Upload folder using huggingface_hub

README.md

@@ -0,0 +1,78 @@
+---
+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_random_0_70
+  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_random_0_70
+
+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_random_0_70 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5414
+- Rewards/chosen: 0.5872
+- Rewards/rejected: -1.5508
+- Rewards/accuracies: 0.7768
+- Rewards/margins: 2.1380
+- Logps/rejected: -227.1739
+- Logps/chosen: -233.6734
+- Logits/rejected: -1.9224
+- Logits/chosen: -1.9691
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.6034        | 0.5348 | 50   | 0.5869          | 0.7400         | -0.1413          | 0.7292             | 0.8813          | -213.0786      | -232.1449    | -2.5305         | -2.5372       |
+| 0.2659        | 1.0695 | 100  | 0.5500          | 1.0886         | -0.4196          | 0.7679             | 1.5081          | -215.8615      | -228.6596    | -2.1146         | -2.1482       |
+| 0.2599        | 1.6043 | 150  | 0.5465          | 0.7596         | -1.0841          | 0.7679             | 1.8437          | -222.5069      | -231.9491    | -2.1122         | -2.1442       |
+| 0.1366        | 2.1390 | 200  | 0.5222          | 0.5890         | -1.4225          | 0.7857             | 2.0115          | -225.8904      | -233.6554    | -2.0824         | -2.1154       |
+| 0.1488        | 2.6738 | 250  | 0.5411          | 0.5980         | -1.5260          | 0.7768             | 2.1240          | -226.9253      | -233.5653    | -1.9322         | -1.9781       |
+
+
+### 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": 2.983957219251337,
+    "eval_logits/chosen": -1.9690638780593872,
+    "eval_logits/rejected": -1.9223570823669434,
+    "eval_logps/chosen": -233.67343139648438,
+    "eval_logps/rejected": -227.1739044189453,
+    "eval_loss": 0.5413760542869568,
+    "eval_rewards/accuracies": 0.7767857313156128,
+    "eval_rewards/chosen": 0.5871802568435669,
+    "eval_rewards/margins": 2.1379942893981934,
+    "eval_rewards/rejected": -1.550813913345337,
+    "eval_runtime": 176.7918,
+    "eval_samples_per_second": 15.046,
+    "eval_steps_per_second": 0.238,
+    "total_flos": 3289753017384960.0,
+    "train_loss": 0.3334879027045329,
+    "train_runtime": 10390.4498,
+    "train_samples_per_second": 6.91,
+    "train_steps_per_second": 0.027
+}

config.json

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

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 2.983957219251337,
+    "eval_logits/chosen": -1.9690638780593872,
+    "eval_logits/rejected": -1.9223570823669434,
+    "eval_logps/chosen": -233.67343139648438,
+    "eval_logps/rejected": -227.1739044189453,
+    "eval_loss": 0.5413760542869568,
+    "eval_rewards/accuracies": 0.7767857313156128,
+    "eval_rewards/chosen": 0.5871802568435669,
+    "eval_rewards/margins": 2.1379942893981934,
+    "eval_rewards/rejected": -1.550813913345337,
+    "eval_runtime": 176.7918,
+    "eval_samples_per_second": 15.046,
+    "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:c1e6adaea3d0b951b8f8d50fa747710ff1d0a946c726b2e46387ef82e66eda41
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ffc2fe9e7baf570c0766b7f8740365df7f7c6c0efc41c5f30d0f4ac7a2fc686
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:622ecf9f509a39eb77e3cd26a4734832fc0a81d44e10172222b85e4a3147507a
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ff2ff370085bf37b63d726a0a6b019cad9332d8986425120400b8d2cd9e14b
+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": 2.983957219251337,
+    "total_flos": 3289753017384960.0,
+    "train_loss": 0.3334879027045329,
+    "train_runtime": 10390.4498,
+    "train_samples_per_second": 6.91,
+    "train_steps_per_second": 0.027
+}

trainer_log.jsonl

@@ -0,0 +1,61 @@
+{"current_steps": 5, "total_steps": 279, "loss": 0.6903, "accuracy": 0.3125, "learning_rate": 5e-07, "epoch": 0.053475935828877004, "percentage": 1.79, "elapsed_time": "0:02:53", "remaining_time": "2:38:38"}
+{"current_steps": 10, "total_steps": 279, "loss": 0.6648, "accuracy": 0.668749988079071, "learning_rate": 1e-06, "epoch": 0.10695187165775401, "percentage": 3.58, "elapsed_time": "0:05:42", "remaining_time": "2:33:20"}
+{"current_steps": 15, "total_steps": 279, "loss": 0.6277, "accuracy": 0.699999988079071, "learning_rate": 9.991477798614637e-07, "epoch": 0.16042780748663102, "percentage": 5.38, "elapsed_time": "0:08:28", "remaining_time": "2:29:17"}
+{"current_steps": 20, "total_steps": 279, "loss": 0.5937, "accuracy": 0.731249988079071, "learning_rate": 9.965940245625131e-07, "epoch": 0.21390374331550802, "percentage": 7.17, "elapsed_time": "0:11:17", "remaining_time": "2:26:08"}
+{"current_steps": 25, "total_steps": 279, "loss": 0.5968, "accuracy": 0.6875, "learning_rate": 9.923474395499264e-07, "epoch": 0.26737967914438504, "percentage": 8.96, "elapsed_time": "0:14:05", "remaining_time": "2:23:05"}
+{"current_steps": 30, "total_steps": 279, "loss": 0.591, "accuracy": 0.675000011920929, "learning_rate": 9.86422500924775e-07, "epoch": 0.32085561497326204, "percentage": 10.75, "elapsed_time": "0:16:53", "remaining_time": "2:20:12"}
+{"current_steps": 35, "total_steps": 279, "loss": 0.5951, "accuracy": 0.6312500238418579, "learning_rate": 9.788394060951227e-07, "epoch": 0.37433155080213903, "percentage": 12.54, "elapsed_time": "0:19:42", "remaining_time": "2:17:20"}
+{"current_steps": 40, "total_steps": 279, "loss": 0.5946, "accuracy": 0.7124999761581421, "learning_rate": 9.696240049254742e-07, "epoch": 0.42780748663101603, "percentage": 14.34, "elapsed_time": "0:22:31", "remaining_time": "2:14:32"}
+{"current_steps": 45, "total_steps": 279, "loss": 0.6027, "accuracy": 0.7124999761581421, "learning_rate": 9.588077116176756e-07, "epoch": 0.48128342245989303, "percentage": 16.13, "elapsed_time": "0:25:20", "remaining_time": "2:11:44"}
+{"current_steps": 50, "total_steps": 279, "loss": 0.6034, "accuracy": 0.737500011920929, "learning_rate": 9.464273976236516e-07, "epoch": 0.5347593582887701, "percentage": 17.92, "elapsed_time": "0:28:07", "remaining_time": "2:08:49"}
+{"current_steps": 50, "total_steps": 279, "eval_loss": 0.5868557095527649, "epoch": 0.5347593582887701, "percentage": 17.92, "elapsed_time": "0:31:05", "remaining_time": "2:22:25"}
