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_cosi_new_step10_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_cosi_new_step10_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_cosi_new_step10_0_70 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5004
+- Rewards/chosen: 0.6967
+- Rewards/rejected: -2.0150
+- Rewards/accuracies: 0.8006
+- Rewards/margins: 2.7116
+- Logps/rejected: -216.6696
+- Logps/chosen: -251.2154
+- Logits/rejected: -2.3392
+- Logits/chosen: -2.3776
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5778        | 0.5348 | 50   | 0.5711          | 1.2153         | -0.0689          | 0.7560             | 1.2843          | -197.2090      | -246.0286    | -2.3540         | -2.3824       |
+| 0.232         | 1.0695 | 100  | 0.4935          | 0.9389         | -1.0786          | 0.8036             | 2.0175          | -207.3059      | -248.7935    | -2.4977         | -2.5262       |
+| 0.2427        | 1.6043 | 150  | 0.4994          | 0.6147         | -1.7279          | 0.8185             | 2.3426          | -213.7988      | -252.0355    | -2.1963         | -2.2464       |
+| 0.1239        | 2.1390 | 200  | 0.4941          | 0.6670         | -1.8992          | 0.8065             | 2.5662          | -215.5122      | -251.5120    | -2.3605         | -2.3958       |
+| 0.1607        | 2.6738 | 250  | 0.5006          | 0.6972         | -2.0217          | 0.8006             | 2.7190          | -216.7369      | -251.2096    | -2.3349         | -2.3732       |
+
+
+### 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": -2.377612590789795,
+    "eval_logits/rejected": -2.3392257690429688,
+    "eval_logps/chosen": -251.21542358398438,
+    "eval_logps/rejected": -216.66961669921875,
+    "eval_loss": 0.5004006028175354,
+    "eval_rewards/accuracies": 0.800595223903656,
+    "eval_rewards/chosen": 0.6966643929481506,
+    "eval_rewards/margins": 2.7116470336914062,
+    "eval_rewards/rejected": -2.014982223510742,
+    "eval_runtime": 176.0961,
+    "eval_samples_per_second": 15.105,
+    "eval_steps_per_second": 0.239,
+    "total_flos": 3289753017384960.0,
+    "train_loss": 0.3301437693684759,
+    "train_runtime": 10405.088,
+    "train_samples_per_second": 6.9,
+    "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": -2.377612590789795,
+    "eval_logits/rejected": -2.3392257690429688,
+    "eval_logps/chosen": -251.21542358398438,
+    "eval_logps/rejected": -216.66961669921875,
+    "eval_loss": 0.5004006028175354,
+    "eval_rewards/accuracies": 0.800595223903656,
+    "eval_rewards/chosen": 0.6966643929481506,
+    "eval_rewards/margins": 2.7116470336914062,
+    "eval_rewards/rejected": -2.014982223510742,
+    "eval_runtime": 176.0961,
+    "eval_samples_per_second": 15.105,
+    "eval_steps_per_second": 0.239
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3986e8c08adbf289e04e829ca27dce208a4170477e901bb0b874164c731509dd
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e274b77e90edcb2fc4bea3cb98547223357e37113dfb12a0e0924d5883ed765
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b2f9c2bf97600525be2bc0b1dfa0aff97dc085af2f0b00c6a87b79da98b167
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0036fdf73bd755ddef97daa770b95f95f64adb9bffcfb68340eb03c33b265360
+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": 0.3301437693684759,
+    "train_runtime": 10405.088,
+    "train_samples_per_second": 6.9,
+    "train_steps_per_second": 0.027
+}

trainer_log.jsonl

@@ -0,0 +1,61 @@
+{"current_steps": 5, "total_steps": 279, "loss": 0.6907, "accuracy": 0.3499999940395355, "learning_rate": 5e-07, "epoch": 0.053475935828877004, "percentage": 1.79, "elapsed_time": "0:02:54", "remaining_time": "2:39:16"}
+{"current_steps": 10, "total_steps": 279, "loss": 0.6381, "accuracy": 0.606249988079071, "learning_rate": 1e-06, "epoch": 0.10695187165775401, "percentage": 3.58, "elapsed_time": "0:05:42", "remaining_time": "2:33:40"}
+{"current_steps": 15, "total_steps": 279, "loss": 0.6476, "accuracy": 0.75, "learning_rate": 9.991477798614637e-07, "epoch": 0.16042780748663102, "percentage": 5.38, "elapsed_time": "0:08:30", "remaining_time": "2:29:43"}
+{"current_steps": 20, "total_steps": 279, "loss": 0.6411, "accuracy": 0.7875000238418579, "learning_rate": 9.965940245625131e-07, "epoch": 0.21390374331550802, "percentage": 7.17, "elapsed_time": "0:11:18", "remaining_time": "2:26:32"}
+{"current_steps": 25, "total_steps": 279, "loss": 0.6356, "accuracy": 0.6937500238418579, "learning_rate": 9.923474395499264e-07, "epoch": 0.26737967914438504, "percentage": 8.96, "elapsed_time": "0:14:07", "remaining_time": "2:23:29"}
+{"current_steps": 30, "total_steps": 279, "loss": 0.5918, "accuracy": 0.668749988079071, "learning_rate": 9.86422500924775e-07, "epoch": 0.32085561497326204, "percentage": 10.75, "elapsed_time": "0:16:56", "remaining_time": "2:20:37"}
+{"current_steps": 35, "total_steps": 279, "loss": 0.6045, "accuracy": 0.6937500238418579, "learning_rate": 9.788394060951227e-07, "epoch": 0.37433155080213903, "percentage": 12.54, "elapsed_time": "0:19:45", "remaining_time": "2:17:45"}
+{"current_steps": 40, "total_steps": 279, "loss": 0.6251, "accuracy": 0.737500011920929, "learning_rate": 9.696240049254742e-07, "epoch": 0.42780748663101603, "percentage": 14.34, "elapsed_time": "0:22:33", "remaining_time": "2:14:49"}
+{"current_steps": 45, "total_steps": 279, "loss": 0.6052, "accuracy": 0.731249988079071, "learning_rate": 9.588077116176756e-07, "epoch": 0.48128342245989303, "percentage": 16.13, "elapsed_time": "0:25:22", "remaining_time": "2:11:59"}
+{"current_steps": 50, "total_steps": 279, "loss": 0.5778, "accuracy": 0.7124999761581421, "learning_rate": 9.464273976236516e-07, "epoch": 0.5347593582887701, "percentage": 17.92, "elapsed_time": "0:28:12", "remaining_time": "2:09:10"}
+{"current_steps": 50, "total_steps": 279, "eval_loss": 0.5711008310317993, "epoch": 0.5347593582887701, "percentage": 17.92, "elapsed_time": "0:31:10", "remaining_time": "2:22:46"}
+{"current_steps": 55, "total_steps": 279, "loss": 0.5385, "accuracy": 0.737500011920929, "learning_rate": 9.325252659550308e-07, "epoch": 0.5882352941176471, "percentage": 19.71, "elapsed_time": "0:33:59", "remaining_time": "2:18:26"}
