Upload folder using huggingface_hub

README.md

@@ -0,0 +1,80 @@
+---
+library_name: transformers
+license: other
+base_model: llava-hf/llava-v1.6-mistral-7b-hf
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Compcap_l0_0_70
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Compcap_l0_0_70
+
+This model is a fine-tuned version of [llava-hf/llava-v1.6-mistral-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf) on the Compcap_l0_0_70 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7935
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9541        | 0.1934 | 50   | 0.9273          |
+| 0.8621        | 0.3868 | 100  | 0.8719          |
+| 0.8657        | 0.5803 | 150  | 0.8459          |
+| 0.8232        | 0.7737 | 200  | 0.8287          |
+| 0.8179        | 0.9671 | 250  | 0.8162          |
+| 0.7558        | 1.1605 | 300  | 0.8122          |
+| 0.7602        | 1.3540 | 350  | 0.8059          |
+| 0.771         | 1.5474 | 400  | 0.7998          |
+| 0.753         | 1.7408 | 450  | 0.7955          |
+| 0.7479        | 1.9342 | 500  | 0.7920          |
+| 0.6735        | 2.1277 | 550  | 0.7972          |
+| 0.7116        | 2.3211 | 600  | 0.7952          |
+| 0.6822        | 2.5145 | 650  | 0.7943          |
+| 0.6861        | 2.7079 | 700  | 0.7938          |
+| 0.6989        | 2.9014 | 750  | 0.7935          |
+
+
+### 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": 2.9941972920696323,
+    "eval_loss": 0.7935342788696289,
+    "eval_runtime": 127.3911,
+    "eval_samples_per_second": 57.696,
+    "eval_steps_per_second": 0.903,
+    "total_flos": 4563620855808000.0,
+    "train_loss": 0.7856120132968716,
+    "train_runtime": 12058.8177,
+    "train_samples_per_second": 16.457,
+    "train_steps_per_second": 0.064
+}

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": 2.9941972920696323,
+    "eval_loss": 0.7935342788696289,
+    "eval_runtime": 127.3911,
+    "eval_samples_per_second": 57.696,
+    "eval_steps_per_second": 0.903
+}

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:e7297fc44b4cda633992b8438f75f536617fee0d17d7311dabbaa4fe0062dd57
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4fb4d5ae8fa8d4606dbb85dee550719c19bb3e673783399a6e6cccf279fdab3
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4124f89239c582f8082458b91a92ec188472b13044873e02359f9b6b676edf40
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc4940bb0a7da19e8879990e1c3f38005b2120df104e8dd5203b0e17ab5fb51
+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": 2.9941972920696323,
+    "total_flos": 4563620855808000.0,
+    "train_loss": 0.7856120132968716,
+    "train_runtime": 12058.8177,
+    "train_samples_per_second": 16.457,
+    "train_steps_per_second": 0.064
+}

trainer_log.jsonl

@@ -0,0 +1,170 @@
+{"current_steps": 5, "total_steps": 774, "loss": 1.7186, "learning_rate": 5e-07, "epoch": 0.019342359767891684, "percentage": 0.65, "elapsed_time": "0:01:09", "remaining_time": "2:57:11"}
+{"current_steps": 10, "total_steps": 774, "loss": 1.5925, "learning_rate": 1e-06, "epoch": 0.03868471953578337, "percentage": 1.29, "elapsed_time": "0:02:14", "remaining_time": "2:50:58"}
+{"current_steps": 15, "total_steps": 774, "loss": 1.2917, "learning_rate": 9.998943236640677e-07, "epoch": 0.058027079303675046, "percentage": 1.94, "elapsed_time": "0:03:20", "remaining_time": "2:48:41"}
+{"current_steps": 20, "total_steps": 774, "loss": 1.152, "learning_rate": 9.995773393262229e-07, "epoch": 0.07736943907156674, "percentage": 2.58, "elapsed_time": "0:04:25", "remaining_time": "2:46:52"}
+{"current_steps": 25, "total_steps": 774, "loss": 1.0662, "learning_rate": 9.99049180977439e-07, "epoch": 0.09671179883945841, "percentage": 3.23, "elapsed_time": "0:05:30", "remaining_time": "2:45:03"}
+{"current_steps": 30, "total_steps": 774, "loss": 1.0205, "learning_rate": 9.983100718730718e-07, "epoch": 0.11605415860735009, "percentage": 3.88, "elapsed_time": "0:06:36", "remaining_time": "2:43:42"}
+{"current_steps": 35, "total_steps": 774, "loss": 0.9948, "learning_rate": 9.973603244384906e-07, "epoch": 0.13539651837524178, "percentage": 4.52, "elapsed_time": "0:07:40", "remaining_time": "2:42:09"}
+{"current_steps": 40, "total_steps": 774, "loss": 0.9421, "learning_rate": 9.9620034013701e-07, "epoch": 0.15473887814313347, "percentage": 5.17, "elapsed_time": "0:08:46", "remaining_time": "2:40:55"}
+{"current_steps": 45, "total_steps": 774, "loss": 0.9544, "learning_rate": 9.948306093001933e-07, "epoch": 0.17408123791102514, "percentage": 5.81, "elapsed_time": "0:09:51", "remaining_time": "2:39:39"}
+{"current_steps": 50, "total_steps": 774, "loss": 0.9541, "learning_rate": 9.932517109205849e-07, "epoch": 0.19342359767891681, "percentage": 6.46, "elapsed_time": "0:10:56", "remaining_time": "2:38:32"}
+{"current_steps": 50, "total_steps": 774, "eval_loss": 0.9273383021354675, "epoch": 0.19342359767891681, "percentage": 6.46, "elapsed_time": "0:13:04", "remaining_time": "3:09:23"}
+{"current_steps": 55, "total_steps": 774, "loss": 0.906, "learning_rate": 9.914643124069666e-07, "epoch": 0.2127659574468085, "percentage": 7.11, "elapsed_time": "0:14:09", "remaining_time": "3:05:00"}
+{"current_steps": 60, "total_steps": 774, "loss": 0.9124, "learning_rate": 9.89469169302242e-07, "epoch": 0.23210831721470018, "percentage": 7.75, "elapsed_time": "0:15:14", "remaining_time": "3:01:24"}
+{"current_steps": 65, "total_steps": 774, "loss": 0.9371, "learning_rate": 9.872671249640626e-07, "epoch": 0.2514506769825919, "percentage": 8.4, "elapsed_time": "0:16:19", "remaining_time": "2:58:08"}
+{"current_steps": 70, "total_steps": 774, "loss": 0.9202, "learning_rate": 9.848591102083375e-07, "epoch": 0.27079303675048355, "percentage": 9.04, "elapsed_time": "0:17:24", "remaining_time": "2:55:02"}
+{"current_steps": 75, "total_steps": 774, "loss": 0.9395, "learning_rate": 9.822461429157716e-07, "epoch": 0.2901353965183752, "percentage": 9.69, "elapsed_time": "0:18:29", "remaining_time": "2:52:23"}
+{"current_steps": 80, "total_steps": 774, "loss": 0.9039, "learning_rate": 9.794293276016023e-07, "epoch": 0.30947775628626695, "percentage": 10.34, "elapsed_time": "0:19:34", "remaining_time": "2:49:51"}
+{"current_steps": 85, "total_steps": 774, "loss": 0.8935, "learning_rate": 9.764098549487155e-07, "epoch": 0.3288201160541586, "percentage": 10.98, "elapsed_time": "0:20:40", "remaining_time": "2:47:31"}
+{"current_steps": 90, "total_steps": 774, "loss": 0.8922, "learning_rate": 9.731890013043367e-07, "epoch": 0.3481624758220503, "percentage": 11.63, "elapsed_time": "0:21:44", "remaining_time": "2:45:16"}
+{"current_steps": 95, "total_steps": 774, "loss": 0.8675, "learning_rate": 9.697681281405128e-07, "epoch": 0.36750483558994196, "percentage": 12.27, "elapsed_time": "0:22:50", "remaining_time": "2:43:18"}
+{"current_steps": 100, "total_steps": 774, "loss": 0.8621, "learning_rate": 9.6614868147861e-07, "epoch": 0.38684719535783363, "percentage": 12.92, "elapsed_time": "0:23:55", "remaining_time": "2:41:18"}
+{"current_steps": 100, "total_steps": 774, "eval_loss": 0.8719474077224731, "epoch": 0.38684719535783363, "percentage": 12.92, "elapsed_time": "0:26:03", "remaining_time": "2:55:39"}
+{"current_steps": 105, "total_steps": 774, "loss": 0.8956, "learning_rate": 9.623321912780744e-07, "epoch": 0.40618955512572535, "percentage": 13.57, "elapsed_time": "0:27:09", "remaining_time": "2:53:01"}
+{"current_steps": 110, "total_steps": 774, "loss": 0.8645, "learning_rate": 9.583202707897073e-07, "epoch": 0.425531914893617, "percentage": 14.21, "elapsed_time": "0:28:14", "remaining_time": "2:50:29"}
+{"current_steps": 115, "total_steps": 774, "loss": 0.8526, "learning_rate": 9.54114615873738e-07, "epoch": 0.4448742746615087, "percentage": 14.86, "elapsed_time": "0:29:20", "remaining_time": "2:48:05"}
+{"current_steps": 120, "total_steps": 774, "loss": 0.873, "learning_rate": 9.497170042829736e-07, "epoch": 0.46421663442940037, "percentage": 15.5, "elapsed_time": "0:30:25", "remaining_time": "2:45:47"}
+{"current_steps": 125, "total_steps": 774, "loss": 0.8646, "learning_rate": 9.451292949113329e-07, "epoch": 0.4835589941972921, "percentage": 16.15, "elapsed_time": "0:31:31", "remaining_time": "2:43:38"}
+{"current_steps": 130, "total_steps": 774, "loss": 0.8668, "learning_rate": 9.403534270080829e-07, "epoch": 0.5029013539651838, "percentage": 16.8, "elapsed_time": "0:32:35", "remaining_time": "2:41:26"}
+{"current_steps": 135, "total_steps": 774, "loss": 0.8522, "learning_rate": 9.353914193581072e-07, "epoch": 0.5222437137330754, "percentage": 17.44, "elapsed_time": "0:33:40", "remaining_time": "2:39:25"}
