Upload model 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

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-VL-7B-Instruct
+tags:
+- llama-factory
+- freeze
+- generated_from_trainer
+model-index:
+- name: v24
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# v24
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) on the LlavaGuard-DS-v24-oversampled dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6118
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 5
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 80
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4086        | 0.2920 | 20   | 0.5059          |
+| 0.2844        | 0.5839 | 40   | 0.5329          |
+| 0.232         | 0.8759 | 60   | 0.5338          |
+| 0.0847        | 1.1606 | 80   | 0.6175          |
+| 0.0882        | 1.4526 | 100  | 0.5955          |
+| 0.0868        | 1.7445 | 120  | 0.6069          |
+
+
+### Framework versions
+
+- Transformers 4.49.0.dev0
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.21.0

added_tokens.json

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

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.9781021897810218,
+    "eval_loss": 0.6118338704109192,
+    "eval_runtime": 1.6202,
+    "eval_samples_per_second": 43.821,
+    "eval_steps_per_second": 1.852,
+    "total_flos": 89096184856576.0,
+    "train_loss": 0.23073186133714282,
+    "train_runtime": 917.4487,
+    "train_samples_per_second": 11.959,
+    "train_steps_per_second": 0.148
+}

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 +1,50 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
+  "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": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1280,
+    "in_chans": 3,
+    "model_type": "qwen2_5_vl",
+    "spatial_patch_size": 14,
+    "tokens_per_second": 2,
+    "torch_dtype": "float32"
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.9781021897810218,
+    "eval_loss": 0.6118338704109192,
+    "eval_runtime": 1.6202,
+    "eval_samples_per_second": 43.821,
+    "eval_steps_per_second": 1.852
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.1,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.49.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c910417d713dd7c0eb642154f376eaf15bc718b7644dc209c3182a169bdf6745
+size 4968243304

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff323c3b637d20484268cb31fb81ffa9d64d2d25e6fb2e454fe6374f5eec3405
+size 4991495816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42a1b0b420020dd635afef522c343c1eb49ea54b36b1813ad9745f6c219f8c2
+size 4932751040

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74fbcdceea6ee25025988925ff73f974dfff9b5f90d584962d7189f228cc82b
+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": "Qwen2_5_VLImageProcessor",
+  "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
+}

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": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 16384,
+  "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 +1,8 @@
+{
+    "epoch": 1.9781021897810218,
+    "total_flos": 89096184856576.0,
+    "train_loss": 0.23073186133714282,
+    "train_runtime": 917.4487,
+    "train_samples_per_second": 11.959,
+    "train_steps_per_second": 0.148
+}

trainer_log.jsonl

@@ -0,0 +1,143 @@
+{"current_steps": 1, "total_steps": 136, "loss": 0.7048, "lr": 1e-05, "epoch": 0.014598540145985401, "percentage": 0.74, "elapsed_time": "0:00:11", "remaining_time": "0:26:58"}
+{"current_steps": 2, "total_steps": 136, "loss": 0.706, "lr": 2e-05, "epoch": 0.029197080291970802, "percentage": 1.47, "elapsed_time": "0:00:18", "remaining_time": "0:20:13"}
+{"current_steps": 3, "total_steps": 136, "loss": 0.6427, "lr": 3e-05, "epoch": 0.043795620437956206, "percentage": 2.21, "elapsed_time": "0:00:23", "remaining_time": "0:17:29"}
+{"current_steps": 4, "total_steps": 136, "loss": 0.7227, "lr": 4e-05, "epoch": 0.058394160583941604, "percentage": 2.94, "elapsed_time": "0:00:29", "remaining_time": "0:16:04"}
+{"current_steps": 5, "total_steps": 136, "loss": 0.8235, "lr": 5e-05, "epoch": 0.072992700729927, "percentage": 3.68, "elapsed_time": "0:00:34", "remaining_time": "0:15:13"}
+{"current_steps": 6, "total_steps": 136, "loss": 0.8702, "lr": 4.9992811366328926e-05, "epoch": 0.08759124087591241, "percentage": 4.41, "elapsed_time": "0:00:40", "remaining_time": "0:14:37"}
+{"current_steps": 7, "total_steps": 136, "loss": 0.7634, "lr": 4.997124959943201e-05, "epoch": 0.10218978102189781, "percentage": 5.15, "elapsed_time": "0:00:46", "remaining_time": "0:14:09"}
+{"current_steps": 8, "total_steps": 136, "loss": 0.7925, "lr": 4.993532709928075e-05, "epoch": 0.11678832116788321, "percentage": 5.88, "elapsed_time": "0:00:51", "remaining_time": "0:13:48"}
+{"current_steps": 9, "total_steps": 136, "loss": 0.7246, "lr": 4.9885064524570665e-05, "epoch": 0.13138686131386862, "percentage": 6.62, "elapsed_time": "0:00:57", "remaining_time": "0:13:36"}
+{"current_steps": 10, "total_steps": 136, "loss": 0.6298, "lr": 4.982049078084071e-05, "epoch": 0.145985401459854, "percentage": 7.35, "elapsed_time": "0:01:03", "remaining_time": "0:13:20"}
+{"current_steps": 11, "total_steps": 136, "loss": 0.5719, "lr": 4.974164300384998e-05, "epoch": 0.16058394160583941, "percentage": 8.09, "elapsed_time": "0:01:09", "remaining_time": "0:13:04"}
+{"current_steps": 12, "total_steps": 136, "loss": 0.5577, "lr": 4.964856653822122e-05, "epoch": 0.17518248175182483, "percentage": 8.82, "elapsed_time": "0:01:15", "remaining_time": "0:12:57"}
+{"current_steps": 13, "total_steps": 136, "loss": 0.484, "lr": 4.954131491136362e-05, "epoch": 0.1897810218978102, "percentage": 9.56, "elapsed_time": "0:01:20", "remaining_time": "0:12:46"}
+{"current_steps": 14, "total_steps": 136, "loss": 0.4394, "lr": 4.9419949802689666e-05, "epoch": 0.20437956204379562, "percentage": 10.29, "elapsed_time": "0:01:26", "remaining_time": "0:12:34"}
+{"current_steps": 15, "total_steps": 136, "loss": 0.4575, "lr": 4.92845410081439e-05, "epoch": 0.21897810218978103, "percentage": 11.03, "elapsed_time": "0:01:32", "remaining_time": "0:12:23"}
+{"current_steps": 16, "total_steps": 136, "loss": 0.4642, "lr": 4.913516640006392e-05, "epoch": 0.23357664233576642, "percentage": 11.76, "elapsed_time": "0:01:37", "remaining_time": "0:12:13"}
+{"current_steps": 17, "total_steps": 136, "loss": 0.434, "lr": 4.897191188239667e-05, "epoch": 0.24817518248175183, "percentage": 12.5, "elapsed_time": "0:01:43", "remaining_time": "0:12:03"}
+{"current_steps": 18, "total_steps": 136, "loss": 0.405, "lr": 4.8794871341296e-05, "epoch": 0.26277372262773724, "percentage": 13.24, "elapsed_time": "0:01:48", "remaining_time": "0:11:54"}
+{"current_steps": 19, "total_steps": 136, "loss": 0.3909, "lr": 4.8604146591129485e-05, "epoch": 0.2773722627737226, "percentage": 13.97, "elapsed_time": "0:01:54", "remaining_time": "0:11:45"}
+{"current_steps": 20, "total_steps": 136, "loss": 0.4086, "lr": 4.8399847315926e-05, "epoch": 0.291970802919708, "percentage": 14.71, "elapsed_time": "0:02:00", "remaining_time": "0:11:36"}
