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_cocour_new_step10_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_cocour_new_step10_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_cocour_new_step10_0_50 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5010
+- Rewards/chosen: 1.1422
+- Rewards/rejected: -1.7885
+- Rewards/accuracies: 0.8583
+- Rewards/margins: 2.9307
+- Logps/rejected: -214.9074
+- Logps/chosen: -264.3012
+- Logits/rejected: -2.0474
+- Logits/chosen: -2.1072
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.6039        | 0.7463 | 50   | 0.5475          | 1.3230         | -0.4024          | 0.8167             | 1.7254          | -201.0464      | -262.4934    | -2.4300         | -2.4488       |
+| 0.2811        | 1.4925 | 100  | 0.5121          | 1.3770         | -1.3342          | 0.8542             | 2.7112          | -210.3646      | -261.9533    | -1.9351         | -2.0044       |
+| 0.1518        | 2.2388 | 150  | 0.5044          | 1.4880         | -1.2566          | 0.8542             | 2.7446          | -209.5883      | -260.8434    | -2.0397         | -2.0982       |
+| 0.1381        | 2.9851 | 200  | 0.5010          | 1.1421         | -1.7916          | 0.8583             | 2.9338          | -214.9391      | -264.3022    | -2.0472         | -2.1071       |
+
+
+### 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": -2.107180118560791,
+    "eval_logits/rejected": -2.047370672225952,
+    "eval_logps/chosen": -264.3012390136719,
+    "eval_logps/rejected": -214.9073944091797,
+    "eval_loss": 0.500950038433075,
+    "eval_rewards/accuracies": 0.8583333492279053,
+    "eval_rewards/chosen": 1.1422334909439087,
+    "eval_rewards/margins": 2.9307103157043457,
+    "eval_rewards/rejected": -1.7884769439697266,
+    "eval_runtime": 125.5521,
+    "eval_samples_per_second": 15.133,
+    "eval_steps_per_second": 0.239,
+    "total_flos": 2369906314051584.0,
+    "train_loss": 0.33028975388600457,
+    "train_runtime": 7391.1638,
+    "train_samples_per_second": 6.939,
+    "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": -2.107180118560791,
+    "eval_logits/rejected": -2.047370672225952,
+    "eval_logps/chosen": -264.3012390136719,
+    "eval_logps/rejected": -214.9073944091797,
+    "eval_loss": 0.500950038433075,
+    "eval_rewards/accuracies": 0.8583333492279053,
+    "eval_rewards/chosen": 1.1422334909439087,
+    "eval_rewards/margins": 2.9307103157043457,
+    "eval_rewards/rejected": -1.7884769439697266,
+    "eval_runtime": 125.5521,
+    "eval_samples_per_second": 15.133,
+    "eval_steps_per_second": 0.239
+}

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:bc5f3db061648fc03f3739220d0999c89236f92f47eb6f7508c26b685bc709a2
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daca923462f272b0c11100fef211db00e723bf5a377bd53a2ea7391b6393c113
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc07818509ed20aacb915a7c6b1c134896f695c69f161e63f32ddf882d7364b
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:904b00a91a4d8ed37a38f1e9a69dacaccda9b8aaff5ca0c92c0bd025fd088a42
+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": 0.33028975388600457,
+    "train_runtime": 7391.1638,
+    "train_samples_per_second": 6.939,
+    "train_steps_per_second": 0.027
+}

trainer_log.jsonl

@@ -0,0 +1,45 @@
+{"current_steps": 5, "total_steps": 201, "loss": 0.69, "accuracy": 0.3375000059604645, "learning_rate": 5e-07, "epoch": 0.07462686567164178, "percentage": 2.49, "elapsed_time": "0:02:52", "remaining_time": "1:52:44"}
+{"current_steps": 10, "total_steps": 201, "loss": 0.6347, "accuracy": 0.6312500238418579, "learning_rate": 1e-06, "epoch": 0.14925373134328357, "percentage": 4.98, "elapsed_time": "0:05:40", "remaining_time": "1:48:23"}
+{"current_steps": 15, "total_steps": 201, "loss": 0.6435, "accuracy": 0.6812499761581421, "learning_rate": 9.983100718730718e-07, "epoch": 0.22388059701492538, "percentage": 7.46, "elapsed_time": "0:08:28", "remaining_time": "1:45:06"}
+{"current_steps": 20, "total_steps": 201, "loss": 0.6022, "accuracy": 0.706250011920929, "learning_rate": 9.932517109205849e-07, "epoch": 0.29850746268656714, "percentage": 9.95, "elapsed_time": "0:11:16", "remaining_time": "1:42:06"}
+{"current_steps": 25, "total_steps": 201, "loss": 0.598, "accuracy": 0.762499988079071, "learning_rate": 9.848591102083375e-07, "epoch": 0.373134328358209, "percentage": 12.44, "elapsed_time": "0:14:05", "remaining_time": "1:39:12"}
+{"current_steps": 30, "total_steps": 201, "loss": 0.5785, "accuracy": 0.768750011920929, "learning_rate": 9.731890013043367e-07, "epoch": 0.44776119402985076, "percentage": 14.93, "elapsed_time": "0:16:53", "remaining_time": "1:36:14"}
