Upload folder using huggingface_hub

README.md

@@ -0,0 +1,77 @@
+---
+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: AA_preference_cosi_0_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. -->
+
+# AA_preference_cosi_0_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 AA_preference_cosi_0_50 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5580
+- Rewards/chosen: 1.1191
+- Rewards/rejected: -1.7161
+- Rewards/accuracies: 0.8125
+- Rewards/margins: 2.8352
+- Logps/rejected: -229.3270
+- Logps/chosen: -253.4991
+- Logits/rejected: -2.2872
+- Logits/chosen: -2.3146
+
+## 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 | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5248        | 0.7463 | 50   | 0.5636          | 0.7981         | -0.7376          | 0.7625             | 1.5357          | -219.5417      | -256.7093    | -2.1893         | -2.2123       |
+| 0.2521        | 1.4925 | 100  | 0.5887          | 1.3477         | -1.2511          | 0.8042             | 2.5988          | -224.6767      | -251.2128    | -2.3607         | -2.3766       |
+| 0.1273        | 2.2388 | 150  | 0.5529          | 1.1944         | -1.5829          | 0.8250             | 2.7773          | -227.9948      | -252.7459    | -2.2852         | -2.3106       |
+| 0.1289        | 2.9851 | 200  | 0.5586          | 1.1189         | -1.7195          | 0.8125             | 2.8384          | -229.3605      | -253.5011    | -2.2866         | -2.3140       |
+
+
+### 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 +1,20 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -2.3145642280578613,
+    "eval_logits/rejected": -2.2872278690338135,
+    "eval_logps/chosen": -253.4990997314453,
+    "eval_logps/rejected": -229.3269500732422,
+    "eval_loss": 0.5580384731292725,
+    "eval_rewards/accuracies": 0.8125,
+    "eval_rewards/chosen": 1.1190966367721558,
+    "eval_rewards/margins": 2.8352162837982178,
+    "eval_rewards/rejected": -1.716119647026062,
+    "eval_runtime": 124.3079,
+    "eval_samples_per_second": 15.285,
+    "eval_steps_per_second": 0.241,
+    "total_flos": 2369906314051584.0,
+    "train_loss": 0.3258563337560317,
+    "train_runtime": 7340.6492,
+    "train_samples_per_second": 6.986,
+    "train_steps_per_second": 0.027
+}

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 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -2.3145642280578613,
+    "eval_logits/rejected": -2.2872278690338135,
+    "eval_logps/chosen": -253.4990997314453,
+    "eval_logps/rejected": -229.3269500732422,
+    "eval_loss": 0.5580384731292725,
+    "eval_rewards/accuracies": 0.8125,
+    "eval_rewards/chosen": 1.1190966367721558,
+    "eval_rewards/margins": 2.8352162837982178,
+    "eval_rewards/rejected": -1.716119647026062,
+    "eval_runtime": 124.3079,
+    "eval_samples_per_second": 15.285,
+    "eval_steps_per_second": 0.241
+}

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 sha256:008fc8ab93e47fe13973d2ccd52eff3a040a2d61a14f6c1194b325029f9ec98e
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a75a1448a39452a2865a7e549a79dd3108ac6d508957125ecd2b787136f1ae61
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65136771f63657fbb61de37f34b8c4a3cc3d4977c4d0856a507b0ac614d8cd58
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05fb4477e50014e7e3353e5f7d0ec1fd468527da6468820395d409cc6a213b7
+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": 3.0,
+    "total_flos": 2369906314051584.0,
+    "train_loss": 0.3258563337560317,
+    "train_runtime": 7340.6492,
+    "train_samples_per_second": 6.986,
+    "train_steps_per_second": 0.027
+}

trainer_log.jsonl

@@ -0,0 +1,45 @@
+{"current_steps": 5, "total_steps": 201, "loss": 0.6899, "accuracy": 0.32499998807907104, "learning_rate": 5e-07, "epoch": 0.07462686567164178, "percentage": 2.49, "elapsed_time": "0:02:52", "remaining_time": "1:52:49"}
+{"current_steps": 10, "total_steps": 201, "loss": 0.6424, "accuracy": 0.675000011920929, "learning_rate": 1e-06, "epoch": 0.14925373134328357, "percentage": 4.98, "elapsed_time": "0:05:39", "remaining_time": "1:48:03"}
+{"current_steps": 15, "total_steps": 201, "loss": 0.6323, "accuracy": 0.6625000238418579, "learning_rate": 9.983100718730718e-07, "epoch": 0.22388059701492538, "percentage": 7.46, "elapsed_time": "0:08:27", "remaining_time": "1:44:55"}
+{"current_steps": 20, "total_steps": 201, "loss": 0.5745, "accuracy": 0.7124999761581421, "learning_rate": 9.932517109205849e-07, "epoch": 0.29850746268656714, "percentage": 9.95, "elapsed_time": "0:11:14", "remaining_time": "1:41:48"}
+{"current_steps": 25, "total_steps": 201, "loss": 0.5856, "accuracy": 0.6937500238418579, "learning_rate": 9.848591102083375e-07, "epoch": 0.373134328358209, "percentage": 12.44, "elapsed_time": "0:14:03", "remaining_time": "1:38:55"}
