Upload folder using huggingface_hub

README.md

@@ -0,0 +1,77 @@
+---
+library_name: transformers
+license: other
+base_model: llava-hf/llava-v1.6-mistral-7b-hf
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: RLAIF-V_L0-q0_75
+  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. -->
+
+# RLAIF-V_L0-q0_75
+
+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 RLAIF-V_L0-q0_75 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0089
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1315        | 0.2320 | 50   | 1.1244          |
+| 1.0732        | 0.4640 | 100  | 1.0797          |
+| 1.0352        | 0.6961 | 150  | 1.0541          |
+| 1.0347        | 0.9281 | 200  | 1.0316          |
+| 0.8776        | 1.1601 | 250  | 1.0248          |
+| 0.8888        | 1.3921 | 300  | 1.0145          |
+| 0.8902        | 1.6241 | 350  | 1.0069          |
+| 0.8773        | 1.8561 | 400  | 0.9999          |
+| 0.7847        | 2.0882 | 450  | 1.0114          |
+| 0.7668        | 2.3202 | 500  | 1.0112          |
+| 0.775         | 2.5522 | 550  | 1.0103          |
+| 0.7768        | 2.7842 | 600  | 1.0089          |
+
+
+### 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 +1,12 @@
+{
+    "epoch": 2.9930394431554523,
+    "eval_loss": 1.0089036226272583,
+    "eval_runtime": 105.4087,
+    "eval_samples_per_second": 58.145,
+    "eval_steps_per_second": 0.911,
+    "total_flos": 3802978389590016.0,
+    "train_loss": 0.9239856169205304,
+    "train_runtime": 9561.8566,
+    "train_samples_per_second": 17.305,
+    "train_steps_per_second": 0.067
+}

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 +1,7 @@
+{
+    "epoch": 2.9930394431554523,
+    "eval_loss": 1.0089036226272583,
+    "eval_runtime": 105.4087,
+    "eval_samples_per_second": 58.145,
+    "eval_steps_per_second": 0.911
+}

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:d77989f8ecb81034a99aa3949e91f0a75add4798598f4549f34734cb83faa1ed
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3bb998ab6cd09fdf157dfe7a85948485c968dbefad9a9e33f9b0e3059dfbe0d
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2bba658234b3ee55acb00d644a6de9f1b127fd45eb40ad6902bce3e6f979688
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f0ef8bfb153e2aca6908354f679005e1ba3aec87a119b000b7d29eed3989fe
+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": 2.9930394431554523,
+    "total_flos": 3802978389590016.0,
+    "train_loss": 0.9239856169205304,
+    "train_runtime": 9561.8566,
+    "train_samples_per_second": 17.305,
+    "train_steps_per_second": 0.067
+}

trainer_log.jsonl

@@ -0,0 +1,142 @@
+{"current_steps": 5, "total_steps": 645, "loss": 1.6448, "learning_rate": 5e-07, "epoch": 0.02320185614849188, "percentage": 0.78, "elapsed_time": "0:01:08", "remaining_time": "2:26:29"}
+{"current_steps": 10, "total_steps": 645, "loss": 1.5147, "learning_rate": 1e-06, "epoch": 0.04640371229698376, "percentage": 1.55, "elapsed_time": "0:02:12", "remaining_time": "2:19:43"}
+{"current_steps": 15, "total_steps": 645, "loss": 1.2888, "learning_rate": 9.998470286265414e-07, "epoch": 0.06960556844547564, "percentage": 2.33, "elapsed_time": "0:03:15", "remaining_time": "2:16:44"}
+{"current_steps": 20, "total_steps": 645, "loss": 1.2291, "learning_rate": 9.993882081071305e-07, "epoch": 0.09280742459396751, "percentage": 3.1, "elapsed_time": "0:04:17", "remaining_time": "2:14:20"}
+{"current_steps": 25, "total_steps": 645, "loss": 1.1827, "learning_rate": 9.986238191873872e-07, "epoch": 0.11600928074245939, "percentage": 3.88, "elapsed_time": "0:05:20", "remaining_time": "2:12:21"}
+{"current_steps": 30, "total_steps": 645, "loss": 1.1637, "learning_rate": 9.975543295858033e-07, "epoch": 0.13921113689095127, "percentage": 4.65, "elapsed_time": "0:06:22", "remaining_time": "2:10:50"}
+{"current_steps": 35, "total_steps": 645, "loss": 1.1448, "learning_rate": 9.961803937075514e-07, "epoch": 0.16241299303944315, "percentage": 5.43, "elapsed_time": "0:07:25", "remaining_time": "2:09:32"}
+{"current_steps": 40, "total_steps": 645, "loss": 1.1539, "learning_rate": 9.945028522440653e-07, "epoch": 0.18561484918793503, "percentage": 6.2, "elapsed_time": "0:08:28", "remaining_time": "2:08:10"}
+{"current_steps": 45, "total_steps": 645, "loss": 1.1302, "learning_rate": 9.925227316586314e-07, "epoch": 0.2088167053364269, "percentage": 6.98, "elapsed_time": "0:09:30", "remaining_time": "2:06:51"}
+{"current_steps": 50, "total_steps": 645, "loss": 1.1315, "learning_rate": 9.902412435583125e-07, "epoch": 0.23201856148491878, "percentage": 7.75, "elapsed_time": "0:10:34", "remaining_time": "2:05:46"}
+{"current_steps": 50, "total_steps": 645, "eval_loss": 1.1243596076965332, "epoch": 0.23201856148491878, "percentage": 7.75, "elapsed_time": "0:12:21", "remaining_time": "2:27:04"}
+{"current_steps": 55, "total_steps": 645, "loss": 1.1184, "learning_rate": 9.876597839525813e-07, "epoch": 0.2552204176334107, "percentage": 8.53, "elapsed_time": "0:13:24", "remaining_time": "2:23:54"}
+{"current_steps": 60, "total_steps": 645, "loss": 1.1112, "learning_rate": 9.847799323991233e-07, "epoch": 0.27842227378190254, "percentage": 9.3, "elapsed_time": "0:14:27", "remaining_time": "2:20:59"}
+{"current_steps": 65, "total_steps": 645, "loss": 1.1022, "learning_rate": 9.816034510373285e-07, "epoch": 0.30162412993039445, "percentage": 10.08, "elapsed_time": "0:15:30", "remaining_time": "2:18:19"}
+{"current_steps": 70, "total_steps": 645, "loss": 1.1109, "learning_rate": 9.781322835100637e-07, "epoch": 0.3248259860788863, "percentage": 10.85, "elapsed_time": "0:16:33", "remaining_time": "2:15:59"}
+{"current_steps": 75, "total_steps": 645, "loss": 1.1044, "learning_rate": 9.743685537743856e-07, "epoch": 0.3480278422273782, "percentage": 11.63, "elapsed_time": "0:17:35", "remaining_time": "2:13:43"}
+{"current_steps": 80, "total_steps": 645, "loss": 1.0982, "learning_rate": 9.70314564801922e-07, "epoch": 0.37122969837587005, "percentage": 12.4, "elapsed_time": "0:18:38", "remaining_time": "2:11:40"}
+{"current_steps": 85, "total_steps": 645, "loss": 1.0798, "learning_rate": 9.659727971697173e-07, "epoch": 0.39443155452436196, "percentage": 13.18, "elapsed_time": "0:19:41", "remaining_time": "2:09:41"}
+{"current_steps": 90, "total_steps": 645, "loss": 1.0925, "learning_rate": 9.613459075424033e-07, "epoch": 0.4176334106728538, "percentage": 13.95, "elapsed_time": "0:20:43", "remaining_time": "2:07:49"}
+{"current_steps": 95, "total_steps": 645, "loss": 1.0726, "learning_rate": 9.564367270466245e-07, "epoch": 0.4408352668213457, "percentage": 14.73, "elapsed_time": "0:21:45", "remaining_time": "2:06:00"}
+{"current_steps": 100, "total_steps": 645, "loss": 1.0732, "learning_rate": 9.51248259538713e-07, "epoch": 0.46403712296983757, "percentage": 15.5, "elapsed_time": "0:22:48", "remaining_time": "2:04:18"}
+{"current_steps": 100, "total_steps": 645, "eval_loss": 1.079745888710022, "epoch": 0.46403712296983757, "percentage": 15.5, "elapsed_time": "0:24:34", "remaining_time": "2:13:57"}
+{"current_steps": 105, "total_steps": 645, "loss": 1.0596, "learning_rate": 9.457836797666721e-07, "epoch": 0.4872389791183295, "percentage": 16.28, "elapsed_time": "0:26:09", "remaining_time": "2:14:31"}
