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_l0_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_l0_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_l0_0_50 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8117
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9428        | 0.2706 | 50   | 0.9270          |
+| 0.8747        | 0.5413 | 100  | 0.8709          |
+| 0.8698        | 0.8119 | 150  | 0.8460          |
+| 0.7652        | 1.0825 | 200  | 0.8337          |
+| 0.7822        | 1.3532 | 250  | 0.8234          |
+| 0.7628        | 1.6238 | 300  | 0.8164          |
+| 0.768         | 1.8945 | 350  | 0.8106          |
+| 0.7075        | 2.1651 | 400  | 0.8137          |
+| 0.71          | 2.4357 | 450  | 0.8127          |
+| 0.7069        | 2.7064 | 500  | 0.8119          |
+| 0.7088        | 2.9770 | 550  | 0.8117          |
+
+
+### 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": 0.8117280602455139,
+    "eval_runtime": 91.967,
+    "eval_samples_per_second": 57.086,
+    "eval_steps_per_second": 0.902,
+    "total_flos": 3254608239525888.0,
+    "train_loss": 0.8072819815597673,
+    "train_runtime": 8267.6947,
+    "train_samples_per_second": 17.145,
+    "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": 0.8117280602455139,
+    "eval_runtime": 91.967,
+    "eval_samples_per_second": 57.086,
+    "eval_steps_per_second": 0.902
+}

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:e12ecbc9452a22c140299620356c99a8020caf6f2d66d92fd63b9cc650a92eb7
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b8a95d4aad5fcba5407bb26ba2a056cb48c4cc06a7a7f583bb99ee1e6cdd86c
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:556425790ff869c5314ea7d22f84f68a5fa043688ebd224cdcd28bc5a866c090
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40d714deab0fa98b33e2432c2a9524fdbaa9980c156d6ac3ac3f149f32b027f
+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": 0.8072819815597673,
+    "train_runtime": 8267.6947,
+    "train_samples_per_second": 17.145,
+    "train_steps_per_second": 0.067
+}

trainer_log.jsonl

@@ -0,0 +1,122 @@
+{"current_steps": 5, "total_steps": 552, "loss": 1.734, "learning_rate": 5e-07, "epoch": 0.02706359945872801, "percentage": 0.91, "elapsed_time": "0:01:09", "remaining_time": "2:05:59"}
+{"current_steps": 10, "total_steps": 552, "loss": 1.6027, "learning_rate": 1e-06, "epoch": 0.05412719891745602, "percentage": 1.81, "elapsed_time": "0:02:14", "remaining_time": "2:01:22"}
+{"current_steps": 15, "total_steps": 552, "loss": 1.2943, "learning_rate": 9.997900331216397e-07, "epoch": 0.08119079837618404, "percentage": 2.72, "elapsed_time": "0:03:20", "remaining_time": "1:59:29"}
+{"current_steps": 20, "total_steps": 552, "loss": 1.1214, "learning_rate": 9.991603088309193e-07, "epoch": 0.10825439783491204, "percentage": 3.62, "elapsed_time": "0:04:25", "remaining_time": "1:57:46"}
+{"current_steps": 25, "total_steps": 552, "loss": 1.0701, "learning_rate": 9.981113560128126e-07, "epoch": 0.13531799729364005, "percentage": 4.53, "elapsed_time": "0:05:31", "remaining_time": "1:56:20"}
+{"current_steps": 30, "total_steps": 552, "loss": 1.0514, "learning_rate": 9.966440556487147e-07, "epoch": 0.16238159675236807, "percentage": 5.43, "elapsed_time": "0:06:35", "remaining_time": "1:54:46"}
+{"current_steps": 35, "total_steps": 552, "loss": 0.9816, "learning_rate": 9.947596400765342e-07, "epoch": 0.18944519621109607, "percentage": 6.34, "elapsed_time": "0:07:41", "remaining_time": "1:53:30"}
+{"current_steps": 40, "total_steps": 552, "loss": 0.9671, "learning_rate": 9.924596919556916e-07, "epoch": 0.2165087956698241, "percentage": 7.25, "elapsed_time": "0:08:46", "remaining_time": "1:52:14"}
+{"current_steps": 45, "total_steps": 552, "loss": 0.9488, "learning_rate": 9.897461429378964e-07, "epoch": 0.2435723951285521, "percentage": 8.15, "elapsed_time": "0:09:51", "remaining_time": "1:50:59"}
+{"current_steps": 50, "total_steps": 552, "loss": 0.9428, "learning_rate": 9.866212720448147e-07, "epoch": 0.2706359945872801, "percentage": 9.06, "elapsed_time": "0:10:56", "remaining_time": "1:49:46"}
+{"current_steps": 50, "total_steps": 552, "eval_loss": 0.9270144701004028, "epoch": 0.2706359945872801, "percentage": 9.06, "elapsed_time": "0:12:29", "remaining_time": "2:05:22"}
+{"current_steps": 55, "total_steps": 552, "loss": 0.9318, "learning_rate": 9.830877037539935e-07, "epoch": 0.2976995940460081, "percentage": 9.96, "elapsed_time": "0:13:34", "remaining_time": "2:02:39"}
+{"current_steps": 60, "total_steps": 552, "loss": 0.9079, "learning_rate": 9.791484057946465e-07, "epoch": 0.32476319350473615, "percentage": 10.87, "elapsed_time": "0:14:39", "remaining_time": "2:00:12"}
+{"current_steps": 65, "total_steps": 552, "loss": 0.8999, "learning_rate": 9.748066866551555e-07, "epoch": 0.35182679296346414, "percentage": 11.78, "elapsed_time": "0:15:45", "remaining_time": "1:58:03"}
+{"current_steps": 70, "total_steps": 552, "loss": 0.9047, "learning_rate": 9.700661928043785e-07, "epoch": 0.37889039242219213, "percentage": 12.68, "elapsed_time": "0:16:51", "remaining_time": "1:56:03"}
+{"current_steps": 75, "total_steps": 552, "loss": 0.8954, "learning_rate": 9.649309056290984e-07, "epoch": 0.4059539918809202, "percentage": 13.59, "elapsed_time": "0:17:56", "remaining_time": "1:54:04"}
+{"current_steps": 80, "total_steps": 552, "loss": 0.8984, "learning_rate": 9.594051380901858e-07, "epoch": 0.4330175913396482, "percentage": 14.49, "elapsed_time": "0:19:01", "remaining_time": "1:52:15"}
+{"current_steps": 85, "total_steps": 552, "loss": 0.9018, "learning_rate": 9.534935311002834e-07, "epoch": 0.46008119079837617, "percentage": 15.4, "elapsed_time": "0:20:07", "remaining_time": "1:50:33"}
+{"current_steps": 90, "total_steps": 552, "loss": 0.888, "learning_rate": 9.472010496260544e-07, "epoch": 0.4871447902571042, "percentage": 16.3, "elapsed_time": "0:21:12", "remaining_time": "1:48:54"}
+{"current_steps": 95, "total_steps": 552, "loss": 0.8828, "learning_rate": 9.405329785182678e-07, "epoch": 0.5142083897158322, "percentage": 17.21, "elapsed_time": "0:22:18", "remaining_time": "1:47:17"}