+{"current_steps": 60, "total_steps": 279, "loss": 0.5661, "accuracy": 0.7875000238418579, "learning_rate": 9.171487073181197e-07, "epoch": 0.6417112299465241, "percentage": 21.51, "elapsed_time": "0:36:48", "remaining_time": "2:14:21"}
+{"current_steps": 65, "total_steps": 279, "loss": 0.5596, "accuracy": 0.8125, "learning_rate": 9.003501385646448e-07, "epoch": 0.6951871657754011, "percentage": 23.3, "elapsed_time": "0:39:38", "remaining_time": "2:10:29"}
+{"current_steps": 70, "total_steps": 279, "loss": 0.5263, "accuracy": 0.762499988079071, "learning_rate": 8.821868240089676e-07, "epoch": 0.7486631016042781, "percentage": 25.09, "elapsed_time": "0:42:27", "remaining_time": "2:06:44"}
+{"current_steps": 75, "total_steps": 279, "loss": 0.5073, "accuracy": 0.731249988079071, "learning_rate": 8.62720680220876e-07, "epoch": 0.8021390374331551, "percentage": 26.88, "elapsed_time": "0:45:15", "remaining_time": "2:03:05"}
+{"current_steps": 80, "total_steps": 279, "loss": 0.5523, "accuracy": 0.7875000238418579, "learning_rate": 8.420180649593929e-07, "epoch": 0.8556149732620321, "percentage": 28.67, "elapsed_time": "0:48:04", "remaining_time": "1:59:34"}
+{"current_steps": 85, "total_steps": 279, "loss": 0.5362, "accuracy": 0.762499988079071, "learning_rate": 8.201495509671036e-07, "epoch": 0.9090909090909091, "percentage": 30.47, "elapsed_time": "0:50:51", "remaining_time": "1:56:05"}
+{"current_steps": 90, "total_steps": 279, "loss": 0.5064, "accuracy": 0.7437499761581421, "learning_rate": 7.971896853961042e-07, "epoch": 0.9625668449197861, "percentage": 32.26, "elapsed_time": "0:53:41", "remaining_time": "1:52:44"}
+{"current_steps": 95, "total_steps": 279, "loss": 0.4555, "accuracy": 0.824999988079071, "learning_rate": 7.732167356856654e-07, "epoch": 1.0160427807486632, "percentage": 34.05, "elapsed_time": "0:56:29", "remaining_time": "1:49:24"}
+{"current_steps": 100, "total_steps": 279, "loss": 0.232, "accuracy": 0.90625, "learning_rate": 7.48312422757881e-07, "epoch": 1.0695187165775402, "percentage": 35.84, "elapsed_time": "0:59:18", "remaining_time": "1:46:10"}
+{"current_steps": 100, "total_steps": 279, "eval_loss": 0.49347466230392456, "epoch": 1.0695187165775402, "percentage": 35.84, "elapsed_time": "1:02:15", "remaining_time": "1:51:27"}
+{"current_steps": 105, "total_steps": 279, "loss": 0.2233, "accuracy": 0.9125000238418579, "learning_rate": 7.225616424408044e-07, "epoch": 1.1229946524064172, "percentage": 37.63, "elapsed_time": "1:05:38", "remaining_time": "1:48:47"}
+{"current_steps": 110, "total_steps": 279, "loss": 0.2622, "accuracy": 0.9437500238418579, "learning_rate": 6.96052176068713e-07, "epoch": 1.1764705882352942, "percentage": 39.43, "elapsed_time": "1:08:27", "remaining_time": "1:45:10"}
+{"current_steps": 115, "total_steps": 279, "loss": 0.2755, "accuracy": 0.887499988079071, "learning_rate": 6.688743912460229e-07, "epoch": 1.2299465240641712, "percentage": 41.22, "elapsed_time": "1:11:15", "remaining_time": "1:41:36"}
+{"current_steps": 120, "total_steps": 279, "loss": 0.2087, "accuracy": 0.925000011920929, "learning_rate": 6.411209337949213e-07, "epoch": 1.2834224598930482, "percentage": 43.01, "elapsed_time": "1:14:03", "remaining_time": "1:38:07"}
+{"current_steps": 125, "total_steps": 279, "loss": 0.311, "accuracy": 0.893750011920929, "learning_rate": 6.128864119368233e-07, "epoch": 1.3368983957219251, "percentage": 44.8, "elapsed_time": "1:16:51", "remaining_time": "1:34:41"}
+{"current_steps": 130, "total_steps": 279, "loss": 0.2738, "accuracy": 0.925000011920929, "learning_rate": 5.842670737842467e-07, "epoch": 1.3903743315508021, "percentage": 46.59, "elapsed_time": "1:19:40", "remaining_time": "1:31:19"}
+{"current_steps": 135, "total_steps": 279, "loss": 0.2369, "accuracy": 0.90625, "learning_rate": 5.553604792424922e-07, "epoch": 1.4438502673796791, "percentage": 48.39, "elapsed_time": "1:22:29", "remaining_time": "1:27:59"}
+{"current_steps": 140, "total_steps": 279, "loss": 0.2554, "accuracy": 0.887499988079071, "learning_rate": 5.262651674395798e-07, "epoch": 1.4973262032085561, "percentage": 50.18, "elapsed_time": "1:25:18", "remaining_time": "1:24:41"}
+{"current_steps": 145, "total_steps": 279, "loss": 0.2808, "accuracy": 0.8812500238418579, "learning_rate": 4.970803208181314e-07, "epoch": 1.5508021390374331, "percentage": 51.97, "elapsed_time": "1:28:07", "remaining_time": "1:21:26"}
+{"current_steps": 150, "total_steps": 279, "loss": 0.2427, "accuracy": 0.893750011920929, "learning_rate": 4.679054270342702e-07, "epoch": 1.6042780748663101, "percentage": 53.76, "elapsed_time": "1:30:55", "remaining_time": "1:18:11"}
+{"current_steps": 150, "total_steps": 279, "eval_loss": 0.4994485378265381, "epoch": 1.6042780748663101, "percentage": 53.76, "elapsed_time": "1:33:52", "remaining_time": "1:20:43"}
+{"current_steps": 155, "total_steps": 279, "loss": 0.2553, "accuracy": 0.9125000238418579, "learning_rate": 4.3883993981608567e-07, "epoch": 1.6577540106951871, "percentage": 55.56, "elapsed_time": "1:36:40", "remaining_time": "1:17:20"}
+{"current_steps": 160, "total_steps": 279, "loss": 0.2627, "accuracy": 0.8999999761581421, "learning_rate": 4.0998293993775234e-07, "epoch": 1.7112299465240641, "percentage": 57.35, "elapsed_time": "1:39:28", "remaining_time": "1:13:58"}
+{"current_steps": 165, "total_steps": 279, "loss": 0.2499, "accuracy": 0.90625, "learning_rate": 3.814327974650066e-07, "epoch": 1.7647058823529411, "percentage": 59.14, "elapsed_time": "1:42:16", "remaining_time": "1:10:39"}
+{"current_steps": 170, "total_steps": 279, "loss": 0.2275, "accuracy": 0.918749988079071, "learning_rate": 3.532868364233416e-07, "epoch": 1.8181818181818183, "percentage": 60.93, "elapsed_time": "1:45:05", "remaining_time": "1:07:22"}
+{"current_steps": 175, "total_steps": 279, "loss": 0.2749, "accuracy": 0.893750011920929, "learning_rate": 3.256410030320304e-07, "epoch": 1.8716577540106951, "percentage": 62.72, "elapsed_time": "1:47:53", "remaining_time": "1:04:07"}
+{"current_steps": 180, "total_steps": 279, "loss": 0.2368, "accuracy": 0.9375, "learning_rate": 2.985895386349233e-07, "epoch": 1.9251336898395723, "percentage": 64.52, "elapsed_time": "1:50:43", "remaining_time": "1:00:54"}