+{"current_steps": 110, "total_steps": 645, "loss": 1.0699, "learning_rate": 9.400463314275941e-07, "epoch": 0.5104408352668214, "percentage": 17.05, "elapsed_time": "0:27:12", "remaining_time": "2:12:20"}
+{"current_steps": 115, "total_steps": 645, "loss": 1.0653, "learning_rate": 9.340397251217008e-07, "epoch": 0.5336426914153132, "percentage": 17.83, "elapsed_time": "0:28:14", "remaining_time": "2:10:09"}
+{"current_steps": 120, "total_steps": 645, "loss": 1.0729, "learning_rate": 9.27767536204258e-07, "epoch": 0.5568445475638051, "percentage": 18.6, "elapsed_time": "0:29:16", "remaining_time": "2:08:05"}
+{"current_steps": 125, "total_steps": 645, "loss": 1.0709, "learning_rate": 9.212336025366787e-07, "epoch": 0.580046403712297, "percentage": 19.38, "elapsed_time": "0:30:18", "remaining_time": "2:06:05"}
+{"current_steps": 130, "total_steps": 645, "loss": 1.0579, "learning_rate": 9.144419221381918e-07, "epoch": 0.6032482598607889, "percentage": 20.16, "elapsed_time": "0:31:21", "remaining_time": "2:04:11"}
+{"current_steps": 135, "total_steps": 645, "loss": 1.0554, "learning_rate": 9.073966507395121e-07, "epoch": 0.6264501160092807, "percentage": 20.93, "elapsed_time": "0:32:23", "remaining_time": "2:02:22"}
+{"current_steps": 140, "total_steps": 645, "loss": 1.043, "learning_rate": 9.001020992400085e-07, "epoch": 0.6496519721577726, "percentage": 21.71, "elapsed_time": "0:33:26", "remaining_time": "2:00:36"}
+{"current_steps": 145, "total_steps": 645, "loss": 1.0531, "learning_rate": 8.925627310699274e-07, "epoch": 0.6728538283062645, "percentage": 22.48, "elapsed_time": "0:34:29", "remaining_time": "1:58:56"}
+{"current_steps": 150, "total_steps": 645, "loss": 1.0352, "learning_rate": 8.84783159459285e-07, "epoch": 0.6960556844547564, "percentage": 23.26, "elapsed_time": "0:35:31", "remaining_time": "1:57:14"}
+{"current_steps": 150, "total_steps": 645, "eval_loss": 1.054144263267517, "epoch": 0.6960556844547564, "percentage": 23.26, "elapsed_time": "0:37:17", "remaining_time": "2:03:04"}
+{"current_steps": 155, "total_steps": 645, "loss": 1.0565, "learning_rate": 8.767681446150976e-07, "epoch": 0.7192575406032483, "percentage": 24.03, "elapsed_time": "0:38:20", "remaining_time": "2:01:12"}
+{"current_steps": 160, "total_steps": 645, "loss": 1.0409, "learning_rate": 8.68522590808682e-07, "epoch": 0.7424593967517401, "percentage": 24.81, "elapsed_time": "0:39:22", "remaining_time": "1:59:21"}
+{"current_steps": 165, "total_steps": 645, "loss": 1.0531, "learning_rate": 8.600515433748001e-07, "epoch": 0.765661252900232, "percentage": 25.58, "elapsed_time": "0:40:24", "remaining_time": "1:57:33"}
+{"current_steps": 170, "total_steps": 645, "loss": 1.0321, "learning_rate": 8.51360185624495e-07, "epoch": 0.7888631090487239, "percentage": 26.36, "elapsed_time": "0:41:26", "remaining_time": "1:55:48"}
+{"current_steps": 175, "total_steps": 645, "loss": 1.0366, "learning_rate": 8.424538356734956e-07, "epoch": 0.8120649651972158, "percentage": 27.13, "elapsed_time": "0:42:29", "remaining_time": "1:54:06"}
+{"current_steps": 180, "total_steps": 645, "loss": 1.0454, "learning_rate": 8.333379431881397e-07, "epoch": 0.8352668213457076, "percentage": 27.91, "elapsed_time": "0:43:31", "remaining_time": "1:52:26"}
+{"current_steps": 185, "total_steps": 645, "loss": 1.0368, "learning_rate": 8.240180860508026e-07, "epoch": 0.8584686774941995, "percentage": 28.68, "elapsed_time": "0:44:33", "remaining_time": "1:50:48"}
+{"current_steps": 190, "total_steps": 645, "loss": 1.0288, "learning_rate": 8.144999669468713e-07, "epoch": 0.8816705336426914, "percentage": 29.46, "elapsed_time": "0:45:36", "remaining_time": "1:49:13"}
+{"current_steps": 195, "total_steps": 645, "loss": 1.0323, "learning_rate": 8.047894098753539e-07, "epoch": 0.9048723897911833, "percentage": 30.23, "elapsed_time": "0:46:39", "remaining_time": "1:47:40"}
+{"current_steps": 200, "total_steps": 645, "loss": 1.0347, "learning_rate": 7.948923565852597e-07, "epoch": 0.9280742459396751, "percentage": 31.01, "elapsed_time": "0:47:42", "remaining_time": "1:46:08"}
+{"current_steps": 200, "total_steps": 645, "eval_loss": 1.0315721035003662, "epoch": 0.9280742459396751, "percentage": 31.01, "elapsed_time": "0:49:28", "remaining_time": "1:50:04"}
+{"current_steps": 205, "total_steps": 645, "loss": 1.0264, "learning_rate": 7.848148629399285e-07, "epoch": 0.951276102088167, "percentage": 31.78, "elapsed_time": "0:51:02", "remaining_time": "1:49:34"}
+{"current_steps": 210, "total_steps": 645, "loss": 1.0204, "learning_rate": 7.745630952115363e-07, "epoch": 0.974477958236659, "percentage": 32.56, "elapsed_time": "0:52:04", "remaining_time": "1:47:53"}
+{"current_steps": 215, "total_steps": 645, "loss": 1.0287, "learning_rate": 7.641433263080418e-07, "epoch": 0.9976798143851509, "percentage": 33.33, "elapsed_time": "0:53:07", "remaining_time": "1:46:15"}
+{"current_steps": 220, "total_steps": 645, "loss": 0.92, "learning_rate": 7.535619319348865e-07, "epoch": 1.0208816705336428, "percentage": 34.11, "elapsed_time": "0:54:09", "remaining_time": "1:44:38"}
+{"current_steps": 225, "total_steps": 645, "loss": 0.9119, "learning_rate": 7.428253866937918e-07, "epoch": 1.0440835266821347, "percentage": 34.88, "elapsed_time": "0:55:12", "remaining_time": "1:43:02"}
+{"current_steps": 230, "total_steps": 645, "loss": 0.9091, "learning_rate": 7.319402601210447e-07, "epoch": 1.0672853828306264, "percentage": 35.66, "elapsed_time": "0:56:14", "remaining_time": "1:41:28"}
+{"current_steps": 235, "total_steps": 645, "loss": 0.8901, "learning_rate": 7.209132126676933e-07, "epoch": 1.0904872389791183, "percentage": 36.43, "elapsed_time": "0:57:16", "remaining_time": "1:39:56"}
+{"current_steps": 240, "total_steps": 645, "loss": 0.8963, "learning_rate": 7.097509916241145e-07, "epoch": 1.1136890951276102, "percentage": 37.21, "elapsed_time": "0:58:18", "remaining_time": "1:38:24"}
+{"current_steps": 245, "total_steps": 645, "loss": 0.878, "learning_rate": 6.984604269914436e-07, "epoch": 1.136890951276102, "percentage": 37.98, "elapsed_time": "0:59:21", "remaining_time": "1:36:53"}
+{"current_steps": 250, "total_steps": 645, "loss": 0.8776, "learning_rate": 6.870484273023967e-07, "epoch": 1.160092807424594, "percentage": 38.76, "elapsed_time": "1:00:23", "remaining_time": "1:35:24"}
+{"current_steps": 250, "total_steps": 645, "eval_loss": 1.0247548818588257, "epoch": 1.160092807424594, "percentage": 38.76, "elapsed_time": "1:02:09", "remaining_time": "1:38:11"}
+{"current_steps": 255, "total_steps": 645, "loss": 0.8925, "learning_rate": 6.755219753940388e-07, "epoch": 1.1832946635730859, "percentage": 39.53, "elapsed_time": "1:03:11", "remaining_time": "1:36:38"}
+{"current_steps": 260, "total_steps": 645, "loss": 0.897, "learning_rate": 6.638881241350883e-07, "epoch": 1.2064965197215778, "percentage": 40.31, "elapsed_time": "1:04:13", "remaining_time": "1:35:05"}
+{"current_steps": 265, "total_steps": 645, "loss": 0.8839, "learning_rate": 6.52153992110368e-07, "epoch": 1.2296983758700697, "percentage": 41.09, "elapsed_time": "1:05:15", "remaining_time": "1:33:34"}