+{"current_steps": 20, "total_steps": 136, "eval_loss": 0.5058628916740417, "epoch": 0.291970802919708, "percentage": 14.71, "elapsed_time": "0:02:02", "remaining_time": "0:11:50"}
+{"current_steps": 21, "total_steps": 136, "loss": 0.3901, "lr": 4.818209100629745e-05, "epoch": 0.30656934306569344, "percentage": 15.44, "elapsed_time": "0:02:08", "remaining_time": "0:11:41"}
+{"current_steps": 22, "total_steps": 136, "loss": 0.3723, "lr": 4.795100289187099e-05, "epoch": 0.32116788321167883, "percentage": 16.18, "elapsed_time": "0:02:13", "remaining_time": "0:11:33"}
+{"current_steps": 23, "total_steps": 136, "loss": 0.3757, "lr": 4.7706715869270635e-05, "epoch": 0.3357664233576642, "percentage": 16.91, "elapsed_time": "0:02:19", "remaining_time": "0:11:24"}
+{"current_steps": 24, "total_steps": 136, "loss": 0.377, "lr": 4.74493704256897e-05, "epoch": 0.35036496350364965, "percentage": 17.65, "elapsed_time": "0:02:25", "remaining_time": "0:11:16"}
+{"current_steps": 25, "total_steps": 136, "loss": 0.3599, "lr": 4.717911455809782e-05, "epoch": 0.36496350364963503, "percentage": 18.38, "elapsed_time": "0:02:30", "remaining_time": "0:11:08"}
+{"current_steps": 26, "total_steps": 136, "loss": 0.3235, "lr": 4.6896103688129385e-05, "epoch": 0.3795620437956204, "percentage": 19.12, "elapsed_time": "0:02:36", "remaining_time": "0:11:00"}
+{"current_steps": 27, "total_steps": 136, "loss": 0.3538, "lr": 4.660050057270191e-05, "epoch": 0.39416058394160586, "percentage": 19.85, "elapsed_time": "0:02:41", "remaining_time": "0:10:52"}
+{"current_steps": 28, "total_steps": 136, "loss": 0.347, "lr": 4.6292475210416106e-05, "epoch": 0.40875912408759124, "percentage": 20.59, "elapsed_time": "0:02:47", "remaining_time": "0:10:45"}
+{"current_steps": 29, "total_steps": 136, "loss": 0.3239, "lr": 4.597220474379125e-05, "epoch": 0.4233576642335766, "percentage": 21.32, "elapsed_time": "0:02:53", "remaining_time": "0:10:40"}
+{"current_steps": 30, "total_steps": 136, "loss": 0.3172, "lr": 4.563987335739216e-05, "epoch": 0.43795620437956206, "percentage": 22.06, "elapsed_time": "0:02:59", "remaining_time": "0:10:33"}
+{"current_steps": 31, "total_steps": 136, "loss": 0.3161, "lr": 4.5295672171906364e-05, "epoch": 0.45255474452554745, "percentage": 22.79, "elapsed_time": "0:03:04", "remaining_time": "0:10:25"}
+{"current_steps": 32, "total_steps": 136, "loss": 0.3231, "lr": 4.49397991342324e-05, "epoch": 0.46715328467153283, "percentage": 23.53, "elapsed_time": "0:03:10", "remaining_time": "0:10:20"}
+{"current_steps": 33, "total_steps": 136, "loss": 0.3305, "lr": 4.4572458903642354e-05, "epoch": 0.48175182481751827, "percentage": 24.26, "elapsed_time": "0:03:16", "remaining_time": "0:10:13"}
+{"current_steps": 34, "total_steps": 136, "loss": 0.3384, "lr": 4.419386273408428e-05, "epoch": 0.49635036496350365, "percentage": 25.0, "elapsed_time": "0:03:22", "remaining_time": "0:10:06"}
+{"current_steps": 35, "total_steps": 136, "loss": 0.3178, "lr": 4.3804228352691935e-05, "epoch": 0.5109489051094891, "percentage": 25.74, "elapsed_time": "0:03:27", "remaining_time": "0:09:59"}
+{"current_steps": 36, "total_steps": 136, "loss": 0.3346, "lr": 4.3403779834572004e-05, "epoch": 0.5255474452554745, "percentage": 26.47, "elapsed_time": "0:03:33", "remaining_time": "0:09:52"}
+{"current_steps": 37, "total_steps": 136, "loss": 0.3268, "lr": 4.2992747473940556e-05, "epoch": 0.5401459854014599, "percentage": 27.21, "elapsed_time": "0:03:38", "remaining_time": "0:09:45"}
+{"current_steps": 38, "total_steps": 136, "loss": 0.2861, "lr": 4.2571367651683e-05, "epoch": 0.5547445255474452, "percentage": 27.94, "elapsed_time": "0:03:44", "remaining_time": "0:09:39"}
+{"current_steps": 39, "total_steps": 136, "loss": 0.2516, "lr": 4.213988269941362e-05, "epoch": 0.5693430656934306, "percentage": 28.68, "elapsed_time": "0:03:50", "remaining_time": "0:09:32"}
+{"current_steps": 40, "total_steps": 136, "loss": 0.2844, "lr": 4.169854076011292e-05, "epoch": 0.583941605839416, "percentage": 29.41, "elapsed_time": "0:03:55", "remaining_time": "0:09:25"}
+{"current_steps": 40, "total_steps": 136, "eval_loss": 0.5329129099845886, "epoch": 0.583941605839416, "percentage": 29.41, "elapsed_time": "0:03:57", "remaining_time": "0:09:29"}
+{"current_steps": 41, "total_steps": 136, "loss": 0.2759, "lr": 4.124759564542295e-05, "epoch": 0.5985401459854015, "percentage": 30.15, "elapsed_time": "0:04:03", "remaining_time": "0:09:23"}
+{"current_steps": 42, "total_steps": 136, "loss": 0.2614, "lr": 4.078730668968253e-05, "epoch": 0.6131386861313869, "percentage": 30.88, "elapsed_time": "0:04:08", "remaining_time": "0:09:16"}
+{"current_steps": 43, "total_steps": 136, "loss": 0.2577, "lr": 4.031793860078649e-05, "epoch": 0.6277372262773723, "percentage": 31.62, "elapsed_time": "0:04:14", "remaining_time": "0:09:10"}
+{"current_steps": 44, "total_steps": 136, "loss": 0.2518, "lr": 3.9839761307954675e-05, "epoch": 0.6423357664233577, "percentage": 32.35, "elapsed_time": "0:04:19", "remaining_time": "0:09:03"}
+{"current_steps": 45, "total_steps": 136, "loss": 0.3, "lr": 3.935304980649813e-05, "epoch": 0.656934306569343, "percentage": 33.09, "elapsed_time": "0:04:25", "remaining_time": "0:08:56"}
+{"current_steps": 46, "total_steps": 136, "loss": 0.2604, "lr": 3.8858083999671855e-05, "epoch": 0.6715328467153284, "percentage": 33.82, "elapsed_time": "0:04:31", "remaining_time": "0:08:50"}
+{"current_steps": 47, "total_steps": 136, "loss": 0.2716, "lr": 3.835514853770505e-05, "epoch": 0.6861313868613139, "percentage": 34.56, "elapsed_time": "0:04:36", "remaining_time": "0:08:44"}
+{"current_steps": 48, "total_steps": 136, "loss": 0.2535, "lr": 3.784453265410141e-05, "epoch": 0.7007299270072993, "percentage": 35.29, "elapsed_time": "0:04:42", "remaining_time": "0:08:37"}
+{"current_steps": 49, "total_steps": 136, "loss": 0.2341, "lr": 3.732652999930364e-05, "epoch": 0.7153284671532847, "percentage": 36.03, "elapsed_time": "0:04:48", "remaining_time": "0:08:31"}
+{"current_steps": 50, "total_steps": 136, "loss": 0.2702, "lr": 3.680143847181783e-05, "epoch": 0.7299270072992701, "percentage": 36.76, "elapsed_time": "0:04:53", "remaining_time": "0:08:25"}
+{"current_steps": 51, "total_steps": 136, "loss": 0.2579, "lr": 3.6269560046894766e-05, "epoch": 0.7445255474452555, "percentage": 37.5, "elapsed_time": "0:04:59", "remaining_time": "0:08:19"}
+{"current_steps": 52, "total_steps": 136, "loss": 0.2287, "lr": 3.573120060286679e-05, "epoch": 0.7591240875912408, "percentage": 38.24, "elapsed_time": "0:05:05", "remaining_time": "0:08:12"}
+{"current_steps": 53, "total_steps": 136, "loss": 0.2501, "lr": 3.5186669745240026e-05, "epoch": 0.7737226277372263, "percentage": 38.97, "elapsed_time": "0:05:10", "remaining_time": "0:08:06"}
+{"current_steps": 54, "total_steps": 136, "loss": 0.2195, "lr": 3.463628062864312e-05, "epoch": 0.7883211678832117, "percentage": 39.71, "elapsed_time": "0:05:16", "remaining_time": "0:08:01"}
+{"current_steps": 55, "total_steps": 136, "loss": 0.2243, "lr": 3.4080349776734925e-05, "epoch": 0.8029197080291971, "percentage": 40.44, "elapsed_time": "0:05:22", "remaining_time": "0:07:54"}