+{"current_steps": 55, "total_steps": 279, "loss": 0.5728, "accuracy": 0.71875, "learning_rate": 9.325252659550308e-07, "epoch": 0.5882352941176471, "percentage": 19.71, "elapsed_time": "0:33:53", "remaining_time": "2:18:03"}
+{"current_steps": 60, "total_steps": 279, "loss": 0.5838, "accuracy": 0.737500011920929, "learning_rate": 9.171487073181197e-07, "epoch": 0.6417112299465241, "percentage": 21.51, "elapsed_time": "0:36:42", "remaining_time": "2:13:58"}
+{"current_steps": 65, "total_steps": 279, "loss": 0.5857, "accuracy": 0.737500011920929, "learning_rate": 9.003501385646448e-07, "epoch": 0.6951871657754011, "percentage": 23.3, "elapsed_time": "0:39:30", "remaining_time": "2:10:04"}
+{"current_steps": 70, "total_steps": 279, "loss": 0.587, "accuracy": 0.6812499761581421, "learning_rate": 8.821868240089676e-07, "epoch": 0.7486631016042781, "percentage": 25.09, "elapsed_time": "0:42:19", "remaining_time": "2:06:20"}
+{"current_steps": 75, "total_steps": 279, "loss": 0.5926, "accuracy": 0.7124999761581421, "learning_rate": 8.62720680220876e-07, "epoch": 0.8021390374331551, "percentage": 26.88, "elapsed_time": "0:45:09", "remaining_time": "2:02:49"}
+{"current_steps": 80, "total_steps": 279, "loss": 0.5303, "accuracy": 0.75, "learning_rate": 8.420180649593929e-07, "epoch": 0.8556149732620321, "percentage": 28.67, "elapsed_time": "0:47:56", "remaining_time": "1:59:15"}
+{"current_steps": 85, "total_steps": 279, "loss": 0.5561, "accuracy": 0.7250000238418579, "learning_rate": 8.201495509671036e-07, "epoch": 0.9090909090909091, "percentage": 30.47, "elapsed_time": "0:50:44", "remaining_time": "1:55:47"}
+{"current_steps": 90, "total_steps": 279, "loss": 0.4894, "accuracy": 0.862500011920929, "learning_rate": 7.971896853961042e-07, "epoch": 0.9625668449197861, "percentage": 32.26, "elapsed_time": "0:53:33", "remaining_time": "1:52:27"}
+{"current_steps": 95, "total_steps": 279, "loss": 0.4711, "accuracy": 0.831250011920929, "learning_rate": 7.732167356856654e-07, "epoch": 1.0160427807486632, "percentage": 34.05, "elapsed_time": "0:56:21", "remaining_time": "1:49:08"}
+{"current_steps": 100, "total_steps": 279, "loss": 0.2659, "accuracy": 0.9125000238418579, "learning_rate": 7.48312422757881e-07, "epoch": 1.0695187165775402, "percentage": 35.84, "elapsed_time": "0:59:08", "remaining_time": "1:45:52"}
+{"current_steps": 100, "total_steps": 279, "eval_loss": 0.5500321388244629, "epoch": 1.0695187165775402, "percentage": 35.84, "elapsed_time": "1:02:06", "remaining_time": "1:51:10"}
+{"current_steps": 105, "total_steps": 279, "loss": 0.2083, "accuracy": 0.925000011920929, "learning_rate": 7.225616424408044e-07, "epoch": 1.1229946524064172, "percentage": 37.63, "elapsed_time": "1:05:30", "remaining_time": "1:48:34"}
+{"current_steps": 110, "total_steps": 279, "loss": 0.2286, "accuracy": 0.9312499761581421, "learning_rate": 6.96052176068713e-07, "epoch": 1.1764705882352942, "percentage": 39.43, "elapsed_time": "1:08:20", "remaining_time": "1:45:00"}
+{"current_steps": 115, "total_steps": 279, "loss": 0.2429, "accuracy": 0.90625, "learning_rate": 6.688743912460229e-07, "epoch": 1.2299465240641712, "percentage": 41.22, "elapsed_time": "1:11:08", "remaining_time": "1:41:27"}
+{"current_steps": 120, "total_steps": 279, "loss": 0.2529, "accuracy": 0.9375, "learning_rate": 6.411209337949213e-07, "epoch": 1.2834224598930482, "percentage": 43.01, "elapsed_time": "1:13:57", "remaining_time": "1:37:59"}
+{"current_steps": 125, "total_steps": 279, "loss": 0.2611, "accuracy": 0.8999999761581421, "learning_rate": 6.128864119368233e-07, "epoch": 1.3368983957219251, "percentage": 44.8, "elapsed_time": "1:16:45", "remaining_time": "1:34:34"}
+{"current_steps": 130, "total_steps": 279, "loss": 0.2933, "accuracy": 0.893750011920929, "learning_rate": 5.842670737842467e-07, "epoch": 1.3903743315508021, "percentage": 46.59, "elapsed_time": "1:19:34", "remaining_time": "1:31:12"}
+{"current_steps": 135, "total_steps": 279, "loss": 0.2246, "accuracy": 0.918749988079071, "learning_rate": 5.553604792424922e-07, "epoch": 1.4438502673796791, "percentage": 48.39, "elapsed_time": "1:22:22", "remaining_time": "1:27:52"}
+{"current_steps": 140, "total_steps": 279, "loss": 0.2528, "accuracy": 0.9312499761581421, "learning_rate": 5.262651674395798e-07, "epoch": 1.4973262032085561, "percentage": 50.18, "elapsed_time": "1:25:10", "remaining_time": "1:24:34"}
+{"current_steps": 145, "total_steps": 279, "loss": 0.292, "accuracy": 0.9312499761581421, "learning_rate": 4.970803208181314e-07, "epoch": 1.5508021390374331, "percentage": 51.97, "elapsed_time": "1:27:58", "remaining_time": "1:21:18"}
+{"current_steps": 150, "total_steps": 279, "loss": 0.2599, "accuracy": 0.8999999761581421, "learning_rate": 4.679054270342702e-07, "epoch": 1.6042780748663101, "percentage": 53.76, "elapsed_time": "1:30:46", "remaining_time": "1:18:03"}
+{"current_steps": 150, "total_steps": 279, "eval_loss": 0.546504020690918, "epoch": 1.6042780748663101, "percentage": 53.76, "elapsed_time": "1:33:44", "remaining_time": "1:20:36"}
+{"current_steps": 155, "total_steps": 279, "loss": 0.2643, "accuracy": 0.9312499761581421, "learning_rate": 4.3883993981608567e-07, "epoch": 1.6577540106951871, "percentage": 55.56, "elapsed_time": "1:36:32", "remaining_time": "1:17:13"}
+{"current_steps": 160, "total_steps": 279, "loss": 0.2942, "accuracy": 0.918749988079071, "learning_rate": 4.0998293993775234e-07, "epoch": 1.7112299465240641, "percentage": 57.35, "elapsed_time": "1:39:19", "remaining_time": "1:13:52"}
+{"current_steps": 165, "total_steps": 279, "loss": 0.2401, "accuracy": 0.9312499761581421, "learning_rate": 3.814327974650066e-07, "epoch": 1.7647058823529411, "percentage": 59.14, "elapsed_time": "1:42:06", "remaining_time": "1:10:32"}
+{"current_steps": 170, "total_steps": 279, "loss": 0.2635, "accuracy": 0.875, "learning_rate": 3.532868364233416e-07, "epoch": 1.8181818181818183, "percentage": 60.93, "elapsed_time": "1:44:54", "remaining_time": "1:07:16"}
+{"current_steps": 175, "total_steps": 279, "loss": 0.2622, "accuracy": 0.893750011920929, "learning_rate": 3.256410030320304e-07, "epoch": 1.8716577540106951, "percentage": 62.72, "elapsed_time": "1:47:43", "remaining_time": "1:04:01"}