+{"current_steps": 270, "total_steps": 645, "loss": 0.8916, "learning_rate": 6.403267592650466e-07, "epoch": 1.2529002320185616, "percentage": 41.86, "elapsed_time": "1:06:17", "remaining_time": "1:32:04"}
+{"current_steps": 275, "total_steps": 645, "loss": 0.8755, "learning_rate": 6.28413662511334e-07, "epoch": 1.2761020881670533, "percentage": 42.64, "elapsed_time": "1:07:20", "remaining_time": "1:30:35"}
+{"current_steps": 280, "total_steps": 645, "loss": 0.8775, "learning_rate": 6.164219913003207e-07, "epoch": 1.2993039443155452, "percentage": 43.41, "elapsed_time": "1:08:23", "remaining_time": "1:29:08"}
+{"current_steps": 285, "total_steps": 645, "loss": 0.9028, "learning_rate": 6.043590831616676e-07, "epoch": 1.322505800464037, "percentage": 44.19, "elapsed_time": "1:09:25", "remaining_time": "1:27:42"}
+{"current_steps": 290, "total_steps": 645, "loss": 0.887, "learning_rate": 5.92232319213878e-07, "epoch": 1.345707656612529, "percentage": 44.96, "elapsed_time": "1:10:28", "remaining_time": "1:26:16"}
+{"current_steps": 295, "total_steps": 645, "loss": 0.8759, "learning_rate": 5.800491196478988e-07, "epoch": 1.368909512761021, "percentage": 45.74, "elapsed_time": "1:11:30", "remaining_time": "1:24:50"}
+{"current_steps": 300, "total_steps": 645, "loss": 0.8888, "learning_rate": 5.678169391868127e-07, "epoch": 1.3921113689095128, "percentage": 46.51, "elapsed_time": "1:12:33", "remaining_time": "1:23:26"}
+{"current_steps": 300, "total_steps": 645, "eval_loss": 1.0144710540771484, "epoch": 1.3921113689095128, "percentage": 46.51, "elapsed_time": "1:14:19", "remaining_time": "1:25:28"}
+{"current_steps": 305, "total_steps": 645, "loss": 0.8939, "learning_rate": 5.555432625244023e-07, "epoch": 1.4153132250580047, "percentage": 47.29, "elapsed_time": "1:15:53", "remaining_time": "1:24:36"}
+{"current_steps": 310, "total_steps": 645, "loss": 0.8929, "learning_rate": 5.432355997453728e-07, "epoch": 1.4385150812064964, "percentage": 48.06, "elapsed_time": "1:16:56", "remaining_time": "1:23:08"}
+{"current_steps": 315, "total_steps": 645, "loss": 0.9025, "learning_rate": 5.309014817300421e-07, "epoch": 1.4617169373549883, "percentage": 48.84, "elapsed_time": "1:17:58", "remaining_time": "1:21:41"}
+{"current_steps": 320, "total_steps": 645, "loss": 0.8753, "learning_rate": 5.185484555463026e-07, "epoch": 1.4849187935034802, "percentage": 49.61, "elapsed_time": "1:19:00", "remaining_time": "1:20:14"}
+{"current_steps": 325, "total_steps": 645, "loss": 0.8938, "learning_rate": 5.061840798316814e-07, "epoch": 1.5081206496519721, "percentage": 50.39, "elapsed_time": "1:20:03", "remaining_time": "1:18:49"}
+{"current_steps": 330, "total_steps": 645, "loss": 0.882, "learning_rate": 4.938159201683186e-07, "epoch": 1.531322505800464, "percentage": 51.16, "elapsed_time": "1:21:06", "remaining_time": "1:17:25"}
+{"current_steps": 335, "total_steps": 645, "loss": 0.8846, "learning_rate": 4.814515444536974e-07, "epoch": 1.554524361948956, "percentage": 51.94, "elapsed_time": "1:22:08", "remaining_time": "1:16:01"}
+{"current_steps": 340, "total_steps": 645, "loss": 0.8875, "learning_rate": 4.69098518269958e-07, "epoch": 1.5777262180974478, "percentage": 52.71, "elapsed_time": "1:23:10", "remaining_time": "1:14:37"}
+{"current_steps": 345, "total_steps": 645, "loss": 0.8713, "learning_rate": 4.5676440025462726e-07, "epoch": 1.6009280742459397, "percentage": 53.49, "elapsed_time": "1:24:13", "remaining_time": "1:13:13"}
+{"current_steps": 350, "total_steps": 645, "loss": 0.8902, "learning_rate": 4.444567374755977e-07, "epoch": 1.6241299303944317, "percentage": 54.26, "elapsed_time": "1:25:15", "remaining_time": "1:11:51"}
+{"current_steps": 350, "total_steps": 645, "eval_loss": 1.0069366693496704, "epoch": 1.6241299303944317, "percentage": 54.26, "elapsed_time": "1:27:01", "remaining_time": "1:13:21"}
+{"current_steps": 355, "total_steps": 645, "loss": 0.8789, "learning_rate": 4.3218306081318713e-07, "epoch": 1.6473317865429236, "percentage": 55.04, "elapsed_time": "1:28:03", "remaining_time": "1:11:56"}
+{"current_steps": 360, "total_steps": 645, "loss": 0.8774, "learning_rate": 4.199508803521012e-07, "epoch": 1.6705336426914155, "percentage": 55.81, "elapsed_time": "1:29:06", "remaining_time": "1:10:32"}
+{"current_steps": 365, "total_steps": 645, "loss": 0.8717, "learning_rate": 4.0776768078612207e-07, "epoch": 1.6937354988399071, "percentage": 56.59, "elapsed_time": "1:30:08", "remaining_time": "1:09:09"}
+{"current_steps": 370, "total_steps": 645, "loss": 0.8764, "learning_rate": 3.9564091683833244e-07, "epoch": 1.716937354988399, "percentage": 57.36, "elapsed_time": "1:31:11", "remaining_time": "1:07:46"}
+{"current_steps": 375, "total_steps": 645, "loss": 0.865, "learning_rate": 3.835780086996793e-07, "epoch": 1.740139211136891, "percentage": 58.14, "elapsed_time": "1:32:13", "remaining_time": "1:06:24"}
+{"current_steps": 380, "total_steps": 645, "loss": 0.8779, "learning_rate": 3.7158633748866607e-07, "epoch": 1.7633410672853829, "percentage": 58.91, "elapsed_time": "1:33:15", "remaining_time": "1:05:02"}
+{"current_steps": 385, "total_steps": 645, "loss": 0.8672, "learning_rate": 3.596732407349536e-07, "epoch": 1.7865429234338746, "percentage": 59.69, "elapsed_time": "1:34:18", "remaining_time": "1:03:41"}
+{"current_steps": 390, "total_steps": 645, "loss": 0.8725, "learning_rate": 3.4784600788963193e-07, "epoch": 1.8097447795823665, "percentage": 60.47, "elapsed_time": "1:35:20", "remaining_time": "1:02:20"}
+{"current_steps": 395, "total_steps": 645, "loss": 0.8615, "learning_rate": 3.3611187586491157e-07, "epoch": 1.8329466357308584, "percentage": 61.24, "elapsed_time": "1:36:23", "remaining_time": "1:01:00"}
+{"current_steps": 400, "total_steps": 645, "loss": 0.8773, "learning_rate": 3.244780246059612e-07, "epoch": 1.8561484918793503, "percentage": 62.02, "elapsed_time": "1:37:25", "remaining_time": "0:59:40"}
+{"current_steps": 400, "total_steps": 645, "eval_loss": 0.9998582005500793, "epoch": 1.8561484918793503, "percentage": 62.02, "elapsed_time": "1:39:11", "remaining_time": "1:00:45"}
+{"current_steps": 405, "total_steps": 645, "loss": 0.8671, "learning_rate": 3.129515726976034e-07, "epoch": 1.8793503480278422, "percentage": 62.79, "elapsed_time": "1:40:44", "remaining_time": "0:59:42"}
+{"current_steps": 410, "total_steps": 645, "loss": 0.8614, "learning_rate": 3.015395730085565e-07, "epoch": 1.902552204176334, "percentage": 63.57, "elapsed_time": "1:41:46", "remaining_time": "0:58:20"}
+{"current_steps": 415, "total_steps": 645, "loss": 0.871, "learning_rate": 2.902490083758856e-07, "epoch": 1.925754060324826, "percentage": 64.34, "elapsed_time": "1:42:49", "remaining_time": "0:56:59"}
+{"current_steps": 420, "total_steps": 645, "loss": 0.8795, "learning_rate": 2.790867873323067e-07, "epoch": 1.948955916473318, "percentage": 65.12, "elapsed_time": "1:43:51", "remaining_time": "0:55:38"}
+{"current_steps": 425, "total_steps": 645, "loss": 0.8588, "learning_rate": 2.680597398789554e-07, "epoch": 1.9721577726218098, "percentage": 65.89, "elapsed_time": "1:44:54", "remaining_time": "0:54:18"}
+{"current_steps": 430, "total_steps": 645, "loss": 0.8719, "learning_rate": 2.5717461330620815e-07, "epoch": 1.9953596287703017, "percentage": 66.67, "elapsed_time": "1:45:57", "remaining_time": "0:52:58"}
