 562993712,
+      "step": 2331
+    },
+    {
+      "epoch": 1.0151000377500943,
+      "grad_norm": 0.18279159983012744,
+      "learning_rate": 7.431193119467008e-05,
+      "loss": 0.217,
+      "num_input_tokens_seen": 568021744,
+      "step": 2352
+    },
+    {
+      "epoch": 1.024160060400151,
+      "grad_norm": 0.266530218109695,
+      "learning_rate": 7.389615876105774e-05,
+      "loss": 0.2145,
+      "num_input_tokens_seen": 572956608,
+      "step": 2373
+    },
+    {
+      "epoch": 1.0332200830502076,
+      "grad_norm": 0.178808088687151,
+      "learning_rate": 7.347823370139042e-05,
+      "loss": 0.2179,
+      "num_input_tokens_seen": 577973792,
+      "step": 2394
+    },
+    {
+      "epoch": 1.0422801057002642,
+      "grad_norm": 0.15535901011827938,
+      "learning_rate": 7.30581936634082e-05,
+      "loss": 0.2098,
+      "num_input_tokens_seen": 582948368,
+      "step": 2415
+    },
+    {
+      "epoch": 1.051340128350321,
+      "grad_norm": 0.1879255010231289,
+      "learning_rate": 7.263607648537364e-05,
+      "loss": 0.2174,
+      "num_input_tokens_seen": 587973936,
+      "step": 2436
+    },
+    {
+      "epoch": 1.0604001510003775,
+      "grad_norm": 0.18116579180636055,
+      "learning_rate": 7.221192019266332e-05,
+      "loss": 0.2187,
+      "num_input_tokens_seen": 593048624,
+      "step": 2457
+    },
+    {
+      "epoch": 1.069460173650434,
+      "grad_norm": 0.16067683672474237,
+      "learning_rate": 7.178576299434238e-05,
+      "loss": 0.2162,
+      "num_input_tokens_seen": 598171840,
+      "step": 2478
+    },
+    {
+      "epoch": 1.0785201963004907,
+      "grad_norm": 0.16890347919356866,
+      "learning_rate": 7.135764327972261e-05,
+      "loss": 0.2202,
+      "num_input_tokens_seen": 603168000,
+      "step": 2499
+    },
+    {
+      "epoch": 1.0875802189505475,
+      "grad_norm": 0.171528446871021,
+      "learning_rate": 7.092759961490415e-05,
+      "loss": 0.2237,
+      "num_input_tokens_seen": 608280544,
+      "step": 2520
+    },
+    {
+      "epoch": 1.096640241600604,
+      "grad_norm": 0.16674379731500746,
+      "learning_rate": 7.049567073930143e-05,
+      "loss": 0.2199,
+      "num_input_tokens_seen": 613215280,
+      "step": 2541
+    },
+    {
+      "epoch": 1.1057002642506606,
+      "grad_norm": 0.18816045716369076,
+      "learning_rate": 7.006189556215345e-05,
+      "loss": 0.2189,
+      "num_input_tokens_seen": 618261984,
+      "step": 2562
+    },
+    {
+      "epoch": 1.1147602869007172,
+      "grad_norm": 0.16658411013718444,
+      "learning_rate": 6.962631315901861e-05,
+      "loss": 0.2163,
+      "num_input_tokens_seen": 623492320,
+      "step": 2583
+    },
+    {
+      "epoch": 1.123820309550774,
+      "grad_norm": 0.19772642288828662,
+      "learning_rate": 6.918896276825485e-05,
+      "loss": 0.2157,
+      "num_input_tokens_seen": 628563152,
+      "step": 2604
+    },
+    {
+      "epoch": 1.1328803322008305,
+      "grad_norm": 0.17075347503361357,
+      "learning_rate": 6.874988378748483e-05,
+      "loss": 0.2141,
+      "num_input_tokens_seen": 633639472,
+      "step": 2625
+    },
+    {
+      "epoch": 1.141940354850887,
+      "grad_norm": 0.14444472527009938,
+      "learning_rate": 6.830911577004698e-05,
+      "loss": 0.2185,
+      "num_input_tokens_seen": 638639648,
+      "step": 2646
+    },
+    {
+      "epoch": 1.1510003775009436,
+      "grad_norm": 0.17948926082904845,
+      "learning_rate": 6.786669842143236e-05,
+      "loss": 0.2125,
+      "num_input_tokens_seen": 643743632,
+      "step": 2667
+    },
+    {
+      "epoch": 1.1600604001510004,
+      "grad_norm": 0.1845862453656852,
+      "learning_rate": 6.742267159570795e-05,
+      "loss": 0.2138,
+      "num_input_tokens_seen": 648823584,
+      "step": 2688
+    },
+    {
+      "epoch": 1.169120422801057,
+      "grad_norm": 0.1611490189496428,
+      "learning_rate": 6.697707529192648e-05,
+      "loss": 0.2152,
+      "num_input_tokens_seen": 653949232,
+      "step": 2709
+    },
+    {
+      "epoch": 1.1781804454511136,
+      "grad_norm": 0.19293414419678218,
+      "learning_rate": 6.652994965052319e-05,
+      "loss": 0.2125,
+      "num_input_tokens_seen": 658996016,
+      "step": 2730
+    },
+    {
+      "epoch": 1.1872404681011703,
+      "grad_norm": 0.1887515649690068,
+      "learning_rate": 6.608133494969994e-05,
+      "loss": 0.2123,
+      "num_input_tokens_seen": 664102304,
+      "step": 2751
+    },
+    {
+      "epoch": 1.196300490751227,
+      "grad_norm": 0.15668371616625942,
+      "learning_rate": 6.563127160179671e-05,
+      "loss": 0.2101,
+      "num_input_tokens_seen": 669123584,
+      "step": 2772
+    },
+    {
+      "epoch": 1.2053605134012835,
+      "grad_norm": 0.17871386948979864,
+      "learning_rate": 6.517980014965139e-05,
+      "loss": 0.209,
+      "num_input_tokens_seen": 674256592,
+      "step": 2793
+    },
+    {
+      "epoch": 1.21442053605134,
+      "grad_norm": 0.16852785549912133,
+      "learning_rate": 6.472696126294732e-05,
+      "loss": 0.2122,
+      "num_input_tokens_seen": 679248208,
+      "step": 2814
+    },
+    {
+      "epoch": 1.2234805587013968,
+      "grad_norm": 0.1758847676430736,
+      "learning_rate": 6.427279573454985e-05,
+      "loss": 0.2093,
+      "num_input_tokens_seen": 684325632,
+      "step": 2835
+    },
+    {
+      "epoch": 1.2325405813514534,
+      "grad_norm": 0.19298009720432585,
+      "learning_rate": 6.381734447683152e-05,
+      "loss": 0.2114,
+      "num_input_tokens_seen": 689336736,
+      "step": 2856
+    },
+    {
+      "epoch": 1.24160060400151,
+      "grad_norm": 0.16439303725722001,
+      "learning_rate": 6.33606485179866e-05,
+      "loss": 0.2111,
+      "num_input_tokens_seen": 694382688,
+      "step": 2877
+    },
+    {
+      "epoch": 1.2506606266515665,
+      "grad_norm": 0.18140167193790194,
+      "learning_rate": 6.290274899833517e-05,
+      "loss": 0.2086,
+      "num_input_tokens_seen": 699371792,
+      "step": 2898
+    },
+    {
+      "epoch": 1.2597206493016233,
+      "grad_norm": 0.17151657072780352,
+      "learning_rate": 6.244368716661713e-05,
+      "loss": 0.2095,
+      "num_input_tokens_seen": 704404624,
+      "step": 2919
+    },
+    {
+      "epoch": 1.2687806719516799,
+      "grad_norm": 0.2052334824788225,