+{"current_steps": 180, "total_steps": 279, "loss": 0.296, "accuracy": 0.90625, "learning_rate": 2.985895386349233e-07, "epoch": 1.9251336898395723, "percentage": 64.52, "elapsed_time": "1:50:33", "remaining_time": "1:00:48"}
+{"current_steps": 185, "total_steps": 279, "loss": 0.3228, "accuracy": 0.9125000238418579, "learning_rate": 2.7222465844296514e-07, "epoch": 1.9786096256684491, "percentage": 66.31, "elapsed_time": "1:53:20", "remaining_time": "0:57:35"}
+{"current_steps": 190, "total_steps": 279, "loss": 0.2084, "accuracy": 0.9437500238418579, "learning_rate": 2.466362371835544e-07, "epoch": 2.0320855614973263, "percentage": 68.1, "elapsed_time": "1:56:09", "remaining_time": "0:54:24"}
+{"current_steps": 195, "total_steps": 279, "loss": 0.1457, "accuracy": 0.949999988079071, "learning_rate": 2.2191150272833386e-07, "epoch": 2.085561497326203, "percentage": 69.89, "elapsed_time": "1:58:58", "remaining_time": "0:51:14"}
+{"current_steps": 200, "total_steps": 279, "loss": 0.1366, "accuracy": 0.9750000238418579, "learning_rate": 1.9813473874379395e-07, "epoch": 2.1390374331550803, "percentage": 71.68, "elapsed_time": "2:01:46", "remaining_time": "0:48:05"}
+{"current_steps": 200, "total_steps": 279, "eval_loss": 0.5221620202064514, "epoch": 2.1390374331550803, "percentage": 71.68, "elapsed_time": "2:04:44", "remaining_time": "0:49:16"}
+{"current_steps": 205, "total_steps": 279, "loss": 0.1322, "accuracy": 0.9375, "learning_rate": 1.7538699737832237e-07, "epoch": 2.192513368983957, "percentage": 73.48, "elapsed_time": "2:08:04", "remaining_time": "0:46:13"}
+{"current_steps": 210, "total_steps": 279, "loss": 0.146, "accuracy": 0.949999988079071, "learning_rate": 1.5374582296511053e-07, "epoch": 2.2459893048128343, "percentage": 75.27, "elapsed_time": "2:10:52", "remaining_time": "0:43:00"}
+{"current_steps": 215, "total_steps": 279, "loss": 0.1554, "accuracy": 0.9375, "learning_rate": 1.3328498768278418e-07, "epoch": 2.299465240641711, "percentage": 77.06, "elapsed_time": "2:13:41", "remaining_time": "0:39:47"}
+{"current_steps": 220, "total_steps": 279, "loss": 0.1268, "accuracy": 0.9624999761581421, "learning_rate": 1.1407424007485928e-07, "epoch": 2.3529411764705883, "percentage": 78.85, "elapsed_time": "2:16:30", "remaining_time": "0:36:36"}
+{"current_steps": 225, "total_steps": 279, "loss": 0.1401, "accuracy": 0.96875, "learning_rate": 9.617906728528679e-08, "epoch": 2.406417112299465, "percentage": 80.65, "elapsed_time": "2:19:18", "remaining_time": "0:33:25"}
+{"current_steps": 230, "total_steps": 279, "loss": 0.1625, "accuracy": 0.8999999761581421, "learning_rate": 7.966047182060226e-08, "epoch": 2.4598930481283423, "percentage": 82.44, "elapsed_time": "2:22:06", "remaining_time": "0:30:16"}
+{"current_steps": 235, "total_steps": 279, "loss": 0.1397, "accuracy": 0.925000011920929, "learning_rate": 6.457476359966684e-08, "epoch": 2.5133689839572195, "percentage": 84.23, "elapsed_time": "2:24:54", "remaining_time": "0:27:07"}
+{"current_steps": 240, "total_steps": 279, "loss": 0.1576, "accuracy": 0.9375, "learning_rate": 5.097336799988067e-08, "epoch": 2.5668449197860963, "percentage": 86.02, "elapsed_time": "2:27:43", "remaining_time": "0:24:00"}
+{"current_steps": 245, "total_steps": 279, "loss": 0.1618, "accuracy": 0.9312499761581421, "learning_rate": 3.8902650554212826e-08, "epoch": 2.620320855614973, "percentage": 87.81, "elapsed_time": "2:30:32", "remaining_time": "0:20:53"}
+{"current_steps": 250, "total_steps": 279, "loss": 0.1488, "accuracy": 0.9375, "learning_rate": 2.8403758896638707e-08, "epoch": 2.6737967914438503, "percentage": 89.61, "elapsed_time": "2:33:21", "remaining_time": "0:17:47"}
+{"current_steps": 250, "total_steps": 279, "eval_loss": 0.5411336421966553, "epoch": 2.6737967914438503, "percentage": 89.61, "elapsed_time": "2:36:20", "remaining_time": "0:18:08"}
+{"current_steps": 255, "total_steps": 279, "loss": 0.1533, "accuracy": 0.925000011920929, "learning_rate": 1.951248249476961e-08, "epoch": 2.7272727272727275, "percentage": 91.4, "elapsed_time": "2:39:08", "remaining_time": "0:14:58"}
+{"current_steps": 260, "total_steps": 279, "loss": 0.1239, "accuracy": 0.956250011920929, "learning_rate": 1.2259130647833626e-08, "epoch": 2.7807486631016043, "percentage": 93.19, "elapsed_time": "2:41:55", "remaining_time": "0:11:50"}
+{"current_steps": 265, "total_steps": 279, "loss": 0.1353, "accuracy": 0.949999988079071, "learning_rate": 6.668429165893996e-09, "epoch": 2.834224598930481, "percentage": 94.98, "elapsed_time": "2:44:44", "remaining_time": "0:08:42"}
+{"current_steps": 270, "total_steps": 279, "loss": 0.1532, "accuracy": 0.9375, "learning_rate": 2.759436082516664e-09, "epoch": 2.8877005347593583, "percentage": 96.77, "elapsed_time": "2:47:32", "remaining_time": "0:05:35"}
+{"current_steps": 275, "total_steps": 279, "loss": 0.1405, "accuracy": 0.90625, "learning_rate": 5.454766882097006e-10, "epoch": 2.9411764705882355, "percentage": 98.57, "elapsed_time": "2:50:20", "remaining_time": "0:02:28"}
+{"current_steps": 279, "total_steps": 279, "epoch": 2.983957219251337, "percentage": 100.0, "elapsed_time": "2:53:08", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,947 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.983957219251337,
+  "eval_steps": 50,
+  "global_step": 279,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.053475935828877004,
+      "grad_norm": 75.08688576643534,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.740462064743042,
+      "logits/rejected": -2.7282073497772217,
+      "logps/chosen": -257.7225646972656,
+      "logps/rejected": -215.97402954101562,
+      "loss": 0.6903,
+      "rewards/accuracies": 0.3125,
+      "rewards/chosen": 0.011177328415215015,
+      "rewards/margins": 0.0018132120603695512,
+      "rewards/rejected": 0.009364116936922073,
+      "step": 5
+    },
+    {
+      "epoch": 0.10695187165775401,
+      "grad_norm": 55.24172880066687,
+      "learning_rate": 1e-06,
+      "logits/chosen": -2.706225872039795,
+      "logits/rejected": -2.695012092590332,
+      "logps/chosen": -241.26431274414062,
+      "logps/rejected": -213.05960083007812,
+      "loss": 0.6648,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": 0.5042427182197571,
+      "rewards/margins": 0.1558745801448822,