+{"current_steps": 435, "total_steps": 645, "loss": 0.7933, "learning_rate": 2.464380680651134e-07, "epoch": 2.0185614849187936, "percentage": 67.44, "elapsed_time": "1:47:00", "remaining_time": "0:51:39"}
+{"current_steps": 440, "total_steps": 645, "loss": 0.7943, "learning_rate": 2.358566736919581e-07, "epoch": 2.0417633410672855, "percentage": 68.22, "elapsed_time": "1:48:02", "remaining_time": "0:50:20"}
+{"current_steps": 445, "total_steps": 645, "loss": 0.778, "learning_rate": 2.2543690478846388e-07, "epoch": 2.0649651972157774, "percentage": 68.99, "elapsed_time": "1:49:04", "remaining_time": "0:49:01"}
+{"current_steps": 450, "total_steps": 645, "loss": 0.7847, "learning_rate": 2.1518513706007152e-07, "epoch": 2.0881670533642693, "percentage": 69.77, "elapsed_time": "1:50:07", "remaining_time": "0:47:43"}
+{"current_steps": 450, "total_steps": 645, "eval_loss": 1.0113998651504517, "epoch": 2.0881670533642693, "percentage": 69.77, "elapsed_time": "1:51:53", "remaining_time": "0:48:29"}
+{"current_steps": 455, "total_steps": 645, "loss": 0.7843, "learning_rate": 2.051076434147403e-07, "epoch": 2.111368909512761, "percentage": 70.54, "elapsed_time": "1:52:57", "remaining_time": "0:47:10"}
+{"current_steps": 460, "total_steps": 645, "loss": 0.7678, "learning_rate": 1.9521059012464607e-07, "epoch": 2.1345707656612527, "percentage": 71.32, "elapsed_time": "1:53:59", "remaining_time": "0:45:50"}
+{"current_steps": 465, "total_steps": 645, "loss": 0.7897, "learning_rate": 1.855000330531289e-07, "epoch": 2.1577726218097446, "percentage": 72.09, "elapsed_time": "1:55:02", "remaining_time": "0:44:31"}
+{"current_steps": 470, "total_steps": 645, "loss": 0.7811, "learning_rate": 1.7598191394919737e-07, "epoch": 2.1809744779582365, "percentage": 72.87, "elapsed_time": "1:56:04", "remaining_time": "0:43:13"}
+{"current_steps": 475, "total_steps": 645, "loss": 0.7975, "learning_rate": 1.666620568118603e-07, "epoch": 2.2041763341067284, "percentage": 73.64, "elapsed_time": "1:57:06", "remaining_time": "0:41:54"}
+{"current_steps": 480, "total_steps": 645, "loss": 0.7801, "learning_rate": 1.5754616432650443e-07, "epoch": 2.2273781902552203, "percentage": 74.42, "elapsed_time": "1:58:09", "remaining_time": "0:40:36"}
+{"current_steps": 485, "total_steps": 645, "loss": 0.781, "learning_rate": 1.4863981437550498e-07, "epoch": 2.2505800464037122, "percentage": 75.19, "elapsed_time": "1:59:11", "remaining_time": "0:39:19"}
+{"current_steps": 490, "total_steps": 645, "loss": 0.7799, "learning_rate": 1.3994845662519983e-07, "epoch": 2.273781902552204, "percentage": 75.97, "elapsed_time": "2:00:13", "remaining_time": "0:38:01"}
+{"current_steps": 495, "total_steps": 645, "loss": 0.783, "learning_rate": 1.3147740919131812e-07, "epoch": 2.296983758700696, "percentage": 76.74, "elapsed_time": "2:01:16", "remaining_time": "0:36:44"}
+{"current_steps": 500, "total_steps": 645, "loss": 0.7668, "learning_rate": 1.2323185538490228e-07, "epoch": 2.320185614849188, "percentage": 77.52, "elapsed_time": "2:02:18", "remaining_time": "0:35:28"}
+{"current_steps": 500, "total_steps": 645, "eval_loss": 1.0112136602401733, "epoch": 2.320185614849188, "percentage": 77.52, "elapsed_time": "2:04:04", "remaining_time": "0:35:58"}
+{"current_steps": 505, "total_steps": 645, "loss": 0.7762, "learning_rate": 1.1521684054071523e-07, "epoch": 2.34338747099768, "percentage": 78.29, "elapsed_time": "2:05:38", "remaining_time": "0:34:49"}
+{"current_steps": 510, "total_steps": 645, "loss": 0.7806, "learning_rate": 1.0743726893007254e-07, "epoch": 2.3665893271461718, "percentage": 79.07, "elapsed_time": "2:06:41", "remaining_time": "0:33:32"}
+{"current_steps": 515, "total_steps": 645, "loss": 0.7731, "learning_rate": 9.989790075999144e-08, "epoch": 2.3897911832946637, "percentage": 79.84, "elapsed_time": "2:07:43", "remaining_time": "0:32:14"}
+{"current_steps": 520, "total_steps": 645, "loss": 0.7892, "learning_rate": 9.260334926048785e-08, "epoch": 2.4129930394431556, "percentage": 80.62, "elapsed_time": "2:08:45", "remaining_time": "0:30:57"}
+{"current_steps": 525, "total_steps": 645, "loss": 0.7785, "learning_rate": 8.555807786180813e-08, "epoch": 2.4361948955916475, "percentage": 81.4, "elapsed_time": "2:09:47", "remaining_time": "0:29:39"}
+{"current_steps": 530, "total_steps": 645, "loss": 0.7829, "learning_rate": 7.876639746332131e-08, "epoch": 2.4593967517401394, "percentage": 82.17, "elapsed_time": "2:10:49", "remaining_time": "0:28:23"}
+{"current_steps": 535, "total_steps": 645, "loss": 0.7919, "learning_rate": 7.223246379574205e-08, "epoch": 2.4825986078886313, "percentage": 82.95, "elapsed_time": "2:11:51", "remaining_time": "0:27:06"}
+{"current_steps": 540, "total_steps": 645, "loss": 0.7688, "learning_rate": 6.596027487829913e-08, "epoch": 2.505800464037123, "percentage": 83.72, "elapsed_time": "2:12:54", "remaining_time": "0:25:50"}
+{"current_steps": 545, "total_steps": 645, "loss": 0.7789, "learning_rate": 5.995366857240591e-08, "epoch": 2.529002320185615, "percentage": 84.5, "elapsed_time": "2:13:56", "remaining_time": "0:24:34"}
+{"current_steps": 550, "total_steps": 645, "loss": 0.775, "learning_rate": 5.421632023332778e-08, "epoch": 2.5522041763341066, "percentage": 85.27, "elapsed_time": "2:14:59", "remaining_time": "0:23:18"}
+{"current_steps": 550, "total_steps": 645, "eval_loss": 1.0103154182434082, "epoch": 2.5522041763341066, "percentage": 85.27, "elapsed_time": "2:16:44", "remaining_time": "0:23:37"}
+{"current_steps": 555, "total_steps": 645, "loss": 0.789, "learning_rate": 4.8751740461286826e-08, "epoch": 2.5754060324825985, "percentage": 86.05, "elapsed_time": "2:17:47", "remaining_time": "0:22:20"}
+{"current_steps": 560, "total_steps": 645, "loss": 0.7992, "learning_rate": 4.356327295337542e-08, "epoch": 2.5986078886310904, "percentage": 86.82, "elapsed_time": "2:18:50", "remaining_time": "0:21:04"}
+{"current_steps": 565, "total_steps": 645, "loss": 0.7824, "learning_rate": 3.865409245759671e-08, "epoch": 2.6218097447795823, "percentage": 87.6, "elapsed_time": "2:19:53", "remaining_time": "0:19:48"}
+{"current_steps": 570, "total_steps": 645, "loss": 0.7807, "learning_rate": 3.402720283028277e-08, "epoch": 2.645011600928074, "percentage": 88.37, "elapsed_time": "2:20:55", "remaining_time": "0:18:32"}
+{"current_steps": 575, "total_steps": 645, "loss": 0.7836, "learning_rate": 2.968543519807809e-08, "epoch": 2.668213457076566, "percentage": 89.15, "elapsed_time": "2:21:58", "remaining_time": "0:17:16"}
+{"current_steps": 580, "total_steps": 645, "loss": 0.7866, "learning_rate": 2.5631446225614527e-08, "epoch": 2.691415313225058, "percentage": 89.92, "elapsed_time": "2:23:01", "remaining_time": "0:16:01"}
+{"current_steps": 585, "total_steps": 645, "loss": 0.7724, "learning_rate": 2.1867716489936294e-08, "epoch": 2.71461716937355, "percentage": 90.7, "elapsed_time": "2:24:04", "remaining_time": "0:14:46"}
+{"current_steps": 590, "total_steps": 645, "loss": 0.7903, "learning_rate": 1.8396548962671454e-08, "epoch": 2.737819025522042, "percentage": 91.47, "elapsed_time": "2:25:06", "remaining_time": "0:13:31"}
