Upload folder using huggingface_hub

README.md

@@ -0,0 +1,80 @@
+---
+library_name: transformers
+license: other
+base_model: llava-hf/llava-v1.6-mistral-7b-hf
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: AA_preference_cosi_new_step10_0_90
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# AA_preference_cosi_new_step10_0_90
+
+This model is a fine-tuned version of [llava-hf/llava-v1.6-mistral-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf) on the AA_preference_cosi_new_step10_0_90 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4606
+- Rewards/chosen: 0.1088
+- Rewards/rejected: -2.5083
+- Rewards/accuracies: 0.7963
+- Rewards/margins: 2.6171
+- Logps/rejected: -247.9763
+- Logps/chosen: -252.3918
+- Logits/rejected: -2.0273
+- Logits/chosen: -2.0758
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5991        | 0.4158 | 50   | 0.5701          | 1.0641         | 0.0162           | 0.7199             | 1.0479          | -222.7316      | -242.8391    | -2.2582         | -2.2788       |
+| 0.4822        | 0.8316 | 100  | 0.4792          | 0.2741         | -1.4181          | 0.7708             | 1.6922          | -237.0740      | -250.7390    | -2.2864         | -2.3142       |
+| 0.2575        | 1.2474 | 150  | 0.4869          | 0.5197         | -1.5659          | 0.7731             | 2.0855          | -238.5522      | -248.2833    | -2.1810         | -2.2088       |
+| 0.2918        | 1.6632 | 200  | 0.4748          | 0.6541         | -1.5052          | 0.7894             | 2.1593          | -237.9451      | -246.9389    | -2.1041         | -2.1397       |
+| 0.1553        | 2.0790 | 250  | 0.4500          | 0.2460         | -2.1200          | 0.7917             | 2.3660          | -244.0935      | -251.0200    | -2.0244         | -2.0690       |
+| 0.1681        | 2.4948 | 300  | 0.4637          | 0.1908         | -2.3560          | 0.7917             | 2.5468          | -246.4534      | -251.5723    | -2.0304         | -2.0780       |
+| 0.2027        | 2.9106 | 350  | 0.4606          | 0.1105         | -2.5095          | 0.7940             | 2.6200          | -247.9879      | -252.3748    | -2.0270         | -2.0755       |
+
+
+### 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": 2.993762993762994,
+    "eval_logits/chosen": -2.0757534503936768,
+    "eval_logits/rejected": -2.0273303985595703,
+    "eval_logps/chosen": -252.39178466796875,
+    "eval_logps/rejected": -247.9762725830078,
+    "eval_loss": 0.460649311542511,
+    "eval_rewards/accuracies": 0.7962962985038757,
+    "eval_rewards/chosen": 0.10880651324987411,
+    "eval_rewards/margins": 2.6171069145202637,
+    "eval_rewards/rejected": -2.508300304412842,
+    "eval_runtime": 226.7432,
+    "eval_samples_per_second": 15.083,
+    "eval_steps_per_second": 0.238,
+    "total_flos": 4244978440077312.0,
+    "train_loss": 0.3317935415440135,
+    "train_runtime": 13850.2535,
+    "train_samples_per_second": 6.665,
+    "train_steps_per_second": 0.026
+}

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": 2.993762993762994,
+    "eval_logits/chosen": -2.0757534503936768,
+    "eval_logits/rejected": -2.0273303985595703,
+    "eval_logps/chosen": -252.39178466796875,
+    "eval_logps/rejected": -247.9762725830078,
+    "eval_loss": 0.460649311542511,
+    "eval_rewards/accuracies": 0.7962962985038757,
+    "eval_rewards/chosen": 0.10880651324987411,
+    "eval_rewards/margins": 2.6171069145202637,
+    "eval_rewards/rejected": -2.508300304412842,
+    "eval_runtime": 226.7432,
+    "eval_samples_per_second": 15.083,
+    "eval_steps_per_second": 0.238
+}

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 sha256:73c87f22a5cffc627a09c35bf0e59637097da176ea4bcb0e8176d5a2291c1fc8
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b158c10ef3860ab6973670699aba46735b0a1dfaf02992392ff2534b0d679bce
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:815bdcefc544745818a73223058c294761c2e60384ed8858e8b1900b4bf173ee
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c814cc92220a4f059d94355c236d8bbd6732917e1cd059b1511707827c4a36
+size 380134008

model.safetensors.index.json

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

preprocessor_config.json

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

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.993762993762994,
+    "total_flos": 4244978440077312.0,
+    "train_loss": 0.3317935415440135,
+    "train_runtime": 13850.2535,
+    "train_samples_per_second": 6.665,
+    "train_steps_per_second": 0.026
+}

trainer_log.jsonl

@@ -0,0 +1,80 @@
+{"current_steps": 5, "total_steps": 360, "loss": 0.6915, "accuracy": 0.35624998807907104, "learning_rate": 5e-07, "epoch": 0.04158004158004158, "percentage": 1.39, "elapsed_time": "0:02:53", "remaining_time": "3:24:59"}
+{"current_steps": 10, "total_steps": 360, "loss": 0.65, "accuracy": 0.6937500238418579, "learning_rate": 1e-06, "epoch": 0.08316008316008316, "percentage": 2.78, "elapsed_time": "0:05:42", "remaining_time": "3:19:46"}
+{"current_steps": 15, "total_steps": 360, "loss": 0.6685, "accuracy": 0.668749988079071, "learning_rate": 9.994965332706572e-07, "epoch": 0.12474012474012475, "percentage": 4.17, "elapsed_time": "0:08:30", "remaining_time": "3:15:48"}
+{"current_steps": 20, "total_steps": 360, "loss": 0.6267, "accuracy": 0.6812499761581421, "learning_rate": 9.979871469976195e-07, "epoch": 0.16632016632016633, "percentage": 5.56, "elapsed_time": "0:11:18", "remaining_time": "3:12:12"}
+{"current_steps": 25, "total_steps": 360, "loss": 0.6521, "accuracy": 0.550000011920929, "learning_rate": 9.954748808839674e-07, "epoch": 0.2079002079002079, "percentage": 6.94, "elapsed_time": "0:14:06", "remaining_time": "3:09:06"}
+{"current_steps": 30, "total_steps": 360, "loss": 0.5948, "accuracy": 0.6937500238418579, "learning_rate": 9.919647942993147e-07, "epoch": 0.2494802494802495, "percentage": 8.33, "elapsed_time": "0:16:54", "remaining_time": "3:06:01"}
+{"current_steps": 35, "total_steps": 360, "loss": 0.5831, "accuracy": 0.6625000238418579, "learning_rate": 9.874639560909118e-07, "epoch": 0.2910602910602911, "percentage": 9.72, "elapsed_time": "0:19:42", "remaining_time": "3:03:00"}
+{"current_steps": 40, "total_steps": 360, "loss": 0.6182, "accuracy": 0.668749988079071, "learning_rate": 9.819814303479267e-07, "epoch": 0.33264033264033266, "percentage": 11.11, "elapsed_time": "0:22:31", "remaining_time": "3:00:09"}
+{"current_steps": 45, "total_steps": 360, "loss": 0.5829, "accuracy": 0.768750011920929, "learning_rate": 9.755282581475767e-07, "epoch": 0.37422037422037424, "percentage": 12.5, "elapsed_time": "0:25:19", "remaining_time": "2:57:15"}
+{"current_steps": 50, "total_steps": 360, "loss": 0.5991, "accuracy": 0.768750011920929, "learning_rate": 9.681174353198686e-07, "epoch": 0.4158004158004158, "percentage": 13.89, "elapsed_time": "0:28:06", "remaining_time": "2:54:17"}
+{"current_steps": 50, "total_steps": 360, "eval_loss": 0.5700664520263672, "epoch": 0.4158004158004158, "percentage": 13.89, "elapsed_time": "0:31:54", "remaining_time": "3:17:50"}
+{"current_steps": 55, "total_steps": 360, "loss": 0.5861, "accuracy": 0.7749999761581421, "learning_rate": 9.597638862757253e-07, "epoch": 0.4573804573804574, "percentage": 15.28, "elapsed_time": "0:34:43", "remaining_time": "3:12:33"}
+{"current_steps": 60, "total_steps": 360, "loss": 0.6042, "accuracy": 0.706250011920929, "learning_rate": 9.504844339512094e-07, "epoch": 0.498960498960499, "percentage": 16.67, "elapsed_time": "0:37:30", "remaining_time": "3:07:34"}
+{"current_steps": 65, "total_steps": 360, "loss": 0.5768, "accuracy": 0.800000011920929, "learning_rate": 9.402977659283689e-07, "epoch": 0.5405405405405406, "percentage": 18.06, "elapsed_time": "0:40:17", "remaining_time": "3:02:53"}
+{"current_steps": 70, "total_steps": 360, "loss": 0.553, "accuracy": 0.8187500238418579, "learning_rate": 9.29224396800933e-07, "epoch": 0.5821205821205822, "percentage": 19.44, "elapsed_time": "0:43:06", "remaining_time": "2:58:35"}
+{"current_steps": 75, "total_steps": 360, "loss": 0.5715, "accuracy": 0.7562500238418579, "learning_rate": 9.172866268606513e-07, "epoch": 0.6237006237006237, "percentage": 20.83, "elapsed_time": "0:45:56", "remaining_time": "2:54:34"}