+{"current_steps": 140, "total_steps": 774, "loss": 0.8552, "learning_rate": 9.302453694285548e-07, "epoch": 0.5415860735009671, "percentage": 18.09, "elapsed_time": "0:34:45", "remaining_time": "2:37:23"}
+{"current_steps": 145, "total_steps": 774, "loss": 0.8569, "learning_rate": 9.249174524822305e-07, "epoch": 0.5609284332688588, "percentage": 18.73, "elapsed_time": "0:35:50", "remaining_time": "2:35:27"}
+{"current_steps": 150, "total_steps": 774, "loss": 0.8657, "learning_rate": 9.19409920658098e-07, "epoch": 0.5802707930367504, "percentage": 19.38, "elapsed_time": "0:36:55", "remaining_time": "2:33:35"}
+{"current_steps": 150, "total_steps": 774, "eval_loss": 0.8459084033966064, "epoch": 0.5802707930367504, "percentage": 19.38, "elapsed_time": "0:39:02", "remaining_time": "2:42:26"}
+{"current_steps": 155, "total_steps": 774, "loss": 0.8513, "learning_rate": 9.137251020192907e-07, "epoch": 0.5996131528046421, "percentage": 20.03, "elapsed_time": "0:40:07", "remaining_time": "2:40:13"}
+{"current_steps": 160, "total_steps": 774, "loss": 0.8375, "learning_rate": 9.078653995690246e-07, "epoch": 0.6189555125725339, "percentage": 20.67, "elapsed_time": "0:41:11", "remaining_time": "2:38:05"}
+{"current_steps": 165, "total_steps": 774, "loss": 0.8505, "learning_rate": 9.018332902348388e-07, "epoch": 0.6382978723404256, "percentage": 21.32, "elapsed_time": "0:42:16", "remaining_time": "2:36:03"}
+{"current_steps": 170, "total_steps": 774, "loss": 0.8472, "learning_rate": 8.956313238215823e-07, "epoch": 0.6576402321083172, "percentage": 21.96, "elapsed_time": "0:43:22", "remaining_time": "2:34:05"}
+{"current_steps": 175, "total_steps": 774, "loss": 0.8489, "learning_rate": 8.892621219336e-07, "epoch": 0.6769825918762089, "percentage": 22.61, "elapsed_time": "0:44:27", "remaining_time": "2:32:11"}
+{"current_steps": 180, "total_steps": 774, "loss": 0.8463, "learning_rate": 8.827283768665648e-07, "epoch": 0.6963249516441006, "percentage": 23.26, "elapsed_time": "0:45:32", "remaining_time": "2:30:17"}
+{"current_steps": 185, "total_steps": 774, "loss": 0.8303, "learning_rate": 8.760328504694317e-07, "epoch": 0.7156673114119922, "percentage": 23.9, "elapsed_time": "0:46:37", "remaining_time": "2:28:27"}
+{"current_steps": 190, "total_steps": 774, "loss": 0.8285, "learning_rate": 8.691783729769873e-07, "epoch": 0.7350096711798839, "percentage": 24.55, "elapsed_time": "0:47:43", "remaining_time": "2:26:41"}
+{"current_steps": 195, "total_steps": 774, "loss": 0.8267, "learning_rate": 8.621678418134963e-07, "epoch": 0.7543520309477756, "percentage": 25.19, "elapsed_time": "0:48:48", "remaining_time": "2:24:56"}
+{"current_steps": 200, "total_steps": 774, "loss": 0.8232, "learning_rate": 8.550042203679439e-07, "epoch": 0.7736943907156673, "percentage": 25.84, "elapsed_time": "0:49:54", "remaining_time": "2:23:13"}
+{"current_steps": 200, "total_steps": 774, "eval_loss": 0.8286838531494141, "epoch": 0.7736943907156673, "percentage": 25.84, "elapsed_time": "0:52:01", "remaining_time": "2:29:19"}
+{"current_steps": 205, "total_steps": 774, "loss": 0.8321, "learning_rate": 8.476905367413957e-07, "epoch": 0.793036750483559, "percentage": 26.49, "elapsed_time": "0:53:06", "remaining_time": "2:27:25"}
+{"current_steps": 210, "total_steps": 774, "loss": 0.8261, "learning_rate": 8.402298824670029e-07, "epoch": 0.8123791102514507, "percentage": 27.13, "elapsed_time": "0:54:12", "remaining_time": "2:25:35"}
+{"current_steps": 215, "total_steps": 774, "loss": 0.83, "learning_rate": 8.326254112031949e-07, "epoch": 0.8317214700193424, "percentage": 27.78, "elapsed_time": "0:55:18", "remaining_time": "2:23:48"}
+{"current_steps": 220, "total_steps": 774, "loss": 0.8263, "learning_rate": 8.248803374006113e-07, "epoch": 0.851063829787234, "percentage": 28.42, "elapsed_time": "0:56:23", "remaining_time": "2:22:01"}
+{"current_steps": 225, "total_steps": 774, "loss": 0.8233, "learning_rate": 8.169979349433358e-07, "epoch": 0.8704061895551257, "percentage": 29.07, "elapsed_time": "0:57:29", "remaining_time": "2:20:17"}
+{"current_steps": 230, "total_steps": 774, "loss": 0.8224, "learning_rate": 8.089815357650089e-07, "epoch": 0.8897485493230174, "percentage": 29.72, "elapsed_time": "0:58:35", "remaining_time": "2:18:35"}
+{"current_steps": 235, "total_steps": 774, "loss": 0.823, "learning_rate": 8.008345284404003e-07, "epoch": 0.9090909090909091, "percentage": 30.36, "elapsed_time": "0:59:41", "remaining_time": "2:16:53"}
+{"current_steps": 240, "total_steps": 774, "loss": 0.8363, "learning_rate": 7.925603567530418e-07, "epoch": 0.9284332688588007, "percentage": 31.01, "elapsed_time": "1:00:45", "remaining_time": "2:15:12"}
+{"current_steps": 245, "total_steps": 774, "loss": 0.8396, "learning_rate": 7.841625182395206e-07, "epoch": 0.9477756286266924, "percentage": 31.65, "elapsed_time": "1:01:50", "remaining_time": "2:13:31"}
+{"current_steps": 250, "total_steps": 774, "loss": 0.8179, "learning_rate": 7.756445627110522e-07, "epoch": 0.9671179883945842, "percentage": 32.3, "elapsed_time": "1:02:55", "remaining_time": "2:11:53"}
+{"current_steps": 250, "total_steps": 774, "eval_loss": 0.8162312507629395, "epoch": 0.9671179883945842, "percentage": 32.3, "elapsed_time": "1:05:03", "remaining_time": "2:16:21"}
+{"current_steps": 255, "total_steps": 774, "loss": 0.8267, "learning_rate": 7.670100907529557e-07, "epoch": 0.9864603481624759, "percentage": 32.95, "elapsed_time": "1:06:08", "remaining_time": "2:14:37"}
+{"current_steps": 260, "total_steps": 774, "loss": 0.7992, "learning_rate": 7.582627522026685e-07, "epoch": 1.0058027079303675, "percentage": 33.59, "elapsed_time": "1:07:14", "remaining_time": "2:12:55"}
+{"current_steps": 265, "total_steps": 774, "loss": 0.7297, "learning_rate": 7.49406244606939e-07, "epoch": 1.0251450676982592, "percentage": 34.24, "elapsed_time": "1:08:18", "remaining_time": "2:11:12"}
+{"current_steps": 270, "total_steps": 774, "loss": 0.7652, "learning_rate": 7.404443116588547e-07, "epoch": 1.0444874274661509, "percentage": 34.88, "elapsed_time": "1:09:23", "remaining_time": "2:09:32"}
+{"current_steps": 275, "total_steps": 774, "loss": 0.7412, "learning_rate": 7.31380741615363e-07, "epoch": 1.0638297872340425, "percentage": 35.53, "elapsed_time": "1:10:28", "remaining_time": "2:07:53"}
+{"current_steps": 280, "total_steps": 774, "loss": 0.7637, "learning_rate": 7.222193656959546e-07, "epoch": 1.0831721470019342, "percentage": 36.18, "elapsed_time": "1:11:33", "remaining_time": "2:06:15"}
+{"current_steps": 285, "total_steps": 774, "loss": 0.7634, "learning_rate": 7.129640564631863e-07, "epoch": 1.1025145067698259, "percentage": 36.82, "elapsed_time": "1:12:39", "remaining_time": "2:04:39"}
+{"current_steps": 290, "total_steps": 774, "loss": 0.7502, "learning_rate": 7.036187261857288e-07, "epoch": 1.1218568665377175, "percentage": 37.47, "elapsed_time": "1:13:44", "remaining_time": "2:03:05"}
+{"current_steps": 295, "total_steps": 774, "loss": 0.7737, "learning_rate": 6.941873251846293e-07, "epoch": 1.1411992263056092, "percentage": 38.11, "elapsed_time": "1:14:50", "remaining_time": "2:01:31"}
+{"current_steps": 300, "total_steps": 774, "loss": 0.7558, "learning_rate": 6.846738401634898e-07, "epoch": 1.1605415860735009, "percentage": 38.76, "elapsed_time": "1:15:55", "remaining_time": "1:59:58"}
+{"current_steps": 300, "total_steps": 774, "eval_loss": 0.8122316598892212, "epoch": 1.1605415860735009, "percentage": 38.76, "elapsed_time": "1:18:03", "remaining_time": "2:03:20"}
+{"current_steps": 305, "total_steps": 774, "loss": 0.7701, "learning_rate": 6.750822925232663e-07, "epoch": 1.1798839458413926, "percentage": 39.41, "elapsed_time": "1:19:08", "remaining_time": "2:01:41"}
+{"current_steps": 310, "total_steps": 774, "loss": 0.7641, "learning_rate": 6.654167366624008e-07, "epoch": 1.1992263056092844, "percentage": 40.05, "elapsed_time": "1:20:13", "remaining_time": "2:00:05"}
+{"current_steps": 315, "total_steps": 774, "loss": 0.7481, "learning_rate": 6.556812582630059e-07, "epoch": 1.218568665377176, "percentage": 40.7, "elapsed_time": "1:21:18", "remaining_time": "1:58:29"}
+{"current_steps": 320, "total_steps": 774, "loss": 0.7494, "learning_rate": 6.458799725638248e-07, "epoch": 1.2379110251450678, "percentage": 41.34, "elapsed_time": "1:22:23", "remaining_time": "1:56:53"}
+{"current_steps": 325, "total_steps": 774, "loss": 0.7291, "learning_rate": 6.36017022620698e-07, "epoch": 1.2572533849129595, "percentage": 41.99, "elapsed_time": "1:23:29", "remaining_time": "1:55:20"}
