Upload folder using huggingface_hub

README.md

@@ -0,0 +1,76 @@
+---
+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_cosi_0_50
+  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_cosi_0_50
+
+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_cosi_0_50 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8178
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9375        | 0.2706 | 50   | 0.9355          |
+| 0.8824        | 0.5413 | 100  | 0.8776          |
+| 0.8549        | 0.8119 | 150  | 0.8518          |
+| 0.7825        | 1.0825 | 200  | 0.8398          |
+| 0.759         | 1.3532 | 250  | 0.8301          |
+| 0.7676        | 1.6238 | 300  | 0.8219          |
+| 0.7624        | 1.8945 | 350  | 0.8160          |
+| 0.6976        | 2.1651 | 400  | 0.8193          |
+| 0.7004        | 2.4357 | 450  | 0.8186          |
+| 0.7133        | 2.7064 | 500  | 0.8176          |
+| 0.7           | 2.9770 | 550  | 0.8178          |
+
+
+### 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": 2.9878213802435725,
+    "eval_loss": 0.8177559971809387,
+    "eval_runtime": 91.3088,
+    "eval_samples_per_second": 57.497,
+    "eval_steps_per_second": 0.909,
+    "total_flos": 3254608239525888.0,
+    "train_loss": 0.8081599063631417,
+    "train_runtime": 8273.4491,
+    "train_samples_per_second": 17.133,
+    "train_steps_per_second": 0.067
+}

config.json

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

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9878213802435725,
+    "eval_loss": 0.8177559971809387,
+    "eval_runtime": 91.3088,
+    "eval_samples_per_second": 57.497,
+    "eval_steps_per_second": 0.909
+}

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 sha256:297be20096ce4b072f46c72c1d4831b33561fc9392519064cbd289808106d3b2
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812206dbe5df9c5349838e10ac64833246601b7b04dd936a7e24b5eefc8eedb8
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b64b4fe6144f28b65aa236a12cabb774877e44b9360265ab4342a4a58684698
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee3cb31c9bc975b5264ae2cb3461ff919fea8ae2a32c69090f026e4642aa2d9
+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": 2.9878213802435725,
+    "total_flos": 3254608239525888.0,
+    "train_loss": 0.8081599063631417,
+    "train_runtime": 8273.4491,
+    "train_samples_per_second": 17.133,
+    "train_steps_per_second": 0.067
+}

trainer_log.jsonl

@@ -0,0 +1,122 @@
+{"current_steps": 5, "total_steps": 552, "loss": 1.7202, "learning_rate": 5e-07, "epoch": 0.02706359945872801, "percentage": 0.91, "elapsed_time": "0:01:10", "remaining_time": "2:07:38"}
+{"current_steps": 10, "total_steps": 552, "loss": 1.5858, "learning_rate": 1e-06, "epoch": 0.05412719891745602, "percentage": 1.81, "elapsed_time": "0:02:16", "remaining_time": "2:02:53"}
+{"current_steps": 15, "total_steps": 552, "loss": 1.2962, "learning_rate": 9.997900331216397e-07, "epoch": 0.08119079837618404, "percentage": 2.72, "elapsed_time": "0:03:21", "remaining_time": "2:00:18"}
+{"current_steps": 20, "total_steps": 552, "loss": 1.1481, "learning_rate": 9.991603088309193e-07, "epoch": 0.10825439783491204, "percentage": 3.62, "elapsed_time": "0:04:27", "remaining_time": "1:58:38"}
+{"current_steps": 25, "total_steps": 552, "loss": 1.0683, "learning_rate": 9.981113560128126e-07, "epoch": 0.13531799729364005, "percentage": 4.53, "elapsed_time": "0:05:32", "remaining_time": "1:56:53"}
+{"current_steps": 30, "total_steps": 552, "loss": 1.0347, "learning_rate": 9.966440556487147e-07, "epoch": 0.16238159675236807, "percentage": 5.43, "elapsed_time": "0:06:37", "remaining_time": "1:55:24"}
+{"current_steps": 35, "total_steps": 552, "loss": 0.9829, "learning_rate": 9.947596400765342e-07, "epoch": 0.18944519621109607, "percentage": 6.34, "elapsed_time": "0:07:43", "remaining_time": "1:54:09"}
+{"current_steps": 40, "total_steps": 552, "loss": 0.9751, "learning_rate": 9.924596919556916e-07, "epoch": 0.2165087956698241, "percentage": 7.25, "elapsed_time": "0:08:49", "remaining_time": "1:52:51"}
+{"current_steps": 45, "total_steps": 552, "loss": 0.9534, "learning_rate": 9.897461429378964e-07, "epoch": 0.2435723951285521, "percentage": 8.15, "elapsed_time": "0:09:54", "remaining_time": "1:51:34"}
+{"current_steps": 50, "total_steps": 552, "loss": 0.9375, "learning_rate": 9.866212720448147e-07, "epoch": 0.2706359945872801, "percentage": 9.06, "elapsed_time": "0:10:59", "remaining_time": "1:50:19"}
+{"current_steps": 50, "total_steps": 552, "eval_loss": 0.9354712963104248, "epoch": 0.2706359945872801, "percentage": 9.06, "elapsed_time": "0:12:31", "remaining_time": "2:05:43"}
+{"current_steps": 55, "total_steps": 552, "loss": 0.9241, "learning_rate": 9.830877037539935e-07, "epoch": 0.2976995940460081, "percentage": 9.96, "elapsed_time": "0:13:36", "remaining_time": "2:03:00"}
+{"current_steps": 60, "total_steps": 552, "loss": 0.9301, "learning_rate": 9.791484057946465e-07, "epoch": 0.32476319350473615, "percentage": 10.87, "elapsed_time": "0:14:42", "remaining_time": "2:00:39"}
+{"current_steps": 65, "total_steps": 552, "loss": 0.9141, "learning_rate": 9.748066866551555e-07, "epoch": 0.35182679296346414, "percentage": 11.78, "elapsed_time": "0:15:48", "remaining_time": "1:58:28"}
+{"current_steps": 70, "total_steps": 552, "loss": 0.9099, "learning_rate": 9.700661928043785e-07, "epoch": 0.37889039242219213, "percentage": 12.68, "elapsed_time": "0:16:54", "remaining_time": "1:56:25"}
+{"current_steps": 75, "total_steps": 552, "loss": 0.9034, "learning_rate": 9.649309056290984e-07, "epoch": 0.4059539918809202, "percentage": 13.59, "elapsed_time": "0:17:59", "remaining_time": "1:54:26"}
+{"current_steps": 80, "total_steps": 552, "loss": 0.8755, "learning_rate": 9.594051380901858e-07, "epoch": 0.4330175913396482, "percentage": 14.49, "elapsed_time": "0:19:04", "remaining_time": "1:52:35"}
+{"current_steps": 85, "total_steps": 552, "loss": 0.887, "learning_rate": 9.534935311002834e-07, "epoch": 0.46008119079837617, "percentage": 15.4, "elapsed_time": "0:20:10", "remaining_time": "1:50:48"}
+{"current_steps": 90, "total_steps": 552, "loss": 0.8868, "learning_rate": 9.472010496260544e-07, "epoch": 0.4871447902571042, "percentage": 16.3, "elapsed_time": "0:21:15", "remaining_time": "1:49:09"}
