Upload folder using huggingface_hub

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: other
+base_model: llava-hf/llava-v1.6-mistral-7b-hf
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Compcap_cooccur_0_40
+  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. -->
+
+# Compcap_cooccur_0_40
+
+This model is a fine-tuned version of [llava-hf/llava-v1.6-mistral-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf) on the Compcap_cooccur_0_40 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8389
+
+## 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: 1e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9458        | 0.3384 | 50   | 0.9426          |
+| 0.8779        | 0.6768 | 100  | 0.8877          |
+| 0.82          | 1.0152 | 150  | 0.8625          |
+| 0.7763        | 1.3536 | 200  | 0.8518          |
+| 0.7719        | 1.6920 | 250  | 0.8421          |
+| 0.7347        | 2.0305 | 300  | 0.8381          |
+| 0.7232        | 2.3689 | 350  | 0.8402          |
+| 0.721         | 2.7073 | 400  | 0.8391          |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.984771573604061,
+    "eval_loss": 0.8388660550117493,
+    "eval_runtime": 72.5974,
+    "eval_samples_per_second": 57.853,
+    "eval_steps_per_second": 0.909,
+    "total_flos": 2600101931384832.0,
+    "train_loss": 0.8256486911081673,
+    "train_runtime": 6391.2706,
+    "train_samples_per_second": 17.743,
+    "train_steps_per_second": 0.069
+}

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
+  "architectures": [
+    "LlavaNextForConditionalGeneration"
+  ],
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava_next",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "architectures": [
+      "MistralForCausalLM"
+    ],
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_image_newline_parameter": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.984771573604061,
+    "eval_loss": 0.8388660550117493,
+    "eval_runtime": 72.5974,
+    "eval_samples_per_second": 57.853,
+    "eval_steps_per_second": 0.909
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f59dd92c608448c54aace804f7c704ba927a5693319c6ebbfbebf86ab0e47f7
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc8bcea41ff35a0a94698e0dbbb5d2dec92fb5f7047180a44d17a8b9e6de67e
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7634579453dcb5f5a3c6d7593c8fac9e54f3a40732876f1e876e3c0055624d7
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e8acc387b1ac67cc60ca4fc23f20774434cffe4bf00813efca6bfb16372d0c
+size 380134008

model.safetensors.index.json

@@ -0,0 +1,694 @@
+{
+  "metadata": {
+    "total_size": 15133495296
+  },
+  "weight_map": {
+    "image_newline": "model-00001-of-00004.safetensors",
+    "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00004.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,52 @@
+{
+  "aspect_ratio_setting": "anyres",
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaNextProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '`[INST] `' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {
+    "image_token": "<image>"
+  },
+  "image_token": "<image>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "LlavaNextProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.984771573604061,
+    "total_flos": 2600101931384832.0,
+    "train_loss": 0.8256486911081673,
+    "train_runtime": 6391.2706,
+    "train_samples_per_second": 17.743,
+    "train_steps_per_second": 0.069
+}

trainer_log.jsonl

@@ -0,0 +1,97 @@
+{"current_steps": 5, "total_steps": 441, "loss": 1.7543, "learning_rate": 5e-07, "epoch": 0.0338409475465313, "percentage": 1.13, "elapsed_time": "0:01:09", "remaining_time": "1:40:18"}
+{"current_steps": 10, "total_steps": 441, "loss": 1.5921, "learning_rate": 1e-06, "epoch": 0.0676818950930626, "percentage": 2.27, "elapsed_time": "0:02:14", "remaining_time": "1:36:46"}
+{"current_steps": 15, "total_steps": 441, "loss": 1.2895, "learning_rate": 9.996679701338661e-07, "epoch": 0.10152284263959391, "percentage": 3.4, "elapsed_time": "0:03:20", "remaining_time": "1:35:02"}
+{"current_steps": 20, "total_steps": 441, "loss": 1.135, "learning_rate": 9.986723215107924e-07, "epoch": 0.1353637901861252, "percentage": 4.54, "elapsed_time": "0:04:25", "remaining_time": "1:33:16"}
+{"current_steps": 25, "total_steps": 441, "loss": 1.0651, "learning_rate": 9.97014376471095e-07, "epoch": 0.1692047377326565, "percentage": 5.67, "elapsed_time": "0:05:30", "remaining_time": "1:31:39"}
+{"current_steps": 30, "total_steps": 441, "loss": 1.0038, "learning_rate": 9.946963369638524e-07, "epoch": 0.20304568527918782, "percentage": 6.8, "elapsed_time": "0:06:35", "remaining_time": "1:30:22"}
+{"current_steps": 35, "total_steps": 441, "loss": 0.9911, "learning_rate": 9.917212816224536e-07, "epoch": 0.23688663282571912, "percentage": 7.94, "elapsed_time": "0:07:41", "remaining_time": "1:29:12"}
+{"current_steps": 40, "total_steps": 441, "loss": 0.9617, "learning_rate": 9.880931616758056e-07, "epoch": 0.2707275803722504, "percentage": 9.07, "elapsed_time": "0:08:47", "remaining_time": "1:28:08"}