+{"current_steps": 56, "total_steps": 136, "loss": 0.2184, "lr": 3.351919690017473e-05, "epoch": 0.8175182481751825, "percentage": 41.18, "elapsed_time": "0:05:28", "remaining_time": "0:07:48"}
+{"current_steps": 57, "total_steps": 136, "loss": 0.2255, "lr": 3.2953144712759545e-05, "epoch": 0.8321167883211679, "percentage": 41.91, "elapsed_time": "0:05:33", "remaining_time": "0:07:42"}
+{"current_steps": 58, "total_steps": 136, "loss": 0.24, "lr": 3.238251874583452e-05, "epoch": 0.8467153284671532, "percentage": 42.65, "elapsed_time": "0:05:39", "remaining_time": "0:07:36"}
+{"current_steps": 59, "total_steps": 136, "loss": 0.2246, "lr": 3.1807647161082795e-05, "epoch": 0.8613138686131386, "percentage": 43.38, "elapsed_time": "0:05:44", "remaining_time": "0:07:30"}
+{"current_steps": 60, "total_steps": 136, "loss": 0.232, "lr": 3.122886056180284e-05, "epoch": 0.8759124087591241, "percentage": 44.12, "elapsed_time": "0:05:50", "remaining_time": "0:07:23"}
+{"current_steps": 60, "total_steps": 136, "eval_loss": 0.5338236093521118, "epoch": 0.8759124087591241, "percentage": 44.12, "elapsed_time": "0:05:52", "remaining_time": "0:07:26"}
+{"current_steps": 61, "total_steps": 136, "loss": 0.2636, "lr": 3.064649180278152e-05, "epoch": 0.8905109489051095, "percentage": 44.85, "elapsed_time": "0:05:57", "remaining_time": "0:07:19"}
+{"current_steps": 62, "total_steps": 136, "loss": 0.2112, "lr": 3.006087579887244e-05, "epoch": 0.9051094890510949, "percentage": 45.59, "elapsed_time": "0:06:03", "remaining_time": "0:07:13"}
+{"current_steps": 63, "total_steps": 136, "loss": 0.1924, "lr": 2.9472349332389525e-05, "epoch": 0.9197080291970803, "percentage": 46.32, "elapsed_time": "0:06:08", "remaining_time": "0:07:07"}
+{"current_steps": 64, "total_steps": 136, "loss": 0.2254, "lr": 2.8881250859426646e-05, "epoch": 0.9343065693430657, "percentage": 47.06, "elapsed_time": "0:06:14", "remaining_time": "0:07:01"}
+{"current_steps": 65, "total_steps": 136, "loss": 0.2074, "lr": 2.8287920315214643e-05, "epoch": 0.948905109489051, "percentage": 47.79, "elapsed_time": "0:06:20", "remaining_time": "0:06:55"}
+{"current_steps": 66, "total_steps": 136, "loss": 0.1833, "lr": 2.7692698918627778e-05, "epoch": 0.9635036496350365, "percentage": 48.53, "elapsed_time": "0:06:25", "remaining_time": "0:06:49"}
+{"current_steps": 67, "total_steps": 136, "loss": 0.2125, "lr": 2.7095928975951913e-05, "epoch": 0.9781021897810219, "percentage": 49.26, "elapsed_time": "0:06:31", "remaining_time": "0:06:43"}
+{"current_steps": 68, "total_steps": 136, "loss": 0.2373, "lr": 2.649795368402735e-05, "epoch": 0.9927007299270073, "percentage": 50.0, "elapsed_time": "0:06:37", "remaining_time": "0:06:37"}
+{"current_steps": 69, "total_steps": 136, "loss": 0.1027, "lr": 2.649795368402735e-05, "epoch": 1.0, "percentage": 50.74, "elapsed_time": "0:06:39", "remaining_time": "0:06:28"}
+{"current_steps": 70, "total_steps": 136, "loss": 0.1039, "lr": 2.5899116932879534e-05, "epoch": 1.0145985401459854, "percentage": 51.47, "elapsed_time": "0:07:32", "remaining_time": "0:07:07"}
+{"current_steps": 71, "total_steps": 136, "loss": 0.1075, "lr": 2.529976310795108e-05, "epoch": 1.0291970802919708, "percentage": 52.21, "elapsed_time": "0:07:38", "remaining_time": "0:06:59"}
+{"current_steps": 72, "total_steps": 136, "loss": 0.1053, "lr": 2.470023689204893e-05, "epoch": 1.0437956204379562, "percentage": 52.94, "elapsed_time": "0:07:44", "remaining_time": "0:06:52"}
+{"current_steps": 73, "total_steps": 136, "loss": 0.1048, "lr": 2.4100883067120475e-05, "epoch": 1.0583941605839415, "percentage": 53.68, "elapsed_time": "0:07:49", "remaining_time": "0:06:45"}
+{"current_steps": 74, "total_steps": 136, "loss": 0.0987, "lr": 2.3502046315972656e-05, "epoch": 1.072992700729927, "percentage": 54.41, "elapsed_time": "0:07:55", "remaining_time": "0:06:38"}
+{"current_steps": 75, "total_steps": 136, "loss": 0.0836, "lr": 2.290407102404809e-05, "epoch": 1.0875912408759123, "percentage": 55.15, "elapsed_time": "0:08:01", "remaining_time": "0:06:31"}
+{"current_steps": 76, "total_steps": 136, "loss": 0.1159, "lr": 2.2307301081372224e-05, "epoch": 1.102189781021898, "percentage": 55.88, "elapsed_time": "0:08:06", "remaining_time": "0:06:24"}
+{"current_steps": 77, "total_steps": 136, "loss": 0.0816, "lr": 2.1712079684785363e-05, "epoch": 1.1167883211678833, "percentage": 56.62, "elapsed_time": "0:08:12", "remaining_time": "0:06:17"}
+{"current_steps": 78, "total_steps": 136, "loss": 0.1141, "lr": 2.111874914057336e-05, "epoch": 1.1313868613138687, "percentage": 57.35, "elapsed_time": "0:08:17", "remaining_time": "0:06:10"}
+{"current_steps": 79, "total_steps": 136, "loss": 0.1146, "lr": 2.0527650667610478e-05, "epoch": 1.145985401459854, "percentage": 58.09, "elapsed_time": "0:08:23", "remaining_time": "0:06:03"}
+{"current_steps": 80, "total_steps": 136, "loss": 0.0847, "lr": 1.993912420112756e-05, "epoch": 1.1605839416058394, "percentage": 58.82, "elapsed_time": "0:08:29", "remaining_time": "0:05:56"}
+{"current_steps": 80, "total_steps": 136, "eval_loss": 0.6174606084823608, "epoch": 1.1605839416058394, "percentage": 58.82, "elapsed_time": "0:08:30", "remaining_time": "0:05:57"}
+{"current_steps": 81, "total_steps": 136, "loss": 0.1019, "lr": 1.935350819721849e-05, "epoch": 1.1751824817518248, "percentage": 59.56, "elapsed_time": "0:08:36", "remaining_time": "0:05:50"}
+{"current_steps": 82, "total_steps": 136, "loss": 0.1077, "lr": 1.8771139438197168e-05, "epoch": 1.1897810218978102, "percentage": 60.29, "elapsed_time": "0:08:42", "remaining_time": "0:05:43"}
+{"current_steps": 83, "total_steps": 136, "loss": 0.091, "lr": 1.819235283891721e-05, "epoch": 1.2043795620437956, "percentage": 61.03, "elapsed_time": "0:08:47", "remaining_time": "0:05:36"}
+{"current_steps": 84, "total_steps": 136, "loss": 0.1081, "lr": 1.7617481254165487e-05, "epoch": 1.218978102189781, "percentage": 61.76, "elapsed_time": "0:08:53", "remaining_time": "0:05:30"}
+{"current_steps": 85, "total_steps": 136, "loss": 0.1087, "lr": 1.704685528724046e-05, "epoch": 1.2335766423357664, "percentage": 62.5, "elapsed_time": "0:08:58", "remaining_time": "0:05:23"}
+{"current_steps": 86, "total_steps": 136, "loss": 0.1094, "lr": 1.648080309982528e-05, "epoch": 1.2481751824817517, "percentage": 63.24, "elapsed_time": "0:09:04", "remaining_time": "0:05:16"}
+{"current_steps": 87, "total_steps": 136, "loss": 0.1018, "lr": 1.591965022326507e-05, "epoch": 1.2627737226277373, "percentage": 63.97, "elapsed_time": "0:09:09", "remaining_time": "0:05:09"}
+{"current_steps": 88, "total_steps": 136, "loss": 0.0921, "lr": 1.536371937135688e-05, "epoch": 1.2773722627737225, "percentage": 64.71, "elapsed_time": "0:09:15", "remaining_time": "0:05:03"}
+{"current_steps": 89, "total_steps": 136, "loss": 0.1044, "lr": 1.4813330254759985e-05, "epoch": 1.2919708029197081, "percentage": 65.44, "elapsed_time": "0:09:21", "remaining_time": "0:04:56"}
+{"current_steps": 90, "total_steps": 136, "loss": 0.0816, "lr": 1.426879939713322e-05, "epoch": 1.3065693430656935, "percentage": 66.18, "elapsed_time": "0:09:26", "remaining_time": "0:04:49"}