+{"current_steps": 35, "total_steps": 201, "loss": 0.5553, "accuracy": 0.7437499761581421, "learning_rate": 9.583202707897073e-07, "epoch": 0.5223880597014925, "percentage": 17.41, "elapsed_time": "0:19:42", "remaining_time": "1:33:26"}
+{"current_steps": 40, "total_steps": 201, "loss": 0.5634, "accuracy": 0.731249988079071, "learning_rate": 9.403534270080829e-07, "epoch": 0.5970149253731343, "percentage": 19.9, "elapsed_time": "0:22:30", "remaining_time": "1:30:37"}
+{"current_steps": 45, "total_steps": 201, "loss": 0.5355, "accuracy": 0.7562500238418579, "learning_rate": 9.19409920658098e-07, "epoch": 0.6716417910447762, "percentage": 22.39, "elapsed_time": "0:25:19", "remaining_time": "1:27:46"}
+{"current_steps": 50, "total_steps": 201, "loss": 0.6039, "accuracy": 0.7250000238418579, "learning_rate": 8.956313238215823e-07, "epoch": 0.746268656716418, "percentage": 24.88, "elapsed_time": "0:28:08", "remaining_time": "1:24:57"}
+{"current_steps": 50, "total_steps": 201, "eval_loss": 0.5474794507026672, "epoch": 0.746268656716418, "percentage": 24.88, "elapsed_time": "0:30:14", "remaining_time": "1:31:19"}
+{"current_steps": 55, "total_steps": 201, "loss": 0.5075, "accuracy": 0.768750011920929, "learning_rate": 8.691783729769873e-07, "epoch": 0.8208955223880597, "percentage": 27.36, "elapsed_time": "0:33:02", "remaining_time": "1:27:43"}
+{"current_steps": 60, "total_steps": 201, "loss": 0.5362, "accuracy": 0.8125, "learning_rate": 8.402298824670029e-07, "epoch": 0.8955223880597015, "percentage": 29.85, "elapsed_time": "0:35:51", "remaining_time": "1:24:16"}
+{"current_steps": 65, "total_steps": 201, "loss": 0.5397, "accuracy": 0.768750011920929, "learning_rate": 8.089815357650089e-07, "epoch": 0.9701492537313433, "percentage": 32.34, "elapsed_time": "0:38:41", "remaining_time": "1:20:57"}
+{"current_steps": 70, "total_steps": 201, "loss": 0.3658, "accuracy": 0.8500000238418579, "learning_rate": 7.756445627110522e-07, "epoch": 1.044776119402985, "percentage": 34.83, "elapsed_time": "0:41:30", "remaining_time": "1:17:40"}
+{"current_steps": 75, "total_steps": 201, "loss": 0.2501, "accuracy": 0.9125000238418579, "learning_rate": 7.404443116588547e-07, "epoch": 1.1194029850746268, "percentage": 37.31, "elapsed_time": "0:44:19", "remaining_time": "1:14:27"}
+{"current_steps": 80, "total_steps": 201, "loss": 0.2198, "accuracy": 0.925000011920929, "learning_rate": 7.036187261857288e-07, "epoch": 1.1940298507462686, "percentage": 39.8, "elapsed_time": "0:47:08", "remaining_time": "1:11:17"}
+{"current_steps": 85, "total_steps": 201, "loss": 0.2434, "accuracy": 0.887499988079071, "learning_rate": 6.654167366624008e-07, "epoch": 1.2686567164179103, "percentage": 42.29, "elapsed_time": "0:49:57", "remaining_time": "1:08:10"}
+{"current_steps": 90, "total_steps": 201, "loss": 0.2496, "accuracy": 0.90625, "learning_rate": 6.260965775552713e-07, "epoch": 1.3432835820895521, "percentage": 44.78, "elapsed_time": "0:52:45", "remaining_time": "1:05:04"}
+{"current_steps": 95, "total_steps": 201, "loss": 0.2431, "accuracy": 0.9312499761581421, "learning_rate": 5.859240418356614e-07, "epoch": 1.417910447761194, "percentage": 47.26, "elapsed_time": "0:55:33", "remaining_time": "1:01:59"}
+{"current_steps": 100, "total_steps": 201, "loss": 0.2811, "accuracy": 0.8999999761581421, "learning_rate": 5.451706842957421e-07, "epoch": 1.4925373134328357, "percentage": 49.75, "elapsed_time": "0:58:21", "remaining_time": "0:58:56"}
+{"current_steps": 100, "total_steps": 201, "eval_loss": 0.5120986700057983, "epoch": 1.4925373134328357, "percentage": 49.75, "elapsed_time": "1:00:27", "remaining_time": "1:01:03"}
+{"current_steps": 105, "total_steps": 201, "loss": 0.2519, "accuracy": 0.9375, "learning_rate": 5.041119859162068e-07, "epoch": 1.5671641791044775, "percentage": 52.24, "elapsed_time": "1:03:50", "remaining_time": "0:58:21"}
+{"current_steps": 110, "total_steps": 201, "loss": 0.2646, "accuracy": 0.918749988079071, "learning_rate": 4.630254916940423e-07, "epoch": 1.6417910447761193, "percentage": 54.73, "elapsed_time": "1:06:38", "remaining_time": "0:55:07"}
+{"current_steps": 115, "total_steps": 201, "loss": 0.2487, "accuracy": 0.893750011920929, "learning_rate": 4.2218893451814e-07, "epoch": 1.716417910447761, "percentage": 57.21, "elapsed_time": "1:09:26", "remaining_time": "0:51:55"}
+{"current_steps": 120, "total_steps": 201, "loss": 0.2907, "accuracy": 0.918749988079071, "learning_rate": 3.8187835777481375e-07, "epoch": 1.7910447761194028, "percentage": 59.7, "elapsed_time": "1:12:14", "remaining_time": "0:48:45"}