+{"current_steps": 595, "total_steps": 645, "loss": 0.7711, "learning_rate": 1.5220067600876684e-08, "epoch": 2.7610208816705337, "percentage": 92.25, "elapsed_time": "2:26:09", "remaining_time": "0:12:16"}
+{"current_steps": 600, "total_steps": 645, "loss": 0.7768, "learning_rate": 1.2340216047418694e-08, "epoch": 2.7842227378190256, "percentage": 93.02, "elapsed_time": "2:27:11", "remaining_time": "0:11:02"}
+{"current_steps": 600, "total_steps": 645, "eval_loss": 1.008864164352417, "epoch": 2.7842227378190256, "percentage": 93.02, "elapsed_time": "2:28:57", "remaining_time": "0:11:10"}
+{"current_steps": 605, "total_steps": 645, "loss": 0.7875, "learning_rate": 9.758756441687332e-09, "epoch": 2.8074245939675175, "percentage": 93.8, "elapsed_time": "2:30:30", "remaining_time": "0:09:57"}
+{"current_steps": 610, "total_steps": 645, "loss": 0.785, "learning_rate": 7.477268341368359e-09, "epoch": 2.8306264501160094, "percentage": 94.57, "elapsed_time": "2:31:33", "remaining_time": "0:08:41"}
+{"current_steps": 615, "total_steps": 645, "loss": 0.7832, "learning_rate": 5.497147755934628e-09, "epoch": 2.853828306264501, "percentage": 95.35, "elapsed_time": "2:32:35", "remaining_time": "0:07:26"}
+{"current_steps": 620, "total_steps": 645, "loss": 0.7789, "learning_rate": 3.819606292448541e-09, "epoch": 2.877030162412993, "percentage": 96.12, "elapsed_time": "2:33:37", "remaining_time": "0:06:11"}
+{"current_steps": 625, "total_steps": 645, "loss": 0.7973, "learning_rate": 2.4456704141967433e-09, "epoch": 2.9002320185614847, "percentage": 96.9, "elapsed_time": "2:34:39", "remaining_time": "0:04:56"}
+{"current_steps": 630, "total_steps": 645, "loss": 0.7696, "learning_rate": 1.3761808126126483e-09, "epoch": 2.9234338747099766, "percentage": 97.67, "elapsed_time": "2:35:41", "remaining_time": "0:03:42"}
+{"current_steps": 635, "total_steps": 645, "loss": 0.7886, "learning_rate": 6.117918928693622e-10, "epoch": 2.9466357308584685, "percentage": 98.45, "elapsed_time": "2:36:44", "remaining_time": "0:02:28"}
+{"current_steps": 640, "total_steps": 645, "loss": 0.7661, "learning_rate": 1.529713734584326e-10, "epoch": 2.9698375870069604, "percentage": 99.22, "elapsed_time": "2:37:46", "remaining_time": "0:01:13"}
+{"current_steps": 645, "total_steps": 645, "loss": 0.7806, "learning_rate": 0.0, "epoch": 2.9930394431554523, "percentage": 100.0, "elapsed_time": "2:38:48", "remaining_time": "0:00:00"}
+{"current_steps": 645, "total_steps": 645, "epoch": 2.9930394431554523, "percentage": 100.0, "elapsed_time": "2:39:19", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1041 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9930394431554523,
+  "eval_steps": 50,
+  "global_step": 645,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02320185614849188,
+      "grad_norm": 29.851993456423653,
+      "learning_rate": 5e-07,
+      "loss": 1.6448,
+      "step": 5
+    },
+    {
+      "epoch": 0.04640371229698376,
+      "grad_norm": 14.665681394229273,
+      "learning_rate": 1e-06,
+      "loss": 1.5147,
+      "step": 10
+    },
+    {
+      "epoch": 0.06960556844547564,
+      "grad_norm": 7.818944779433003,
+      "learning_rate": 9.998470286265414e-07,
+      "loss": 1.2888,
+      "step": 15
+    },
+    {
+      "epoch": 0.09280742459396751,
+      "grad_norm": 6.011350341653904,
+      "learning_rate": 9.993882081071305e-07,
+      "loss": 1.2291,
+      "step": 20
+    },
+    {
+      "epoch": 0.11600928074245939,
+      "grad_norm": 5.834488035843988,
+      "learning_rate": 9.986238191873872e-07,
+      "loss": 1.1827,
+      "step": 25
+    },
+    {
+      "epoch": 0.13921113689095127,
+      "grad_norm": 4.944851583820086,
+      "learning_rate": 9.975543295858033e-07,
+      "loss": 1.1637,
+      "step": 30
+    },
+    {
+      "epoch": 0.16241299303944315,
+      "grad_norm": 5.051276519398371,
+      "learning_rate": 9.961803937075514e-07,
+      "loss": 1.1448,
+      "step": 35
+    },
+    {
+      "epoch": 0.18561484918793503,
+      "grad_norm": 5.008630441799495,
+      "learning_rate": 9.945028522440653e-07,
+      "loss": 1.1539,
+      "step": 40
+    },
+    {
+      "epoch": 0.2088167053364269,
+      "grad_norm": 4.527889171881266,
+      "learning_rate": 9.925227316586314e-07,
+      "loss": 1.1302,
+      "step": 45
+    },
+    {
+      "epoch": 0.23201856148491878,
+      "grad_norm": 4.665448898349117,
+      "learning_rate": 9.902412435583125e-07,
+      "loss": 1.1315,
+      "step": 50
+    },
+    {
+      "epoch": 0.23201856148491878,
+      "eval_loss": 1.1243596076965332,
+      "eval_runtime": 107.3706,
+      "eval_samples_per_second": 57.083,
+      "eval_steps_per_second": 0.894,
+      "step": 50
+    },
+    {
+      "epoch": 0.2552204176334107,
+      "grad_norm": 4.780072580854242,
+      "learning_rate": 9.876597839525813e-07,
+      "loss": 1.1184,
+      "step": 55
+    },
+    {
+      "epoch": 0.27842227378190254,
+      "grad_norm": 4.698899616021614,
+      "learning_rate": 9.847799323991233e-07,
+      "loss": 1.1112,
+      "step": 60
+    },
+    {
+      "epoch": 0.30162412993039445,
+      "grad_norm": 4.798544900134018,
+      "learning_rate": 9.816034510373285e-07,
+      "loss": 1.1022,
+      "step": 65
+    },
+    {
+      "epoch": 0.3248259860788863,
+      "grad_norm": 4.7554420584590105,
+      "learning_rate": 9.781322835100637e-07,
+      "loss": 1.1109,
+      "step": 70
+    },
+    {
+      "epoch": 0.3480278422273782,
+      "grad_norm": 4.715791460597178,
+      "learning_rate": 9.743685537743856e-07,
+      "loss": 1.1044,
+      "step": 75
+    },
+    {
+      "epoch": 0.37122969837587005,
+      "grad_norm": 4.781446446456838,
+      "learning_rate": 9.70314564801922e-07,
+      "loss": 1.0982,
+      "step": 80
+    },
+    {
+      "epoch": 0.39443155452436196,
+      "grad_norm": 4.616375479434296,
+      "learning_rate": 9.659727971697173e-07,
+      "loss": 1.0798,
+      "step": 85
+    },
+    {
+      "epoch": 0.4176334106728538,
+      "grad_norm": 4.81678899141071,
+      "learning_rate": 9.613459075424033e-07,
+      "loss": 1.0925,
+      "step": 90
+    },
+    {
+      "epoch": 0.4408352668213457,
+      "grad_norm": 4.804913673447656,
+      "learning_rate": 9.564367270466245e-07,
+      "loss": 1.0726,
+      "step": 95
+    },
+    {
+      "epoch": 0.46403712296983757,
+      "grad_norm": 5.428814841421836,
+      "learning_rate": 9.51248259538713e-07,
+      "loss": 1.0732,
+      "step": 100
+    },
+    {
+      "epoch": 0.46403712296983757,
+      "eval_loss": 1.079745888710022,
+      "eval_runtime": 106.1023,
+      "eval_samples_per_second": 57.765,
+      "eval_steps_per_second": 0.905,
+      "step": 100
+    },
+    {
+      "epoch": 0.4872389791183295,
+      "grad_norm": 4.842120094208203,
+      "learning_rate": 9.457836797666721e-07,
+      "loss": 1.0596,
+      "step": 105
+    },
+    {
+      "epoch": 0.5104408352668214,
+      "grad_norm": 5.09946277444771,
+      "learning_rate": 9.400463314275941e-07,
+      "loss": 1.0699,
+      "step": 110
+    },
+    {
+      "epoch": 0.5336426914153132,
+      "grad_norm": 4.86963572334168,
+      "learning_rate": 9.340397251217008e-07,
+      "loss": 1.0653,
+      "step": 115
+    },
+    {
