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: RLAIF-V_L0-q0_50
+  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. -->
+
+# RLAIF-V_L0-q0_50
+
+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 RLAIF-V_L0-q0_50 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0366
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1363        | 0.3478 | 50   | 1.1215          |
+| 1.0856        | 0.6957 | 100  | 1.0748          |
+| 0.9426        | 1.0435 | 150  | 1.0553          |
+| 0.9144        | 1.3913 | 200  | 1.0432          |
+| 0.9069        | 1.7391 | 250  | 1.0292          |
+| 0.8152        | 2.0870 | 300  | 1.0396          |
+| 0.8141        | 2.4348 | 350  | 1.0376          |
+| 0.8097        | 2.7826 | 400  | 1.0366          |
+
+
+### 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": 2.9843478260869567,
+    "eval_loss": 1.0366261005401611,
+    "eval_runtime": 70.3377,
+    "eval_samples_per_second": 58.091,
+    "eval_steps_per_second": 0.91,
+    "total_flos": 2529344492666880.0,
+    "train_loss": 0.9555719093287186,
+    "train_runtime": 6085.5766,
+    "train_samples_per_second": 18.127,
+    "train_steps_per_second": 0.07
+}

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": 2.9843478260869567,
+    "eval_loss": 1.0366261005401611,
+    "eval_runtime": 70.3377,
+    "eval_samples_per_second": 58.091,
+    "eval_steps_per_second": 0.91
+}

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 sha256:799997f97d15ccfecdd50d02704918f97c03b1290c4ade9b81c161e00f328046
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e3ccf9b3a662108b54d447b844f38bfcff14cedca01e20971ff7628757419bb
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdeea9a1b403fdf3c3c5218771b0e443d4eac83a5b7a5c550c55d0f86a1d0f71
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa928e1e9dad1769d4b0ee789f85f83b053f6efcf713f067b732bcfbd2e1a26
+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": 2.9843478260869567,
+    "total_flos": 2529344492666880.0,
+    "train_loss": 0.9555719093287186,
+    "train_runtime": 6085.5766,
+    "train_samples_per_second": 18.127,
+    "train_steps_per_second": 0.07
+}

trainer_log.jsonl

@@ -0,0 +1,94 @@
+{"current_steps": 5, "total_steps": 429, "loss": 1.6404, "learning_rate": 5e-07, "epoch": 0.034782608695652174, "percentage": 1.17, "elapsed_time": "0:01:07", "remaining_time": "1:35:10"}
+{"current_steps": 10, "total_steps": 429, "loss": 1.5079, "learning_rate": 1e-06, "epoch": 0.06956521739130435, "percentage": 2.33, "elapsed_time": "0:02:09", "remaining_time": "1:30:28"}
+{"current_steps": 15, "total_steps": 429, "loss": 1.2858, "learning_rate": 9.99648681635985e-07, "epoch": 0.10434782608695652, "percentage": 3.5, "elapsed_time": "0:03:12", "remaining_time": "1:28:37"}
+{"current_steps": 20, "total_steps": 429, "loss": 1.2292, "learning_rate": 9.985952202423114e-07, "epoch": 0.1391304347826087, "percentage": 4.66, "elapsed_time": "0:04:15", "remaining_time": "1:27:09"}
+{"current_steps": 25, "total_steps": 429, "loss": 1.2035, "learning_rate": 9.96841096220313e-07, "epoch": 0.17391304347826086, "percentage": 5.83, "elapsed_time": "0:05:18", "remaining_time": "1:25:39"}
+{"current_steps": 30, "total_steps": 429, "loss": 1.1615, "learning_rate": 9.943887745939163e-07, "epoch": 0.20869565217391303, "percentage": 6.99, "elapsed_time": "0:06:20", "remaining_time": "1:24:17"}
+{"current_steps": 35, "total_steps": 429, "loss": 1.1627, "learning_rate": 9.912417015456088e-07, "epoch": 0.24347826086956523, "percentage": 8.16, "elapsed_time": "0:07:23", "remaining_time": "1:23:11"}
+{"current_steps": 40, "total_steps": 429, "loss": 1.1468, "learning_rate": 9.874042995736093e-07, "epoch": 0.2782608695652174, "percentage": 9.32, "elapsed_time": "0:08:25", "remaining_time": "1:21:59"}
+{"current_steps": 45, "total_steps": 429, "loss": 1.1457, "learning_rate": 9.828819612770495e-07, "epoch": 0.3130434782608696, "percentage": 10.49, "elapsed_time": "0:09:27", "remaining_time": "1:20:46"}
+{"current_steps": 50, "total_steps": 429, "loss": 1.1363, "learning_rate": 9.77681041777897e-07, "epoch": 0.34782608695652173, "percentage": 11.66, "elapsed_time": "0:10:30", "remaining_time": "1:19:40"}
+{"current_steps": 50, "total_steps": 429, "eval_loss": 1.1214656829833984, "epoch": 0.34782608695652173, "percentage": 11.66, "elapsed_time": "0:11:41", "remaining_time": "1:28:39"}
+{"current_steps": 55, "total_steps": 429, "loss": 1.1252, "learning_rate": 9.718088497902707e-07, "epoch": 0.3826086956521739, "percentage": 12.82, "elapsed_time": "0:12:44", "remaining_time": "1:26:35"}
+{"current_steps": 60, "total_steps": 429, "loss": 1.1144, "learning_rate": 9.652736373497e-07, "epoch": 0.41739130434782606, "percentage": 13.99, "elapsed_time": "0:13:46", "remaining_time": "1:24:41"}