+{"current_steps": 125, "total_steps": 201, "loss": 0.2537, "accuracy": 0.918749988079071, "learning_rate": 3.423662493738687e-07, "epoch": 1.8656716417910446, "percentage": 62.19, "elapsed_time": "1:15:02", "remaining_time": "0:45:37"}
+{"current_steps": 130, "total_steps": 201, "loss": 0.2703, "accuracy": 0.90625, "learning_rate": 3.039196998086687e-07, "epoch": 1.9402985074626866, "percentage": 64.68, "elapsed_time": "1:17:51", "remaining_time": "0:42:31"}
+{"current_steps": 135, "total_steps": 201, "loss": 0.2636, "accuracy": 0.90625, "learning_rate": 2.667985967011878e-07, "epoch": 2.014925373134328, "percentage": 67.16, "elapsed_time": "1:20:40", "remaining_time": "0:39:26"}
+{"current_steps": 140, "total_steps": 201, "loss": 0.1728, "accuracy": 0.956250011920929, "learning_rate": 2.3125386803640183e-07, "epoch": 2.08955223880597, "percentage": 69.65, "elapsed_time": "1:23:29", "remaining_time": "0:36:22"}
+{"current_steps": 145, "total_steps": 201, "loss": 0.1454, "accuracy": 0.9750000238418579, "learning_rate": 1.9752578596124952e-07, "epoch": 2.1641791044776117, "percentage": 72.14, "elapsed_time": "1:26:19", "remaining_time": "0:33:20"}
+{"current_steps": 150, "total_steps": 201, "loss": 0.1518, "accuracy": 0.9437500238418579, "learning_rate": 1.6584234261399532e-07, "epoch": 2.2388059701492535, "percentage": 74.63, "elapsed_time": "1:29:08", "remaining_time": "0:30:18"}
+{"current_steps": 150, "total_steps": 201, "eval_loss": 0.5043797492980957, "epoch": 2.2388059701492535, "percentage": 74.63, "elapsed_time": "1:31:15", "remaining_time": "0:31:01"}
+{"current_steps": 155, "total_steps": 201, "loss": 0.1395, "accuracy": 0.956250011920929, "learning_rate": 1.3641770896292082e-07, "epoch": 2.3134328358208958, "percentage": 77.11, "elapsed_time": "1:34:03", "remaining_time": "0:27:54"}
+{"current_steps": 160, "total_steps": 201, "loss": 0.1418, "accuracy": 0.918749988079071, "learning_rate": 1.0945078707215221e-07, "epoch": 2.388059701492537, "percentage": 79.6, "elapsed_time": "1:36:51", "remaining_time": "0:24:49"}
+{"current_steps": 165, "total_steps": 201, "loss": 0.154, "accuracy": 0.9312499761581421, "learning_rate": 8.512386558088919e-08, "epoch": 2.4626865671641793, "percentage": 82.09, "elapsed_time": "1:39:39", "remaining_time": "0:21:44"}
+{"current_steps": 170, "total_steps": 201, "loss": 0.1596, "accuracy": 0.949999988079071, "learning_rate": 6.360138748461013e-08, "epoch": 2.5373134328358207, "percentage": 84.58, "elapsed_time": "1:42:28", "remaining_time": "0:18:41"}
+{"current_steps": 175, "total_steps": 201, "loss": 0.1698, "accuracy": 0.949999988079071, "learning_rate": 4.5028838547699346e-08, "epoch": 2.611940298507463, "percentage": 87.06, "elapsed_time": "1:45:16", "remaining_time": "0:15:38"}
+{"current_steps": 180, "total_steps": 201, "loss": 0.1637, "accuracy": 0.90625, "learning_rate": 2.9531763861505964e-08, "epoch": 2.6865671641791042, "percentage": 89.55, "elapsed_time": "1:48:05", "remaining_time": "0:12:36"}
+{"current_steps": 185, "total_steps": 201, "loss": 0.1418, "accuracy": 0.9624999761581421, "learning_rate": 1.7214919195619125e-08, "epoch": 2.7611940298507465, "percentage": 92.04, "elapsed_time": "1:50:53", "remaining_time": "0:09:35"}
+{"current_steps": 190, "total_steps": 201, "loss": 0.1596, "accuracy": 0.9312499761581421, "learning_rate": 8.161562878982398e-09, "epoch": 2.835820895522388, "percentage": 94.53, "elapsed_time": "1:53:42", "remaining_time": "0:06:34"}
+{"current_steps": 195, "total_steps": 201, "loss": 0.1348, "accuracy": 0.9125000238418579, "learning_rate": 2.432892997526026e-09, "epoch": 2.91044776119403, "percentage": 97.01, "elapsed_time": "1:56:29", "remaining_time": "0:03:35"}
+{"current_steps": 200, "total_steps": 201, "loss": 0.1381, "accuracy": 0.9750000238418579, "learning_rate": 6.763371270035457e-11, "epoch": 2.9850746268656714, "percentage": 99.5, "elapsed_time": "1:59:17", "remaining_time": "0:00:35"}
+{"current_steps": 200, "total_steps": 201, "eval_loss": 0.5009533762931824, "epoch": 2.9850746268656714, "percentage": 99.5, "elapsed_time": "2:01:23", "remaining_time": "0:00:36"}
+{"current_steps": 201, "total_steps": 201, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:03:08", "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": 56.774636606182945,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.7173850536346436,
+      "logits/rejected": -2.71553373336792,
+      "logps/chosen": -263.896728515625,
+      "logps/rejected": -227.8684539794922,
+      "loss": 0.69,
+      "rewards/accuracies": 0.3375000059604645,
+      "rewards/chosen": 0.018741395324468613,
+      "rewards/margins": 0.007884879596531391,