+      "learning_rate": 6.198350437627632e-05,
+      "loss": 0.2083,
+      "num_input_tokens_seen": 709451392,
+      "step": 2940
+    },
+    {
+      "epoch": 1.2778406946017364,
+      "grad_norm": 0.18426322385396474,
+      "learning_rate": 6.152224208173533e-05,
+      "loss": 0.2088,
+      "num_input_tokens_seen": 714486848,
+      "step": 2961
+    },
+    {
+      "epoch": 1.2869007172517932,
+      "grad_norm": 0.1949416856665576,
+      "learning_rate": 6.10599418346613e-05,
+      "loss": 0.2118,
+      "num_input_tokens_seen": 719556448,
+      "step": 2982
+    },
+    {
+      "epoch": 1.2959607399018498,
+      "grad_norm": 0.16224663869829734,
+      "learning_rate": 6.059664528022266e-05,
+      "loss": 0.2058,
+      "num_input_tokens_seen": 724625472,
+      "step": 3003
+    },
+    {
+      "epoch": 1.3050207625519064,
+      "grad_norm": 0.1742996675080445,
+      "learning_rate": 6.0132394153337755e-05,
+      "loss": 0.2065,
+      "num_input_tokens_seen": 729794320,
+      "step": 3024
+    },
+    {
+      "epoch": 1.3140807852019631,
+      "grad_norm": 0.17806291944392397,
+      "learning_rate": 5.9667230274915174e-05,
+      "loss": 0.207,
+      "num_input_tokens_seen": 734753392,
+      "step": 3045
+    },
+    {
+      "epoch": 1.3231408078520197,
+      "grad_norm": 0.18436964692073765,
+      "learning_rate": 5.920119554808651e-05,
+      "loss": 0.2049,
+      "num_input_tokens_seen": 739827088,
+      "step": 3066
+    },
+    {
+      "epoch": 1.3322008305020763,
+      "grad_norm": 0.16939954583438047,
+      "learning_rate": 5.873433195443152e-05,
+      "loss": 0.208,
+      "num_input_tokens_seen": 744847184,
+      "step": 3087
+    },
+    {
+      "epoch": 1.3412608531521328,
+      "grad_norm": 0.1635889048824763,
+      "learning_rate": 5.82666815501964e-05,
+      "loss": 0.2047,
+      "num_input_tokens_seen": 749874880,
+      "step": 3108
+    },
+    {
+      "epoch": 1.3503208758021894,
+      "grad_norm": 0.16527453811089068,
+      "learning_rate": 5.779828646250521e-05,
+      "loss": 0.2022,
+      "num_input_tokens_seen": 754848400,
+      "step": 3129
+    },
+    {
+      "epoch": 1.3593808984522462,
+      "grad_norm": 0.18777829379599956,
+      "learning_rate": 5.7329188885565e-05,
+      "loss": 0.2073,
+      "num_input_tokens_seen": 759913728,
+      "step": 3150
+    },
+    {
+      "epoch": 1.3684409211023028,
+      "grad_norm": 0.15155859962967053,
+      "learning_rate": 5.6859431076864755e-05,
+      "loss": 0.2056,
+      "num_input_tokens_seen": 765009632,
+      "step": 3171
+    },
+    {
+      "epoch": 1.3775009437523593,
+      "grad_norm": 0.154719416013354,
+      "learning_rate": 5.6389055353368826e-05,
+      "loss": 0.2056,
+      "num_input_tokens_seen": 770016704,
+      "step": 3192
+    },
+    {
+      "epoch": 1.386560966402416,
+      "grad_norm": 0.16028731910302912,
+      "learning_rate": 5.591810408770493e-05,
+      "loss": 0.2037,
+      "num_input_tokens_seen": 775197264,
+      "step": 3213
+    },
+    {
+      "epoch": 1.3956209890524727,
+      "grad_norm": 0.15645057759509218,
+      "learning_rate": 5.544661970434696e-05,
+      "loss": 0.2042,
+      "num_input_tokens_seen": 780209328,
+      "step": 3234
+    },
+    {
+      "epoch": 1.4046810117025292,
+      "grad_norm": 0.17948486028711083,
+      "learning_rate": 5.497464467579351e-05,
+      "loss": 0.2011,
+      "num_input_tokens_seen": 785402112,
+      "step": 3255
+    },
+    {
+      "epoch": 1.4137410343525858,
+      "grad_norm": 0.16643670433003308,
+      "learning_rate": 5.450222151874166e-05,
+      "loss": 0.2015,
+      "num_input_tokens_seen": 790429216,
+      "step": 3276
+    },
+    {
+      "epoch": 1.4228010570026426,
+      "grad_norm": 0.17345996800344896,
+      "learning_rate": 5.402939279025705e-05,
+      "loss": 0.2005,
+      "num_input_tokens_seen": 795543264,
+      "step": 3297
+    },
+    {
+      "epoch": 1.4318610796526992,
+      "grad_norm": 0.1663960297870033,
+      "learning_rate": 5.355620108394018e-05,
+      "loss": 0.2052,
+      "num_input_tokens_seen": 800533200,
+      "step": 3318
+    },
+    {
+      "epoch": 1.4409211023027557,
+      "grad_norm": 0.15958882963062815,
+      "learning_rate": 5.308268902608958e-05,
+      "loss": 0.2042,
+      "num_input_tokens_seen": 805542720,
+      "step": 3339
+    },
+    {
+      "epoch": 1.4499811249528123,
+      "grad_norm": 0.17053093118312482,
+      "learning_rate": 5.2608899271861765e-05,
+      "loss": 0.1984,
+      "num_input_tokens_seen": 810549376,
+      "step": 3360
+    },
+    {
+      "epoch": 1.459041147602869,
+      "grad_norm": 0.1731330043830458,
+      "learning_rate": 5.213487450142892e-05,
+      "loss": 0.2038,
+      "num_input_tokens_seen": 815599232,
+      "step": 3381
+    },
+    {
+      "epoch": 1.4681011702529256,
+      "grad_norm": 0.17941197802062514,
+      "learning_rate": 5.166065741613402e-05,
+      "loss": 0.2012,
+      "num_input_tokens_seen": 820700608,
+      "step": 3402
+    },
+    {
+      "epoch": 1.4771611929029822,
+      "grad_norm": 0.1844938407002505,
+      "learning_rate": 5.118629073464424e-05,
+      "loss": 0.1987,
+      "num_input_tokens_seen": 825686176,
+      "step": 3423
+    },
+    {
+      "epoch": 1.486221215553039,
+      "grad_norm": 0.1748567417166297,
+      "learning_rate": 5.071181718910283e-05,
+      "loss": 0.1986,
+      "num_input_tokens_seen": 830730000,
+      "step": 3444
+    },
+    {
+      "epoch": 1.4952812382030956,
+      "grad_norm": 0.15694569688029672,
+      "learning_rate": 5.023727952127954e-05,
+      "loss": 0.1987,
+      "num_input_tokens_seen": 835738032,
+      "step": 3465
+    },
+    {
+      "epoch": 1.5043412608531521,
+      "grad_norm": 0.18575993893540607,
+      "learning_rate": 4.976272047872046e-05,
+      "loss": 0.1952,
+      "num_input_tokens_seen": 840806528,
+      "step": 3486
+    },
+    {
+      "epoch": 1.513401283503209,
+      "grad_norm": 0.16316391964141339,
+      "learning_rate": 4.9288182810897184e-05,
+      "loss": 0.1957,
+      "num_input_tokens_seen": 845877808,
+      "step": 3507
+    },
+    {
+      "epoch": 1.5224613061532652,
+      "grad_norm": 0.1809977532876625,
+      "learning_rate": 4.8813709265355766e-05,
+      "loss": 0.1957,
+      "num_input_tokens_seen": 851002432,
+      "step": 3528
+    },