+{"current_steps": 30, "total_steps": 201, "loss": 0.5741, "accuracy": 0.7437499761581421, "learning_rate": 9.731890013043367e-07, "epoch": 0.44776119402985076, "percentage": 14.93, "elapsed_time": "0:16:49", "remaining_time": "1:35:56"}
+{"current_steps": 35, "total_steps": 201, "loss": 0.557, "accuracy": 0.7749999761581421, "learning_rate": 9.583202707897073e-07, "epoch": 0.5223880597014925, "percentage": 17.41, "elapsed_time": "0:19:37", "remaining_time": "1:33:06"}
+{"current_steps": 40, "total_steps": 201, "loss": 0.5337, "accuracy": 0.668749988079071, "learning_rate": 9.403534270080829e-07, "epoch": 0.5970149253731343, "percentage": 19.9, "elapsed_time": "0:22:27", "remaining_time": "1:30:22"}
+{"current_steps": 45, "total_steps": 201, "loss": 0.56, "accuracy": 0.7124999761581421, "learning_rate": 9.19409920658098e-07, "epoch": 0.6716417910447762, "percentage": 22.39, "elapsed_time": "0:25:15", "remaining_time": "1:27:33"}
+{"current_steps": 50, "total_steps": 201, "loss": 0.5248, "accuracy": 0.7437499761581421, "learning_rate": 8.956313238215823e-07, "epoch": 0.746268656716418, "percentage": 24.88, "elapsed_time": "0:28:03", "remaining_time": "1:24:45"}
+{"current_steps": 50, "total_steps": 201, "eval_loss": 0.5635779500007629, "epoch": 0.746268656716418, "percentage": 24.88, "elapsed_time": "0:30:10", "remaining_time": "1:31:07"}
+{"current_steps": 55, "total_steps": 201, "loss": 0.5358, "accuracy": 0.800000011920929, "learning_rate": 8.691783729769873e-07, "epoch": 0.8208955223880597, "percentage": 27.36, "elapsed_time": "0:32:58", "remaining_time": "1:27:31"}
+{"current_steps": 60, "total_steps": 201, "loss": 0.5812, "accuracy": 0.7124999761581421, "learning_rate": 8.402298824670029e-07, "epoch": 0.8955223880597015, "percentage": 29.85, "elapsed_time": "0:35:46", "remaining_time": "1:24:03"}
+{"current_steps": 65, "total_steps": 201, "loss": 0.5166, "accuracy": 0.768750011920929, "learning_rate": 8.089815357650089e-07, "epoch": 0.9701492537313433, "percentage": 32.34, "elapsed_time": "0:38:34", "remaining_time": "1:20:43"}
+{"current_steps": 70, "total_steps": 201, "loss": 0.3443, "accuracy": 0.862500011920929, "learning_rate": 7.756445627110522e-07, "epoch": 1.044776119402985, "percentage": 34.83, "elapsed_time": "0:41:21", "remaining_time": "1:17:23"}
+{"current_steps": 75, "total_steps": 201, "loss": 0.228, "accuracy": 0.918749988079071, "learning_rate": 7.404443116588547e-07, "epoch": 1.1194029850746268, "percentage": 37.31, "elapsed_time": "0:44:08", "remaining_time": "1:14:09"}
+{"current_steps": 80, "total_steps": 201, "loss": 0.2314, "accuracy": 0.925000011920929, "learning_rate": 7.036187261857288e-07, "epoch": 1.1940298507462686, "percentage": 39.8, "elapsed_time": "0:46:56", "remaining_time": "1:10:59"}
+{"current_steps": 85, "total_steps": 201, "loss": 0.2303, "accuracy": 0.9437500238418579, "learning_rate": 6.654167366624008e-07, "epoch": 1.2686567164179103, "percentage": 42.29, "elapsed_time": "0:49:44", "remaining_time": "1:07:52"}
+{"current_steps": 90, "total_steps": 201, "loss": 0.256, "accuracy": 0.925000011920929, "learning_rate": 6.260965775552713e-07, "epoch": 1.3432835820895521, "percentage": 44.78, "elapsed_time": "0:52:32", "remaining_time": "1:04:48"}
+{"current_steps": 95, "total_steps": 201, "loss": 0.2499, "accuracy": 0.918749988079071, "learning_rate": 5.859240418356614e-07, "epoch": 1.417910447761194, "percentage": 47.26, "elapsed_time": "0:55:20", "remaining_time": "1:01:44"}
+{"current_steps": 100, "total_steps": 201, "loss": 0.2521, "accuracy": 0.918749988079071, "learning_rate": 5.451706842957421e-07, "epoch": 1.4925373134328357, "percentage": 49.75, "elapsed_time": "0:58:07", "remaining_time": "0:58:42"}
+{"current_steps": 100, "total_steps": 201, "eval_loss": 0.588749885559082, "epoch": 1.4925373134328357, "percentage": 49.75, "elapsed_time": "1:00:12", "remaining_time": "1:00:48"}
+{"current_steps": 105, "total_steps": 201, "loss": 0.3064, "accuracy": 0.9125000238418579, "learning_rate": 5.041119859162068e-07, "epoch": 1.5671641791044775, "percentage": 52.24, "elapsed_time": "1:03:32", "remaining_time": "0:58:05"}
+{"current_steps": 110, "total_steps": 201, "loss": 0.2489, "accuracy": 0.9312499761581421, "learning_rate": 4.630254916940423e-07, "epoch": 1.6417910447761193, "percentage": 54.73, "elapsed_time": "1:06:18", "remaining_time": "0:54:51"}
+{"current_steps": 115, "total_steps": 201, "loss": 0.2599, "accuracy": 0.887499988079071, "learning_rate": 4.2218893451814e-07, "epoch": 1.716417910447761, "percentage": 57.21, "elapsed_time": "1:09:06", "remaining_time": "0:51:40"}