+{"current_steps": 80, "total_steps": 360, "loss": 0.521, "accuracy": 0.7875000238418579, "learning_rate": 9.045084971874737e-07, "epoch": 0.6652806652806653, "percentage": 22.22, "elapsed_time": "0:48:45", "remaining_time": "2:50:38"}
+{"current_steps": 85, "total_steps": 360, "loss": 0.5316, "accuracy": 0.78125, "learning_rate": 8.909157412340149e-07, "epoch": 0.7068607068607069, "percentage": 23.61, "elapsed_time": "0:51:33", "remaining_time": "2:46:48"}
+{"current_steps": 90, "total_steps": 360, "loss": 0.4841, "accuracy": 0.8374999761581421, "learning_rate": 8.765357330018055e-07, "epoch": 0.7484407484407485, "percentage": 25.0, "elapsed_time": "0:54:22", "remaining_time": "2:43:07"}
+{"current_steps": 95, "total_steps": 360, "loss": 0.5302, "accuracy": 0.7749999761581421, "learning_rate": 8.613974319136957e-07, "epoch": 0.7900207900207901, "percentage": 26.39, "elapsed_time": "0:57:12", "remaining_time": "2:39:35"}
+{"current_steps": 100, "total_steps": 360, "loss": 0.4822, "accuracy": 0.7749999761581421, "learning_rate": 8.455313244934324e-07, "epoch": 0.8316008316008316, "percentage": 27.78, "elapsed_time": "1:00:01", "remaining_time": "2:36:04"}
+{"current_steps": 100, "total_steps": 360, "eval_loss": 0.47921186685562134, "epoch": 0.8316008316008316, "percentage": 27.78, "elapsed_time": "1:03:49", "remaining_time": "2:45:55"}
+{"current_steps": 105, "total_steps": 360, "loss": 0.4906, "accuracy": 0.7875000238418579, "learning_rate": 8.289693629698563e-07, "epoch": 0.8731808731808732, "percentage": 29.17, "elapsed_time": "1:07:07", "remaining_time": "2:43:01"}
+{"current_steps": 110, "total_steps": 360, "loss": 0.5116, "accuracy": 0.8125, "learning_rate": 8.117449009293668e-07, "epoch": 0.9147609147609148, "percentage": 30.56, "elapsed_time": "1:09:56", "remaining_time": "2:38:58"}
+{"current_steps": 115, "total_steps": 360, "loss": 0.5512, "accuracy": 0.737500011920929, "learning_rate": 7.938926261462365e-07, "epoch": 0.9563409563409564, "percentage": 31.94, "elapsed_time": "1:12:45", "remaining_time": "2:35:00"}
+{"current_steps": 120, "total_steps": 360, "loss": 0.5079, "accuracy": 0.8125, "learning_rate": 7.754484907260512e-07, "epoch": 0.997920997920998, "percentage": 33.33, "elapsed_time": "1:15:34", "remaining_time": "2:31:09"}
+{"current_steps": 125, "total_steps": 360, "loss": 0.2517, "accuracy": 0.8812500238418579, "learning_rate": 7.564496387029531e-07, "epoch": 1.0395010395010396, "percentage": 34.72, "elapsed_time": "1:18:22", "remaining_time": "2:27:20"}
+{"current_steps": 130, "total_steps": 360, "loss": 0.2685, "accuracy": 0.90625, "learning_rate": 7.369343312364993e-07, "epoch": 1.0810810810810811, "percentage": 36.11, "elapsed_time": "1:21:10", "remaining_time": "2:23:37"}
+{"current_steps": 135, "total_steps": 360, "loss": 0.21, "accuracy": 0.918749988079071, "learning_rate": 7.16941869558779e-07, "epoch": 1.1226611226611227, "percentage": 37.5, "elapsed_time": "1:24:01", "remaining_time": "2:20:02"}
+{"current_steps": 140, "total_steps": 360, "loss": 0.2644, "accuracy": 0.9312499761581421, "learning_rate": 6.965125158269618e-07, "epoch": 1.1642411642411643, "percentage": 38.89, "elapsed_time": "1:26:48", "remaining_time": "2:16:24"}
+{"current_steps": 145, "total_steps": 360, "loss": 0.2391, "accuracy": 0.956250011920929, "learning_rate": 6.756874120406714e-07, "epoch": 1.2058212058212059, "percentage": 40.28, "elapsed_time": "1:29:37", "remaining_time": "2:12:53"}
+{"current_steps": 150, "total_steps": 360, "loss": 0.2575, "accuracy": 0.8812500238418579, "learning_rate": 6.545084971874736e-07, "epoch": 1.2474012474012475, "percentage": 41.67, "elapsed_time": "1:32:26", "remaining_time": "2:09:25"}
+{"current_steps": 150, "total_steps": 360, "eval_loss": 0.4868723452091217, "epoch": 1.2474012474012475, "percentage": 41.67, "elapsed_time": "1:36:14", "remaining_time": "2:14:44"}
+{"current_steps": 155, "total_steps": 360, "loss": 0.2452, "accuracy": 0.918749988079071, "learning_rate": 6.330184227833375e-07, "epoch": 1.288981288981289, "percentage": 43.06, "elapsed_time": "1:39:01", "remaining_time": "2:10:58"}
+{"current_steps": 160, "total_steps": 360, "loss": 0.2569, "accuracy": 0.956250011920929, "learning_rate": 6.112604669781572e-07, "epoch": 1.3305613305613306, "percentage": 44.44, "elapsed_time": "1:41:50", "remaining_time": "2:07:17"}
+{"current_steps": 165, "total_steps": 360, "loss": 0.2213, "accuracy": 0.925000011920929, "learning_rate": 5.892784473993183e-07, "epoch": 1.3721413721413722, "percentage": 45.83, "elapsed_time": "1:44:38", "remaining_time": "2:03:39"}
+{"current_steps": 170, "total_steps": 360, "loss": 0.2751, "accuracy": 0.925000011920929, "learning_rate": 5.671166329088277e-07, "epoch": 1.4137214137214138, "percentage": 47.22, "elapsed_time": "1:47:25", "remaining_time": "2:00:04"}
+{"current_steps": 175, "total_steps": 360, "loss": 0.2936, "accuracy": 0.887499988079071, "learning_rate": 5.448196544517167e-07, "epoch": 1.4553014553014554, "percentage": 48.61, "elapsed_time": "1:50:14", "remaining_time": "1:56:32"}
+{"current_steps": 180, "total_steps": 360, "loss": 0.3075, "accuracy": 0.90625, "learning_rate": 5.224324151752575e-07, "epoch": 1.496881496881497, "percentage": 50.0, "elapsed_time": "1:53:02", "remaining_time": "1:53:02"}
+{"current_steps": 185, "total_steps": 360, "loss": 0.2867, "accuracy": 0.918749988079071, "learning_rate": 5e-07, "epoch": 1.5384615384615383, "percentage": 51.39, "elapsed_time": "1:55:53", "remaining_time": "1:49:37"}
+{"current_steps": 190, "total_steps": 360, "loss": 0.2762, "accuracy": 0.9437500238418579, "learning_rate": 4.775675848247427e-07, "epoch": 1.5800415800415801, "percentage": 52.78, "elapsed_time": "1:58:42", "remaining_time": "1:46:12"}
+{"current_steps": 195, "total_steps": 360, "loss": 0.2972, "accuracy": 0.90625, "learning_rate": 4.5518034554828327e-07, "epoch": 1.6216216216216215, "percentage": 54.17, "elapsed_time": "2:01:31", "remaining_time": "1:42:49"}
+{"current_steps": 200, "total_steps": 360, "loss": 0.2918, "accuracy": 0.862500011920929, "learning_rate": 4.328833670911724e-07, "epoch": 1.6632016632016633, "percentage": 55.56, "elapsed_time": "2:04:19", "remaining_time": "1:39:27"}
+{"current_steps": 200, "total_steps": 360, "eval_loss": 0.47476285696029663, "epoch": 1.6632016632016633, "percentage": 55.56, "elapsed_time": "2:08:07", "remaining_time": "1:42:29"}
+{"current_steps": 205, "total_steps": 360, "loss": 0.2589, "accuracy": 0.8999999761581421, "learning_rate": 4.107215526006817e-07, "epoch": 1.7047817047817047, "percentage": 56.94, "elapsed_time": "2:11:25", "remaining_time": "1:39:22"}
+{"current_steps": 210, "total_steps": 360, "loss": 0.2871, "accuracy": 0.8812500238418579, "learning_rate": 3.8873953302184283e-07, "epoch": 1.7463617463617465, "percentage": 58.33, "elapsed_time": "2:14:13", "remaining_time": "1:35:52"}
+{"current_steps": 215, "total_steps": 360, "loss": 0.2941, "accuracy": 0.925000011920929, "learning_rate": 3.669815772166625e-07, "epoch": 1.7879417879417878, "percentage": 59.72, "elapsed_time": "2:17:02", "remaining_time": "1:32:25"}
+{"current_steps": 220, "total_steps": 360, "loss": 0.2762, "accuracy": 0.893750011920929, "learning_rate": 3.454915028125263e-07, "epoch": 1.8295218295218296, "percentage": 61.11, "elapsed_time": "2:19:50", "remaining_time": "1:28:59"}
+{"current_steps": 225, "total_steps": 360, "loss": 0.2515, "accuracy": 0.9312499761581421, "learning_rate": 3.243125879593286e-07, "epoch": 1.871101871101871, "percentage": 62.5, "elapsed_time": "2:22:39", "remaining_time": "1:25:35"}
+{"current_steps": 230, "total_steps": 360, "loss": 0.2611, "accuracy": 0.8812500238418579, "learning_rate": 3.034874841730382e-07, "epoch": 1.9126819126819128, "percentage": 63.89, "elapsed_time": "2:25:27", "remaining_time": "1:22:12"}
+{"current_steps": 235, "total_steps": 360, "loss": 0.2666, "accuracy": 0.8999999761581421, "learning_rate": 2.8305813044122093e-07, "epoch": 1.9542619542619541, "percentage": 65.28, "elapsed_time": "2:28:15", "remaining_time": "1:18:51"}