+{"current_steps": 100, "total_steps": 552, "loss": 0.8747, "learning_rate": 9.334949180732244e-07, "epoch": 0.5412719891745602, "percentage": 18.12, "elapsed_time": "0:23:22", "remaining_time": "1:45:41"}
+{"current_steps": 100, "total_steps": 552, "eval_loss": 0.8708707690238953, "epoch": 0.5412719891745602, "percentage": 18.12, "elapsed_time": "0:24:55", "remaining_time": "1:52:38"}
+{"current_steps": 105, "total_steps": 552, "loss": 0.8665, "learning_rate": 9.260927793292497e-07, "epoch": 0.5683355886332883, "percentage": 19.02, "elapsed_time": "0:26:00", "remaining_time": "1:50:43"}
+{"current_steps": 110, "total_steps": 552, "loss": 0.8528, "learning_rate": 9.183327791022047e-07, "epoch": 0.5953991880920162, "percentage": 19.93, "elapsed_time": "0:27:05", "remaining_time": "1:48:49"}
+{"current_steps": 115, "total_steps": 552, "loss": 0.8865, "learning_rate": 9.102214347641843e-07, "epoch": 0.6224627875507442, "percentage": 20.83, "elapsed_time": "0:28:10", "remaining_time": "1:47:02"}
+{"current_steps": 120, "total_steps": 552, "loss": 0.8648, "learning_rate": 9.017655587697883e-07, "epoch": 0.6495263870094723, "percentage": 21.74, "elapsed_time": "0:29:15", "remaining_time": "1:45:20"}
+{"current_steps": 125, "total_steps": 552, "loss": 0.8484, "learning_rate": 8.929722529345623e-07, "epoch": 0.6765899864682002, "percentage": 22.64, "elapsed_time": "0:30:20", "remaining_time": "1:43:40"}
+{"current_steps": 130, "total_steps": 552, "loss": 0.8496, "learning_rate": 8.83848902470413e-07, "epoch": 0.7036535859269283, "percentage": 23.55, "elapsed_time": "0:31:26", "remaining_time": "1:42:03"}
+{"current_steps": 135, "total_steps": 552, "loss": 0.8592, "learning_rate": 8.744031697830088e-07, "epoch": 0.7307171853856563, "percentage": 24.46, "elapsed_time": "0:32:30", "remaining_time": "1:40:26"}
+{"current_steps": 140, "total_steps": 552, "loss": 0.8624, "learning_rate": 8.646429880363746e-07, "epoch": 0.7577807848443843, "percentage": 25.36, "elapsed_time": "0:33:36", "remaining_time": "1:38:54"}
+{"current_steps": 145, "total_steps": 552, "loss": 0.8516, "learning_rate": 8.545765544900846e-07, "epoch": 0.7848443843031123, "percentage": 26.27, "elapsed_time": "0:34:42", "remaining_time": "1:37:24"}
+{"current_steps": 150, "total_steps": 552, "loss": 0.8698, "learning_rate": 8.442123236146508e-07, "epoch": 0.8119079837618404, "percentage": 27.17, "elapsed_time": "0:35:47", "remaining_time": "1:35:54"}
+{"current_steps": 150, "total_steps": 552, "eval_loss": 0.8459715247154236, "epoch": 0.8119079837618404, "percentage": 27.17, "elapsed_time": "0:37:19", "remaining_time": "1:40:01"}
+{"current_steps": 155, "total_steps": 552, "loss": 0.844, "learning_rate": 8.33558999990887e-07, "epoch": 0.8389715832205683, "percentage": 28.08, "elapsed_time": "0:38:25", "remaining_time": "1:38:25"}
+{"current_steps": 160, "total_steps": 552, "loss": 0.829, "learning_rate": 8.22625530999215e-07, "epoch": 0.8660351826792964, "percentage": 28.99, "elapsed_time": "0:39:30", "remaining_time": "1:36:47"}
+{"current_steps": 165, "total_steps": 552, "loss": 0.859, "learning_rate": 8.114210993050502e-07, "epoch": 0.8930987821380244, "percentage": 29.89, "elapsed_time": "0:40:36", "remaining_time": "1:35:13"}
+{"current_steps": 170, "total_steps": 552, "loss": 0.8373, "learning_rate": 7.999551151465791e-07, "epoch": 0.9201623815967523, "percentage": 30.8, "elapsed_time": "0:41:42", "remaining_time": "1:33:42"}
+{"current_steps": 175, "total_steps": 552, "loss": 0.8301, "learning_rate": 7.88237208431406e-07, "epoch": 0.9472259810554804, "percentage": 31.7, "elapsed_time": "0:42:47", "remaining_time": "1:32:10"}
+{"current_steps": 180, "total_steps": 552, "loss": 0.824, "learning_rate": 7.762772206487065e-07, "epoch": 0.9742895805142084, "percentage": 32.61, "elapsed_time": "0:43:52", "remaining_time": "1:30:39"}
+{"current_steps": 185, "total_steps": 552, "loss": 0.8525, "learning_rate": 7.640851966036805e-07, "epoch": 1.0013531799729365, "percentage": 33.51, "elapsed_time": "0:44:57", "remaining_time": "1:29:11"}
+{"current_steps": 190, "total_steps": 552, "loss": 0.778, "learning_rate": 7.516713759812464e-07, "epoch": 1.0284167794316643, "percentage": 34.42, "elapsed_time": "0:46:01", "remaining_time": "1:27:41"}
+{"current_steps": 195, "total_steps": 552, "loss": 0.7658, "learning_rate": 7.390461847460628e-07, "epoch": 1.0554803788903924, "percentage": 35.33, "elapsed_time": "0:47:07", "remaining_time": "1:26:16"}
+{"current_steps": 200, "total_steps": 552, "loss": 0.7652, "learning_rate": 7.262202263860988e-07, "epoch": 1.0825439783491204, "percentage": 36.23, "elapsed_time": "0:48:13", "remaining_time": "1:24:52"}
+{"current_steps": 200, "total_steps": 552, "eval_loss": 0.833743155002594, "epoch": 1.0825439783491204, "percentage": 36.23, "elapsed_time": "0:49:45", "remaining_time": "1:27:34"}
+{"current_steps": 205, "total_steps": 552, "loss": 0.7688, "learning_rate": 7.1320427300711e-07, "epoch": 1.1096075778078485, "percentage": 37.14, "elapsed_time": "0:50:50", "remaining_time": "1:26:03"}
+{"current_steps": 210, "total_steps": 552, "loss": 0.762, "learning_rate": 7.000092562854959e-07, "epoch": 1.1366711772665765, "percentage": 38.04, "elapsed_time": "0:51:56", "remaining_time": "1:24:35"}
+{"current_steps": 215, "total_steps": 552, "loss": 0.7764, "learning_rate": 6.866462582871401e-07, "epoch": 1.1637347767253043, "percentage": 38.95, "elapsed_time": "0:53:01", "remaining_time": "1:23:07"}
+{"current_steps": 220, "total_steps": 552, "loss": 0.772, "learning_rate": 6.731265021599436e-07, "epoch": 1.1907983761840324, "percentage": 39.86, "elapsed_time": "0:54:06", "remaining_time": "1:21:39"}
+{"current_steps": 225, "total_steps": 552, "loss": 0.7738, "learning_rate": 6.594613427078674e-07, "epoch": 1.2178619756427604, "percentage": 40.76, "elapsed_time": "0:55:12", "remaining_time": "1:20:14"}