+{"current_steps": 120, "total_steps": 201, "loss": 0.2738, "accuracy": 0.9312499761581421, "learning_rate": 3.8187835777481375e-07, "epoch": 1.7910447761194028, "percentage": 59.7, "elapsed_time": "1:11:53", "remaining_time": "0:48:31"}
+{"current_steps": 125, "total_steps": 201, "loss": 0.2635, "accuracy": 0.9125000238418579, "learning_rate": 3.423662493738687e-07, "epoch": 1.8656716417910446, "percentage": 62.19, "elapsed_time": "1:14:41", "remaining_time": "0:45:24"}
+{"current_steps": 130, "total_steps": 201, "loss": 0.278, "accuracy": 0.925000011920929, "learning_rate": 3.039196998086687e-07, "epoch": 1.9402985074626866, "percentage": 64.68, "elapsed_time": "1:17:28", "remaining_time": "0:42:18"}
+{"current_steps": 135, "total_steps": 201, "loss": 0.2614, "accuracy": 0.9125000238418579, "learning_rate": 2.667985967011878e-07, "epoch": 2.014925373134328, "percentage": 67.16, "elapsed_time": "1:20:16", "remaining_time": "0:39:14"}
+{"current_steps": 140, "total_steps": 201, "loss": 0.1341, "accuracy": 0.9437500238418579, "learning_rate": 2.3125386803640183e-07, "epoch": 2.08955223880597, "percentage": 69.65, "elapsed_time": "1:23:03", "remaining_time": "0:36:11"}
+{"current_steps": 145, "total_steps": 201, "loss": 0.1518, "accuracy": 0.9375, "learning_rate": 1.9752578596124952e-07, "epoch": 2.1641791044776117, "percentage": 72.14, "elapsed_time": "1:25:51", "remaining_time": "0:33:09"}
+{"current_steps": 150, "total_steps": 201, "loss": 0.1273, "accuracy": 0.956250011920929, "learning_rate": 1.6584234261399532e-07, "epoch": 2.2388059701492535, "percentage": 74.63, "elapsed_time": "1:28:38", "remaining_time": "0:30:08"}
+{"current_steps": 150, "total_steps": 201, "eval_loss": 0.5529021620750427, "epoch": 2.2388059701492535, "percentage": 74.63, "elapsed_time": "1:30:43", "remaining_time": "0:30:50"}
+{"current_steps": 155, "total_steps": 201, "loss": 0.1588, "accuracy": 0.9750000238418579, "learning_rate": 1.3641770896292082e-07, "epoch": 2.3134328358208958, "percentage": 77.11, "elapsed_time": "1:33:31", "remaining_time": "0:27:45"}
+{"current_steps": 160, "total_steps": 201, "loss": 0.1638, "accuracy": 0.925000011920929, "learning_rate": 1.0945078707215221e-07, "epoch": 2.388059701492537, "percentage": 79.6, "elapsed_time": "1:36:18", "remaining_time": "0:24:40"}
+{"current_steps": 165, "total_steps": 201, "loss": 0.1669, "accuracy": 0.918749988079071, "learning_rate": 8.512386558088919e-08, "epoch": 2.4626865671641793, "percentage": 82.09, "elapsed_time": "1:39:05", "remaining_time": "0:21:37"}
+{"current_steps": 170, "total_steps": 201, "loss": 0.1735, "accuracy": 0.949999988079071, "learning_rate": 6.360138748461013e-08, "epoch": 2.5373134328358207, "percentage": 84.58, "elapsed_time": "1:41:52", "remaining_time": "0:18:34"}
+{"current_steps": 175, "total_steps": 201, "loss": 0.1397, "accuracy": 0.9375, "learning_rate": 4.5028838547699346e-08, "epoch": 2.611940298507463, "percentage": 87.06, "elapsed_time": "1:44:40", "remaining_time": "0:15:33"}
+{"current_steps": 180, "total_steps": 201, "loss": 0.1557, "accuracy": 0.956250011920929, "learning_rate": 2.9531763861505964e-08, "epoch": 2.6865671641791042, "percentage": 89.55, "elapsed_time": "1:47:27", "remaining_time": "0:12:32"}
+{"current_steps": 185, "total_steps": 201, "loss": 0.1517, "accuracy": 0.9624999761581421, "learning_rate": 1.7214919195619125e-08, "epoch": 2.7611940298507465, "percentage": 92.04, "elapsed_time": "1:50:14", "remaining_time": "0:09:32"}
+{"current_steps": 190, "total_steps": 201, "loss": 0.1267, "accuracy": 0.96875, "learning_rate": 8.161562878982398e-09, "epoch": 2.835820895522388, "percentage": 94.53, "elapsed_time": "1:53:02", "remaining_time": "0:06:32"}
+{"current_steps": 195, "total_steps": 201, "loss": 0.1148, "accuracy": 0.9375, "learning_rate": 2.432892997526026e-09, "epoch": 2.91044776119403, "percentage": 97.01, "elapsed_time": "1:55:49", "remaining_time": "0:03:33"}
+{"current_steps": 200, "total_steps": 201, "loss": 0.1289, "accuracy": 0.949999988079071, "learning_rate": 6.763371270035457e-11, "epoch": 2.9850746268656714, "percentage": 99.5, "elapsed_time": "1:58:37", "remaining_time": "0:00:35"}
+{"current_steps": 200, "total_steps": 201, "eval_loss": 0.5585500001907349, "epoch": 2.9850746268656714, "percentage": 99.5, "elapsed_time": "2:00:43", "remaining_time": "0:00:36"}
+{"current_steps": 201, "total_steps": 201, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:02:18", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,706 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 201,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07462686567164178,
+      "grad_norm": 61.0959203382154,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.7374632358551025,
+      "logits/rejected": -2.7177176475524902,