+{"current_steps": 95, "total_steps": 552, "loss": 0.8685, "learning_rate": 9.405329785182678e-07, "epoch": 0.5142083897158322, "percentage": 17.21, "elapsed_time": "0:22:20", "remaining_time": "1:47:28"}
+{"current_steps": 100, "total_steps": 552, "loss": 0.8824, "learning_rate": 9.334949180732244e-07, "epoch": 0.5412719891745602, "percentage": 18.12, "elapsed_time": "0:23:25", "remaining_time": "1:45:54"}
+{"current_steps": 100, "total_steps": 552, "eval_loss": 0.8775722980499268, "epoch": 0.5412719891745602, "percentage": 18.12, "elapsed_time": "0:24:57", "remaining_time": "1:52:49"}
+{"current_steps": 105, "total_steps": 552, "loss": 0.8847, "learning_rate": 9.260927793292497e-07, "epoch": 0.5683355886332883, "percentage": 19.02, "elapsed_time": "0:26:03", "remaining_time": "1:50:54"}
+{"current_steps": 110, "total_steps": 552, "loss": 0.8716, "learning_rate": 9.183327791022047e-07, "epoch": 0.5953991880920162, "percentage": 19.93, "elapsed_time": "0:27:08", "remaining_time": "1:49:01"}
+{"current_steps": 115, "total_steps": 552, "loss": 0.879, "learning_rate": 9.102214347641843e-07, "epoch": 0.6224627875507442, "percentage": 20.83, "elapsed_time": "0:28:13", "remaining_time": "1:47:14"}
+{"current_steps": 120, "total_steps": 552, "loss": 0.849, "learning_rate": 9.017655587697883e-07, "epoch": 0.6495263870094723, "percentage": 21.74, "elapsed_time": "0:29:19", "remaining_time": "1:45:34"}
+{"current_steps": 125, "total_steps": 552, "loss": 0.8623, "learning_rate": 8.929722529345623e-07, "epoch": 0.6765899864682002, "percentage": 22.64, "elapsed_time": "0:30:24", "remaining_time": "1:43:51"}
+{"current_steps": 130, "total_steps": 552, "loss": 0.8821, "learning_rate": 8.83848902470413e-07, "epoch": 0.7036535859269283, "percentage": 23.55, "elapsed_time": "0:31:30", "remaining_time": "1:42:15"}
+{"current_steps": 135, "total_steps": 552, "loss": 0.864, "learning_rate": 8.744031697830088e-07, "epoch": 0.7307171853856563, "percentage": 24.46, "elapsed_time": "0:32:35", "remaining_time": "1:40:40"}
+{"current_steps": 140, "total_steps": 552, "loss": 0.8469, "learning_rate": 8.646429880363746e-07, "epoch": 0.7577807848443843, "percentage": 25.36, "elapsed_time": "0:33:40", "remaining_time": "1:39:07"}
+{"current_steps": 145, "total_steps": 552, "loss": 0.8488, "learning_rate": 8.545765544900846e-07, "epoch": 0.7848443843031123, "percentage": 26.27, "elapsed_time": "0:34:46", "remaining_time": "1:37:36"}
+{"current_steps": 150, "total_steps": 552, "loss": 0.8549, "learning_rate": 8.442123236146508e-07, "epoch": 0.8119079837618404, "percentage": 27.17, "elapsed_time": "0:35:51", "remaining_time": "1:36:06"}
+{"current_steps": 150, "total_steps": 552, "eval_loss": 0.8518306612968445, "epoch": 0.8119079837618404, "percentage": 27.17, "elapsed_time": "0:37:23", "remaining_time": "1:40:12"}
+{"current_steps": 155, "total_steps": 552, "loss": 0.846, "learning_rate": 8.33558999990887e-07, "epoch": 0.8389715832205683, "percentage": 28.08, "elapsed_time": "0:38:28", "remaining_time": "1:38:33"}
+{"current_steps": 160, "total_steps": 552, "loss": 0.8485, "learning_rate": 8.22625530999215e-07, "epoch": 0.8660351826792964, "percentage": 28.99, "elapsed_time": "0:39:34", "remaining_time": "1:36:57"}
+{"current_steps": 165, "total_steps": 552, "loss": 0.86, "learning_rate": 8.114210993050502e-07, "epoch": 0.8930987821380244, "percentage": 29.89, "elapsed_time": "0:40:39", "remaining_time": "1:35:20"}
+{"current_steps": 170, "total_steps": 552, "loss": 0.8445, "learning_rate": 7.999551151465791e-07, "epoch": 0.9201623815967523, "percentage": 30.8, "elapsed_time": "0:41:43", "remaining_time": "1:33:46"}
+{"current_steps": 175, "total_steps": 552, "loss": 0.8366, "learning_rate": 7.88237208431406e-07, "epoch": 0.9472259810554804, "percentage": 31.7, "elapsed_time": "0:42:49", "remaining_time": "1:32:15"}
+{"current_steps": 180, "total_steps": 552, "loss": 0.8377, "learning_rate": 7.762772206487065e-07, "epoch": 0.9742895805142084, "percentage": 32.61, "elapsed_time": "0:43:55", "remaining_time": "1:30:46"}
+{"current_steps": 185, "total_steps": 552, "loss": 0.8402, "learning_rate": 7.640851966036805e-07, "epoch": 1.0013531799729365, "percentage": 33.51, "elapsed_time": "0:45:00", "remaining_time": "1:29:18"}
+{"current_steps": 190, "total_steps": 552, "loss": 0.7742, "learning_rate": 7.516713759812464e-07, "epoch": 1.0284167794316643, "percentage": 34.42, "elapsed_time": "0:46:06", "remaining_time": "1:27:51"}
+{"current_steps": 195, "total_steps": 552, "loss": 0.7723, "learning_rate": 7.390461847460628e-07, "epoch": 1.0554803788903924, "percentage": 35.33, "elapsed_time": "0:47:12", "remaining_time": "1:26:25"}
+{"current_steps": 200, "total_steps": 552, "loss": 0.7825, "learning_rate": 7.262202263860988e-07, "epoch": 1.0825439783491204, "percentage": 36.23, "elapsed_time": "0:48:17", "remaining_time": "1:24:59"}
+{"current_steps": 200, "total_steps": 552, "eval_loss": 0.8397604823112488, "epoch": 1.0825439783491204, "percentage": 36.23, "elapsed_time": "0:49:49", "remaining_time": "1:27:40"}
+{"current_steps": 205, "total_steps": 552, "loss": 0.7622, "learning_rate": 7.1320427300711e-07, "epoch": 1.1096075778078485, "percentage": 37.14, "elapsed_time": "0:50:54", "remaining_time": "1:26:11"}
+{"current_steps": 210, "total_steps": 552, "loss": 0.7683, "learning_rate": 7.000092562854959e-07, "epoch": 1.1366711772665765, "percentage": 38.04, "elapsed_time": "0:52:01", "remaining_time": "1:24:43"}
+{"current_steps": 215, "total_steps": 552, "loss": 0.7536, "learning_rate": 6.866462582871401e-07, "epoch": 1.1637347767253043, "percentage": 38.95, "elapsed_time": "0:53:07", "remaining_time": "1:23:16"}
+{"current_steps": 220, "total_steps": 552, "loss": 0.775, "learning_rate": 6.731265021599436e-07, "epoch": 1.1907983761840324, "percentage": 39.86, "elapsed_time": "0:54:12", "remaining_time": "1:21:48"}
+{"current_steps": 225, "total_steps": 552, "loss": 0.7736, "learning_rate": 6.594613427078674e-07, "epoch": 1.2178619756427604, "percentage": 40.76, "elapsed_time": "0:55:18", "remaining_time": "1:20:22"}
+{"current_steps": 230, "total_steps": 552, "loss": 0.7723, "learning_rate": 6.456622568544011e-07, "epoch": 1.2449255751014885, "percentage": 41.67, "elapsed_time": "0:56:23", "remaining_time": "1:18:56"}