+{"current_steps": 45, "total_steps": 441, "loss": 0.955, "learning_rate": 9.838167957006293e-07, "epoch": 0.30456852791878175, "percentage": 10.2, "elapsed_time": "0:09:52", "remaining_time": "1:26:51"}
+{"current_steps": 50, "total_steps": 441, "loss": 0.9458, "learning_rate": 9.788978632218138e-07, "epoch": 0.338409475465313, "percentage": 11.34, "elapsed_time": "0:10:57", "remaining_time": "1:25:41"}
+{"current_steps": 50, "total_steps": 441, "eval_loss": 0.9426366686820984, "epoch": 0.338409475465313, "percentage": 11.34, "elapsed_time": "0:12:10", "remaining_time": "1:35:12"}
+{"current_steps": 55, "total_steps": 441, "loss": 0.943, "learning_rate": 9.73342897169329e-07, "epoch": 0.37225042301184436, "percentage": 12.47, "elapsed_time": "0:13:16", "remaining_time": "1:33:08"}
+{"current_steps": 60, "total_steps": 441, "loss": 0.9093, "learning_rate": 9.671592752017137e-07, "epoch": 0.40609137055837563, "percentage": 13.61, "elapsed_time": "0:14:21", "remaining_time": "1:31:09"}
+{"current_steps": 65, "total_steps": 441, "loss": 0.9195, "learning_rate": 9.603552099076648e-07, "epoch": 0.43993231810490696, "percentage": 14.74, "elapsed_time": "0:15:27", "remaining_time": "1:29:22"}
+{"current_steps": 70, "total_steps": 441, "loss": 0.886, "learning_rate": 9.52939737898737e-07, "epoch": 0.47377326565143824, "percentage": 15.87, "elapsed_time": "0:16:32", "remaining_time": "1:27:42"}
+{"current_steps": 75, "total_steps": 441, "loss": 0.9185, "learning_rate": 9.449227078076443e-07, "epoch": 0.5076142131979695, "percentage": 17.01, "elapsed_time": "0:17:38", "remaining_time": "1:26:04"}
+{"current_steps": 80, "total_steps": 441, "loss": 0.8983, "learning_rate": 9.363147672080985e-07, "epoch": 0.5414551607445008, "percentage": 18.14, "elapsed_time": "0:18:43", "remaining_time": "1:24:28"}
+{"current_steps": 85, "total_steps": 441, "loss": 0.8843, "learning_rate": 9.271273484735592e-07, "epoch": 0.5752961082910322, "percentage": 19.27, "elapsed_time": "0:19:48", "remaining_time": "1:22:56"}
+{"current_steps": 90, "total_steps": 441, "loss": 0.8844, "learning_rate": 9.173726535936766e-07, "epoch": 0.6091370558375635, "percentage": 20.41, "elapsed_time": "0:20:54", "remaining_time": "1:21:31"}
+{"current_steps": 95, "total_steps": 441, "loss": 0.8994, "learning_rate": 9.070636379685915e-07, "epoch": 0.6429780033840947, "percentage": 21.54, "elapsed_time": "0:21:59", "remaining_time": "1:20:05"}
+{"current_steps": 100, "total_steps": 441, "loss": 0.8779, "learning_rate": 8.962139932026156e-07, "epoch": 0.676818950930626, "percentage": 22.68, "elapsed_time": "0:23:05", "remaining_time": "1:18:45"}
+{"current_steps": 100, "total_steps": 441, "eval_loss": 0.887722373008728, "epoch": 0.676818950930626, "percentage": 22.68, "elapsed_time": "0:24:18", "remaining_time": "1:22:53"}
+{"current_steps": 105, "total_steps": 441, "loss": 0.864, "learning_rate": 8.848381289201459e-07, "epoch": 0.7106598984771574, "percentage": 23.81, "elapsed_time": "0:25:24", "remaining_time": "1:21:17"}
+{"current_steps": 110, "total_steps": 441, "loss": 0.8795, "learning_rate": 8.72951153627962e-07, "epoch": 0.7445008460236887, "percentage": 24.94, "elapsed_time": "0:26:29", "remaining_time": "1:19:42"}
+{"current_steps": 115, "total_steps": 441, "loss": 0.8657, "learning_rate": 8.605688546493238e-07, "epoch": 0.7783417935702199, "percentage": 26.08, "elapsed_time": "0:27:34", "remaining_time": "1:18:09"}
+{"current_steps": 120, "total_steps": 441, "loss": 0.8627, "learning_rate": 8.477076771565202e-07, "epoch": 0.8121827411167513, "percentage": 27.21, "elapsed_time": "0:28:39", "remaining_time": "1:16:40"}
+{"current_steps": 125, "total_steps": 441, "loss": 0.8695, "learning_rate": 8.343847023297169e-07, "epoch": 0.8460236886632826, "percentage": 28.34, "elapsed_time": "0:29:45", "remaining_time": "1:15:13"}
+{"current_steps": 130, "total_steps": 441, "loss": 0.8429, "learning_rate": 8.206176246711065e-07, "epoch": 0.8798646362098139, "percentage": 29.48, "elapsed_time": "0:30:51", "remaining_time": "1:13:48"}
+{"current_steps": 135, "total_steps": 441, "loss": 0.8603, "learning_rate": 8.064247285044972e-07, "epoch": 0.9137055837563451, "percentage": 30.61, "elapsed_time": "0:31:56", "remaining_time": "1:12:23"}
+{"current_steps": 140, "total_steps": 441, "loss": 0.8622, "learning_rate": 7.918248636915459e-07, "epoch": 0.9475465313028765, "percentage": 31.75, "elapsed_time": "0:33:02", "remaining_time": "1:11:01"}
+{"current_steps": 145, "total_steps": 441, "loss": 0.8473, "learning_rate": 7.768374205968906e-07, "epoch": 0.9813874788494078, "percentage": 32.88, "elapsed_time": "0:34:07", "remaining_time": "1:09:39"}
+{"current_steps": 150, "total_steps": 441, "loss": 0.82, "learning_rate": 7.614823043354285e-07, "epoch": 1.015228426395939, "percentage": 34.01, "elapsed_time": "0:35:13", "remaining_time": "1:08:19"}
+{"current_steps": 150, "total_steps": 441, "eval_loss": 0.8625058531761169, "epoch": 1.015228426395939, "percentage": 34.01, "elapsed_time": "0:36:25", "remaining_time": "1:10:40"}
+{"current_steps": 155, "total_steps": 441, "loss": 0.823, "learning_rate": 7.457799083359471e-07, "epoch": 1.0490693739424704, "percentage": 35.15, "elapsed_time": "0:37:30", "remaining_time": "1:09:13"}