+{"current_steps": 230, "total_steps": 552, "loss": 0.78, "learning_rate": 6.456622568544011e-07, "epoch": 1.2449255751014885, "percentage": 41.67, "elapsed_time": "0:56:18", "remaining_time": "1:18:49"}
+{"current_steps": 235, "total_steps": 552, "loss": 0.7832, "learning_rate": 6.317408340034684e-07, "epoch": 1.2719891745602165, "percentage": 42.57, "elapsed_time": "0:57:23", "remaining_time": "1:17:24"}
+{"current_steps": 240, "total_steps": 552, "loss": 0.776, "learning_rate": 6.177087663058625e-07, "epoch": 1.2990527740189446, "percentage": 43.48, "elapsed_time": "0:58:29", "remaining_time": "1:16:02"}
+{"current_steps": 245, "total_steps": 552, "loss": 0.7556, "learning_rate": 6.035778388393893e-07, "epoch": 1.3261163734776726, "percentage": 44.38, "elapsed_time": "0:59:34", "remaining_time": "1:14:39"}
+{"current_steps": 250, "total_steps": 552, "loss": 0.7822, "learning_rate": 5.893599197109624e-07, "epoch": 1.3531799729364005, "percentage": 45.29, "elapsed_time": "1:00:40", "remaining_time": "1:13:17"}
+{"current_steps": 250, "total_steps": 552, "eval_loss": 0.8234151005744934, "epoch": 1.3531799729364005, "percentage": 45.29, "elapsed_time": "1:02:12", "remaining_time": "1:15:08"}
+{"current_steps": 255, "total_steps": 552, "loss": 0.7841, "learning_rate": 5.750669500889666e-07, "epoch": 1.3802435723951285, "percentage": 46.2, "elapsed_time": "1:03:17", "remaining_time": "1:13:43"}
+{"current_steps": 260, "total_steps": 552, "loss": 0.7684, "learning_rate": 5.607109341742578e-07, "epoch": 1.4073071718538566, "percentage": 47.1, "elapsed_time": "1:04:24", "remaining_time": "1:12:20"}
+{"current_steps": 265, "total_steps": 552, "loss": 0.7704, "learning_rate": 5.463039291182256e-07, "epoch": 1.4343707713125846, "percentage": 48.01, "elapsed_time": "1:05:30", "remaining_time": "1:10:56"}
+{"current_steps": 270, "total_steps": 552, "loss": 0.749, "learning_rate": 5.318580348963825e-07, "epoch": 1.4614343707713127, "percentage": 48.91, "elapsed_time": "1:06:35", "remaining_time": "1:09:33"}
+{"current_steps": 275, "total_steps": 552, "loss": 0.7643, "learning_rate": 5.173853841459877e-07, "epoch": 1.4884979702300405, "percentage": 49.82, "elapsed_time": "1:07:40", "remaining_time": "1:08:09"}
+{"current_steps": 280, "total_steps": 552, "loss": 0.7564, "learning_rate": 5.028981319762399e-07, "epoch": 1.5155615696887685, "percentage": 50.72, "elapsed_time": "1:08:44", "remaining_time": "1:06:47"}
+{"current_steps": 285, "total_steps": 552, "loss": 0.7512, "learning_rate": 4.884084457595956e-07, "epoch": 1.5426251691474966, "percentage": 51.63, "elapsed_time": "1:09:49", "remaining_time": "1:05:25"}
+{"current_steps": 290, "total_steps": 552, "loss": 0.7729, "learning_rate": 4.7392849491278817e-07, "epoch": 1.5696887686062246, "percentage": 52.54, "elapsed_time": "1:10:55", "remaining_time": "1:04:04"}
+{"current_steps": 295, "total_steps": 552, "loss": 0.7479, "learning_rate": 4.5947044067613e-07, "epoch": 1.5967523680649527, "percentage": 53.44, "elapsed_time": "1:12:01", "remaining_time": "1:02:44"}
+{"current_steps": 300, "total_steps": 552, "loss": 0.7628, "learning_rate": 4.4504642589968217e-07, "epoch": 1.6238159675236807, "percentage": 54.35, "elapsed_time": "1:13:06", "remaining_time": "1:01:24"}
+{"current_steps": 300, "total_steps": 552, "eval_loss": 0.816413402557373, "epoch": 1.6238159675236807, "percentage": 54.35, "elapsed_time": "1:14:38", "remaining_time": "1:02:42"}
+{"current_steps": 305, "total_steps": 552, "loss": 0.7534, "learning_rate": 4.3066856484486847e-07, "epoch": 1.6508795669824088, "percentage": 55.25, "elapsed_time": "1:15:44", "remaining_time": "1:01:20"}
+{"current_steps": 310, "total_steps": 552, "loss": 0.7607, "learning_rate": 4.1634893301010165e-07, "epoch": 1.6779431664411368, "percentage": 56.16, "elapsed_time": "1:16:49", "remaining_time": "0:59:58"}
+{"current_steps": 315, "total_steps": 552, "loss": 0.7514, "learning_rate": 4.0209955698896445e-07, "epoch": 1.7050067658998647, "percentage": 57.07, "elapsed_time": "1:17:55", "remaining_time": "0:58:38"}
+{"current_steps": 320, "total_steps": 552, "loss": 0.7597, "learning_rate": 3.8793240436946385e-07, "epoch": 1.7320703653585927, "percentage": 57.97, "elapsed_time": "1:19:00", "remaining_time": "0:57:17"}
+{"current_steps": 325, "total_steps": 552, "loss": 0.7649, "learning_rate": 3.738593736828426e-07, "epoch": 1.7591339648173205, "percentage": 58.88, "elapsed_time": "1:20:05", "remaining_time": "0:55:56"}
+{"current_steps": 330, "total_steps": 552, "loss": 0.7599, "learning_rate": 3.598922844103902e-07, "epoch": 1.7861975642760486, "percentage": 59.78, "elapsed_time": "1:21:11", "remaining_time": "0:54:36"}
+{"current_steps": 335, "total_steps": 552, "loss": 0.7498, "learning_rate": 3.4604286705664397e-07, "epoch": 1.8132611637347766, "percentage": 60.69, "elapsed_time": "1:22:16", "remaining_time": "0:53:17"}
+{"current_steps": 340, "total_steps": 552, "loss": 0.7689, "learning_rate": 3.323227532973193e-07, "epoch": 1.8403247631935047, "percentage": 61.59, "elapsed_time": "1:23:22", "remaining_time": "0:51:59"}
+{"current_steps": 345, "total_steps": 552, "loss": 0.7727, "learning_rate": 3.187434662102434e-07, "epoch": 1.8673883626522327, "percentage": 62.5, "elapsed_time": "1:24:27", "remaining_time": "0:50:40"}
+{"current_steps": 350, "total_steps": 552, "loss": 0.768, "learning_rate": 3.0531641059749634e-07, "epoch": 1.8944519621109608, "percentage": 63.41, "elapsed_time": "1:25:32", "remaining_time": "0:49:22"}
+{"current_steps": 350, "total_steps": 552, "eval_loss": 0.810582160949707, "epoch": 1.8944519621109608, "percentage": 63.41, "elapsed_time": "1:27:05", "remaining_time": "0:50:15"}
+{"current_steps": 355, "total_steps": 552, "loss": 0.7411, "learning_rate": 2.920528634068885e-07, "epoch": 1.9215155615696888, "percentage": 64.31, "elapsed_time": "1:28:10", "remaining_time": "0:48:55"}
+{"current_steps": 360, "total_steps": 552, "loss": 0.7385, "learning_rate": 2.789639642608184e-07, "epoch": 1.9485791610284169, "percentage": 65.22, "elapsed_time": "1:29:15", "remaining_time": "0:47:36"}