+      "logps/chosen": -269.4803466796875,
+      "logps/rejected": -218.5151824951172,
+      "loss": 0.6899,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 0.015100441873073578,
+      "rewards/margins": 0.00384025601670146,
+      "rewards/rejected": 0.01126018911600113,
+      "step": 5
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "grad_norm": 47.476570306913814,
+      "learning_rate": 1e-06,
+      "logits/chosen": -2.707982063293457,
+      "logits/rejected": -2.699347972869873,
+      "logps/chosen": -259.8061218261719,
+      "logps/rejected": -198.84274291992188,
+      "loss": 0.6424,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.5450258255004883,
+      "rewards/margins": 0.22254791855812073,
+      "rewards/rejected": 0.32247787714004517,
+      "step": 10
+    },
+    {
+      "epoch": 0.22388059701492538,
+      "grad_norm": 49.6551549631888,
+      "learning_rate": 9.983100718730718e-07,
+      "logits/chosen": -2.5320260524749756,
+      "logits/rejected": -2.5290334224700928,
+      "logps/chosen": -251.0294189453125,
+      "logps/rejected": -215.8909912109375,
+      "loss": 0.6323,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 1.2386159896850586,
+      "rewards/margins": 0.6581863164901733,
+      "rewards/rejected": 0.5804295539855957,
+      "step": 15
+    },
+    {
+      "epoch": 0.29850746268656714,
+      "grad_norm": 45.55094865985364,
+      "learning_rate": 9.932517109205849e-07,
+      "logits/chosen": -2.3432915210723877,
+      "logits/rejected": -2.327422857284546,
+      "logps/chosen": -261.6549377441406,
+      "logps/rejected": -206.00390625,
+      "loss": 0.5745,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.5904659032821655,
+      "rewards/margins": 0.9221122860908508,
+      "rewards/rejected": 0.6683536767959595,
+      "step": 20
+    },
+    {
+      "epoch": 0.373134328358209,
+      "grad_norm": 66.0842546576943,
+      "learning_rate": 9.848591102083375e-07,
+      "logits/chosen": -2.217444896697998,
+      "logits/rejected": -2.2028653621673584,
+      "logps/chosen": -256.9215087890625,
+      "logps/rejected": -198.91497802734375,
+      "loss": 0.5856,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": 1.46311354637146,
+      "rewards/margins": 0.9280970692634583,
+      "rewards/rejected": 0.535016655921936,
+      "step": 25
+    },
+    {
+      "epoch": 0.44776119402985076,
+      "grad_norm": 39.48000022183853,
+      "learning_rate": 9.731890013043367e-07,
+      "logits/chosen": -2.1940948963165283,
+      "logits/rejected": -2.1792752742767334,
+      "logps/chosen": -220.172119140625,
+      "logps/rejected": -174.2005615234375,
+      "loss": 0.5741,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": 1.1630795001983643,
+      "rewards/margins": 1.0479199886322021,
+      "rewards/rejected": 0.11515955626964569,
+      "step": 30
+    },
+    {
+      "epoch": 0.5223880597014925,
+      "grad_norm": 39.73516854243651,
+      "learning_rate": 9.583202707897073e-07,
+      "logits/chosen": -2.151578426361084,
+      "logits/rejected": -2.138328790664673,
+      "logps/chosen": -271.12274169921875,
+      "logps/rejected": -222.46035766601562,
+      "loss": 0.557,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 1.6392730474472046,
+      "rewards/margins": 1.4565646648406982,
+      "rewards/rejected": 0.18270835280418396,
+      "step": 35
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 48.22042549381445,
+      "learning_rate": 9.403534270080829e-07,
+      "logits/chosen": -2.090759515762329,
+      "logits/rejected": -2.0454089641571045,
+      "logps/chosen": -246.8798370361328,
+      "logps/rejected": -208.13858032226562,
+      "loss": 0.5337,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": 1.0543644428253174,
+      "rewards/margins": 1.0213631391525269,
+      "rewards/rejected": 0.033001236617565155,
+      "step": 40
+    },
+    {
+      "epoch": 0.6716417910447762,
+      "grad_norm": 33.38243910231056,
+      "learning_rate": 9.19409920658098e-07,
+      "logits/chosen": -2.1067168712615967,
+      "logits/rejected": -2.0509848594665527,
+      "logps/chosen": -238.5055694580078,
+      "logps/rejected": -232.6929473876953,
+      "loss": 0.56,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.017447590827942,
+      "rewards/margins": 1.3171851634979248,
+      "rewards/rejected": -0.2997375428676605,
+      "step": 45
+    },
+    {
+      "epoch": 0.746268656716418,
+      "grad_norm": 36.138653661809,
+      "learning_rate": 8.956313238215823e-07,
+      "logits/chosen": -2.1871049404144287,
+      "logits/rejected": -2.1779439449310303,
+      "logps/chosen": -246.9051513671875,