+{"current_steps": 160, "total_steps": 441, "loss": 0.7903, "learning_rate": 7.297510872562131e-07, "epoch": 1.0829103214890017, "percentage": 36.28, "elapsed_time": "0:38:36", "remaining_time": "1:07:49"}
+{"current_steps": 165, "total_steps": 441, "loss": 0.7844, "learning_rate": 7.134171292854955e-07, "epoch": 1.116751269035533, "percentage": 37.41, "elapsed_time": "0:39:42", "remaining_time": "1:06:24"}
+{"current_steps": 170, "total_steps": 441, "loss": 0.7888, "learning_rate": 6.967997278713089e-07, "epoch": 1.1505922165820643, "percentage": 38.55, "elapsed_time": "0:40:47", "remaining_time": "1:05:01"}
+{"current_steps": 175, "total_steps": 441, "loss": 0.7968, "learning_rate": 6.79920952907921e-07, "epoch": 1.1844331641285957, "percentage": 39.68, "elapsed_time": "0:41:53", "remaining_time": "1:03:39"}
+{"current_steps": 180, "total_steps": 441, "loss": 0.7823, "learning_rate": 6.628032214248982e-07, "epoch": 1.218274111675127, "percentage": 40.82, "elapsed_time": "0:42:58", "remaining_time": "1:02:19"}
+{"current_steps": 185, "total_steps": 441, "loss": 0.7848, "learning_rate": 6.454692678146119e-07, "epoch": 1.252115059221658, "percentage": 41.95, "elapsed_time": "0:44:04", "remaining_time": "1:00:59"}
+{"current_steps": 190, "total_steps": 441, "loss": 0.7683, "learning_rate": 6.279421136382494e-07, "epoch": 1.2859560067681894, "percentage": 43.08, "elapsed_time": "0:45:10", "remaining_time": "0:59:40"}
+{"current_steps": 195, "total_steps": 441, "loss": 0.7776, "learning_rate": 6.102450370504299e-07, "epoch": 1.3197969543147208, "percentage": 44.22, "elapsed_time": "0:46:16", "remaining_time": "0:58:22"}
+{"current_steps": 200, "total_steps": 441, "loss": 0.7763, "learning_rate": 5.924015418830354e-07, "epoch": 1.353637901861252, "percentage": 45.35, "elapsed_time": "0:47:21", "remaining_time": "0:57:04"}
+{"current_steps": 200, "total_steps": 441, "eval_loss": 0.8517683148384094, "epoch": 1.353637901861252, "percentage": 45.35, "elapsed_time": "0:48:34", "remaining_time": "0:58:31"}
+{"current_steps": 205, "total_steps": 441, "loss": 0.7586, "learning_rate": 5.74435326429313e-07, "epoch": 1.3874788494077834, "percentage": 46.49, "elapsed_time": "0:49:40", "remaining_time": "0:57:10"}
+{"current_steps": 210, "total_steps": 441, "loss": 0.7693, "learning_rate": 5.563702519697108e-07, "epoch": 1.4213197969543148, "percentage": 47.62, "elapsed_time": "0:50:46", "remaining_time": "0:55:50"}
+{"current_steps": 215, "total_steps": 441, "loss": 0.7784, "learning_rate": 5.382303110812466e-07, "epoch": 1.455160744500846, "percentage": 48.75, "elapsed_time": "0:51:52", "remaining_time": "0:54:31"}
+{"current_steps": 220, "total_steps": 441, "loss": 0.7789, "learning_rate": 5.200395957725005e-07, "epoch": 1.4890016920473772, "percentage": 49.89, "elapsed_time": "0:52:57", "remaining_time": "0:53:11"}
+{"current_steps": 225, "total_steps": 441, "loss": 0.7692, "learning_rate": 5.018222654865471e-07, "epoch": 1.5228426395939088, "percentage": 51.02, "elapsed_time": "0:54:02", "remaining_time": "0:51:53"}
+{"current_steps": 230, "total_steps": 441, "loss": 0.7954, "learning_rate": 4.836025150143318e-07, "epoch": 1.5566835871404399, "percentage": 52.15, "elapsed_time": "0:55:08", "remaining_time": "0:50:34"}
+{"current_steps": 235, "total_steps": 441, "loss": 0.7882, "learning_rate": 4.654045423610952e-07, "epoch": 1.5905245346869712, "percentage": 53.29, "elapsed_time": "0:56:13", "remaining_time": "0:49:17"}
+{"current_steps": 240, "total_steps": 441, "loss": 0.7782, "learning_rate": 4.4725251660853357e-07, "epoch": 1.6243654822335025, "percentage": 54.42, "elapsed_time": "0:57:19", "remaining_time": "0:48:00"}
+{"current_steps": 245, "total_steps": 441, "loss": 0.7709, "learning_rate": 4.2917054581536926e-07, "epoch": 1.6582064297800339, "percentage": 55.56, "elapsed_time": "0:58:24", "remaining_time": "0:46:43"}
+{"current_steps": 250, "total_steps": 441, "loss": 0.7719, "learning_rate": 4.1118264499897003e-07, "epoch": 1.6920473773265652, "percentage": 56.69, "elapsed_time": "0:59:29", "remaining_time": "0:45:27"}
+{"current_steps": 250, "total_steps": 441, "eval_loss": 0.8421301245689392, "epoch": 1.6920473773265652, "percentage": 56.69, "elapsed_time": "1:00:42", "remaining_time": "0:46:22"}
+{"current_steps": 255, "total_steps": 441, "loss": 0.7599, "learning_rate": 3.9331270424053616e-07, "epoch": 1.7258883248730963, "percentage": 57.82, "elapsed_time": "1:01:46", "remaining_time": "0:45:03"}
+{"current_steps": 260, "total_steps": 441, "loss": 0.7727, "learning_rate": 3.755844569562191e-07, "epoch": 1.7597292724196278, "percentage": 58.96, "elapsed_time": "1:02:52", "remaining_time": "0:43:45"}
+{"current_steps": 265, "total_steps": 441, "loss": 0.7709, "learning_rate": 3.580214483763093e-07, "epoch": 1.793570219966159, "percentage": 60.09, "elapsed_time": "1:03:57", "remaining_time": "0:42:28"}
+{"current_steps": 270, "total_steps": 441, "loss": 0.782, "learning_rate": 3.406470042743574e-07, "epoch": 1.8274111675126905, "percentage": 61.22, "elapsed_time": "1:05:03", "remaining_time": "0:41:11"}