+{"current_steps": 240, "total_steps": 360, "loss": 0.2917, "accuracy": 0.831250011920929, "learning_rate": 2.6306566876350067e-07, "epoch": 1.995841995841996, "percentage": 66.67, "elapsed_time": "2:31:04", "remaining_time": "1:15:32"}
+{"current_steps": 245, "total_steps": 360, "loss": 0.1651, "accuracy": 0.918749988079071, "learning_rate": 2.4355036129704696e-07, "epoch": 2.0374220374220373, "percentage": 68.06, "elapsed_time": "2:33:51", "remaining_time": "1:12:13"}
+{"current_steps": 250, "total_steps": 360, "loss": 0.1553, "accuracy": 0.956250011920929, "learning_rate": 2.2455150927394878e-07, "epoch": 2.079002079002079, "percentage": 69.44, "elapsed_time": "2:36:39", "remaining_time": "1:08:55"}
+{"current_steps": 250, "total_steps": 360, "eval_loss": 0.4500342309474945, "epoch": 2.079002079002079, "percentage": 69.44, "elapsed_time": "2:40:27", "remaining_time": "1:10:36"}
+{"current_steps": 255, "total_steps": 360, "loss": 0.1469, "accuracy": 0.9624999761581421, "learning_rate": 2.0610737385376348e-07, "epoch": 2.1205821205821205, "percentage": 70.83, "elapsed_time": "2:43:15", "remaining_time": "1:07:13"}
+{"current_steps": 260, "total_steps": 360, "loss": 0.1396, "accuracy": 0.987500011920929, "learning_rate": 1.8825509907063326e-07, "epoch": 2.1621621621621623, "percentage": 72.22, "elapsed_time": "2:46:04", "remaining_time": "1:03:52"}
+{"current_steps": 265, "total_steps": 360, "loss": 0.1486, "accuracy": 0.925000011920929, "learning_rate": 1.710306370301437e-07, "epoch": 2.2037422037422036, "percentage": 73.61, "elapsed_time": "2:48:53", "remaining_time": "1:00:32"}
+{"current_steps": 270, "total_steps": 360, "loss": 0.1582, "accuracy": 0.9437500238418579, "learning_rate": 1.5446867550656767e-07, "epoch": 2.2453222453222454, "percentage": 75.0, "elapsed_time": "2:51:43", "remaining_time": "0:57:14"}
+{"current_steps": 275, "total_steps": 360, "loss": 0.1695, "accuracy": 0.9437500238418579, "learning_rate": 1.3860256808630427e-07, "epoch": 2.286902286902287, "percentage": 76.39, "elapsed_time": "2:54:32", "remaining_time": "0:53:57"}
+{"current_steps": 280, "total_steps": 360, "loss": 0.1458, "accuracy": 0.9437500238418579, "learning_rate": 1.2346426699819456e-07, "epoch": 2.3284823284823286, "percentage": 77.78, "elapsed_time": "2:57:21", "remaining_time": "0:50:40"}
+{"current_steps": 285, "total_steps": 360, "loss": 0.1381, "accuracy": 0.9375, "learning_rate": 1.090842587659851e-07, "epoch": 2.37006237006237, "percentage": 79.17, "elapsed_time": "3:00:10", "remaining_time": "0:47:24"}
+{"current_steps": 290, "total_steps": 360, "loss": 0.1704, "accuracy": 0.9437500238418579, "learning_rate": 9.549150281252632e-08, "epoch": 2.4116424116424118, "percentage": 80.56, "elapsed_time": "3:02:58", "remaining_time": "0:44:09"}
+{"current_steps": 295, "total_steps": 360, "loss": 0.1352, "accuracy": 0.9624999761581421, "learning_rate": 8.271337313934867e-08, "epoch": 2.453222453222453, "percentage": 81.94, "elapsed_time": "3:05:45", "remaining_time": "0:40:55"}
+{"current_steps": 300, "total_steps": 360, "loss": 0.1681, "accuracy": 0.949999988079071, "learning_rate": 7.077560319906694e-08, "epoch": 2.494802494802495, "percentage": 83.33, "elapsed_time": "3:08:33", "remaining_time": "0:37:42"}
+{"current_steps": 300, "total_steps": 360, "eval_loss": 0.4636799395084381, "epoch": 2.494802494802495, "percentage": 83.33, "elapsed_time": "3:12:21", "remaining_time": "0:38:28"}
+{"current_steps": 305, "total_steps": 360, "loss": 0.1636, "accuracy": 0.949999988079071, "learning_rate": 5.9702234071631e-08, "epoch": 2.5363825363825363, "percentage": 84.72, "elapsed_time": "3:15:39", "remaining_time": "0:35:16"}
+{"current_steps": 310, "total_steps": 360, "loss": 0.1442, "accuracy": 0.9437500238418579, "learning_rate": 4.951556604879048e-08, "epoch": 2.577962577962578, "percentage": 86.11, "elapsed_time": "3:18:27", "remaining_time": "0:32:00"}
+{"current_steps": 315, "total_steps": 360, "loss": 0.1422, "accuracy": 0.9437500238418579, "learning_rate": 4.023611372427471e-08, "epoch": 2.6195426195426195, "percentage": 87.5, "elapsed_time": "3:21:14", "remaining_time": "0:28:44"}
+{"current_steps": 320, "total_steps": 360, "loss": 0.1407, "accuracy": 0.9375, "learning_rate": 3.188256468013139e-08, "epoch": 2.6611226611226613, "percentage": 88.89, "elapsed_time": "3:24:03", "remaining_time": "0:25:30"}
+{"current_steps": 325, "total_steps": 360, "loss": 0.1424, "accuracy": 0.981249988079071, "learning_rate": 2.4471741852423233e-08, "epoch": 2.7027027027027026, "percentage": 90.28, "elapsed_time": "3:26:50", "remaining_time": "0:22:16"}
+{"current_steps": 330, "total_steps": 360, "loss": 0.1487, "accuracy": 0.9375, "learning_rate": 1.8018569652073378e-08, "epoch": 2.7442827442827444, "percentage": 91.67, "elapsed_time": "3:29:38", "remaining_time": "0:19:03"}
+{"current_steps": 335, "total_steps": 360, "loss": 0.157, "accuracy": 0.96875, "learning_rate": 1.253604390908819e-08, "epoch": 2.785862785862786, "percentage": 93.06, "elapsed_time": "3:32:27", "remaining_time": "0:15:51"}
+{"current_steps": 340, "total_steps": 360, "loss": 0.1622, "accuracy": 0.9375, "learning_rate": 8.035205700685165e-09, "epoch": 2.8274428274428276, "percentage": 94.44, "elapsed_time": "3:35:15", "remaining_time": "0:12:39"}
+{"current_steps": 345, "total_steps": 360, "loss": 0.1463, "accuracy": 0.96875, "learning_rate": 4.5251191160326495e-09, "epoch": 2.869022869022869, "percentage": 95.83, "elapsed_time": "3:38:04", "remaining_time": "0:09:28"}
+{"current_steps": 350, "total_steps": 360, "loss": 0.2027, "accuracy": 0.925000011920929, "learning_rate": 2.0128530023804656e-09, "epoch": 2.9106029106029108, "percentage": 97.22, "elapsed_time": "3:40:52", "remaining_time": "0:06:18"}
+{"current_steps": 350, "total_steps": 360, "eval_loss": 0.46064791083335876, "epoch": 2.9106029106029108, "percentage": 97.22, "elapsed_time": "3:44:40", "remaining_time": "0:06:25"}
+{"current_steps": 355, "total_steps": 360, "loss": 0.1491, "accuracy": 0.8999999761581421, "learning_rate": 5.034667293427053e-10, "epoch": 2.952182952182952, "percentage": 98.61, "elapsed_time": "3:47:29", "remaining_time": "0:03:12"}
+{"current_steps": 360, "total_steps": 360, "loss": 0.1508, "accuracy": 0.956250011920929, "learning_rate": 0.0, "epoch": 2.993762993762994, "percentage": 100.0, "elapsed_time": "3:50:16", "remaining_time": "0:00:00"}
+{"current_steps": 360, "total_steps": 360, "epoch": 2.993762993762994, "percentage": 100.0, "elapsed_time": "3:50:48", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1234 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.993762993762994,
+  "eval_steps": 50,
+  "global_step": 360,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04158004158004158,
+      "grad_norm": 54.37076298007274,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.713756561279297,
+      "logits/rejected": -2.7325329780578613,
+      "logps/chosen": -255.3134307861328,
+      "logps/rejected": -212.7609405517578,
+      "loss": 0.6915,
+      "rewards/accuracies": 0.35624998807907104,
+      "rewards/chosen": 0.01350476872175932,
+      "rewards/margins": 0.005657805595546961,
+      "rewards/rejected": 0.007846963591873646,
+      "step": 5
+    },
+    {
+      "epoch": 0.08316008316008316,
+      "grad_norm": 76.9573578816108,
+      "learning_rate": 1e-06,
+      "logits/chosen": -2.6956191062927246,
+      "logits/rejected": -2.6987128257751465,
+      "logps/chosen": -263.4132385253906,
+      "logps/rejected": -229.77084350585938,
+      "loss": 0.65,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": 0.5041084885597229,
+      "rewards/margins": 0.15891990065574646,
+      "rewards/rejected": 0.34518855810165405,
+      "step": 10
+    },
+    {
+      "epoch": 0.12474012474012475,
+      "grad_norm": 51.75777652370901,
+      "learning_rate": 9.994965332706572e-07,
+      "logits/chosen": -2.6011486053466797,
+      "logits/rejected": -2.5905685424804688,
+      "logps/chosen": -244.81539916992188,
+      "logps/rejected": -204.1315460205078,
+      "loss": 0.6685,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": 1.3856022357940674,
+      "rewards/margins": 0.6152002215385437,
+      "rewards/rejected": 0.7704019546508789,
+      "step": 15