+      "rewards/rejected": 0.3483680784702301,
+      "step": 10
+    },
+    {
+      "epoch": 0.16042780748663102,
+      "grad_norm": 55.35417452063743,
+      "learning_rate": 9.991477798614637e-07,
+      "logits/chosen": -2.567713737487793,
+      "logits/rejected": -2.5728023052215576,
+      "logps/chosen": -252.4267578125,
+      "logps/rejected": -216.68722534179688,
+      "loss": 0.6277,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 1.2536556720733643,
+      "rewards/margins": 0.6526123881340027,
+      "rewards/rejected": 0.6010432839393616,
+      "step": 15
+    },
+    {
+      "epoch": 0.21390374331550802,
+      "grad_norm": 41.54015316305311,
+      "learning_rate": 9.965940245625131e-07,
+      "logits/chosen": -2.49863862991333,
+      "logits/rejected": -2.4633045196533203,
+      "logps/chosen": -239.6151580810547,
+      "logps/rejected": -216.32748413085938,
+      "loss": 0.5937,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": 1.429532766342163,
+      "rewards/margins": 1.0765190124511719,
+      "rewards/rejected": 0.3530138432979584,
+      "step": 20
+    },
+    {
+      "epoch": 0.26737967914438504,
+      "grad_norm": 43.266733978086314,
+      "learning_rate": 9.923474395499264e-07,
+      "logits/chosen": -2.3930270671844482,
+      "logits/rejected": -2.391124725341797,
+      "logps/chosen": -231.81448364257812,
+      "logps/rejected": -213.6909942626953,
+      "loss": 0.5968,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 1.252290964126587,
+      "rewards/margins": 0.7059992551803589,
+      "rewards/rejected": 0.5462917685508728,
+      "step": 25
+    },
+    {
+      "epoch": 0.32085561497326204,
+      "grad_norm": 49.04579174218152,
+      "learning_rate": 9.86422500924775e-07,
+      "logits/chosen": -2.431389093399048,
+      "logits/rejected": -2.420288562774658,
+      "logps/chosen": -233.90640258789062,
+      "logps/rejected": -232.1009521484375,
+      "loss": 0.591,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 1.3160102367401123,
+      "rewards/margins": 1.2142870426177979,
+      "rewards/rejected": 0.10172319412231445,
+      "step": 30
+    },
+    {
+      "epoch": 0.37433155080213903,
+      "grad_norm": 45.76490813889267,
+      "learning_rate": 9.788394060951227e-07,
+      "logits/chosen": -2.5551607608795166,
+      "logits/rejected": -2.560732126235962,
+      "logps/chosen": -243.9866180419922,
+      "logps/rejected": -210.0946044921875,
+      "loss": 0.5951,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": 0.9597422480583191,
+      "rewards/margins": 0.7127350568771362,
+      "rewards/rejected": 0.2470073401927948,
+      "step": 35
+    },
+    {
+      "epoch": 0.42780748663101603,
+      "grad_norm": 35.943159004433745,
+      "learning_rate": 9.696240049254742e-07,
+      "logits/chosen": -2.607058048248291,
+      "logits/rejected": -2.6059868335723877,
+      "logps/chosen": -245.34237670898438,
+      "logps/rejected": -215.133056640625,
+      "loss": 0.5946,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.8869549036026001,
+      "rewards/margins": 1.1748888492584229,
+      "rewards/rejected": -0.2879341244697571,
+      "step": 40
+    },
+    {
+      "epoch": 0.48128342245989303,
+      "grad_norm": 43.25794768968881,
+      "learning_rate": 9.588077116176756e-07,
+      "logits/chosen": -2.5988757610321045,
+      "logits/rejected": -2.587991952896118,
+      "logps/chosen": -279.42425537109375,
+      "logps/rejected": -214.3015594482422,
+      "loss": 0.6027,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.1399929523468018,
+      "rewards/margins": 1.116516351699829,
+      "rewards/rejected": 0.023476576432585716,
+      "step": 45
+    },
+    {
+      "epoch": 0.5347593582887701,
+      "grad_norm": 42.38890964644049,
+      "learning_rate": 9.464273976236516e-07,
+      "logits/chosen": -2.5599303245544434,
+      "logits/rejected": -2.567230701446533,
+      "logps/chosen": -254.52859497070312,
+      "logps/rejected": -213.7172088623047,
+      "loss": 0.6034,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 1.0623753070831299,
+      "rewards/margins": 1.170297622680664,
+      "rewards/rejected": -0.10792229324579239,
+      "step": 50
+    },
+    {
+      "epoch": 0.5347593582887701,
+      "eval_logits/chosen": -2.5372207164764404,
+      "eval_logits/rejected": -2.5304667949676514,
+      "eval_logps/chosen": -232.14488220214844,
+      "eval_logps/rejected": -213.0785675048828,
+      "eval_loss": 0.5868557095527649,
+      "eval_rewards/accuracies": 0.7291666865348816,
+      "eval_rewards/chosen": 0.7400359511375427,
+      "eval_rewards/margins": 0.881316602230072,
+      "eval_rewards/rejected": -0.14128059148788452,
+      "eval_runtime": 178.1115,
+      "eval_samples_per_second": 14.934,
+      "eval_steps_per_second": 0.236,
+      "step": 50
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 35.35460256124788,
+      "learning_rate": 9.325252659550308e-07,
+      "logits/chosen": -2.5456783771514893,
+      "logits/rejected": -2.5366146564483643,
+      "logps/chosen": -250.4248504638672,
+      "logps/rejected": -213.6925048828125,
+      "loss": 0.5728,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.9326599836349487,
+      "rewards/margins": 1.1307684183120728,
+      "rewards/rejected": -0.19810837507247925,
+      "step": 55
+    },
+    {
+      "epoch": 0.6417112299465241,
+      "grad_norm": 36.50601945986719,
+      "learning_rate": 9.171487073181197e-07,
+      "logits/chosen": -2.497873544692993,
+      "logits/rejected": -2.4702892303466797,
+      "logps/chosen": -253.4021453857422,
+      "logps/rejected": -218.5993194580078,
+      "loss": 0.5838,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.9917839169502258,
+      "rewards/margins": 1.002171516418457,
+      "rewards/rejected": -0.010387664660811424,
+      "step": 60
+    },
+    {
+      "epoch": 0.6951871657754011,
+      "grad_norm": 38.76671127630058,
+      "learning_rate": 9.003501385646448e-07,
+      "logits/chosen": -2.4642693996429443,
+      "logits/rejected": -2.444017171859741,
+      "logps/chosen": -231.67507934570312,
+      "logps/rejected": -207.4264678955078,