+{"current_steps": 235, "total_steps": 552, "loss": 0.7675, "learning_rate": 6.317408340034684e-07, "epoch": 1.2719891745602165, "percentage": 42.57, "elapsed_time": "0:57:27", "remaining_time": "1:17:31"}
+{"current_steps": 240, "total_steps": 552, "loss": 0.786, "learning_rate": 6.177087663058625e-07, "epoch": 1.2990527740189446, "percentage": 43.48, "elapsed_time": "0:58:32", "remaining_time": "1:16:05"}
+{"current_steps": 245, "total_steps": 552, "loss": 0.7569, "learning_rate": 6.035778388393893e-07, "epoch": 1.3261163734776726, "percentage": 44.38, "elapsed_time": "0:59:37", "remaining_time": "1:14:43"}
+{"current_steps": 250, "total_steps": 552, "loss": 0.759, "learning_rate": 5.893599197109624e-07, "epoch": 1.3531799729364005, "percentage": 45.29, "elapsed_time": "1:00:43", "remaining_time": "1:13:21"}
+{"current_steps": 250, "total_steps": 552, "eval_loss": 0.8301268219947815, "epoch": 1.3531799729364005, "percentage": 45.29, "elapsed_time": "1:02:15", "remaining_time": "1:15:12"}
+{"current_steps": 255, "total_steps": 552, "loss": 0.7549, "learning_rate": 5.750669500889666e-07, "epoch": 1.3802435723951285, "percentage": 46.2, "elapsed_time": "1:03:20", "remaining_time": "1:13:45"}
+{"current_steps": 260, "total_steps": 552, "loss": 0.7801, "learning_rate": 5.607109341742578e-07, "epoch": 1.4073071718538566, "percentage": 47.1, "elapsed_time": "1:04:25", "remaining_time": "1:12:21"}
+{"current_steps": 265, "total_steps": 552, "loss": 0.7765, "learning_rate": 5.463039291182256e-07, "epoch": 1.4343707713125846, "percentage": 48.01, "elapsed_time": "1:05:30", "remaining_time": "1:10:57"}
+{"current_steps": 270, "total_steps": 552, "loss": 0.7662, "learning_rate": 5.318580348963825e-07, "epoch": 1.4614343707713127, "percentage": 48.91, "elapsed_time": "1:06:36", "remaining_time": "1:09:33"}
+{"current_steps": 275, "total_steps": 552, "loss": 0.7554, "learning_rate": 5.173853841459877e-07, "epoch": 1.4884979702300405, "percentage": 49.82, "elapsed_time": "1:07:41", "remaining_time": "1:08:11"}
+{"current_steps": 280, "total_steps": 552, "loss": 0.7616, "learning_rate": 5.028981319762399e-07, "epoch": 1.5155615696887685, "percentage": 50.72, "elapsed_time": "1:08:47", "remaining_time": "1:06:49"}
+{"current_steps": 285, "total_steps": 552, "loss": 0.7818, "learning_rate": 4.884084457595956e-07, "epoch": 1.5426251691474966, "percentage": 51.63, "elapsed_time": "1:09:53", "remaining_time": "1:05:28"}
+{"current_steps": 290, "total_steps": 552, "loss": 0.7691, "learning_rate": 4.7392849491278817e-07, "epoch": 1.5696887686062246, "percentage": 52.54, "elapsed_time": "1:10:58", "remaining_time": "1:04:07"}
+{"current_steps": 295, "total_steps": 552, "loss": 0.7681, "learning_rate": 4.5947044067613e-07, "epoch": 1.5967523680649527, "percentage": 53.44, "elapsed_time": "1:12:04", "remaining_time": "1:02:47"}
+{"current_steps": 300, "total_steps": 552, "loss": 0.7676, "learning_rate": 4.4504642589968217e-07, "epoch": 1.6238159675236807, "percentage": 54.35, "elapsed_time": "1:13:10", "remaining_time": "1:01:28"}
+{"current_steps": 300, "total_steps": 552, "eval_loss": 0.8219158053398132, "epoch": 1.6238159675236807, "percentage": 54.35, "elapsed_time": "1:14:42", "remaining_time": "1:02:45"}
+{"current_steps": 305, "total_steps": 552, "loss": 0.7602, "learning_rate": 4.3066856484486847e-07, "epoch": 1.6508795669824088, "percentage": 55.25, "elapsed_time": "1:15:47", "remaining_time": "1:01:23"}
+{"current_steps": 310, "total_steps": 552, "loss": 0.7589, "learning_rate": 4.1634893301010165e-07, "epoch": 1.6779431664411368, "percentage": 56.16, "elapsed_time": "1:16:53", "remaining_time": "1:00:01"}
+{"current_steps": 315, "total_steps": 552, "loss": 0.7475, "learning_rate": 4.0209955698896445e-07, "epoch": 1.7050067658998647, "percentage": 57.07, "elapsed_time": "1:17:59", "remaining_time": "0:58:40"}
+{"current_steps": 320, "total_steps": 552, "loss": 0.7548, "learning_rate": 3.8793240436946385e-07, "epoch": 1.7320703653585927, "percentage": 57.97, "elapsed_time": "1:19:04", "remaining_time": "0:57:19"}
+{"current_steps": 325, "total_steps": 552, "loss": 0.761, "learning_rate": 3.738593736828426e-07, "epoch": 1.7591339648173205, "percentage": 58.88, "elapsed_time": "1:20:09", "remaining_time": "0:55:59"}
+{"current_steps": 330, "total_steps": 552, "loss": 0.7704, "learning_rate": 3.598922844103902e-07, "epoch": 1.7861975642760486, "percentage": 59.78, "elapsed_time": "1:21:14", "remaining_time": "0:54:39"}
+{"current_steps": 335, "total_steps": 552, "loss": 0.7578, "learning_rate": 3.4604286705664397e-07, "epoch": 1.8132611637347766, "percentage": 60.69, "elapsed_time": "1:22:20", "remaining_time": "0:53:20"}
+{"current_steps": 340, "total_steps": 552, "loss": 0.7548, "learning_rate": 3.323227532973193e-07, "epoch": 1.8403247631935047, "percentage": 61.59, "elapsed_time": "1:23:25", "remaining_time": "0:52:01"}
+{"current_steps": 345, "total_steps": 552, "loss": 0.7624, "learning_rate": 3.187434662102434e-07, "epoch": 1.8673883626522327, "percentage": 62.5, "elapsed_time": "1:24:30", "remaining_time": "0:50:42"}
+{"current_steps": 350, "total_steps": 552, "loss": 0.7624, "learning_rate": 3.0531641059749634e-07, "epoch": 1.8944519621109608, "percentage": 63.41, "elapsed_time": "1:25:36", "remaining_time": "0:49:24"}
+{"current_steps": 350, "total_steps": 552, "eval_loss": 0.81601482629776, "epoch": 1.8944519621109608, "percentage": 63.41, "elapsed_time": "1:27:07", "remaining_time": "0:50:17"}
+{"current_steps": 355, "total_steps": 552, "loss": 0.7342, "learning_rate": 2.920528634068885e-07, "epoch": 1.9215155615696888, "percentage": 64.31, "elapsed_time": "1:28:12", "remaining_time": "0:48:57"}
+{"current_steps": 360, "total_steps": 552, "loss": 0.7552, "learning_rate": 2.789639642608184e-07, "epoch": 1.9485791610284169, "percentage": 65.22, "elapsed_time": "1:29:17", "remaining_time": "0:47:37"}
+{"current_steps": 365, "total_steps": 552, "loss": 0.7578, "learning_rate": 2.6606070610046526e-07, "epoch": 1.975642760487145, "percentage": 66.12, "elapsed_time": "1:30:22", "remaining_time": "0:46:18"}