+      "rewards/rejected": 0.010856516659259796,
+      "step": 5
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "grad_norm": 49.171395793260366,
+      "learning_rate": 1e-06,
+      "logits/chosen": -2.658963680267334,
+      "logits/rejected": -2.6707260608673096,
+      "logps/chosen": -239.9593963623047,
+      "logps/rejected": -201.82704162597656,
+      "loss": 0.6347,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": 0.49142637848854065,
+      "rewards/margins": 0.10814571380615234,
+      "rewards/rejected": 0.3832806348800659,
+      "step": 10
+    },
+    {
+      "epoch": 0.22388059701492538,
+      "grad_norm": 49.521893521620925,
+      "learning_rate": 9.983100718730718e-07,
+      "logits/chosen": -2.462752103805542,
+      "logits/rejected": -2.4498093128204346,
+      "logps/chosen": -223.9767608642578,
+      "logps/rejected": -186.4107208251953,
+      "loss": 0.6435,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": 1.3751007318496704,
+      "rewards/margins": 0.8284648656845093,
+      "rewards/rejected": 0.5466357469558716,
+      "step": 15
+    },
+    {
+      "epoch": 0.29850746268656714,
+      "grad_norm": 39.064368139363026,
+      "learning_rate": 9.932517109205849e-07,
+      "logits/chosen": -2.3084564208984375,
+      "logits/rejected": -2.284285306930542,
+      "logps/chosen": -216.29672241210938,
+      "logps/rejected": -210.03366088867188,
+      "loss": 0.6022,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": 1.3789255619049072,
+      "rewards/margins": 1.200923204421997,
+      "rewards/rejected": 0.17800235748291016,
+      "step": 20
+    },
+    {
+      "epoch": 0.373134328358209,
+      "grad_norm": 42.02666971304695,
+      "learning_rate": 9.848591102083375e-07,
+      "logits/chosen": -2.1679234504699707,
+      "logits/rejected": -2.1585092544555664,
+      "logps/chosen": -248.0310821533203,
+      "logps/rejected": -202.24365234375,
+      "loss": 0.598,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 1.483551025390625,
+      "rewards/margins": 1.0866239070892334,
+      "rewards/rejected": 0.39692699909210205,
+      "step": 25
+    },
+    {
+      "epoch": 0.44776119402985076,
+      "grad_norm": 35.54152957556429,
+      "learning_rate": 9.731890013043367e-07,
+      "logits/chosen": -2.1620185375213623,
+      "logits/rejected": -2.134643793106079,
+      "logps/chosen": -258.4416809082031,
+      "logps/rejected": -218.0922393798828,
+      "loss": 0.5785,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": 1.5798461437225342,
+      "rewards/margins": 1.5195716619491577,
+      "rewards/rejected": 0.06027444079518318,
+      "step": 30
+    },
+    {
+      "epoch": 0.5223880597014925,
+      "grad_norm": 39.252296599241106,
+      "learning_rate": 9.583202707897073e-07,
+      "logits/chosen": -2.246034622192383,
+      "logits/rejected": -2.1999077796936035,
+      "logps/chosen": -247.757568359375,
+      "logps/rejected": -200.7145538330078,
+      "loss": 0.5553,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": 0.9202949404716492,
+      "rewards/margins": 1.2205396890640259,
+      "rewards/rejected": -0.3002447187900543,
+      "step": 35
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 40.409666420169685,
+      "learning_rate": 9.403534270080829e-07,
+      "logits/chosen": -2.2683088779449463,
+      "logits/rejected": -2.2772603034973145,
+      "logps/chosen": -232.68746948242188,
+      "logps/rejected": -204.03921508789062,
+      "loss": 0.5634,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": 0.9635717272758484,
+      "rewards/margins": 0.9926932454109192,
+      "rewards/rejected": -0.029121670871973038,
+      "step": 40
+    },
+    {
+      "epoch": 0.6716417910447762,
+      "grad_norm": 35.68185280636666,
+      "learning_rate": 9.19409920658098e-07,
+      "logits/chosen": -2.325417995452881,
+      "logits/rejected": -2.3191263675689697,
+      "logps/chosen": -246.6074676513672,
+      "logps/rejected": -206.07778930664062,
+      "loss": 0.5355,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": 1.4123908281326294,
+      "rewards/margins": 1.4990627765655518,
+      "rewards/rejected": -0.08667198568582535,
+      "step": 45
+    },
+    {
+      "epoch": 0.746268656716418,
+      "grad_norm": 37.69485379762672,
+      "learning_rate": 8.956313238215823e-07,
+      "logits/chosen": -2.412565231323242,
+      "logits/rejected": -2.4015040397644043,
+      "logps/chosen": -253.4149169921875,
+      "logps/rejected": -191.1724090576172,
+      "loss": 0.6039,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 1.2345142364501953,