+      "logps/rejected": -219.9314727783203,
+      "loss": 0.5248,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": 0.8862677812576294,
+      "rewards/margins": 1.3551105260849,
+      "rewards/rejected": -0.46884289383888245,
+      "step": 50
+    },
+    {
+      "epoch": 0.746268656716418,
+      "eval_logits/chosen": -2.2122514247894287,
+      "eval_logits/rejected": -2.189319372177124,
+      "eval_logps/chosen": -256.70928955078125,
+      "eval_logps/rejected": -219.54171752929688,
+      "eval_loss": 0.5635779500007629,
+      "eval_rewards/accuracies": 0.762499988079071,
+      "eval_rewards/chosen": 0.7980793118476868,
+      "eval_rewards/margins": 1.5356768369674683,
+      "eval_rewards/rejected": -0.7375972867012024,
+      "eval_runtime": 126.5339,
+      "eval_samples_per_second": 15.016,
+      "eval_steps_per_second": 0.237,
+      "step": 50
+    },
+    {
+      "epoch": 0.8208955223880597,
+      "grad_norm": 33.94437450648354,
+      "learning_rate": 8.691783729769873e-07,
+      "logits/chosen": -2.2479443550109863,
+      "logits/rejected": -2.2048230171203613,
+      "logps/chosen": -273.5711669921875,
+      "logps/rejected": -232.6655731201172,
+      "loss": 0.5358,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 1.0500261783599854,
+      "rewards/margins": 1.8445498943328857,
+      "rewards/rejected": -0.7945237755775452,
+      "step": 55
+    },
+    {
+      "epoch": 0.8955223880597015,
+      "grad_norm": 37.74564809329687,
+      "learning_rate": 8.402298824670029e-07,
+      "logits/chosen": -2.271031379699707,
+      "logits/rejected": -2.2530617713928223,
+      "logps/chosen": -274.867431640625,
+      "logps/rejected": -254.64004516601562,
+      "loss": 0.5812,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.9566941261291504,
+      "rewards/margins": 1.3896009922027588,
+      "rewards/rejected": -0.4329068064689636,
+      "step": 60
+    },
+    {
+      "epoch": 0.9701492537313433,
+      "grad_norm": 38.80874148817025,
+      "learning_rate": 8.089815357650089e-07,
+      "logits/chosen": -2.2410566806793213,
+      "logits/rejected": -2.2488720417022705,
+      "logps/chosen": -264.5858154296875,
+      "logps/rejected": -241.58132934570312,
+      "loss": 0.5166,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": 1.0656400918960571,
+      "rewards/margins": 1.8931087255477905,
+      "rewards/rejected": -0.8274686932563782,
+      "step": 65
+    },
+    {
+      "epoch": 1.044776119402985,
+      "grad_norm": 21.639463733660858,
+      "learning_rate": 7.756445627110522e-07,
+      "logits/chosen": -2.2948756217956543,
+      "logits/rejected": -2.271857738494873,
+      "logps/chosen": -264.6029052734375,
+      "logps/rejected": -239.9524688720703,
+      "loss": 0.3443,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 2.131361484527588,
+      "rewards/margins": 2.913156747817993,
+      "rewards/rejected": -0.78179532289505,
+      "step": 70
+    },
+    {
+      "epoch": 1.1194029850746268,
+      "grad_norm": 20.321072984977437,
+      "learning_rate": 7.404443116588547e-07,
+      "logits/chosen": -2.4182841777801514,
+      "logits/rejected": -2.384591579437256,
+      "logps/chosen": -246.2628173828125,
+      "logps/rejected": -195.36721801757812,
+      "loss": 0.228,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 2.294548988342285,
+      "rewards/margins": 2.9579689502716064,
+      "rewards/rejected": -0.663419783115387,
+      "step": 75
+    },
+    {
+      "epoch": 1.1940298507462686,
+      "grad_norm": 20.59550122688431,
+      "learning_rate": 7.036187261857288e-07,
+      "logits/chosen": -2.4467270374298096,
+      "logits/rejected": -2.423452854156494,
+      "logps/chosen": -260.4637145996094,
+      "logps/rejected": -222.98629760742188,
+      "loss": 0.2314,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 2.8386921882629395,
+      "rewards/margins": 3.558907985687256,
+      "rewards/rejected": -0.720215916633606,
+      "step": 80
+    },
+    {
+      "epoch": 1.2686567164179103,
+      "grad_norm": 24.122507472196027,
+      "learning_rate": 6.654167366624008e-07,
+      "logits/chosen": -2.408604145050049,
+      "logits/rejected": -2.39865779876709,
+      "logps/chosen": -232.1356201171875,
+      "logps/rejected": -221.2658233642578,
+      "loss": 0.2303,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.9124815464019775,
+      "rewards/margins": 3.2088208198547363,
+      "rewards/rejected": -1.2963393926620483,
+      "step": 85
+    },
+    {
+      "epoch": 1.3432835820895521,
+      "grad_norm": 42.3904683299003,
+      "learning_rate": 6.260965775552713e-07,
+      "logits/chosen": -2.4137942790985107,