+{"current_steps": 91, "total_steps": 136, "loss": 0.0842, "lr": 1.3730439953105243e-05, "epoch": 1.3211678832116789, "percentage": 66.91, "elapsed_time": "0:09:32", "remaining_time": "0:04:43"}
+{"current_steps": 92, "total_steps": 136, "loss": 0.0744, "lr": 1.3198561528182183e-05, "epoch": 1.3357664233576643, "percentage": 67.65, "elapsed_time": "0:09:38", "remaining_time": "0:04:36"}
+{"current_steps": 93, "total_steps": 136, "loss": 0.1033, "lr": 1.2673470000696364e-05, "epoch": 1.3503649635036497, "percentage": 68.38, "elapsed_time": "0:09:44", "remaining_time": "0:04:30"}
+{"current_steps": 94, "total_steps": 136, "loss": 0.1001, "lr": 1.2155467345898602e-05, "epoch": 1.364963503649635, "percentage": 69.12, "elapsed_time": "0:09:49", "remaining_time": "0:04:23"}
+{"current_steps": 95, "total_steps": 136, "loss": 0.101, "lr": 1.1644851462294957e-05, "epoch": 1.3795620437956204, "percentage": 69.85, "elapsed_time": "0:09:55", "remaining_time": "0:04:16"}
+{"current_steps": 96, "total_steps": 136, "loss": 0.0863, "lr": 1.114191600032815e-05, "epoch": 1.3941605839416058, "percentage": 70.59, "elapsed_time": "0:10:01", "remaining_time": "0:04:10"}
+{"current_steps": 97, "total_steps": 136, "loss": 0.0855, "lr": 1.064695019350187e-05, "epoch": 1.4087591240875912, "percentage": 71.32, "elapsed_time": "0:10:06", "remaining_time": "0:04:03"}
+{"current_steps": 98, "total_steps": 136, "loss": 0.111, "lr": 1.0160238692045332e-05, "epoch": 1.4233576642335766, "percentage": 72.06, "elapsed_time": "0:10:12", "remaining_time": "0:03:57"}
+{"current_steps": 99, "total_steps": 136, "loss": 0.0939, "lr": 9.682061399213525e-06, "epoch": 1.437956204379562, "percentage": 72.79, "elapsed_time": "0:10:17", "remaining_time": "0:03:50"}
+{"current_steps": 100, "total_steps": 136, "loss": 0.0882, "lr": 9.21269331031748e-06, "epoch": 1.4525547445255476, "percentage": 73.53, "elapsed_time": "0:10:23", "remaining_time": "0:03:44"}
+{"current_steps": 100, "total_steps": 136, "eval_loss": 0.5955010652542114, "epoch": 1.4525547445255476, "percentage": 73.53, "elapsed_time": "0:10:25", "remaining_time": "0:03:45"}
+{"current_steps": 101, "total_steps": 136, "loss": 0.0937, "lr": 8.752404354577052e-06, "epoch": 1.4671532846715327, "percentage": 74.26, "elapsed_time": "0:10:31", "remaining_time": "0:03:38"}
+{"current_steps": 102, "total_steps": 136, "loss": 0.0803, "lr": 8.301459239887074e-06, "epoch": 1.4817518248175183, "percentage": 75.0, "elapsed_time": "0:10:36", "remaining_time": "0:03:32"}
+{"current_steps": 103, "total_steps": 136, "loss": 0.1008, "lr": 7.860117300586383e-06, "epoch": 1.4963503649635037, "percentage": 75.74, "elapsed_time": "0:10:42", "remaining_time": "0:03:25"}
+{"current_steps": 104, "total_steps": 136, "loss": 0.0731, "lr": 7.428632348317005e-06, "epoch": 1.510948905109489, "percentage": 76.47, "elapsed_time": "0:10:47", "remaining_time": "0:03:19"}
+{"current_steps": 105, "total_steps": 136, "loss": 0.075, "lr": 7.007252526059446e-06, "epoch": 1.5255474452554745, "percentage": 77.21, "elapsed_time": "0:10:53", "remaining_time": "0:03:12"}
+{"current_steps": 106, "total_steps": 136, "loss": 0.0797, "lr": 6.596220165428002e-06, "epoch": 1.5401459854014599, "percentage": 77.94, "elapsed_time": "0:10:59", "remaining_time": "0:03:06"}
+{"current_steps": 107, "total_steps": 136, "loss": 0.1031, "lr": 6.195771647308074e-06, "epoch": 1.5547445255474452, "percentage": 78.68, "elapsed_time": "0:11:04", "remaining_time": "0:03:00"}
+{"current_steps": 108, "total_steps": 136, "loss": 0.0876, "lr": 5.806137265915732e-06, "epoch": 1.5693430656934306, "percentage": 79.41, "elapsed_time": "0:11:10", "remaining_time": "0:02:53"}
+{"current_steps": 109, "total_steps": 136, "loss": 0.0859, "lr": 5.427541096357647e-06, "epoch": 1.583941605839416, "percentage": 80.15, "elapsed_time": "0:11:16", "remaining_time": "0:02:47"}
+{"current_steps": 110, "total_steps": 136, "loss": 0.0914, "lr": 5.060200865767606e-06, "epoch": 1.5985401459854014, "percentage": 80.88, "elapsed_time": "0:11:22", "remaining_time": "0:02:41"}
+{"current_steps": 111, "total_steps": 136, "loss": 0.0891, "lr": 4.704327828093641e-06, "epoch": 1.613138686131387, "percentage": 81.62, "elapsed_time": "0:11:27", "remaining_time": "0:02:34"}
+{"current_steps": 112, "total_steps": 136, "loss": 0.0802, "lr": 4.3601266426078426e-06, "epoch": 1.6277372262773722, "percentage": 82.35, "elapsed_time": "0:11:33", "remaining_time": "0:02:28"}
+{"current_steps": 113, "total_steps": 136, "loss": 0.0837, "lr": 4.02779525620875e-06, "epoch": 1.6423357664233578, "percentage": 83.09, "elapsed_time": "0:11:38", "remaining_time": "0:02:22"}
+{"current_steps": 114, "total_steps": 136, "loss": 0.0733, "lr": 3.707524789583891e-06, "epoch": 1.656934306569343, "percentage": 83.82, "elapsed_time": "0:11:44", "remaining_time": "0:02:15"}
+{"current_steps": 115, "total_steps": 136, "loss": 0.0816, "lr": 3.3994994272980946e-06, "epoch": 1.6715328467153285, "percentage": 84.56, "elapsed_time": "0:11:50", "remaining_time": "0:02:09"}
+{"current_steps": 116, "total_steps": 136, "loss": 0.0947, "lr": 3.1038963118706244e-06, "epoch": 1.686131386861314, "percentage": 85.29, "elapsed_time": "0:11:55", "remaining_time": "0:02:03"}
+{"current_steps": 117, "total_steps": 136, "loss": 0.0807, "lr": 2.8208854419021824e-06, "epoch": 1.7007299270072993, "percentage": 86.03, "elapsed_time": "0:12:01", "remaining_time": "0:01:57"}
+{"current_steps": 118, "total_steps": 136, "loss": 0.0576, "lr": 2.5506295743103094e-06, "epoch": 1.7153284671532847, "percentage": 86.76, "elapsed_time": "0:12:07", "remaining_time": "0:01:50"}
+{"current_steps": 119, "total_steps": 136, "loss": 0.0857, "lr": 2.2932841307293644e-06, "epoch": 1.72992700729927, "percentage": 87.5, "elapsed_time": "0:12:12", "remaining_time": "0:01:44"}
+{"current_steps": 120, "total_steps": 136, "loss": 0.0868, "lr": 2.0489971081290195e-06, "epoch": 1.7445255474452555, "percentage": 88.24, "elapsed_time": "0:12:18", "remaining_time": "0:01:38"}
+{"current_steps": 120, "total_steps": 136, "eval_loss": 0.6069221496582031, "epoch": 1.7445255474452555, "percentage": 88.24, "elapsed_time": "0:12:20", "remaining_time": "0:01:38"}
+{"current_steps": 121, "total_steps": 136, "loss": 0.0781, "lr": 1.817908993702555e-06, "epoch": 1.7591240875912408, "percentage": 88.97, "elapsed_time": "0:12:25", "remaining_time": "0:01:32"}
+{"current_steps": 122, "total_steps": 136, "loss": 0.0773, "lr": 1.6001526840740049e-06, "epoch": 1.7737226277372264, "percentage": 89.71, "elapsed_time": "0:12:31", "remaining_time": "0:01:26"}
+{"current_steps": 123, "total_steps": 136, "loss": 0.0648, "lr": 1.3958534088705206e-06, "epoch": 1.7883211678832116, "percentage": 90.44, "elapsed_time": "0:12:36", "remaining_time": "0:01:19"}
+{"current_steps": 124, "total_steps": 136, "loss": 0.0685, "lr": 1.205128658704005e-06, "epoch": 1.8029197080291972, "percentage": 91.18, "elapsed_time": "0:12:42", "remaining_time": "0:01:13"}
+{"current_steps": 125, "total_steps": 136, "loss": 0.0597, "lr": 1.028088117603332e-06, "epoch": 1.8175182481751824, "percentage": 91.91, "elapsed_time": "0:12:48", "remaining_time": "0:01:07"}