+{"current_steps": 365, "total_steps": 552, "loss": 0.7573, "learning_rate": 2.6606070610046526e-07, "epoch": 1.975642760487145, "percentage": 66.12, "elapsed_time": "1:30:21", "remaining_time": "0:46:17"}
+{"current_steps": 370, "total_steps": 552, "loss": 0.7353, "learning_rate": 2.533539259531757e-07, "epoch": 2.002706359945873, "percentage": 67.03, "elapsed_time": "1:31:26", "remaining_time": "0:44:58"}
+{"current_steps": 375, "total_steps": 552, "loss": 0.7006, "learning_rate": 2.408542958307957e-07, "epoch": 2.029769959404601, "percentage": 67.93, "elapsed_time": "1:32:32", "remaining_time": "0:43:40"}
+{"current_steps": 380, "total_steps": 552, "loss": 0.7166, "learning_rate": 2.2857231376659514e-07, "epoch": 2.0568335588633286, "percentage": 68.84, "elapsed_time": "1:33:37", "remaining_time": "0:42:22"}
+{"current_steps": 385, "total_steps": 552, "loss": 0.7113, "learning_rate": 2.1651829499831043e-07, "epoch": 2.0838971583220567, "percentage": 69.75, "elapsed_time": "1:34:42", "remaining_time": "0:41:04"}
+{"current_steps": 390, "total_steps": 552, "loss": 0.709, "learning_rate": 2.0470236330471126e-07, "epoch": 2.1109607577807847, "percentage": 70.65, "elapsed_time": "1:35:48", "remaining_time": "0:39:47"}
+{"current_steps": 395, "total_steps": 552, "loss": 0.7132, "learning_rate": 1.9313444250296846e-07, "epoch": 2.138024357239513, "percentage": 71.56, "elapsed_time": "1:36:53", "remaining_time": "0:38:30"}
+{"current_steps": 400, "total_steps": 552, "loss": 0.7075, "learning_rate": 1.818242481139613e-07, "epoch": 2.165087956698241, "percentage": 72.46, "elapsed_time": "1:37:59", "remaining_time": "0:37:14"}
+{"current_steps": 400, "total_steps": 552, "eval_loss": 0.8137385249137878, "epoch": 2.165087956698241, "percentage": 72.46, "elapsed_time": "1:39:31", "remaining_time": "0:37:49"}
+{"current_steps": 405, "total_steps": 552, "loss": 0.7064, "learning_rate": 1.7078127920252783e-07, "epoch": 2.192151556156969, "percentage": 73.37, "elapsed_time": "1:40:36", "remaining_time": "0:36:30"}
+{"current_steps": 410, "total_steps": 552, "loss": 0.7055, "learning_rate": 1.600148103995087e-07, "epoch": 2.219215155615697, "percentage": 74.28, "elapsed_time": "1:41:41", "remaining_time": "0:35:13"}
+{"current_steps": 415, "total_steps": 552, "loss": 0.7147, "learning_rate": 1.4953388411228602e-07, "epoch": 2.246278755074425, "percentage": 75.18, "elapsed_time": "1:42:47", "remaining_time": "0:33:56"}
+{"current_steps": 420, "total_steps": 552, "loss": 0.6951, "learning_rate": 1.3934730293035936e-07, "epoch": 2.273342354533153, "percentage": 76.09, "elapsed_time": "1:43:52", "remaining_time": "0:32:38"}
+{"current_steps": 425, "total_steps": 552, "loss": 0.709, "learning_rate": 1.2946362223233614e-07, "epoch": 2.300405953991881, "percentage": 76.99, "elapsed_time": "1:44:57", "remaining_time": "0:31:21"}
+{"current_steps": 430, "total_steps": 552, "loss": 0.7197, "learning_rate": 1.198911430005478e-07, "epoch": 2.3274695534506087, "percentage": 77.9, "elapsed_time": "1:46:03", "remaining_time": "0:30:05"}
+{"current_steps": 435, "total_steps": 552, "loss": 0.7163, "learning_rate": 1.1063790484932462e-07, "epoch": 2.3545331529093367, "percentage": 78.8, "elapsed_time": "1:47:09", "remaining_time": "0:28:49"}
+{"current_steps": 440, "total_steps": 552, "loss": 0.6888, "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": 0.7105, "learning_rate": 9.311996311780446e-08, "epoch": 2.408660351826793, "percentage": 80.62, "elapsed_time": "1:49:19", "remaining_time": "0:26:17"}
+{"current_steps": 450, "total_steps": 552, "loss": 0.71, "learning_rate": 8.486997228767012e-08, "epoch": 2.435723951285521, "percentage": 81.52, "elapsed_time": "1:50:24", "remaining_time": "0:25:01"}
+{"current_steps": 450, "total_steps": 552, "eval_loss": 0.8126546144485474, "epoch": 2.435723951285521, "percentage": 81.52, "elapsed_time": "1:51:57", "remaining_time": "0:25:22"}
+{"current_steps": 455, "total_steps": 552, "loss": 0.6992, "learning_rate": 7.696863568166518e-08, "epoch": 2.462787550744249, "percentage": 82.43, "elapsed_time": "1:53:02", "remaining_time": "0:24:05"}
+{"current_steps": 460, "total_steps": 552, "loss": 0.6948, "learning_rate": 6.942258937571771e-08, "epoch": 2.489851150202977, "percentage": 83.33, "elapsed_time": "1:54:07", "remaining_time": "0:22:49"}
+{"current_steps": 465, "total_steps": 552, "loss": 0.6949, "learning_rate": 6.2238171048975e-08, "epoch": 2.516914749661705, "percentage": 84.24, "elapsed_time": "1:55:13", "remaining_time": "0:21:33"}
+{"current_steps": 470, "total_steps": 552, "loss": 0.733, "learning_rate": 5.5421414660992705e-08, "epoch": 2.543978349120433, "percentage": 85.14, "elapsed_time": "1:56:18", "remaining_time": "0:20:17"}
+{"current_steps": 475, "total_steps": 552, "loss": 0.7058, "learning_rate": 4.8978045384008125e-08, "epoch": 2.571041948579161, "percentage": 86.05, "elapsed_time": "1:57:24", "remaining_time": "0:19:01"}
+{"current_steps": 480, "total_steps": 552, "loss": 0.7229, "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": 0.6851, "learning_rate": 3.723279632845155e-08, "epoch": 2.6251691474966172, "percentage": 87.86, "elapsed_time": "1:59:34", "remaining_time": "0:16:31"}
+{"current_steps": 490, "total_steps": 552, "loss": 0.7011, "learning_rate": 3.194078100299863e-08, "epoch": 2.6522327469553453, "percentage": 88.77, "elapsed_time": "2:00:40", "remaining_time": "0:15:16"}
+{"current_steps": 495, "total_steps": 552, "loss": 0.6853, "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": 0.7069, "learning_rate": 2.2540187982637627e-08, "epoch": 2.706359945872801, "percentage": 90.58, "elapsed_time": "2:02:49", "remaining_time": "0:12:46"}
+{"current_steps": 500, "total_steps": 552, "eval_loss": 0.8118973970413208, "epoch": 2.706359945872801, "percentage": 90.58, "elapsed_time": "2:04:21", "remaining_time": "0:12:55"}
+{"current_steps": 505, "total_steps": 552, "loss": 0.7075, "learning_rate": 1.8439505540414458e-08, "epoch": 2.733423545331529, "percentage": 91.49, "elapsed_time": "2:05:26", "remaining_time": "0:11:40"}