+{"current_steps": 65, "total_steps": 429, "loss": 1.1048, "learning_rate": 9.580845882167572e-07, "epoch": 0.45217391304347826, "percentage": 15.15, "elapsed_time": "0:14:48", "remaining_time": "1:22:54"}
+{"current_steps": 70, "total_steps": 429, "loss": 1.0967, "learning_rate": 9.502518049713631e-07, "epoch": 0.48695652173913045, "percentage": 16.32, "elapsed_time": "0:15:50", "remaining_time": "1:21:13"}
+{"current_steps": 75, "total_steps": 429, "loss": 1.0922, "learning_rate": 9.417862948158997e-07, "epoch": 0.5217391304347826, "percentage": 17.48, "elapsed_time": "0:16:52", "remaining_time": "1:19:39"}
+{"current_steps": 80, "total_steps": 429, "loss": 1.1065, "learning_rate": 9.326999541070803e-07, "epoch": 0.5565217391304348, "percentage": 18.65, "elapsed_time": "0:17:55", "remaining_time": "1:18:10"}
+{"current_steps": 85, "total_steps": 429, "loss": 1.08, "learning_rate": 9.23005551638316e-07, "epoch": 0.591304347826087, "percentage": 19.81, "elapsed_time": "0:18:57", "remaining_time": "1:16:44"}
+{"current_steps": 90, "total_steps": 429, "loss": 1.0871, "learning_rate": 9.127167106960681e-07, "epoch": 0.6260869565217392, "percentage": 20.98, "elapsed_time": "0:20:00", "remaining_time": "1:15:20"}
+{"current_steps": 95, "total_steps": 429, "loss": 1.0791, "learning_rate": 9.018478899154066e-07, "epoch": 0.6608695652173913, "percentage": 22.14, "elapsed_time": "0:21:02", "remaining_time": "1:13:59"}
+{"current_steps": 100, "total_steps": 429, "loss": 1.0856, "learning_rate": 8.904143629616732e-07, "epoch": 0.6956521739130435, "percentage": 23.31, "elapsed_time": "0:22:05", "remaining_time": "1:12:40"}
+{"current_steps": 100, "total_steps": 429, "eval_loss": 1.074812412261963, "epoch": 0.6956521739130435, "percentage": 23.31, "elapsed_time": "0:23:16", "remaining_time": "1:16:33"}
+{"current_steps": 105, "total_steps": 429, "loss": 1.0638, "learning_rate": 8.784321970668053e-07, "epoch": 0.7304347826086957, "percentage": 24.48, "elapsed_time": "0:24:50", "remaining_time": "1:16:40"}
+{"current_steps": 110, "total_steps": 429, "loss": 1.0768, "learning_rate": 8.659182304504808e-07, "epoch": 0.7652173913043478, "percentage": 25.64, "elapsed_time": "0:25:53", "remaining_time": "1:15:04"}
+{"current_steps": 115, "total_steps": 429, "loss": 1.0838, "learning_rate": 8.528900486578158e-07, "epoch": 0.8, "percentage": 26.81, "elapsed_time": "0:26:55", "remaining_time": "1:13:29"}
+{"current_steps": 120, "total_steps": 429, "loss": 1.0633, "learning_rate": 8.393659598468642e-07, "epoch": 0.8347826086956521, "percentage": 27.97, "elapsed_time": "0:27:57", "remaining_time": "1:11:58"}
+{"current_steps": 125, "total_steps": 429, "loss": 1.0748, "learning_rate": 8.253649690606494e-07, "epoch": 0.8695652173913043, "percentage": 29.14, "elapsed_time": "0:28:59", "remaining_time": "1:10:30"}
+{"current_steps": 130, "total_steps": 429, "loss": 1.0623, "learning_rate": 8.10906751519882e-07, "epoch": 0.9043478260869565, "percentage": 30.3, "elapsed_time": "0:30:02", "remaining_time": "1:09:04"}
+{"current_steps": 135, "total_steps": 429, "loss": 1.0396, "learning_rate": 7.960116249738937e-07, "epoch": 0.9391304347826087, "percentage": 31.47, "elapsed_time": "0:31:05", "remaining_time": "1:07:41"}
+{"current_steps": 140, "total_steps": 429, "loss": 1.0662, "learning_rate": 7.807005211486444e-07, "epoch": 0.9739130434782609, "percentage": 32.63, "elapsed_time": "0:32:07", "remaining_time": "1:06:18"}
+{"current_steps": 145, "total_steps": 429, "loss": 1.0155, "learning_rate": 7.649949563319227e-07, "epoch": 1.008695652173913, "percentage": 33.8, "elapsed_time": "0:33:10", "remaining_time": "1:04:58"}
+{"current_steps": 150, "total_steps": 429, "loss": 0.9426, "learning_rate": 7.489170011370779e-07, "epoch": 1.0434782608695652, "percentage": 34.97, "elapsed_time": "0:34:12", "remaining_time": "1:03:37"}
+{"current_steps": 150, "total_steps": 429, "eval_loss": 1.0552960634231567, "epoch": 1.0434782608695652, "percentage": 34.97, "elapsed_time": "0:35:23", "remaining_time": "1:05:48"}
+{"current_steps": 155, "total_steps": 429, "loss": 0.9222, "learning_rate": 7.324892494877733e-07, "epoch": 1.0782608695652174, "percentage": 36.13, "elapsed_time": "0:36:25", "remaining_time": "1:04:22"}
+{"current_steps": 160, "total_steps": 429, "loss": 0.9223, "learning_rate": 7.15734786867344e-07, "epoch": 1.1130434782608696, "percentage": 37.3, "elapsed_time": "0:37:28", "remaining_time": "1:03:00"}
+{"current_steps": 165, "total_steps": 429, "loss": 0.937, "learning_rate": 6.986771578773811e-07, "epoch": 1.1478260869565218, "percentage": 38.46, "elapsed_time": "0:38:31", "remaining_time": "1:01:37"}
+{"current_steps": 170, "total_steps": 429, "loss": 0.9173, "learning_rate": 6.81340333151128e-07, "epoch": 1.182608695652174, "percentage": 39.63, "elapsed_time": "0:39:33", "remaining_time": "1:00:16"}