+{"current_steps": 275, "total_steps": 441, "loss": 0.7793, "learning_rate": 3.23484199987761e-07, "epoch": 1.8612521150592216, "percentage": 62.36, "elapsed_time": "1:06:09", "remaining_time": "0:39:55"}
+{"current_steps": 280, "total_steps": 441, "loss": 0.7623, "learning_rate": 3.065558297709588e-07, "epoch": 1.895093062605753, "percentage": 63.49, "elapsed_time": "1:07:14", "remaining_time": "0:38:39"}
+{"current_steps": 285, "total_steps": 441, "loss": 0.7628, "learning_rate": 2.898843765219388e-07, "epoch": 1.9289340101522843, "percentage": 64.63, "elapsed_time": "1:08:20", "remaining_time": "0:37:24"}
+{"current_steps": 290, "total_steps": 441, "loss": 0.7584, "learning_rate": 2.7349198192226295e-07, "epoch": 1.9627749576988156, "percentage": 65.76, "elapsed_time": "1:09:25", "remaining_time": "0:36:09"}
+{"current_steps": 295, "total_steps": 441, "loss": 0.7645, "learning_rate": 2.574004170302696e-07, "epoch": 1.996615905245347, "percentage": 66.89, "elapsed_time": "1:10:31", "remaining_time": "0:34:54"}
+{"current_steps": 300, "total_steps": 441, "loss": 0.7347, "learning_rate": 2.4163105336650643e-07, "epoch": 2.030456852791878, "percentage": 68.03, "elapsed_time": "1:11:36", "remaining_time": "0:33:39"}
+{"current_steps": 300, "total_steps": 441, "eval_loss": 0.8380723595619202, "epoch": 2.030456852791878, "percentage": 68.03, "elapsed_time": "1:12:48", "remaining_time": "0:34:13"}
+{"current_steps": 305, "total_steps": 441, "loss": 0.7348, "learning_rate": 2.2620483452979887e-07, "epoch": 2.0642978003384096, "percentage": 69.16, "elapsed_time": "1:13:54", "remaining_time": "0:32:57"}
+{"current_steps": 310, "total_steps": 441, "loss": 0.7193, "learning_rate": 2.1114224838164806e-07, "epoch": 2.0981387478849407, "percentage": 70.29, "elapsed_time": "1:14:59", "remaining_time": "0:31:41"}
+{"current_steps": 315, "total_steps": 441, "loss": 0.7286, "learning_rate": 1.964632998359036e-07, "epoch": 2.1319796954314723, "percentage": 71.43, "elapsed_time": "1:16:04", "remaining_time": "0:30:25"}
+{"current_steps": 320, "total_steps": 441, "loss": 0.7024, "learning_rate": 1.8218748428984782e-07, "epoch": 2.1658206429780034, "percentage": 72.56, "elapsed_time": "1:17:09", "remaining_time": "0:29:10"}
+{"current_steps": 325, "total_steps": 441, "loss": 0.7084, "learning_rate": 1.6833376173198005e-07, "epoch": 2.199661590524535, "percentage": 73.7, "elapsed_time": "1:18:15", "remaining_time": "0:27:55"}
+{"current_steps": 330, "total_steps": 441, "loss": 0.7088, "learning_rate": 1.5492053156088498e-07, "epoch": 2.233502538071066, "percentage": 74.83, "elapsed_time": "1:19:20", "remaining_time": "0:26:41"}
+{"current_steps": 335, "total_steps": 441, "loss": 0.7244, "learning_rate": 1.4196560814863567e-07, "epoch": 2.267343485617597, "percentage": 75.96, "elapsed_time": "1:20:25", "remaining_time": "0:25:26"}
+{"current_steps": 340, "total_steps": 441, "loss": 0.7261, "learning_rate": 1.294861971811773e-07, "epoch": 2.3011844331641287, "percentage": 77.1, "elapsed_time": "1:21:31", "remaining_time": "0:24:13"}
+{"current_steps": 345, "total_steps": 441, "loss": 0.7193, "learning_rate": 1.1749887280712161e-07, "epoch": 2.33502538071066, "percentage": 78.23, "elapsed_time": "1:22:38", "remaining_time": "0:22:59"}
+{"current_steps": 350, "total_steps": 441, "loss": 0.7232, "learning_rate": 1.0601955562529774e-07, "epoch": 2.3688663282571913, "percentage": 79.37, "elapsed_time": "1:23:43", "remaining_time": "0:21:46"}
+{"current_steps": 350, "total_steps": 441, "eval_loss": 0.84018474817276, "epoch": 2.3688663282571913, "percentage": 79.37, "elapsed_time": "1:24:56", "remaining_time": "0:22:05"}
+{"current_steps": 355, "total_steps": 441, "loss": 0.7072, "learning_rate": 9.506349154029425e-08, "epoch": 2.4027072758037225, "percentage": 80.5, "elapsed_time": "1:26:02", "remaining_time": "0:20:50"}
+{"current_steps": 360, "total_steps": 441, "loss": 0.724, "learning_rate": 8.46452315140772e-08, "epoch": 2.436548223350254, "percentage": 81.63, "elapsed_time": "1:27:07", "remaining_time": "0:19:36"}
+{"current_steps": 365, "total_steps": 441, "loss": 0.726, "learning_rate": 7.477861224057403e-08, "epoch": 2.470389170896785, "percentage": 82.77, "elapsed_time": "1:28:12", "remaining_time": "0:18:21"}
+{"current_steps": 370, "total_steps": 441, "loss": 0.7152, "learning_rate": 6.547673776889095e-08, "epoch": 2.504230118443316, "percentage": 83.9, "elapsed_time": "1:29:17", "remaining_time": "0:17:08"}
+{"current_steps": 375, "total_steps": 441, "loss": 0.7222, "learning_rate": 5.6751962099570396e-08, "epoch": 2.5380710659898478, "percentage": 85.03, "elapsed_time": "1:30:22", "remaining_time": "0:15:54"}
+{"current_steps": 380, "total_steps": 441, "loss": 0.7141, "learning_rate": 4.861587277700274e-08, "epoch": 2.571912013536379, "percentage": 86.17, "elapsed_time": "1:31:28", "remaining_time": "0:14:41"}
+{"current_steps": 385, "total_steps": 441, "loss": 0.7075, "learning_rate": 4.107927549978235e-08, "epoch": 2.6057529610829104, "percentage": 87.3, "elapsed_time": "1:32:33", "remaining_time": "0:13:27"}
+{"current_steps": 390, "total_steps": 441, "loss": 0.7171, "learning_rate": 3.4152179769449396e-08, "epoch": 2.6395939086294415, "percentage": 88.44, "elapsed_time": "1:33:39", "remaining_time": "0:12:14"}