+      "rewards/margins": 1.3397375345230103,
+      "rewards/rejected": -0.10522329807281494,
+      "step": 50
+    },
+    {
+      "epoch": 0.746268656716418,
+      "eval_logits/chosen": -2.448784351348877,
+      "eval_logits/rejected": -2.429978609085083,
+      "eval_logps/chosen": -262.4934387207031,
+      "eval_logps/rejected": -201.04635620117188,
+      "eval_loss": 0.5474794507026672,
+      "eval_rewards/accuracies": 0.8166666626930237,
+      "eval_rewards/chosen": 1.3230173587799072,
+      "eval_rewards/margins": 1.7253921031951904,
+      "eval_rewards/rejected": -0.402374804019928,
+      "eval_runtime": 126.4937,
+      "eval_samples_per_second": 15.021,
+      "eval_steps_per_second": 0.237,
+      "step": 50
+    },
+    {
+      "epoch": 0.8208955223880597,
+      "grad_norm": 33.62557977902233,
+      "learning_rate": 8.691783729769873e-07,
+      "logits/chosen": -2.448288679122925,
+      "logits/rejected": -2.420079231262207,
+      "logps/chosen": -246.814453125,
+      "logps/rejected": -222.81369018554688,
+      "loss": 0.5075,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": 1.3512744903564453,
+      "rewards/margins": 1.5960042476654053,
+      "rewards/rejected": -0.24473004043102264,
+      "step": 55
+    },
+    {
+      "epoch": 0.8955223880597015,
+      "grad_norm": 34.40548669609605,
+      "learning_rate": 8.402298824670029e-07,
+      "logits/chosen": -2.4062578678131104,
+      "logits/rejected": -2.3980088233947754,
+      "logps/chosen": -244.09963989257812,
+      "logps/rejected": -220.0731658935547,
+      "loss": 0.5362,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 1.0276352167129517,
+      "rewards/margins": 1.7561748027801514,
+      "rewards/rejected": -0.7285395860671997,
+      "step": 60
+    },
+    {
+      "epoch": 0.9701492537313433,
+      "grad_norm": 28.164310082130665,
+      "learning_rate": 8.089815357650089e-07,
+      "logits/chosen": -2.3062520027160645,
+      "logits/rejected": -2.2625319957733154,
+      "logps/chosen": -252.2916717529297,
+      "logps/rejected": -205.3076629638672,
+      "loss": 0.5397,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": 1.2947864532470703,
+      "rewards/margins": 1.5517289638519287,
+      "rewards/rejected": -0.2569425106048584,
+      "step": 65
+    },
+    {
+      "epoch": 1.044776119402985,
+      "grad_norm": 21.112407246277925,
+      "learning_rate": 7.756445627110522e-07,
+      "logits/chosen": -2.2231955528259277,
+      "logits/rejected": -2.1976494789123535,
+      "logps/chosen": -235.33688354492188,
+      "logps/rejected": -231.05859375,
+      "loss": 0.3658,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": 1.7080755233764648,
+      "rewards/margins": 2.355454921722412,
+      "rewards/rejected": -0.6473790407180786,
+      "step": 70
+    },
+    {
+      "epoch": 1.1194029850746268,
+      "grad_norm": 19.878898492793304,
+      "learning_rate": 7.404443116588547e-07,
+      "logits/chosen": -2.1846470832824707,
+      "logits/rejected": -2.1705875396728516,
+      "logps/chosen": -260.013427734375,
+      "logps/rejected": -221.21255493164062,
+      "loss": 0.2501,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.7602205276489258,
+      "rewards/margins": 2.9061784744262695,
+      "rewards/rejected": -1.1459578275680542,
+      "step": 75
+    },
+    {
+      "epoch": 1.1940298507462686,
+      "grad_norm": 18.98334057762975,
+      "learning_rate": 7.036187261857288e-07,
+      "logits/chosen": -2.139054775238037,
+      "logits/rejected": -2.1150176525115967,
+      "logps/chosen": -220.98129272460938,
+      "logps/rejected": -219.1953125,
+      "loss": 0.2198,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.633134126663208,
+      "rewards/margins": 3.2258033752441406,
+      "rewards/rejected": -1.592669129371643,
+      "step": 80
+    },
+    {
+      "epoch": 1.2686567164179103,
+      "grad_norm": 19.761118649470582,
+      "learning_rate": 6.654167366624008e-07,
+      "logits/chosen": -2.1024246215820312,
+      "logits/rejected": -2.0848536491394043,
+      "logps/chosen": -234.4004669189453,
+      "logps/rejected": -226.5931396484375,
+      "loss": 0.2434,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 1.7910864353179932,
+      "rewards/margins": 3.391458511352539,
+      "rewards/rejected": -1.600372314453125,
+      "step": 85
+    },
+    {
+      "epoch": 1.3432835820895521,
+      "grad_norm": 18.92386433541345,
+      "learning_rate": 6.260965775552713e-07,
+      "logits/chosen": -2.071793794631958,
+      "logits/rejected": -1.9989004135131836,
+      "logps/chosen": -224.1923065185547,