+{"current_steps": 185, "total_steps": 279, "loss": 0.2766, "accuracy": 0.887499988079071, "learning_rate": 2.7222465844296514e-07, "epoch": 1.9786096256684491, "percentage": 66.31, "elapsed_time": "1:53:33", "remaining_time": "0:57:42"}
+{"current_steps": 190, "total_steps": 279, "loss": 0.1829, "accuracy": 0.9624999761581421, "learning_rate": 2.466362371835544e-07, "epoch": 2.0320855614973263, "percentage": 68.1, "elapsed_time": "1:56:22", "remaining_time": "0:54:30"}
+{"current_steps": 195, "total_steps": 279, "loss": 0.1495, "accuracy": 0.949999988079071, "learning_rate": 2.2191150272833386e-07, "epoch": 2.085561497326203, "percentage": 69.89, "elapsed_time": "1:59:10", "remaining_time": "0:51:20"}
+{"current_steps": 200, "total_steps": 279, "loss": 0.1239, "accuracy": 0.956250011920929, "learning_rate": 1.9813473874379395e-07, "epoch": 2.1390374331550803, "percentage": 71.68, "elapsed_time": "2:01:58", "remaining_time": "0:48:10"}
+{"current_steps": 200, "total_steps": 279, "eval_loss": 0.4940880835056305, "epoch": 2.1390374331550803, "percentage": 71.68, "elapsed_time": "2:04:55", "remaining_time": "0:49:20"}
+{"current_steps": 205, "total_steps": 279, "loss": 0.1469, "accuracy": 0.96875, "learning_rate": 1.7538699737832237e-07, "epoch": 2.192513368983957, "percentage": 73.48, "elapsed_time": "2:08:16", "remaining_time": "0:46:18"}
+{"current_steps": 210, "total_steps": 279, "loss": 0.1481, "accuracy": 0.949999988079071, "learning_rate": 1.5374582296511053e-07, "epoch": 2.2459893048128343, "percentage": 75.27, "elapsed_time": "2:11:03", "remaining_time": "0:43:03"}
+{"current_steps": 215, "total_steps": 279, "loss": 0.1182, "accuracy": 0.9624999761581421, "learning_rate": 1.3328498768278418e-07, "epoch": 2.299465240641711, "percentage": 77.06, "elapsed_time": "2:13:52", "remaining_time": "0:39:51"}
+{"current_steps": 220, "total_steps": 279, "loss": 0.1353, "accuracy": 0.9624999761581421, "learning_rate": 1.1407424007485928e-07, "epoch": 2.3529411764705883, "percentage": 78.85, "elapsed_time": "2:16:42", "remaining_time": "0:36:39"}
+{"current_steps": 225, "total_steps": 279, "loss": 0.1406, "accuracy": 0.9750000238418579, "learning_rate": 9.617906728528679e-08, "epoch": 2.406417112299465, "percentage": 80.65, "elapsed_time": "2:19:31", "remaining_time": "0:33:29"}
+{"current_steps": 230, "total_steps": 279, "loss": 0.137, "accuracy": 0.9437500238418579, "learning_rate": 7.966047182060226e-08, "epoch": 2.4598930481283423, "percentage": 82.44, "elapsed_time": "2:22:20", "remaining_time": "0:30:19"}
+{"current_steps": 235, "total_steps": 279, "loss": 0.1324, "accuracy": 0.981249988079071, "learning_rate": 6.457476359966684e-08, "epoch": 2.5133689839572195, "percentage": 84.23, "elapsed_time": "2:25:07", "remaining_time": "0:27:10"}
+{"current_steps": 240, "total_steps": 279, "loss": 0.1575, "accuracy": 0.949999988079071, "learning_rate": 5.097336799988067e-08, "epoch": 2.5668449197860963, "percentage": 86.02, "elapsed_time": "2:27:56", "remaining_time": "0:24:02"}
+{"current_steps": 245, "total_steps": 279, "loss": 0.1404, "accuracy": 0.9375, "learning_rate": 3.8902650554212826e-08, "epoch": 2.620320855614973, "percentage": 87.81, "elapsed_time": "2:30:46", "remaining_time": "0:20:55"}
+{"current_steps": 250, "total_steps": 279, "loss": 0.1607, "accuracy": 0.96875, "learning_rate": 2.8403758896638707e-08, "epoch": 2.6737967914438503, "percentage": 89.61, "elapsed_time": "2:33:34", "remaining_time": "0:17:48"}
+{"current_steps": 250, "total_steps": 279, "eval_loss": 0.5006157755851746, "epoch": 2.6737967914438503, "percentage": 89.61, "elapsed_time": "2:36:32", "remaining_time": "0:18:09"}
+{"current_steps": 255, "total_steps": 279, "loss": 0.1515, "accuracy": 0.949999988079071, "learning_rate": 1.951248249476961e-08, "epoch": 2.7272727272727275, "percentage": 91.4, "elapsed_time": "2:39:21", "remaining_time": "0:14:59"}
+{"current_steps": 260, "total_steps": 279, "loss": 0.1517, "accuracy": 0.949999988079071, "learning_rate": 1.2259130647833626e-08, "epoch": 2.7807486631016043, "percentage": 93.19, "elapsed_time": "2:42:10", "remaining_time": "0:11:51"}
+{"current_steps": 265, "total_steps": 279, "loss": 0.1479, "accuracy": 0.9125000238418579, "learning_rate": 6.668429165893996e-09, "epoch": 2.834224598930481, "percentage": 94.98, "elapsed_time": "2:45:00", "remaining_time": "0:08:43"}
+{"current_steps": 270, "total_steps": 279, "loss": 0.1573, "accuracy": 0.9375, "learning_rate": 2.759436082516664e-09, "epoch": 2.8877005347593583, "percentage": 96.77, "elapsed_time": "2:47:49", "remaining_time": "0:05:35"}
+{"current_steps": 275, "total_steps": 279, "loss": 0.1708, "accuracy": 0.918749988079071, "learning_rate": 5.454766882097006e-10, "epoch": 2.9411764705882355, "percentage": 98.57, "elapsed_time": "2:50:37", "remaining_time": "0:02:28"}
+{"current_steps": 279, "total_steps": 279, "epoch": 2.983957219251337, "percentage": 100.0, "elapsed_time": "2:53:23", "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": 65.08164204257967,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.733124017715454,
+      "logits/rejected": -2.7089576721191406,
+      "logps/chosen": -271.7913818359375,
+      "logps/rejected": -220.1679229736328,
+      "loss": 0.6907,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 0.01848032884299755,
+      "rewards/margins": 0.006348843220621347,
+      "rewards/rejected": 0.01213148795068264,
+      "step": 5
+    },
+    {
+      "epoch": 0.10695187165775401,
+      "grad_norm": 50.59833986698045,
+      "learning_rate": 1e-06,
+      "logits/chosen": -2.66473388671875,
+      "logits/rejected": -2.6718990802764893,
+      "logps/chosen": -258.00506591796875,
+      "logps/rejected": -206.7321319580078,
+      "loss": 0.6381,
+      "rewards/accuracies": 0.606249988079071,
+      "rewards/chosen": 0.5401543378829956,
+      "rewards/margins": 0.19901855289936066,
+      "rewards/rejected": 0.3411358594894409,
+      "step": 10
+    },
+    {
+      "epoch": 0.16042780748663102,
+      "grad_norm": 50.14290028396245,
+      "learning_rate": 9.991477798614637e-07,