+{"current_steps": 395, "total_steps": 441, "loss": 0.7198, "learning_rate": 2.784378559667622e-08, "epoch": 2.673434856175973, "percentage": 89.57, "elapsed_time": "1:34:45", "remaining_time": "0:11:02"}
+{"current_steps": 400, "total_steps": 441, "loss": 0.721, "learning_rate": 2.2162471282553553e-08, "epoch": 2.707275803722504, "percentage": 90.7, "elapsed_time": "1:35:51", "remaining_time": "0:09:49"}
+{"current_steps": 400, "total_steps": 441, "eval_loss": 0.8391405940055847, "epoch": 2.707275803722504, "percentage": 90.7, "elapsed_time": "1:37:04", "remaining_time": "0:09:56"}
+{"current_steps": 405, "total_steps": 441, "loss": 0.7091, "learning_rate": 1.7115782291206082e-08, "epoch": 2.7411167512690353, "percentage": 91.84, "elapsed_time": "1:38:09", "remaining_time": "0:08:43"}
+{"current_steps": 410, "total_steps": 441, "loss": 0.7247, "learning_rate": 1.2710421228514733e-08, "epoch": 2.774957698815567, "percentage": 92.97, "elapsed_time": "1:39:14", "remaining_time": "0:07:30"}
+{"current_steps": 415, "total_steps": 441, "loss": 0.7245, "learning_rate": 8.952238940255153e-09, "epoch": 2.808798646362098, "percentage": 94.1, "elapsed_time": "1:40:19", "remaining_time": "0:06:17"}
+{"current_steps": 420, "total_steps": 441, "loss": 0.7254, "learning_rate": 5.846226741475557e-09, "epoch": 2.8426395939086295, "percentage": 95.24, "elapsed_time": "1:41:25", "remaining_time": "0:05:04"}
+{"current_steps": 425, "total_steps": 441, "loss": 0.7037, "learning_rate": 3.3965097874343872e-09, "epoch": 2.8764805414551606, "percentage": 96.37, "elapsed_time": "1:42:29", "remaining_time": "0:03:51"}
+{"current_steps": 430, "total_steps": 441, "loss": 0.7319, "learning_rate": 1.6063415949008618e-09, "epoch": 2.910321489001692, "percentage": 97.51, "elapsed_time": "1:43:35", "remaining_time": "0:02:38"}
+{"current_steps": 435, "total_steps": 441, "loss": 0.7199, "learning_rate": 4.780997210962478e-10, "epoch": 2.9441624365482233, "percentage": 98.64, "elapsed_time": "1:44:40", "remaining_time": "0:01:26"}
+{"current_steps": 440, "total_steps": 441, "loss": 0.7036, "learning_rate": 1.328260601385356e-11, "epoch": 2.9780033840947544, "percentage": 99.77, "elapsed_time": "1:45:45", "remaining_time": "0:00:14"}
+{"current_steps": 441, "total_steps": 441, "epoch": 2.984771573604061, "percentage": 100.0, "elapsed_time": "1:46:29", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,722 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.984771573604061,
+  "eval_steps": 50,
+  "global_step": 441,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0338409475465313,
+      "grad_norm": 19.362921643157705,
+      "learning_rate": 5e-07,
+      "loss": 1.7543,
+      "step": 5
+    },
+    {
+      "epoch": 0.0676818950930626,
+      "grad_norm": 12.440471039796169,
+      "learning_rate": 1e-06,
+      "loss": 1.5921,
+      "step": 10
+    },
+    {
+      "epoch": 0.10152284263959391,
+      "grad_norm": 7.151840796848598,
+      "learning_rate": 9.996679701338661e-07,
+      "loss": 1.2895,
+      "step": 15
+    },
+    {
+      "epoch": 0.1353637901861252,
+      "grad_norm": 4.254605069904108,
+      "learning_rate": 9.986723215107924e-07,
+      "loss": 1.135,
+      "step": 20
+    },
+    {
+      "epoch": 0.1692047377326565,
+      "grad_norm": 3.6917219941972412,
+      "learning_rate": 9.97014376471095e-07,
+      "loss": 1.0651,
+      "step": 25
+    },
+    {
+      "epoch": 0.20304568527918782,
+      "grad_norm": 3.7987347848198634,
+      "learning_rate": 9.946963369638524e-07,
+      "loss": 1.0038,
+      "step": 30
+    },
+    {
+      "epoch": 0.23688663282571912,
+      "grad_norm": 3.637845138860867,
+      "learning_rate": 9.917212816224536e-07,
+      "loss": 0.9911,
+      "step": 35
+    },
+    {
+      "epoch": 0.2707275803722504,
+      "grad_norm": 3.3460567231716873,
+      "learning_rate": 9.880931616758056e-07,
+      "loss": 0.9617,
+      "step": 40
+    },
+    {
+      "epoch": 0.30456852791878175,
+      "grad_norm": 3.377056006196627,
+      "learning_rate": 9.838167957006293e-07,
+      "loss": 0.955,
+      "step": 45
+    },
+    {
+      "epoch": 0.338409475465313,
+      "grad_norm": 3.3982403942088624,
+      "learning_rate": 9.788978632218138e-07,
+      "loss": 0.9458,
+      "step": 50
+    },
+    {
+      "epoch": 0.338409475465313,
+      "eval_loss": 0.9426366686820984,
+      "eval_runtime": 73.0561,
+      "eval_samples_per_second": 57.49,
+      "eval_steps_per_second": 0.903,
+      "step": 50
+    },
+    {
+      "epoch": 0.37225042301184436,
+      "grad_norm": 3.689104664245426,
+      "learning_rate": 9.73342897169329e-07,
+      "loss": 0.943,
+      "step": 55
+    },
+    {
+      "epoch": 0.40609137055837563,
+      "grad_norm": 3.395123607137787,
+      "learning_rate": 9.671592752017137e-07,
+      "loss": 0.9093,
+      "step": 60
+    },
+    {
+      "epoch": 0.43993231810490696,
+      "grad_norm": 3.357446602126202,
+      "learning_rate": 9.603552099076648e-07,
+      "loss": 0.9195,
+      "step": 65
+    },
+    {