+      "loss": 0.5857,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.6439246535301208,
+      "rewards/margins": 1.2459630966186523,
+      "rewards/rejected": -0.6020383834838867,
+      "step": 65
+    },
+    {
+      "epoch": 0.7486631016042781,
+      "grad_norm": 58.07607723312624,
+      "learning_rate": 8.821868240089676e-07,
+      "logits/chosen": -2.4684462547302246,
+      "logits/rejected": -2.4463274478912354,
+      "logps/chosen": -249.26455688476562,
+      "logps/rejected": -222.1261749267578,
+      "loss": 0.587,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": 0.7888789772987366,
+      "rewards/margins": 1.0215551853179932,
+      "rewards/rejected": -0.23267626762390137,
+      "step": 70
+    },
+    {
+      "epoch": 0.8021390374331551,
+      "grad_norm": 36.09293428060366,
+      "learning_rate": 8.62720680220876e-07,
+      "logits/chosen": -2.501340866088867,
+      "logits/rejected": -2.4918720722198486,
+      "logps/chosen": -225.94638061523438,
+      "logps/rejected": -218.7044219970703,
+      "loss": 0.5926,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.8816758394241333,
+      "rewards/margins": 0.8755629658699036,
+      "rewards/rejected": 0.006112849805504084,
+      "step": 75
+    },
+    {
+      "epoch": 0.8556149732620321,
+      "grad_norm": 35.74459897866162,
+      "learning_rate": 8.420180649593929e-07,
+      "logits/chosen": -2.487574815750122,
+      "logits/rejected": -2.478224277496338,
+      "logps/chosen": -232.3713836669922,
+      "logps/rejected": -208.5014190673828,
+      "loss": 0.5303,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.8995177149772644,
+      "rewards/margins": 1.0680756568908691,
+      "rewards/rejected": -0.16855797171592712,
+      "step": 80
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 34.953324196432796,
+      "learning_rate": 8.201495509671036e-07,
+      "logits/chosen": -2.4268527030944824,
+      "logits/rejected": -2.394615888595581,
+      "logps/chosen": -247.49609375,
+      "logps/rejected": -214.3662567138672,
+      "loss": 0.5561,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.6183642148971558,
+      "rewards/margins": 1.220983862876892,
+      "rewards/rejected": -0.6026195883750916,
+      "step": 85
+    },
+    {
+      "epoch": 0.9625668449197861,
+      "grad_norm": 31.39573691027677,
+      "learning_rate": 7.971896853961042e-07,
+      "logits/chosen": -2.2767372131347656,
+      "logits/rejected": -2.252058506011963,
+      "logps/chosen": -261.1527099609375,
+      "logps/rejected": -220.43667602539062,
+      "loss": 0.4894,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 0.6145283579826355,
+      "rewards/margins": 2.0016326904296875,
+      "rewards/rejected": -1.3871045112609863,
+      "step": 90
+    },
+    {
+      "epoch": 1.0160427807486632,
+      "grad_norm": 17.75039945985475,
+      "learning_rate": 7.732167356856654e-07,
+      "logits/chosen": -2.166287660598755,
+      "logits/rejected": -2.1111903190612793,
+      "logps/chosen": -252.02944946289062,
+      "logps/rejected": -232.24282836914062,
+      "loss": 0.4711,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": 0.22497756779193878,
+      "rewards/margins": 1.9439351558685303,
+      "rewards/rejected": -1.7189576625823975,
+      "step": 95
+    },
+    {
+      "epoch": 1.0695187165775402,
+      "grad_norm": 23.02216164814203,
+      "learning_rate": 7.48312422757881e-07,
+      "logits/chosen": -2.144843339920044,
+      "logits/rejected": -2.077284336090088,
+      "logps/chosen": -268.06707763671875,
+      "logps/rejected": -234.98910522460938,
+      "loss": 0.2659,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.0067119598388672,
+      "rewards/margins": 2.941673994064331,
+      "rewards/rejected": -1.9349620342254639,
+      "step": 100
+    },
+    {
+      "epoch": 1.0695187165775402,
+      "eval_logits/chosen": -2.1482443809509277,
+      "eval_logits/rejected": -2.1145682334899902,
+      "eval_logps/chosen": -228.6596221923828,
+      "eval_logps/rejected": -215.86151123046875,
+      "eval_loss": 0.5500321388244629,
+      "eval_rewards/accuracies": 0.7678571343421936,
+      "eval_rewards/chosen": 1.0885626077651978,
+      "eval_rewards/margins": 1.508140206336975,
+      "eval_rewards/rejected": -0.419577419757843,
+      "eval_runtime": 178.0144,
+      "eval_samples_per_second": 14.943,
+      "eval_steps_per_second": 0.236,
+      "step": 100
+    },
+    {
+      "epoch": 1.1229946524064172,
+      "grad_norm": 16.09113711061208,
+      "learning_rate": 7.225616424408044e-07,
+      "logits/chosen": -2.157158374786377,
+      "logits/rejected": -2.128385066986084,
+      "logps/chosen": -237.67849731445312,
+      "logps/rejected": -231.83877563476562,
+      "loss": 0.2083,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 2.0537843704223633,
+      "rewards/margins": 3.18843412399292,
+      "rewards/rejected": -1.134649634361267,
+      "step": 105
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 17.181507055460564,
+      "learning_rate": 6.96052176068713e-07,
+      "logits/chosen": -2.2130496501922607,
+      "logits/rejected": -2.1648192405700684,
+      "logps/chosen": -225.992431640625,
+      "logps/rejected": -225.93643188476562,
+      "loss": 0.2286,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 1.768799066543579,
+      "rewards/margins": 2.9698195457458496,
+      "rewards/rejected": -1.2010207176208496,
+      "step": 110
+    },
+    {
+      "epoch": 1.2299465240641712,
+      "grad_norm": 23.325905689437562,
+      "learning_rate": 6.688743912460229e-07,
+      "logits/chosen": -2.257979154586792,
+      "logits/rejected": -2.24532151222229,
+      "logps/chosen": -245.7477569580078,
+      "logps/rejected": -220.7982177734375,
+      "loss": 0.2429,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 1.9697185754776,
+      "rewards/margins": 3.129720687866211,
+      "rewards/rejected": -1.1600019931793213,
+      "step": 115
+    },
+    {
+      "epoch": 1.2834224598930482,
+      "grad_norm": 19.723516785510316,
+      "learning_rate": 6.411209337949213e-07,
+      "logits/chosen": -2.244814395904541,
+      "logits/rejected": -2.2148585319519043,
+      "logps/chosen": -234.61392211914062,