+      "logps/rejected": -204.32492065429688,
+      "loss": 0.2496,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 2.095130681991577,
+      "rewards/margins": 3.073395013809204,
+      "rewards/rejected": -0.9782641530036926,
+      "step": 90
+    },
+    {
+      "epoch": 1.417910447761194,
+      "grad_norm": 22.257616479363563,
+      "learning_rate": 5.859240418356614e-07,
+      "logits/chosen": -2.0160460472106934,
+      "logits/rejected": -1.9418752193450928,
+      "logps/chosen": -225.38796997070312,
+      "logps/rejected": -223.72238159179688,
+      "loss": 0.2431,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 1.8588430881500244,
+      "rewards/margins": 3.6276745796203613,
+      "rewards/rejected": -1.7688310146331787,
+      "step": 95
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "grad_norm": 21.00323840319488,
+      "learning_rate": 5.451706842957421e-07,
+      "logits/chosen": -1.9949266910552979,
+      "logits/rejected": -1.9681007862091064,
+      "logps/chosen": -226.308837890625,
+      "logps/rejected": -214.67807006835938,
+      "loss": 0.2811,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.7654300928115845,
+      "rewards/margins": 3.4513607025146484,
+      "rewards/rejected": -1.6859302520751953,
+      "step": 100
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "eval_logits/chosen": -2.004354476928711,
+      "eval_logits/rejected": -1.935070276260376,
+      "eval_logps/chosen": -261.9532775878906,
+      "eval_logps/rejected": -210.36463928222656,
+      "eval_loss": 0.5120986700057983,
+      "eval_rewards/accuracies": 0.8541666865348816,
+      "eval_rewards/chosen": 1.3770320415496826,
+      "eval_rewards/margins": 2.7112340927124023,
+      "eval_rewards/rejected": -1.3342019319534302,
+      "eval_runtime": 126.4659,
+      "eval_samples_per_second": 15.024,
+      "eval_steps_per_second": 0.237,
+      "step": 100
+    },
+    {
+      "epoch": 1.5671641791044775,
+      "grad_norm": 22.397179602439476,
+      "learning_rate": 5.041119859162068e-07,
+      "logits/chosen": -2.0054097175598145,
+      "logits/rejected": -1.9702081680297852,
+      "logps/chosen": -249.3375701904297,
+      "logps/rejected": -218.004638671875,
+      "loss": 0.2519,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 2.2315516471862793,
+      "rewards/margins": 3.9727096557617188,
+      "rewards/rejected": -1.74115788936615,
+      "step": 105
+    },
+    {
+      "epoch": 1.6417910447761193,
+      "grad_norm": 20.094359300465378,
+      "learning_rate": 4.630254916940423e-07,
+      "logits/chosen": -1.9229028224945068,
+      "logits/rejected": -1.9023786783218384,
+      "logps/chosen": -224.10360717773438,
+      "logps/rejected": -198.1254119873047,
+      "loss": 0.2646,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.7623440027236938,
+      "rewards/margins": 3.4057388305664062,
+      "rewards/rejected": -1.6433947086334229,
+      "step": 110
+    },
+    {
+      "epoch": 1.716417910447761,
+      "grad_norm": 21.24809202102134,
+      "learning_rate": 4.2218893451814e-07,
+      "logits/chosen": -1.9529317617416382,
+      "logits/rejected": -1.9107424020767212,
+      "logps/chosen": -237.7430877685547,
+      "logps/rejected": -229.7592315673828,
+      "loss": 0.2487,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": 1.7564747333526611,
+      "rewards/margins": 3.5565059185028076,
+      "rewards/rejected": -1.800031304359436,
+      "step": 115
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "grad_norm": 20.483863352494325,
+      "learning_rate": 3.8187835777481375e-07,
+      "logits/chosen": -2.03513240814209,
+      "logits/rejected": -2.012155055999756,
+      "logps/chosen": -255.811279296875,
+      "logps/rejected": -215.11550903320312,
+      "loss": 0.2907,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.8352388143539429,
+      "rewards/margins": 3.5237317085266113,
+      "rewards/rejected": -1.688493013381958,
+      "step": 120
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 21.267003087310385,
+      "learning_rate": 3.423662493738687e-07,
+      "logits/chosen": -2.090149402618408,
+      "logits/rejected": -2.037410259246826,
+      "logps/chosen": -224.0563201904297,
+      "logps/rejected": -232.9271697998047,
+      "loss": 0.2537,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.5230239629745483,
+      "rewards/margins": 3.965744733810425,
+      "rewards/rejected": -2.442720651626587,
+      "step": 125
+    },
+    {
+      "epoch": 1.9402985074626866,
+      "grad_norm": 19.665426167854065,
+      "learning_rate": 3.039196998086687e-07,