+    },
+    {
+      "epoch": 0.16632016632016633,
+      "grad_norm": 57.21047514820573,
+      "learning_rate": 9.979871469976195e-07,
+      "logits/chosen": -2.5031514167785645,
+      "logits/rejected": -2.4860281944274902,
+      "logps/chosen": -259.409912109375,
+      "logps/rejected": -219.88015747070312,
+      "loss": 0.6267,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": 1.566732406616211,
+      "rewards/margins": 1.105370283126831,
+      "rewards/rejected": 0.4613622725009918,
+      "step": 20
+    },
+    {
+      "epoch": 0.2079002079002079,
+      "grad_norm": 41.637159789331015,
+      "learning_rate": 9.954748808839674e-07,
+      "logits/chosen": -2.3722968101501465,
+      "logits/rejected": -2.359870195388794,
+      "logps/chosen": -235.3915252685547,
+      "logps/rejected": -216.30117797851562,
+      "loss": 0.6521,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": 1.2608864307403564,
+      "rewards/margins": 0.3079569935798645,
+      "rewards/rejected": 0.9529293775558472,
+      "step": 25
+    },
+    {
+      "epoch": 0.2494802494802495,
+      "grad_norm": 36.54823945023964,
+      "learning_rate": 9.919647942993147e-07,
+      "logits/chosen": -2.390732765197754,
+      "logits/rejected": -2.3800339698791504,
+      "logps/chosen": -236.30908203125,
+      "logps/rejected": -201.73260498046875,
+      "loss": 0.5948,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": 1.547703504562378,
+      "rewards/margins": 0.9216065406799316,
+      "rewards/rejected": 0.6260967254638672,
+      "step": 30
+    },
+    {
+      "epoch": 0.2910602910602911,
+      "grad_norm": 35.49805196967732,
+      "learning_rate": 9.874639560909118e-07,
+      "logits/chosen": -2.4424479007720947,
+      "logits/rejected": -2.4472975730895996,
+      "logps/chosen": -237.1094207763672,
+      "logps/rejected": -213.6556854248047,
+      "loss": 0.5831,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.9917442202568054,
+      "rewards/margins": 0.7290633320808411,
+      "rewards/rejected": 0.2626809775829315,
+      "step": 35
+    },
+    {
+      "epoch": 0.33264033264033266,
+      "grad_norm": 42.53155079418441,
+      "learning_rate": 9.819814303479267e-07,
+      "logits/chosen": -2.5173354148864746,
+      "logits/rejected": -2.5085394382476807,
+      "logps/chosen": -252.16220092773438,
+      "logps/rejected": -205.01742553710938,
+      "loss": 0.6182,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": 0.5249898433685303,
+      "rewards/margins": 0.7051706314086914,
+      "rewards/rejected": -0.18018092215061188,
+      "step": 40
+    },
+    {
+      "epoch": 0.37422037422037424,
+      "grad_norm": 38.9354275651786,
+      "learning_rate": 9.755282581475767e-07,
+      "logits/chosen": -2.4824609756469727,
+      "logits/rejected": -2.475179433822632,
+      "logps/chosen": -239.98574829101562,
+      "logps/rejected": -192.90554809570312,
+      "loss": 0.5829,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": 1.0752050876617432,
+      "rewards/margins": 1.0579692125320435,
+      "rewards/rejected": 0.017235904932022095,
+      "step": 45
+    },
+    {
+      "epoch": 0.4158004158004158,
+      "grad_norm": 39.48744249206175,
+      "learning_rate": 9.681174353198686e-07,
+      "logits/chosen": -2.3598358631134033,
+      "logits/rejected": -2.3516647815704346,
+      "logps/chosen": -226.94308471679688,
+      "logps/rejected": -197.4553680419922,
+      "loss": 0.5991,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": 1.1579209566116333,
+      "rewards/margins": 1.1758655309677124,
+      "rewards/rejected": -0.01794450543820858,
+      "step": 50
+    },
+    {
+      "epoch": 0.4158004158004158,
+      "eval_logits/chosen": -2.278756856918335,
+      "eval_logits/rejected": -2.258207082748413,
+      "eval_logps/chosen": -242.83909606933594,
+      "eval_logps/rejected": -222.73158264160156,
+      "eval_loss": 0.5700664520263672,
+      "eval_rewards/accuracies": 0.7199074029922485,
+      "eval_rewards/chosen": 1.06407630443573,
+      "eval_rewards/margins": 1.0479047298431396,
+      "eval_rewards/rejected": 0.016171585768461227,
+      "eval_runtime": 227.8559,
+      "eval_samples_per_second": 15.009,
+      "eval_steps_per_second": 0.237,
+      "step": 50
+    },
+    {
+      "epoch": 0.4573804573804574,
+      "grad_norm": 58.02646284889146,
+      "learning_rate": 9.597638862757253e-07,
+      "logits/chosen": -2.226616382598877,
+      "logits/rejected": -2.2312285900115967,
+      "logps/chosen": -251.00244140625,
+      "logps/rejected": -202.50601196289062,
+      "loss": 0.5861,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.9385547637939453,
+      "rewards/margins": 1.0976479053497314,
+      "rewards/rejected": -0.15909315645694733,
+      "step": 55
+    },
+    {
+      "epoch": 0.498960498960499,
+      "grad_norm": 38.695181290677844,
+      "learning_rate": 9.504844339512094e-07,
+      "logits/chosen": -2.289625644683838,
+      "logits/rejected": -2.2505855560302734,
+      "logps/chosen": -241.419921875,
+      "logps/rejected": -226.2331085205078,
+      "loss": 0.6042,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": 0.7523998022079468,
+      "rewards/margins": 1.1783866882324219,
+      "rewards/rejected": -0.4259868562221527,
+      "step": 60
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 37.640452345301874,
+      "learning_rate": 9.402977659283689e-07,
+      "logits/chosen": -2.3811450004577637,
+      "logits/rejected": -2.36521053314209,
+      "logps/chosen": -234.2858428955078,
+      "logps/rejected": -204.07333374023438,
+      "loss": 0.5768,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.8714672327041626,
+      "rewards/margins": 1.4110157489776611,
+      "rewards/rejected": -0.5395486950874329,
+      "step": 65
+    },
+    {
+      "epoch": 0.5821205821205822,
+      "grad_norm": 39.36509358362743,
+      "learning_rate": 9.29224396800933e-07,
+      "logits/chosen": -2.378622055053711,
+      "logits/rejected": -2.3395094871520996,
+      "logps/chosen": -257.758056640625,
+      "logps/rejected": -242.8697509765625,
+      "loss": 0.553,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": 0.6064122319221497,
+      "rewards/margins": 1.7327152490615845,
+      "rewards/rejected": -1.12630295753479,
+      "step": 70
+    },
+    {
+      "epoch": 0.6237006237006237,
+      "grad_norm": 35.183102501453625,
+      "learning_rate": 9.172866268606513e-07,
+      "logits/chosen": -2.374014377593994,
+      "logits/rejected": -2.336141586303711,
+      "logps/chosen": -244.1781005859375,
+      "logps/rejected": -210.8193359375,
+      "loss": 0.5715,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": 0.34850460290908813,
+      "rewards/margins": 1.3979551792144775,
+      "rewards/rejected": -1.0494506359100342,
+      "step": 75
+    },
+    {
+      "epoch": 0.6652806652806653,
+      "grad_norm": 34.301741895867416,
+      "learning_rate": 9.045084971874737e-07,
+      "logits/chosen": -2.350186586380005,
+      "logits/rejected": -2.3284194469451904,
+      "logps/chosen": -251.4392547607422,
+      "logps/rejected": -233.503662109375,
+      "loss": 0.521,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.5821531414985657,
+      "rewards/margins": 1.4417784214019775,
+      "rewards/rejected": -0.8596252202987671,
+      "step": 80
+    },
+    {
+      "epoch": 0.7068607068607069,
+      "grad_norm": 34.61172120511482,
+      "learning_rate": 8.909157412340149e-07,
+      "logits/chosen": -2.2655510902404785,
+      "logits/rejected": -2.239112615585327,
+      "logps/chosen": -279.3992614746094,
+      "logps/rejected": -235.103759765625,
+      "loss": 0.5316,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": 0.4485341012477875,
+      "rewards/margins": 1.9937374591827393,
+      "rewards/rejected": -1.545203447341919,
+      "step": 85
+    },
+    {
+      "epoch": 0.7484407484407485,
+      "grad_norm": 32.81683848375174,
+      "learning_rate": 8.765357330018055e-07,
+      "logits/chosen": -2.2851290702819824,
+      "logits/rejected": -2.261535167694092,