+    {
+      "epoch": 1.531521328803322,
+      "grad_norm": 0.15896204329046001,
+      "learning_rate": 4.8339342583866005e-05,
+      "loss": 0.197,
+      "num_input_tokens_seen": 856037440,
+      "step": 3549
+    },
+    {
+      "epoch": 1.5405813514533786,
+      "grad_norm": 0.1848696286617871,
+      "learning_rate": 4.7865125498571086e-05,
+      "loss": 0.1957,
+      "num_input_tokens_seen": 860972624,
+      "step": 3570
+    },
+    {
+      "epoch": 1.5496413741034352,
+      "grad_norm": 0.16411859849940666,
+      "learning_rate": 4.739110072813823e-05,
+      "loss": 0.1926,
+      "num_input_tokens_seen": 866078128,
+      "step": 3591
+    },
+    {
+      "epoch": 1.558701396753492,
+      "grad_norm": 0.15293153546751434,
+      "learning_rate": 4.6917310973910425e-05,
+      "loss": 0.1934,
+      "num_input_tokens_seen": 871290720,
+      "step": 3612
+    },
+    {
+      "epoch": 1.5677614194035485,
+      "grad_norm": 0.18580264173261662,
+      "learning_rate": 4.6443798916059836e-05,
+      "loss": 0.1961,
+      "num_input_tokens_seen": 876353920,
+      "step": 3633
+    },
+    {
+      "epoch": 1.576821442053605,
+      "grad_norm": 0.16117670144515006,
+      "learning_rate": 4.597060720974298e-05,
+      "loss": 0.1902,
+      "num_input_tokens_seen": 881469536,
+      "step": 3654
+    },
+    {
+      "epoch": 1.5858814647036619,
+      "grad_norm": 0.1821844142116438,
+      "learning_rate": 4.549777848125833e-05,
+      "loss": 0.1971,
+      "num_input_tokens_seen": 886532048,
+      "step": 3675
+    },
+    {
+      "epoch": 1.5949414873537184,
+      "grad_norm": 0.188981157327872,
+      "learning_rate": 4.50253553242065e-05,
+      "loss": 0.1952,
+      "num_input_tokens_seen": 891565152,
+      "step": 3696
+    },
+    {
+      "epoch": 1.604001510003775,
+      "grad_norm": 0.1663775536476532,
+      "learning_rate": 4.4553380295653053e-05,
+      "loss": 0.1908,
+      "num_input_tokens_seen": 896603568,
+      "step": 3717
+    },
+    {
+      "epoch": 1.6130615326538318,
+      "grad_norm": 0.16695660636413406,
+      "learning_rate": 4.40818959122951e-05,
+      "loss": 0.1945,
+      "num_input_tokens_seen": 901703264,
+      "step": 3738
+    },
+    {
+      "epoch": 1.6221215553038881,
+      "grad_norm": 0.18003132042487852,
+      "learning_rate": 4.361094464663118e-05,
+      "loss": 0.1911,
+      "num_input_tokens_seen": 906846256,
+      "step": 3759
+    },
+    {
+      "epoch": 1.631181577953945,
+      "grad_norm": 0.16377146934729214,
+      "learning_rate": 4.3140568923135264e-05,
+      "loss": 0.193,
+      "num_input_tokens_seen": 911964272,
+      "step": 3780
+    },
+    {
+      "epoch": 1.6402416006040015,
+      "grad_norm": 0.1711801561805431,
+      "learning_rate": 4.267081111443501e-05,
+      "loss": 0.1898,
+      "num_input_tokens_seen": 917101840,
+      "step": 3801
+    },
+    {
+      "epoch": 1.649301623254058,
+      "grad_norm": 0.1743609898038798,
+      "learning_rate": 4.22017135374948e-05,
+      "loss": 0.1852,
+      "num_input_tokens_seen": 922205664,
+      "step": 3822
+    },
+    {
+      "epoch": 1.6583616459041148,
+      "grad_norm": 0.17938627926996303,
+      "learning_rate": 4.1733318449803624e-05,
+      "loss": 0.1863,
+      "num_input_tokens_seen": 927302560,
+      "step": 3843
+    },
+    {
+      "epoch": 1.6674216685541714,
+      "grad_norm": 0.16947333759434738,
+      "learning_rate": 4.1265668045568495e-05,
+      "loss": 0.1882,
+      "num_input_tokens_seen": 932325424,
+      "step": 3864
+    },
+    {
+      "epoch": 1.676481691204228,
+      "grad_norm": 0.16639553173104588,
+      "learning_rate": 4.079880445191351e-05,
+      "loss": 0.1893,
+      "num_input_tokens_seen": 937438464,
+      "step": 3885
+    },
+    {
+      "epoch": 1.6855417138542848,
+      "grad_norm": 0.14651023615133163,
+      "learning_rate": 4.033276972508484e-05,
+      "loss": 0.1885,
+      "num_input_tokens_seen": 942617840,
+      "step": 3906
+    },
+    {
+      "epoch": 1.6946017365043413,
+      "grad_norm": 0.17812367097504705,
+      "learning_rate": 3.9867605846662256e-05,
+      "loss": 0.1883,
+      "num_input_tokens_seen": 947823200,
+      "step": 3927
+    },
+    {
+      "epoch": 1.7036617591543979,
+      "grad_norm": 0.1872194452488721,
+      "learning_rate": 3.940335471977734e-05,
+      "loss": 0.1871,
+      "num_input_tokens_seen": 952872784,
+      "step": 3948
+    },
+    {
+      "epoch": 1.7127217818044547,
+      "grad_norm": 0.1643081487678093,
+      "learning_rate": 3.89400581653387e-05,
+      "loss": 0.1853,
+      "num_input_tokens_seen": 957908608,
+      "step": 3969
+    },
+    {
+      "epoch": 1.721781804454511,
+      "grad_norm": 0.1753318656372752,
+      "learning_rate": 3.847775791826468e-05,
+      "loss": 0.1862,
+      "num_input_tokens_seen": 962972208,
+      "step": 3990
+    },
+    {
+      "epoch": 1.7308418271045678,
+      "grad_norm": 0.15851578473823177,
+      "learning_rate": 3.801649562372371e-05,
+      "loss": 0.1913,
+      "num_input_tokens_seen": 968020256,
+      "step": 4011
+    },
+    {
+      "epoch": 1.7399018497546244,
+      "grad_norm": 0.1812244935434252,
+      "learning_rate": 3.755631283338287e-05,
+      "loss": 0.1908,
+      "num_input_tokens_seen": 973116912,
+      "step": 4032
+    },
+    {
+      "epoch": 1.748961872404681,
+      "grad_norm": 0.16265272189557067,
+      "learning_rate": 3.709725100166482e-05,
+      "loss": 0.1839,
+      "num_input_tokens_seen": 978276224,
+      "step": 4053
+    },
+    {
+      "epoch": 1.7580218950547377,
+      "grad_norm": 0.16695166226650535,
+      "learning_rate": 3.663935148201341e-05,
+      "loss": 0.1869,
+      "num_input_tokens_seen": 983499184,
+      "step": 4074
+    },
+    {
+      "epoch": 1.7670819177047943,
+      "grad_norm": 0.17046617487207735,
+      "learning_rate": 3.618265552316849e-05,
+      "loss": 0.1884,
+      "num_input_tokens_seen": 988511216,
+      "step": 4095
+    },
+    {
+      "epoch": 1.7761419403548508,
+      "grad_norm": 0.16853521697476523,
+      "learning_rate": 3.572720426545017e-05,
+      "loss": 0.1863,
+      "num_input_tokens_seen": 993542272,
+      "step": 4116
+    },
+    {
+      "epoch": 1.7852019630049076,
+      "grad_norm": 0.16196055724715774,
+      "learning_rate": 3.5273038737052675e-05,