+{"current_steps": 126, "total_steps": 136, "loss": 0.0851, "lr": 8.648335999360935e-07, "epoch": 1.832116788321168, "percentage": 92.65, "elapsed_time": "0:12:53", "remaining_time": "0:01:01"}
+{"current_steps": 127, "total_steps": 136, "loss": 0.0775, "lr": 7.154589918561022e-07, "epoch": 1.8467153284671531, "percentage": 93.38, "elapsed_time": "0:12:59", "remaining_time": "0:00:55"}
+{"current_steps": 128, "total_steps": 136, "loss": 0.0837, "lr": 5.800501973103362e-07, "epoch": 1.8613138686131387, "percentage": 94.12, "elapsed_time": "0:13:05", "remaining_time": "0:00:49"}
+{"current_steps": 129, "total_steps": 136, "loss": 0.104, "lr": 4.586850886363875e-07, "epoch": 1.8759124087591241, "percentage": 94.85, "elapsed_time": "0:13:10", "remaining_time": "0:00:42"}
+{"current_steps": 130, "total_steps": 136, "loss": 0.0694, "lr": 3.514334617787857e-07, "epoch": 1.8905109489051095, "percentage": 95.59, "elapsed_time": "0:13:16", "remaining_time": "0:00:36"}
+{"current_steps": 131, "total_steps": 136, "loss": 0.0617, "lr": 2.5835699615002764e-07, "epoch": 1.905109489051095, "percentage": 96.32, "elapsed_time": "0:13:22", "remaining_time": "0:00:30"}
+{"current_steps": 132, "total_steps": 136, "loss": 0.0792, "lr": 1.7950921915928788e-07, "epoch": 1.9197080291970803, "percentage": 97.06, "elapsed_time": "0:13:27", "remaining_time": "0:00:24"}
+{"current_steps": 133, "total_steps": 136, "loss": 0.0919, "lr": 1.1493547542933969e-07, "epoch": 1.9343065693430657, "percentage": 97.79, "elapsed_time": "0:13:33", "remaining_time": "0:00:18"}
+{"current_steps": 134, "total_steps": 136, "loss": 0.0655, "lr": 6.467290071925647e-08, "epoch": 1.948905109489051, "percentage": 98.53, "elapsed_time": "0:13:38", "remaining_time": "0:00:12"}
+{"current_steps": 135, "total_steps": 136, "loss": 0.0607, "lr": 2.8750400567992274e-08, "epoch": 1.9635036496350367, "percentage": 99.26, "elapsed_time": "0:13:44", "remaining_time": "0:00:06"}
+{"current_steps": 136, "total_steps": 136, "loss": 0.0823, "lr": 7.188633671079137e-09, "epoch": 1.9781021897810218, "percentage": 100.0, "elapsed_time": "0:13:50", "remaining_time": "0:00:00"}
+{"current_steps": 136, "total_steps": 136, "epoch": 1.9781021897810218, "percentage": 100.0, "elapsed_time": "0:15:16", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1042 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9781021897810218,
+  "eval_steps": 20,
+  "global_step": 136,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014598540145985401,
+      "grad_norm": 5.558824092078288,
+      "learning_rate": 1e-05,
+      "loss": 0.7048,
+      "step": 1
+    },
+    {
+      "epoch": 0.029197080291970802,
+      "grad_norm": 5.39781753446926,
+      "learning_rate": 2e-05,
+      "loss": 0.706,
+      "step": 2
+    },
+    {
+      "epoch": 0.043795620437956206,
+      "grad_norm": 2.5767987530959293,
+      "learning_rate": 3e-05,
+      "loss": 0.6427,
+      "step": 3
+    },
+    {
+      "epoch": 0.058394160583941604,
+      "grad_norm": 5.332582144004997,
+      "learning_rate": 4e-05,
+      "loss": 0.7227,
+      "step": 4
+    },
+    {
+      "epoch": 0.072992700729927,
+      "grad_norm": 6.654038960215542,
+      "learning_rate": 5e-05,
+      "loss": 0.8235,
+      "step": 5
+    },
+    {
+      "epoch": 0.08759124087591241,
+      "grad_norm": 6.676666009964554,
+      "learning_rate": 4.9992811366328926e-05,
+      "loss": 0.8702,
+      "step": 6
+    },
+    {
+      "epoch": 0.10218978102189781,
+      "grad_norm": 4.274269796378038,
+      "learning_rate": 4.997124959943201e-05,
+      "loss": 0.7634,
+      "step": 7
+    },
+    {
+      "epoch": 0.11678832116788321,
+      "grad_norm": 9.488201233376888,
+      "learning_rate": 4.993532709928075e-05,
+      "loss": 0.7925,
+      "step": 8
+    },
+    {
+      "epoch": 0.13138686131386862,
+      "grad_norm": 5.052354667424013,
+      "learning_rate": 4.9885064524570665e-05,
+      "loss": 0.7246,
+      "step": 9
+    },
+    {
+      "epoch": 0.145985401459854,
+      "grad_norm": 1.5775620837406379,
+      "learning_rate": 4.982049078084071e-05,
+      "loss": 0.6298,
+      "step": 10
+    },
+    {
+      "epoch": 0.16058394160583941,
+      "grad_norm": 2.0338294097415694,
+      "learning_rate": 4.974164300384998e-05,
+      "loss": 0.5719,
+      "step": 11
+    },
+    {
+      "epoch": 0.17518248175182483,
+      "grad_norm": 1.4271467759265182,
+      "learning_rate": 4.964856653822122e-05,
+      "loss": 0.5577,
+      "step": 12
+    },
+    {
+      "epoch": 0.1897810218978102,
+      "grad_norm": 1.4553670927449545,
+      "learning_rate": 4.954131491136362e-05,
+      "loss": 0.484,
+      "step": 13
+    },
+    {
+      "epoch": 0.20437956204379562,
+      "grad_norm": 1.270113333054875,
+      "learning_rate": 4.9419949802689666e-05,
+      "loss": 0.4394,
+      "step": 14
+    },
+    {
+      "epoch": 0.21897810218978103,
+      "grad_norm": 1.2876560129600205,
+      "learning_rate": 4.92845410081439e-05,
+      "loss": 0.4575,
+      "step": 15
+    },
+    {
+      "epoch": 0.23357664233576642,
+      "grad_norm": 1.3643309071212184,
+      "learning_rate": 4.913516640006392e-05,
+      "loss": 0.4642,
+      "step": 16
+    },
+    {
+      "epoch": 0.24817518248175183,
+      "grad_norm": 1.1729936051973566,
+      "learning_rate": 4.897191188239667e-05,
+      "loss": 0.434,
+      "step": 17
+    },
+    {
+      "epoch": 0.26277372262773724,
+      "grad_norm": 1.1621979050371054,
+      "learning_rate": 4.8794871341296e-05,
+      "loss": 0.405,
+      "step": 18
+    },
+    {
+      "epoch": 0.2773722627737226,
+      "grad_norm": 1.1218709581501245,
+      "learning_rate": 4.8604146591129485e-05,
+      "loss": 0.3909,
+      "step": 19
+    },
+    {
+      "epoch": 0.291970802919708,
+      "grad_norm": 1.0395959826090466,
+      "learning_rate": 4.8399847315926e-05,
+      "loss": 0.4086,
+      "step": 20
+    },
+    {
+      "epoch": 0.291970802919708,
+      "eval_loss": 0.5058628916740417,
+      "eval_runtime": 2.3522,
+      "eval_samples_per_second": 30.184,
+      "eval_steps_per_second": 1.275,
+      "step": 20
+    },
+    {
+      "epoch": 0.30656934306569344,
+      "grad_norm": 1.1417380012049692,
+      "learning_rate": 4.818209100629745e-05,
+      "loss": 0.3901,
+      "step": 21
+    },
+    {
+      "epoch": 0.32116788321167883,
+      "grad_norm": 1.0254963744794567,
+      "learning_rate": 4.795100289187099e-05,
+      "loss": 0.3723,
+      "step": 22
+    },
+    {
+      "epoch": 0.3357664233576642,
+      "grad_norm": 1.0470804323692136,
+      "learning_rate": 4.7706715869270635e-05,
+      "loss": 0.3757,
+      "step": 23
+    },
+    {
+      "epoch": 0.35036496350364965,
+      "grad_norm": 0.9566801844725584,
+      "learning_rate": 4.74493704256897e-05,
+      "loss": 0.377,
+      "step": 24
+    },
+    {
+      "epoch": 0.36496350364963503,
+      "grad_norm": 0.8719622478856044,
+      "learning_rate": 4.717911455809782e-05,
+      "loss": 0.3599,
+      "step": 25
+    },
+    {
+      "epoch": 0.3795620437956204,
+      "grad_norm": 0.8993416168257213,