+{"current_steps": 370, "total_steps": 552, "loss": 0.755, "learning_rate": 2.533539259531757e-07, "epoch": 2.002706359945873, "percentage": 67.03, "elapsed_time": "1:31:28", "remaining_time": "0:44:59"}
+{"current_steps": 375, "total_steps": 552, "loss": 0.6915, "learning_rate": 2.408542958307957e-07, "epoch": 2.029769959404601, "percentage": 67.93, "elapsed_time": "1:32:33", "remaining_time": "0:43:41"}
+{"current_steps": 380, "total_steps": 552, "loss": 0.7139, "learning_rate": 2.2857231376659514e-07, "epoch": 2.0568335588633286, "percentage": 68.84, "elapsed_time": "1:33:39", "remaining_time": "0:42:23"}
+{"current_steps": 385, "total_steps": 552, "loss": 0.7127, "learning_rate": 2.1651829499831043e-07, "epoch": 2.0838971583220567, "percentage": 69.75, "elapsed_time": "1:34:44", "remaining_time": "0:41:05"}
+{"current_steps": 390, "total_steps": 552, "loss": 0.7188, "learning_rate": 2.0470236330471126e-07, "epoch": 2.1109607577807847, "percentage": 70.65, "elapsed_time": "1:35:49", "remaining_time": "0:39:48"}
+{"current_steps": 395, "total_steps": 552, "loss": 0.7319, "learning_rate": 1.9313444250296846e-07, "epoch": 2.138024357239513, "percentage": 71.56, "elapsed_time": "1:36:55", "remaining_time": "0:38:31"}
+{"current_steps": 400, "total_steps": 552, "loss": 0.6976, "learning_rate": 1.818242481139613e-07, "epoch": 2.165087956698241, "percentage": 72.46, "elapsed_time": "1:38:01", "remaining_time": "0:37:14"}
+{"current_steps": 400, "total_steps": 552, "eval_loss": 0.8192901611328125, "epoch": 2.165087956698241, "percentage": 72.46, "elapsed_time": "1:39:33", "remaining_time": "0:37:49"}
+{"current_steps": 405, "total_steps": 552, "loss": 0.7018, "learning_rate": 1.7078127920252783e-07, "epoch": 2.192151556156969, "percentage": 73.37, "elapsed_time": "1:40:38", "remaining_time": "0:36:31"}
+{"current_steps": 410, "total_steps": 552, "loss": 0.7062, "learning_rate": 1.600148103995087e-07, "epoch": 2.219215155615697, "percentage": 74.28, "elapsed_time": "1:41:43", "remaining_time": "0:35:13"}
+{"current_steps": 415, "total_steps": 552, "loss": 0.714, "learning_rate": 1.4953388411228602e-07, "epoch": 2.246278755074425, "percentage": 75.18, "elapsed_time": "1:42:48", "remaining_time": "0:33:56"}
+{"current_steps": 420, "total_steps": 552, "loss": 0.7028, "learning_rate": 1.3934730293035936e-07, "epoch": 2.273342354533153, "percentage": 76.09, "elapsed_time": "1:43:53", "remaining_time": "0:32:39"}
+{"current_steps": 425, "total_steps": 552, "loss": 0.7023, "learning_rate": 1.2946362223233614e-07, "epoch": 2.300405953991881, "percentage": 76.99, "elapsed_time": "1:44:58", "remaining_time": "0:31:21"}
+{"current_steps": 430, "total_steps": 552, "loss": 0.7022, "learning_rate": 1.198911430005478e-07, "epoch": 2.3274695534506087, "percentage": 77.9, "elapsed_time": "1:46:02", "remaining_time": "0:30:05"}
+{"current_steps": 435, "total_steps": 552, "loss": 0.7083, "learning_rate": 1.1063790484932462e-07, "epoch": 2.3545331529093367, "percentage": 78.8, "elapsed_time": "1:47:08", "remaining_time": "0:28:49"}
+{"current_steps": 440, "total_steps": 552, "loss": 0.6996, "learning_rate": 1.0171167927278368e-07, "epoch": 2.381596752368065, "percentage": 79.71, "elapsed_time": "1:48:14", "remaining_time": "0:27:33"}
+{"current_steps": 445, "total_steps": 552, "loss": 0.7032, "learning_rate": 9.311996311780446e-08, "epoch": 2.408660351826793, "percentage": 80.62, "elapsed_time": "1:49:20", "remaining_time": "0:26:17"}
+{"current_steps": 450, "total_steps": 552, "loss": 0.7004, "learning_rate": 8.486997228767012e-08, "epoch": 2.435723951285521, "percentage": 81.52, "elapsed_time": "1:50:26", "remaining_time": "0:25:01"}
+{"current_steps": 450, "total_steps": 552, "eval_loss": 0.8185598254203796, "epoch": 2.435723951285521, "percentage": 81.52, "elapsed_time": "1:51:57", "remaining_time": "0:25:22"}
+{"current_steps": 455, "total_steps": 552, "loss": 0.6951, "learning_rate": 7.696863568166518e-08, "epoch": 2.462787550744249, "percentage": 82.43, "elapsed_time": "1:53:03", "remaining_time": "0:24:06"}
+{"current_steps": 460, "total_steps": 552, "loss": 0.7148, "learning_rate": 6.942258937571771e-08, "epoch": 2.489851150202977, "percentage": 83.33, "elapsed_time": "1:54:09", "remaining_time": "0:22:49"}
+{"current_steps": 465, "total_steps": 552, "loss": 0.7011, "learning_rate": 6.2238171048975e-08, "epoch": 2.516914749661705, "percentage": 84.24, "elapsed_time": "1:55:15", "remaining_time": "0:21:33"}
+{"current_steps": 470, "total_steps": 552, "loss": 0.7206, "learning_rate": 5.5421414660992705e-08, "epoch": 2.543978349120433, "percentage": 85.14, "elapsed_time": "1:56:20", "remaining_time": "0:20:17"}
+{"current_steps": 475, "total_steps": 552, "loss": 0.7116, "learning_rate": 4.8978045384008125e-08, "epoch": 2.571041948579161, "percentage": 86.05, "elapsed_time": "1:57:25", "remaining_time": "0:19:02"}
+{"current_steps": 480, "total_steps": 552, "loss": 0.7192, "learning_rate": 4.2913474794554036e-08, "epoch": 2.598105548037889, "percentage": 86.96, "elapsed_time": "1:58:30", "remaining_time": "0:17:46"}
+{"current_steps": 485, "total_steps": 552, "loss": 0.7213, "learning_rate": 3.723279632845155e-08, "epoch": 2.6251691474966172, "percentage": 87.86, "elapsed_time": "1:59:35", "remaining_time": "0:16:31"}
+{"current_steps": 490, "total_steps": 552, "loss": 0.7058, "learning_rate": 3.194078100299863e-08, "epoch": 2.6522327469553453, "percentage": 88.77, "elapsed_time": "2:00:41", "remaining_time": "0:15:16"}
+{"current_steps": 495, "total_steps": 552, "loss": 0.7155, "learning_rate": 2.7041873409947734e-08, "epoch": 2.6792963464140733, "percentage": 89.67, "elapsed_time": "2:01:45", "remaining_time": "0:14:01"}
+{"current_steps": 500, "total_steps": 552, "loss": 0.7133, "learning_rate": 2.2540187982637627e-08, "epoch": 2.706359945872801, "percentage": 90.58, "elapsed_time": "2:02:51", "remaining_time": "0:12:46"}
+{"current_steps": 500, "total_steps": 552, "eval_loss": 0.817565381526947, "epoch": 2.706359945872801, "percentage": 90.58, "elapsed_time": "2:04:23", "remaining_time": "0:12:56"}
+{"current_steps": 505, "total_steps": 552, "loss": 0.7024, "learning_rate": 1.8439505540414458e-08, "epoch": 2.733423545331529, "percentage": 91.49, "elapsed_time": "2:05:29", "remaining_time": "0:11:40"}