+      "loss": 0.1884,
+      "num_input_tokens_seen": 998561584,
+      "step": 4137
+    },
+    {
+      "epoch": 1.794261985654964,
+      "grad_norm": 0.17704958458091835,
+      "learning_rate": 3.482019985034861e-05,
+      "loss": 0.1815,
+      "num_input_tokens_seen": 1003535696,
+      "step": 4158
+    },
+    {
+      "epoch": 1.8033220083050208,
+      "grad_norm": 0.17212954264417213,
+      "learning_rate": 3.43687283982033e-05,
+      "loss": 0.1798,
+      "num_input_tokens_seen": 1008610432,
+      "step": 4179
+    },
+    {
+      "epoch": 1.8123820309550775,
+      "grad_norm": 0.1642508897074481,
+      "learning_rate": 3.391866505030009e-05,
+      "loss": 0.1797,
+      "num_input_tokens_seen": 1013577840,
+      "step": 4200
+    },
+    {
+      "epoch": 1.821442053605134,
+      "grad_norm": 0.1895193964135349,
+      "learning_rate": 3.347005034947681e-05,
+      "loss": 0.1773,
+      "num_input_tokens_seen": 1018549888,
+      "step": 4221
+    },
+    {
+      "epoch": 1.8305020762551907,
+      "grad_norm": 0.18935672208270557,
+      "learning_rate": 3.3022924708073524e-05,
+      "loss": 0.1828,
+      "num_input_tokens_seen": 1023498368,
+      "step": 4242
+    },
+    {
+      "epoch": 1.8395620989052472,
+      "grad_norm": 0.15473627402095172,
+      "learning_rate": 3.257732840429206e-05,
+      "loss": 0.18,
+      "num_input_tokens_seen": 1028542992,
+      "step": 4263
+    },
+    {
+      "epoch": 1.8486221215553038,
+      "grad_norm": 0.17782850850732204,
+      "learning_rate": 3.2133301578567646e-05,
+      "loss": 0.1825,
+      "num_input_tokens_seen": 1033574288,
+      "step": 4284
+    },
+    {
+      "epoch": 1.8576821442053606,
+      "grad_norm": 0.17879475744218412,
+      "learning_rate": 3.169088422995304e-05,
+      "loss": 0.1776,
+      "num_input_tokens_seen": 1038606208,
+      "step": 4305
+    },
+    {
+      "epoch": 1.8667421668554172,
+      "grad_norm": 0.16166293718253705,
+      "learning_rate": 3.125011621251516e-05,
+      "loss": 0.1768,
+      "num_input_tokens_seen": 1043770704,
+      "step": 4326
+    },
+    {
+      "epoch": 1.8758021895054737,
+      "grad_norm": 0.1607230134601091,
+      "learning_rate": 3.081103723174515e-05,
+      "loss": 0.1778,
+      "num_input_tokens_seen": 1048829664,
+      "step": 4347
+    },
+    {
+      "epoch": 1.8848622121555305,
+      "grad_norm": 0.159447656379203,
+      "learning_rate": 3.0373686840981397e-05,
+      "loss": 0.1788,
+      "num_input_tokens_seen": 1053950224,
+      "step": 4368
+    },
+    {
+      "epoch": 1.8939222348055869,
+      "grad_norm": 0.1674766446494019,
+      "learning_rate": 2.9938104437846572e-05,
+      "loss": 0.176,
+      "num_input_tokens_seen": 1059119888,
+      "step": 4389
+    },
+    {
+      "epoch": 1.9029822574556436,
+      "grad_norm": 0.17753675611302996,
+      "learning_rate": 2.950432926069857e-05,
+      "loss": 0.1783,
+      "num_input_tokens_seen": 1064177088,
+      "step": 4410
+    },
+    {
+      "epoch": 1.9120422801057002,
+      "grad_norm": 0.17087252328331373,
+      "learning_rate": 2.9072400385095865e-05,
+      "loss": 0.178,
+      "num_input_tokens_seen": 1069200928,
+      "step": 4431
+    },
+    {
+      "epoch": 1.9211023027557568,
+      "grad_norm": 0.16133227423173738,
+      "learning_rate": 2.864235672027741e-05,
+      "loss": 0.1759,
+      "num_input_tokens_seen": 1074313840,
+      "step": 4452
+    },
+    {
+      "epoch": 1.9301623254058136,
+      "grad_norm": 0.1865580464555286,
+      "learning_rate": 2.8214237005657627e-05,
+      "loss": 0.1769,
+      "num_input_tokens_seen": 1079348080,
+      "step": 4473
+    },
+    {
+      "epoch": 1.9392223480558701,
+      "grad_norm": 0.17483638643553473,
+      "learning_rate": 2.7788079807336692e-05,
+      "loss": 0.1761,
+      "num_input_tokens_seen": 1084415072,
+      "step": 4494
+    },
+    {
+      "epoch": 1.9482823707059267,
+      "grad_norm": 0.16127203478332483,
+      "learning_rate": 2.7363923514626367e-05,
+      "loss": 0.1762,
+      "num_input_tokens_seen": 1089576528,
+      "step": 4515
+    },
+    {
+      "epoch": 1.9573423933559835,
+      "grad_norm": 0.1818665955450248,
+      "learning_rate": 2.6941806336591808e-05,
+      "loss": 0.1715,
+      "num_input_tokens_seen": 1094741664,
+      "step": 4536
+    },
+    {
+      "epoch": 1.96640241600604,
+      "grad_norm": 0.16510174569454042,
+      "learning_rate": 2.6521766298609584e-05,
+      "loss": 0.1728,
+      "num_input_tokens_seen": 1099708896,
+      "step": 4557
+    },
+    {
+      "epoch": 1.9754624386560966,
+      "grad_norm": 0.17393602608748607,
+      "learning_rate": 2.610384123894229e-05,
+      "loss": 0.175,
+      "num_input_tokens_seen": 1104824512,
+      "step": 4578
+    },
+    {
+      "epoch": 1.9845224613061534,
+      "grad_norm": 0.18901915034549496,
+      "learning_rate": 2.568806880532991e-05,
+      "loss": 0.1736,
+      "num_input_tokens_seen": 1109954160,
+      "step": 4599
+    },
+    {
+      "epoch": 1.9935824839562097,
+      "grad_norm": 0.19336693087348367,
+      "learning_rate": 2.5274486451598565e-05,
+      "loss": 0.1704,
+      "num_input_tokens_seen": 1115130992,
+      "step": 4620
+    },
+    {
+      "epoch": 2.003020007550019,
+      "grad_norm": 0.192558427240515,
+      "learning_rate": 2.4863131434286342e-05,
+      "loss": 0.1548,
+      "num_input_tokens_seen": 1120294784,
+      "step": 4641
+    },
+    {
+      "epoch": 2.0120800302000754,
+      "grad_norm": 0.19360993518356076,
+      "learning_rate": 2.4454040809287342e-05,
+      "loss": 0.1188,
+      "num_input_tokens_seen": 1125375728,
+      "step": 4662
+    },
+    {
+      "epoch": 2.021140052850132,
+      "grad_norm": 0.19346692314512148,
+      "learning_rate": 2.4047251428513485e-05,
+      "loss": 0.1176,
+      "num_input_tokens_seen": 1130663488,
+      "step": 4683
+    },
+    {
+      "epoch": 2.0302000755001886,
+      "grad_norm": 0.1915500646603155,
+      "learning_rate": 2.364279993657487e-05,
+      "loss": 0.1166,
+      "num_input_tokens_seen": 1135729856,
+      "step": 4704
+    },
+    {
+      "epoch": 2.0392600981502453,
+      "grad_norm": 0.21320689744431512,
+      "learning_rate": 2.3240722767478657e-05,
+      "loss": 0.1129,
+      "num_input_tokens_seen": 1140728768,
+      "step": 4725
+    },