+{"current_steps": 330, "total_steps": 774, "loss": 0.7643, "learning_rate": 6.260965775552713e-07, "epoch": 1.2765957446808511, "percentage": 42.64, "elapsed_time": "1:24:35", "remaining_time": "1:53:48"}
+{"current_steps": 335, "total_steps": 774, "loss": 0.7374, "learning_rate": 6.161228307926858e-07, "epoch": 1.2959381044487428, "percentage": 43.28, "elapsed_time": "1:25:39", "remaining_time": "1:52:15"}
+{"current_steps": 340, "total_steps": 774, "loss": 0.7568, "learning_rate": 6.060999982889954e-07, "epoch": 1.3152804642166345, "percentage": 43.93, "elapsed_time": "1:26:45", "remaining_time": "1:50:44"}
+{"current_steps": 345, "total_steps": 774, "loss": 0.7453, "learning_rate": 5.960323167490588e-07, "epoch": 1.3346228239845261, "percentage": 44.57, "elapsed_time": "1:27:50", "remaining_time": "1:49:13"}
+{"current_steps": 350, "total_steps": 774, "loss": 0.7602, "learning_rate": 5.859240418356614e-07, "epoch": 1.3539651837524178, "percentage": 45.22, "elapsed_time": "1:28:55", "remaining_time": "1:47:43"}
+{"current_steps": 350, "total_steps": 774, "eval_loss": 0.8059322834014893, "epoch": 1.3539651837524178, "percentage": 45.22, "elapsed_time": "1:31:03", "remaining_time": "1:50:18"}
+{"current_steps": 355, "total_steps": 774, "loss": 0.7523, "learning_rate": 5.757794463706253e-07, "epoch": 1.3733075435203095, "percentage": 45.87, "elapsed_time": "1:32:09", "remaining_time": "1:48:45"}
+{"current_steps": 360, "total_steps": 774, "loss": 0.7496, "learning_rate": 5.656028185286637e-07, "epoch": 1.3926499032882012, "percentage": 46.51, "elapsed_time": "1:33:14", "remaining_time": "1:47:13"}
+{"current_steps": 365, "total_steps": 774, "loss": 0.7647, "learning_rate": 5.553984600247463e-07, "epoch": 1.4119922630560928, "percentage": 47.16, "elapsed_time": "1:34:19", "remaining_time": "1:45:41"}
+{"current_steps": 370, "total_steps": 774, "loss": 0.718, "learning_rate": 5.451706842957421e-07, "epoch": 1.4313346228239845, "percentage": 47.8, "elapsed_time": "1:35:24", "remaining_time": "1:44:10"}
+{"current_steps": 375, "total_steps": 774, "loss": 0.7583, "learning_rate": 5.349238146771061e-07, "epoch": 1.4506769825918762, "percentage": 48.45, "elapsed_time": "1:36:30", "remaining_time": "1:42:40"}
+{"current_steps": 380, "total_steps": 774, "loss": 0.7435, "learning_rate": 5.246621825753827e-07, "epoch": 1.4700193423597678, "percentage": 49.1, "elapsed_time": "1:37:35", "remaining_time": "1:41:11"}
+{"current_steps": 385, "total_steps": 774, "loss": 0.7397, "learning_rate": 5.143901256372967e-07, "epoch": 1.4893617021276595, "percentage": 49.74, "elapsed_time": "1:38:41", "remaining_time": "1:39:42"}
+{"current_steps": 390, "total_steps": 774, "loss": 0.7295, "learning_rate": 5.041119859162068e-07, "epoch": 1.5087040618955512, "percentage": 50.39, "elapsed_time": "1:39:46", "remaining_time": "1:38:13"}
+{"current_steps": 395, "total_steps": 774, "loss": 0.7484, "learning_rate": 4.938321080366968e-07, "epoch": 1.528046421663443, "percentage": 51.03, "elapsed_time": "1:40:51", "remaining_time": "1:36:46"}
+{"current_steps": 400, "total_steps": 774, "loss": 0.771, "learning_rate": 4.835548373580792e-07, "epoch": 1.5473887814313345, "percentage": 51.68, "elapsed_time": "1:41:57", "remaining_time": "1:35:19"}
+{"current_steps": 400, "total_steps": 774, "eval_loss": 0.7998485565185547, "epoch": 1.5473887814313345, "percentage": 51.68, "elapsed_time": "1:44:05", "remaining_time": "1:37:19"}
+{"current_steps": 405, "total_steps": 774, "loss": 0.7472, "learning_rate": 4.73284518137589e-07, "epoch": 1.5667311411992264, "percentage": 52.33, "elapsed_time": "1:45:10", "remaining_time": "1:35:49"}
+{"current_steps": 410, "total_steps": 774, "loss": 0.7349, "learning_rate": 4.630254916940423e-07, "epoch": 1.5860735009671179, "percentage": 52.97, "elapsed_time": "1:46:15", "remaining_time": "1:34:20"}
+{"current_steps": 415, "total_steps": 774, "loss": 0.7539, "learning_rate": 4.5278209457273825e-07, "epoch": 1.6054158607350097, "percentage": 53.62, "elapsed_time": "1:47:20", "remaining_time": "1:32:51"}
+{"current_steps": 420, "total_steps": 774, "loss": 0.7561, "learning_rate": 4.425586567123779e-07, "epoch": 1.6247582205029012, "percentage": 54.26, "elapsed_time": "1:48:25", "remaining_time": "1:31:23"}
+{"current_steps": 425, "total_steps": 774, "loss": 0.7456, "learning_rate": 4.3235949961477627e-07, "epoch": 1.644100580270793, "percentage": 54.91, "elapsed_time": "1:49:30", "remaining_time": "1:29:55"}
+{"current_steps": 430, "total_steps": 774, "loss": 0.7458, "learning_rate": 4.2218893451814e-07, "epoch": 1.6634429400386848, "percentage": 55.56, "elapsed_time": "1:50:35", "remaining_time": "1:28:28"}
+{"current_steps": 435, "total_steps": 774, "loss": 0.7394, "learning_rate": 4.120512605746842e-07, "epoch": 1.6827852998065764, "percentage": 56.2, "elapsed_time": "1:51:40", "remaining_time": "1:27:02"}
+{"current_steps": 440, "total_steps": 774, "loss": 0.7365, "learning_rate": 4.019507630333577e-07, "epoch": 1.702127659574468, "percentage": 56.85, "elapsed_time": "1:52:46", "remaining_time": "1:25:36"}
+{"current_steps": 445, "total_steps": 774, "loss": 0.7559, "learning_rate": 3.9189171142844553e-07, "epoch": 1.7214700193423598, "percentage": 57.49, "elapsed_time": "1:53:52", "remaining_time": "1:24:11"}
+{"current_steps": 450, "total_steps": 774, "loss": 0.753, "learning_rate": 3.8187835777481375e-07, "epoch": 1.7408123791102514, "percentage": 58.14, "elapsed_time": "1:54:56", "remaining_time": "1:22:45"}
+{"current_steps": 450, "total_steps": 774, "eval_loss": 0.7954617738723755, "epoch": 1.7408123791102514, "percentage": 58.14, "elapsed_time": "1:57:04", "remaining_time": "1:24:17"}
+{"current_steps": 455, "total_steps": 774, "loss": 0.7416, "learning_rate": 3.7191493477056086e-07, "epoch": 1.760154738878143, "percentage": 58.79, "elapsed_time": "1:58:09", "remaining_time": "1:22:50"}
+{"current_steps": 460, "total_steps": 774, "loss": 0.7465, "learning_rate": 3.620056540078323e-07, "epoch": 1.7794970986460348, "percentage": 59.43, "elapsed_time": "1:59:15", "remaining_time": "1:21:24"}
+{"current_steps": 465, "total_steps": 774, "loss": 0.7381, "learning_rate": 3.5215470419255897e-07, "epoch": 1.7988394584139265, "percentage": 60.08, "elapsed_time": "2:00:20", "remaining_time": "1:19:58"}
+{"current_steps": 470, "total_steps": 774, "loss": 0.7393, "learning_rate": 3.423662493738687e-07, "epoch": 1.8181818181818183, "percentage": 60.72, "elapsed_time": "2:01:24", "remaining_time": "1:18:31"}
+{"current_steps": 475, "total_steps": 774, "loss": 0.7361, "learning_rate": 3.3264442718392014e-07, "epoch": 1.8375241779497098, "percentage": 61.37, "elapsed_time": "2:02:30", "remaining_time": "1:17:06"}
+{"current_steps": 480, "total_steps": 774, "loss": 0.743, "learning_rate": 3.229933470889038e-07, "epoch": 1.8568665377176017, "percentage": 62.02, "elapsed_time": "2:03:36", "remaining_time": "1:15:42"}
+{"current_steps": 485, "total_steps": 774, "loss": 0.722, "learning_rate": 3.134170886519486e-07, "epoch": 1.8762088974854931, "percentage": 62.66, "elapsed_time": "2:04:41", "remaining_time": "1:14:17"}
+{"current_steps": 490, "total_steps": 774, "loss": 0.7292, "learning_rate": 3.039196998086687e-07, "epoch": 1.895551257253385, "percentage": 63.31, "elapsed_time": "2:05:46", "remaining_time": "1:12:53"}
+{"current_steps": 495, "total_steps": 774, "loss": 0.7402, "learning_rate": 2.9450519515607963e-07, "epoch": 1.9148936170212765, "percentage": 63.95, "elapsed_time": "2:06:52", "remaining_time": "1:11:30"}
+{"current_steps": 500, "total_steps": 774, "loss": 0.7479, "learning_rate": 2.8517755425560663e-07, "epoch": 1.9342359767891684, "percentage": 64.6, "elapsed_time": "2:07:57", "remaining_time": "1:10:07"}
+{"current_steps": 500, "total_steps": 774, "eval_loss": 0.7919633984565735, "epoch": 1.9342359767891684, "percentage": 64.6, "elapsed_time": "2:10:05", "remaining_time": "1:11:17"}
+{"current_steps": 505, "total_steps": 774, "loss": 0.7414, "learning_rate": 2.7594071995090283e-07, "epoch": 1.9535783365570598, "percentage": 65.25, "elapsed_time": "2:11:10", "remaining_time": "1:09:52"}
+{"current_steps": 510, "total_steps": 774, "loss": 0.7442, "learning_rate": 2.667985967011878e-07, "epoch": 1.9729206963249517, "percentage": 65.89, "elapsed_time": "2:12:15", "remaining_time": "1:08:27"}
+{"current_steps": 515, "total_steps": 774, "loss": 0.7445, "learning_rate": 2.577550489308123e-07, "epoch": 1.9922630560928434, "percentage": 66.54, "elapsed_time": "2:13:21", "remaining_time": "1:07:04"}