+      "epoch": 0.47377326565143824,
+      "grad_norm": 3.691462819097496,
+      "learning_rate": 9.52939737898737e-07,
+      "loss": 0.886,
+      "step": 70
+    },
+    {
+      "epoch": 0.5076142131979695,
+      "grad_norm": 3.5969341059847415,
+      "learning_rate": 9.449227078076443e-07,
+      "loss": 0.9185,
+      "step": 75
+    },
+    {
+      "epoch": 0.5414551607445008,
+      "grad_norm": 3.558555135432629,
+      "learning_rate": 9.363147672080985e-07,
+      "loss": 0.8983,
+      "step": 80
+    },
+    {
+      "epoch": 0.5752961082910322,
+      "grad_norm": 3.6252630464826523,
+      "learning_rate": 9.271273484735592e-07,
+      "loss": 0.8843,
+      "step": 85
+    },
+    {
+      "epoch": 0.6091370558375635,
+      "grad_norm": 3.3121290866804913,
+      "learning_rate": 9.173726535936766e-07,
+      "loss": 0.8844,
+      "step": 90
+    },
+    {
+      "epoch": 0.6429780033840947,
+      "grad_norm": 3.580257416417439,
+      "learning_rate": 9.070636379685915e-07,
+      "loss": 0.8994,
+      "step": 95
+    },
+    {
+      "epoch": 0.676818950930626,
+      "grad_norm": 3.629629801061202,
+      "learning_rate": 8.962139932026156e-07,
+      "loss": 0.8779,
+      "step": 100
+    },
+    {
+      "epoch": 0.676818950930626,
+      "eval_loss": 0.887722373008728,
+      "eval_runtime": 72.6917,
+      "eval_samples_per_second": 57.778,
+      "eval_steps_per_second": 0.908,
+      "step": 100
+    },
+    {
+      "epoch": 0.7106598984771574,
+      "grad_norm": 3.3980001711357466,
+      "learning_rate": 8.848381289201459e-07,
+      "loss": 0.864,
+      "step": 105
+    },
+    {
+      "epoch": 0.7445008460236887,
+      "grad_norm": 3.37541287934786,
+      "learning_rate": 8.72951153627962e-07,
+      "loss": 0.8795,
+      "step": 110
+    },
+    {
+      "epoch": 0.7783417935702199,
+      "grad_norm": 5.903555404027213,
+      "learning_rate": 8.605688546493238e-07,
+      "loss": 0.8657,
+      "step": 115
+    },
+    {
+      "epoch": 0.8121827411167513,
+      "grad_norm": 3.3534687236406615,
+      "learning_rate": 8.477076771565202e-07,
+      "loss": 0.8627,
+      "step": 120
+    },
+    {
+      "epoch": 0.8460236886632826,
+      "grad_norm": 3.472402321033115,
+      "learning_rate": 8.343847023297169e-07,
+      "loss": 0.8695,
+      "step": 125
+    },
+    {
+      "epoch": 0.8798646362098139,
+      "grad_norm": 3.5485673752671865,
+      "learning_rate": 8.206176246711065e-07,
+      "loss": 0.8429,
+      "step": 130
+    },
+    {
+      "epoch": 0.9137055837563451,
+      "grad_norm": 3.4858020678381054,
+      "learning_rate": 8.064247285044972e-07,
+      "loss": 0.8603,
+      "step": 135
+    },
+    {
+      "epoch": 0.9475465313028765,
+      "grad_norm": 3.7500528392849324,
+      "learning_rate": 7.918248636915459e-07,
+      "loss": 0.8622,
+      "step": 140
+    },
+    {
+      "epoch": 0.9813874788494078,
+      "grad_norm": 3.409665848861188,
+      "learning_rate": 7.768374205968906e-07,
+      "loss": 0.8473,
+      "step": 145
+    },
+    {
+      "epoch": 1.015228426395939,
+      "grad_norm": 3.6326130834418944,
+      "learning_rate": 7.614823043354285e-07,
+      "loss": 0.82,
+      "step": 150
+    },
+    {
+      "epoch": 1.015228426395939,
+      "eval_loss": 0.8625058531761169,
+      "eval_runtime": 72.7377,
+      "eval_samples_per_second": 57.742,
+      "eval_steps_per_second": 0.907,
+      "step": 150
+    },
+    {
+      "epoch": 1.0490693739424704,
+      "grad_norm": 3.6224664863477494,
+      "learning_rate": 7.457799083359471e-07,
+      "loss": 0.823,
+      "step": 155
+    },
+    {
+      "epoch": 1.0829103214890017,
+      "grad_norm": 3.392243863011647,
+      "learning_rate": 7.297510872562131e-07,
+      "loss": 0.7903,
+      "step": 160
+    },
+    {
+      "epoch": 1.116751269035533,
+      "grad_norm": 3.6101258998571875,
+      "learning_rate": 7.134171292854955e-07,
+      "loss": 0.7844,
+      "step": 165
+    },
+    {
+      "epoch": 1.1505922165820643,
+      "grad_norm": 3.4039338742997685,
+      "learning_rate": 6.967997278713089e-07,
+      "loss": 0.7888,
+      "step": 170
+    },
+    {
+      "epoch": 1.1844331641285957,
+      "grad_norm": 3.3872407965058384,
+      "learning_rate": 6.79920952907921e-07,
+      "loss": 0.7968,
+      "step": 175
+    },
+    {
+      "epoch": 1.218274111675127,
+      "grad_norm": 3.5554493985038684,
+      "learning_rate": 6.628032214248982e-07,
+      "loss": 0.7823,
+      "step": 180
+    },
+    {
+      "epoch": 1.252115059221658,
+      "grad_norm": 3.655696778331916,
+      "learning_rate": 6.454692678146119e-07,
+      "loss": 0.7848,
+      "step": 185
+    },
+    {
+      "epoch": 1.2859560067681894,
+      "grad_norm": 3.459528935552729,
+      "learning_rate": 6.279421136382494e-07,
+      "loss": 0.7683,
+      "step": 190
+    },
+    {
+      "epoch": 1.3197969543147208,
+      "grad_norm": 3.506826792292506,
+      "learning_rate": 6.102450370504299e-07,
+      "loss": 0.7776,
+      "step": 195
+    },
+    {
+      "epoch": 1.353637901861252,
+      "grad_norm": 3.53257152623125,