+      "logps/chosen": -268.8089294433594,
+      "logps/rejected": -226.6311492919922,
+      "loss": 0.4841,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": 0.18254558742046356,
+      "rewards/margins": 1.8468830585479736,
+      "rewards/rejected": -1.6643375158309937,
+      "step": 90
+    },
+    {
+      "epoch": 0.7900207900207901,
+      "grad_norm": 31.276848847163553,
+      "learning_rate": 8.613974319136957e-07,
+      "logits/chosen": -2.276081085205078,
+      "logits/rejected": -2.268982410430908,
+      "logps/chosen": -251.25534057617188,
+      "logps/rejected": -237.03457641601562,
+      "loss": 0.5302,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.31729841232299805,
+      "rewards/margins": 2.034406900405884,
+      "rewards/rejected": -1.7171084880828857,
+      "step": 95
+    },
+    {
+      "epoch": 0.8316008316008316,
+      "grad_norm": 30.890611546872623,
+      "learning_rate": 8.455313244934324e-07,
+      "logits/chosen": -2.321735382080078,
+      "logits/rejected": -2.287306547164917,
+      "logps/chosen": -258.73321533203125,
+      "logps/rejected": -233.6432647705078,
+      "loss": 0.4822,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.4251006543636322,
+      "rewards/margins": 1.8721868991851807,
+      "rewards/rejected": -1.447086215019226,
+      "step": 100
+    },
+    {
+      "epoch": 0.8316008316008316,
+      "eval_logits/chosen": -2.314237594604492,
+      "eval_logits/rejected": -2.2864315509796143,
+      "eval_logps/chosen": -250.7389678955078,
+      "eval_logps/rejected": -237.07403564453125,
+      "eval_loss": 0.47921186685562134,
+      "eval_rewards/accuracies": 0.7708333134651184,
+      "eval_rewards/chosen": 0.2740871012210846,
+      "eval_rewards/margins": 1.692162275314331,
+      "eval_rewards/rejected": -1.4180750846862793,
+      "eval_runtime": 227.5143,
+      "eval_samples_per_second": 15.032,
+      "eval_steps_per_second": 0.237,
+      "step": 100
+    },
+    {
+      "epoch": 0.8731808731808732,
+      "grad_norm": 28.25218133644015,
+      "learning_rate": 8.289693629698563e-07,
+      "logits/chosen": -2.2942633628845215,
+      "logits/rejected": -2.24989652633667,
+      "logps/chosen": -244.9521026611328,
+      "logps/rejected": -230.9259490966797,
+      "loss": 0.4906,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.14940057694911957,
+      "rewards/margins": 1.7479984760284424,
+      "rewards/rejected": -1.598597764968872,
+      "step": 105
+    },
+    {
+      "epoch": 0.9147609147609148,
+      "grad_norm": 41.4993187811424,
+      "learning_rate": 8.117449009293668e-07,
+      "logits/chosen": -2.1534812450408936,
+      "logits/rejected": -2.149482011795044,
+      "logps/chosen": -262.1253662109375,
+      "logps/rejected": -229.8566131591797,
+      "loss": 0.5116,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.1877366602420807,
+      "rewards/margins": 1.9870322942733765,
+      "rewards/rejected": -2.1747689247131348,
+      "step": 110
+    },
+    {
+      "epoch": 0.9563409563409564,
+      "grad_norm": 33.56170785485805,
+      "learning_rate": 7.938926261462365e-07,
+      "logits/chosen": -2.1278510093688965,
+      "logits/rejected": -2.1188061237335205,
+      "logps/chosen": -273.69512939453125,
+      "logps/rejected": -229.3671112060547,
+      "loss": 0.5512,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.2501869201660156,
+      "rewards/margins": 1.7830606698989868,
+      "rewards/rejected": -2.033247470855713,
+      "step": 115
+    },
+    {
+      "epoch": 0.997920997920998,
+      "grad_norm": 32.64818540489769,
+      "learning_rate": 7.754484907260512e-07,
+      "logits/chosen": -2.087319850921631,
+      "logits/rejected": -2.05534029006958,
+      "logps/chosen": -282.62884521484375,
+      "logps/rejected": -243.00833129882812,
+      "loss": 0.5079,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.30245959758758545,
+      "rewards/margins": 2.3980941772460938,
+      "rewards/rejected": -2.095634698867798,
+      "step": 120
+    },
+    {
+      "epoch": 1.0395010395010396,
+      "grad_norm": 19.999107925858855,
+      "learning_rate": 7.564496387029531e-07,
+      "logits/chosen": -2.042459487915039,
+      "logits/rejected": -2.0114758014678955,
+      "logps/chosen": -248.462158203125,
+      "logps/rejected": -234.9170684814453,
+      "loss": 0.2517,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": -0.07480224221944809,
+      "rewards/margins": 2.8013529777526855,
+      "rewards/rejected": -2.876155376434326,
+      "step": 125
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 18.062097858523995,
+      "learning_rate": 7.369343312364993e-07,
+      "logits/chosen": -2.0688469409942627,
+      "logits/rejected": -2.0446696281433105,
+      "logps/chosen": -254.21109008789062,
+      "logps/rejected": -226.58352661132812,
+      "loss": 0.2685,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 0.28042837977409363,
+      "rewards/margins": 2.8127834796905518,
+      "rewards/rejected": -2.5323550701141357,
+      "step": 130
+    },
+    {
+      "epoch": 1.1226611226611227,
+      "grad_norm": 14.247798273776342,
+      "learning_rate": 7.16941869558779e-07,
+      "logits/chosen": -2.146953582763672,
+      "logits/rejected": -2.118887424468994,
+      "logps/chosen": -244.89370727539062,
+      "logps/rejected": -237.91537475585938,
+      "loss": 0.21,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 0.407196581363678,
+      "rewards/margins": 3.331601619720459,
+      "rewards/rejected": -2.924405336380005,
+      "step": 135
+    },
+    {
+      "epoch": 1.1642411642411643,
+      "grad_norm": 22.628796395906495,
+      "learning_rate": 6.965125158269618e-07,
+      "logits/chosen": -2.204144239425659,
+      "logits/rejected": -2.1619129180908203,
+      "logps/chosen": -234.0556182861328,
+      "logps/rejected": -218.4832305908203,
+      "loss": 0.2644,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 0.6617838144302368,
+      "rewards/margins": 3.3233935832977295,
+      "rewards/rejected": -2.661609649658203,
+      "step": 140
+    },
+    {
+      "epoch": 1.2058212058212059,
+      "grad_norm": 18.93519878891401,
+      "learning_rate": 6.756874120406714e-07,
+      "logits/chosen": -2.1856284141540527,
+      "logits/rejected": -2.1593949794769287,
+      "logps/chosen": -234.7235565185547,
+      "logps/rejected": -229.6350860595703,
+      "loss": 0.2391,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": 0.9280608892440796,
+      "rewards/margins": 3.3084418773651123,
+      "rewards/rejected": -2.3803811073303223,
+      "step": 145
+    },
+    {
+      "epoch": 1.2474012474012475,
+      "grad_norm": 20.700069764911532,
+      "learning_rate": 6.545084971874736e-07,
+      "logits/chosen": -2.1871914863586426,
+      "logits/rejected": -2.1489927768707275,
+      "logps/chosen": -242.25534057617188,
+      "logps/rejected": -222.1703643798828,
+      "loss": 0.2575,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": 1.060232162475586,
+      "rewards/margins": 3.268009662628174,
+      "rewards/rejected": -2.207777500152588,
+      "step": 150
+    },
+    {
+      "epoch": 1.2474012474012475,
+      "eval_logits/chosen": -2.208766460418701,
+      "eval_logits/rejected": -2.1809799671173096,
+      "eval_logps/chosen": -248.28334045410156,
+      "eval_logps/rejected": -238.55223083496094,
+      "eval_loss": 0.4868723452091217,
+      "eval_rewards/accuracies": 0.7731481194496155,
+      "eval_rewards/chosen": 0.5196511149406433,
+      "eval_rewards/margins": 2.085545539855957,
+      "eval_rewards/rejected": -1.5658944845199585,
+      "eval_runtime": 227.885,
+      "eval_samples_per_second": 15.008,
+      "eval_steps_per_second": 0.237,
+      "step": 150
+    },
+    {
+      "epoch": 1.288981288981289,
+      "grad_norm": 23.745384000015278,
+      "learning_rate": 6.330184227833375e-07,
+      "logits/chosen": -2.2330305576324463,
+      "logits/rejected": -2.1969778537750244,
+      "logps/chosen": -264.57208251953125,
+      "logps/rejected": -239.2760467529297,
+      "loss": 0.2452,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.4050263166427612,