+      "learning_rate": 4.6896103688129385e-05,
+      "loss": 0.3235,
+      "step": 26
+    },
+    {
+      "epoch": 0.39416058394160586,
+      "grad_norm": 0.9295183450455919,
+      "learning_rate": 4.660050057270191e-05,
+      "loss": 0.3538,
+      "step": 27
+    },
+    {
+      "epoch": 0.40875912408759124,
+      "grad_norm": 0.8210997173864658,
+      "learning_rate": 4.6292475210416106e-05,
+      "loss": 0.347,
+      "step": 28
+    },
+    {
+      "epoch": 0.4233576642335766,
+      "grad_norm": 0.9109711747983845,
+      "learning_rate": 4.597220474379125e-05,
+      "loss": 0.3239,
+      "step": 29
+    },
+    {
+      "epoch": 0.43795620437956206,
+      "grad_norm": 0.917876136961733,
+      "learning_rate": 4.563987335739216e-05,
+      "loss": 0.3172,
+      "step": 30
+    },
+    {
+      "epoch": 0.45255474452554745,
+      "grad_norm": 0.8348657603950833,
+      "learning_rate": 4.5295672171906364e-05,
+      "loss": 0.3161,
+      "step": 31
+    },
+    {
+      "epoch": 0.46715328467153283,
+      "grad_norm": 0.9628144830881412,
+      "learning_rate": 4.49397991342324e-05,
+      "loss": 0.3231,
+      "step": 32
+    },
+    {
+      "epoch": 0.48175182481751827,
+      "grad_norm": 0.8758205697486683,
+      "learning_rate": 4.4572458903642354e-05,
+      "loss": 0.3305,
+      "step": 33
+    },
+    {
+      "epoch": 0.49635036496350365,
+      "grad_norm": 0.8177550425000464,
+      "learning_rate": 4.419386273408428e-05,
+      "loss": 0.3384,
+      "step": 34
+    },
+    {
+      "epoch": 0.5109489051094891,
+      "grad_norm": 0.7707655080363717,
+      "learning_rate": 4.3804228352691935e-05,
+      "loss": 0.3178,
+      "step": 35
+    },
+    {
+      "epoch": 0.5255474452554745,
+      "grad_norm": 0.8191298252366446,
+      "learning_rate": 4.3403779834572004e-05,
+      "loss": 0.3346,
+      "step": 36
+    },
+    {
+      "epoch": 0.5401459854014599,
+      "grad_norm": 0.9406397953710217,
+      "learning_rate": 4.2992747473940556e-05,
+      "loss": 0.3268,
+      "step": 37
+    },
+    {
+      "epoch": 0.5547445255474452,
+      "grad_norm": 0.757783885677172,
+      "learning_rate": 4.2571367651683e-05,
+      "loss": 0.2861,
+      "step": 38
+    },
+    {
+      "epoch": 0.5693430656934306,
+      "grad_norm": 0.7275760878949353,
+      "learning_rate": 4.213988269941362e-05,
+      "loss": 0.2516,
+      "step": 39
+    },
+    {
+      "epoch": 0.583941605839416,
+      "grad_norm": 0.9299663609616579,
+      "learning_rate": 4.169854076011292e-05,
+      "loss": 0.2844,
+      "step": 40
+    },
+    {
+      "epoch": 0.583941605839416,
+      "eval_loss": 0.5329129099845886,
+      "eval_runtime": 1.6671,
+      "eval_samples_per_second": 42.589,
+      "eval_steps_per_second": 1.8,
+      "step": 40
+    },
+    {
+      "epoch": 0.5985401459854015,
+      "grad_norm": 0.7884853681211518,
+      "learning_rate": 4.124759564542295e-05,
+      "loss": 0.2759,
+      "step": 41
+    },
+    {
+      "epoch": 0.6131386861313869,
+      "grad_norm": 0.7356673142072975,
+      "learning_rate": 4.078730668968253e-05,
+      "loss": 0.2614,
+      "step": 42
+    },
+    {
+      "epoch": 0.6277372262773723,
+      "grad_norm": 0.7411930478686042,
+      "learning_rate": 4.031793860078649e-05,
+      "loss": 0.2577,
+      "step": 43
+    },
+    {
+      "epoch": 0.6423357664233577,
+      "grad_norm": 0.6945647014688631,
+      "learning_rate": 3.9839761307954675e-05,
+      "loss": 0.2518,
+      "step": 44
+    },
+    {
+      "epoch": 0.656934306569343,
+      "grad_norm": 0.758841305493356,
+      "learning_rate": 3.935304980649813e-05,
+      "loss": 0.3,
+      "step": 45
+    },
+    {
+      "epoch": 0.6715328467153284,
+      "grad_norm": 0.7083671932224866,
+      "learning_rate": 3.8858083999671855e-05,
+      "loss": 0.2604,
+      "step": 46
+    },
+    {
+      "epoch": 0.6861313868613139,
+      "grad_norm": 0.7105677438159481,
+      "learning_rate": 3.835514853770505e-05,
+      "loss": 0.2716,
+      "step": 47
+    },
+    {
+      "epoch": 0.7007299270072993,
+      "grad_norm": 0.6955300432925063,
+      "learning_rate": 3.784453265410141e-05,
+      "loss": 0.2535,
+      "step": 48
+    },
+    {
+      "epoch": 0.7153284671532847,
+      "grad_norm": 0.6251239165395376,
+      "learning_rate": 3.732652999930364e-05,
+      "loss": 0.2341,
+      "step": 49
+    },
+    {
+      "epoch": 0.7299270072992701,
+      "grad_norm": 0.7101720555562038,
+      "learning_rate": 3.680143847181783e-05,
+      "loss": 0.2702,
+      "step": 50
+    },
+    {
+      "epoch": 0.7445255474452555,
+      "grad_norm": 0.7982281837079658,
+      "learning_rate": 3.6269560046894766e-05,
+      "loss": 0.2579,
+      "step": 51
+    },
+    {
+      "epoch": 0.7591240875912408,
+      "grad_norm": 0.6679783854698054,
+      "learning_rate": 3.573120060286679e-05,
+      "loss": 0.2287,
+      "step": 52
+    },
+    {
+      "epoch": 0.7737226277372263,
+      "grad_norm": 0.6971062669945208,
+      "learning_rate": 3.5186669745240026e-05,
+      "loss": 0.2501,
+      "step": 53
+    },
+    {
+      "epoch": 0.7883211678832117,
+      "grad_norm": 0.6212428454824916,
+      "learning_rate": 3.463628062864312e-05,
+      "loss": 0.2195,
+      "step": 54
+    },
+    {
+      "epoch": 0.8029197080291971,
+      "grad_norm": 0.6621251726886289,
+      "learning_rate": 3.4080349776734925e-05,
+      "loss": 0.2243,
+      "step": 55
+    },
+    {
+      "epoch": 0.8175182481751825,
+      "grad_norm": 0.618969299596716,
+      "learning_rate": 3.351919690017473e-05,
+      "loss": 0.2184,
+      "step": 56
+    },
+    {
+      "epoch": 0.8321167883211679,
+      "grad_norm": 0.6210248745374214,
+      "learning_rate": 3.2953144712759545e-05,
+      "loss": 0.2255,
+      "step": 57
+    },
+    {
+      "epoch": 0.8467153284671532,
+      "grad_norm": 0.648626857719657,
+      "learning_rate": 3.238251874583452e-05,
+      "loss": 0.24,
+      "step": 58
+    },
+    {
+      "epoch": 0.8613138686131386,
+      "grad_norm": 0.6442995895157195,
+      "learning_rate": 3.1807647161082795e-05,
+      "loss": 0.2246,
+      "step": 59
+    },
+    {
+      "epoch": 0.8759124087591241,
+      "grad_norm": 0.5822022754916901,
+      "learning_rate": 3.122886056180284e-05,
+      "loss": 0.232,
+      "step": 60
+    },
+    {
+      "epoch": 0.8759124087591241,
+      "eval_loss": 0.5338236093521118,
+      "eval_runtime": 1.6696,
+      "eval_samples_per_second": 42.525,
+      "eval_steps_per_second": 1.797,
+      "step": 60
+    },
+    {
+      "epoch": 0.8905109489051095,
+      "grad_norm": 0.6753004591751348,
+      "learning_rate": 3.064649180278152e-05,
+      "loss": 0.2636,
+      "step": 61
+    },
+    {
+      "epoch": 0.9051094890510949,
+      "grad_norm": 0.6326351355678477,
+      "learning_rate": 3.006087579887244e-05,
+      "loss": 0.2112,
+      "step": 62
+    },
+    {
+      "epoch": 0.9197080291970803,
+      "grad_norm": 0.5944744601386913,
+      "learning_rate": 2.9472349332389525e-05,
+      "loss": 0.1924,
+      "step": 63