+      "learning_rate": 5.924015418830354e-07,
+      "loss": 0.7763,
+      "step": 200
+    },
+    {
+      "epoch": 1.353637901861252,
+      "eval_loss": 0.8517683148384094,
+      "eval_runtime": 72.7613,
+      "eval_samples_per_second": 57.723,
+      "eval_steps_per_second": 0.907,
+      "step": 200
+    },
+    {
+      "epoch": 1.3874788494077834,
+      "grad_norm": 3.4808019080846138,
+      "learning_rate": 5.74435326429313e-07,
+      "loss": 0.7586,
+      "step": 205
+    },
+    {
+      "epoch": 1.4213197969543148,
+      "grad_norm": 3.4920276219604696,
+      "learning_rate": 5.563702519697108e-07,
+      "loss": 0.7693,
+      "step": 210
+    },
+    {
+      "epoch": 1.455160744500846,
+      "grad_norm": 3.563387899492764,
+      "learning_rate": 5.382303110812466e-07,
+      "loss": 0.7784,
+      "step": 215
+    },
+    {
+      "epoch": 1.4890016920473772,
+      "grad_norm": 3.3319886045415914,
+      "learning_rate": 5.200395957725005e-07,
+      "loss": 0.7789,
+      "step": 220
+    },
+    {
+      "epoch": 1.5228426395939088,
+      "grad_norm": 3.824253256636034,
+      "learning_rate": 5.018222654865471e-07,
+      "loss": 0.7692,
+      "step": 225
+    },
+    {
+      "epoch": 1.5566835871404399,
+      "grad_norm": 3.49580497047461,
+      "learning_rate": 4.836025150143318e-07,
+      "loss": 0.7954,
+      "step": 230
+    },
+    {
+      "epoch": 1.5905245346869712,
+      "grad_norm": 3.726391320444098,
+      "learning_rate": 4.654045423610952e-07,
+      "loss": 0.7882,
+      "step": 235
+    },
+    {
+      "epoch": 1.6243654822335025,
+      "grad_norm": 3.940367355899551,
+      "learning_rate": 4.4725251660853357e-07,
+      "loss": 0.7782,
+      "step": 240
+    },
+    {
+      "epoch": 1.6582064297800339,
+      "grad_norm": 3.603115659587366,
+      "learning_rate": 4.2917054581536926e-07,
+      "loss": 0.7709,
+      "step": 245
+    },
+    {
+      "epoch": 1.6920473773265652,
+      "grad_norm": 3.5695746889936726,
+      "learning_rate": 4.1118264499897003e-07,
+      "loss": 0.7719,
+      "step": 250
+    },
+    {
+      "epoch": 1.6920473773265652,
+      "eval_loss": 0.8421301245689392,
+      "eval_runtime": 72.7217,
+      "eval_samples_per_second": 57.754,
+      "eval_steps_per_second": 0.908,
+      "step": 250
+    },
+    {
+      "epoch": 1.7258883248730963,
+      "grad_norm": 3.654464869264395,
+      "learning_rate": 3.9331270424053616e-07,
+      "loss": 0.7599,
+      "step": 255
+    },
+    {
+      "epoch": 1.7597292724196278,
+      "grad_norm": 3.669706546573186,
+      "learning_rate": 3.755844569562191e-07,
+      "loss": 0.7727,
+      "step": 260
+    },
+    {
+      "epoch": 1.793570219966159,
+      "grad_norm": 3.514197357489897,
+      "learning_rate": 3.580214483763093e-07,
+      "loss": 0.7709,
+      "step": 265
+    },
+    {
+      "epoch": 1.8274111675126905,
+      "grad_norm": 3.8443336447359244,
+      "learning_rate": 3.406470042743574e-07,
+      "loss": 0.782,
+      "step": 270
+    },
+    {
+      "epoch": 1.8612521150592216,
+      "grad_norm": 3.625482123749312,
+      "learning_rate": 3.23484199987761e-07,
+      "loss": 0.7793,
+      "step": 275
+    },
+    {
+      "epoch": 1.895093062605753,
+      "grad_norm": 3.5197175718189317,
+      "learning_rate": 3.065558297709588e-07,
+      "loss": 0.7623,
+      "step": 280
+    },
+    {
+      "epoch": 1.9289340101522843,
+      "grad_norm": 3.4330767306351935,
+      "learning_rate": 2.898843765219388e-07,
+      "loss": 0.7628,
+      "step": 285
+    },
+    {
+      "epoch": 1.9627749576988156,
+      "grad_norm": 3.822061440419418,
+      "learning_rate": 2.7349198192226295e-07,
+      "loss": 0.7584,
+      "step": 290
+    },
+    {
+      "epoch": 1.996615905245347,
+      "grad_norm": 3.553974834774039,
+      "learning_rate": 2.574004170302696e-07,
+      "loss": 0.7645,
+      "step": 295
+    },
+    {
+      "epoch": 2.030456852791878,
+      "grad_norm": 3.9479223535228574,
+      "learning_rate": 2.4163105336650643e-07,
+      "loss": 0.7347,
+      "step": 300
+    },
+    {
+      "epoch": 2.030456852791878,
+      "eval_loss": 0.8380723595619202,
+      "eval_runtime": 72.7338,
+      "eval_samples_per_second": 57.745,
+      "eval_steps_per_second": 0.907,
+      "step": 300
+    },
+    {
+      "epoch": 2.0642978003384096,
+      "grad_norm": 3.7132773157030425,
+      "learning_rate": 2.2620483452979887e-07,
+      "loss": 0.7348,
+      "step": 305
+    },
+    {
+      "epoch": 2.0981387478849407,
+      "grad_norm": 3.6057007836329147,
+      "learning_rate": 2.1114224838164806e-07,
+      "loss": 0.7193,
+      "step": 310
+    },
+    {
+      "epoch": 2.1319796954314723,
+      "grad_norm": 3.6945593121525286,
+      "learning_rate": 1.964632998359036e-07,
+      "loss": 0.7286,
+      "step": 315
+    },
+    {
+      "epoch": 2.1658206429780034,
+      "grad_norm": 3.9031426698674663,
+      "learning_rate": 1.8218748428984782e-07,
+      "loss": 0.7024,
+      "step": 320
+    },
+    {
+      "epoch": 2.199661590524535,
+      "grad_norm": 3.4579222711663786,