+{"current_steps": 510, "total_steps": 552, "loss": 0.7051, "learning_rate": 1.4743270113244277e-08, "epoch": 2.760487144790257, "percentage": 92.39, "elapsed_time": "2:06:31", "remaining_time": "0:10:25"}
+{"current_steps": 515, "total_steps": 552, "loss": 0.6957, "learning_rate": 1.1454586049184589e-08, "epoch": 2.787550744248985, "percentage": 93.3, "elapsed_time": "2:07:37", "remaining_time": "0:09:10"}
+{"current_steps": 520, "total_steps": 552, "loss": 0.7189, "learning_rate": 8.576215407142651e-09, "epoch": 2.814614343707713, "percentage": 94.2, "elapsed_time": "2:08:42", "remaining_time": "0:07:55"}
+{"current_steps": 525, "total_steps": 552, "loss": 0.7245, "learning_rate": 6.110575637112425e-09, "epoch": 2.841677943166441, "percentage": 95.11, "elapsed_time": "2:09:48", "remaining_time": "0:06:40"}
+{"current_steps": 530, "total_steps": 552, "loss": 0.7008, "learning_rate": 4.059737549836517e-09, "epoch": 2.8687415426251692, "percentage": 96.01, "elapsed_time": "2:10:53", "remaining_time": "0:05:26"}
+{"current_steps": 535, "total_steps": 552, "loss": 0.7199, "learning_rate": 2.425423577599783e-09, "epoch": 2.8958051420838973, "percentage": 96.92, "elapsed_time": "2:11:59", "remaining_time": "0:04:11"}
+{"current_steps": 540, "total_steps": 552, "loss": 0.6992, "learning_rate": 1.209006327614226e-09, "epoch": 2.9228687415426253, "percentage": 97.83, "elapsed_time": "2:13:05", "remaining_time": "0:02:57"}
+{"current_steps": 545, "total_steps": 552, "loss": 0.7005, "learning_rate": 4.115074292109777e-10, "epoch": 2.949932341001353, "percentage": 98.73, "elapsed_time": "2:14:10", "remaining_time": "0:01:43"}
+{"current_steps": 550, "total_steps": 552, "loss": 0.7088, "learning_rate": 3.3596675806824013e-11, "epoch": 2.976995940460081, "percentage": 99.64, "elapsed_time": "2:15:15", "remaining_time": "0:00:29"}
+{"current_steps": 550, "total_steps": 552, "eval_loss": 0.8117214441299438, "epoch": 2.976995940460081, "percentage": 99.64, "elapsed_time": "2:16:47", "remaining_time": "0:00:29"}
+{"current_steps": 552, "total_steps": 552, "epoch": 2.9878213802435725, "percentage": 100.0, "elapsed_time": "2:17:45", "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": 18.82761565702094,
+      "learning_rate": 5e-07,
+      "loss": 1.734,
+      "step": 5
+    },
+    {
+      "epoch": 0.05412719891745602,
+      "grad_norm": 12.867825529466979,
+      "learning_rate": 1e-06,
+      "loss": 1.6027,
+      "step": 10
+    },
+    {
+      "epoch": 0.08119079837618404,
+      "grad_norm": 7.146838469131762,
+      "learning_rate": 9.997900331216397e-07,
+      "loss": 1.2943,
+      "step": 15
+    },
+    {
+      "epoch": 0.10825439783491204,
+      "grad_norm": 4.096985428996853,
+      "learning_rate": 9.991603088309193e-07,
+      "loss": 1.1214,
+      "step": 20
+    },
+    {
+      "epoch": 0.13531799729364005,
+      "grad_norm": 4.030931956641265,
+      "learning_rate": 9.981113560128126e-07,
+      "loss": 1.0701,
+      "step": 25
+    },
+    {
+      "epoch": 0.16238159675236807,
+      "grad_norm": 3.9631259966731793,
+      "learning_rate": 9.966440556487147e-07,
+      "loss": 1.0514,
+      "step": 30
+    },
+    {
+      "epoch": 0.18944519621109607,
+      "grad_norm": 3.7182444654950806,
+      "learning_rate": 9.947596400765342e-07,
+      "loss": 0.9816,
+      "step": 35
+    },
+    {
+      "epoch": 0.2165087956698241,
+      "grad_norm": 3.8553362221283574,
+      "learning_rate": 9.924596919556916e-07,
+      "loss": 0.9671,
+      "step": 40
+    },
+    {
+      "epoch": 0.2435723951285521,
+      "grad_norm": 3.48008462855318,
+      "learning_rate": 9.897461429378964e-07,
+      "loss": 0.9488,
+      "step": 45
+    },
+    {
+      "epoch": 0.2706359945872801,
+      "grad_norm": 3.5713771414265274,
+      "learning_rate": 9.866212720448147e-07,
+      "loss": 0.9428,
+      "step": 50
+    },
+    {
+      "epoch": 0.2706359945872801,
+      "eval_loss": 0.9270144701004028,
+      "eval_runtime": 93.2201,
+      "eval_samples_per_second": 56.318,
+      "eval_steps_per_second": 0.89,
+      "step": 50
+    },
+    {
+      "epoch": 0.2976995940460081,
+      "grad_norm": 3.5829158119832303,
+      "learning_rate": 9.830877037539935e-07,
+      "loss": 0.9318,
+      "step": 55
+    },
+    {
+      "epoch": 0.32476319350473615,
+      "grad_norm": 3.4021832899344626,
+      "learning_rate": 9.791484057946465e-07,
+      "loss": 0.9079,
+      "step": 60
+    },
+    {
+      "epoch": 0.35182679296346414,
+      "grad_norm": 3.391325595052156,
+      "learning_rate": 9.748066866551555e-07,
+      "loss": 0.8999,
+      "step": 65
+    },
+    {
+      "epoch": 0.37889039242219213,
+      "grad_norm": 3.515379759871202,
+      "learning_rate": 9.700661928043785e-07,
+      "loss": 0.9047,
+      "step": 70
+    },
+    {
+      "epoch": 0.4059539918809202,
+      "grad_norm": 3.44913794411675,
+      "learning_rate": 9.649309056290984e-07,
+      "loss": 0.8954,
+      "step": 75
+    },
+    {
+      "epoch": 0.4330175913396482,
+      "grad_norm": 3.5207352414980435,
+      "learning_rate": 9.594051380901858e-07,
+      "loss": 0.8984,
+      "step": 80
+    },
+    {
+      "epoch": 0.46008119079837617,
+      "grad_norm": 3.7404288010932287,
+      "learning_rate": 9.534935311002834e-07,
+      "loss": 0.9018,
+      "step": 85
+    },
+    {
+      "epoch": 0.4871447902571042,
+      "grad_norm": 3.435250970708313,
+      "learning_rate": 9.472010496260544e-07,
+      "loss": 0.888,
+      "step": 90
+    },
+    {
+      "epoch": 0.5142083897158322,
+      "grad_norm": 3.5926141044891455,
+      "learning_rate": 9.405329785182678e-07,
+      "loss": 0.8828,
+      "step": 95
+    },
+    {
+      "epoch": 0.5412719891745602,
+      "grad_norm": 3.8742294578209013,
+      "learning_rate": 9.334949180732244e-07,
+      "loss": 0.8747,
+      "step": 100
+    },
+    {
+      "epoch": 0.5412719891745602,
+      "eval_loss": 0.8708707690238953,
+      "eval_runtime": 92.2649,