+{"current_steps": 510, "total_steps": 552, "loss": 0.7039, "learning_rate": 1.4743270113244277e-08, "epoch": 2.760487144790257, "percentage": 92.39, "elapsed_time": "2:06:34", "remaining_time": "0:10:25"}
+{"current_steps": 515, "total_steps": 552, "loss": 0.7096, "learning_rate": 1.1454586049184589e-08, "epoch": 2.787550744248985, "percentage": 93.3, "elapsed_time": "2:07:40", "remaining_time": "0:09:10"}
+{"current_steps": 520, "total_steps": 552, "loss": 0.6872, "learning_rate": 8.576215407142651e-09, "epoch": 2.814614343707713, "percentage": 94.2, "elapsed_time": "2:08:46", "remaining_time": "0:07:55"}
+{"current_steps": 525, "total_steps": 552, "loss": 0.6934, "learning_rate": 6.110575637112425e-09, "epoch": 2.841677943166441, "percentage": 95.11, "elapsed_time": "2:09:51", "remaining_time": "0:06:40"}
+{"current_steps": 530, "total_steps": 552, "loss": 0.7066, "learning_rate": 4.059737549836517e-09, "epoch": 2.8687415426251692, "percentage": 96.01, "elapsed_time": "2:10:57", "remaining_time": "0:05:26"}
+{"current_steps": 535, "total_steps": 552, "loss": 0.6894, "learning_rate": 2.425423577599783e-09, "epoch": 2.8958051420838973, "percentage": 96.92, "elapsed_time": "2:12:02", "remaining_time": "0:04:11"}
+{"current_steps": 540, "total_steps": 552, "loss": 0.7122, "learning_rate": 1.209006327614226e-09, "epoch": 2.9228687415426253, "percentage": 97.83, "elapsed_time": "2:13:08", "remaining_time": "0:02:57"}
+{"current_steps": 545, "total_steps": 552, "loss": 0.7, "learning_rate": 4.115074292109777e-10, "epoch": 2.949932341001353, "percentage": 98.73, "elapsed_time": "2:14:14", "remaining_time": "0:01:43"}
+{"current_steps": 550, "total_steps": 552, "loss": 0.7, "learning_rate": 3.3596675806824013e-11, "epoch": 2.976995940460081, "percentage": 99.64, "elapsed_time": "2:15:19", "remaining_time": "0:00:29"}
+{"current_steps": 550, "total_steps": 552, "eval_loss": 0.8177570104598999, "epoch": 2.976995940460081, "percentage": 99.64, "elapsed_time": "2:16:50", "remaining_time": "0:00:29"}
+{"current_steps": 552, "total_steps": 552, "epoch": 2.9878213802435725, "percentage": 100.0, "elapsed_time": "2:17:51", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,900 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9878213802435725,
+  "eval_steps": 50,
+  "global_step": 552,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02706359945872801,
+      "grad_norm": 18.62096133756944,
+      "learning_rate": 5e-07,
+      "loss": 1.7202,
+      "step": 5
+    },
+    {
+      "epoch": 0.05412719891745602,
+      "grad_norm": 12.425223769043265,
+      "learning_rate": 1e-06,
+      "loss": 1.5858,
+      "step": 10
+    },
+    {
+      "epoch": 0.08119079837618404,
+      "grad_norm": 7.4903509661138825,
+      "learning_rate": 9.997900331216397e-07,
+      "loss": 1.2962,
+      "step": 15
+    },
+    {
+      "epoch": 0.10825439783491204,
+      "grad_norm": 4.423017017969494,
+      "learning_rate": 9.991603088309193e-07,
+      "loss": 1.1481,
+      "step": 20
+    },
+    {
+      "epoch": 0.13531799729364005,
+      "grad_norm": 4.05084233893573,
+      "learning_rate": 9.981113560128126e-07,
+      "loss": 1.0683,
+      "step": 25
+    },
+    {
+      "epoch": 0.16238159675236807,
+      "grad_norm": 3.6533701555355194,
+      "learning_rate": 9.966440556487147e-07,
+      "loss": 1.0347,
+      "step": 30
+    },
+    {
+      "epoch": 0.18944519621109607,
+      "grad_norm": 3.5509774718765037,
+      "learning_rate": 9.947596400765342e-07,
+      "loss": 0.9829,
+      "step": 35
+    },
+    {
+      "epoch": 0.2165087956698241,
+      "grad_norm": 3.389187665280499,
+      "learning_rate": 9.924596919556916e-07,
+      "loss": 0.9751,
+      "step": 40
+    },
+    {
+      "epoch": 0.2435723951285521,
+      "grad_norm": 3.7276246548668697,
+      "learning_rate": 9.897461429378964e-07,
+      "loss": 0.9534,
+      "step": 45
+    },
+    {
+      "epoch": 0.2706359945872801,
+      "grad_norm": 3.6238376734485906,
+      "learning_rate": 9.866212720448147e-07,
+      "loss": 0.9375,
+      "step": 50
+    },
+    {
+      "epoch": 0.2706359945872801,
+      "eval_loss": 0.9354712963104248,
+      "eval_runtime": 91.9855,
+      "eval_samples_per_second": 57.074,
+      "eval_steps_per_second": 0.902,
+      "step": 50
+    },
+    {
+      "epoch": 0.2976995940460081,
+      "grad_norm": 3.650038732579689,
+      "learning_rate": 9.830877037539935e-07,
+      "loss": 0.9241,
+      "step": 55
+    },
+    {
+      "epoch": 0.32476319350473615,
+      "grad_norm": 3.282303443355455,
+      "learning_rate": 9.791484057946465e-07,
+      "loss": 0.9301,
+      "step": 60
+    },
+    {
+      "epoch": 0.35182679296346414,
+      "grad_norm": 3.5367161380439316,
+      "learning_rate": 9.748066866551555e-07,
+      "loss": 0.9141,
+      "step": 65
+    },
+    {
+      "epoch": 0.37889039242219213,
+      "grad_norm": 3.384471001472233,
+      "learning_rate": 9.700661928043785e-07,
+      "loss": 0.9099,
+      "step": 70
+    },
+    {
+      "epoch": 0.4059539918809202,
+      "grad_norm": 3.6506849242542603,
+      "learning_rate": 9.649309056290984e-07,
+      "loss": 0.9034,
+      "step": 75
+    },
+    {
+      "epoch": 0.4330175913396482,
+      "grad_norm": 3.5334381489912654,
+      "learning_rate": 9.594051380901858e-07,
+      "loss": 0.8755,
+      "step": 80
+    },
+    {
+      "epoch": 0.46008119079837617,
+      "grad_norm": 3.617605597301526,
+      "learning_rate": 9.534935311002834e-07,
+      "loss": 0.887,
+      "step": 85
+    },
+    {
+      "epoch": 0.4871447902571042,
+      "grad_norm": 3.8303351034768016,
+      "learning_rate": 9.472010496260544e-07,
+      "loss": 0.8868,
+      "step": 90
+    },
+    {
+      "epoch": 0.5142083897158322,
+      "grad_norm": 3.4133330247065485,
+      "learning_rate": 9.405329785182678e-07,
+      "loss": 0.8685,
+      "step": 95
+    },
+    {
+      "epoch": 0.5412719891745602,
+      "grad_norm": 3.598327334615042,
+      "learning_rate": 9.334949180732244e-07,
+      "loss": 0.8824,
+      "step": 100
+    },
+    {
+      "epoch": 0.5412719891745602,
+      "eval_loss": 0.8775722980499268,
+      "eval_runtime": 91.8061,
+      "eval_samples_per_second": 57.186,