+      "learning_rate": 1.6833376173198005e-07,
+      "loss": 0.7084,
+      "step": 325
+    },
+    {
+      "epoch": 2.233502538071066,
+      "grad_norm": 3.719715731546776,
+      "learning_rate": 1.5492053156088498e-07,
+      "loss": 0.7088,
+      "step": 330
+    },
+    {
+      "epoch": 2.267343485617597,
+      "grad_norm": 3.8269194060342446,
+      "learning_rate": 1.4196560814863567e-07,
+      "loss": 0.7244,
+      "step": 335
+    },
+    {
+      "epoch": 2.3011844331641287,
+      "grad_norm": 3.839398221167279,
+      "learning_rate": 1.294861971811773e-07,
+      "loss": 0.7261,
+      "step": 340
+    },
+    {
+      "epoch": 2.33502538071066,
+      "grad_norm": 3.6636890535123885,
+      "learning_rate": 1.1749887280712161e-07,
+      "loss": 0.7193,
+      "step": 345
+    },
+    {
+      "epoch": 2.3688663282571913,
+      "grad_norm": 3.9676568766055165,
+      "learning_rate": 1.0601955562529774e-07,
+      "loss": 0.7232,
+      "step": 350
+    },
+    {
+      "epoch": 2.3688663282571913,
+      "eval_loss": 0.84018474817276,
+      "eval_runtime": 72.7538,
+      "eval_samples_per_second": 57.729,
+      "eval_steps_per_second": 0.907,
+      "step": 350
+    },
+    {
+      "epoch": 2.4027072758037225,
+      "grad_norm": 3.871757730003177,
+      "learning_rate": 9.506349154029425e-08,
+      "loss": 0.7072,
+      "step": 355
+    },
+    {
+      "epoch": 2.436548223350254,
+      "grad_norm": 3.709431977886577,
+      "learning_rate": 8.46452315140772e-08,
+      "loss": 0.724,
+      "step": 360
+    },
+    {
+      "epoch": 2.470389170896785,
+      "grad_norm": 3.778002504886439,
+      "learning_rate": 7.477861224057403e-08,
+      "loss": 0.726,
+      "step": 365
+    },
+    {
+      "epoch": 2.504230118443316,
+      "grad_norm": 4.034569033748593,
+      "learning_rate": 6.547673776889095e-08,
+      "loss": 0.7152,
+      "step": 370
+    },
+    {
+      "epoch": 2.5380710659898478,
+      "grad_norm": 3.6052144662756582,
+      "learning_rate": 5.6751962099570396e-08,
+      "loss": 0.7222,
+      "step": 375
+    },
+    {
+      "epoch": 2.571912013536379,
+      "grad_norm": 3.6412688810760887,
+      "learning_rate": 4.861587277700274e-08,
+      "loss": 0.7141,
+      "step": 380
+    },
+    {
+      "epoch": 2.6057529610829104,
+      "grad_norm": 3.788492541312578,
+      "learning_rate": 4.107927549978235e-08,
+      "loss": 0.7075,
+      "step": 385
+    },
+    {
+      "epoch": 2.6395939086294415,
+      "grad_norm": 3.7740858241104385,
+      "learning_rate": 3.4152179769449396e-08,
+      "loss": 0.7171,
+      "step": 390
+    },
+    {
+      "epoch": 2.673434856175973,
+      "grad_norm": 3.693130131986868,
+      "learning_rate": 2.784378559667622e-08,
+      "loss": 0.7198,
+      "step": 395
+    },
+    {
+      "epoch": 2.707275803722504,
+      "grad_norm": 3.627471625901726,
+      "learning_rate": 2.2162471282553553e-08,
+      "loss": 0.721,
+      "step": 400
+    },
+    {
+      "epoch": 2.707275803722504,
+      "eval_loss": 0.8391405940055847,
+      "eval_runtime": 72.6846,
+      "eval_samples_per_second": 57.784,
+      "eval_steps_per_second": 0.908,
+      "step": 400
+    },
+    {
+      "epoch": 2.7411167512690353,
+      "grad_norm": 3.7944346677217715,
+      "learning_rate": 1.7115782291206082e-08,
+      "loss": 0.7091,
+      "step": 405
+    },
+    {
+      "epoch": 2.774957698815567,
+      "grad_norm": 3.684276269607114,
+      "learning_rate": 1.2710421228514733e-08,
+      "loss": 0.7247,
+      "step": 410
+    },
+    {
+      "epoch": 2.808798646362098,
+      "grad_norm": 3.551925911903825,
+      "learning_rate": 8.952238940255153e-09,
+      "loss": 0.7245,
+      "step": 415
+    },
+    {
+      "epoch": 2.8426395939086295,
+      "grad_norm": 3.549163935230389,
+      "learning_rate": 5.846226741475557e-09,
+      "loss": 0.7254,
+      "step": 420
+    },
+    {
+      "epoch": 2.8764805414551606,
+      "grad_norm": 3.809089531185781,
+      "learning_rate": 3.3965097874343872e-09,
+      "loss": 0.7037,
+      "step": 425
+    },
+    {
+      "epoch": 2.910321489001692,
+      "grad_norm": 3.5360521655033934,
+      "learning_rate": 1.6063415949008618e-09,
+      "loss": 0.7319,
+      "step": 430
+    },
+    {
+      "epoch": 2.9441624365482233,
+      "grad_norm": 3.8076879389100875,
+      "learning_rate": 4.780997210962478e-10,
+      "loss": 0.7199,
+      "step": 435
+    },
+    {
+      "epoch": 2.9780033840947544,
+      "grad_norm": 3.6857618291895236,
+      "learning_rate": 1.328260601385356e-11,
+      "loss": 0.7036,
+      "step": 440
+    },
+    {
+      "epoch": 2.984771573604061,
+      "step": 441,
+      "total_flos": 2600101931384832.0,
+      "train_loss": 0.8256486911081673,
+      "train_runtime": 6391.2706,
+      "train_samples_per_second": 17.743,
+      "train_steps_per_second": 0.069
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 441,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2600101931384832.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69b5036b28c7d5d18b37af578ed9354a94cdbc2d0b3c3ecc74ad7262e4c868d
+size 7096