+      "eval_samples_per_second": 56.901,
+      "eval_steps_per_second": 0.9,
+      "step": 100
+    },
+    {
+      "epoch": 0.5683355886332883,
+      "grad_norm": 3.592933241886934,
+      "learning_rate": 9.260927793292497e-07,
+      "loss": 0.8665,
+      "step": 105
+    },
+    {
+      "epoch": 0.5953991880920162,
+      "grad_norm": 3.5073835258263855,
+      "learning_rate": 9.183327791022047e-07,
+      "loss": 0.8528,
+      "step": 110
+    },
+    {
+      "epoch": 0.6224627875507442,
+      "grad_norm": 3.460111360598304,
+      "learning_rate": 9.102214347641843e-07,
+      "loss": 0.8865,
+      "step": 115
+    },
+    {
+      "epoch": 0.6495263870094723,
+      "grad_norm": 3.3741983776754854,
+      "learning_rate": 9.017655587697883e-07,
+      "loss": 0.8648,
+      "step": 120
+    },
+    {
+      "epoch": 0.6765899864682002,
+      "grad_norm": 3.5787989483258675,
+      "learning_rate": 8.929722529345623e-07,
+      "loss": 0.8484,
+      "step": 125
+    },
+    {
+      "epoch": 0.7036535859269283,
+      "grad_norm": 3.532632305089824,
+      "learning_rate": 8.83848902470413e-07,
+      "loss": 0.8496,
+      "step": 130
+    },
+    {
+      "epoch": 0.7307171853856563,
+      "grad_norm": 3.800249509395461,
+      "learning_rate": 8.744031697830088e-07,
+      "loss": 0.8592,
+      "step": 135
+    },
+    {
+      "epoch": 0.7577807848443843,
+      "grad_norm": 3.471168235847642,
+      "learning_rate": 8.646429880363746e-07,
+      "loss": 0.8624,
+      "step": 140
+    },
+    {
+      "epoch": 0.7848443843031123,
+      "grad_norm": 3.220664028161556,
+      "learning_rate": 8.545765544900846e-07,
+      "loss": 0.8516,
+      "step": 145
+    },
+    {
+      "epoch": 0.8119079837618404,
+      "grad_norm": 3.5792636736018637,
+      "learning_rate": 8.442123236146508e-07,
+      "loss": 0.8698,
+      "step": 150
+    },
+    {
+      "epoch": 0.8119079837618404,
+      "eval_loss": 0.8459715247154236,
+      "eval_runtime": 92.3333,
+      "eval_samples_per_second": 56.859,
+      "eval_steps_per_second": 0.899,
+      "step": 150
+    },
+    {
+      "epoch": 0.8389715832205683,
+      "grad_norm": 3.6444829594963184,
+      "learning_rate": 8.33558999990887e-07,
+      "loss": 0.844,
+      "step": 155
+    },
+    {
+      "epoch": 0.8660351826792964,
+      "grad_norm": 3.619543017726238,
+      "learning_rate": 8.22625530999215e-07,
+      "loss": 0.829,
+      "step": 160
+    },
+    {
+      "epoch": 0.8930987821380244,
+      "grad_norm": 3.4305250980444866,
+      "learning_rate": 8.114210993050502e-07,
+      "loss": 0.859,
+      "step": 165
+    },
+    {
+      "epoch": 0.9201623815967523,
+      "grad_norm": 3.4515883823343816,
+      "learning_rate": 7.999551151465791e-07,
+      "loss": 0.8373,
+      "step": 170
+    },
+    {
+      "epoch": 0.9472259810554804,
+      "grad_norm": 3.4061397273113494,
+      "learning_rate": 7.88237208431406e-07,
+      "loss": 0.8301,
+      "step": 175
+    },
+    {
+      "epoch": 0.9742895805142084,
+      "grad_norm": 3.450097547042426,
+      "learning_rate": 7.762772206487065e-07,
+      "loss": 0.824,
+      "step": 180
+    },
+    {
+      "epoch": 1.0013531799729365,
+      "grad_norm": 3.7734602033825495,
+      "learning_rate": 7.640851966036805e-07,
+      "loss": 0.8525,
+      "step": 185
+    },
+    {
+      "epoch": 1.0284167794316643,
+      "grad_norm": 3.540725853109944,
+      "learning_rate": 7.516713759812464e-07,
+      "loss": 0.778,
+      "step": 190
+    },
+    {
+      "epoch": 1.0554803788903924,
+      "grad_norm": 3.5399554970338456,
+      "learning_rate": 7.390461847460628e-07,
+      "loss": 0.7658,
+      "step": 195
+    },
+    {
+      "epoch": 1.0825439783491204,
+      "grad_norm": 3.6301828104234843,
+      "learning_rate": 7.262202263860988e-07,
+      "loss": 0.7652,
+      "step": 200
+    },
+    {
+      "epoch": 1.0825439783491204,
+      "eval_loss": 0.833743155002594,
+      "eval_runtime": 92.2579,
+      "eval_samples_per_second": 56.906,
+      "eval_steps_per_second": 0.9,
+      "step": 200
+    },
+    {
+      "epoch": 1.1096075778078485,
+      "grad_norm": 3.458697572657953,
+      "learning_rate": 7.1320427300711e-07,
+      "loss": 0.7688,
+      "step": 205
+    },
+    {
+      "epoch": 1.1366711772665765,
+      "grad_norm": 3.48579357869599,
+      "learning_rate": 7.000092562854959e-07,
+      "loss": 0.762,
+      "step": 210
+    },
+    {
+      "epoch": 1.1637347767253043,
+      "grad_norm": 3.364903450939617,
+      "learning_rate": 6.866462582871401e-07,
+      "loss": 0.7764,
+      "step": 215
+    },
+    {
+      "epoch": 1.1907983761840324,
+      "grad_norm": 3.6608165573448352,
+      "learning_rate": 6.731265021599436e-07,
+      "loss": 0.772,
+      "step": 220
+    },
+    {
+      "epoch": 1.2178619756427604,
+      "grad_norm": 3.3685745523262587,
+      "learning_rate": 6.594613427078674e-07,
+      "loss": 0.7738,
+      "step": 225
+    },
+    {
+      "epoch": 1.2449255751014885,
+      "grad_norm": 3.8004909414967263,
+      "learning_rate": 6.456622568544011e-07,
+      "loss": 0.78,
+      "step": 230
+    },
+    {
+      "epoch": 1.2719891745602165,
+      "grad_norm": 3.507999447214229,
+      "learning_rate": 6.317408340034684e-07,
+      "loss": 0.7832,
+      "step": 235
+    },
+    {
+      "epoch": 1.2990527740189446,
+      "grad_norm": 3.622195105708189,
+      "learning_rate": 6.177087663058625e-07,
+      "loss": 0.776,
+      "step": 240
+    },
+    {
+      "epoch": 1.3261163734776726,
+      "grad_norm": 3.5978192394759616,
+      "learning_rate": 6.035778388393893e-07,
+      "loss": 0.7556,
+      "step": 245
+    },
+    {
+      "epoch": 1.3531799729364005,
+      "grad_norm": 3.3885549115018554,
+      "learning_rate": 5.893599197109624e-07,
+      "loss": 0.7822,
+      "step": 250
+    },
+    {
+      "epoch": 1.3531799729364005,
+      "eval_loss": 0.8234151005744934,
+      "eval_runtime": 92.2768,
+      "eval_samples_per_second": 56.894,