+      "eval_steps_per_second": 0.904,
+      "step": 100
+    },
+    {
+      "epoch": 0.5683355886332883,
+      "grad_norm": 3.4406636804059803,
+      "learning_rate": 9.260927793292497e-07,
+      "loss": 0.8847,
+      "step": 105
+    },
+    {
+      "epoch": 0.5953991880920162,
+      "grad_norm": 3.7093344605385363,
+      "learning_rate": 9.183327791022047e-07,
+      "loss": 0.8716,
+      "step": 110
+    },
+    {
+      "epoch": 0.6224627875507442,
+      "grad_norm": 3.6150174879821275,
+      "learning_rate": 9.102214347641843e-07,
+      "loss": 0.879,
+      "step": 115
+    },
+    {
+      "epoch": 0.6495263870094723,
+      "grad_norm": 3.323783724540155,
+      "learning_rate": 9.017655587697883e-07,
+      "loss": 0.849,
+      "step": 120
+    },
+    {
+      "epoch": 0.6765899864682002,
+      "grad_norm": 3.4870778817811705,
+      "learning_rate": 8.929722529345623e-07,
+      "loss": 0.8623,
+      "step": 125
+    },
+    {
+      "epoch": 0.7036535859269283,
+      "grad_norm": 3.3887325632646554,
+      "learning_rate": 8.83848902470413e-07,
+      "loss": 0.8821,
+      "step": 130
+    },
+    {
+      "epoch": 0.7307171853856563,
+      "grad_norm": 3.4877253492258253,
+      "learning_rate": 8.744031697830088e-07,
+      "loss": 0.864,
+      "step": 135
+    },
+    {
+      "epoch": 0.7577807848443843,
+      "grad_norm": 3.4539745143868643,
+      "learning_rate": 8.646429880363746e-07,
+      "loss": 0.8469,
+      "step": 140
+    },
+    {
+      "epoch": 0.7848443843031123,
+      "grad_norm": 3.6501092648768645,
+      "learning_rate": 8.545765544900846e-07,
+      "loss": 0.8488,
+      "step": 145
+    },
+    {
+      "epoch": 0.8119079837618404,
+      "grad_norm": 3.6661416233299233,
+      "learning_rate": 8.442123236146508e-07,
+      "loss": 0.8549,
+      "step": 150
+    },
+    {
+      "epoch": 0.8119079837618404,
+      "eval_loss": 0.8518306612968445,
+      "eval_runtime": 91.7277,
+      "eval_samples_per_second": 57.235,
+      "eval_steps_per_second": 0.905,
+      "step": 150
+    },
+    {
+      "epoch": 0.8389715832205683,
+      "grad_norm": 3.6360925835102895,
+      "learning_rate": 8.33558999990887e-07,
+      "loss": 0.846,
+      "step": 155
+    },
+    {
+      "epoch": 0.8660351826792964,
+      "grad_norm": 3.325785655756218,
+      "learning_rate": 8.22625530999215e-07,
+      "loss": 0.8485,
+      "step": 160
+    },
+    {
+      "epoch": 0.8930987821380244,
+      "grad_norm": 3.5191969682264492,
+      "learning_rate": 8.114210993050502e-07,
+      "loss": 0.86,
+      "step": 165
+    },
+    {
+      "epoch": 0.9201623815967523,
+      "grad_norm": 3.505912957460407,
+      "learning_rate": 7.999551151465791e-07,
+      "loss": 0.8445,
+      "step": 170
+    },
+    {
+      "epoch": 0.9472259810554804,
+      "grad_norm": 3.567280090097035,
+      "learning_rate": 7.88237208431406e-07,
+      "loss": 0.8366,
+      "step": 175
+    },
+    {
+      "epoch": 0.9742895805142084,
+      "grad_norm": 3.5124657783307143,
+      "learning_rate": 7.762772206487065e-07,
+      "loss": 0.8377,
+      "step": 180
+    },
+    {
+      "epoch": 1.0013531799729365,
+      "grad_norm": 3.661655068528439,
+      "learning_rate": 7.640851966036805e-07,
+      "loss": 0.8402,
+      "step": 185
+    },
+    {
+      "epoch": 1.0284167794316643,
+      "grad_norm": 3.443540295008513,
+      "learning_rate": 7.516713759812464e-07,
+      "loss": 0.7742,
+      "step": 190
+    },
+    {
+      "epoch": 1.0554803788903924,
+      "grad_norm": 3.5551780337145975,
+      "learning_rate": 7.390461847460628e-07,
+      "loss": 0.7723,
+      "step": 195
+    },
+    {
+      "epoch": 1.0825439783491204,
+      "grad_norm": 3.4346090387850965,
+      "learning_rate": 7.262202263860988e-07,
+      "loss": 0.7825,
+      "step": 200
+    },
+    {
+      "epoch": 1.0825439783491204,
+      "eval_loss": 0.8397604823112488,
+      "eval_runtime": 91.7114,
+      "eval_samples_per_second": 57.245,
+      "eval_steps_per_second": 0.905,
+      "step": 200
+    },
+    {
+      "epoch": 1.1096075778078485,
+      "grad_norm": 3.346387935116934,
+      "learning_rate": 7.1320427300711e-07,
+      "loss": 0.7622,
+      "step": 205
+    },
+    {
+      "epoch": 1.1366711772665765,
+      "grad_norm": 3.6975628986759532,
+      "learning_rate": 7.000092562854959e-07,
+      "loss": 0.7683,
+      "step": 210
+    },
+    {
+      "epoch": 1.1637347767253043,
+      "grad_norm": 3.534180683955908,
+      "learning_rate": 6.866462582871401e-07,
+      "loss": 0.7536,
+      "step": 215
+    },
+    {
+      "epoch": 1.1907983761840324,
+      "grad_norm": 3.6284911794109322,
+      "learning_rate": 6.731265021599436e-07,
+      "loss": 0.775,
+      "step": 220
+    },
+    {
+      "epoch": 1.2178619756427604,
+      "grad_norm": 3.9686622547711816,
+      "learning_rate": 6.594613427078674e-07,
+      "loss": 0.7736,
+      "step": 225
+    },
+    {
+      "epoch": 1.2449255751014885,
+      "grad_norm": 3.4953313507774797,
+      "learning_rate": 6.456622568544011e-07,
+      "loss": 0.7723,
+      "step": 230
+    },
+    {
+      "epoch": 1.2719891745602165,
+      "grad_norm": 3.600480261317538,
+      "learning_rate": 6.317408340034684e-07,
+      "loss": 0.7675,
+      "step": 235
+    },
+    {
+      "epoch": 1.2990527740189446,
+      "grad_norm": 4.160648083143722,
+      "learning_rate": 6.177087663058625e-07,
+      "loss": 0.786,
+      "step": 240
+    },
+    {
+      "epoch": 1.3261163734776726,
+      "grad_norm": 3.554038996352176,
+      "learning_rate": 6.035778388393893e-07,
+      "loss": 0.7569,
+      "step": 245
+    },
+    {
+      "epoch": 1.3531799729364005,
+      "grad_norm": 3.4314153682677517,
+      "learning_rate": 5.893599197109624e-07,
+      "loss": 0.759,
+      "step": 250
+    },
+    {
+      "epoch": 1.3531799729364005,
+      "eval_loss": 0.8301268219947815,
+      "eval_runtime": 91.7237,
+      "eval_samples_per_second": 57.237,
+      "eval_steps_per_second": 0.905,
+      "step": 250
+    },
+    {
+      "epoch": 1.3802435723951285,
+      "grad_norm": 3.405464319479644,
+      "learning_rate": 5.750669500889666e-07,