+      "logits/chosen": -2.508185863494873,
+      "logits/rejected": -2.524341106414795,
+      "logps/chosen": -271.5559997558594,
+      "logps/rejected": -203.901123046875,
+      "loss": 0.6476,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.8893938064575195,
+      "rewards/margins": 0.9772478342056274,
+      "rewards/rejected": 0.9121459126472473,
+      "step": 15
+    },
+    {
+      "epoch": 0.21390374331550802,
+      "grad_norm": 42.09940353495551,
+      "learning_rate": 9.965940245625131e-07,
+      "logits/chosen": -2.3450875282287598,
+      "logits/rejected": -2.3332550525665283,
+      "logps/chosen": -231.1672821044922,
+      "logps/rejected": -189.68919372558594,
+      "loss": 0.6411,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 1.9618078470230103,
+      "rewards/margins": 1.288054347038269,
+      "rewards/rejected": 0.6737534403800964,
+      "step": 20
+    },
+    {
+      "epoch": 0.26737967914438504,
+      "grad_norm": 50.008448633201716,
+      "learning_rate": 9.923474395499264e-07,
+      "logits/chosen": -2.2368509769439697,
+      "logits/rejected": -2.2110252380371094,
+      "logps/chosen": -238.6009063720703,
+      "logps/rejected": -201.56163024902344,
+      "loss": 0.6356,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": 1.4835152626037598,
+      "rewards/margins": 0.7462359666824341,
+      "rewards/rejected": 0.7372792959213257,
+      "step": 25
+    },
+    {
+      "epoch": 0.32085561497326204,
+      "grad_norm": 37.46999153089867,
+      "learning_rate": 9.86422500924775e-07,
+      "logits/chosen": -2.279388904571533,
+      "logits/rejected": -2.2622551918029785,
+      "logps/chosen": -210.3643798828125,
+      "logps/rejected": -200.84750366210938,
+      "loss": 0.5918,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": 1.0033924579620361,
+      "rewards/margins": 0.8053790330886841,
+      "rewards/rejected": 0.1980135291814804,
+      "step": 30
+    },
+    {
+      "epoch": 0.37433155080213903,
+      "grad_norm": 40.36951895662085,
+      "learning_rate": 9.788394060951227e-07,
+      "logits/chosen": -2.380889654159546,
+      "logits/rejected": -2.3877792358398438,
+      "logps/chosen": -242.85470581054688,
+      "logps/rejected": -207.0241241455078,
+      "loss": 0.6045,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": 0.8806816935539246,
+      "rewards/margins": 0.9049984812736511,
+      "rewards/rejected": -0.024316836148500443,
+      "step": 35
+    },
+    {
+      "epoch": 0.42780748663101603,
+      "grad_norm": 49.54969179550948,
+      "learning_rate": 9.696240049254742e-07,
+      "logits/chosen": -2.361086368560791,
+      "logits/rejected": -2.358868360519409,
+      "logps/chosen": -250.7805633544922,
+      "logps/rejected": -223.0339813232422,
+      "loss": 0.6251,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.8420997858047485,
+      "rewards/margins": 1.0070801973342896,
+      "rewards/rejected": -0.16498039662837982,
+      "step": 40
+    },
+    {
+      "epoch": 0.48128342245989303,
+      "grad_norm": 38.326754460806335,
+      "learning_rate": 9.588077116176756e-07,
+      "logits/chosen": -2.3445451259613037,
+      "logits/rejected": -2.329608917236328,
+      "logps/chosen": -244.2638702392578,
+      "logps/rejected": -213.9591522216797,
+      "loss": 0.6052,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": 0.9911876916885376,
+      "rewards/margins": 0.9155967831611633,
+      "rewards/rejected": 0.07559084892272949,
+      "step": 45
+    },
+    {
+      "epoch": 0.5347593582887701,
+      "grad_norm": 41.70114459904792,
+      "learning_rate": 9.464273976236516e-07,
+      "logits/chosen": -2.3615097999572754,
+      "logits/rejected": -2.375725269317627,
+      "logps/chosen": -235.63998413085938,
+      "logps/rejected": -205.462158203125,
+      "loss": 0.5778,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.0482008457183838,
+      "rewards/margins": 1.3194622993469238,
+      "rewards/rejected": -0.27126139402389526,
+      "step": 50
+    },
+    {
+      "epoch": 0.5347593582887701,
+      "eval_logits/chosen": -2.382444381713867,
+      "eval_logits/rejected": -2.353994369506836,
+      "eval_logps/chosen": -246.02862548828125,
+      "eval_logps/rejected": -197.20895385742188,
+      "eval_loss": 0.5711008310317993,
+      "eval_rewards/accuracies": 0.7559523582458496,
+      "eval_rewards/chosen": 1.21534264087677,
+      "eval_rewards/margins": 1.2842590808868408,
+      "eval_rewards/rejected": -0.0689164251089096,
+      "eval_runtime": 178.2179,
+      "eval_samples_per_second": 14.926,
+      "eval_steps_per_second": 0.236,
+      "step": 50
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 37.61770640976083,
+      "learning_rate": 9.325252659550308e-07,
+      "logits/chosen": -2.4103198051452637,
+      "logits/rejected": -2.375884532928467,
+      "logps/chosen": -232.7388458251953,
+      "logps/rejected": -197.4444122314453,
+      "loss": 0.5385,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 1.110247015953064,
+      "rewards/margins": 1.345210075378418,
+      "rewards/rejected": -0.23496298491954803,
+      "step": 55
+    },
+    {
+      "epoch": 0.6417112299465241,
+      "grad_norm": 36.284977037429975,
+      "learning_rate": 9.171487073181197e-07,
+      "logits/chosen": -2.45546817779541,
+      "logits/rejected": -2.4268698692321777,
+      "logps/chosen": -264.7644958496094,
+      "logps/rejected": -237.2240753173828,
+      "loss": 0.5661,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 1.084460973739624,
+      "rewards/margins": 1.5218535661697388,
+      "rewards/rejected": -0.4373924136161804,
+      "step": 60
+    },
+    {
+      "epoch": 0.6951871657754011,
+      "grad_norm": 37.36342990536676,
+      "learning_rate": 9.003501385646448e-07,
+      "logits/chosen": -2.4519729614257812,
+      "logits/rejected": -2.4639739990234375,
+      "logps/chosen": -251.09231567382812,
+      "logps/rejected": -201.4525909423828,
+      "loss": 0.5596,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 1.1350815296173096,
+      "rewards/margins": 1.5527232885360718,