+      "eval_steps_per_second": 0.899,
+      "step": 250
+    },
+    {
+      "epoch": 1.3802435723951285,
+      "grad_norm": 3.6453760206706898,
+      "learning_rate": 5.750669500889666e-07,
+      "loss": 0.7841,
+      "step": 255
+    },
+    {
+      "epoch": 1.4073071718538566,
+      "grad_norm": 3.6248461961460254,
+      "learning_rate": 5.607109341742578e-07,
+      "loss": 0.7684,
+      "step": 260
+    },
+    {
+      "epoch": 1.4343707713125846,
+      "grad_norm": 3.482156523315791,
+      "learning_rate": 5.463039291182256e-07,
+      "loss": 0.7704,
+      "step": 265
+    },
+    {
+      "epoch": 1.4614343707713127,
+      "grad_norm": 3.402395974373717,
+      "learning_rate": 5.318580348963825e-07,
+      "loss": 0.749,
+      "step": 270
+    },
+    {
+      "epoch": 1.4884979702300405,
+      "grad_norm": 3.6300127193307237,
+      "learning_rate": 5.173853841459877e-07,
+      "loss": 0.7643,
+      "step": 275
+    },
+    {
+      "epoch": 1.5155615696887685,
+      "grad_norm": 3.699178765966641,
+      "learning_rate": 5.028981319762399e-07,
+      "loss": 0.7564,
+      "step": 280
+    },
+    {
+      "epoch": 1.5426251691474966,
+      "grad_norm": 3.7257683305221967,
+      "learning_rate": 4.884084457595956e-07,
+      "loss": 0.7512,
+      "step": 285
+    },
+    {
+      "epoch": 1.5696887686062246,
+      "grad_norm": 3.443950941720584,
+      "learning_rate": 4.7392849491278817e-07,
+      "loss": 0.7729,
+      "step": 290
+    },
+    {
+      "epoch": 1.5967523680649527,
+      "grad_norm": 3.485674476973515,
+      "learning_rate": 4.5947044067613e-07,
+      "loss": 0.7479,
+      "step": 295
+    },
+    {
+      "epoch": 1.6238159675236807,
+      "grad_norm": 3.6693587030820574,
+      "learning_rate": 4.4504642589968217e-07,
+      "loss": 0.7628,
+      "step": 300
+    },
+    {
+      "epoch": 1.6238159675236807,
+      "eval_loss": 0.816413402557373,
+      "eval_runtime": 92.3489,
+      "eval_samples_per_second": 56.85,
+      "eval_steps_per_second": 0.899,
+      "step": 300
+    },
+    {
+      "epoch": 1.6508795669824088,
+      "grad_norm": 3.6447287635482084,
+      "learning_rate": 4.3066856484486847e-07,
+      "loss": 0.7534,
+      "step": 305
+    },
+    {
+      "epoch": 1.6779431664411368,
+      "grad_norm": 3.643734092885536,
+      "learning_rate": 4.1634893301010165e-07,
+      "loss": 0.7607,
+      "step": 310
+    },
+    {
+      "epoch": 1.7050067658998647,
+      "grad_norm": 3.6916619314799797,
+      "learning_rate": 4.0209955698896445e-07,
+      "loss": 0.7514,
+      "step": 315
+    },
+    {
+      "epoch": 1.7320703653585927,
+      "grad_norm": 3.6681332975803977,
+      "learning_rate": 3.8793240436946385e-07,
+      "loss": 0.7597,
+      "step": 320
+    },
+    {
+      "epoch": 1.7591339648173205,
+      "grad_norm": 3.6184885278786663,
+      "learning_rate": 3.738593736828426e-07,
+      "loss": 0.7649,
+      "step": 325
+    },
+    {
+      "epoch": 1.7861975642760486,
+      "grad_norm": 3.737975444433867,
+      "learning_rate": 3.598922844103902e-07,
+      "loss": 0.7599,
+      "step": 330
+    },
+    {
+      "epoch": 1.8132611637347766,
+      "grad_norm": 3.456980655495973,
+      "learning_rate": 3.4604286705664397e-07,
+      "loss": 0.7498,
+      "step": 335
+    },
+    {
+      "epoch": 1.8403247631935047,
+      "grad_norm": 3.479321682385595,
+      "learning_rate": 3.323227532973193e-07,
+      "loss": 0.7689,
+      "step": 340
+    },
+    {
+      "epoch": 1.8673883626522327,
+      "grad_norm": 3.670587230199258,
+      "learning_rate": 3.187434662102434e-07,
+      "loss": 0.7727,
+      "step": 345
+    },
+    {
+      "epoch": 1.8944519621109608,
+      "grad_norm": 3.659280365639458,
+      "learning_rate": 3.0531641059749634e-07,
+      "loss": 0.768,
+      "step": 350
+    },
+    {
+      "epoch": 1.8944519621109608,
+      "eval_loss": 0.810582160949707,
+      "eval_runtime": 92.3521,
+      "eval_samples_per_second": 56.848,
+      "eval_steps_per_second": 0.899,
+      "step": 350
+    },
+    {
+      "epoch": 1.9215155615696888,
+      "grad_norm": 3.515883526758233,
+      "learning_rate": 2.920528634068885e-07,
+      "loss": 0.7411,
+      "step": 355
+    },
+    {
+      "epoch": 1.9485791610284169,
+      "grad_norm": 3.5334817509226593,
+      "learning_rate": 2.789639642608184e-07,
+      "loss": 0.7385,
+      "step": 360
+    },
+    {
+      "epoch": 1.975642760487145,
+      "grad_norm": 3.698753767478549,
+      "learning_rate": 2.6606070610046526e-07,
+      "loss": 0.7573,
+      "step": 365
+    },
+    {
+      "epoch": 2.002706359945873,
+      "grad_norm": 3.3551617194703063,
+      "learning_rate": 2.533539259531757e-07,
+      "loss": 0.7353,
+      "step": 370
+    },
+    {
+      "epoch": 2.029769959404601,
+      "grad_norm": 3.6997168009784684,
+      "learning_rate": 2.408542958307957e-07,
+      "loss": 0.7006,
+      "step": 375
+    },
+    {
+      "epoch": 2.0568335588633286,
+      "grad_norm": 3.636840131305413,
+      "learning_rate": 2.2857231376659514e-07,
+      "loss": 0.7166,
+      "step": 380
+    },
+    {
+      "epoch": 2.0838971583220567,
+      "grad_norm": 3.972386455839474,
+      "learning_rate": 2.1651829499831043e-07,
+      "loss": 0.7113,
+      "step": 385
+    },
+    {
+      "epoch": 2.1109607577807847,
+      "grad_norm": 3.696729837743398,
+      "learning_rate": 2.0470236330471126e-07,
+      "loss": 0.709,
+      "step": 390
+    },
+    {
+      "epoch": 2.138024357239513,
+      "grad_norm": 3.7691871086231017,
+      "learning_rate": 1.9313444250296846e-07,
+      "loss": 0.7132,
+      "step": 395
+    },
+    {
+      "epoch": 2.165087956698241,
+      "grad_norm": 3.6764401143556014,
+      "learning_rate": 1.818242481139613e-07,
+      "loss": 0.7075,
+      "step": 400
+    },
+    {
+      "epoch": 2.165087956698241,
+      "eval_loss": 0.8137385249137878,
+      "eval_runtime": 92.2291,
+      "eval_samples_per_second": 56.923,