+      "logps/rejected": -258.7725830078125,
+      "loss": 0.2529,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.9211610555648804,
+      "rewards/margins": 4.399371147155762,
+      "rewards/rejected": -2.478209972381592,
+      "step": 120
+    },
+    {
+      "epoch": 1.3368983957219251,
+      "grad_norm": 21.739425991143058,
+      "learning_rate": 6.128864119368233e-07,
+      "logits/chosen": -2.119013547897339,
+      "logits/rejected": -2.083933115005493,
+      "logps/chosen": -228.73965454101562,
+      "logps/rejected": -208.091552734375,
+      "loss": 0.2611,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.3465216159820557,
+      "rewards/margins": 3.1292195320129395,
+      "rewards/rejected": -1.7826979160308838,
+      "step": 125
+    },
+    {
+      "epoch": 1.3903743315508021,
+      "grad_norm": 22.912282028009347,
+      "learning_rate": 5.842670737842467e-07,
+      "logits/chosen": -2.0183815956115723,
+      "logits/rejected": -1.987648367881775,
+      "logps/chosen": -251.6590118408203,
+      "logps/rejected": -229.6842803955078,
+      "loss": 0.2933,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": 1.9206100702285767,
+      "rewards/margins": 3.7730064392089844,
+      "rewards/rejected": -1.8523967266082764,
+      "step": 130
+    },
+    {
+      "epoch": 1.4438502673796791,
+      "grad_norm": 22.11760289550141,
+      "learning_rate": 5.553604792424922e-07,
+      "logits/chosen": -2.0348455905914307,
+      "logits/rejected": -1.9738250970840454,
+      "logps/chosen": -245.8058319091797,
+      "logps/rejected": -270.13043212890625,
+      "loss": 0.2246,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.6829955577850342,
+      "rewards/margins": 3.753596782684326,
+      "rewards/rejected": -2.070600986480713,
+      "step": 135
+    },
+    {
+      "epoch": 1.4973262032085561,
+      "grad_norm": 28.32892420101821,
+      "learning_rate": 5.262651674395798e-07,
+      "logits/chosen": -2.038222312927246,
+      "logits/rejected": -1.9750888347625732,
+      "logps/chosen": -240.39102172851562,
+      "logps/rejected": -231.63534545898438,
+      "loss": 0.2528,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 1.2107157707214355,
+      "rewards/margins": 3.3977603912353516,
+      "rewards/rejected": -2.187044143676758,
+      "step": 140
+    },
+    {
+      "epoch": 1.5508021390374331,
+      "grad_norm": 23.418588451486066,
+      "learning_rate": 4.970803208181314e-07,
+      "logits/chosen": -2.0812251567840576,
+      "logits/rejected": -2.0191798210144043,
+      "logps/chosen": -231.6563720703125,
+      "logps/rejected": -240.78842163085938,
+      "loss": 0.292,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 1.538320779800415,
+      "rewards/margins": 3.8071465492248535,
+      "rewards/rejected": -2.2688257694244385,
+      "step": 145
+    },
+    {
+      "epoch": 1.6042780748663101,
+      "grad_norm": 19.90761377348951,
+      "learning_rate": 4.679054270342702e-07,
+      "logits/chosen": -2.124783992767334,
+      "logits/rejected": -2.077249050140381,
+      "logps/chosen": -235.0903778076172,
+      "logps/rejected": -243.20028686523438,
+      "loss": 0.2599,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.3953964710235596,
+      "rewards/margins": 3.141361951828003,
+      "rewards/rejected": -1.7459657192230225,
+      "step": 150
+    },
+    {
+      "epoch": 1.6042780748663101,
+      "eval_logits/chosen": -2.1441855430603027,
+      "eval_logits/rejected": -2.112197160720825,
+      "eval_logps/chosen": -231.94912719726562,
+      "eval_logps/rejected": -222.50692749023438,
+      "eval_loss": 0.546504020690918,
+      "eval_rewards/accuracies": 0.7678571343421936,
+      "eval_rewards/chosen": 0.7596126198768616,
+      "eval_rewards/margins": 1.8437296152114868,
+      "eval_rewards/rejected": -1.0841171741485596,
+      "eval_runtime": 177.8643,
+      "eval_samples_per_second": 14.955,
+      "eval_steps_per_second": 0.236,
+      "step": 150
+    },
+    {
+      "epoch": 1.6577540106951871,
+      "grad_norm": 21.93947550108777,
+      "learning_rate": 4.3883993981608567e-07,
+      "logits/chosen": -2.181997776031494,
+      "logits/rejected": -2.123137950897217,
+      "logps/chosen": -242.07229614257812,
+      "logps/rejected": -237.5500030517578,
+      "loss": 0.2643,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 1.5722686052322388,
+      "rewards/margins": 3.503065824508667,
+      "rewards/rejected": -1.9307969808578491,
+      "step": 155
+    },
+    {
+      "epoch": 1.7112299465240641,
+      "grad_norm": 24.144023300435187,
+      "learning_rate": 4.0998293993775234e-07,
+      "logits/chosen": -2.226807117462158,
+      "logits/rejected": -2.199307680130005,
+      "logps/chosen": -237.28543090820312,
+      "logps/rejected": -238.6820831298828,
+      "loss": 0.2942,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.480787992477417,
+      "rewards/margins": 3.468074083328247,
+      "rewards/rejected": -1.987285852432251,
+      "step": 160
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 24.407740221287682,
+      "learning_rate": 3.814327974650066e-07,
+      "logits/chosen": -2.258931875228882,
+      "logits/rejected": -2.2550344467163086,
+      "logps/chosen": -239.78543090820312,
+      "logps/rejected": -235.02456665039062,
+      "loss": 0.2401,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 1.147258996963501,
+      "rewards/margins": 3.696079969406128,
+      "rewards/rejected": -2.548820972442627,
+      "step": 165
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 22.96884736732694,
+      "learning_rate": 3.532868364233416e-07,
+      "logits/chosen": -2.2801005840301514,
+      "logits/rejected": -2.2604260444641113,
+      "logps/chosen": -256.41278076171875,
+      "logps/rejected": -237.5870361328125,
+      "loss": 0.2635,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 0.8354307413101196,
+      "rewards/margins": 3.1207101345062256,
+      "rewards/rejected": -2.2852795124053955,
+      "step": 170
+    },
+    {
+      "epoch": 1.8716577540106951,
+      "grad_norm": 21.468713981869463,
+      "learning_rate": 3.256410030320304e-07,
+      "logits/chosen": -2.2765324115753174,