+{"current_steps": 175, "total_steps": 429, "loss": 0.9232, "learning_rate": 6.637486756681842e-07, "epoch": 1.2173913043478262, "percentage": 40.79, "elapsed_time": "0:40:36", "remaining_time": "0:58:56"}
+{"current_steps": 180, "total_steps": 429, "loss": 0.9146, "learning_rate": 6.459269065178591e-07, "epoch": 1.2521739130434781, "percentage": 41.96, "elapsed_time": "0:41:39", "remaining_time": "0:57:37"}
+{"current_steps": 185, "total_steps": 429, "loss": 0.919, "learning_rate": 6.279000701592794e-07, "epoch": 1.2869565217391306, "percentage": 43.12, "elapsed_time": "0:42:41", "remaining_time": "0:56:18"}
+{"current_steps": 190, "total_steps": 429, "loss": 0.9201, "learning_rate": 6.096934992270767e-07, "epoch": 1.3217391304347825, "percentage": 44.29, "elapsed_time": "0:43:44", "remaining_time": "0:55:00"}
+{"current_steps": 195, "total_steps": 429, "loss": 0.9151, "learning_rate": 5.913327789321077e-07, "epoch": 1.3565217391304347, "percentage": 45.45, "elapsed_time": "0:44:46", "remaining_time": "0:53:43"}
+{"current_steps": 200, "total_steps": 429, "loss": 0.9144, "learning_rate": 5.728437111072375e-07, "epoch": 1.391304347826087, "percentage": 46.62, "elapsed_time": "0:45:48", "remaining_time": "0:52:26"}
+{"current_steps": 200, "total_steps": 429, "eval_loss": 1.043231725692749, "epoch": 1.391304347826087, "percentage": 46.62, "elapsed_time": "0:46:59", "remaining_time": "0:53:47"}
+{"current_steps": 205, "total_steps": 429, "loss": 0.9173, "learning_rate": 5.542522779487071e-07, "epoch": 1.4260869565217391, "percentage": 47.79, "elapsed_time": "0:48:33", "remaining_time": "0:53:03"}
+{"current_steps": 210, "total_steps": 429, "loss": 0.9102, "learning_rate": 5.355846055040448e-07, "epoch": 1.4608695652173913, "percentage": 48.95, "elapsed_time": "0:49:36", "remaining_time": "0:51:43"}
+{"current_steps": 215, "total_steps": 429, "loss": 0.9199, "learning_rate": 5.168669269578232e-07, "epoch": 1.4956521739130435, "percentage": 50.12, "elapsed_time": "0:50:38", "remaining_time": "0:50:24"}
+{"current_steps": 220, "total_steps": 429, "loss": 0.9233, "learning_rate": 4.981255457668624e-07, "epoch": 1.5304347826086957, "percentage": 51.28, "elapsed_time": "0:51:40", "remaining_time": "0:49:05"}
+{"current_steps": 225, "total_steps": 429, "loss": 0.9091, "learning_rate": 4.793867986966802e-07, "epoch": 1.5652173913043477, "percentage": 52.45, "elapsed_time": "0:52:42", "remaining_time": "0:47:47"}
+{"current_steps": 230, "total_steps": 429, "loss": 0.8952, "learning_rate": 4.606770188111338e-07, "epoch": 1.6, "percentage": 53.61, "elapsed_time": "0:53:44", "remaining_time": "0:46:30"}
+{"current_steps": 235, "total_steps": 429, "loss": 0.9053, "learning_rate": 4.420224984672653e-07, "epoch": 1.634782608695652, "percentage": 54.78, "elapsed_time": "0:54:47", "remaining_time": "0:45:13"}
+{"current_steps": 240, "total_steps": 429, "loss": 0.9109, "learning_rate": 4.2344945236734963e-07, "epoch": 1.6695652173913045, "percentage": 55.94, "elapsed_time": "0:55:49", "remaining_time": "0:43:57"}
+{"current_steps": 245, "total_steps": 429, "loss": 0.9037, "learning_rate": 4.049839807200688e-07, "epoch": 1.7043478260869565, "percentage": 57.11, "elapsed_time": "0:56:51", "remaining_time": "0:42:42"}
+{"current_steps": 250, "total_steps": 429, "loss": 0.9069, "learning_rate": 3.866520325625825e-07, "epoch": 1.7391304347826086, "percentage": 58.28, "elapsed_time": "0:57:54", "remaining_time": "0:41:27"}
+{"current_steps": 250, "total_steps": 429, "eval_loss": 1.029205083847046, "epoch": 1.7391304347826086, "percentage": 58.28, "elapsed_time": "0:59:04", "remaining_time": "0:42:18"}
+{"current_steps": 255, "total_steps": 429, "loss": 0.879, "learning_rate": 3.684793692950344e-07, "epoch": 1.7739130434782608, "percentage": 59.44, "elapsed_time": "1:00:07", "remaining_time": "0:41:01"}
+{"current_steps": 260, "total_steps": 429, "loss": 0.8932, "learning_rate": 3.504915284787405e-07, "epoch": 1.808695652173913, "percentage": 60.61, "elapsed_time": "1:01:09", "remaining_time": "0:39:45"}
+{"current_steps": 265, "total_steps": 429, "loss": 0.894, "learning_rate": 3.327137879489312e-07, "epoch": 1.8434782608695652, "percentage": 61.77, "elapsed_time": "1:02:11", "remaining_time": "0:38:29"}
+{"current_steps": 270, "total_steps": 429, "loss": 0.9063, "learning_rate": 3.1517113029248233e-07, "epoch": 1.8782608695652174, "percentage": 62.94, "elapsed_time": "1:03:13", "remaining_time": "0:37:13"}
+{"current_steps": 275, "total_steps": 429, "loss": 0.8991, "learning_rate": 2.9788820774054697e-07, "epoch": 1.9130434782608696, "percentage": 64.1, "elapsed_time": "1:04:15", "remaining_time": "0:35:59"}
+{"current_steps": 280, "total_steps": 429, "loss": 0.8986, "learning_rate": 2.8088930752543063e-07, "epoch": 1.9478260869565216, "percentage": 65.27, "elapsed_time": "1:05:18", "remaining_time": "0:34:45"}