+      "epoch": 0.5568445475638051,
+      "grad_norm": 4.762779682097982,
+      "learning_rate": 9.27767536204258e-07,
+      "loss": 1.0729,
+      "step": 120
+    },
+    {
+      "epoch": 0.580046403712297,
+      "grad_norm": 4.737687820279848,
+      "learning_rate": 9.212336025366787e-07,
+      "loss": 1.0709,
+      "step": 125
+    },
+    {
+      "epoch": 0.6032482598607889,
+      "grad_norm": 4.782611230029462,
+      "learning_rate": 9.144419221381918e-07,
+      "loss": 1.0579,
+      "step": 130
+    },
+    {
+      "epoch": 0.6264501160092807,
+      "grad_norm": 4.991569479884324,
+      "learning_rate": 9.073966507395121e-07,
+      "loss": 1.0554,
+      "step": 135
+    },
+    {
+      "epoch": 0.6496519721577726,
+      "grad_norm": 5.008963657772678,
+      "learning_rate": 9.001020992400085e-07,
+      "loss": 1.043,
+      "step": 140
+    },
+    {
+      "epoch": 0.6728538283062645,
+      "grad_norm": 5.0207483196868985,
+      "learning_rate": 8.925627310699274e-07,
+      "loss": 1.0531,
+      "step": 145
+    },
+    {
+      "epoch": 0.6960556844547564,
+      "grad_norm": 5.288716673563479,
+      "learning_rate": 8.84783159459285e-07,
+      "loss": 1.0352,
+      "step": 150
+    },
+    {
+      "epoch": 0.6960556844547564,
+      "eval_loss": 1.054144263267517,
+      "eval_runtime": 106.0227,
+      "eval_samples_per_second": 57.808,
+      "eval_steps_per_second": 0.905,
+      "step": 150
+    },
+    {
+      "epoch": 0.7192575406032483,
+      "grad_norm": 5.04033042010659,
+      "learning_rate": 8.767681446150976e-07,
+      "loss": 1.0565,
+      "step": 155
+    },
+    {
+      "epoch": 0.7424593967517401,
+      "grad_norm": 4.8573560396750395,
+      "learning_rate": 8.68522590808682e-07,
+      "loss": 1.0409,
+      "step": 160
+    },
+    {
+      "epoch": 0.765661252900232,
+      "grad_norm": 4.8296712724118125,
+      "learning_rate": 8.600515433748001e-07,
+      "loss": 1.0531,
+      "step": 165
+    },
+    {
+      "epoch": 0.7888631090487239,
+      "grad_norm": 5.039044240861594,
+      "learning_rate": 8.51360185624495e-07,
+      "loss": 1.0321,
+      "step": 170
+    },
+    {
+      "epoch": 0.8120649651972158,
+      "grad_norm": 4.944895975035593,
+      "learning_rate": 8.424538356734956e-07,
+      "loss": 1.0366,
+      "step": 175
+    },
+    {
+      "epoch": 0.8352668213457076,
+      "grad_norm": 5.568497060519676,
+      "learning_rate": 8.333379431881397e-07,
+      "loss": 1.0454,
+      "step": 180
+    },
+    {
+      "epoch": 0.8584686774941995,
+      "grad_norm": 4.984582777418547,
+      "learning_rate": 8.240180860508026e-07,
+      "loss": 1.0368,
+      "step": 185
+    },
+    {
+      "epoch": 0.8816705336426914,
+      "grad_norm": 5.7520355685162,
+      "learning_rate": 8.144999669468713e-07,
+      "loss": 1.0288,
+      "step": 190
+    },
+    {
+      "epoch": 0.9048723897911833,
+      "grad_norm": 5.580835397673134,
+      "learning_rate": 8.047894098753539e-07,
+      "loss": 1.0323,
+      "step": 195
+    },
+    {
+      "epoch": 0.9280742459396751,
+      "grad_norm": 4.941555770840273,
+      "learning_rate": 7.948923565852597e-07,
+      "loss": 1.0347,
+      "step": 200
+    },
+    {
+      "epoch": 0.9280742459396751,
+      "eval_loss": 1.0315721035003662,
+      "eval_runtime": 106.1537,
+      "eval_samples_per_second": 57.737,
+      "eval_steps_per_second": 0.904,
+      "step": 200
+    },
+    {
+      "epoch": 0.951276102088167,
+      "grad_norm": 5.3026133930305335,
+      "learning_rate": 7.848148629399285e-07,
+      "loss": 1.0264,
+      "step": 205
+    },
+    {
+      "epoch": 0.974477958236659,
+      "grad_norm": 5.3528963387584945,
+      "learning_rate": 7.745630952115363e-07,
+      "loss": 1.0204,
+      "step": 210
+    },
+    {
+      "epoch": 0.9976798143851509,
+      "grad_norm": 4.897176107855643,
+      "learning_rate": 7.641433263080418e-07,
+      "loss": 1.0287,
+      "step": 215
+    },
+    {
+      "epoch": 1.0208816705336428,
+      "grad_norm": 5.265360108783065,
+      "learning_rate": 7.535619319348865e-07,
+      "loss": 0.92,
+      "step": 220
+    },
+    {
+      "epoch": 1.0440835266821347,
+      "grad_norm": 5.842663985054576,
+      "learning_rate": 7.428253866937918e-07,
+      "loss": 0.9119,
+      "step": 225
+    },
+    {
+      "epoch": 1.0672853828306264,
+      "grad_norm": 5.255941350708592,
+      "learning_rate": 7.319402601210447e-07,
+      "loss": 0.9091,
+      "step": 230
+    },
+    {
+      "epoch": 1.0904872389791183,
+      "grad_norm": 5.099242988471265,
+      "learning_rate": 7.209132126676933e-07,
+      "loss": 0.8901,
+      "step": 235
+    },
+    {
+      "epoch": 1.1136890951276102,
+      "grad_norm": 5.963233610769237,
+      "learning_rate": 7.097509916241145e-07,
+      "loss": 0.8963,
+      "step": 240
+    },
+    {
+      "epoch": 1.136890951276102,
+      "grad_norm": 5.342236832387553,
+      "learning_rate": 6.984604269914436e-07,
+      "loss": 0.878,
+      "step": 245
+    },
+    {
+      "epoch": 1.160092807424594,
+      "grad_norm": 5.312138241916301,
+      "learning_rate": 6.870484273023967e-07,
+      "loss": 0.8776,
+      "step": 250
+    },
+    {
+      "epoch": 1.160092807424594,
+      "eval_loss": 1.0247548818588257,
+      "eval_runtime": 105.9632,
+      "eval_samples_per_second": 57.841,
+      "eval_steps_per_second": 0.906,
+      "step": 250
+    },
+    {
+      "epoch": 1.1832946635730859,
+      "grad_norm": 5.364600498172952,
+      "learning_rate": 6.755219753940388e-07,
+      "loss": 0.8925,
+      "step": 255
+    },
+    {
+      "epoch": 1.2064965197215778,
+      "grad_norm": 5.752065985447796,
+      "learning_rate": 6.638881241350883e-07,
+      "loss": 0.897,
+      "step": 260
+    },
+    {
+      "epoch": 1.2296983758700697,
+      "grad_norm": 5.570817988636112,
+      "learning_rate": 6.52153992110368e-07,
+      "loss": 0.8839,
+      "step": 265
+    },
+    {
+      "epoch": 1.2529002320185616,
+      "grad_norm": 5.496660790853752,
+      "learning_rate": 6.403267592650466e-07,
+      "loss": 0.8916,
+      "step": 270
+    },
+    {
+      "epoch": 1.2761020881670533,
+      "grad_norm": 5.463347675557559,
+      "learning_rate": 6.28413662511334e-07,
+      "loss": 0.8755,
+      "step": 275
+    },
+    {
+      "epoch": 1.2993039443155452,
+      "grad_norm": 5.514605068924435,
+      "learning_rate": 6.164219913003207e-07,
+      "loss": 0.8775,
+      "step": 280
+    },
+    {
+      "epoch": 1.322505800464037,
+      "grad_norm": 5.727155908190926,
+      "learning_rate": 6.043590831616676e-07,
+      "loss": 0.9028,
+      "step": 285
+    },
+    {
+      "epoch": 1.345707656612529,
+      "grad_norm": 5.429710747722258,
+      "learning_rate": 5.92232319213878e-07,
+      "loss": 0.887,
+      "step": 290
+    },
+    {
+      "epoch": 1.368909512761021,
+      "grad_norm": 5.482889252366046,
+      "learning_rate": 5.800491196478988e-07,
+      "loss": 0.8759,
+      "step": 295
+    },
+    {
+      "epoch": 1.3921113689095128,
+      "grad_norm": 5.670067440966938,
+      "learning_rate": 5.678169391868127e-07,
+      "loss": 0.8888,