+      "loss": 0.7549,
+      "step": 255
+    },
+    {
+      "epoch": 1.4073071718538566,
+      "grad_norm": 3.500530938219073,
+      "learning_rate": 5.607109341742578e-07,
+      "loss": 0.7801,
+      "step": 260
+    },
+    {
+      "epoch": 1.4343707713125846,
+      "grad_norm": 3.726591852861668,
+      "learning_rate": 5.463039291182256e-07,
+      "loss": 0.7765,
+      "step": 265
+    },
+    {
+      "epoch": 1.4614343707713127,
+      "grad_norm": 3.619160960040315,
+      "learning_rate": 5.318580348963825e-07,
+      "loss": 0.7662,
+      "step": 270
+    },
+    {
+      "epoch": 1.4884979702300405,
+      "grad_norm": 3.4244376461150208,
+      "learning_rate": 5.173853841459877e-07,
+      "loss": 0.7554,
+      "step": 275
+    },
+    {
+      "epoch": 1.5155615696887685,
+      "grad_norm": 3.700667266849164,
+      "learning_rate": 5.028981319762399e-07,
+      "loss": 0.7616,
+      "step": 280
+    },
+    {
+      "epoch": 1.5426251691474966,
+      "grad_norm": 3.567507416375757,
+      "learning_rate": 4.884084457595956e-07,
+      "loss": 0.7818,
+      "step": 285
+    },
+    {
+      "epoch": 1.5696887686062246,
+      "grad_norm": 3.7802418009731755,
+      "learning_rate": 4.7392849491278817e-07,
+      "loss": 0.7691,
+      "step": 290
+    },
+    {
+      "epoch": 1.5967523680649527,
+      "grad_norm": 3.501336855850476,
+      "learning_rate": 4.5947044067613e-07,
+      "loss": 0.7681,
+      "step": 295
+    },
+    {
+      "epoch": 1.6238159675236807,
+      "grad_norm": 3.656073742916776,
+      "learning_rate": 4.4504642589968217e-07,
+      "loss": 0.7676,
+      "step": 300
+    },
+    {
+      "epoch": 1.6238159675236807,
+      "eval_loss": 0.8219158053398132,
+      "eval_runtime": 91.7533,
+      "eval_samples_per_second": 57.219,
+      "eval_steps_per_second": 0.905,
+      "step": 300
+    },
+    {
+      "epoch": 1.6508795669824088,
+      "grad_norm": 3.704023712304986,
+      "learning_rate": 4.3066856484486847e-07,
+      "loss": 0.7602,
+      "step": 305
+    },
+    {
+      "epoch": 1.6779431664411368,
+      "grad_norm": 3.504247839905232,
+      "learning_rate": 4.1634893301010165e-07,
+      "loss": 0.7589,
+      "step": 310
+    },
+    {
+      "epoch": 1.7050067658998647,
+      "grad_norm": 3.470803136242184,
+      "learning_rate": 4.0209955698896445e-07,
+      "loss": 0.7475,
+      "step": 315
+    },
+    {
+      "epoch": 1.7320703653585927,
+      "grad_norm": 3.5356035894949045,
+      "learning_rate": 3.8793240436946385e-07,
+      "loss": 0.7548,
+      "step": 320
+    },
+    {
+      "epoch": 1.7591339648173205,
+      "grad_norm": 3.559368281490328,
+      "learning_rate": 3.738593736828426e-07,
+      "loss": 0.761,
+      "step": 325
+    },
+    {
+      "epoch": 1.7861975642760486,
+      "grad_norm": 3.4859137753013942,
+      "learning_rate": 3.598922844103902e-07,
+      "loss": 0.7704,
+      "step": 330
+    },
+    {
+      "epoch": 1.8132611637347766,
+      "grad_norm": 3.6109852467133607,
+      "learning_rate": 3.4604286705664397e-07,
+      "loss": 0.7578,
+      "step": 335
+    },
+    {
+      "epoch": 1.8403247631935047,
+      "grad_norm": 3.478328670865475,
+      "learning_rate": 3.323227532973193e-07,
+      "loss": 0.7548,
+      "step": 340
+    },
+    {
+      "epoch": 1.8673883626522327,
+      "grad_norm": 3.670794273772087,
+      "learning_rate": 3.187434662102434e-07,
+      "loss": 0.7624,
+      "step": 345
+    },
+    {
+      "epoch": 1.8944519621109608,
+      "grad_norm": 3.6564249976504963,
+      "learning_rate": 3.0531641059749634e-07,
+      "loss": 0.7624,
+      "step": 350
+    },
+    {
+      "epoch": 1.8944519621109608,
+      "eval_loss": 0.81601482629776,
+      "eval_runtime": 91.595,
+      "eval_samples_per_second": 57.318,
+      "eval_steps_per_second": 0.906,
+      "step": 350
+    },
+    {
+      "epoch": 1.9215155615696888,
+      "grad_norm": 3.8249796571875754,
+      "learning_rate": 2.920528634068885e-07,
+      "loss": 0.7342,
+      "step": 355
+    },
+    {
+      "epoch": 1.9485791610284169,
+      "grad_norm": 3.4390639442266044,
+      "learning_rate": 2.789639642608184e-07,
+      "loss": 0.7552,
+      "step": 360
+    },
+    {
+      "epoch": 1.975642760487145,
+      "grad_norm": 3.681741592514357,
+      "learning_rate": 2.6606070610046526e-07,
+      "loss": 0.7578,
+      "step": 365
+    },
+    {
+      "epoch": 2.002706359945873,
+      "grad_norm": 3.7841567374808815,
+      "learning_rate": 2.533539259531757e-07,
+      "loss": 0.755,
+      "step": 370
+    },
+    {
+      "epoch": 2.029769959404601,
+      "grad_norm": 3.406665416810156,
+      "learning_rate": 2.408542958307957e-07,
+      "loss": 0.6915,
+      "step": 375
+    },
+    {
+      "epoch": 2.0568335588633286,
+      "grad_norm": 3.627816770705192,
+      "learning_rate": 2.2857231376659514e-07,
+      "loss": 0.7139,
+      "step": 380
+    },
+    {
+      "epoch": 2.0838971583220567,
+      "grad_norm": 3.8009146897382164,
+      "learning_rate": 2.1651829499831043e-07,
+      "loss": 0.7127,
+      "step": 385
+    },
+    {
+      "epoch": 2.1109607577807847,
+      "grad_norm": 3.7612594070053578,
+      "learning_rate": 2.0470236330471126e-07,
+      "loss": 0.7188,
+      "step": 390
+    },
+    {
+      "epoch": 2.138024357239513,
+      "grad_norm": 3.881855102735637,
+      "learning_rate": 1.9313444250296846e-07,
+      "loss": 0.7319,
+      "step": 395
+    },
+    {
+      "epoch": 2.165087956698241,
+      "grad_norm": 3.8666379554848103,
+      "learning_rate": 1.818242481139613e-07,
+      "loss": 0.6976,
+      "step": 400
+    },
+    {
+      "epoch": 2.165087956698241,
+      "eval_loss": 0.8192901611328125,
+      "eval_runtime": 91.7299,
+      "eval_samples_per_second": 57.233,
+      "eval_steps_per_second": 0.905,
+      "step": 400
+    },
+    {
+      "epoch": 2.192151556156969,
+      "grad_norm": 3.6983015115543676,
+      "learning_rate": 1.7078127920252783e-07,
+      "loss": 0.7018,
+      "step": 405
+    },
+    {
+      "epoch": 2.219215155615697,
+      "grad_norm": 3.4856114871878408,
+      "learning_rate": 1.600148103995087e-07,
+      "loss": 0.7062,