+      "logits/rejected": -2.3900933265686035,
+      "logps/chosen": -248.0010986328125,
+      "logps/rejected": -238.64633178710938,
+      "loss": 0.256,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.8915069103240967,
+      "rewards/margins": 3.8078389167785645,
+      "rewards/rejected": -1.9163316488265991,
+      "step": 90
+    },
+    {
+      "epoch": 1.417910447761194,
+      "grad_norm": 21.496325022000395,
+      "learning_rate": 5.859240418356614e-07,
+      "logits/chosen": -2.409926176071167,
+      "logits/rejected": -2.3968422412872314,
+      "logps/chosen": -257.95928955078125,
+      "logps/rejected": -229.03427124023438,
+      "loss": 0.2499,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.9667186737060547,
+      "rewards/margins": 3.4216525554656982,
+      "rewards/rejected": -1.4549338817596436,
+      "step": 95
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "grad_norm": 18.487359146042973,
+      "learning_rate": 5.451706842957421e-07,
+      "logits/chosen": -2.389950752258301,
+      "logits/rejected": -2.3891632556915283,
+      "logps/chosen": -239.16134643554688,
+      "logps/rejected": -224.28585815429688,
+      "loss": 0.2521,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 2.022460460662842,
+      "rewards/margins": 3.3933162689208984,
+      "rewards/rejected": -1.3708559274673462,
+      "step": 100
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "eval_logits/chosen": -2.3766472339630127,
+      "eval_logits/rejected": -2.3607330322265625,
+      "eval_logps/chosen": -251.21282958984375,
+      "eval_logps/rejected": -224.6766815185547,
+      "eval_loss": 0.588749885559082,
+      "eval_rewards/accuracies": 0.8041666746139526,
+      "eval_rewards/chosen": 1.3477253913879395,
+      "eval_rewards/margins": 2.5988175868988037,
+      "eval_rewards/rejected": -1.251092553138733,
+      "eval_runtime": 125.127,
+      "eval_samples_per_second": 15.185,
+      "eval_steps_per_second": 0.24,
+      "step": 100
+    },
+    {
+      "epoch": 1.5671641791044775,
+      "grad_norm": 23.780577010359053,
+      "learning_rate": 5.041119859162068e-07,
+      "logits/chosen": -2.3645894527435303,
+      "logits/rejected": -2.3296666145324707,
+      "logps/chosen": -224.6007537841797,
+      "logps/rejected": -210.8166961669922,
+      "loss": 0.3064,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.5829575061798096,
+      "rewards/margins": 3.0166916847229004,
+      "rewards/rejected": -1.4337340593338013,
+      "step": 105
+    },
+    {
+      "epoch": 1.6417910447761193,
+      "grad_norm": 21.34094409707377,
+      "learning_rate": 4.630254916940423e-07,
+      "logits/chosen": -2.327462673187256,
+      "logits/rejected": -2.322633743286133,
+      "logps/chosen": -242.1077117919922,
+      "logps/rejected": -230.09719848632812,
+      "loss": 0.2489,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 1.909563422203064,
+      "rewards/margins": 3.9303386211395264,
+      "rewards/rejected": -2.020775318145752,
+      "step": 110
+    },
+    {
+      "epoch": 1.716417910447761,
+      "grad_norm": 22.148504337429173,
+      "learning_rate": 4.2218893451814e-07,
+      "logits/chosen": -2.3157925605773926,
+      "logits/rejected": -2.328068733215332,
+      "logps/chosen": -259.54437255859375,
+      "logps/rejected": -237.518798828125,
+      "loss": 0.2599,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 1.7707016468048096,
+      "rewards/margins": 3.8864364624023438,
+      "rewards/rejected": -2.1157352924346924,
+      "step": 115
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "grad_norm": 25.842103699055016,
+      "learning_rate": 3.8187835777481375e-07,
+      "logits/chosen": -2.306485652923584,
+      "logits/rejected": -2.307807445526123,
+      "logps/chosen": -252.6112518310547,
+      "logps/rejected": -246.40322875976562,
+      "loss": 0.2738,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 1.641487717628479,
+      "rewards/margins": 3.6894028186798096,
+      "rewards/rejected": -2.047914981842041,
+      "step": 120
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 22.252666568025052,
+      "learning_rate": 3.423662493738687e-07,
+      "logits/chosen": -2.279599189758301,
+      "logits/rejected": -2.2538650035858154,
+      "logps/chosen": -243.33535766601562,
+      "logps/rejected": -206.66940307617188,
+      "loss": 0.2635,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.8119112253189087,
+      "rewards/margins": 3.5522758960723877,
+      "rewards/rejected": -1.740364670753479,
+      "step": 125
+    },
+    {
+      "epoch": 1.9402985074626866,
+      "grad_norm": 25.3950797198185,
+      "learning_rate": 3.039196998086687e-07,