+    {
+      "epoch": 2.048320120800302,
+      "grad_norm": 0.20002232427856995,
+      "learning_rate": 2.2841056141347038e-05,
+      "loss": 0.1122,
+      "num_input_tokens_seen": 1145810672,
+      "step": 4746
+    },
+    {
+      "epoch": 2.0573801434503585,
+      "grad_norm": 0.21228559927967805,
+      "learning_rate": 2.2443836061154415e-05,
+      "loss": 0.1145,
+      "num_input_tokens_seen": 1150862064,
+      "step": 4767
+    },
+    {
+      "epoch": 2.0664401661004153,
+      "grad_norm": 0.19792768108065947,
+      "learning_rate": 2.2049098309484195e-05,
+      "loss": 0.1153,
+      "num_input_tokens_seen": 1155954544,
+      "step": 4788
+    },
+    {
+      "epoch": 2.075500188750472,
+      "grad_norm": 0.21247296887779493,
+      "learning_rate": 2.1656878445305447e-05,
+      "loss": 0.1152,
+      "num_input_tokens_seen": 1161054256,
+      "step": 4809
+    },
+    {
+      "epoch": 2.0845602114005284,
+      "grad_norm": 0.19109010163603735,
+      "learning_rate": 2.1267211800769528e-05,
+      "loss": 0.1148,
+      "num_input_tokens_seen": 1166056688,
+      "step": 4830
+    },
+    {
+      "epoch": 2.093620234050585,
+      "grad_norm": 0.19679782828606215,
+      "learning_rate": 2.088013347802738e-05,
+      "loss": 0.1119,
+      "num_input_tokens_seen": 1171231104,
+      "step": 4851
+    },
+    {
+      "epoch": 2.102680256700642,
+      "grad_norm": 0.2128224999872872,
+      "learning_rate": 2.0495678346067414e-05,
+      "loss": 0.1101,
+      "num_input_tokens_seen": 1176284976,
+      "step": 4872
+    },
+    {
+      "epoch": 2.1117402793506983,
+      "grad_norm": 0.2123206811047115,
+      "learning_rate": 2.011388103757442e-05,
+      "loss": 0.1139,
+      "num_input_tokens_seen": 1181400944,
+      "step": 4893
+    },
+    {
+      "epoch": 2.120800302000755,
+      "grad_norm": 0.2071017368245751,
+      "learning_rate": 1.973477594580977e-05,
+      "loss": 0.1116,
+      "num_input_tokens_seen": 1186527776,
+      "step": 4914
+    },
+    {
+      "epoch": 2.1298603246508114,
+      "grad_norm": 0.17323287993849096,
+      "learning_rate": 1.9358397221513176e-05,
+      "loss": 0.112,
+      "num_input_tokens_seen": 1191661680,
+      "step": 4935
+    },
+    {
+      "epoch": 2.138920347300868,
+      "grad_norm": 0.20213151950682676,
+      "learning_rate": 1.8984778769826316e-05,
+      "loss": 0.1106,
+      "num_input_tokens_seen": 1196759648,
+      "step": 4956
+    },
+    {
+      "epoch": 2.147980369950925,
+      "grad_norm": 0.19700292148625387,
+      "learning_rate": 1.8613954247238586e-05,
+      "loss": 0.1124,
+      "num_input_tokens_seen": 1201857104,
+      "step": 4977
+    },
+    {
+      "epoch": 2.1570403926009813,
+      "grad_norm": 0.21527000496492768,
+      "learning_rate": 1.82459570585552e-05,
+      "loss": 0.1136,
+      "num_input_tokens_seen": 1206927520,
+      "step": 4998
+    },
+    {
+      "epoch": 2.157903251900987,
+      "eval_loss": 0.19485081732273102,
+      "eval_runtime": 529.4687,
+      "eval_samples_per_second": 17.331,
+      "eval_steps_per_second": 1.084,
+      "num_input_tokens_seen": 1207385424,
+      "step": 5000
+    },
+    {
+      "epoch": 2.166100415251038,
+      "grad_norm": 0.2275158963594303,
+      "learning_rate": 1.7880820353888056e-05,
+      "loss": 0.1102,
+      "num_input_tokens_seen": 1211875824,
+      "step": 5019
+    },
+    {
+      "epoch": 2.175160437901095,
+      "grad_norm": 0.20450931488489404,
+      "learning_rate": 1.751857702566944e-05,
+      "loss": 0.113,
+      "num_input_tokens_seen": 1216954688,
+      "step": 5040
+    },
+    {
+      "epoch": 2.1842204605511513,
+      "grad_norm": 0.21173943893990088,
+      "learning_rate": 1.7159259705689e-05,
+      "loss": 0.1104,
+      "num_input_tokens_seen": 1221976560,
+      "step": 5061
+    },
+    {
+      "epoch": 2.193280483201208,
+      "grad_norm": 0.20717537063008165,
+      "learning_rate": 1.6802900762154267e-05,
+      "loss": 0.1152,
+      "num_input_tokens_seen": 1226975776,
+      "step": 5082
+    },
+    {
+      "epoch": 2.2023405058512644,
+      "grad_norm": 0.19831781893791461,
+      "learning_rate": 1.644953229677474e-05,
+      "loss": 0.1097,
+      "num_input_tokens_seen": 1231998784,
+      "step": 5103
+    },
+    {
+      "epoch": 2.211400528501321,
+      "grad_norm": 0.18492554370023317,
+      "learning_rate": 1.609918614187009e-05,
+      "loss": 0.1111,
+      "num_input_tokens_seen": 1236990864,
+      "step": 5124
+    },
+    {
+      "epoch": 2.220460551151378,
+      "grad_norm": 0.20016085842409992,
+      "learning_rate": 1.575189385750271e-05,
+      "loss": 0.1104,
+      "num_input_tokens_seen": 1242051280,
+      "step": 5145
+    },
+    {
+      "epoch": 2.2295205738014343,
+      "grad_norm": 0.2070887723839001,
+      "learning_rate": 1.540768672863468e-05,
+      "loss": 0.1075,
+      "num_input_tokens_seen": 1247127040,
+      "step": 5166
+    },
+    {
+      "epoch": 2.238580596451491,
+      "grad_norm": 0.1925213910719394,
+      "learning_rate": 1.5066595762309477e-05,
+      "loss": 0.1093,
+      "num_input_tokens_seen": 1252158672,
+      "step": 5187
+    },
+    {
+      "epoch": 2.247640619101548,
+      "grad_norm": 0.205831347337121,
+      "learning_rate": 1.4728651684858834e-05,
+      "loss": 0.1126,
+      "num_input_tokens_seen": 1257321184,
+      "step": 5208
+    },
+    {
+      "epoch": 2.2567006417516042,
+      "grad_norm": 0.19926488557298117,
+      "learning_rate": 1.4393884939134833e-05,
+      "loss": 0.1064,
+      "num_input_tokens_seen": 1262315984,
+      "step": 5229
+    },
+    {
+      "epoch": 2.265760664401661,
+      "grad_norm": 0.18546254868875062,
+      "learning_rate": 1.4062325681767469e-05,
+      "loss": 0.1096,
+      "num_input_tokens_seen": 1267351616,
+      "step": 5250
+    },
+    {
+      "epoch": 2.274820687051718,
+      "grad_norm": 0.21880629906349583,
+      "learning_rate": 1.3734003780448218e-05,
+      "loss": 0.1089,
+      "num_input_tokens_seen": 1272350592,
+      "step": 5271
+    },
+    {
+      "epoch": 2.283880709701774,
+      "grad_norm": 0.1996371660776893,
+      "learning_rate": 1.340894881123932e-05,
+      "loss": 0.1093,
+      "num_input_tokens_seen": 1277314160,
+      "step": 5292
+    },
+    {
+      "epoch": 2.292940732351831,