+      "rewards/margins": 3.3950893878936768,
+      "rewards/rejected": -1.9900630712509155,
+      "step": 155
+    },
+    {
+      "epoch": 1.3305613305613306,
+      "grad_norm": 18.063307503658212,
+      "learning_rate": 6.112604669781572e-07,
+      "logits/chosen": -2.244858503341675,
+      "logits/rejected": -2.228745937347412,
+      "logps/chosen": -244.28140258789062,
+      "logps/rejected": -264.75811767578125,
+      "loss": 0.2569,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": 0.9857003092765808,
+      "rewards/margins": 4.130752086639404,
+      "rewards/rejected": -3.1450517177581787,
+      "step": 160
+    },
+    {
+      "epoch": 1.3721413721413722,
+      "grad_norm": 21.533351048166008,
+      "learning_rate": 5.892784473993183e-07,
+      "logits/chosen": -2.2544522285461426,
+      "logits/rejected": -2.2583537101745605,
+      "logps/chosen": -273.48675537109375,
+      "logps/rejected": -261.84027099609375,
+      "loss": 0.2213,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.1246474981307983,
+      "rewards/margins": 4.170534610748291,
+      "rewards/rejected": -3.0458874702453613,
+      "step": 165
+    },
+    {
+      "epoch": 1.4137214137214138,
+      "grad_norm": 23.25615225421175,
+      "learning_rate": 5.671166329088277e-07,
+      "logits/chosen": -2.2688093185424805,
+      "logits/rejected": -2.2384774684906006,
+      "logps/chosen": -238.3243865966797,
+      "logps/rejected": -240.37777709960938,
+      "loss": 0.2751,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 0.6020036935806274,
+      "rewards/margins": 3.808955430984497,
+      "rewards/rejected": -3.20695161819458,
+      "step": 170
+    },
+    {
+      "epoch": 1.4553014553014554,
+      "grad_norm": 24.8005088659585,
+      "learning_rate": 5.448196544517167e-07,
+      "logits/chosen": -2.2849674224853516,
+      "logits/rejected": -2.2544331550598145,
+      "logps/chosen": -228.5469970703125,
+      "logps/rejected": -253.1507568359375,
+      "loss": 0.2936,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 0.9252071380615234,
+      "rewards/margins": 3.8109142780303955,
+      "rewards/rejected": -2.885706901550293,
+      "step": 175
+    },
+    {
+      "epoch": 1.496881496881497,
+      "grad_norm": 23.612056178752066,
+      "learning_rate": 5.224324151752575e-07,
+      "logits/chosen": -2.285452365875244,
+      "logits/rejected": -2.2679247856140137,
+      "logps/chosen": -244.0481414794922,
+      "logps/rejected": -242.934326171875,
+      "loss": 0.3075,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 0.8627504110336304,
+      "rewards/margins": 3.3582921028137207,
+      "rewards/rejected": -2.495541572570801,
+      "step": 180
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 18.628858729154818,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.280660629272461,
+      "logits/rejected": -2.25248384475708,
+      "logps/chosen": -266.83843994140625,
+      "logps/rejected": -240.79458618164062,
+      "loss": 0.2867,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.5424957275390625,
+      "rewards/margins": 3.944887161254883,
+      "rewards/rejected": -2.4023914337158203,
+      "step": 185
+    },
+    {
+      "epoch": 1.5800415800415801,
+      "grad_norm": 21.583610652311428,
+      "learning_rate": 4.775675848247427e-07,
+      "logits/chosen": -2.220531940460205,
+      "logits/rejected": -2.2063937187194824,
+      "logps/chosen": -249.5376434326172,
+      "logps/rejected": -239.2724609375,
+      "loss": 0.2762,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.249489665031433,
+      "rewards/margins": 3.775002956390381,
+      "rewards/rejected": -2.525513172149658,
+      "step": 190
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 22.305824426736503,
+      "learning_rate": 4.5518034554828327e-07,
+      "logits/chosen": -2.18373441696167,
+      "logits/rejected": -2.1448349952697754,
+      "logps/chosen": -215.9366455078125,
+      "logps/rejected": -238.5803985595703,
+      "loss": 0.2972,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 0.727931559085846,
+      "rewards/margins": 3.2119574546813965,
+      "rewards/rejected": -2.4840259552001953,
+      "step": 195
+    },
+    {
+      "epoch": 1.6632016632016633,
+      "grad_norm": 22.30870466168293,
+      "learning_rate": 4.328833670911724e-07,
+      "logits/chosen": -2.156912326812744,
+      "logits/rejected": -2.1097471714019775,
+      "logps/chosen": -244.296142578125,
+      "logps/rejected": -245.1069793701172,
+      "loss": 0.2918,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 1.1990578174591064,
+      "rewards/margins": 3.445786714553833,
+      "rewards/rejected": -2.2467288970947266,
+      "step": 200
+    },
+    {
+      "epoch": 1.6632016632016633,
+      "eval_logits/chosen": -2.1396963596343994,
+      "eval_logits/rejected": -2.104109764099121,
+      "eval_logps/chosen": -246.9388885498047,
+      "eval_logps/rejected": -237.9451446533203,
+      "eval_loss": 0.47476285696029663,
+      "eval_rewards/accuracies": 0.7893518805503845,
+      "eval_rewards/chosen": 0.6540950536727905,
+      "eval_rewards/margins": 2.159281015396118,
+      "eval_rewards/rejected": -1.5051857233047485,
+      "eval_runtime": 227.5908,
+      "eval_samples_per_second": 15.027,
+      "eval_steps_per_second": 0.237,
+      "step": 200
+    },
+    {
+      "epoch": 1.7047817047817047,
+      "grad_norm": 22.330548758723538,
+      "learning_rate": 4.107215526006817e-07,
+      "logits/chosen": -2.127753257751465,
+      "logits/rejected": -2.1029341220855713,
+      "logps/chosen": -254.81784057617188,
+      "logps/rejected": -240.69406127929688,
+      "loss": 0.2589,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.2017463445663452,
+      "rewards/margins": 3.6836166381835938,
+      "rewards/rejected": -2.481870174407959,
+      "step": 205
+    },
+    {
+      "epoch": 1.7463617463617465,
+      "grad_norm": 23.42618534782943,
+      "learning_rate": 3.8873953302184283e-07,
+      "logits/chosen": -2.119067430496216,
+      "logits/rejected": -2.097999095916748,
+      "logps/chosen": -252.0382843017578,
+      "logps/rejected": -252.5121612548828,
+      "loss": 0.2871,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": 1.1906788349151611,
+      "rewards/margins": 3.765472888946533,
+      "rewards/rejected": -2.574794054031372,
+      "step": 210
+    },
+    {
+      "epoch": 1.7879417879417878,
+      "grad_norm": 23.828745785592012,
+      "learning_rate": 3.669815772166625e-07,
+      "logits/chosen": -2.12138032913208,
+      "logits/rejected": -2.0937047004699707,
+      "logps/chosen": -236.6370849609375,
+      "logps/rejected": -245.3629913330078,
+      "loss": 0.2941,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 0.7747229337692261,
+      "rewards/margins": 3.729300022125244,
+      "rewards/rejected": -2.9545769691467285,
+      "step": 215
+    },
+    {
+      "epoch": 1.8295218295218296,
+      "grad_norm": 24.310629259778715,
+      "learning_rate": 3.454915028125263e-07,
+      "logits/chosen": -2.160141706466675,
+      "logits/rejected": -2.1324830055236816,
+      "logps/chosen": -268.5956726074219,
+      "logps/rejected": -233.184814453125,
+      "loss": 0.2762,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": 0.6775209903717041,
+      "rewards/margins": 3.3985679149627686,
+      "rewards/rejected": -2.7210471630096436,
+      "step": 220
+    },
+    {
+      "epoch": 1.871101871101871,
+      "grad_norm": 21.655108770253698,
+      "learning_rate": 3.243125879593286e-07,
+      "logits/chosen": -2.127842664718628,
+      "logits/rejected": -2.0952022075653076,
+      "logps/chosen": -256.9776611328125,
+      "logps/rejected": -223.1400909423828,
+      "loss": 0.2515,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 0.6245139241218567,
+      "rewards/margins": 3.6011645793914795,
+      "rewards/rejected": -2.9766499996185303,
+      "step": 225
+    },
+    {
+      "epoch": 1.9126819126819128,
+      "grad_norm": 20.97953443300121,
+      "learning_rate": 3.034874841730382e-07,