+      "logits/rejected": -2.2345592975616455,
+      "logps/chosen": -226.8909912109375,
+      "logps/rejected": -206.7959442138672,
+      "loss": 0.2622,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": 0.8324386477470398,
+      "rewards/margins": 3.093674659729004,
+      "rewards/rejected": -2.2612357139587402,
+      "step": 175
+    },
+    {
+      "epoch": 1.9251336898395723,
+      "grad_norm": 25.530423897408046,
+      "learning_rate": 2.985895386349233e-07,
+      "logits/chosen": -2.2696175575256348,
+      "logits/rejected": -2.244253635406494,
+      "logps/chosen": -264.6595458984375,
+      "logps/rejected": -227.76455688476562,
+      "loss": 0.296,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 1.391035795211792,
+      "rewards/margins": 3.3874428272247314,
+      "rewards/rejected": -1.99640691280365,
+      "step": 180
+    },
+    {
+      "epoch": 1.9786096256684491,
+      "grad_norm": 23.57510964659792,
+      "learning_rate": 2.7222465844296514e-07,
+      "logits/chosen": -2.2398269176483154,
+      "logits/rejected": -2.2095816135406494,
+      "logps/chosen": -236.76220703125,
+      "logps/rejected": -239.87649536132812,
+      "loss": 0.3228,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.6798350811004639,
+      "rewards/margins": 3.8687007427215576,
+      "rewards/rejected": -2.1888651847839355,
+      "step": 185
+    },
+    {
+      "epoch": 2.0320855614973263,
+      "grad_norm": 11.237636994206616,
+      "learning_rate": 2.466362371835544e-07,
+      "logits/chosen": -2.2077956199645996,
+      "logits/rejected": -2.1770200729370117,
+      "logps/chosen": -253.8419647216797,
+      "logps/rejected": -241.77560424804688,
+      "loss": 0.2084,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.6418447494506836,
+      "rewards/margins": 4.010140419006348,
+      "rewards/rejected": -2.368295431137085,
+      "step": 190
+    },
+    {
+      "epoch": 2.085561497326203,
+      "grad_norm": 14.896733636093304,
+      "learning_rate": 2.2191150272833386e-07,
+      "logits/chosen": -2.168065309524536,
+      "logits/rejected": -2.139242649078369,
+      "logps/chosen": -239.03555297851562,
+      "logps/rejected": -262.7664794921875,
+      "loss": 0.1457,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.6537681818008423,
+      "rewards/margins": 4.138239860534668,
+      "rewards/rejected": -2.484471559524536,
+      "step": 195
+    },
+    {
+      "epoch": 2.1390374331550803,
+      "grad_norm": 15.573127323302417,
+      "learning_rate": 1.9813473874379395e-07,
+      "logits/chosen": -2.1352179050445557,
+      "logits/rejected": -2.1201109886169434,
+      "logps/chosen": -243.68276977539062,
+      "logps/rejected": -257.8447265625,
+      "loss": 0.1366,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 1.748744249343872,
+      "rewards/margins": 4.428500652313232,
+      "rewards/rejected": -2.6797564029693604,
+      "step": 200
+    },
+    {
+      "epoch": 2.1390374331550803,
+      "eval_logits/chosen": -2.1154227256774902,
+      "eval_logits/rejected": -2.0823864936828613,
+      "eval_logps/chosen": -233.65536499023438,
+      "eval_logps/rejected": -225.89039611816406,
+      "eval_loss": 0.5221620202064514,
+      "eval_rewards/accuracies": 0.7857142686843872,
+      "eval_rewards/chosen": 0.5889881253242493,
+      "eval_rewards/margins": 2.0114519596099854,
+      "eval_rewards/rejected": -1.4224637746810913,
+      "eval_runtime": 177.8889,
+      "eval_samples_per_second": 14.953,
+      "eval_steps_per_second": 0.236,
+      "step": 200
+    },
+    {
+      "epoch": 2.192513368983957,
+      "grad_norm": 18.629951176458935,
+      "learning_rate": 1.7538699737832237e-07,
+      "logits/chosen": -2.113478899002075,
+      "logits/rejected": -2.069943904876709,
+      "logps/chosen": -237.72598266601562,
+      "logps/rejected": -261.28759765625,
+      "loss": 0.1322,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.763622522354126,
+      "rewards/margins": 4.295041084289551,
+      "rewards/rejected": -2.531418561935425,
+      "step": 205
+    },
+    {
+      "epoch": 2.2459893048128343,
+      "grad_norm": 14.516798660616674,
+      "learning_rate": 1.5374582296511053e-07,
+      "logits/chosen": -2.103269577026367,
+      "logits/rejected": -2.035609245300293,
+      "logps/chosen": -238.05905151367188,
+      "logps/rejected": -222.5261688232422,
+      "loss": 0.146,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.79998779296875,
+      "rewards/margins": 4.091170310974121,
+      "rewards/rejected": -2.29118275642395,
+      "step": 210
+    },
+    {
+      "epoch": 2.299465240641711,
+      "grad_norm": 17.56968018814267,
+      "learning_rate": 1.3328498768278418e-07,
+      "logits/chosen": -2.057720184326172,
+      "logits/rejected": -2.012430191040039,
+      "logps/chosen": -234.6757049560547,
+      "logps/rejected": -250.71371459960938,
+      "loss": 0.1554,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.705297827720642,
+      "rewards/margins": 4.06239128112793,
+      "rewards/rejected": -2.357093334197998,
+      "step": 215
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 12.58961314545,
+      "learning_rate": 1.1407424007485928e-07,
+      "logits/chosen": -2.0317530632019043,
+      "logits/rejected": -1.9697539806365967,
+      "logps/chosen": -247.4468536376953,
+      "logps/rejected": -237.97738647460938,
+      "loss": 0.1268,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 2.1162328720092773,
+      "rewards/margins": 4.372066020965576,
+      "rewards/rejected": -2.2558329105377197,
+      "step": 220
+    },
+    {
+      "epoch": 2.406417112299465,
+      "grad_norm": 21.013389395031766,
+      "learning_rate": 9.617906728528679e-08,
+      "logits/chosen": -2.0227417945861816,
+      "logits/rejected": -1.967592477798462,
+      "logps/chosen": -222.5628662109375,
+      "logps/rejected": -241.11947631835938,
+      "loss": 0.1401,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 1.6054117679595947,
+      "rewards/margins": 3.956458330154419,
+      "rewards/rejected": -2.3510468006134033,
+      "step": 225
+    },
+    {
+      "epoch": 2.4598930481283423,
+      "grad_norm": 15.57246636151293,