+      "grad_norm": 0.18322023913039737,
+      "learning_rate": 1.308719005590957e-05,
+      "loss": 0.1064,
+      "num_input_tokens_seen": 1282348896,
+      "step": 5313
+    },
+    {
+      "epoch": 2.3020007550018873,
+      "grad_norm": 0.19825429674508396,
+      "learning_rate": 1.276875649929654e-05,
+      "loss": 0.1103,
+      "num_input_tokens_seen": 1287503120,
+      "step": 5334
+    },
+    {
+      "epoch": 2.311060777651944,
+      "grad_norm": 0.20100225641083314,
+      "learning_rate": 1.2453676826695532e-05,
+      "loss": 0.1077,
+      "num_input_tokens_seen": 1292488224,
+      "step": 5355
+    },
+    {
+      "epoch": 2.320120800302001,
+      "grad_norm": 0.19869949736224346,
+      "learning_rate": 1.2141979421275545e-05,
+      "loss": 0.1051,
+      "num_input_tokens_seen": 1297613792,
+      "step": 5376
+    },
+    {
+      "epoch": 2.329180822952057,
+      "grad_norm": 0.20145867765354752,
+      "learning_rate": 1.1833692361522459e-05,
+      "loss": 0.1063,
+      "num_input_tokens_seen": 1302765200,
+      "step": 5397
+    },
+    {
+      "epoch": 2.338240845602114,
+      "grad_norm": 0.20680505787617295,
+      "learning_rate": 1.1528843418709622e-05,
+      "loss": 0.1073,
+      "num_input_tokens_seen": 1307780896,
+      "step": 5418
+    },
+    {
+      "epoch": 2.3473008682521708,
+      "grad_norm": 0.23847500451035963,
+      "learning_rate": 1.1227460054396177e-05,
+      "loss": 0.1076,
+      "num_input_tokens_seen": 1312916864,
+      "step": 5439
+    },
+    {
+      "epoch": 2.356360890902227,
+      "grad_norm": 0.21518454470567003,
+      "learning_rate": 1.0929569417953278e-05,
+      "loss": 0.1049,
+      "num_input_tokens_seen": 1317924528,
+      "step": 5460
+    },
+    {
+      "epoch": 2.365420913552284,
+      "grad_norm": 0.19953783012904103,
+      "learning_rate": 1.0635198344118296e-05,
+      "loss": 0.1038,
+      "num_input_tokens_seen": 1322892896,
+      "step": 5481
+    },
+    {
+      "epoch": 2.3744809362023407,
+      "grad_norm": 0.20097656219123833,
+      "learning_rate": 1.034437335057762e-05,
+      "loss": 0.1049,
+      "num_input_tokens_seen": 1328000960,
+      "step": 5502
+    },
+    {
+      "epoch": 2.383540958852397,
+      "grad_norm": 0.20223248741837738,
+      "learning_rate": 1.005712063557776e-05,
+      "loss": 0.1026,
+      "num_input_tokens_seen": 1333104928,
+      "step": 5523
+    },
+    {
+      "epoch": 2.392600981502454,
+      "grad_norm": 0.184389360298103,
+      "learning_rate": 9.773466075565457e-06,
+      "loss": 0.1061,
+      "num_input_tokens_seen": 1338094928,
+      "step": 5544
+    },
+    {
+      "epoch": 2.40166100415251,
+      "grad_norm": 0.18202586925329933,
+      "learning_rate": 9.493435222856556e-06,
+      "loss": 0.1078,
+      "num_input_tokens_seen": 1343094352,
+      "step": 5565
+    },
+    {
+      "epoch": 2.410721026802567,
+      "grad_norm": 0.21238526697964133,
+      "learning_rate": 9.21705330333426e-06,
+      "loss": 0.1021,
+      "num_input_tokens_seen": 1348209008,
+      "step": 5586
+    },
+    {
+      "epoch": 2.4197810494526237,
+      "grad_norm": 0.2033611614783377,
+      "learning_rate": 8.944345214176675e-06,
+      "loss": 0.105,
+      "num_input_tokens_seen": 1353281712,
+      "step": 5607
+    },
+    {
+      "epoch": 2.42884107210268,
+      "grad_norm": 0.19144661395169293,
+      "learning_rate": 8.675335521614036e-06,
+      "loss": 0.1039,
+      "num_input_tokens_seen": 1358325728,
+      "step": 5628
+    },
+    {
+      "epoch": 2.437901094752737,
+      "grad_norm": 0.20545555012965147,
+      "learning_rate": 8.410048458715763e-06,
+      "loss": 0.1026,
+      "num_input_tokens_seen": 1363274864,
+      "step": 5649
+    },
+    {
+      "epoch": 2.4469611174027937,
+      "grad_norm": 0.20596285141748574,
+      "learning_rate": 8.148507923207377e-06,
+      "loss": 0.1046,
+      "num_input_tokens_seen": 1368398176,
+      "step": 5670
+    },
+    {
+      "epoch": 2.45602114005285,
+      "grad_norm": 0.21097019629979452,
+      "learning_rate": 7.890737475317817e-06,
+      "loss": 0.1062,
+      "num_input_tokens_seen": 1373421664,
+      "step": 5691
+    },
+    {
+      "epoch": 2.465081162702907,
+      "grad_norm": 0.1903944548607354,
+      "learning_rate": 7.636760335657056e-06,
+      "loss": 0.1005,
+      "num_input_tokens_seen": 1378386688,
+      "step": 5712
+    },
+    {
+      "epoch": 2.4741411853529636,
+      "grad_norm": 0.19609864215469505,
+      "learning_rate": 7.38659938312432e-06,
+      "loss": 0.1008,
+      "num_input_tokens_seen": 1383515360,
+      "step": 5733
+    },
+    {
+      "epoch": 2.48320120800302,
+      "grad_norm": 0.18901755025774616,
+      "learning_rate": 7.140277152847103e-06,
+      "loss": 0.1012,
+      "num_input_tokens_seen": 1388651712,
+      "step": 5754
+    },
+    {
+      "epoch": 2.4922612306530767,
+      "grad_norm": 0.2089521843263624,
+      "learning_rate": 6.89781583415115e-06,
+      "loss": 0.1004,
+      "num_input_tokens_seen": 1393819168,
+      "step": 5775
+    },
+    {
+      "epoch": 2.501321253303133,
+      "grad_norm": 0.20297486453222555,
+      "learning_rate": 6.659237268561569e-06,
+      "loss": 0.1058,
+      "num_input_tokens_seen": 1399005008,
+      "step": 5796
+    },
+    {
+      "epoch": 2.51038127595319,
+      "grad_norm": 0.1950872269091398,
+      "learning_rate": 6.424562947835367e-06,
+      "loss": 0.0996,
+      "num_input_tokens_seen": 1404075040,
+      "step": 5817
+    },
+    {
+      "epoch": 2.5194412986032466,
+      "grad_norm": 0.19137900590478205,
+      "learning_rate": 6.193814012025278e-06,
+      "loss": 0.098,
+      "num_input_tokens_seen": 1409145760,
+      "step": 5838
+    },
+    {
+      "epoch": 2.5285013212533034,
+      "grad_norm": 0.21343987395986905,
+      "learning_rate": 5.967011247575532e-06,
+      "loss": 0.1053,
+      "num_input_tokens_seen": 1414225568,
+      "step": 5859
+    },
+    {
+      "epoch": 2.5375613439033597,
+      "grad_norm": 0.21335949851815006,
+      "learning_rate": 5.744175085449338e-06,
+      "loss": 0.1021,
+      "num_input_tokens_seen": 1419339216,
+      "step": 5880
+    },
+    {
+      "epoch": 2.5466213665534165,
+      "grad_norm": 0.19658196939034006,
+      "learning_rate": 5.525325599288356e-06,
+      "loss": 0.1003,