+{"current_steps": 520, "total_steps": 774, "loss": 0.7238, "learning_rate": 2.488138993957452e-07, "epoch": 2.011605415860735, "percentage": 67.18, "elapsed_time": "2:14:26", "remaining_time": "1:05:40"}
+{"current_steps": 525, "total_steps": 774, "loss": 0.7148, "learning_rate": 2.3997892756767394e-07, "epoch": 2.0309477756286265, "percentage": 67.83, "elapsed_time": "2:15:31", "remaining_time": "1:04:16"}
+{"current_steps": 530, "total_steps": 774, "loss": 0.6955, "learning_rate": 2.3125386803640183e-07, "epoch": 2.0502901353965184, "percentage": 68.48, "elapsed_time": "2:16:36", "remaining_time": "1:02:53"}
+{"current_steps": 535, "total_steps": 774, "loss": 0.7016, "learning_rate": 2.226424089312174e-07, "epoch": 2.0696324951644103, "percentage": 69.12, "elapsed_time": "2:17:41", "remaining_time": "1:01:30"}
+{"current_steps": 540, "total_steps": 774, "loss": 0.7054, "learning_rate": 2.1414819036190157e-07, "epoch": 2.0889748549323017, "percentage": 69.77, "elapsed_time": "2:18:47", "remaining_time": "1:00:08"}
+{"current_steps": 545, "total_steps": 774, "loss": 0.6801, "learning_rate": 2.057748028800344e-07, "epoch": 2.1083172147001936, "percentage": 70.41, "elapsed_time": "2:19:52", "remaining_time": "0:58:46"}
+{"current_steps": 550, "total_steps": 774, "loss": 0.6735, "learning_rate": 1.9752578596124952e-07, "epoch": 2.127659574468085, "percentage": 71.06, "elapsed_time": "2:20:57", "remaining_time": "0:57:24"}
+{"current_steps": 550, "total_steps": 774, "eval_loss": 0.7972328066825867, "epoch": 2.127659574468085, "percentage": 71.06, "elapsed_time": "2:23:05", "remaining_time": "0:58:16"}
+{"current_steps": 555, "total_steps": 774, "loss": 0.6887, "learning_rate": 1.8940462650907912e-07, "epoch": 2.147001934235977, "percentage": 71.71, "elapsed_time": "2:24:10", "remaining_time": "0:56:53"}
+{"current_steps": 560, "total_steps": 774, "loss": 0.6829, "learning_rate": 1.8141475738102086e-07, "epoch": 2.1663442940038684, "percentage": 72.35, "elapsed_time": "2:25:15", "remaining_time": "0:55:30"}
+{"current_steps": 565, "total_steps": 774, "loss": 0.701, "learning_rate": 1.735595559374508e-07, "epoch": 2.1856866537717603, "percentage": 73.0, "elapsed_time": "2:26:20", "remaining_time": "0:54:08"}
+{"current_steps": 570, "total_steps": 774, "loss": 0.6962, "learning_rate": 1.6584234261399532e-07, "epoch": 2.2050290135396517, "percentage": 73.64, "elapsed_time": "2:27:27", "remaining_time": "0:52:46"}
+{"current_steps": 575, "total_steps": 774, "loss": 0.704, "learning_rate": 1.5826637951796474e-07, "epoch": 2.2243713733075436, "percentage": 74.29, "elapsed_time": "2:28:32", "remaining_time": "0:51:24"}
+{"current_steps": 580, "total_steps": 774, "loss": 0.6866, "learning_rate": 1.5083486904944387e-07, "epoch": 2.243713733075435, "percentage": 74.94, "elapsed_time": "2:29:37", "remaining_time": "0:50:02"}
+{"current_steps": 585, "total_steps": 774, "loss": 0.6921, "learning_rate": 1.4355095254761974e-07, "epoch": 2.263056092843327, "percentage": 75.58, "elapsed_time": "2:30:42", "remaining_time": "0:48:41"}
+{"current_steps": 590, "total_steps": 774, "loss": 0.6813, "learning_rate": 1.3641770896292082e-07, "epoch": 2.2823984526112184, "percentage": 76.23, "elapsed_time": "2:31:48", "remaining_time": "0:47:20"}
+{"current_steps": 595, "total_steps": 774, "loss": 0.6928, "learning_rate": 1.2943815355552851e-07, "epoch": 2.3017408123791103, "percentage": 76.87, "elapsed_time": "2:32:52", "remaining_time": "0:45:59"}
+{"current_steps": 600, "total_steps": 774, "loss": 0.7116, "learning_rate": 1.226152366208104e-07, "epoch": 2.3210831721470018, "percentage": 77.52, "elapsed_time": "2:33:58", "remaining_time": "0:44:39"}
+{"current_steps": 600, "total_steps": 774, "eval_loss": 0.7951865196228027, "epoch": 2.3210831721470018, "percentage": 77.52, "elapsed_time": "2:36:06", "remaining_time": "0:45:16"}
+{"current_steps": 605, "total_steps": 774, "loss": 0.692, "learning_rate": 1.1595184224221466e-07, "epoch": 2.3404255319148937, "percentage": 78.17, "elapsed_time": "2:37:11", "remaining_time": "0:43:54"}
+{"current_steps": 610, "total_steps": 774, "loss": 0.6865, "learning_rate": 1.0945078707215221e-07, "epoch": 2.359767891682785, "percentage": 78.81, "elapsed_time": "2:38:17", "remaining_time": "0:42:33"}
+{"current_steps": 615, "total_steps": 774, "loss": 0.6985, "learning_rate": 1.0311481914138371e-07, "epoch": 2.379110251450677, "percentage": 79.46, "elapsed_time": "2:39:22", "remaining_time": "0:41:12"}
+{"current_steps": 620, "total_steps": 774, "loss": 0.6968, "learning_rate": 9.6946616697411e-08, "epoch": 2.398452611218569, "percentage": 80.1, "elapsed_time": "2:40:27", "remaining_time": "0:39:51"}
+{"current_steps": 625, "total_steps": 774, "loss": 0.7002, "learning_rate": 9.094878707236841e-08, "epoch": 2.4177949709864603, "percentage": 80.75, "elapsed_time": "2:41:33", "remaining_time": "0:38:30"}
+{"current_steps": 630, "total_steps": 774, "loss": 0.7018, "learning_rate": 8.512386558088919e-08, "epoch": 2.437137330754352, "percentage": 81.4, "elapsed_time": "2:42:38", "remaining_time": "0:37:10"}
+{"current_steps": 635, "total_steps": 774, "loss": 0.6953, "learning_rate": 7.947431444841452e-08, "epoch": 2.4564796905222437, "percentage": 82.04, "elapsed_time": "2:43:43", "remaining_time": "0:35:50"}
+{"current_steps": 640, "total_steps": 774, "loss": 0.7023, "learning_rate": 7.400252177039784e-08, "epoch": 2.4758220502901356, "percentage": 82.69, "elapsed_time": "2:44:48", "remaining_time": "0:34:30"}
+{"current_steps": 645, "total_steps": 774, "loss": 0.6822, "learning_rate": 6.871080050284394e-08, "epoch": 2.495164410058027, "percentage": 83.33, "elapsed_time": "2:45:53", "remaining_time": "0:33:10"}
+{"current_steps": 650, "total_steps": 774, "loss": 0.6822, "learning_rate": 6.360138748461013e-08, "epoch": 2.514506769825919, "percentage": 83.98, "elapsed_time": "2:46:58", "remaining_time": "0:31:51"}
+{"current_steps": 650, "total_steps": 774, "eval_loss": 0.794310986995697, "epoch": 2.514506769825919, "percentage": 83.98, "elapsed_time": "2:49:06", "remaining_time": "0:32:15"}
+{"current_steps": 655, "total_steps": 774, "loss": 0.6991, "learning_rate": 5.867644249188247e-08, "epoch": 2.5338491295938104, "percentage": 84.63, "elapsed_time": "2:50:12", "remaining_time": "0:30:55"}
+{"current_steps": 660, "total_steps": 774, "loss": 0.6986, "learning_rate": 5.3938047325226944e-08, "epoch": 2.5531914893617023, "percentage": 85.27, "elapsed_time": "2:51:18", "remaining_time": "0:29:35"}
+{"current_steps": 665, "total_steps": 774, "loss": 0.6854, "learning_rate": 4.9388204929601326e-08, "epoch": 2.5725338491295937, "percentage": 85.92, "elapsed_time": "2:52:23", "remaining_time": "0:28:15"}
+{"current_steps": 670, "total_steps": 774, "loss": 0.6924, "learning_rate": 4.5028838547699346e-08, "epoch": 2.5918762088974856, "percentage": 86.56, "elapsed_time": "2:53:28", "remaining_time": "0:26:55"}
+{"current_steps": 675, "total_steps": 774, "loss": 0.6888, "learning_rate": 4.0861790906985884e-08, "epoch": 2.611218568665377, "percentage": 87.21, "elapsed_time": "2:54:34", "remaining_time": "0:25:36"}
+{"current_steps": 680, "total_steps": 774, "loss": 0.6914, "learning_rate": 3.6888823440766214e-08, "epoch": 2.630560928433269, "percentage": 87.86, "elapsed_time": "2:55:39", "remaining_time": "0:24:16"}
+{"current_steps": 685, "total_steps": 774, "loss": 0.6773, "learning_rate": 3.311161554361874e-08, "epoch": 2.6499032882011604, "percentage": 88.5, "elapsed_time": "2:56:44", "remaining_time": "0:22:57"}
+{"current_steps": 690, "total_steps": 774, "loss": 0.6908, "learning_rate": 2.9531763861505964e-08, "epoch": 2.6692456479690523, "percentage": 89.15, "elapsed_time": "2:57:49", "remaining_time": "0:21:38"}
+{"current_steps": 695, "total_steps": 774, "loss": 0.6638, "learning_rate": 2.6150781616863794e-08, "epoch": 2.6885880077369437, "percentage": 89.79, "elapsed_time": "2:58:55", "remaining_time": "0:20:20"}
+{"current_steps": 700, "total_steps": 774, "loss": 0.6861, "learning_rate": 2.2970097968953994e-08, "epoch": 2.7079303675048356, "percentage": 90.44, "elapsed_time": "3:00:00", "remaining_time": "0:19:01"}
+{"current_steps": 700, "total_steps": 774, "eval_loss": 0.7937687635421753, "epoch": 2.7079303675048356, "percentage": 90.44, "elapsed_time": "3:02:08", "remaining_time": "0:19:15"}
+{"current_steps": 705, "total_steps": 774, "loss": 0.6911, "learning_rate": 1.9991057409751267e-08, "epoch": 2.7272727272727275, "percentage": 91.09, "elapsed_time": "3:03:14", "remaining_time": "0:17:56"}