+      "logits/chosen": -2.13321852684021,
+      "logits/rejected": -2.061434507369995,
+      "logps/chosen": -228.10855102539062,
+      "logps/rejected": -247.96017456054688,
+      "loss": 0.2611,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": 0.6115671396255493,
+      "rewards/margins": 3.505589008331299,
+      "rewards/rejected": -2.894021987915039,
+      "step": 230
+    },
+    {
+      "epoch": 1.9542619542619541,
+      "grad_norm": 22.181830498973316,
+      "learning_rate": 2.8305813044122093e-07,
+      "logits/chosen": -2.1058921813964844,
+      "logits/rejected": -2.05732798576355,
+      "logps/chosen": -254.475830078125,
+      "logps/rejected": -236.3775177001953,
+      "loss": 0.2666,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.6889549493789673,
+      "rewards/margins": 3.523211717605591,
+      "rewards/rejected": -2.834256649017334,
+      "step": 235
+    },
+    {
+      "epoch": 1.995841995841996,
+      "grad_norm": 23.583037883722724,
+      "learning_rate": 2.6306566876350067e-07,
+      "logits/chosen": -2.053210735321045,
+      "logits/rejected": -2.0301995277404785,
+      "logps/chosen": -255.9599151611328,
+      "logps/rejected": -232.1293487548828,
+      "loss": 0.2917,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": 0.26249581575393677,
+      "rewards/margins": 3.1315131187438965,
+      "rewards/rejected": -2.8690171241760254,
+      "step": 240
+    },
+    {
+      "epoch": 2.0374220374220373,
+      "grad_norm": 16.400038597920425,
+      "learning_rate": 2.4355036129704696e-07,
+      "logits/chosen": -2.0550200939178467,
+      "logits/rejected": -2.018430709838867,
+      "logps/chosen": -259.5970764160156,
+      "logps/rejected": -258.3427734375,
+      "loss": 0.1651,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.1610878705978394,
+      "rewards/margins": 4.203980445861816,
+      "rewards/rejected": -3.0428924560546875,
+      "step": 245
+    },
+    {
+      "epoch": 2.079002079002079,
+      "grad_norm": 12.2552842371032,
+      "learning_rate": 2.2455150927394878e-07,
+      "logits/chosen": -2.0654613971710205,
+      "logits/rejected": -2.038012742996216,
+      "logps/chosen": -245.9919891357422,
+      "logps/rejected": -258.2598571777344,
+      "loss": 0.1553,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": 1.1950385570526123,
+      "rewards/margins": 4.2309184074401855,
+      "rewards/rejected": -3.0358798503875732,
+      "step": 250
+    },
+    {
+      "epoch": 2.079002079002079,
+      "eval_logits/chosen": -2.0690126419067383,
+      "eval_logits/rejected": -2.0243546962738037,
+      "eval_logps/chosen": -251.02001953125,
+      "eval_logps/rejected": -244.09349060058594,
+      "eval_loss": 0.4500342309474945,
+      "eval_rewards/accuracies": 0.7916666865348816,
+      "eval_rewards/chosen": 0.2459830939769745,
+      "eval_rewards/margins": 2.366004467010498,
+      "eval_rewards/rejected": -2.1200215816497803,
+      "eval_runtime": 227.5327,
+      "eval_samples_per_second": 15.031,
+      "eval_steps_per_second": 0.237,
+      "step": 250
+    },
+    {
+      "epoch": 2.1205821205821205,
+      "grad_norm": 14.665336411887568,
+      "learning_rate": 2.0610737385376348e-07,
+      "logits/chosen": -2.07989764213562,
+      "logits/rejected": -2.0319314002990723,
+      "logps/chosen": -232.17626953125,
+      "logps/rejected": -245.3802947998047,
+      "loss": 0.1469,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 1.211355209350586,
+      "rewards/margins": 4.2340617179870605,
+      "rewards/rejected": -3.022706985473633,
+      "step": 255
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 20.54334882028054,
+      "learning_rate": 1.8825509907063326e-07,
+      "logits/chosen": -2.0753746032714844,
+      "logits/rejected": -2.05375337600708,
+      "logps/chosen": -267.84564208984375,
+      "logps/rejected": -247.1650848388672,
+      "loss": 0.1396,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 1.6367136240005493,
+      "rewards/margins": 4.657883644104004,
+      "rewards/rejected": -3.021169900894165,
+      "step": 260
+    },
+    {
+      "epoch": 2.2037422037422036,
+      "grad_norm": 13.522288492209173,
+      "learning_rate": 1.710306370301437e-07,
+      "logits/chosen": -2.0679497718811035,
+      "logits/rejected": -2.044339418411255,
+      "logps/chosen": -245.69747924804688,
+      "logps/rejected": -231.1640167236328,
+      "loss": 0.1486,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.1823408603668213,
+      "rewards/margins": 4.235699653625488,
+      "rewards/rejected": -3.053358554840088,
+      "step": 265
+    },
+    {
+      "epoch": 2.2453222453222454,
+      "grad_norm": 14.311936428237873,
+      "learning_rate": 1.5446867550656767e-07,
+      "logits/chosen": -2.0583014488220215,
+      "logits/rejected": -2.0194382667541504,
+      "logps/chosen": -238.56881713867188,
+      "logps/rejected": -230.8579559326172,
+      "loss": 0.1582,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.0703871250152588,
+      "rewards/margins": 4.322309970855713,
+      "rewards/rejected": -3.251922607421875,
+      "step": 270
+    },
+    {
+      "epoch": 2.286902286902287,
+      "grad_norm": 16.316621526893123,
+      "learning_rate": 1.3860256808630427e-07,
+      "logits/chosen": -2.0828161239624023,
+      "logits/rejected": -2.0464069843292236,
+      "logps/chosen": -254.72598266601562,
+      "logps/rejected": -259.24456787109375,
+      "loss": 0.1695,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.3350589275360107,
+      "rewards/margins": 4.5173187255859375,
+      "rewards/rejected": -3.182260036468506,
+      "step": 275
+    },
+    {
+      "epoch": 2.3284823284823286,
+      "grad_norm": 15.027859809390153,
+      "learning_rate": 1.2346426699819456e-07,
+      "logits/chosen": -2.043334484100342,
+      "logits/rejected": -2.0351319313049316,
+      "logps/chosen": -244.282958984375,
+      "logps/rejected": -227.07412719726562,
+      "loss": 0.1458,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.0487641096115112,
+      "rewards/margins": 4.314339637756348,
+      "rewards/rejected": -3.265575408935547,
+      "step": 280
+    },
+    {
+      "epoch": 2.37006237006237,
+      "grad_norm": 17.560727135336002,
+      "learning_rate": 1.090842587659851e-07,
+      "logits/chosen": -2.0772533416748047,
+      "logits/rejected": -2.0204625129699707,
+      "logps/chosen": -229.1877899169922,
+      "logps/rejected": -239.1647186279297,
+      "loss": 0.1381,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.9350064396858215,
+      "rewards/margins": 4.154140949249268,
+      "rewards/rejected": -3.21913480758667,
+      "step": 285
+    },
+    {
+      "epoch": 2.4116424116424118,
+      "grad_norm": 16.58334845699487,
+      "learning_rate": 9.549150281252632e-08,
+      "logits/chosen": -2.048074245452881,
+      "logits/rejected": -2.0141758918762207,
+      "logps/chosen": -240.11776733398438,
+      "logps/rejected": -246.3990478515625,
+      "loss": 0.1704,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 0.7491234540939331,
+      "rewards/margins": 4.333771705627441,
+      "rewards/rejected": -3.584648609161377,
+      "step": 290
+    },
+    {
+      "epoch": 2.453222453222453,
+      "grad_norm": 16.448184054381468,
+      "learning_rate": 8.271337313934867e-08,
+      "logits/chosen": -2.0629689693450928,
+      "logits/rejected": -2.0243401527404785,
+      "logps/chosen": -265.8284606933594,
+      "logps/rejected": -243.48721313476562,
+      "loss": 0.1352,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 1.5819892883300781,
+      "rewards/margins": 4.679896354675293,
+      "rewards/rejected": -3.0979068279266357,
+      "step": 295
+    },
+    {
+      "epoch": 2.494802494802495,
+      "grad_norm": 19.119314110216063,
+      "learning_rate": 7.077560319906694e-08,
+      "logits/chosen": -2.064866065979004,
+      "logits/rejected": -2.0365378856658936,
+      "logps/chosen": -229.75283813476562,
+      "logps/rejected": -239.24575805664062,
+      "loss": 0.1681,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.9728547930717468,