+      "step": 300
+    },
+    {
+      "epoch": 1.3921113689095128,
+      "eval_loss": 1.0144710540771484,
+      "eval_runtime": 105.8665,
+      "eval_samples_per_second": 57.894,
+      "eval_steps_per_second": 0.907,
+      "step": 300
+    },
+    {
+      "epoch": 1.4153132250580047,
+      "grad_norm": 5.530990774365388,
+      "learning_rate": 5.555432625244023e-07,
+      "loss": 0.8939,
+      "step": 305
+    },
+    {
+      "epoch": 1.4385150812064964,
+      "grad_norm": 5.572591226625499,
+      "learning_rate": 5.432355997453728e-07,
+      "loss": 0.8929,
+      "step": 310
+    },
+    {
+      "epoch": 1.4617169373549883,
+      "grad_norm": 5.456192949381362,
+      "learning_rate": 5.309014817300421e-07,
+      "loss": 0.9025,
+      "step": 315
+    },
+    {
+      "epoch": 1.4849187935034802,
+      "grad_norm": 5.799863863147117,
+      "learning_rate": 5.185484555463026e-07,
+      "loss": 0.8753,
+      "step": 320
+    },
+    {
+      "epoch": 1.5081206496519721,
+      "grad_norm": 5.73261677068134,
+      "learning_rate": 5.061840798316814e-07,
+      "loss": 0.8938,
+      "step": 325
+    },
+    {
+      "epoch": 1.531322505800464,
+      "grad_norm": 5.762497249365714,
+      "learning_rate": 4.938159201683186e-07,
+      "loss": 0.882,
+      "step": 330
+    },
+    {
+      "epoch": 1.554524361948956,
+      "grad_norm": 5.533641700223646,
+      "learning_rate": 4.814515444536974e-07,
+      "loss": 0.8846,
+      "step": 335
+    },
+    {
+      "epoch": 1.5777262180974478,
+      "grad_norm": 5.782636301369744,
+      "learning_rate": 4.69098518269958e-07,
+      "loss": 0.8875,
+      "step": 340
+    },
+    {
+      "epoch": 1.6009280742459397,
+      "grad_norm": 5.461443407271733,
+      "learning_rate": 4.5676440025462726e-07,
+      "loss": 0.8713,
+      "step": 345
+    },
+    {
+      "epoch": 1.6241299303944317,
+      "grad_norm": 5.571957109149912,
+      "learning_rate": 4.444567374755977e-07,
+      "loss": 0.8902,
+      "step": 350
+    },
+    {
+      "epoch": 1.6241299303944317,
+      "eval_loss": 1.0069366693496704,
+      "eval_runtime": 106.2838,
+      "eval_samples_per_second": 57.666,
+      "eval_steps_per_second": 0.903,
+      "step": 350
+    },
+    {
+      "epoch": 1.6473317865429236,
+      "grad_norm": 5.528554551947589,
+      "learning_rate": 4.3218306081318713e-07,
+      "loss": 0.8789,
+      "step": 355
+    },
+    {
+      "epoch": 1.6705336426914155,
+      "grad_norm": 5.640345642741927,
+      "learning_rate": 4.199508803521012e-07,
+      "loss": 0.8774,
+      "step": 360
+    },
+    {
+      "epoch": 1.6937354988399071,
+      "grad_norm": 5.603129030745687,
+      "learning_rate": 4.0776768078612207e-07,
+      "loss": 0.8717,
+      "step": 365
+    },
+    {
+      "epoch": 1.716937354988399,
+      "grad_norm": 5.6707399409090895,
+      "learning_rate": 3.9564091683833244e-07,
+      "loss": 0.8764,
+      "step": 370
+    },
+    {
+      "epoch": 1.740139211136891,
+      "grad_norm": 5.448091702098461,
+      "learning_rate": 3.835780086996793e-07,
+      "loss": 0.865,
+      "step": 375
+    },
+    {
+      "epoch": 1.7633410672853829,
+      "grad_norm": 5.582199831694094,
+      "learning_rate": 3.7158633748866607e-07,
+      "loss": 0.8779,
+      "step": 380
+    },
+    {
+      "epoch": 1.7865429234338746,
+      "grad_norm": 5.6752676781492255,
+      "learning_rate": 3.596732407349536e-07,
+      "loss": 0.8672,
+      "step": 385
+    },
+    {
+      "epoch": 1.8097447795823665,
+      "grad_norm": 5.5587691039632015,
+      "learning_rate": 3.4784600788963193e-07,
+      "loss": 0.8725,
+      "step": 390
+    },
+    {
+      "epoch": 1.8329466357308584,
+      "grad_norm": 5.5052011161351615,
+      "learning_rate": 3.3611187586491157e-07,
+      "loss": 0.8615,
+      "step": 395
+    },
+    {
+      "epoch": 1.8561484918793503,
+      "grad_norm": 5.507497258082307,
+      "learning_rate": 3.244780246059612e-07,
+      "loss": 0.8773,
+      "step": 400
+    },
+    {
+      "epoch": 1.8561484918793503,
+      "eval_loss": 0.9998582005500793,
+      "eval_runtime": 105.9976,
+      "eval_samples_per_second": 57.822,
+      "eval_steps_per_second": 0.906,
+      "step": 400
+    },
+    {
+      "epoch": 1.8793503480278422,
+      "grad_norm": 5.492700851735595,
+      "learning_rate": 3.129515726976034e-07,
+      "loss": 0.8671,
+      "step": 405
+    },
+    {
+      "epoch": 1.902552204176334,
+      "grad_norm": 5.7486034264931165,
+      "learning_rate": 3.015395730085565e-07,
+      "loss": 0.8614,
+      "step": 410
+    },
+    {
+      "epoch": 1.925754060324826,
+      "grad_norm": 5.124949765854869,
+      "learning_rate": 2.902490083758856e-07,
+      "loss": 0.871,
+      "step": 415
+    },
+    {
+      "epoch": 1.948955916473318,
+      "grad_norm": 5.408996022602446,
+      "learning_rate": 2.790867873323067e-07,
+      "loss": 0.8795,
+      "step": 420
+    },
+    {
+      "epoch": 1.9721577726218098,
+      "grad_norm": 5.750334709291967,
+      "learning_rate": 2.680597398789554e-07,
+      "loss": 0.8588,
+      "step": 425
+    },
+    {
+      "epoch": 1.9953596287703017,
+      "grad_norm": 5.711244881678974,
+      "learning_rate": 2.5717461330620815e-07,
+      "loss": 0.8719,
+      "step": 430
+    },
+    {
+      "epoch": 2.0185614849187936,
+      "grad_norm": 6.122014805843198,
+      "learning_rate": 2.464380680651134e-07,
+      "loss": 0.7933,
+      "step": 435
+    },
+    {
+      "epoch": 2.0417633410672855,
+      "grad_norm": 6.215562802835813,
+      "learning_rate": 2.358566736919581e-07,
+      "loss": 0.7943,
+      "step": 440
+    },
+    {
+      "epoch": 2.0649651972157774,
+      "grad_norm": 5.90592154174332,
+      "learning_rate": 2.2543690478846388e-07,
+      "loss": 0.778,
+      "step": 445
+    },
+    {
+      "epoch": 2.0881670533642693,
+      "grad_norm": 5.689955483676048,
+      "learning_rate": 2.1518513706007152e-07,
+      "loss": 0.7847,
+      "step": 450
+    },
+    {
+      "epoch": 2.0881670533642693,
+      "eval_loss": 1.0113998651504517,
+      "eval_runtime": 106.2215,
+      "eval_samples_per_second": 57.7,
+      "eval_steps_per_second": 0.904,
+      "step": 450
+    },
+    {
+      "epoch": 2.111368909512761,
+      "grad_norm": 5.550398002087045,
+      "learning_rate": 2.051076434147403e-07,
+      "loss": 0.7843,
+      "step": 455
+    },
+    {
+      "epoch": 2.1345707656612527,
+      "grad_norm": 5.681734155354411,
+      "learning_rate": 1.9521059012464607e-07,
+      "loss": 0.7678,
+      "step": 460
+    },
+    {
+      "epoch": 2.1577726218097446,
+      "grad_norm": 5.865956254391275,
+      "learning_rate": 1.855000330531289e-07,
+      "loss": 0.7897,
+      "step": 465
+    },
+    {
+      "epoch": 2.1809744779582365,
+      "grad_norm": 6.055658613132172,
+      "learning_rate": 1.7598191394919737e-07,
+      "loss": 0.7811,
+      "step": 470
+    },
+    {
+      "epoch": 2.2041763341067284,
+      "grad_norm": 6.233987278809335,
+      "learning_rate": 1.666620568118603e-07,
+      "loss": 0.7975,
+      "step": 475
+    },
+    {
+      "epoch": 2.2273781902552203,