+    },
+    {
+      "epoch": 0.9343065693430657,
+      "grad_norm": 0.6089460479407833,
+      "learning_rate": 2.8881250859426646e-05,
+      "loss": 0.2254,
+      "step": 64
+    },
+    {
+      "epoch": 0.948905109489051,
+      "grad_norm": 0.5901015804515078,
+      "learning_rate": 2.8287920315214643e-05,
+      "loss": 0.2074,
+      "step": 65
+    },
+    {
+      "epoch": 0.9635036496350365,
+      "grad_norm": 0.5482779301116911,
+      "learning_rate": 2.7692698918627778e-05,
+      "loss": 0.1833,
+      "step": 66
+    },
+    {
+      "epoch": 0.9781021897810219,
+      "grad_norm": 0.619204984698149,
+      "learning_rate": 2.7095928975951913e-05,
+      "loss": 0.2125,
+      "step": 67
+    },
+    {
+      "epoch": 0.9927007299270073,
+      "grad_norm": 0.5754857994127854,
+      "learning_rate": 2.649795368402735e-05,
+      "loss": 0.2373,
+      "step": 68
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5754857994127854,
+      "learning_rate": 2.649795368402735e-05,
+      "loss": 0.1027,
+      "step": 69
+    },
+    {
+      "epoch": 1.0145985401459854,
+      "grad_norm": 0.5481032621072542,
+      "learning_rate": 2.5899116932879534e-05,
+      "loss": 0.1039,
+      "step": 70
+    },
+    {
+      "epoch": 1.0291970802919708,
+      "grad_norm": 0.44573568671990305,
+      "learning_rate": 2.529976310795108e-05,
+      "loss": 0.1075,
+      "step": 71
+    },
+    {
+      "epoch": 1.0437956204379562,
+      "grad_norm": 0.46800129257717743,
+      "learning_rate": 2.470023689204893e-05,
+      "loss": 0.1053,
+      "step": 72
+    },
+    {
+      "epoch": 1.0583941605839415,
+      "grad_norm": 0.5217427141578048,
+      "learning_rate": 2.4100883067120475e-05,
+      "loss": 0.1048,
+      "step": 73
+    },
+    {
+      "epoch": 1.072992700729927,
+      "grad_norm": 0.46349892807310117,
+      "learning_rate": 2.3502046315972656e-05,
+      "loss": 0.0987,
+      "step": 74
+    },
+    {
+      "epoch": 1.0875912408759123,
+      "grad_norm": 0.4835213983318123,
+      "learning_rate": 2.290407102404809e-05,
+      "loss": 0.0836,
+      "step": 75
+    },
+    {
+      "epoch": 1.102189781021898,
+      "grad_norm": 0.5194340907634253,
+      "learning_rate": 2.2307301081372224e-05,
+      "loss": 0.1159,
+      "step": 76
+    },
+    {
+      "epoch": 1.1167883211678833,
+      "grad_norm": 0.5807960446197283,
+      "learning_rate": 2.1712079684785363e-05,
+      "loss": 0.0816,
+      "step": 77
+    },
+    {
+      "epoch": 1.1313868613138687,
+      "grad_norm": 0.5578387906848328,
+      "learning_rate": 2.111874914057336e-05,
+      "loss": 0.1141,
+      "step": 78
+    },
+    {
+      "epoch": 1.145985401459854,
+      "grad_norm": 0.5639933149192473,
+      "learning_rate": 2.0527650667610478e-05,
+      "loss": 0.1146,
+      "step": 79
+    },
+    {
+      "epoch": 1.1605839416058394,
+      "grad_norm": 0.5239001485998342,
+      "learning_rate": 1.993912420112756e-05,
+      "loss": 0.0847,
+      "step": 80
+    },
+    {
+      "epoch": 1.1605839416058394,
+      "eval_loss": 0.6174606084823608,
+      "eval_runtime": 1.6663,
+      "eval_samples_per_second": 42.61,
+      "eval_steps_per_second": 1.8,
+      "step": 80
+    },
+    {
+      "epoch": 1.1751824817518248,
+      "grad_norm": 0.4929761742504611,
+      "learning_rate": 1.935350819721849e-05,
+      "loss": 0.1019,
+      "step": 81
+    },
+    {
+      "epoch": 1.1897810218978102,
+      "grad_norm": 0.5544859652703089,
+      "learning_rate": 1.8771139438197168e-05,
+      "loss": 0.1077,
+      "step": 82
+    },
+    {
+      "epoch": 1.2043795620437956,
+      "grad_norm": 0.5164965039818554,
+      "learning_rate": 1.819235283891721e-05,
+      "loss": 0.091,
+      "step": 83
+    },
+    {
+      "epoch": 1.218978102189781,
+      "grad_norm": 0.49567303589016076,
+      "learning_rate": 1.7617481254165487e-05,
+      "loss": 0.1081,
+      "step": 84
+    },
+    {
+      "epoch": 1.2335766423357664,
+      "grad_norm": 0.4587304943562019,
+      "learning_rate": 1.704685528724046e-05,
+      "loss": 0.1087,
+      "step": 85
+    },
+    {
+      "epoch": 1.2481751824817517,
+      "grad_norm": 0.5758635229758376,
+      "learning_rate": 1.648080309982528e-05,
+      "loss": 0.1094,
+      "step": 86
+    },
+    {
+      "epoch": 1.2627737226277373,
+      "grad_norm": 0.4790913429309353,
+      "learning_rate": 1.591965022326507e-05,
+      "loss": 0.1018,
+      "step": 87
+    },
+    {
+      "epoch": 1.2773722627737225,
+      "grad_norm": 0.42743049770737657,
+      "learning_rate": 1.536371937135688e-05,
+      "loss": 0.0921,
+      "step": 88
+    },
+    {
+      "epoch": 1.2919708029197081,
+      "grad_norm": 0.4874948888356134,
+      "learning_rate": 1.4813330254759985e-05,
+      "loss": 0.1044,
+      "step": 89
+    },
+    {
+      "epoch": 1.3065693430656935,
+      "grad_norm": 0.4772485634630385,
+      "learning_rate": 1.426879939713322e-05,
+      "loss": 0.0816,
+      "step": 90
+    },
+    {
+      "epoch": 1.3211678832116789,
+      "grad_norm": 0.40079927908899615,
+      "learning_rate": 1.3730439953105243e-05,
+      "loss": 0.0842,
+      "step": 91
+    },
+    {
+      "epoch": 1.3357664233576643,
+      "grad_norm": 0.4275504239180154,
+      "learning_rate": 1.3198561528182183e-05,
+      "loss": 0.0744,
+      "step": 92
+    },
+    {
+      "epoch": 1.3503649635036497,
+      "grad_norm": 0.3793648773284397,
+      "learning_rate": 1.2673470000696364e-05,
+      "loss": 0.1033,
+      "step": 93
+    },
+    {
+      "epoch": 1.364963503649635,
+      "grad_norm": 0.5181460659792264,
+      "learning_rate": 1.2155467345898602e-05,
+      "loss": 0.1001,
+      "step": 94
+    },
+    {
+      "epoch": 1.3795620437956204,
+      "grad_norm": 0.45318669096336833,
+      "learning_rate": 1.1644851462294957e-05,
+      "loss": 0.101,
+      "step": 95
+    },
+    {
+      "epoch": 1.3941605839416058,
+      "grad_norm": 0.4766867331350184,
+      "learning_rate": 1.114191600032815e-05,
+      "loss": 0.0863,
+      "step": 96
+    },
+    {
+      "epoch": 1.4087591240875912,
+      "grad_norm": 0.4080689197803639,
+      "learning_rate": 1.064695019350187e-05,
+      "loss": 0.0855,
+      "step": 97
+    },
+    {
+      "epoch": 1.4233576642335766,
+      "grad_norm": 0.4653770430519792,
+      "learning_rate": 1.0160238692045332e-05,
+      "loss": 0.111,
+      "step": 98
+    },
+    {
+      "epoch": 1.437956204379562,
+      "grad_norm": 0.45097632263026527,
+      "learning_rate": 9.682061399213525e-06,
+      "loss": 0.0939,
+      "step": 99
+    },
+    {
+      "epoch": 1.4525547445255476,
+      "grad_norm": 0.4496977114474888,
+      "learning_rate": 9.21269331031748e-06,
+      "loss": 0.0882,
+      "step": 100
+    },
+    {
+      "epoch": 1.4525547445255476,
+      "eval_loss": 0.5955010652542114,
+      "eval_runtime": 1.6733,
+      "eval_samples_per_second": 42.432,
+      "eval_steps_per_second": 1.793,
+      "step": 100
+    },
+    {
+      "epoch": 1.4671532846715327,
+      "grad_norm": 0.45643797377810924,