+      "logits/chosen": -2.119109630584717,
+      "logits/rejected": -2.0918455123901367,
+      "logps/chosen": -218.8955078125,
+      "logps/rejected": -214.98388671875,
+      "loss": 0.2703,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 1.6914072036743164,
+      "rewards/margins": 3.2345032691955566,
+      "rewards/rejected": -1.5430960655212402,
+      "step": 130
+    },
+    {
+      "epoch": 2.014925373134328,
+      "grad_norm": 15.333779299159936,
+      "learning_rate": 2.667985967011878e-07,
+      "logits/chosen": -2.1006662845611572,
+      "logits/rejected": -2.1327574253082275,
+      "logps/chosen": -227.55078125,
+      "logps/rejected": -216.8292236328125,
+      "loss": 0.2636,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 1.8686821460723877,
+      "rewards/margins": 3.199751853942871,
+      "rewards/rejected": -1.3310701847076416,
+      "step": 135
+    },
+    {
+      "epoch": 2.08955223880597,
+      "grad_norm": 21.411151288029885,
+      "learning_rate": 2.3125386803640183e-07,
+      "logits/chosen": -2.1000330448150635,
+      "logits/rejected": -2.096583127975464,
+      "logps/chosen": -225.46200561523438,
+      "logps/rejected": -206.5730438232422,
+      "loss": 0.1728,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": 2.2989490032196045,
+      "rewards/margins": 3.712939739227295,
+      "rewards/rejected": -1.4139907360076904,
+      "step": 140
+    },
+    {
+      "epoch": 2.1641791044776117,
+      "grad_norm": 13.508008476385893,
+      "learning_rate": 1.9752578596124952e-07,
+      "logits/chosen": -2.0918757915496826,
+      "logits/rejected": -2.084589958190918,
+      "logps/chosen": -228.3970489501953,
+      "logps/rejected": -231.37820434570312,
+      "loss": 0.1454,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 2.3735086917877197,
+      "rewards/margins": 4.1814985275268555,
+      "rewards/rejected": -1.807989478111267,
+      "step": 145
+    },
+    {
+      "epoch": 2.2388059701492535,
+      "grad_norm": 17.667435726292307,
+      "learning_rate": 1.6584234261399532e-07,
+      "logits/chosen": -2.0861001014709473,
+      "logits/rejected": -2.1118366718292236,
+      "logps/chosen": -228.27438354492188,
+      "logps/rejected": -210.40005493164062,
+      "loss": 0.1518,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 2.1165130138397217,
+      "rewards/margins": 3.9735045433044434,
+      "rewards/rejected": -1.8569917678833008,
+      "step": 150
+    },
+    {
+      "epoch": 2.2388059701492535,
+      "eval_logits/chosen": -2.098158121109009,
+      "eval_logits/rejected": -2.039686918258667,
+      "eval_logps/chosen": -260.8434143066406,
+      "eval_logps/rejected": -209.58831787109375,
+      "eval_loss": 0.5043797492980957,
+      "eval_rewards/accuracies": 0.8541666865348816,
+      "eval_rewards/chosen": 1.4880186319351196,
+      "eval_rewards/margins": 2.744588613510132,
+      "eval_rewards/rejected": -1.2565699815750122,
+      "eval_runtime": 126.9044,
+      "eval_samples_per_second": 14.972,
+      "eval_steps_per_second": 0.236,
+      "step": 150
+    },
+    {
+      "epoch": 2.3134328358208958,
+      "grad_norm": 14.584825419510635,
+      "learning_rate": 1.3641770896292082e-07,
+      "logits/chosen": -2.0857396125793457,
+      "logits/rejected": -2.0918917655944824,
+      "logps/chosen": -248.5997772216797,
+      "logps/rejected": -237.12857055664062,
+      "loss": 0.1395,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": 2.5311789512634277,
+      "rewards/margins": 4.292832851409912,
+      "rewards/rejected": -1.7616539001464844,
+      "step": 155
+    },
+    {
+      "epoch": 2.388059701492537,
+      "grad_norm": 14.909309745253823,
+      "learning_rate": 1.0945078707215221e-07,
+      "logits/chosen": -2.121391534805298,
+      "logits/rejected": -2.058969497680664,
+      "logps/chosen": -240.8168487548828,
+      "logps/rejected": -242.3682861328125,
+      "loss": 0.1418,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 2.222982406616211,
+      "rewards/margins": 4.225098609924316,
+      "rewards/rejected": -2.0021157264709473,
+      "step": 160
+    },
+    {
+      "epoch": 2.4626865671641793,
+      "grad_norm": 21.84821531200421,
+      "learning_rate": 8.512386558088919e-08,
+      "logits/chosen": -2.121065616607666,
+      "logits/rejected": -2.1130306720733643,
+      "logps/chosen": -261.7530517578125,
+      "logps/rejected": -241.3323974609375,
+      "loss": 0.154,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 2.2334556579589844,
+      "rewards/margins": 4.155540943145752,
+      "rewards/rejected": -1.9220850467681885,