+      "num_input_tokens_seen": 1424423024,
+      "step": 5901
+    },
+    {
+      "epoch": 2.555681389203473,
+      "grad_norm": 0.1831370056225536,
+      "learning_rate": 5.310482503604497e-06,
+      "loss": 0.1039,
+      "num_input_tokens_seen": 1429360512,
+      "step": 5922
+    },
+    {
+      "epoch": 2.5647414118535297,
+      "grad_norm": 0.21013156618721565,
+      "learning_rate": 5.09966515200393e-06,
+      "loss": 0.1034,
+      "num_input_tokens_seen": 1434443216,
+      "step": 5943
+    },
+    {
+      "epoch": 2.5738014345035864,
+      "grad_norm": 0.2204689190211589,
+      "learning_rate": 4.892892535443655e-06,
+      "loss": 0.1025,
+      "num_input_tokens_seen": 1439693152,
+      "step": 5964
+    },
+    {
+      "epoch": 2.582861457153643,
+      "grad_norm": 0.20888767875138448,
+      "learning_rate": 4.690183280520777e-06,
+      "loss": 0.1041,
+      "num_input_tokens_seen": 1444742640,
+      "step": 5985
+    },
+    {
+      "epoch": 2.5919214798036996,
+      "grad_norm": 0.20314033156230726,
+      "learning_rate": 4.491555647794609e-06,
+      "loss": 0.1035,
+      "num_input_tokens_seen": 1449817024,
+      "step": 6006
+    },
+    {
+      "epoch": 2.600981502453756,
+      "grad_norm": 0.1878500846044568,
+      "learning_rate": 4.297027530141634e-06,
+      "loss": 0.102,
+      "num_input_tokens_seen": 1454966656,
+      "step": 6027
+    },
+    {
+      "epoch": 2.6100415251038127,
+      "grad_norm": 0.1689243463349296,
+      "learning_rate": 4.106616451143719e-06,
+      "loss": 0.0968,
+      "num_input_tokens_seen": 1460107904,
+      "step": 6048
+    },
+    {
+      "epoch": 2.6191015477538695,
+      "grad_norm": 0.20642026958771845,
+      "learning_rate": 3.9203395635095615e-06,
+      "loss": 0.1025,
+      "num_input_tokens_seen": 1465329712,
+      "step": 6069
+    },
+    {
+      "epoch": 2.6281615704039263,
+      "grad_norm": 0.18586990386683522,
+      "learning_rate": 3.7382136475294592e-06,
+      "loss": 0.0992,
+      "num_input_tokens_seen": 1470486400,
+      "step": 6090
+    },
+    {
+      "epoch": 2.6372215930539826,
+      "grad_norm": 0.2145218277764739,
+      "learning_rate": 3.5602551095638094e-06,
+      "loss": 0.1014,
+      "num_input_tokens_seen": 1475481216,
+      "step": 6111
+    },
+    {
+      "epoch": 2.6462816157040394,
+      "grad_norm": 0.18413690443200365,
+      "learning_rate": 3.386479980565077e-06,
+      "loss": 0.097,
+      "num_input_tokens_seen": 1480509520,
+      "step": 6132
+    },
+    {
+      "epoch": 2.6553416383540958,
+      "grad_norm": 0.20568925987079073,
+      "learning_rate": 3.2169039146337455e-06,
+      "loss": 0.1011,
+      "num_input_tokens_seen": 1485415168,
+      "step": 6153
+    },
+    {
+      "epoch": 2.6644016610041525,
+      "grad_norm": 0.19689596480908558,
+      "learning_rate": 3.0515421876081364e-06,
+      "loss": 0.1003,
+      "num_input_tokens_seen": 1490580288,
+      "step": 6174
+    },
+    {
+      "epoch": 2.6734616836542093,
+      "grad_norm": 0.19998505506705416,
+      "learning_rate": 2.8904096956883396e-06,
+      "loss": 0.1011,
+      "num_input_tokens_seen": 1495724928,
+      "step": 6195
+    },
+    {
+      "epoch": 2.6825217063042657,
+      "grad_norm": 0.19403273255448156,
+      "learning_rate": 2.733520954094304e-06,
+      "loss": 0.0992,
+      "num_input_tokens_seen": 1500671568,
+      "step": 6216
+    },
+    {
+      "epoch": 2.6915817289543225,
+      "grad_norm": 0.2062968511222456,
+      "learning_rate": 2.580890095758276e-06,
+      "loss": 0.0985,
+      "num_input_tokens_seen": 1505736848,
+      "step": 6237
+    },
+    {
+      "epoch": 2.700641751604379,
+      "grad_norm": 0.18160540614114035,
+      "learning_rate": 2.4325308700516804e-06,
+      "loss": 0.0999,
+      "num_input_tokens_seen": 1510772384,
+      "step": 6258
+    },
+    {
+      "epoch": 2.7097017742544356,
+      "grad_norm": 0.1923201194653099,
+      "learning_rate": 2.288456641546549e-06,
+      "loss": 0.1015,
+      "num_input_tokens_seen": 1515840336,
+      "step": 6279
+    },
+    {
+      "epoch": 2.7187617969044924,
+      "grad_norm": 0.19463587674679012,
+      "learning_rate": 2.1486803888115802e-06,
+      "loss": 0.0952,
+      "num_input_tokens_seen": 1520795728,
+      "step": 6300
+    },
+    {
+      "epoch": 2.7278218195545487,
+      "grad_norm": 0.20675363777805839,
+      "learning_rate": 2.013214703242994e-06,
+      "loss": 0.1014,
+      "num_input_tokens_seen": 1525885232,
+      "step": 6321
+    },
+    {
+      "epoch": 2.7368818422046055,
+      "grad_norm": 0.20373174987364437,
+      "learning_rate": 1.8820717879303175e-06,
+      "loss": 0.0962,
+      "num_input_tokens_seen": 1531020736,
+      "step": 6342
+    },
+    {
+      "epoch": 2.7459418648546623,
+      "grad_norm": 0.1956195345947546,
+      "learning_rate": 1.7552634565570325e-06,
+      "loss": 0.0984,
+      "num_input_tokens_seen": 1536139280,
+      "step": 6363
+    },
+    {
+      "epoch": 2.7550018875047186,
+      "grad_norm": 0.1948987852214273,
+      "learning_rate": 1.6328011323364313e-06,
+      "loss": 0.0996,
+      "num_input_tokens_seen": 1541119392,
+      "step": 6384
+    },
+    {
+      "epoch": 2.7640619101547754,
+      "grad_norm": 0.20220064200986687,
+      "learning_rate": 1.5146958469825445e-06,
+      "loss": 0.098,
+      "num_input_tokens_seen": 1546172016,
+      "step": 6405
+    },
+    {
+      "epoch": 2.773121932804832,
+      "grad_norm": 0.18253057622469138,
+      "learning_rate": 1.4009582397163879e-06,
+      "loss": 0.0979,
+      "num_input_tokens_seen": 1551424800,
+      "step": 6426
+    },
+    {
+      "epoch": 2.7821819554548886,
+      "grad_norm": 0.19954203330015002,
+      "learning_rate": 1.2915985563075383e-06,
+      "loss": 0.096,
+      "num_input_tokens_seen": 1556510032,
+      "step": 6447
+    },
+    {
+      "epoch": 2.7912419781049453,
+      "grad_norm": 0.18349734934457243,
+      "learning_rate": 1.1866266481512234e-06,
+      "loss": 0.0995,
+      "num_input_tokens_seen": 1561425840,
+      "step": 6468
+    },
+    {
+      "epoch": 2.8003020007550017,
+      "grad_norm": 0.19583118554915796,
+      "learning_rate": 1.0860519713808082e-06,
+      "loss": 0.0979,
+      "num_input_tokens_seen": 1566437584,
+      "step": 6489
+    },
+    {
+      "epoch": 2.8093620234050585,