+      "step": 410
+    },
+    {
+      "epoch": 2.246278755074425,
+      "grad_norm": 3.7609793781320042,
+      "learning_rate": 1.4953388411228602e-07,
+      "loss": 0.714,
+      "step": 415
+    },
+    {
+      "epoch": 2.273342354533153,
+      "grad_norm": 3.7207726096154206,
+      "learning_rate": 1.3934730293035936e-07,
+      "loss": 0.7028,
+      "step": 420
+    },
+    {
+      "epoch": 2.300405953991881,
+      "grad_norm": 3.9694406933094193,
+      "learning_rate": 1.2946362223233614e-07,
+      "loss": 0.7023,
+      "step": 425
+    },
+    {
+      "epoch": 2.3274695534506087,
+      "grad_norm": 3.63014175931209,
+      "learning_rate": 1.198911430005478e-07,
+      "loss": 0.7022,
+      "step": 430
+    },
+    {
+      "epoch": 2.3545331529093367,
+      "grad_norm": 3.7202986392499295,
+      "learning_rate": 1.1063790484932462e-07,
+      "loss": 0.7083,
+      "step": 435
+    },
+    {
+      "epoch": 2.381596752368065,
+      "grad_norm": 3.640272659998316,
+      "learning_rate": 1.0171167927278368e-07,
+      "loss": 0.6996,
+      "step": 440
+    },
+    {
+      "epoch": 2.408660351826793,
+      "grad_norm": 3.830774844166055,
+      "learning_rate": 9.311996311780446e-08,
+      "loss": 0.7032,
+      "step": 445
+    },
+    {
+      "epoch": 2.435723951285521,
+      "grad_norm": 3.835735833278635,
+      "learning_rate": 8.486997228767012e-08,
+      "loss": 0.7004,
+      "step": 450
+    },
+    {
+      "epoch": 2.435723951285521,
+      "eval_loss": 0.8185598254203796,
+      "eval_runtime": 91.6401,
+      "eval_samples_per_second": 57.289,
+      "eval_steps_per_second": 0.906,
+      "step": 450
+    },
+    {
+      "epoch": 2.462787550744249,
+      "grad_norm": 3.8096679910803526,
+      "learning_rate": 7.696863568166518e-08,
+      "loss": 0.6951,
+      "step": 455
+    },
+    {
+      "epoch": 2.489851150202977,
+      "grad_norm": 3.9855447041279612,
+      "learning_rate": 6.942258937571771e-08,
+      "loss": 0.7148,
+      "step": 460
+    },
+    {
+      "epoch": 2.516914749661705,
+      "grad_norm": 3.8539380052102943,
+      "learning_rate": 6.2238171048975e-08,
+      "loss": 0.7011,
+      "step": 465
+    },
+    {
+      "epoch": 2.543978349120433,
+      "grad_norm": 4.0430762185988725,
+      "learning_rate": 5.5421414660992705e-08,
+      "loss": 0.7206,
+      "step": 470
+    },
+    {
+      "epoch": 2.571041948579161,
+      "grad_norm": 3.936740213024643,
+      "learning_rate": 4.8978045384008125e-08,
+      "loss": 0.7116,
+      "step": 475
+    },
+    {
+      "epoch": 2.598105548037889,
+      "grad_norm": 3.9575285108660196,
+      "learning_rate": 4.2913474794554036e-08,
+      "loss": 0.7192,
+      "step": 480
+    },
+    {
+      "epoch": 2.6251691474966172,
+      "grad_norm": 3.8004579862768604,
+      "learning_rate": 3.723279632845155e-08,
+      "loss": 0.7213,
+      "step": 485
+    },
+    {
+      "epoch": 2.6522327469553453,
+      "grad_norm": 3.9896579923804953,
+      "learning_rate": 3.194078100299863e-08,
+      "loss": 0.7058,
+      "step": 490
+    },
+    {
+      "epoch": 2.6792963464140733,
+      "grad_norm": 3.485486386140113,
+      "learning_rate": 2.7041873409947734e-08,
+      "loss": 0.7155,
+      "step": 495
+    },
+    {
+      "epoch": 2.706359945872801,
+      "grad_norm": 3.7310098177240625,
+      "learning_rate": 2.2540187982637627e-08,
+      "loss": 0.7133,
+      "step": 500
+    },
+    {
+      "epoch": 2.706359945872801,
+      "eval_loss": 0.817565381526947,
+      "eval_runtime": 91.7069,
+      "eval_samples_per_second": 57.248,
+      "eval_steps_per_second": 0.905,
+      "step": 500
+    },
+    {
+      "epoch": 2.733423545331529,
+      "grad_norm": 3.6063602953215654,
+      "learning_rate": 1.8439505540414458e-08,
+      "loss": 0.7024,
+      "step": 505
+    },
+    {
+      "epoch": 2.760487144790257,
+      "grad_norm": 3.6598065079223527,
+      "learning_rate": 1.4743270113244277e-08,
+      "loss": 0.7039,
+      "step": 510
+    },
+    {
+      "epoch": 2.787550744248985,
+      "grad_norm": 3.7941708315282847,
+      "learning_rate": 1.1454586049184589e-08,
+      "loss": 0.7096,
+      "step": 515
+    },
+    {
+      "epoch": 2.814614343707713,
+      "grad_norm": 4.0192290237097765,
+      "learning_rate": 8.576215407142651e-09,
+      "loss": 0.6872,
+      "step": 520
+    },
+    {
+      "epoch": 2.841677943166441,
+      "grad_norm": 3.671284433438612,
+      "learning_rate": 6.110575637112425e-09,
+      "loss": 0.6934,
+      "step": 525
+    },
+    {
+      "epoch": 2.8687415426251692,
+      "grad_norm": 4.26951192895122,
+      "learning_rate": 4.059737549836517e-09,
+      "loss": 0.7066,
+      "step": 530
+    },
+    {
+      "epoch": 2.8958051420838973,
+      "grad_norm": 3.732791917417492,
+      "learning_rate": 2.425423577599783e-09,
+      "loss": 0.6894,
+      "step": 535
+    },
+    {
+      "epoch": 2.9228687415426253,
+      "grad_norm": 3.626360935172459,
+      "learning_rate": 1.209006327614226e-09,
+      "loss": 0.7122,
+      "step": 540
+    },
+    {
+      "epoch": 2.949932341001353,
+      "grad_norm": 3.649121404665413,
+      "learning_rate": 4.115074292109777e-10,
+      "loss": 0.7,
+      "step": 545
+    },
+    {
+      "epoch": 2.976995940460081,
+      "grad_norm": 3.550586809689184,
+      "learning_rate": 3.3596675806824013e-11,
+      "loss": 0.7,
+      "step": 550
+    },
+    {
+      "epoch": 2.976995940460081,
+      "eval_loss": 0.8177570104598999,
+      "eval_runtime": 91.665,
+      "eval_samples_per_second": 57.274,
+      "eval_steps_per_second": 0.905,
+      "step": 550
+    },
+    {
+      "epoch": 2.9878213802435725,
+      "step": 552,
+      "total_flos": 3254608239525888.0,
+      "train_loss": 0.8081599063631417,
+      "train_runtime": 8273.4491,
+      "train_samples_per_second": 17.133,
+      "train_steps_per_second": 0.067
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 552,
+  "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": 3254608239525888.0,
+  "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 sha256:8c9b0f3ef194a7125f93690f76a60f802d265059835ec52d51cf92b59129dbee
+size 7096