+      "rewards/margins": 4.20751953125,
+      "rewards/rejected": -3.2346649169921875,
+      "step": 300
+    },
+    {
+      "epoch": 2.494802494802495,
+      "eval_logits/chosen": -2.0779573917388916,
+      "eval_logits/rejected": -2.030367612838745,
+      "eval_logps/chosen": -251.5723419189453,
+      "eval_logps/rejected": -246.45338439941406,
+      "eval_loss": 0.4636799395084381,
+      "eval_rewards/accuracies": 0.7916666865348816,
+      "eval_rewards/chosen": 0.19075357913970947,
+      "eval_rewards/margins": 2.546764612197876,
+      "eval_rewards/rejected": -2.356010913848877,
+      "eval_runtime": 227.5729,
+      "eval_samples_per_second": 15.028,
+      "eval_steps_per_second": 0.237,
+      "step": 300
+    },
+    {
+      "epoch": 2.5363825363825363,
+      "grad_norm": 14.667470869179501,
+      "learning_rate": 5.9702234071631e-08,
+      "logits/chosen": -2.0607783794403076,
+      "logits/rejected": -2.041450023651123,
+      "logps/chosen": -243.2858123779297,
+      "logps/rejected": -240.99411010742188,
+      "loss": 0.1636,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.1499525308609009,
+      "rewards/margins": 4.42706298828125,
+      "rewards/rejected": -3.277111053466797,
+      "step": 305
+    },
+    {
+      "epoch": 2.577962577962578,
+      "grad_norm": 19.39345609322425,
+      "learning_rate": 4.951556604879048e-08,
+      "logits/chosen": -2.0797219276428223,
+      "logits/rejected": -2.0556273460388184,
+      "logps/chosen": -261.95294189453125,
+      "logps/rejected": -274.20855712890625,
+      "loss": 0.1442,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.5042924880981445,
+      "rewards/margins": 4.629009246826172,
+      "rewards/rejected": -3.1247167587280273,
+      "step": 310
+    },
+    {
+      "epoch": 2.6195426195426195,
+      "grad_norm": 18.606904479351094,
+      "learning_rate": 4.023611372427471e-08,
+      "logits/chosen": -2.07034969329834,
+      "logits/rejected": -2.035374164581299,
+      "logps/chosen": -245.9356231689453,
+      "logps/rejected": -250.6208953857422,
+      "loss": 0.1422,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 0.7137230634689331,
+      "rewards/margins": 3.9477944374084473,
+      "rewards/rejected": -3.2340710163116455,
+      "step": 315
+    },
+    {
+      "epoch": 2.6611226611226613,
+      "grad_norm": 14.227432530418904,
+      "learning_rate": 3.188256468013139e-08,
+      "logits/chosen": -2.067927598953247,
+      "logits/rejected": -2.0321035385131836,
+      "logps/chosen": -241.3792266845703,
+      "logps/rejected": -236.80282592773438,
+      "loss": 0.1407,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.0587596893310547,
+      "rewards/margins": 4.400935173034668,
+      "rewards/rejected": -3.342175245285034,
+      "step": 320
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 17.201920271422672,
+      "learning_rate": 2.4471741852423233e-08,
+      "logits/chosen": -2.114290952682495,
+      "logits/rejected": -2.0510830879211426,
+      "logps/chosen": -281.11358642578125,
+      "logps/rejected": -241.0150909423828,
+      "loss": 0.1424,
+      "rewards/accuracies": 0.981249988079071,
+      "rewards/chosen": 1.6817333698272705,
+      "rewards/margins": 5.000082492828369,
+      "rewards/rejected": -3.3183486461639404,
+      "step": 325
+    },
+    {
+      "epoch": 2.7442827442827444,
+      "grad_norm": 17.323036546917454,
+      "learning_rate": 1.8018569652073378e-08,
+      "logits/chosen": -2.083601474761963,
+      "logits/rejected": -2.048649311065674,
+      "logps/chosen": -260.6294860839844,
+      "logps/rejected": -255.7637176513672,
+      "loss": 0.1487,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.3188153505325317,
+      "rewards/margins": 4.595917224884033,
+      "rewards/rejected": -3.27710223197937,
+      "step": 330
+    },
+    {
+      "epoch": 2.785862785862786,
+      "grad_norm": 21.42768190025909,
+      "learning_rate": 1.253604390908819e-08,
+      "logits/chosen": -2.0744071006774902,
+      "logits/rejected": -2.0306787490844727,
+      "logps/chosen": -222.31716918945312,
+      "logps/rejected": -228.0690155029297,
+      "loss": 0.157,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 0.849885106086731,
+      "rewards/margins": 4.167181968688965,
+      "rewards/rejected": -3.3172969818115234,
+      "step": 335
+    },
+    {
+      "epoch": 2.8274428274428276,
+      "grad_norm": 18.263866530185883,
+      "learning_rate": 8.035205700685165e-09,
+      "logits/chosen": -2.0773751735687256,
+      "logits/rejected": -2.034102439880371,
+      "logps/chosen": -249.54611206054688,
+      "logps/rejected": -240.7930145263672,
+      "loss": 0.1622,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.9739130735397339,
+      "rewards/margins": 4.316155433654785,
+      "rewards/rejected": -3.342242479324341,
+      "step": 340
+    },
+    {
+      "epoch": 2.869022869022869,
+      "grad_norm": 17.41270846396853,
+      "learning_rate": 4.5251191160326495e-09,
+      "logits/chosen": -2.0841946601867676,
+      "logits/rejected": -2.033412456512451,
+      "logps/chosen": -257.4566650390625,
+      "logps/rejected": -244.41024780273438,
+      "loss": 0.1463,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 1.161675214767456,
+      "rewards/margins": 4.546628952026367,
+      "rewards/rejected": -3.384953737258911,
+      "step": 345
+    },
+    {
+      "epoch": 2.9106029106029108,
+      "grad_norm": 20.545923134031526,
+      "learning_rate": 2.0128530023804656e-09,
+      "logits/chosen": -2.062431812286377,
+      "logits/rejected": -2.0312106609344482,
+      "logps/chosen": -240.2437744140625,
+      "logps/rejected": -254.35855102539062,
+      "loss": 0.2027,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 0.7562185525894165,
+      "rewards/margins": 4.034458160400391,
+      "rewards/rejected": -3.2782390117645264,
+      "step": 350
+    },
+    {
+      "epoch": 2.9106029106029108,
+      "eval_logits/chosen": -2.0754621028900146,
+      "eval_logits/rejected": -2.027017831802368,
+      "eval_logps/chosen": -252.3748321533203,
+      "eval_logps/rejected": -247.98789978027344,
+      "eval_loss": 0.46064791083335876,
+      "eval_rewards/accuracies": 0.7939814925193787,
+      "eval_rewards/chosen": 0.1105002835392952,
+      "eval_rewards/margins": 2.6199629306793213,
+      "eval_rewards/rejected": -2.509462594985962,
+      "eval_runtime": 227.7575,
+      "eval_samples_per_second": 15.016,
+      "eval_steps_per_second": 0.237,
+      "step": 350
+    },
+    {
+      "epoch": 2.952182952182952,
+      "grad_norm": 15.620508129026678,
+      "learning_rate": 5.034667293427053e-10,
+      "logits/chosen": -2.0936946868896484,
+      "logits/rejected": -2.026482582092285,
+      "logps/chosen": -249.20462036132812,
+      "logps/rejected": -244.3335418701172,
+      "loss": 0.1491,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.9666486978530884,
+      "rewards/margins": 4.209371089935303,
+      "rewards/rejected": -3.242722272872925,
+      "step": 355
+    },
+    {
+      "epoch": 2.993762993762994,
+      "grad_norm": 17.80073073785331,
+      "learning_rate": 0.0,
+      "logits/chosen": -2.074941635131836,
+      "logits/rejected": -2.031865119934082,
+      "logps/chosen": -242.9724578857422,
+      "logps/rejected": -253.39767456054688,
+      "loss": 0.1508,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": 1.1560876369476318,
+      "rewards/margins": 4.581432819366455,
+      "rewards/rejected": -3.425344467163086,
+      "step": 360
+    },
+    {
+      "epoch": 2.993762993762994,
+      "step": 360,
+      "total_flos": 4244978440077312.0,
+      "train_loss": 0.3317935415440135,
+      "train_runtime": 13850.2535,
+      "train_samples_per_second": 6.665,
+      "train_steps_per_second": 0.026
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 360,
+  "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": 4244978440077312.0,
+  "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 sha256:7d661e6ce03d2ac1b518469f0ff11ac90e65b5c9f1454e9c6ed937955518e9cf
+size 7096