+      "learning_rate": 7.966047182060226e-08,
+      "logits/chosen": -1.9939205646514893,
+      "logits/rejected": -1.947488784790039,
+      "logps/chosen": -233.0928192138672,
+      "logps/rejected": -235.1240692138672,
+      "loss": 0.1625,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.5731914043426514,
+      "rewards/margins": 3.795226573944092,
+      "rewards/rejected": -2.2220349311828613,
+      "step": 230
+    },
+    {
+      "epoch": 2.5133689839572195,
+      "grad_norm": 13.432171621332934,
+      "learning_rate": 6.457476359966684e-08,
+      "logits/chosen": -1.992582082748413,
+      "logits/rejected": -1.917047142982483,
+      "logps/chosen": -227.5784912109375,
+      "logps/rejected": -232.44485473632812,
+      "loss": 0.1397,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.6688787937164307,
+      "rewards/margins": 3.8221230506896973,
+      "rewards/rejected": -2.1532444953918457,
+      "step": 235
+    },
+    {
+      "epoch": 2.5668449197860963,
+      "grad_norm": 17.803144360723795,
+      "learning_rate": 5.097336799988067e-08,
+      "logits/chosen": -1.9870818853378296,
+      "logits/rejected": -1.9163825511932373,
+      "logps/chosen": -236.98666381835938,
+      "logps/rejected": -237.57760620117188,
+      "loss": 0.1576,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.9307695627212524,
+      "rewards/margins": 4.332042217254639,
+      "rewards/rejected": -2.4012725353240967,
+      "step": 240
+    },
+    {
+      "epoch": 2.620320855614973,
+      "grad_norm": 17.516307037134144,
+      "learning_rate": 3.8902650554212826e-08,
+      "logits/chosen": -1.971273422241211,
+      "logits/rejected": -1.9711790084838867,
+      "logps/chosen": -243.27542114257812,
+      "logps/rejected": -231.23574829101562,
+      "loss": 0.1618,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 2.017270565032959,
+      "rewards/margins": 4.455116271972656,
+      "rewards/rejected": -2.4378464221954346,
+      "step": 245
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 19.66674156907619,
+      "learning_rate": 2.8403758896638707e-08,
+      "logits/chosen": -1.9871242046356201,
+      "logits/rejected": -1.9288272857666016,
+      "logps/chosen": -238.3242645263672,
+      "logps/rejected": -238.7816162109375,
+      "loss": 0.1488,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.674863576889038,
+      "rewards/margins": 4.010067939758301,
+      "rewards/rejected": -2.335204839706421,
+      "step": 250
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "eval_logits/chosen": -1.97805917263031,
+      "eval_logits/rejected": -1.932228446006775,
+      "eval_logps/chosen": -233.5652618408203,
+      "eval_logps/rejected": -226.9253387451172,
+      "eval_loss": 0.5411336421966553,
+      "eval_rewards/accuracies": 0.7767857313156128,
+      "eval_rewards/chosen": 0.5979987382888794,
+      "eval_rewards/margins": 2.1239590644836426,
+      "eval_rewards/rejected": -1.5259599685668945,
+      "eval_runtime": 178.7366,
+      "eval_samples_per_second": 14.882,
+      "eval_steps_per_second": 0.235,
+      "step": 250
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 20.207169205524593,
+      "learning_rate": 1.951248249476961e-08,
+      "logits/chosen": -1.9819082021713257,
+      "logits/rejected": -1.9226843118667603,
+      "logps/chosen": -231.9635009765625,
+      "logps/rejected": -247.98446655273438,
+      "loss": 0.1533,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.6299917697906494,
+      "rewards/margins": 4.123189449310303,
+      "rewards/rejected": -2.4931979179382324,
+      "step": 255
+    },
+    {
+      "epoch": 2.7807486631016043,
+      "grad_norm": 16.578647534749194,
+      "learning_rate": 1.2259130647833626e-08,
+      "logits/chosen": -1.9796741008758545,
+      "logits/rejected": -1.9408137798309326,
+      "logps/chosen": -235.86093139648438,
+      "logps/rejected": -228.4602813720703,
+      "loss": 0.1239,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": 1.7039449214935303,
+      "rewards/margins": 4.0229291915893555,
+      "rewards/rejected": -2.3189845085144043,
+      "step": 260
+    },
+    {
+      "epoch": 2.834224598930481,
+      "grad_norm": 16.969502053181888,
+      "learning_rate": 6.668429165893996e-09,
+      "logits/chosen": -1.9918749332427979,
+      "logits/rejected": -1.9296365976333618,
+      "logps/chosen": -262.6291809082031,
+      "logps/rejected": -232.1147918701172,
+      "loss": 0.1353,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.8621528148651123,
+      "rewards/margins": 4.288115501403809,
+      "rewards/rejected": -2.4259629249572754,
+      "step": 265
+    },
+    {
+      "epoch": 2.8877005347593583,
+      "grad_norm": 14.34594308225596,
+      "learning_rate": 2.759436082516664e-09,
+      "logits/chosen": -1.991707444190979,
+      "logits/rejected": -1.9247620105743408,
+      "logps/chosen": -240.2772674560547,
+      "logps/rejected": -234.63717651367188,
+      "loss": 0.1532,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.6390937566757202,
+      "rewards/margins": 4.325857162475586,
+      "rewards/rejected": -2.686763286590576,
+      "step": 270
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 14.078396993164128,
+      "learning_rate": 5.454766882097006e-10,
+      "logits/chosen": -1.9781386852264404,
+      "logits/rejected": -1.933526635169983,
+      "logps/chosen": -232.15744018554688,
+      "logps/rejected": -263.4436340332031,
+      "loss": 0.1405,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 1.8876819610595703,
+      "rewards/margins": 4.5024919509887695,
+      "rewards/rejected": -2.6148104667663574,
+      "step": 275
+    },
+    {
+      "epoch": 2.983957219251337,
+      "step": 279,
+      "total_flos": 3289753017384960.0,
+      "train_loss": 0.3334879027045329,
+      "train_runtime": 10390.4498,
+      "train_samples_per_second": 6.91,
+      "train_steps_per_second": 0.027
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 279,
+  "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": 3289753017384960.0,
+  "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 sha256:3efcf6c04d2a7322424cc9195c9949efae8775190d44b93fe40217c32346813c
+size 7096