+{"current_steps": 285, "total_steps": 429, "loss": 0.8953, "learning_rate": 2.641983177503876e-07, "epoch": 1.982608695652174, "percentage": 66.43, "elapsed_time": "1:06:20", "remaining_time": "0:33:31"}
+{"current_steps": 290, "total_steps": 429, "loss": 0.8563, "learning_rate": 2.4783869382030424e-07, "epoch": 2.017391304347826, "percentage": 67.6, "elapsed_time": "1:07:22", "remaining_time": "0:32:17"}
+{"current_steps": 295, "total_steps": 429, "loss": 0.7987, "learning_rate": 2.3183342548044065e-07, "epoch": 2.0521739130434784, "percentage": 68.76, "elapsed_time": "1:08:25", "remaining_time": "0:31:05"}
+{"current_steps": 300, "total_steps": 429, "loss": 0.8152, "learning_rate": 2.1620500450955221e-07, "epoch": 2.0869565217391304, "percentage": 69.93, "elapsed_time": "1:09:28", "remaining_time": "0:29:52"}
+{"current_steps": 300, "total_steps": 429, "eval_loss": 1.039559245109558, "epoch": 2.0869565217391304, "percentage": 69.93, "elapsed_time": "1:10:38", "remaining_time": "0:30:22"}
+{"current_steps": 305, "total_steps": 429, "loss": 0.8055, "learning_rate": 2.0097539311278898e-07, "epoch": 2.121739130434783, "percentage": 71.1, "elapsed_time": "1:12:12", "remaining_time": "0:29:21"}
+{"current_steps": 310, "total_steps": 429, "loss": 0.8184, "learning_rate": 1.8616599305879333e-07, "epoch": 2.1565217391304348, "percentage": 72.26, "elapsed_time": "1:13:14", "remaining_time": "0:28:07"}
+{"current_steps": 315, "total_steps": 429, "loss": 0.8201, "learning_rate": 1.7179761560436097e-07, "epoch": 2.1913043478260867, "percentage": 73.43, "elapsed_time": "1:14:17", "remaining_time": "0:26:53"}
+{"current_steps": 320, "total_steps": 429, "loss": 0.8166, "learning_rate": 1.5789045224893538e-07, "epoch": 2.226086956521739, "percentage": 74.59, "elapsed_time": "1:15:19", "remaining_time": "0:25:39"}
+{"current_steps": 325, "total_steps": 429, "loss": 0.8265, "learning_rate": 1.444640463600293e-07, "epoch": 2.260869565217391, "percentage": 75.76, "elapsed_time": "1:16:22", "remaining_time": "0:24:26"}
+{"current_steps": 330, "total_steps": 429, "loss": 0.8008, "learning_rate": 1.3153726570944828e-07, "epoch": 2.2956521739130435, "percentage": 76.92, "elapsed_time": "1:17:24", "remaining_time": "0:23:13"}
+{"current_steps": 335, "total_steps": 429, "loss": 0.8131, "learning_rate": 1.1912827595891312e-07, "epoch": 2.3304347826086955, "percentage": 78.09, "elapsed_time": "1:18:27", "remaining_time": "0:22:00"}
+{"current_steps": 340, "total_steps": 429, "loss": 0.8219, "learning_rate": 1.0725451513233674e-07, "epoch": 2.365217391304348, "percentage": 79.25, "elapsed_time": "1:19:29", "remaining_time": "0:20:48"}
+{"current_steps": 345, "total_steps": 429, "loss": 0.8005, "learning_rate": 9.593266911063253e-08, "epoch": 2.4, "percentage": 80.42, "elapsed_time": "1:20:31", "remaining_time": "0:19:36"}
+{"current_steps": 350, "total_steps": 429, "loss": 0.8141, "learning_rate": 8.517864818348803e-08, "epoch": 2.4347826086956523, "percentage": 81.59, "elapsed_time": "1:21:33", "remaining_time": "0:18:24"}
+{"current_steps": 350, "total_steps": 429, "eval_loss": 1.0375770330429077, "epoch": 2.4347826086956523, "percentage": 81.59, "elapsed_time": "1:22:44", "remaining_time": "0:18:40"}
+{"current_steps": 355, "total_steps": 429, "loss": 0.8119, "learning_rate": 7.500756469105818e-08, "epoch": 2.4695652173913043, "percentage": 82.75, "elapsed_time": "1:23:46", "remaining_time": "0:17:27"}
+{"current_steps": 360, "total_steps": 429, "loss": 0.7997, "learning_rate": 6.543371178699442e-08, "epoch": 2.5043478260869563, "percentage": 83.92, "elapsed_time": "1:24:49", "remaining_time": "0:16:15"}
+{"current_steps": 365, "total_steps": 429, "loss": 0.8019, "learning_rate": 5.647054335265489e-08, "epoch": 2.5391304347826087, "percentage": 85.08, "elapsed_time": "1:25:51", "remaining_time": "0:15:03"}
+{"current_steps": 370, "total_steps": 429, "loss": 0.7917, "learning_rate": 4.813065509072278e-08, "epoch": 2.573913043478261, "percentage": 86.25, "elapsed_time": "1:26:53", "remaining_time": "0:13:51"}
+{"current_steps": 375, "total_steps": 429, "loss": 0.8107, "learning_rate": 4.0425766824798814e-08, "epoch": 2.608695652173913, "percentage": 87.41, "elapsed_time": "1:27:56", "remaining_time": "0:12:39"}
+{"current_steps": 380, "total_steps": 429, "loss": 0.8191, "learning_rate": 3.3366706029845096e-08, "epoch": 2.643478260869565, "percentage": 88.58, "elapsed_time": "1:28:58", "remaining_time": "0:11:28"}
+{"current_steps": 385, "total_steps": 429, "loss": 0.8074, "learning_rate": 2.696339261662156e-08, "epoch": 2.6782608695652175, "percentage": 89.74, "elapsed_time": "1:30:01", "remaining_time": "0:10:17"}