+{"current_steps": 710, "total_steps": 774, "loss": 0.6909, "learning_rate": 1.7214919195619125e-08, "epoch": 2.746615087040619, "percentage": 91.73, "elapsed_time": "3:04:19", "remaining_time": "0:16:36"}
+{"current_steps": 715, "total_steps": 774, "loss": 0.6999, "learning_rate": 1.4642856815015758e-08, "epoch": 2.7659574468085104, "percentage": 92.38, "elapsed_time": "3:05:24", "remaining_time": "0:15:17"}
+{"current_steps": 720, "total_steps": 774, "loss": 0.6933, "learning_rate": 1.2275957492453692e-08, "epoch": 2.7852998065764023, "percentage": 93.02, "elapsed_time": "3:06:30", "remaining_time": "0:13:59"}
+{"current_steps": 725, "total_steps": 774, "loss": 0.6775, "learning_rate": 1.0115221728924706e-08, "epoch": 2.804642166344294, "percentage": 93.67, "elapsed_time": "3:07:35", "remaining_time": "0:12:40"}
+{"current_steps": 730, "total_steps": 774, "loss": 0.6748, "learning_rate": 8.161562878982398e-09, "epoch": 2.8239845261121856, "percentage": 94.32, "elapsed_time": "3:08:40", "remaining_time": "0:11:22"}
+{"current_steps": 735, "total_steps": 774, "loss": 0.6759, "learning_rate": 6.415806764662524e-09, "epoch": 2.843326885880077, "percentage": 94.96, "elapsed_time": "3:09:46", "remaining_time": "0:10:04"}
+{"current_steps": 740, "total_steps": 774, "loss": 0.698, "learning_rate": 4.8786913264033945e-09, "epoch": 2.862669245647969, "percentage": 95.61, "elapsed_time": "3:10:51", "remaining_time": "0:08:46"}
+{"current_steps": 745, "total_steps": 774, "loss": 0.6856, "learning_rate": 3.5508663111147306e-09, "epoch": 2.882011605415861, "percentage": 96.25, "elapsed_time": "3:11:56", "remaining_time": "0:07:28"}
+{"current_steps": 750, "total_steps": 774, "loss": 0.6989, "learning_rate": 2.432892997526026e-09, "epoch": 2.9013539651837523, "percentage": 96.9, "elapsed_time": "3:13:02", "remaining_time": "0:06:10"}
+{"current_steps": 750, "total_steps": 774, "eval_loss": 0.7935436367988586, "epoch": 2.9013539651837523, "percentage": 96.9, "elapsed_time": "3:15:09", "remaining_time": "0:06:14"}
+{"current_steps": 755, "total_steps": 774, "loss": 0.6929, "learning_rate": 1.5252439589311107e-09, "epoch": 2.920696324951644, "percentage": 97.55, "elapsed_time": "3:16:15", "remaining_time": "0:04:56"}
+{"current_steps": 760, "total_steps": 774, "loss": 0.6963, "learning_rate": 8.283028634287203e-10, "epoch": 2.9400386847195357, "percentage": 98.19, "elapsed_time": "3:17:21", "remaining_time": "0:03:38"}
+{"current_steps": 765, "total_steps": 774, "loss": 0.683, "learning_rate": 3.4236431174428094e-10, "epoch": 2.9593810444874276, "percentage": 98.84, "elapsed_time": "3:18:26", "remaining_time": "0:02:20"}
+{"current_steps": 770, "total_steps": 774, "loss": 0.684, "learning_rate": 6.763371270035457e-11, "epoch": 2.978723404255319, "percentage": 99.48, "elapsed_time": "3:19:31", "remaining_time": "0:01:02"}
+{"current_steps": 774, "total_steps": 774, "epoch": 2.9941972920696323, "percentage": 100.0, "elapsed_time": "3:20:56", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1240 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9941972920696323,
+  "eval_steps": 50,
+  "global_step": 774,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.019342359767891684,
+      "grad_norm": 17.769769703655175,
+      "learning_rate": 5e-07,
+      "loss": 1.7186,
+      "step": 5
+    },
+    {
+      "epoch": 0.03868471953578337,
+      "grad_norm": 13.081004196040046,
+      "learning_rate": 1e-06,
+      "loss": 1.5925,
+      "step": 10
+    },
+    {
+      "epoch": 0.058027079303675046,
+      "grad_norm": 7.089375759826574,
+      "learning_rate": 9.998943236640677e-07,
+      "loss": 1.2917,
+      "step": 15
+    },
+    {
+      "epoch": 0.07736943907156674,
+      "grad_norm": 4.226052382894484,
+      "learning_rate": 9.995773393262229e-07,
+      "loss": 1.152,
+      "step": 20
+    },
+    {
+      "epoch": 0.09671179883945841,
+      "grad_norm": 4.275706578437442,
+      "learning_rate": 9.99049180977439e-07,
+      "loss": 1.0662,
+      "step": 25
+    },
+    {
+      "epoch": 0.11605415860735009,
+      "grad_norm": 3.8773098526703986,
+      "learning_rate": 9.983100718730718e-07,
+      "loss": 1.0205,
+      "step": 30
+    },
+    {
+      "epoch": 0.13539651837524178,
+      "grad_norm": 3.5740777007667783,
+      "learning_rate": 9.973603244384906e-07,
+      "loss": 0.9948,
+      "step": 35
+    },
+    {
+      "epoch": 0.15473887814313347,
+      "grad_norm": 3.6003113336465318,
+      "learning_rate": 9.9620034013701e-07,
+      "loss": 0.9421,
+      "step": 40
+    },
+    {
+      "epoch": 0.17408123791102514,
+      "grad_norm": 3.583333545710018,
+      "learning_rate": 9.948306093001933e-07,
+      "loss": 0.9544,
+      "step": 45
+    },
+    {
+      "epoch": 0.19342359767891681,
+      "grad_norm": 3.7908364237614416,
+      "learning_rate": 9.932517109205849e-07,
+      "loss": 0.9541,
+      "step": 50
+    },
+    {
+      "epoch": 0.19342359767891681,
+      "eval_loss": 0.9273383021354675,
+      "eval_runtime": 127.7915,
+      "eval_samples_per_second": 57.516,
+      "eval_steps_per_second": 0.9,
+      "step": 50
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 3.613000346904536,
+      "learning_rate": 9.914643124069666e-07,
+      "loss": 0.906,
+      "step": 55
+    },
+    {
+      "epoch": 0.23210831721470018,
+      "grad_norm": 3.6167098335205994,
+      "learning_rate": 9.89469169302242e-07,
+      "loss": 0.9124,
+      "step": 60
+    },
+    {
+      "epoch": 0.2514506769825919,
+      "grad_norm": 3.6118346250444553,
+      "learning_rate": 9.872671249640626e-07,
+      "loss": 0.9371,
+      "step": 65
+    },
+    {
+      "epoch": 0.27079303675048355,
+      "grad_norm": 3.5717388877832117,
+      "learning_rate": 9.848591102083375e-07,
+      "loss": 0.9202,
+      "step": 70
+    },
+    {
+      "epoch": 0.2901353965183752,
+      "grad_norm": 3.713276627714593,
+      "learning_rate": 9.822461429157716e-07,
+      "loss": 0.9395,
+      "step": 75
+    },
+    {
+      "epoch": 0.30947775628626695,
+      "grad_norm": 3.8351121315501007,
+      "learning_rate": 9.794293276016023e-07,
+      "loss": 0.9039,
+      "step": 80
+    },
+    {
+      "epoch": 0.3288201160541586,
+      "grad_norm": 3.3458211116161043,
+      "learning_rate": 9.764098549487155e-07,
+      "loss": 0.8935,
+      "step": 85
+    },
+    {
+      "epoch": 0.3481624758220503,
+      "grad_norm": 3.6453614828666105,
+      "learning_rate": 9.731890013043367e-07,
+      "loss": 0.8922,
+      "step": 90
+    },
+    {
+      "epoch": 0.36750483558994196,
+      "grad_norm": 3.67687317911342,
+      "learning_rate": 9.697681281405128e-07,
+      "loss": 0.8675,
+      "step": 95
+    },
+    {
+      "epoch": 0.38684719535783363,
+      "grad_norm": 3.4055043252450132,
+      "learning_rate": 9.6614868147861e-07,
+      "loss": 0.8621,
+      "step": 100
+    },
+    {
+      "epoch": 0.38684719535783363,
+      "eval_loss": 0.8719474077224731,
+      "eval_runtime": 127.7997,
+      "eval_samples_per_second": 57.512,
+      "eval_steps_per_second": 0.9,
+      "step": 100
+    },
+    {
+      "epoch": 0.40618955512572535,
+      "grad_norm": 3.4010105290171797,
+      "learning_rate": 9.623321912780744e-07,
+      "loss": 0.8956,
+      "step": 105
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 3.726255996119051,
+      "learning_rate": 9.583202707897073e-07,
+      "loss": 0.8645,
+      "step": 110
+    },
+    {
+      "epoch": 0.4448742746615087,
+      "grad_norm": 3.428308495841723,
+      "learning_rate": 9.54114615873738e-07,
+      "loss": 0.8526,
+      "step": 115
+    },
+    {
+      "epoch": 0.46421663442940037,
+      "grad_norm": 3.4777454179113914,
+      "learning_rate": 9.497170042829736e-07,
+      "loss": 0.873,
+      "step": 120
+    },
+    {
+      "epoch": 0.4835589941972921,
+      "grad_norm": 3.306069687386359,
+      "learning_rate": 9.451292949113329e-07,
+      "loss": 0.8646,
+      "step": 125
+    },
+    {
+      "epoch": 0.5029013539651838,
+      "grad_norm": 3.6787006187120315,
+      "learning_rate": 9.403534270080829e-07,
+      "loss": 0.8668,
+      "step": 130
+    },
+    {
+      "epoch": 0.5222437137330754,
+      "grad_norm": 3.8412614001222387,
+      "learning_rate": 9.353914193581072e-07,
+      "loss": 0.8522,
+      "step": 135
+    },
+    {
+      "epoch": 0.5415860735009671,
+      "grad_norm": 3.63279379492409,
+      "learning_rate": 9.302453694285548e-07,
+      "loss": 0.8552,
+      "step": 140
+    },
+    {
+      "epoch": 0.5609284332688588,