+      "step": 165
+    },
+    {
+      "epoch": 2.5373134328358207,
+      "grad_norm": 21.341295540033837,
+      "learning_rate": 6.360138748461013e-08,
+      "logits/chosen": -2.1645936965942383,
+      "logits/rejected": -2.127746105194092,
+      "logps/chosen": -251.10836791992188,
+      "logps/rejected": -253.2220916748047,
+      "loss": 0.1596,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 2.1738197803497314,
+      "rewards/margins": 4.305379390716553,
+      "rewards/rejected": -2.1315596103668213,
+      "step": 170
+    },
+    {
+      "epoch": 2.611940298507463,
+      "grad_norm": 18.659914383245795,
+      "learning_rate": 4.5028838547699346e-08,
+      "logits/chosen": -2.1111814975738525,
+      "logits/rejected": -2.076622486114502,
+      "logps/chosen": -222.6644287109375,
+      "logps/rejected": -234.6880340576172,
+      "loss": 0.1698,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.7883933782577515,
+      "rewards/margins": 4.462481498718262,
+      "rewards/rejected": -2.6740882396698,
+      "step": 175
+    },
+    {
+      "epoch": 2.6865671641791042,
+      "grad_norm": 20.784990616419144,
+      "learning_rate": 2.9531763861505964e-08,
+      "logits/chosen": -2.122183322906494,
+      "logits/rejected": -2.038510799407959,
+      "logps/chosen": -221.64071655273438,
+      "logps/rejected": -208.3445281982422,
+      "loss": 0.1637,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 1.397716999053955,
+      "rewards/margins": 3.8158226013183594,
+      "rewards/rejected": -2.4181056022644043,
+      "step": 180
+    },
+    {
+      "epoch": 2.7611940298507465,
+      "grad_norm": 13.240442052448362,
+      "learning_rate": 1.7214919195619125e-08,
+      "logits/chosen": -2.1085686683654785,
+      "logits/rejected": -2.0911266803741455,
+      "logps/chosen": -237.5169677734375,
+      "logps/rejected": -227.32540893554688,
+      "loss": 0.1418,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 1.997253179550171,
+      "rewards/margins": 4.263888835906982,
+      "rewards/rejected": -2.2666361331939697,
+      "step": 185
+    },
+    {
+      "epoch": 2.835820895522388,
+      "grad_norm": 19.599663846818626,
+      "learning_rate": 8.161562878982398e-09,
+      "logits/chosen": -2.0720620155334473,
+      "logits/rejected": -2.038602113723755,
+      "logps/chosen": -232.0093994140625,
+      "logps/rejected": -199.23355102539062,
+      "loss": 0.1596,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 1.6587365865707397,
+      "rewards/margins": 3.9811177253723145,
+      "rewards/rejected": -2.322380781173706,
+      "step": 190
+    },
+    {
+      "epoch": 2.91044776119403,
+      "grad_norm": 13.085510048513191,
+      "learning_rate": 2.432892997526026e-09,
+      "logits/chosen": -2.1225340366363525,
+      "logits/rejected": -2.0646426677703857,
+      "logps/chosen": -248.36441040039062,
+      "logps/rejected": -275.37506103515625,
+      "loss": 0.1348,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.9732534885406494,
+      "rewards/margins": 4.583985328674316,
+      "rewards/rejected": -2.610731601715088,
+      "step": 195
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "grad_norm": 13.592938607933718,
+      "learning_rate": 6.763371270035457e-11,
+      "logits/chosen": -2.10709810256958,
+      "logits/rejected": -2.0659236907958984,
+      "logps/chosen": -248.839599609375,
+      "logps/rejected": -237.7239532470703,
+      "loss": 0.1381,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 1.9815118312835693,
+      "rewards/margins": 4.483563423156738,
+      "rewards/rejected": -2.502051591873169,
+      "step": 200
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "eval_logits/chosen": -2.107107400894165,
+      "eval_logits/rejected": -2.0472443103790283,
+      "eval_logps/chosen": -264.30224609375,
+      "eval_logps/rejected": -214.93907165527344,
+      "eval_loss": 0.5009533762931824,
+      "eval_rewards/accuracies": 0.8583333492279053,
+      "eval_rewards/chosen": 1.1421351432800293,
+      "eval_rewards/margins": 2.933783769607544,
+      "eval_rewards/rejected": -1.791648507118225,
+      "eval_runtime": 126.3434,
+      "eval_samples_per_second": 15.038,
+      "eval_steps_per_second": 0.237,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "step": 201,
+      "total_flos": 2369906314051584.0,
+      "train_loss": 0.33028975388600457,
+      "train_runtime": 7391.1638,
+      "train_samples_per_second": 6.939,
+      "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:ea50fbc0ecdb429e9b30e98ae8d10c05151dde465b26aa04ef1821bfc43d1d7f
+size 7096