+      "rewards/rejected": -0.4176417887210846,
+      "step": 65
+    },
+    {
+      "epoch": 0.7486631016042781,
+      "grad_norm": 33.50003576842058,
+      "learning_rate": 8.821868240089676e-07,
+      "logits/chosen": -2.400097608566284,
+      "logits/rejected": -2.377209186553955,
+      "logps/chosen": -265.53155517578125,
+      "logps/rejected": -226.5992431640625,
+      "loss": 0.5263,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 0.7660782337188721,
+      "rewards/margins": 1.5463287830352783,
+      "rewards/rejected": -0.7802505493164062,
+      "step": 70
+    },
+    {
+      "epoch": 0.8021390374331551,
+      "grad_norm": 35.415664255337724,
+      "learning_rate": 8.62720680220876e-07,
+      "logits/chosen": -2.389862060546875,
+      "logits/rejected": -2.379544258117676,
+      "logps/chosen": -250.21115112304688,
+      "logps/rejected": -234.2509765625,
+      "loss": 0.5073,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": 0.7700754404067993,
+      "rewards/margins": 1.3676471710205078,
+      "rewards/rejected": -0.597571849822998,
+      "step": 75
+    },
+    {
+      "epoch": 0.8556149732620321,
+      "grad_norm": 38.29403188930404,
+      "learning_rate": 8.420180649593929e-07,
+      "logits/chosen": -2.42349910736084,
+      "logits/rejected": -2.4062836170196533,
+      "logps/chosen": -261.1897277832031,
+      "logps/rejected": -225.38619995117188,
+      "loss": 0.5523,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.5706126689910889,
+      "rewards/margins": 1.5985792875289917,
+      "rewards/rejected": -1.0279667377471924,
+      "step": 80
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 34.7463437300499,
+      "learning_rate": 8.201495509671036e-07,
+      "logits/chosen": -2.4246888160705566,
+      "logits/rejected": -2.438143253326416,
+      "logps/chosen": -259.6698303222656,
+      "logps/rejected": -213.34518432617188,
+      "loss": 0.5362,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 1.5000348091125488,
+      "rewards/margins": 1.8813749551773071,
+      "rewards/rejected": -0.3813403248786926,
+      "step": 85
+    },
+    {
+      "epoch": 0.9625668449197861,
+      "grad_norm": 34.01709977955445,
+      "learning_rate": 7.971896853961042e-07,
+      "logits/chosen": -2.4786272048950195,
+      "logits/rejected": -2.4621052742004395,
+      "logps/chosen": -252.6436004638672,
+      "logps/rejected": -250.2777557373047,
+      "loss": 0.5064,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": 1.4901584386825562,
+      "rewards/margins": 1.7402337789535522,
+      "rewards/rejected": -0.25007539987564087,
+      "step": 90
+    },
+    {
+      "epoch": 1.0160427807486632,
+      "grad_norm": 24.058087864441212,
+      "learning_rate": 7.732167356856654e-07,
+      "logits/chosen": -2.5284178256988525,
+      "logits/rejected": -2.500856876373291,
+      "logps/chosen": -245.199462890625,
+      "logps/rejected": -247.8142852783203,
+      "loss": 0.4555,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 1.14225172996521,
+      "rewards/margins": 2.6005594730377197,
+      "rewards/rejected": -1.4583076238632202,
+      "step": 95
+    },
+    {
+      "epoch": 1.0695187165775402,
+      "grad_norm": 34.758664424975294,
+      "learning_rate": 7.48312422757881e-07,
+      "logits/chosen": -2.516972064971924,
+      "logits/rejected": -2.514902114868164,
+      "logps/chosen": -236.08767700195312,
+      "logps/rejected": -226.1017608642578,
+      "loss": 0.232,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 1.0098340511322021,
+      "rewards/margins": 3.1043362617492676,
+      "rewards/rejected": -2.0945024490356445,
+      "step": 100
+    },
+    {
+      "epoch": 1.0695187165775402,
+      "eval_logits/chosen": -2.5262153148651123,
+      "eval_logits/rejected": -2.4977195262908936,
+      "eval_logps/chosen": -248.79345703125,
+      "eval_logps/rejected": -207.30593872070312,
+      "eval_loss": 0.49347466230392456,
+      "eval_rewards/accuracies": 0.8035714030265808,
+      "eval_rewards/chosen": 0.938858687877655,
+      "eval_rewards/margins": 2.0174732208251953,
+      "eval_rewards/rejected": -1.078614354133606,
+      "eval_runtime": 177.1838,
+      "eval_samples_per_second": 15.013,
+      "eval_steps_per_second": 0.237,
+      "step": 100
+    },
+    {
+      "epoch": 1.1229946524064172,
+      "grad_norm": 23.33568729706663,
+      "learning_rate": 7.225616424408044e-07,
+      "logits/chosen": -2.514841318130493,
+      "logits/rejected": -2.4978649616241455,
+      "logps/chosen": -235.51412963867188,
+      "logps/rejected": -235.5688018798828,
+      "loss": 0.2233,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.734924554824829,
+      "rewards/margins": 3.03052020072937,
+      "rewards/rejected": -1.2955958843231201,
+      "step": 105
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 34.28901770913126,
+      "learning_rate": 6.96052176068713e-07,
+      "logits/chosen": -2.4421210289001465,
+      "logits/rejected": -2.439652919769287,
+      "logps/chosen": -253.3994140625,
+      "logps/rejected": -220.8712615966797,
+      "loss": 0.2622,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.7797740697860718,
+      "rewards/margins": 3.0600085258483887,
+      "rewards/rejected": -1.2802345752716064,
+      "step": 110
+    },
+    {
+      "epoch": 1.2299465240641712,
+      "grad_norm": 25.642631790616498,
+      "learning_rate": 6.688743912460229e-07,
+      "logits/chosen": -2.429490566253662,
+      "logits/rejected": -2.395030975341797,
+      "logps/chosen": -220.0726318359375,
+      "logps/rejected": -223.9545135498047,
+      "loss": 0.2755,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 1.3883707523345947,
+      "rewards/margins": 3.119737386703491,
+      "rewards/rejected": -1.731366515159607,
+      "step": 115
+    },
+    {
+      "epoch": 1.2834224598930482,
+      "grad_norm": 20.428351141406825,
+      "learning_rate": 6.411209337949213e-07,
+      "logits/chosen": -2.4585251808166504,
+      "logits/rejected": -2.4200589656829834,
+      "logps/chosen": -248.60250854492188,
+      "logps/rejected": -234.059814453125,