+      "grad_norm": 0.21286644366673166,
+      "learning_rate": 9.898835860160271e-07,
+      "loss": 0.0944,
+      "num_input_tokens_seen": 1571433728,
+      "step": 6510
+    },
+    {
+      "epoch": 2.8184220460551153,
+      "grad_norm": 0.18549288153723123,
+      "learning_rate": 8.981301551467924e-07,
+      "loss": 0.0949,
+      "num_input_tokens_seen": 1576510304,
+      "step": 6531
+    },
+    {
+      "epoch": 2.8274820687051716,
+      "grad_norm": 0.1969304866148859,
+      "learning_rate": 8.10799944152818e-07,
+      "loss": 0.0959,
+      "num_input_tokens_seen": 1581652480,
+      "step": 6552
+    },
+    {
+      "epoch": 2.8365420913552284,
+      "grad_norm": 0.19621694587220775,
+      "learning_rate": 7.279008199590543e-07,
+      "loss": 0.0995,
+      "num_input_tokens_seen": 1586710928,
+      "step": 6573
+    },
+    {
+      "epoch": 2.845602114005285,
+      "grad_norm": 0.19626099410771614,
+      "learning_rate": 6.494402503270158e-07,
+      "loss": 0.0973,
+      "num_input_tokens_seen": 1591751872,
+      "step": 6594
+    },
+    {
+      "epoch": 2.8546621366553415,
+      "grad_norm": 0.17530668226038035,
+      "learning_rate": 5.754253031820588e-07,
+      "loss": 0.0992,
+      "num_input_tokens_seen": 1596817344,
+      "step": 6615
+    },
+    {
+      "epoch": 2.8637221593053983,
+      "grad_norm": 0.1962276487617284,
+      "learning_rate": 5.058626459766902e-07,
+      "loss": 0.0978,
+      "num_input_tokens_seen": 1601955280,
+      "step": 6636
+    },
+    {
+      "epoch": 2.872782181955455,
+      "grad_norm": 0.19661166968992774,
+      "learning_rate": 4.407585450899587e-07,
+      "loss": 0.0963,
+      "num_input_tokens_seen": 1606977888,
+      "step": 6657
+    },
+    {
+      "epoch": 2.8818422046055114,
+      "grad_norm": 0.1900385103617743,
+      "learning_rate": 3.8011886526292395e-07,
+      "loss": 0.0932,
+      "num_input_tokens_seen": 1612137088,
+      "step": 6678
+    },
+    {
+      "epoch": 2.8909022272555682,
+      "grad_norm": 0.19054833990071282,
+      "learning_rate": 3.2394906907040056e-07,
+      "loss": 0.098,
+      "num_input_tokens_seen": 1617105760,
+      "step": 6699
+    },
+    {
+      "epoch": 2.8999622499056246,
+      "grad_norm": 0.22982156321658473,
+      "learning_rate": 2.7225421642883554e-07,
+      "loss": 0.099,
+      "num_input_tokens_seen": 1622079712,
+      "step": 6720
+    },
+    {
+      "epoch": 2.9090222725556814,
+      "grad_norm": 0.20733117617880123,
+      "learning_rate": 2.250389641405115e-07,
+      "loss": 0.0974,
+      "num_input_tokens_seen": 1627262208,
+      "step": 6741
+    },
+    {
+      "epoch": 2.918082295205738,
+      "grad_norm": 0.2091535861816229,
+      "learning_rate": 1.823075654740547e-07,
+      "loss": 0.0995,
+      "num_input_tokens_seen": 1632293744,
+      "step": 6762
+    },
+    {
+      "epoch": 2.9271423178557945,
+      "grad_norm": 0.2010699924002249,
+      "learning_rate": 1.4406386978128018e-07,
+      "loss": 0.0955,
+      "num_input_tokens_seen": 1637413856,
+      "step": 6783
+    },
+    {
+      "epoch": 2.9362023405058513,
+      "grad_norm": 0.2039974530223662,
+      "learning_rate": 1.1031132215043594e-07,
+      "loss": 0.095,
+      "num_input_tokens_seen": 1642376144,
+      "step": 6804
+    },
+    {
+      "epoch": 2.9452623631559076,
+      "grad_norm": 0.1867785407127438,
+      "learning_rate": 8.105296309586785e-08,
+      "loss": 0.0995,
+      "num_input_tokens_seen": 1647471008,
+      "step": 6825
+    },
+    {
+      "epoch": 2.9543223858059644,
+      "grad_norm": 0.1873978173047584,
+      "learning_rate": 5.629142828411094e-08,
+      "loss": 0.0976,
+      "num_input_tokens_seen": 1652489696,
+      "step": 6846
+    },
+    {
+      "epoch": 2.963382408456021,
+      "grad_norm": 0.1977061377471765,
+      "learning_rate": 3.602894829647374e-08,
+      "loss": 0.0955,
+      "num_input_tokens_seen": 1657488848,
+      "step": 6867
+    },
+    {
+      "epoch": 2.972442431106078,
+      "grad_norm": 0.19200607060766933,
+      "learning_rate": 2.0267348428087974e-08,
+      "loss": 0.0979,
+      "num_input_tokens_seen": 1662468816,
+      "step": 6888
+    },
+    {
+      "epoch": 2.9815024537561343,
+      "grad_norm": 0.21184767679059754,
+      "learning_rate": 9.008048523501122e-09,
+      "loss": 0.0999,
+      "num_input_tokens_seen": 1667627776,
+      "step": 6909
+    },
+    {
+      "epoch": 2.990562476406191,
+      "grad_norm": 0.2003643238535032,
+      "learning_rate": 2.252062848745462e-09,
+      "loss": 0.099,
+      "num_input_tokens_seen": 1672724048,
+      "step": 6930
+    },
+    {
+      "epoch": 2.9996224990562474,
+      "grad_norm": 0.19768122036104033,
+      "learning_rate": 0.0,
+      "loss": 0.0971,
+      "num_input_tokens_seen": 1677860944,
+      "step": 6951
+    },
+    {
+      "epoch": 2.9996224990562474,
+      "num_input_tokens_seen": 1677860944,
+      "step": 6951,
+      "total_flos": 8545808136798208.0,
+      "train_loss": 0.2019795169591595,
+      "train_runtime": 178782.2648,
+      "train_samples_per_second": 4.978,
+      "train_steps_per_second": 0.039
+    }
+  ],
+  "logging_steps": 21,
+  "max_steps": 6951,
+  "num_input_tokens_seen": 1677860944,
+  "num_train_epochs": 3,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8545808136798208.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836bd95485689002d3c81f577ca1ed5609983953380bae747b167b1d2645c8b8
+size 7480

training_args.yaml

@@ -0,0 +1,34 @@
+bf16: true
+cutoff_len: 6000
+dataset: critic_training_data,refined,omnisvg,svgen,llm4svg
+dataset_dir: data
+ddp_timeout: 180000000
+deepspeed: cache/ds_z3_config.json
+do_train: true
+eval_steps: 5000
+eval_strategy: steps
+finetuning_type: full
+flash_attn: auto
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 0.0001
+logging_steps: 21
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 1000000
+model_name_or_path: /gemini-3/space/thu/zhaozhiyuan/wfy-mptsnet/Qwen2.5-VL-7B-Instruct
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Qwen2.5-VL-7B-Instruct/full/all_stage_123
+packing: false
+per_device_eval_batch_size: 2
+per_device_train_batch_size: 2
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+save_steps: 5000
+stage: sft
+template: qwen2_vl
+trust_remote_code: true
+val_size: 0.03
+warmup_steps: 0