+{"current_steps": 390, "total_steps": 429, "loss": 0.802, "learning_rate": 2.122482499149869e-08, "epoch": 2.7130434782608694, "percentage": 90.91, "elapsed_time": "1:31:03", "remaining_time": "0:09:06"}
+{"current_steps": 395, "total_steps": 429, "loss": 0.7993, "learning_rate": 1.6159067411235737e-08, "epoch": 2.747826086956522, "percentage": 92.07, "elapsed_time": "1:32:05", "remaining_time": "0:07:55"}
+{"current_steps": 400, "total_steps": 429, "loss": 0.8097, "learning_rate": 1.177323865049512e-08, "epoch": 2.782608695652174, "percentage": 93.24, "elapsed_time": "1:33:07", "remaining_time": "0:06:45"}
+{"current_steps": 400, "total_steps": 429, "eval_loss": 1.0366120338439941, "epoch": 2.782608695652174, "percentage": 93.24, "elapsed_time": "1:34:18", "remaining_time": "0:06:50"}
+{"current_steps": 405, "total_steps": 429, "loss": 0.7976, "learning_rate": 8.073501998017152e-09, "epoch": 2.8173913043478263, "percentage": 94.41, "elapsed_time": "1:35:52", "remaining_time": "0:05:40"}
+{"current_steps": 410, "total_steps": 429, "loss": 0.8042, "learning_rate": 5.065056595513984e-09, "epoch": 2.8521739130434782, "percentage": 95.57, "elapsed_time": "1:36:55", "remaining_time": "0:04:29"}
+{"current_steps": 415, "total_steps": 429, "loss": 0.797, "learning_rate": 2.752130131453756e-09, "epoch": 2.8869565217391306, "percentage": 96.74, "elapsed_time": "1:37:57", "remaining_time": "0:03:18"}
+{"current_steps": 420, "total_steps": 429, "loss": 0.8181, "learning_rate": 1.137972900002171e-09, "epoch": 2.9217391304347826, "percentage": 97.9, "elapsed_time": "1:38:59", "remaining_time": "0:02:07"}
+{"current_steps": 425, "total_steps": 429, "loss": 0.8073, "learning_rate": 2.2485323347054552e-10, "epoch": 2.9565217391304346, "percentage": 99.07, "elapsed_time": "1:40:02", "remaining_time": "0:00:56"}
+{"current_steps": 429, "total_steps": 429, "epoch": 2.9843478260869567, "percentage": 100.0, "elapsed_time": "1:41:23", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,701 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9843478260869567,
+  "eval_steps": 50,
+  "global_step": 429,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.034782608695652174,
+      "grad_norm": 27.628698806495482,
+      "learning_rate": 5e-07,
+      "loss": 1.6404,
+      "step": 5
+    },
+    {
+      "epoch": 0.06956521739130435,
+      "grad_norm": 14.379307335524663,
+      "learning_rate": 1e-06,
+      "loss": 1.5079,
+      "step": 10
+    },
+    {
+      "epoch": 0.10434782608695652,
+      "grad_norm": 7.6171415097012805,
+      "learning_rate": 9.99648681635985e-07,
+      "loss": 1.2858,
+      "step": 15
+    },
+    {
+      "epoch": 0.1391304347826087,
+      "grad_norm": 5.902380140367801,
+      "learning_rate": 9.985952202423114e-07,
+      "loss": 1.2292,
+      "step": 20
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 5.431235666701782,
+      "learning_rate": 9.96841096220313e-07,
+      "loss": 1.2035,
+      "step": 25
+    },
+    {
+      "epoch": 0.20869565217391303,
+      "grad_norm": 5.011022329519287,
+      "learning_rate": 9.943887745939163e-07,
+      "loss": 1.1615,
+      "step": 30
+    },
+    {
+      "epoch": 0.24347826086956523,
+      "grad_norm": 4.933604072753844,
+      "learning_rate": 9.912417015456088e-07,
+      "loss": 1.1627,
+      "step": 35
+    },
+    {
+      "epoch": 0.2782608695652174,
+      "grad_norm": 4.904429773196176,
+      "learning_rate": 9.874042995736093e-07,
+      "loss": 1.1468,
+      "step": 40
+    },
+    {
+      "epoch": 0.3130434782608696,
+      "grad_norm": 4.566916992899494,
+      "learning_rate": 9.828819612770495e-07,
+      "loss": 1.1457,
+      "step": 45
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 4.618513047328418,
+      "learning_rate": 9.77681041777897e-07,
+      "loss": 1.1363,
+      "step": 50
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "eval_loss": 1.1214656829833984,
+      "eval_runtime": 71.1557,
+      "eval_samples_per_second": 57.423,
+      "eval_steps_per_second": 0.899,
+      "step": 50
+    },
+    {
+      "epoch": 0.3826086956521739,
+      "grad_norm": 4.482447125747761,
+      "learning_rate": 9.718088497902707e-07,
+      "loss": 1.1252,
+      "step": 55
+    },
+    {
+      "epoch": 0.41739130434782606,
+      "grad_norm": 4.746315495183657,
+      "learning_rate": 9.652736373497e-07,
+      "loss": 1.1144,
+      "step": 60
+    },
+    {
+      "epoch": 0.45217391304347826,
+      "grad_norm": 4.800644875448408,
+      "learning_rate": 9.580845882167572e-07,
+      "loss": 1.1048,
+      "step": 65
+    },
+    {
+      "epoch": 0.48695652173913045,
+      "grad_norm": 5.041563912063608,
+      "learning_rate": 9.502518049713631e-07,
+      "loss": 1.0967,
+      "step": 70
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 4.834159384378619,
+      "learning_rate": 9.417862948158997e-07,