+      "loss": 0.2087,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.7997968196868896,
+      "rewards/margins": 3.555243730545044,
+      "rewards/rejected": -1.755446195602417,
+      "step": 120
+    },
+    {
+      "epoch": 1.3368983957219251,
+      "grad_norm": 23.894924535095097,
+      "learning_rate": 6.128864119368233e-07,
+      "logits/chosen": -2.4363160133361816,
+      "logits/rejected": -2.409313201904297,
+      "logps/chosen": -238.1552734375,
+      "logps/rejected": -241.06640625,
+      "loss": 0.311,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": 1.5000994205474854,
+      "rewards/margins": 3.579270839691162,
+      "rewards/rejected": -2.0791714191436768,
+      "step": 125
+    },
+    {
+      "epoch": 1.3903743315508021,
+      "grad_norm": 25.85137765086269,
+      "learning_rate": 5.842670737842467e-07,
+      "logits/chosen": -2.4068820476531982,
+      "logits/rejected": -2.3998050689697266,
+      "logps/chosen": -243.46554565429688,
+      "logps/rejected": -254.32815551757812,
+      "loss": 0.2738,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.553800106048584,
+      "rewards/margins": 3.620004653930664,
+      "rewards/rejected": -2.06620454788208,
+      "step": 130
+    },
+    {
+      "epoch": 1.4438502673796791,
+      "grad_norm": 23.3391055271991,
+      "learning_rate": 5.553604792424922e-07,
+      "logits/chosen": -2.402261734008789,
+      "logits/rejected": -2.388066530227661,
+      "logps/chosen": -257.2569580078125,
+      "logps/rejected": -232.8003387451172,
+      "loss": 0.2369,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 1.5672048330307007,
+      "rewards/margins": 3.8800740242004395,
+      "rewards/rejected": -2.312869071960449,
+      "step": 135
+    },
+    {
+      "epoch": 1.4973262032085561,
+      "grad_norm": 22.523493114917184,
+      "learning_rate": 5.262651674395798e-07,
+      "logits/chosen": -2.3823370933532715,
+      "logits/rejected": -2.363351583480835,
+      "logps/chosen": -251.1205291748047,
+      "logps/rejected": -235.83895874023438,
+      "loss": 0.2554,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 1.209763526916504,
+      "rewards/margins": 3.3722991943359375,
+      "rewards/rejected": -2.1625359058380127,
+      "step": 140
+    },
+    {
+      "epoch": 1.5508021390374331,
+      "grad_norm": 22.629390451583,
+      "learning_rate": 4.970803208181314e-07,
+      "logits/chosen": -2.3576979637145996,
+      "logits/rejected": -2.341073513031006,
+      "logps/chosen": -247.33438110351562,
+      "logps/rejected": -270.8658142089844,
+      "loss": 0.2808,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": 1.388020634651184,
+      "rewards/margins": 3.6264255046844482,
+      "rewards/rejected": -2.2384045124053955,
+      "step": 145
+    },
+    {
+      "epoch": 1.6042780748663101,
+      "grad_norm": 17.721318468581117,
+      "learning_rate": 4.679054270342702e-07,
+      "logits/chosen": -2.3148550987243652,
+      "logits/rejected": -2.2610244750976562,
+      "logps/chosen": -278.3253479003906,
+      "logps/rejected": -230.291259765625,
+      "loss": 0.2427,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": 1.1150439977645874,
+      "rewards/margins": 3.5642380714416504,
+      "rewards/rejected": -2.4491934776306152,
+      "step": 150
+    },
+    {
+      "epoch": 1.6042780748663101,
+      "eval_logits/chosen": -2.2463791370391846,
+      "eval_logits/rejected": -2.1962924003601074,
+      "eval_logps/chosen": -252.03550720214844,
+      "eval_logps/rejected": -213.7987823486328,
+      "eval_loss": 0.4994485378265381,
+      "eval_rewards/accuracies": 0.8184523582458496,
+      "eval_rewards/chosen": 0.6146563291549683,
+      "eval_rewards/margins": 2.342554807662964,
+      "eval_rewards/rejected": -1.727898359298706,
+      "eval_runtime": 177.1502,
+      "eval_samples_per_second": 15.016,
+      "eval_steps_per_second": 0.237,
+      "step": 150
+    },
+    {
+      "epoch": 1.6577540106951871,
+      "grad_norm": 21.833026684822734,
+      "learning_rate": 4.3883993981608567e-07,
+      "logits/chosen": -2.187971591949463,
+      "logits/rejected": -2.1873555183410645,
+      "logps/chosen": -255.7908935546875,
+      "logps/rejected": -228.4761962890625,
+      "loss": 0.2553,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.4208053350448608,
+      "rewards/margins": 3.8419246673583984,
+      "rewards/rejected": -2.421119213104248,
+      "step": 155
+    },
+    {
+      "epoch": 1.7112299465240641,
+      "grad_norm": 21.527834234868564,
+      "learning_rate": 4.0998293993775234e-07,
+      "logits/chosen": -2.1791014671325684,
+      "logits/rejected": -2.1374058723449707,
+      "logps/chosen": -249.51611328125,
+      "logps/rejected": -237.10806274414062,
+      "loss": 0.2627,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.1588197946548462,
+      "rewards/margins": 3.3558552265167236,
+      "rewards/rejected": -2.197035789489746,
+      "step": 160
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 22.141924882028945,
+      "learning_rate": 3.814327974650066e-07,
+      "logits/chosen": -2.1892764568328857,
+      "logits/rejected": -2.154066562652588,
+      "logps/chosen": -245.1927032470703,
+      "logps/rejected": -229.3457794189453,
+      "loss": 0.2499,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 1.5559265613555908,
+      "rewards/margins": 3.307781219482422,
+      "rewards/rejected": -1.751854658126831,
+      "step": 165
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 18.747114781201187,
+      "learning_rate": 3.532868364233416e-07,
+      "logits/chosen": -2.2867817878723145,
+      "logits/rejected": -2.241206645965576,
+      "logps/chosen": -235.2709503173828,
+      "logps/rejected": -254.90792846679688,
+      "loss": 0.2275,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.4621918201446533,
+      "rewards/margins": 3.464813232421875,
+      "rewards/rejected": -2.0026211738586426,
+      "step": 170
+    },
+    {
+      "epoch": 1.8716577540106951,
+      "grad_norm": 22.34846640164264,
+      "learning_rate": 3.256410030320304e-07,
+      "logits/chosen": -2.348212480545044,