+      "grad_norm": 5.824376205357217,
+      "learning_rate": 1.5754616432650443e-07,
+      "loss": 0.7801,
+      "step": 480
+    },
+    {
+      "epoch": 2.2505800464037122,
+      "grad_norm": 6.375178064295241,
+      "learning_rate": 1.4863981437550498e-07,
+      "loss": 0.781,
+      "step": 485
+    },
+    {
+      "epoch": 2.273781902552204,
+      "grad_norm": 6.211607396754804,
+      "learning_rate": 1.3994845662519983e-07,
+      "loss": 0.7799,
+      "step": 490
+    },
+    {
+      "epoch": 2.296983758700696,
+      "grad_norm": 5.980327624770438,
+      "learning_rate": 1.3147740919131812e-07,
+      "loss": 0.783,
+      "step": 495
+    },
+    {
+      "epoch": 2.320185614849188,
+      "grad_norm": 5.925933936835478,
+      "learning_rate": 1.2323185538490228e-07,
+      "loss": 0.7668,
+      "step": 500
+    },
+    {
+      "epoch": 2.320185614849188,
+      "eval_loss": 1.0112136602401733,
+      "eval_runtime": 105.6668,
+      "eval_samples_per_second": 58.003,
+      "eval_steps_per_second": 0.909,
+      "step": 500
+    },
+    {
+      "epoch": 2.34338747099768,
+      "grad_norm": 6.06031016994975,
+      "learning_rate": 1.1521684054071523e-07,
+      "loss": 0.7762,
+      "step": 505
+    },
+    {
+      "epoch": 2.3665893271461718,
+      "grad_norm": 6.173374303238529,
+      "learning_rate": 1.0743726893007254e-07,
+      "loss": 0.7806,
+      "step": 510
+    },
+    {
+      "epoch": 2.3897911832946637,
+      "grad_norm": 6.009209700505245,
+      "learning_rate": 9.989790075999144e-08,
+      "loss": 0.7731,
+      "step": 515
+    },
+    {
+      "epoch": 2.4129930394431556,
+      "grad_norm": 5.744648775110227,
+      "learning_rate": 9.260334926048785e-08,
+      "loss": 0.7892,
+      "step": 520
+    },
+    {
+      "epoch": 2.4361948955916475,
+      "grad_norm": 5.949296215452574,
+      "learning_rate": 8.555807786180813e-08,
+      "loss": 0.7785,
+      "step": 525
+    },
+    {
+      "epoch": 2.4593967517401394,
+      "grad_norm": 5.936014562230361,
+      "learning_rate": 7.876639746332131e-08,
+      "loss": 0.7829,
+      "step": 530
+    },
+    {
+      "epoch": 2.4825986078886313,
+      "grad_norm": 5.859713250927308,
+      "learning_rate": 7.223246379574205e-08,
+      "loss": 0.7919,
+      "step": 535
+    },
+    {
+      "epoch": 2.505800464037123,
+      "grad_norm": 6.243664538264793,
+      "learning_rate": 6.596027487829913e-08,
+      "loss": 0.7688,
+      "step": 540
+    },
+    {
+      "epoch": 2.529002320185615,
+      "grad_norm": 6.031972239373065,
+      "learning_rate": 5.995366857240591e-08,
+      "loss": 0.7789,
+      "step": 545
+    },
+    {
+      "epoch": 2.5522041763341066,
+      "grad_norm": 6.130593159142583,
+      "learning_rate": 5.421632023332778e-08,
+      "loss": 0.775,
+      "step": 550
+    },
+    {
+      "epoch": 2.5522041763341066,
+      "eval_loss": 1.0103154182434082,
+      "eval_runtime": 105.6016,
+      "eval_samples_per_second": 58.039,
+      "eval_steps_per_second": 0.909,
+      "step": 550
+    },
+    {
+      "epoch": 2.5754060324825985,
+      "grad_norm": 5.963207804570064,
+      "learning_rate": 4.8751740461286826e-08,
+      "loss": 0.789,
+      "step": 555
+    },
+    {
+      "epoch": 2.5986078886310904,
+      "grad_norm": 5.8736607983865525,
+      "learning_rate": 4.356327295337542e-08,
+      "loss": 0.7992,
+      "step": 560
+    },
+    {
+      "epoch": 2.6218097447795823,
+      "grad_norm": 6.077763163177709,
+      "learning_rate": 3.865409245759671e-08,
+      "loss": 0.7824,
+      "step": 565
+    },
+    {
+      "epoch": 2.645011600928074,
+      "grad_norm": 5.999232007718555,
+      "learning_rate": 3.402720283028277e-08,
+      "loss": 0.7807,
+      "step": 570
+    },
+    {
+      "epoch": 2.668213457076566,
+      "grad_norm": 5.782915072578643,
+      "learning_rate": 2.968543519807809e-08,
+      "loss": 0.7836,
+      "step": 575
+    },
+    {
+      "epoch": 2.691415313225058,
+      "grad_norm": 5.895133763158038,
+      "learning_rate": 2.5631446225614527e-08,
+      "loss": 0.7866,
+      "step": 580
+    },
+    {
+      "epoch": 2.71461716937355,
+      "grad_norm": 5.789961425841594,
+      "learning_rate": 2.1867716489936294e-08,
+      "loss": 0.7724,
+      "step": 585
+    },
+    {
+      "epoch": 2.737819025522042,
+      "grad_norm": 5.666163619117144,
+      "learning_rate": 1.8396548962671454e-08,
+      "loss": 0.7903,
+      "step": 590
+    },
+    {
+      "epoch": 2.7610208816705337,
+      "grad_norm": 5.768500926901973,
+      "learning_rate": 1.5220067600876684e-08,
+      "loss": 0.7711,
+      "step": 595
+    },
+    {
+      "epoch": 2.7842227378190256,
+      "grad_norm": 6.087496150272388,
+      "learning_rate": 1.2340216047418694e-08,
+      "loss": 0.7768,
+      "step": 600
+    },
+    {
+      "epoch": 2.7842227378190256,
+      "eval_loss": 1.008864164352417,
+      "eval_runtime": 105.8761,
+      "eval_samples_per_second": 57.888,
+      "eval_steps_per_second": 0.907,
+      "step": 600
+    },
+    {
+      "epoch": 2.8074245939675175,
+      "grad_norm": 6.207391484980199,
+      "learning_rate": 9.758756441687332e-09,
+      "loss": 0.7875,
+      "step": 605
+    },
+    {
+      "epoch": 2.8306264501160094,
+      "grad_norm": 5.954613559365798,
+      "learning_rate": 7.477268341368359e-09,
+      "loss": 0.785,
+      "step": 610
+    },
+    {
+      "epoch": 2.853828306264501,
+      "grad_norm": 5.819327712838159,
+      "learning_rate": 5.497147755934628e-09,
+      "loss": 0.7832,
+      "step": 615
+    },
+    {
+      "epoch": 2.877030162412993,
+      "grad_norm": 5.786005516883902,
+      "learning_rate": 3.819606292448541e-09,
+      "loss": 0.7789,
+      "step": 620
+    },
+    {
+      "epoch": 2.9002320185614847,
+      "grad_norm": 6.130101975578697,
+      "learning_rate": 2.4456704141967433e-09,
+      "loss": 0.7973,
+      "step": 625
+    },
+    {
+      "epoch": 2.9234338747099766,
+      "grad_norm": 6.065019587560417,
+      "learning_rate": 1.3761808126126483e-09,
+      "loss": 0.7696,
+      "step": 630
+    },
+    {
+      "epoch": 2.9466357308584685,
+      "grad_norm": 5.601585670340757,
+      "learning_rate": 6.117918928693622e-10,
+      "loss": 0.7886,
+      "step": 635
+    },
+    {
+      "epoch": 2.9698375870069604,
+      "grad_norm": 6.062046858888585,
+      "learning_rate": 1.529713734584326e-10,
+      "loss": 0.7661,
+      "step": 640
+    },
+    {
+      "epoch": 2.9930394431554523,
+      "grad_norm": 6.1764579820644885,
+      "learning_rate": 0.0,
+      "loss": 0.7806,
+      "step": 645
+    },
+    {
+      "epoch": 2.9930394431554523,
+      "step": 645,
+      "total_flos": 3802978389590016.0,
+      "train_loss": 0.9239856169205304,
+      "train_runtime": 9561.8566,
+      "train_samples_per_second": 17.305,
+      "train_steps_per_second": 0.067
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 645,
+  "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": 3802978389590016.0,
+  "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:cef97751db22de2a12cad3d2c8912345ec8e7f9129f20bc7f99d8013b1401f3f
+size 7096