+      "loss": 1.0922,
+      "step": 75
+    },
+    {
+      "epoch": 0.5565217391304348,
+      "grad_norm": 4.966276459660724,
+      "learning_rate": 9.326999541070803e-07,
+      "loss": 1.1065,
+      "step": 80
+    },
+    {
+      "epoch": 0.591304347826087,
+      "grad_norm": 4.651039844387456,
+      "learning_rate": 9.23005551638316e-07,
+      "loss": 1.08,
+      "step": 85
+    },
+    {
+      "epoch": 0.6260869565217392,
+      "grad_norm": 4.61712494812361,
+      "learning_rate": 9.127167106960681e-07,
+      "loss": 1.0871,
+      "step": 90
+    },
+    {
+      "epoch": 0.6608695652173913,
+      "grad_norm": 4.965649778107791,
+      "learning_rate": 9.018478899154066e-07,
+      "loss": 1.0791,
+      "step": 95
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 4.710879346221803,
+      "learning_rate": 8.904143629616732e-07,
+      "loss": 1.0856,
+      "step": 100
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "eval_loss": 1.074812412261963,
+      "eval_runtime": 70.7335,
+      "eval_samples_per_second": 57.766,
+      "eval_steps_per_second": 0.905,
+      "step": 100
+    },
+    {
+      "epoch": 0.7304347826086957,
+      "grad_norm": 4.887377540999055,
+      "learning_rate": 8.784321970668053e-07,
+      "loss": 1.0638,
+      "step": 105
+    },
+    {
+      "epoch": 0.7652173913043478,
+      "grad_norm": 4.804331292468611,
+      "learning_rate": 8.659182304504808e-07,
+      "loss": 1.0768,
+      "step": 110
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.78084183802074,
+      "learning_rate": 8.528900486578158e-07,
+      "loss": 1.0838,
+      "step": 115
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "grad_norm": 5.189973322685715,
+      "learning_rate": 8.393659598468642e-07,
+      "loss": 1.0633,
+      "step": 120
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 5.02605525534553,
+      "learning_rate": 8.253649690606494e-07,
+      "loss": 1.0748,
+      "step": 125
+    },
+    {
+      "epoch": 0.9043478260869565,
+      "grad_norm": 5.433069400847481,
+      "learning_rate": 8.10906751519882e-07,
+      "loss": 1.0623,
+      "step": 130
+    },
+    {
+      "epoch": 0.9391304347826087,
+      "grad_norm": 4.770051175238624,
+      "learning_rate": 7.960116249738937e-07,
+      "loss": 1.0396,
+      "step": 135
+    },
+    {
+      "epoch": 0.9739130434782609,
+      "grad_norm": 4.606677098055935,
+      "learning_rate": 7.807005211486444e-07,
+      "loss": 1.0662,
+      "step": 140
+    },
+    {
+      "epoch": 1.008695652173913,
+      "grad_norm": 5.498117473835195,
+      "learning_rate": 7.649949563319227e-07,
+      "loss": 1.0155,
+      "step": 145
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "grad_norm": 4.9633963344101595,
+      "learning_rate": 7.489170011370779e-07,
+      "loss": 0.9426,
+      "step": 150
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "eval_loss": 1.0552960634231567,
+      "eval_runtime": 70.6918,
+      "eval_samples_per_second": 57.8,
+      "eval_steps_per_second": 0.905,
+      "step": 150
+    },
+    {
+      "epoch": 1.0782608695652174,
+      "grad_norm": 5.4731038473793285,
+      "learning_rate": 7.324892494877733e-07,
+      "loss": 0.9222,
+      "step": 155
+    },
+    {
+      "epoch": 1.1130434782608696,
+      "grad_norm": 5.024873028080845,
+      "learning_rate": 7.15734786867344e-07,
+      "loss": 0.9223,
+      "step": 160
+    },
+    {
+      "epoch": 1.1478260869565218,
+      "grad_norm": 5.363614939434412,
+      "learning_rate": 6.986771578773811e-07,
+      "loss": 0.937,
+      "step": 165
+    },
+    {
+      "epoch": 1.182608695652174,
+      "grad_norm": 5.175874733453326,
+      "learning_rate": 6.81340333151128e-07,
+      "loss": 0.9173,
+      "step": 170
+    },
+    {
+      "epoch": 1.2173913043478262,
+      "grad_norm": 5.446257822096013,
+      "learning_rate": 6.637486756681842e-07,
+      "loss": 0.9232,
+      "step": 175
+    },
+    {
+      "epoch": 1.2521739130434781,
+      "grad_norm": 5.0358352027359174,
+      "learning_rate": 6.459269065178591e-07,
+      "loss": 0.9146,
+      "step": 180
+    },
+    {
+      "epoch": 1.2869565217391306,
+      "grad_norm": 5.287700886552525,
+      "learning_rate": 6.279000701592794e-07,
+      "loss": 0.919,
+      "step": 185
+    },
+    {
+      "epoch": 1.3217391304347825,
+      "grad_norm": 5.280625369358825,
+      "learning_rate": 6.096934992270767e-07,
+      "loss": 0.9201,
+      "step": 190
+    },
+    {
+      "epoch": 1.3565217391304347,
+      "grad_norm": 5.218195920942847,
+      "learning_rate": 5.913327789321077e-07,
+      "loss": 0.9151,
+      "step": 195
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 5.2780690080724515,
+      "learning_rate": 5.728437111072375e-07,