+      "logits/rejected": -2.3325066566467285,
+      "logps/chosen": -267.20892333984375,
+      "logps/rejected": -237.50350952148438,
+      "loss": 0.2749,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": 1.7395166158676147,
+      "rewards/margins": 4.169873237609863,
+      "rewards/rejected": -2.430356502532959,
+      "step": 175
+    },
+    {
+      "epoch": 1.9251336898395723,
+      "grad_norm": 22.707246637809515,
+      "learning_rate": 2.985895386349233e-07,
+      "logits/chosen": -2.4144673347473145,
+      "logits/rejected": -2.401940107345581,
+      "logps/chosen": -228.4314422607422,
+      "logps/rejected": -238.22073364257812,
+      "loss": 0.2368,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.1973397731781006,
+      "rewards/margins": 3.5035414695739746,
+      "rewards/rejected": -2.3062021732330322,
+      "step": 180
+    },
+    {
+      "epoch": 1.9786096256684491,
+      "grad_norm": 27.972224583259134,
+      "learning_rate": 2.7222465844296514e-07,
+      "logits/chosen": -2.4469401836395264,
+      "logits/rejected": -2.4393134117126465,
+      "logps/chosen": -246.10189819335938,
+      "logps/rejected": -265.03594970703125,
+      "loss": 0.2766,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 1.647485375404358,
+      "rewards/margins": 3.863076686859131,
+      "rewards/rejected": -2.2155914306640625,
+      "step": 185
+    },
+    {
+      "epoch": 2.0320855614973263,
+      "grad_norm": 16.97425283327867,
+      "learning_rate": 2.466362371835544e-07,
+      "logits/chosen": -2.438560962677002,
+      "logits/rejected": -2.436560869216919,
+      "logps/chosen": -251.0770263671875,
+      "logps/rejected": -256.6495666503906,
+      "loss": 0.1829,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 1.3526352643966675,
+      "rewards/margins": 4.015156269073486,
+      "rewards/rejected": -2.6625208854675293,
+      "step": 190
+    },
+    {
+      "epoch": 2.085561497326203,
+      "grad_norm": 17.33378544754746,
+      "learning_rate": 2.2191150272833386e-07,
+      "logits/chosen": -2.4327006340026855,
+      "logits/rejected": -2.426313877105713,
+      "logps/chosen": -239.974609375,
+      "logps/rejected": -263.90679931640625,
+      "loss": 0.1495,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.4122151136398315,
+      "rewards/margins": 4.446558475494385,
+      "rewards/rejected": -3.0343427658081055,
+      "step": 195
+    },
+    {
+      "epoch": 2.1390374331550803,
+      "grad_norm": 13.9334572780982,
+      "learning_rate": 1.9813473874379395e-07,
+      "logits/chosen": -2.4262537956237793,
+      "logits/rejected": -2.377641201019287,
+      "logps/chosen": -258.02496337890625,
+      "logps/rejected": -253.2255859375,
+      "loss": 0.1239,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": 1.7413403987884521,
+      "rewards/margins": 4.427127838134766,
+      "rewards/rejected": -2.6857874393463135,
+      "step": 200
+    },
+    {
+      "epoch": 2.1390374331550803,
+      "eval_logits/chosen": -2.3958089351654053,
+      "eval_logits/rejected": -2.360522508621216,
+      "eval_logps/chosen": -251.51199340820312,
+      "eval_logps/rejected": -215.51217651367188,
+      "eval_loss": 0.4940880835056305,
+      "eval_rewards/accuracies": 0.8065476417541504,
+      "eval_rewards/chosen": 0.6670060753822327,
+      "eval_rewards/margins": 2.5662453174591064,
+      "eval_rewards/rejected": -1.8992393016815186,
+      "eval_runtime": 177.0357,
+      "eval_samples_per_second": 15.025,
+      "eval_steps_per_second": 0.237,
+      "step": 200
+    },
+    {
+      "epoch": 2.192513368983957,
+      "grad_norm": 11.582273345860106,
+      "learning_rate": 1.7538699737832237e-07,
+      "logits/chosen": -2.3853468894958496,
+      "logits/rejected": -2.3745884895324707,
+      "logps/chosen": -230.9375457763672,
+      "logps/rejected": -217.5093994140625,
+      "loss": 0.1469,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 1.4965482950210571,
+      "rewards/margins": 4.085664749145508,
+      "rewards/rejected": -2.5891165733337402,
+      "step": 205
+    },
+    {
+      "epoch": 2.2459893048128343,
+      "grad_norm": 19.256743465727453,
+      "learning_rate": 1.5374582296511053e-07,
+      "logits/chosen": -2.3758203983306885,
+      "logits/rejected": -2.350308895111084,
+      "logps/chosen": -257.522705078125,
+      "logps/rejected": -234.826171875,
+      "loss": 0.1481,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.6718244552612305,
+      "rewards/margins": 4.5953168869018555,
+      "rewards/rejected": -2.923491954803467,
+      "step": 210
+    },
+    {
+      "epoch": 2.299465240641711,
+      "grad_norm": 13.139408171077235,
+      "learning_rate": 1.3328498768278418e-07,
+      "logits/chosen": -2.3815619945526123,
+      "logits/rejected": -2.3640360832214355,
+      "logps/chosen": -238.7193603515625,
+      "logps/rejected": -232.0906219482422,
+      "loss": 0.1182,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 1.7218825817108154,
+      "rewards/margins": 4.676151275634766,
+      "rewards/rejected": -2.9542689323425293,
+      "step": 215
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 13.083761092577205,
+      "learning_rate": 1.1407424007485928e-07,
+      "logits/chosen": -2.351168394088745,
+      "logits/rejected": -2.362783908843994,
+      "logps/chosen": -261.3135986328125,
+      "logps/rejected": -223.7679443359375,
+      "loss": 0.1353,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 1.8544862270355225,
+      "rewards/margins": 4.578373908996582,
+      "rewards/rejected": -2.7238874435424805,
+      "step": 220
+    },
+    {
+      "epoch": 2.406417112299465,
+      "grad_norm": 22.686899523674633,
+      "learning_rate": 9.617906728528679e-08,
+      "logits/chosen": -2.3818743228912354,
+      "logits/rejected": -2.3381073474884033,
+      "logps/chosen": -249.3686065673828,
+      "logps/rejected": -266.00616455078125,
+      "loss": 0.1406,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 1.7818124294281006,
+      "rewards/margins": 4.478957176208496,
+      "rewards/rejected": -2.697144031524658,