+      "logits/chosen": -2.2437617778778076,
+      "logits/rejected": -2.2337818145751953,
+      "logps/chosen": -241.3092498779297,
+      "logps/rejected": -242.51657104492188,
+      "loss": 0.278,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 2.186619281768799,
+      "rewards/margins": 3.923696517944336,
+      "rewards/rejected": -1.7370771169662476,
+      "step": 130
+    },
+    {
+      "epoch": 2.014925373134328,
+      "grad_norm": 17.8657699205854,
+      "learning_rate": 2.667985967011878e-07,
+      "logits/chosen": -2.255903720855713,
+      "logits/rejected": -2.2353529930114746,
+      "logps/chosen": -257.59307861328125,
+      "logps/rejected": -241.2735137939453,
+      "loss": 0.2614,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.9635776281356812,
+      "rewards/margins": 3.8186099529266357,
+      "rewards/rejected": -1.8550323247909546,
+      "step": 135
+    },
+    {
+      "epoch": 2.08955223880597,
+      "grad_norm": 16.448108998699187,
+      "learning_rate": 2.3125386803640183e-07,
+      "logits/chosen": -2.245354175567627,
+      "logits/rejected": -2.2395224571228027,
+      "logps/chosen": -241.65097045898438,
+      "logps/rejected": -234.07504272460938,
+      "loss": 0.1341,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.9018363952636719,
+      "rewards/margins": 3.9239959716796875,
+      "rewards/rejected": -2.0221593379974365,
+      "step": 140
+    },
+    {
+      "epoch": 2.1641791044776117,
+      "grad_norm": 16.872186227206235,
+      "learning_rate": 1.9752578596124952e-07,
+      "logits/chosen": -2.273176431655884,
+      "logits/rejected": -2.252638578414917,
+      "logps/chosen": -252.98904418945312,
+      "logps/rejected": -219.36355590820312,
+      "loss": 0.1518,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 2.0040693283081055,
+      "rewards/margins": 3.9979896545410156,
+      "rewards/rejected": -1.9939203262329102,
+      "step": 145
+    },
+    {
+      "epoch": 2.2388059701492535,
+      "grad_norm": 14.753431701417778,
+      "learning_rate": 1.6584234261399532e-07,
+      "logits/chosen": -2.278550148010254,
+      "logits/rejected": -2.28568696975708,
+      "logps/chosen": -227.6191864013672,
+      "logps/rejected": -248.12637329101562,
+      "loss": 0.1273,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": 1.9932959079742432,
+      "rewards/margins": 4.387091636657715,
+      "rewards/rejected": -2.3937957286834717,
+      "step": 150
+    },
+    {
+      "epoch": 2.2388059701492535,
+      "eval_logits/chosen": -2.3105554580688477,
+      "eval_logits/rejected": -2.2852249145507812,
+      "eval_logps/chosen": -252.7459259033203,
+      "eval_logps/rejected": -227.99476623535156,
+      "eval_loss": 0.5529021620750427,
+      "eval_rewards/accuracies": 0.824999988079071,
+      "eval_rewards/chosen": 1.1944137811660767,
+      "eval_rewards/margins": 2.777313709259033,
+      "eval_rewards/rejected": -1.5828994512557983,
+      "eval_runtime": 125.2259,
+      "eval_samples_per_second": 15.173,
+      "eval_steps_per_second": 0.24,
+      "step": 150
+    },
+    {
+      "epoch": 2.3134328358208958,
+      "grad_norm": 16.834571942257156,
+      "learning_rate": 1.3641770896292082e-07,
+      "logits/chosen": -2.3284482955932617,
+      "logits/rejected": -2.2805988788604736,
+      "logps/chosen": -243.53829956054688,
+      "logps/rejected": -229.0917205810547,
+      "loss": 0.1588,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 2.213130235671997,
+      "rewards/margins": 4.087383270263672,
+      "rewards/rejected": -1.874253273010254,
+      "step": 155
+    },
+    {
+      "epoch": 2.388059701492537,
+      "grad_norm": 19.56642516410395,
+      "learning_rate": 1.0945078707215221e-07,
+      "logits/chosen": -2.3081579208374023,
+      "logits/rejected": -2.2797722816467285,
+      "logps/chosen": -247.8934783935547,
+      "logps/rejected": -233.1248779296875,
+      "loss": 0.1638,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 2.279715061187744,
+      "rewards/margins": 4.036622524261475,
+      "rewards/rejected": -1.7569072246551514,
+      "step": 160
+    },
+    {
+      "epoch": 2.4626865671641793,
+      "grad_norm": 18.300870643833345,
+      "learning_rate": 8.512386558088919e-08,
+      "logits/chosen": -2.3260269165039062,
+      "logits/rejected": -2.2975800037384033,
+      "logps/chosen": -242.68701171875,
+      "logps/rejected": -268.1483154296875,
+      "loss": 0.1669,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 2.3186392784118652,
+      "rewards/margins": 4.955061912536621,
+      "rewards/rejected": -2.636422634124756,
+      "step": 165
+    },
+    {
+      "epoch": 2.5373134328358207,