+      "loss": 0.9144,
+      "step": 200
+    },
+    {
+      "epoch": 1.391304347826087,
+      "eval_loss": 1.043231725692749,
+      "eval_runtime": 70.6101,
+      "eval_samples_per_second": 57.867,
+      "eval_steps_per_second": 0.906,
+      "step": 200
+    },
+    {
+      "epoch": 1.4260869565217391,
+      "grad_norm": 5.5857239509669965,
+      "learning_rate": 5.542522779487071e-07,
+      "loss": 0.9173,
+      "step": 205
+    },
+    {
+      "epoch": 1.4608695652173913,
+      "grad_norm": 5.283495401802204,
+      "learning_rate": 5.355846055040448e-07,
+      "loss": 0.9102,
+      "step": 210
+    },
+    {
+      "epoch": 1.4956521739130435,
+      "grad_norm": 5.21771322708205,
+      "learning_rate": 5.168669269578232e-07,
+      "loss": 0.9199,
+      "step": 215
+    },
+    {
+      "epoch": 1.5304347826086957,
+      "grad_norm": 5.2351062433238935,
+      "learning_rate": 4.981255457668624e-07,
+      "loss": 0.9233,
+      "step": 220
+    },
+    {
+      "epoch": 1.5652173913043477,
+      "grad_norm": 5.815315560161152,
+      "learning_rate": 4.793867986966802e-07,
+      "loss": 0.9091,
+      "step": 225
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.43656366363975,
+      "learning_rate": 4.606770188111338e-07,
+      "loss": 0.8952,
+      "step": 230
+    },
+    {
+      "epoch": 1.634782608695652,
+      "grad_norm": 5.330638617903944,
+      "learning_rate": 4.420224984672653e-07,
+      "loss": 0.9053,
+      "step": 235
+    },
+    {
+      "epoch": 1.6695652173913045,
+      "grad_norm": 5.555943570818251,
+      "learning_rate": 4.2344945236734963e-07,
+      "loss": 0.9109,
+      "step": 240
+    },
+    {
+      "epoch": 1.7043478260869565,
+      "grad_norm": 5.513097486509469,
+      "learning_rate": 4.049839807200688e-07,
+      "loss": 0.9037,
+      "step": 245
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 5.47180452288034,
+      "learning_rate": 3.866520325625825e-07,
+      "loss": 0.9069,
+      "step": 250
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "eval_loss": 1.029205083847046,
+      "eval_runtime": 70.7173,
+      "eval_samples_per_second": 57.779,
+      "eval_steps_per_second": 0.905,
+      "step": 250
+    },
+    {
+      "epoch": 1.7739130434782608,
+      "grad_norm": 5.680893425776684,
+      "learning_rate": 3.684793692950344e-07,
+      "loss": 0.879,
+      "step": 255
+    },
+    {
+      "epoch": 1.808695652173913,
+      "grad_norm": 5.872951088572936,
+      "learning_rate": 3.504915284787405e-07,
+      "loss": 0.8932,
+      "step": 260
+    },
+    {
+      "epoch": 1.8434782608695652,
+      "grad_norm": 5.990419512227443,
+      "learning_rate": 3.327137879489312e-07,
+      "loss": 0.894,
+      "step": 265
+    },
+    {
+      "epoch": 1.8782608695652174,
+      "grad_norm": 5.373969959306303,
+      "learning_rate": 3.1517113029248233e-07,
+      "loss": 0.9063,
+      "step": 270
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 5.306825054838355,
+      "learning_rate": 2.9788820774054697e-07,
+      "loss": 0.8991,
+      "step": 275
+    },
+    {
+      "epoch": 1.9478260869565216,
+      "grad_norm": 5.452637165713125,
+      "learning_rate": 2.8088930752543063e-07,
+      "loss": 0.8986,
+      "step": 280
+    },
+    {
+      "epoch": 1.982608695652174,
+      "grad_norm": 5.460619773030644,
+      "learning_rate": 2.641983177503876e-07,
+      "loss": 0.8953,
+      "step": 285
+    },
+    {
+      "epoch": 2.017391304347826,
+      "grad_norm": 6.270694873773961,
+      "learning_rate": 2.4783869382030424e-07,
+      "loss": 0.8563,
+      "step": 290
+    },
+    {
+      "epoch": 2.0521739130434784,
+      "grad_norm": 5.795044001331771,
+      "learning_rate": 2.3183342548044065e-07,
+      "loss": 0.7987,
+      "step": 295
+    },
+    {
+      "epoch": 2.0869565217391304,
+      "grad_norm": 6.0960236861916055,
+      "learning_rate": 2.1620500450955221e-07,
+      "loss": 0.8152,
+      "step": 300
+    },
+    {
+      "epoch": 2.0869565217391304,
+      "eval_loss": 1.039559245109558,
+      "eval_runtime": 70.7734,
+      "eval_samples_per_second": 57.734,
+      "eval_steps_per_second": 0.904,
+      "step": 300
+    },
+    {
+      "epoch": 2.121739130434783,
+      "grad_norm": 5.769696534143466,
+      "learning_rate": 2.0097539311278898e-07,
+      "loss": 0.8055,
+      "step": 305
+    },
+    {
+      "epoch": 2.1565217391304348,
+      "grad_norm": 6.054826333866415,
+      "learning_rate": 1.8616599305879333e-07,
+      "loss": 0.8184,
+      "step": 310
+    },
+    {
+      "epoch": 2.1913043478260867,
+      "grad_norm": 5.8177110155805405,
+      "learning_rate": 1.7179761560436097e-07,
+      "loss": 0.8201,
+      "step": 315
+    },
+    {
+      "epoch": 2.226086956521739,