+      "grad_norm": 3.557168960609258,
+      "learning_rate": 9.249174524822305e-07,
+      "loss": 0.8569,
+      "step": 145
+    },
+    {
+      "epoch": 0.5802707930367504,
+      "grad_norm": 3.6248960952352673,
+      "learning_rate": 9.19409920658098e-07,
+      "loss": 0.8657,
+      "step": 150
+    },
+    {
+      "epoch": 0.5802707930367504,
+      "eval_loss": 0.8459084033966064,
+      "eval_runtime": 127.5971,
+      "eval_samples_per_second": 57.603,
+      "eval_steps_per_second": 0.901,
+      "step": 150
+    },
+    {
+      "epoch": 0.5996131528046421,
+      "grad_norm": 3.4411079524968815,
+      "learning_rate": 9.137251020192907e-07,
+      "loss": 0.8513,
+      "step": 155
+    },
+    {
+      "epoch": 0.6189555125725339,
+      "grad_norm": 3.399830662079635,
+      "learning_rate": 9.078653995690246e-07,
+      "loss": 0.8375,
+      "step": 160
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 3.60600371924574,
+      "learning_rate": 9.018332902348388e-07,
+      "loss": 0.8505,
+      "step": 165
+    },
+    {
+      "epoch": 0.6576402321083172,
+      "grad_norm": 3.331304480330792,
+      "learning_rate": 8.956313238215823e-07,
+      "loss": 0.8472,
+      "step": 170
+    },
+    {
+      "epoch": 0.6769825918762089,
+      "grad_norm": 3.6483016146418876,
+      "learning_rate": 8.892621219336e-07,
+      "loss": 0.8489,
+      "step": 175
+    },
+    {
+      "epoch": 0.6963249516441006,
+      "grad_norm": 3.421730346610911,
+      "learning_rate": 8.827283768665648e-07,
+      "loss": 0.8463,
+      "step": 180
+    },
+    {
+      "epoch": 0.7156673114119922,
+      "grad_norm": 3.7149068640377694,
+      "learning_rate": 8.760328504694317e-07,
+      "loss": 0.8303,
+      "step": 185
+    },
+    {
+      "epoch": 0.7350096711798839,
+      "grad_norm": 3.5148473544431953,
+      "learning_rate": 8.691783729769873e-07,
+      "loss": 0.8285,
+      "step": 190
+    },
+    {
+      "epoch": 0.7543520309477756,
+      "grad_norm": 3.8143875519937227,
+      "learning_rate": 8.621678418134963e-07,
+      "loss": 0.8267,
+      "step": 195
+    },
+    {
+      "epoch": 0.7736943907156673,
+      "grad_norm": 3.665364587167835,
+      "learning_rate": 8.550042203679439e-07,
+      "loss": 0.8232,
+      "step": 200
+    },
+    {
+      "epoch": 0.7736943907156673,
+      "eval_loss": 0.8286838531494141,
+      "eval_runtime": 127.6464,
+      "eval_samples_per_second": 57.581,
+      "eval_steps_per_second": 0.901,
+      "step": 200
+    },
+    {
+      "epoch": 0.793036750483559,
+      "grad_norm": 3.6010898270602216,
+      "learning_rate": 8.476905367413957e-07,
+      "loss": 0.8321,
+      "step": 205
+    },
+    {
+      "epoch": 0.8123791102514507,
+      "grad_norm": 3.4203770888001173,
+      "learning_rate": 8.402298824670029e-07,
+      "loss": 0.8261,
+      "step": 210
+    },
+    {
+      "epoch": 0.8317214700193424,
+      "grad_norm": 3.5555049932560707,
+      "learning_rate": 8.326254112031949e-07,
+      "loss": 0.83,
+      "step": 215
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 3.5446967824907465,
+      "learning_rate": 8.248803374006113e-07,
+      "loss": 0.8263,
+      "step": 220
+    },
+    {
+      "epoch": 0.8704061895551257,
+      "grad_norm": 3.582387564660827,
+      "learning_rate": 8.169979349433358e-07,
+      "loss": 0.8233,
+      "step": 225
+    },
+    {
+      "epoch": 0.8897485493230174,
+      "grad_norm": 3.477179043854488,
+      "learning_rate": 8.089815357650089e-07,
+      "loss": 0.8224,
+      "step": 230
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 3.5228566797833176,
+      "learning_rate": 8.008345284404003e-07,
+      "loss": 0.823,
+      "step": 235
+    },
+    {
+      "epoch": 0.9284332688588007,
+      "grad_norm": 3.5831989534603235,
+      "learning_rate": 7.925603567530418e-07,
+      "loss": 0.8363,
+      "step": 240
+    },
+    {
+      "epoch": 0.9477756286266924,
+      "grad_norm": 3.5406680784685003,
+      "learning_rate": 7.841625182395206e-07,
+      "loss": 0.8396,
+      "step": 245
+    },
+    {
+      "epoch": 0.9671179883945842,
+      "grad_norm": 3.586661139550379,
+      "learning_rate": 7.756445627110522e-07,
+      "loss": 0.8179,
+      "step": 250
+    },
+    {
+      "epoch": 0.9671179883945842,
+      "eval_loss": 0.8162312507629395,
+      "eval_runtime": 127.7269,
+      "eval_samples_per_second": 57.545,
+      "eval_steps_per_second": 0.9,
+      "step": 250
+    },
+    {
+      "epoch": 0.9864603481624759,
+      "grad_norm": 3.583872815575711,
+      "learning_rate": 7.670100907529557e-07,
+      "loss": 0.8267,
+      "step": 255
+    },
+    {
+      "epoch": 1.0058027079303675,
+      "grad_norm": 3.4543546378461354,
+      "learning_rate": 7.582627522026685e-07,
+      "loss": 0.7992,
+      "step": 260
+    },
+    {
+      "epoch": 1.0251450676982592,
+      "grad_norm": 3.4033484910260197,
+      "learning_rate": 7.49406244606939e-07,
+      "loss": 0.7297,
+      "step": 265
+    },
+    {
+      "epoch": 1.0444874274661509,
+      "grad_norm": 3.4147333856503272,
+      "learning_rate": 7.404443116588547e-07,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 3.4496152121107486,
+      "learning_rate": 7.31380741615363e-07,
+      "loss": 0.7412,
+      "step": 275
+    },
+    {
+      "epoch": 1.0831721470019342,
+      "grad_norm": 3.327696184514914,
+      "learning_rate": 7.222193656959546e-07,
+      "loss": 0.7637,
+      "step": 280
+    },
+    {
+      "epoch": 1.1025145067698259,
+      "grad_norm": 3.7061830831988227,
+      "learning_rate": 7.129640564631863e-07,
+      "loss": 0.7634,
+      "step": 285
+    },
+    {
+      "epoch": 1.1218568665377175,
+      "grad_norm": 4.192820471653476,
+      "learning_rate": 7.036187261857288e-07,
+      "loss": 0.7502,
+      "step": 290
+    },
+    {
+      "epoch": 1.1411992263056092,
+      "grad_norm": 3.6982147551712887,
+      "learning_rate": 6.941873251846293e-07,
+      "loss": 0.7737,
+      "step": 295
+    },
+    {
+      "epoch": 1.1605415860735009,
+      "grad_norm": 3.6871631539510807,
+      "learning_rate": 6.846738401634898e-07,
+      "loss": 0.7558,
+      "step": 300
+    },
+    {
+      "epoch": 1.1605415860735009,
+      "eval_loss": 0.8122316598892212,
+      "eval_runtime": 127.708,
+      "eval_samples_per_second": 57.553,
+      "eval_steps_per_second": 0.9,
+      "step": 300
+    },
+    {
+      "epoch": 1.1798839458413926,
+      "grad_norm": 3.6376198365580934,
+      "learning_rate": 6.750822925232663e-07,
+      "loss": 0.7701,
+      "step": 305
+    },
+    {
+      "epoch": 1.1992263056092844,
+      "grad_norm": 3.5708682961272316,
+      "learning_rate": 6.654167366624008e-07,
+      "loss": 0.7641,
+      "step": 310
+    },
+    {
+      "epoch": 1.218568665377176,
+      "grad_norm": 3.71858745567317,
+      "learning_rate": 6.556812582630059e-07,
+      "loss": 0.7481,
+      "step": 315
+    },
+    {
+      "epoch": 1.2379110251450678,
+      "grad_norm": 3.3987189299432217,
+      "learning_rate": 6.458799725638248e-07,
+      "loss": 0.7494,
+      "step": 320
+    },
+    {
+      "epoch": 1.2572533849129595,
+      "grad_norm": 3.582889984477799,
+      "learning_rate": 6.36017022620698e-07,
+      "loss": 0.7291,
+      "step": 325
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 3.7598968173069776,
+      "learning_rate": 6.260965775552713e-07,
+      "loss": 0.7643,
+      "step": 330
+    },
+    {
+      "epoch": 1.2959381044487428,
+      "grad_norm": 3.489163050088922,
+      "learning_rate": 6.161228307926858e-07,
+      "loss": 0.7374,
+      "step": 335
+    },
+    {
+      "epoch": 1.3152804642166345,
+      "grad_norm": 3.75863899391321,
+      "learning_rate": 6.060999982889954e-07,
+      "loss": 0.7568,
+      "step": 340
+    },
+    {
+      "epoch": 1.3346228239845261,
+      "grad_norm": 3.3559127612246233,
+      "learning_rate": 5.960323167490588e-07,
+      "loss": 0.7453,
+      "step": 345
+    },
+    {
+      "epoch": 1.3539651837524178,
+      "grad_norm": 3.490356836359392,
+      "learning_rate": 5.859240418356614e-07,
+      "loss": 0.7602,
+      "step": 350
+    },
+    {
+      "epoch": 1.3539651837524178,
+      "eval_loss": 0.8059322834014893,
+      "eval_runtime": 127.7998,
+      "eval_samples_per_second": 57.512,
+      "eval_steps_per_second": 0.9,
+      "step": 350
+    },
+    {
+      "epoch": 1.3733075435203095,
+      "grad_norm": 3.6757853156395606,
+      "learning_rate": 5.757794463706253e-07,