+      "learning_rate": 8.752404354577052e-06,
+      "loss": 0.0937,
+      "step": 101
+    },
+    {
+      "epoch": 1.4817518248175183,
+      "grad_norm": 0.38809063898842117,
+      "learning_rate": 8.301459239887074e-06,
+      "loss": 0.0803,
+      "step": 102
+    },
+    {
+      "epoch": 1.4963503649635037,
+      "grad_norm": 0.4599787928563747,
+      "learning_rate": 7.860117300586383e-06,
+      "loss": 0.1008,
+      "step": 103
+    },
+    {
+      "epoch": 1.510948905109489,
+      "grad_norm": 0.4265168032214748,
+      "learning_rate": 7.428632348317005e-06,
+      "loss": 0.0731,
+      "step": 104
+    },
+    {
+      "epoch": 1.5255474452554745,
+      "grad_norm": 0.4408034300546994,
+      "learning_rate": 7.007252526059446e-06,
+      "loss": 0.075,
+      "step": 105
+    },
+    {
+      "epoch": 1.5401459854014599,
+      "grad_norm": 0.36837598605703786,
+      "learning_rate": 6.596220165428002e-06,
+      "loss": 0.0797,
+      "step": 106
+    },
+    {
+      "epoch": 1.5547445255474452,
+      "grad_norm": 0.45686833811722544,
+      "learning_rate": 6.195771647308074e-06,
+      "loss": 0.1031,
+      "step": 107
+    },
+    {
+      "epoch": 1.5693430656934306,
+      "grad_norm": 0.43293441847585606,
+      "learning_rate": 5.806137265915732e-06,
+      "loss": 0.0876,
+      "step": 108
+    },
+    {
+      "epoch": 1.583941605839416,
+      "grad_norm": 0.4018622232704113,
+      "learning_rate": 5.427541096357647e-06,
+      "loss": 0.0859,
+      "step": 109
+    },
+    {
+      "epoch": 1.5985401459854014,
+      "grad_norm": 0.42651961163568564,
+      "learning_rate": 5.060200865767606e-06,
+      "loss": 0.0914,
+      "step": 110
+    },
+    {
+      "epoch": 1.613138686131387,
+      "grad_norm": 0.45501350150501924,
+      "learning_rate": 4.704327828093641e-06,
+      "loss": 0.0891,
+      "step": 111
+    },
+    {
+      "epoch": 1.6277372262773722,
+      "grad_norm": 0.4018716741861915,
+      "learning_rate": 4.3601266426078426e-06,
+      "loss": 0.0802,
+      "step": 112
+    },
+    {
+      "epoch": 1.6423357664233578,
+      "grad_norm": 0.4381477464449764,
+      "learning_rate": 4.02779525620875e-06,
+      "loss": 0.0837,
+      "step": 113
+    },
+    {
+      "epoch": 1.656934306569343,
+      "grad_norm": 0.38056775027295703,
+      "learning_rate": 3.707524789583891e-06,
+      "loss": 0.0733,
+      "step": 114
+    },
+    {
+      "epoch": 1.6715328467153285,
+      "grad_norm": 0.38615940067266047,
+      "learning_rate": 3.3994994272980946e-06,
+      "loss": 0.0816,
+      "step": 115
+    },
+    {
+      "epoch": 1.686131386861314,
+      "grad_norm": 0.4083027079839302,
+      "learning_rate": 3.1038963118706244e-06,
+      "loss": 0.0947,
+      "step": 116
+    },
+    {
+      "epoch": 1.7007299270072993,
+      "grad_norm": 0.4281395329269055,
+      "learning_rate": 2.8208854419021824e-06,
+      "loss": 0.0807,
+      "step": 117
+    },
+    {
+      "epoch": 1.7153284671532847,
+      "grad_norm": 0.33771309316638104,
+      "learning_rate": 2.5506295743103094e-06,
+      "loss": 0.0576,
+      "step": 118
+    },
+    {
+      "epoch": 1.72992700729927,
+      "grad_norm": 0.3862388702821623,
+      "learning_rate": 2.2932841307293644e-06,
+      "loss": 0.0857,
+      "step": 119
+    },
+    {
+      "epoch": 1.7445255474452555,
+      "grad_norm": 0.3825839529168523,
+      "learning_rate": 2.0489971081290195e-06,
+      "loss": 0.0868,
+      "step": 120
+    },
+    {
+      "epoch": 1.7445255474452555,
+      "eval_loss": 0.6069221496582031,
+      "eval_runtime": 1.6811,
+      "eval_samples_per_second": 42.233,
+      "eval_steps_per_second": 1.785,
+      "step": 120
+    },
+    {
+      "epoch": 1.7591240875912408,
+      "grad_norm": 0.40516989643017143,
+      "learning_rate": 1.817908993702555e-06,
+      "loss": 0.0781,
+      "step": 121
+    },
+    {
+      "epoch": 1.7737226277372264,
+      "grad_norm": 0.37108997015823786,
+      "learning_rate": 1.6001526840740049e-06,
+      "loss": 0.0773,
+      "step": 122
+    },
+    {
+      "epoch": 1.7883211678832116,
+      "grad_norm": 0.4152153354127059,
+      "learning_rate": 1.3958534088705206e-06,
+      "loss": 0.0648,
+      "step": 123
+    },
+    {
+      "epoch": 1.8029197080291972,
+      "grad_norm": 0.3350032112266357,
+      "learning_rate": 1.205128658704005e-06,
+      "loss": 0.0685,
+      "step": 124
+    },
+    {
+      "epoch": 1.8175182481751824,
+      "grad_norm": 0.37253550313302386,
+      "learning_rate": 1.028088117603332e-06,
+      "loss": 0.0597,
+      "step": 125
+    },
+    {
+      "epoch": 1.832116788321168,
+      "grad_norm": 0.3646815056116574,
+      "learning_rate": 8.648335999360935e-07,
+      "loss": 0.0851,
+      "step": 126
+    },
+    {
+      "epoch": 1.8467153284671531,
+      "grad_norm": 0.40006480391539845,
+      "learning_rate": 7.154589918561022e-07,
+      "loss": 0.0775,
+      "step": 127
+    },
+    {
+      "epoch": 1.8613138686131387,
+      "grad_norm": 0.3998882921725406,
+      "learning_rate": 5.800501973103362e-07,
+      "loss": 0.0837,
+      "step": 128
+    },
+    {
+      "epoch": 1.8759124087591241,
+      "grad_norm": 0.45939594997920835,
+      "learning_rate": 4.586850886363875e-07,
+      "loss": 0.104,
+      "step": 129
+    },
+    {
+      "epoch": 1.8905109489051095,
+      "grad_norm": 0.415499645321787,
+      "learning_rate": 3.514334617787857e-07,
+      "loss": 0.0694,
+      "step": 130
+    },
+    {
+      "epoch": 1.905109489051095,
+      "grad_norm": 0.3572513685399802,
+      "learning_rate": 2.5835699615002764e-07,
+      "loss": 0.0617,
+      "step": 131
+    },
+    {
+      "epoch": 1.9197080291970803,
+      "grad_norm": 0.3824291555094829,
+      "learning_rate": 1.7950921915928788e-07,
+      "loss": 0.0792,
+      "step": 132
+    },
+    {
+      "epoch": 1.9343065693430657,
+      "grad_norm": 0.42192592913917887,
+      "learning_rate": 1.1493547542933969e-07,
+      "loss": 0.0919,
+      "step": 133
+    },
+    {
+      "epoch": 1.948905109489051,
+      "grad_norm": 0.40497490119047314,
+      "learning_rate": 6.467290071925647e-08,
+      "loss": 0.0655,
+      "step": 134
+    },
+    {
+      "epoch": 1.9635036496350367,
+      "grad_norm": 0.3653261951630353,
+      "learning_rate": 2.8750400567992274e-08,
+      "loss": 0.0607,
+      "step": 135
+    },
+    {
+      "epoch": 1.9781021897810218,
+      "grad_norm": 0.40679528870310416,
+      "learning_rate": 7.188633671079137e-09,
+      "loss": 0.0823,
+      "step": 136
+    },
+    {
+      "epoch": 1.9781021897810218,
+      "step": 136,
+      "total_flos": 89096184856576.0,
+      "train_loss": 0.23073186133714282,
+      "train_runtime": 917.4487,
+      "train_samples_per_second": 11.959,
+      "train_steps_per_second": 0.148
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 136,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 89096184856576.0,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74b1a220827ceec689b957c34f20898febea24ed4d9dae61965753808efe0c8
+size 7992