+      "grad_norm": 5.966607504919806,
+      "learning_rate": 1.5789045224893538e-07,
+      "loss": 0.8166,
+      "step": 320
+    },
+    {
+      "epoch": 2.260869565217391,
+      "grad_norm": 5.59992033676923,
+      "learning_rate": 1.444640463600293e-07,
+      "loss": 0.8265,
+      "step": 325
+    },
+    {
+      "epoch": 2.2956521739130435,
+      "grad_norm": 5.804095502408287,
+      "learning_rate": 1.3153726570944828e-07,
+      "loss": 0.8008,
+      "step": 330
+    },
+    {
+      "epoch": 2.3304347826086955,
+      "grad_norm": 5.39590256328954,
+      "learning_rate": 1.1912827595891312e-07,
+      "loss": 0.8131,
+      "step": 335
+    },
+    {
+      "epoch": 2.365217391304348,
+      "grad_norm": 5.653819193920734,
+      "learning_rate": 1.0725451513233674e-07,
+      "loss": 0.8219,
+      "step": 340
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 5.716140358883574,
+      "learning_rate": 9.593266911063253e-08,
+      "loss": 0.8005,
+      "step": 345
+    },
+    {
+      "epoch": 2.4347826086956523,
+      "grad_norm": 6.028759811444573,
+      "learning_rate": 8.517864818348803e-08,
+      "loss": 0.8141,
+      "step": 350
+    },
+    {
+      "epoch": 2.4347826086956523,
+      "eval_loss": 1.0375770330429077,
+      "eval_runtime": 70.8262,
+      "eval_samples_per_second": 57.691,
+      "eval_steps_per_second": 0.904,
+      "step": 350
+    },
+    {
+      "epoch": 2.4695652173913043,
+      "grad_norm": 5.635963856252332,
+      "learning_rate": 7.500756469105818e-08,
+      "loss": 0.8119,
+      "step": 355
+    },
+    {
+      "epoch": 2.5043478260869563,
+      "grad_norm": 6.062141717487416,
+      "learning_rate": 6.543371178699442e-08,
+      "loss": 0.7997,
+      "step": 360
+    },
+    {
+      "epoch": 2.5391304347826087,
+      "grad_norm": 5.747247864530177,
+      "learning_rate": 5.647054335265489e-08,
+      "loss": 0.8019,
+      "step": 365
+    },
+    {
+      "epoch": 2.573913043478261,
+      "grad_norm": 5.7882061983533415,
+      "learning_rate": 4.813065509072278e-08,
+      "loss": 0.7917,
+      "step": 370
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 5.960090404893479,
+      "learning_rate": 4.0425766824798814e-08,
+      "loss": 0.8107,
+      "step": 375
+    },
+    {
+      "epoch": 2.643478260869565,
+      "grad_norm": 6.220656601688518,
+      "learning_rate": 3.3366706029845096e-08,
+      "loss": 0.8191,
+      "step": 380
+    },
+    {
+      "epoch": 2.6782608695652175,
+      "grad_norm": 5.532579400575541,
+      "learning_rate": 2.696339261662156e-08,
+      "loss": 0.8074,
+      "step": 385
+    },
+    {
+      "epoch": 2.7130434782608694,
+      "grad_norm": 5.970542774366677,
+      "learning_rate": 2.122482499149869e-08,
+      "loss": 0.802,
+      "step": 390
+    },
+    {
+      "epoch": 2.747826086956522,
+      "grad_norm": 5.973565867263469,
+      "learning_rate": 1.6159067411235737e-08,
+      "loss": 0.7993,
+      "step": 395
+    },
+    {
+      "epoch": 2.782608695652174,
+      "grad_norm": 5.77223311406108,
+      "learning_rate": 1.177323865049512e-08,
+      "loss": 0.8097,
+      "step": 400
+    },
+    {
+      "epoch": 2.782608695652174,
+      "eval_loss": 1.0366120338439941,
+      "eval_runtime": 70.731,
+      "eval_samples_per_second": 57.768,
+      "eval_steps_per_second": 0.905,
+      "step": 400
+    },
+    {
+      "epoch": 2.8173913043478263,
+      "grad_norm": 5.721453785688962,
+      "learning_rate": 8.073501998017152e-09,
+      "loss": 0.7976,
+      "step": 405
+    },
+    {
+      "epoch": 2.8521739130434782,
+      "grad_norm": 5.82427897146351,
+      "learning_rate": 5.065056595513984e-09,
+      "loss": 0.8042,
+      "step": 410
+    },
+    {
+      "epoch": 2.8869565217391306,
+      "grad_norm": 6.051738285563,
+      "learning_rate": 2.752130131453756e-09,
+      "loss": 0.797,
+      "step": 415
+    },
+    {
+      "epoch": 2.9217391304347826,
+      "grad_norm": 6.0320734666727045,
+      "learning_rate": 1.137972900002171e-09,
+      "loss": 0.8181,
+      "step": 420
+    },
+    {
+      "epoch": 2.9565217391304346,
+      "grad_norm": 5.640940082183562,
+      "learning_rate": 2.2485323347054552e-10,
+      "loss": 0.8073,
+      "step": 425
+    },
+    {
+      "epoch": 2.9843478260869567,
+      "step": 429,
+      "total_flos": 2529344492666880.0,
+      "train_loss": 0.9555719093287186,
+      "train_runtime": 6085.5766,
+      "train_samples_per_second": 18.127,
+      "train_steps_per_second": 0.07
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 429,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2529344492666880.0,
+  "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 sha256:2545191f9a656e1efc4fd4ad67d0eb10f53ea6828b9fbeb51a0048cba47ff04b
+size 7096