+      "loss": 0.7523,
+      "step": 355
+    },
+    {
+      "epoch": 1.3926499032882012,
+      "grad_norm": 3.5063904211356385,
+      "learning_rate": 5.656028185286637e-07,
+      "loss": 0.7496,
+      "step": 360
+    },
+    {
+      "epoch": 1.4119922630560928,
+      "grad_norm": 3.4960857334989806,
+      "learning_rate": 5.553984600247463e-07,
+      "loss": 0.7647,
+      "step": 365
+    },
+    {
+      "epoch": 1.4313346228239845,
+      "grad_norm": 3.6440901222517152,
+      "learning_rate": 5.451706842957421e-07,
+      "loss": 0.718,
+      "step": 370
+    },
+    {
+      "epoch": 1.4506769825918762,
+      "grad_norm": 3.7711569042281576,
+      "learning_rate": 5.349238146771061e-07,
+      "loss": 0.7583,
+      "step": 375
+    },
+    {
+      "epoch": 1.4700193423597678,
+      "grad_norm": 3.4413207786627957,
+      "learning_rate": 5.246621825753827e-07,
+      "loss": 0.7435,
+      "step": 380
+    },
+    {
+      "epoch": 1.4893617021276595,
+      "grad_norm": 3.6324458377021265,
+      "learning_rate": 5.143901256372967e-07,
+      "loss": 0.7397,
+      "step": 385
+    },
+    {
+      "epoch": 1.5087040618955512,
+      "grad_norm": 3.5785578278016485,
+      "learning_rate": 5.041119859162068e-07,
+      "loss": 0.7295,
+      "step": 390
+    },
+    {
+      "epoch": 1.528046421663443,
+      "grad_norm": 3.5486429985289116,
+      "learning_rate": 4.938321080366968e-07,
+      "loss": 0.7484,
+      "step": 395
+    },
+    {
+      "epoch": 1.5473887814313345,
+      "grad_norm": 3.563717839228555,
+      "learning_rate": 4.835548373580792e-07,
+      "loss": 0.771,
+      "step": 400
+    },
+    {
+      "epoch": 1.5473887814313345,
+      "eval_loss": 0.7998485565185547,
+      "eval_runtime": 127.8334,
+      "eval_samples_per_second": 57.497,
+      "eval_steps_per_second": 0.9,
+      "step": 400
+    },
+    {
+      "epoch": 1.5667311411992264,
+      "grad_norm": 3.531231527366412,
+      "learning_rate": 4.73284518137589e-07,
+      "loss": 0.7472,
+      "step": 405
+    },
+    {
+      "epoch": 1.5860735009671179,
+      "grad_norm": 3.4703134540594354,
+      "learning_rate": 4.630254916940423e-07,
+      "loss": 0.7349,
+      "step": 410
+    },
+    {
+      "epoch": 1.6054158607350097,
+      "grad_norm": 3.571312117827743,
+      "learning_rate": 4.5278209457273825e-07,
+      "loss": 0.7539,
+      "step": 415
+    },
+    {
+      "epoch": 1.6247582205029012,
+      "grad_norm": 3.6699695284667304,
+      "learning_rate": 4.425586567123779e-07,
+      "loss": 0.7561,
+      "step": 420
+    },
+    {
+      "epoch": 1.644100580270793,
+      "grad_norm": 3.444249068608954,
+      "learning_rate": 4.3235949961477627e-07,
+      "loss": 0.7456,
+      "step": 425
+    },
+    {
+      "epoch": 1.6634429400386848,
+      "grad_norm": 3.42086843430337,
+      "learning_rate": 4.2218893451814e-07,
+      "loss": 0.7458,
+      "step": 430
+    },
+    {
+      "epoch": 1.6827852998065764,
+      "grad_norm": 3.3865347869200857,
+      "learning_rate": 4.120512605746842e-07,
+      "loss": 0.7394,
+      "step": 435
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 3.677592972618459,
+      "learning_rate": 4.019507630333577e-07,
+      "loss": 0.7365,
+      "step": 440
+    },
+    {
+      "epoch": 1.7214700193423598,
+      "grad_norm": 3.6136504230202435,
+      "learning_rate": 3.9189171142844553e-07,
+      "loss": 0.7559,
+      "step": 445
+    },
+    {
+      "epoch": 1.7408123791102514,
+      "grad_norm": 3.572140075959248,
+      "learning_rate": 3.8187835777481375e-07,
+      "loss": 0.753,
+      "step": 450
+    },
+    {
+      "epoch": 1.7408123791102514,
+      "eval_loss": 0.7954617738723755,
+      "eval_runtime": 127.7956,
+      "eval_samples_per_second": 57.514,
+      "eval_steps_per_second": 0.9,
+      "step": 450
+    },
+    {
+      "epoch": 1.760154738878143,
+      "grad_norm": 3.4557270180643984,
+      "learning_rate": 3.7191493477056086e-07,
+      "loss": 0.7416,
+      "step": 455
+    },
+    {
+      "epoch": 1.7794970986460348,
+      "grad_norm": 3.5454869396159294,
+      "learning_rate": 3.620056540078323e-07,
+      "loss": 0.7465,
+      "step": 460
+    },
+    {
+      "epoch": 1.7988394584139265,
+      "grad_norm": 3.5193296679089197,
+      "learning_rate": 3.5215470419255897e-07,
+      "loss": 0.7381,
+      "step": 465
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 3.6300180309499055,
+      "learning_rate": 3.423662493738687e-07,
+      "loss": 0.7393,
+      "step": 470
+    },
+    {
+      "epoch": 1.8375241779497098,
+      "grad_norm": 3.6128465808218673,
+      "learning_rate": 3.3264442718392014e-07,
+      "loss": 0.7361,
+      "step": 475
+    },
+    {
+      "epoch": 1.8568665377176017,
+      "grad_norm": 3.8823278499726266,
+      "learning_rate": 3.229933470889038e-07,
+      "loss": 0.743,
+      "step": 480
+    },
+    {
+      "epoch": 1.8762088974854931,
+      "grad_norm": 3.4195861313789444,
+      "learning_rate": 3.134170886519486e-07,
+      "loss": 0.722,
+      "step": 485
+    },
+    {
+      "epoch": 1.895551257253385,
+      "grad_norm": 3.6240796400929005,
+      "learning_rate": 3.039196998086687e-07,
+      "loss": 0.7292,
+      "step": 490
+    },
+    {
+      "epoch": 1.9148936170212765,
+      "grad_norm": 3.602124125688223,
+      "learning_rate": 2.9450519515607963e-07,
+      "loss": 0.7402,
+      "step": 495
+    },
+    {
+      "epoch": 1.9342359767891684,
+      "grad_norm": 3.8410929027045757,
+      "learning_rate": 2.8517755425560663e-07,
+      "loss": 0.7479,
+      "step": 500
+    },
+    {
+      "epoch": 1.9342359767891684,
+      "eval_loss": 0.7919633984565735,
+      "eval_runtime": 127.71,
+      "eval_samples_per_second": 57.552,
+      "eval_steps_per_second": 0.9,
+      "step": 500
+    },
+    {
+      "epoch": 1.9535783365570598,
+      "grad_norm": 3.553013732530746,
+      "learning_rate": 2.7594071995090283e-07,
+      "loss": 0.7414,
+      "step": 505
+    },
+    {
+      "epoch": 1.9729206963249517,
+      "grad_norm": 3.726389314193614,
+      "learning_rate": 2.667985967011878e-07,
+      "loss": 0.7442,
+      "step": 510
+    },
+    {
+      "epoch": 1.9922630560928434,
+      "grad_norm": 3.6891205891519196,
+      "learning_rate": 2.577550489308123e-07,
+      "loss": 0.7445,
+      "step": 515
+    },
+    {
+      "epoch": 2.011605415860735,
+      "grad_norm": 4.183763879873082,
+      "learning_rate": 2.488138993957452e-07,
+      "loss": 0.7238,
+      "step": 520
+    },
+    {
+      "epoch": 2.0309477756286265,
+      "grad_norm": 3.5335122665404533,
+      "learning_rate": 2.3997892756767394e-07,
+      "loss": 0.7148,
+      "step": 525
+    },
+    {
+      "epoch": 2.0502901353965184,
+      "grad_norm": 3.877744660356318,
+      "learning_rate": 2.3125386803640183e-07,
+      "loss": 0.6955,
+      "step": 530
+    },
+    {
+      "epoch": 2.0696324951644103,
+      "grad_norm": 3.7193372520055847,
+      "learning_rate": 2.226424089312174e-07,
+      "loss": 0.7016,
+      "step": 535
+    },
+    {
+      "epoch": 2.0889748549323017,
+      "grad_norm": 3.6986475178104063,
+      "learning_rate": 2.1414819036190157e-07,
+      "loss": 0.7054,
+      "step": 540
+    },
+    {
+      "epoch": 2.1083172147001936,
+      "grad_norm": 3.7985188083265258,
+      "learning_rate": 2.057748028800344e-07,
+      "loss": 0.6801,
+      "step": 545
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 3.812215835510966,
+      "learning_rate": 1.9752578596124952e-07,
+      "loss": 0.6735,
+      "step": 550
+    },
+    {
+      "epoch": 2.127659574468085,
+      "eval_loss": 0.7972328066825867,
+      "eval_runtime": 127.877,
+      "eval_samples_per_second": 57.477,
+      "eval_steps_per_second": 0.899,
+      "step": 550
+    },
+    {
+      "epoch": 2.147001934235977,
+      "grad_norm": 3.556112328434251,
+      "learning_rate": 1.8940462650907912e-07,
+      "loss": 0.6887,
+      "step": 555
+    },
+    {
+      "epoch": 2.1663442940038684,
+      "grad_norm": 4.031706169414501,
+      "learning_rate": 1.8141475738102086e-07,
+      "loss": 0.6829,
+      "step": 560
+    },
+    {
+      "epoch": 2.1856866537717603,
+      "grad_norm": 3.9038438081899636,
+      "learning_rate": 1.735595559374508e-07,
+      "loss": 0.701,
+      "step": 565
+    },
+    {
+      "epoch": 2.2050290135396517,
+      "grad_norm": 3.802389298862028,
+      "learning_rate": 1.6584234261399532e-07,
+      "loss": 0.6962,