+      "grad_norm": 21.6227394122481,
+      "learning_rate": 6.360138748461013e-08,
+      "logits/chosen": -2.3063161373138428,
+      "logits/rejected": -2.2875423431396484,
+      "logps/chosen": -255.9014129638672,
+      "logps/rejected": -227.6916961669922,
+      "loss": 0.1735,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 2.3107035160064697,
+      "rewards/margins": 4.324804782867432,
+      "rewards/rejected": -2.01410174369812,
+      "step": 170
+    },
+    {
+      "epoch": 2.611940298507463,
+      "grad_norm": 14.773801488331259,
+      "learning_rate": 4.5028838547699346e-08,
+      "logits/chosen": -2.3168740272521973,
+      "logits/rejected": -2.2947440147399902,
+      "logps/chosen": -243.5282745361328,
+      "logps/rejected": -236.17990112304688,
+      "loss": 0.1397,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 2.2061328887939453,
+      "rewards/margins": 4.2199482917785645,
+      "rewards/rejected": -2.013815402984619,
+      "step": 175
+    },
+    {
+      "epoch": 2.6865671641791042,
+      "grad_norm": 13.973141137191872,
+      "learning_rate": 2.9531763861505964e-08,
+      "logits/chosen": -2.3316142559051514,
+      "logits/rejected": -2.291159152984619,
+      "logps/chosen": -252.21511840820312,
+      "logps/rejected": -246.81796264648438,
+      "loss": 0.1557,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": 2.47810697555542,
+      "rewards/margins": 4.51055908203125,
+      "rewards/rejected": -2.032452344894409,
+      "step": 180
+    },
+    {
+      "epoch": 2.7611940298507465,
+      "grad_norm": 19.964297927354572,
+      "learning_rate": 1.7214919195619125e-08,
+      "logits/chosen": -2.3097987174987793,
+      "logits/rejected": -2.27604079246521,
+      "logps/chosen": -237.06045532226562,
+      "logps/rejected": -232.19808959960938,
+      "loss": 0.1517,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 1.585829496383667,
+      "rewards/margins": 4.088876724243164,
+      "rewards/rejected": -2.503047466278076,
+      "step": 185
+    },
+    {
+      "epoch": 2.835820895522388,
+      "grad_norm": 21.11350475489601,
+      "learning_rate": 8.161562878982398e-09,
+      "logits/chosen": -2.3078198432922363,
+      "logits/rejected": -2.282045602798462,
+      "logps/chosen": -253.4175262451172,
+      "logps/rejected": -224.1904296875,
+      "loss": 0.1267,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 2.3276572227478027,
+      "rewards/margins": 4.33654260635376,
+      "rewards/rejected": -2.0088844299316406,
+      "step": 190
+    },
+    {
+      "epoch": 2.91044776119403,
+      "grad_norm": 18.60016260779278,
+      "learning_rate": 2.432892997526026e-09,
+      "logits/chosen": -2.325418710708618,
+      "logits/rejected": -2.2867703437805176,
+      "logps/chosen": -226.9629669189453,
+      "logps/rejected": -230.8715362548828,
+      "loss": 0.1148,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 2.127265214920044,
+      "rewards/margins": 4.185291290283203,
+      "rewards/rejected": -2.0580265522003174,
+      "step": 195
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "grad_norm": 17.114004265650976,
+      "learning_rate": 6.763371270035457e-11,
+      "logits/chosen": -2.3209595680236816,
+      "logits/rejected": -2.300201416015625,
+      "logps/chosen": -249.88442993164062,
+      "logps/rejected": -224.8131103515625,
+      "loss": 0.1289,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 2.2298994064331055,
+      "rewards/margins": 4.393718719482422,
+      "rewards/rejected": -2.163818836212158,
+      "step": 200
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "eval_logits/chosen": -2.3139846324920654,
+      "eval_logits/rejected": -2.28657865524292,
+      "eval_logps/chosen": -253.50108337402344,
+      "eval_logps/rejected": -229.3605499267578,
+      "eval_loss": 0.5585500001907349,
+      "eval_rewards/accuracies": 0.8125,
+      "eval_rewards/chosen": 1.1188981533050537,
+      "eval_rewards/margins": 2.8383777141571045,
+      "eval_rewards/rejected": -1.7194799184799194,
+      "eval_runtime": 125.2826,
+      "eval_samples_per_second": 15.166,
+      "eval_steps_per_second": 0.239,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "step": 201,
+      "total_flos": 2369906314051584.0,
+      "train_loss": 0.3258563337560317,
+      "train_runtime": 7340.6492,
+      "train_samples_per_second": 6.986,
+      "train_steps_per_second": 0.027
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 201,
+  "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": 2369906314051584.0,
+  "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:ba67567d4b45b8ca82d5bd50448fa116196f189451254da8a14c15165485f876
+size 7096