+      "step": 225
+    },
+    {
+      "epoch": 2.4598930481283423,
+      "grad_norm": 17.488012587001123,
+      "learning_rate": 7.966047182060226e-08,
+      "logits/chosen": -2.363152027130127,
+      "logits/rejected": -2.341928482055664,
+      "logps/chosen": -241.06747436523438,
+      "logps/rejected": -220.3070831298828,
+      "loss": 0.137,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.5707038640975952,
+      "rewards/margins": 4.198428153991699,
+      "rewards/rejected": -2.6277241706848145,
+      "step": 230
+    },
+    {
+      "epoch": 2.5133689839572195,
+      "grad_norm": 16.158136019422187,
+      "learning_rate": 6.457476359966684e-08,
+      "logits/chosen": -2.3634676933288574,
+      "logits/rejected": -2.3343586921691895,
+      "logps/chosen": -230.6551055908203,
+      "logps/rejected": -232.58920288085938,
+      "loss": 0.1324,
+      "rewards/accuracies": 0.981249988079071,
+      "rewards/chosen": 1.5435535907745361,
+      "rewards/margins": 4.363201141357422,
+      "rewards/rejected": -2.819648027420044,
+      "step": 235
+    },
+    {
+      "epoch": 2.5668449197860963,
+      "grad_norm": 19.585075813526288,
+      "learning_rate": 5.097336799988067e-08,
+      "logits/chosen": -2.3822684288024902,
+      "logits/rejected": -2.33119797706604,
+      "logps/chosen": -243.6968994140625,
+      "logps/rejected": -252.494873046875,
+      "loss": 0.1575,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.535332441329956,
+      "rewards/margins": 4.624737739562988,
+      "rewards/rejected": -3.089405059814453,
+      "step": 240
+    },
+    {
+      "epoch": 2.620320855614973,
+      "grad_norm": 16.504173280628983,
+      "learning_rate": 3.8902650554212826e-08,
+      "logits/chosen": -2.377624034881592,
+      "logits/rejected": -2.357320785522461,
+      "logps/chosen": -234.1246337890625,
+      "logps/rejected": -233.6632537841797,
+      "loss": 0.1404,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.701682686805725,
+      "rewards/margins": 4.359586238861084,
+      "rewards/rejected": -2.6579031944274902,
+      "step": 245
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 19.105883784745725,
+      "learning_rate": 2.8403758896638707e-08,
+      "logits/chosen": -2.3754684925079346,
+      "logits/rejected": -2.335705280303955,
+      "logps/chosen": -261.24554443359375,
+      "logps/rejected": -248.94570922851562,
+      "loss": 0.1607,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 1.8046457767486572,
+      "rewards/margins": 4.712311744689941,
+      "rewards/rejected": -2.907665729522705,
+      "step": 250
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "eval_logits/chosen": -2.373189926147461,
+      "eval_logits/rejected": -2.334873914718628,
+      "eval_logps/chosen": -251.20956420898438,
+      "eval_logps/rejected": -216.7368927001953,
+      "eval_loss": 0.5006157755851746,
+      "eval_rewards/accuracies": 0.800595223903656,
+      "eval_rewards/chosen": 0.6972481608390808,
+      "eval_rewards/margins": 2.718956708908081,
+      "eval_rewards/rejected": -2.0217082500457764,
+      "eval_runtime": 177.6741,
+      "eval_samples_per_second": 14.971,
+      "eval_steps_per_second": 0.236,
+      "step": 250
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 16.859647997107373,
+      "learning_rate": 1.951248249476961e-08,
+      "logits/chosen": -2.390385150909424,
+      "logits/rejected": -2.339979648590088,
+      "logps/chosen": -232.9261932373047,
+      "logps/rejected": -252.1141357421875,
+      "loss": 0.1515,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.974938154220581,
+      "rewards/margins": 4.697868824005127,
+      "rewards/rejected": -2.722930431365967,
+      "step": 255
+    },
+    {
+      "epoch": 2.7807486631016043,
+      "grad_norm": 18.408639136313546,
+      "learning_rate": 1.2259130647833626e-08,
+      "logits/chosen": -2.384657621383667,
+      "logits/rejected": -2.3508825302124023,
+      "logps/chosen": -231.360595703125,
+      "logps/rejected": -238.8389892578125,
+      "loss": 0.1517,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.6810638904571533,
+      "rewards/margins": 4.430610179901123,
+      "rewards/rejected": -2.7495458126068115,
+      "step": 260
+    },
+    {
+      "epoch": 2.834224598930481,
+      "grad_norm": 19.216489097516313,
+      "learning_rate": 6.668429165893996e-09,
+      "logits/chosen": -2.379669427871704,
+      "logits/rejected": -2.361882448196411,
+      "logps/chosen": -261.16961669921875,
+      "logps/rejected": -269.8806457519531,
+      "loss": 0.1479,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.4186723232269287,
+      "rewards/margins": 4.286049842834473,
+      "rewards/rejected": -2.867377758026123,
+      "step": 265
+    },
+    {
+      "epoch": 2.8877005347593583,
+      "grad_norm": 18.845102458023714,
+      "learning_rate": 2.759436082516664e-09,
+      "logits/chosen": -2.372851848602295,
+      "logits/rejected": -2.356961488723755,
+      "logps/chosen": -247.1389617919922,
+      "logps/rejected": -257.267822265625,
+      "loss": 0.1573,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.4503118991851807,
+      "rewards/margins": 4.499074935913086,
+      "rewards/rejected": -3.0487632751464844,
+      "step": 270
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 16.5452733632814,
+      "learning_rate": 5.454766882097006e-10,
+      "logits/chosen": -2.3800816535949707,
+      "logits/rejected": -2.3431155681610107,
+      "logps/chosen": -242.17153930664062,
+      "logps/rejected": -259.4877014160156,
+      "loss": 0.1708,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 1.4261102676391602,
+      "rewards/margins": 4.574359893798828,
+      "rewards/rejected": -3.148249864578247,
+      "step": 275
+    },
+    {
+      "epoch": 2.983957219251337,
+      "step": 279,
+      "total_flos": 3289753017384960.0,
+      "train_loss": 0.3301437693684759,
+      "train_runtime": 10405.088,
+      "train_samples_per_second": 6.9,
+      "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:d0fff5d75b9d6d93d18c3a64ad08cce25263b3d0a334ad7f9e991010851ef90c
+size 7096