+      "step": 570
+    },
+    {
+      "epoch": 2.2243713733075436,
+      "grad_norm": 3.95265234731058,
+      "learning_rate": 1.5826637951796474e-07,
+      "loss": 0.704,
+      "step": 575
+    },
+    {
+      "epoch": 2.243713733075435,
+      "grad_norm": 3.920278049666238,
+      "learning_rate": 1.5083486904944387e-07,
+      "loss": 0.6866,
+      "step": 580
+    },
+    {
+      "epoch": 2.263056092843327,
+      "grad_norm": 3.917007172675932,
+      "learning_rate": 1.4355095254761974e-07,
+      "loss": 0.6921,
+      "step": 585
+    },
+    {
+      "epoch": 2.2823984526112184,
+      "grad_norm": 3.7991457510336915,
+      "learning_rate": 1.3641770896292082e-07,
+      "loss": 0.6813,
+      "step": 590
+    },
+    {
+      "epoch": 2.3017408123791103,
+      "grad_norm": 3.687358486996167,
+      "learning_rate": 1.2943815355552851e-07,
+      "loss": 0.6928,
+      "step": 595
+    },
+    {
+      "epoch": 2.3210831721470018,
+      "grad_norm": 3.6543009032276026,
+      "learning_rate": 1.226152366208104e-07,
+      "loss": 0.7116,
+      "step": 600
+    },
+    {
+      "epoch": 2.3210831721470018,
+      "eval_loss": 0.7951865196228027,
+      "eval_runtime": 127.85,
+      "eval_samples_per_second": 57.489,
+      "eval_steps_per_second": 0.899,
+      "step": 600
+    },
+    {
+      "epoch": 2.3404255319148937,
+      "grad_norm": 3.8730917233152384,
+      "learning_rate": 1.1595184224221466e-07,
+      "loss": 0.692,
+      "step": 605
+    },
+    {
+      "epoch": 2.359767891682785,
+      "grad_norm": 4.03531309851571,
+      "learning_rate": 1.0945078707215221e-07,
+      "loss": 0.6865,
+      "step": 610
+    },
+    {
+      "epoch": 2.379110251450677,
+      "grad_norm": 3.872705003238953,
+      "learning_rate": 1.0311481914138371e-07,
+      "loss": 0.6985,
+      "step": 615
+    },
+    {
+      "epoch": 2.398452611218569,
+      "grad_norm": 3.720403831965154,
+      "learning_rate": 9.6946616697411e-08,
+      "loss": 0.6968,
+      "step": 620
+    },
+    {
+      "epoch": 2.4177949709864603,
+      "grad_norm": 3.8402045858860214,
+      "learning_rate": 9.094878707236841e-08,
+      "loss": 0.7002,
+      "step": 625
+    },
+    {
+      "epoch": 2.437137330754352,
+      "grad_norm": 3.870172963176105,
+      "learning_rate": 8.512386558088919e-08,
+      "loss": 0.7018,
+      "step": 630
+    },
+    {
+      "epoch": 2.4564796905222437,
+      "grad_norm": 3.844232920183782,
+      "learning_rate": 7.947431444841452e-08,
+      "loss": 0.6953,
+      "step": 635
+    },
+    {
+      "epoch": 2.4758220502901356,
+      "grad_norm": 3.9369438805219357,
+      "learning_rate": 7.400252177039784e-08,
+      "loss": 0.7023,
+      "step": 640
+    },
+    {
+      "epoch": 2.495164410058027,
+      "grad_norm": 3.7400884688082217,
+      "learning_rate": 6.871080050284394e-08,
+      "loss": 0.6822,
+      "step": 645
+    },
+    {
+      "epoch": 2.514506769825919,
+      "grad_norm": 3.6809188260562498,
+      "learning_rate": 6.360138748461013e-08,
+      "loss": 0.6822,
+      "step": 650
+    },
+    {
+      "epoch": 2.514506769825919,
+      "eval_loss": 0.794310986995697,
+      "eval_runtime": 128.0518,
+      "eval_samples_per_second": 57.399,
+      "eval_steps_per_second": 0.898,
+      "step": 650
+    },
+    {
+      "epoch": 2.5338491295938104,
+      "grad_norm": 4.16744242512269,
+      "learning_rate": 5.867644249188247e-08,
+      "loss": 0.6991,
+      "step": 655
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "grad_norm": 3.851977029205454,
+      "learning_rate": 5.3938047325226944e-08,
+      "loss": 0.6986,
+      "step": 660
+    },
+    {
+      "epoch": 2.5725338491295937,
+      "grad_norm": 4.101916973231146,
+      "learning_rate": 4.9388204929601326e-08,
+      "loss": 0.6854,
+      "step": 665
+    },
+    {
+      "epoch": 2.5918762088974856,
+      "grad_norm": 3.8486651679301023,
+      "learning_rate": 4.5028838547699346e-08,
+      "loss": 0.6924,
+      "step": 670
+    },
+    {
+      "epoch": 2.611218568665377,
+      "grad_norm": 3.717552659671349,
+      "learning_rate": 4.0861790906985884e-08,
+      "loss": 0.6888,
+      "step": 675
+    },
+    {
+      "epoch": 2.630560928433269,
+      "grad_norm": 3.9259495383255314,
+      "learning_rate": 3.6888823440766214e-08,
+      "loss": 0.6914,
+      "step": 680
+    },
+    {
+      "epoch": 2.6499032882011604,
+      "grad_norm": 3.627999141521453,
+      "learning_rate": 3.311161554361874e-08,
+      "loss": 0.6773,
+      "step": 685
+    },
+    {
+      "epoch": 2.6692456479690523,
+      "grad_norm": 3.9122944066082934,
+      "learning_rate": 2.9531763861505964e-08,
+      "loss": 0.6908,
+      "step": 690
+    },
+    {
+      "epoch": 2.6885880077369437,
+      "grad_norm": 3.7957015499021547,
+      "learning_rate": 2.6150781616863794e-08,
+      "loss": 0.6638,
+      "step": 695
+    },
+    {
+      "epoch": 2.7079303675048356,
+      "grad_norm": 3.9116633525167033,
+      "learning_rate": 2.2970097968953994e-08,
+      "loss": 0.6861,
+      "step": 700
+    },
+    {
+      "epoch": 2.7079303675048356,
+      "eval_loss": 0.7937687635421753,
+      "eval_runtime": 127.6414,
+      "eval_samples_per_second": 57.583,
+      "eval_steps_per_second": 0.901,
+      "step": 700
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 3.7729712553297987,
+      "learning_rate": 1.9991057409751267e-08,
+      "loss": 0.6911,
+      "step": 705
+    },
+    {
+      "epoch": 2.746615087040619,
+      "grad_norm": 3.834540719290449,
+      "learning_rate": 1.7214919195619125e-08,
+      "loss": 0.6909,
+      "step": 710
+    },
+    {
+      "epoch": 2.7659574468085104,
+      "grad_norm": 3.7151903198724,
+      "learning_rate": 1.4642856815015758e-08,
+      "loss": 0.6999,
+      "step": 715
+    },
+    {
+      "epoch": 2.7852998065764023,
+      "grad_norm": 3.973205161583112,
+      "learning_rate": 1.2275957492453692e-08,
+      "loss": 0.6933,
+      "step": 720
+    },
+    {
+      "epoch": 2.804642166344294,
+      "grad_norm": 3.8696685699188507,
+      "learning_rate": 1.0115221728924706e-08,
+      "loss": 0.6775,
+      "step": 725
+    },
+    {
+      "epoch": 2.8239845261121856,
+      "grad_norm": 4.076911148311998,
+      "learning_rate": 8.161562878982398e-09,
+      "loss": 0.6748,
+      "step": 730
+    },
+    {
+      "epoch": 2.843326885880077,
+      "grad_norm": 3.6416916556998817,
+      "learning_rate": 6.415806764662524e-09,
+      "loss": 0.6759,
+      "step": 735
+    },
+    {
+      "epoch": 2.862669245647969,
+      "grad_norm": 3.9225986402250754,
+      "learning_rate": 4.8786913264033945e-09,
+      "loss": 0.698,
+      "step": 740
+    },
+    {
+      "epoch": 2.882011605415861,
+      "grad_norm": 4.048565845552162,
+      "learning_rate": 3.5508663111147306e-09,
+      "loss": 0.6856,
+      "step": 745
+    },
+    {
+      "epoch": 2.9013539651837523,
+      "grad_norm": 4.082712170990346,
+      "learning_rate": 2.432892997526026e-09,
+      "loss": 0.6989,
+      "step": 750
+    },
+    {
+      "epoch": 2.9013539651837523,
+      "eval_loss": 0.7935436367988586,
+      "eval_runtime": 127.7461,
+      "eval_samples_per_second": 57.536,
+      "eval_steps_per_second": 0.9,
+      "step": 750
+    },
+    {
+      "epoch": 2.920696324951644,
+      "grad_norm": 3.8537422532400827,
+      "learning_rate": 1.5252439589311107e-09,
+      "loss": 0.6929,
+      "step": 755
+    },
+    {
+      "epoch": 2.9400386847195357,
+      "grad_norm": 3.841072555465488,
+      "learning_rate": 8.283028634287203e-10,
+      "loss": 0.6963,
+      "step": 760
+    },
+    {
+      "epoch": 2.9593810444874276,
+      "grad_norm": 3.741338861355809,
+      "learning_rate": 3.4236431174428094e-10,
+      "loss": 0.683,
+      "step": 765
+    },
+    {
+      "epoch": 2.978723404255319,
+      "grad_norm": 3.962628716770498,
+      "learning_rate": 6.763371270035457e-11,
+      "loss": 0.684,
+      "step": 770
+    },
+    {
+      "epoch": 2.9941972920696323,
+      "step": 774,
+      "total_flos": 4563620855808000.0,
+      "train_loss": 0.7856120132968716,
+      "train_runtime": 12058.8177,
+      "train_samples_per_second": 16.457,
+      "train_steps_per_second": 0.064
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 774,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4563620855808000.0,
+  "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:d576bcd0fc26b233c9c53ca1b8a57d338c3659c66dd4edeca42bd34ec9701fdc
+size 7096