+      "eval_steps_per_second": 0.9,
+      "step": 400
+    },
+    {
+      "epoch": 2.192151556156969,
+      "grad_norm": 3.722594968646584,
+      "learning_rate": 1.7078127920252783e-07,
+      "loss": 0.7064,
+      "step": 405
+    },
+    {
+      "epoch": 2.219215155615697,
+      "grad_norm": 3.9827901528666434,
+      "learning_rate": 1.600148103995087e-07,
+      "loss": 0.7055,
+      "step": 410
+    },
+    {
+      "epoch": 2.246278755074425,
+      "grad_norm": 3.848365017568979,
+      "learning_rate": 1.4953388411228602e-07,
+      "loss": 0.7147,
+      "step": 415
+    },
+    {
+      "epoch": 2.273342354533153,
+      "grad_norm": 3.813956302279095,
+      "learning_rate": 1.3934730293035936e-07,
+      "loss": 0.6951,
+      "step": 420
+    },
+    {
+      "epoch": 2.300405953991881,
+      "grad_norm": 3.816112318327775,
+      "learning_rate": 1.2946362223233614e-07,
+      "loss": 0.709,
+      "step": 425
+    },
+    {
+      "epoch": 2.3274695534506087,
+      "grad_norm": 3.9531391193741667,
+      "learning_rate": 1.198911430005478e-07,
+      "loss": 0.7197,
+      "step": 430
+    },
+    {
+      "epoch": 2.3545331529093367,
+      "grad_norm": 3.9313649848564913,
+      "learning_rate": 1.1063790484932462e-07,
+      "loss": 0.7163,
+      "step": 435
+    },
+    {
+      "epoch": 2.381596752368065,
+      "grad_norm": 3.7946532677122455,
+      "learning_rate": 1.0171167927278368e-07,
+      "loss": 0.6888,
+      "step": 440
+    },
+    {
+      "epoch": 2.408660351826793,
+      "grad_norm": 3.6866229175987737,
+      "learning_rate": 9.311996311780446e-08,
+      "loss": 0.7105,
+      "step": 445
+    },
+    {
+      "epoch": 2.435723951285521,
+      "grad_norm": 3.6331365766503136,
+      "learning_rate": 8.486997228767012e-08,
+      "loss": 0.71,
+      "step": 450
+    },
+    {
+      "epoch": 2.435723951285521,
+      "eval_loss": 0.8126546144485474,
+      "eval_runtime": 92.1857,
+      "eval_samples_per_second": 56.95,
+      "eval_steps_per_second": 0.9,
+      "step": 450
+    },
+    {
+      "epoch": 2.462787550744249,
+      "grad_norm": 3.81903858751765,
+      "learning_rate": 7.696863568166518e-08,
+      "loss": 0.6992,
+      "step": 455
+    },
+    {
+      "epoch": 2.489851150202977,
+      "grad_norm": 3.8485837389475273,
+      "learning_rate": 6.942258937571771e-08,
+      "loss": 0.6948,
+      "step": 460
+    },
+    {
+      "epoch": 2.516914749661705,
+      "grad_norm": 3.7712141765804583,
+      "learning_rate": 6.2238171048975e-08,
+      "loss": 0.6949,
+      "step": 465
+    },
+    {
+      "epoch": 2.543978349120433,
+      "grad_norm": 3.584093640205327,
+      "learning_rate": 5.5421414660992705e-08,
+      "loss": 0.733,
+      "step": 470
+    },
+    {
+      "epoch": 2.571041948579161,
+      "grad_norm": 3.864716126183329,
+      "learning_rate": 4.8978045384008125e-08,
+      "loss": 0.7058,
+      "step": 475
+    },
+    {
+      "epoch": 2.598105548037889,
+      "grad_norm": 4.221053360392504,
+      "learning_rate": 4.2913474794554036e-08,
+      "loss": 0.7229,
+      "step": 480
+    },
+    {
+      "epoch": 2.6251691474966172,
+      "grad_norm": 3.7216448526253267,
+      "learning_rate": 3.723279632845155e-08,
+      "loss": 0.6851,
+      "step": 485
+    },
+    {
+      "epoch": 2.6522327469553453,
+      "grad_norm": 3.714335585514238,
+      "learning_rate": 3.194078100299863e-08,
+      "loss": 0.7011,
+      "step": 490
+    },
+    {
+      "epoch": 2.6792963464140733,
+      "grad_norm": 3.822561595275015,
+      "learning_rate": 2.7041873409947734e-08,
+      "loss": 0.6853,
+      "step": 495
+    },
+    {
+      "epoch": 2.706359945872801,
+      "grad_norm": 3.626297678435798,
+      "learning_rate": 2.2540187982637627e-08,
+      "loss": 0.7069,
+      "step": 500
+    },
+    {
+      "epoch": 2.706359945872801,
+      "eval_loss": 0.8118973970413208,
+      "eval_runtime": 92.3179,
+      "eval_samples_per_second": 56.869,
+      "eval_steps_per_second": 0.899,
+      "step": 500
+    },
+    {
+      "epoch": 2.733423545331529,
+      "grad_norm": 3.6886544451935412,
+      "learning_rate": 1.8439505540414458e-08,
+      "loss": 0.7075,
+      "step": 505
+    },
+    {
+      "epoch": 2.760487144790257,
+      "grad_norm": 3.9389896132103237,
+      "learning_rate": 1.4743270113244277e-08,
+      "loss": 0.7051,
+      "step": 510
+    },
+    {
+      "epoch": 2.787550744248985,
+      "grad_norm": 3.803689145741291,
+      "learning_rate": 1.1454586049184589e-08,
+      "loss": 0.6957,
+      "step": 515
+    },
+    {
+      "epoch": 2.814614343707713,
+      "grad_norm": 3.7647580840059702,
+      "learning_rate": 8.576215407142651e-09,
+      "loss": 0.7189,
+      "step": 520
+    },
+    {
+      "epoch": 2.841677943166441,
+      "grad_norm": 3.731265168222702,
+      "learning_rate": 6.110575637112425e-09,
+      "loss": 0.7245,
+      "step": 525
+    },
+    {
+      "epoch": 2.8687415426251692,
+      "grad_norm": 3.6148858260407883,
+      "learning_rate": 4.059737549836517e-09,
+      "loss": 0.7008,
+      "step": 530
+    },
+    {
+      "epoch": 2.8958051420838973,
+      "grad_norm": 4.036765550791644,
+      "learning_rate": 2.425423577599783e-09,
+      "loss": 0.7199,
+      "step": 535
+    },
+    {
+      "epoch": 2.9228687415426253,
+      "grad_norm": 3.8323701179806386,
+      "learning_rate": 1.209006327614226e-09,
+      "loss": 0.6992,
+      "step": 540
+    },
+    {
+      "epoch": 2.949932341001353,
+      "grad_norm": 3.7653155106882643,
+      "learning_rate": 4.115074292109777e-10,
+      "loss": 0.7005,
+      "step": 545
+    },
+    {
+      "epoch": 2.976995940460081,
+      "grad_norm": 3.9157330059593396,
+      "learning_rate": 3.3596675806824013e-11,
+      "loss": 0.7088,
+      "step": 550
+    },
+    {
+      "epoch": 2.976995940460081,
+      "eval_loss": 0.8117214441299438,
+      "eval_runtime": 92.3355,
+      "eval_samples_per_second": 56.858,
+      "eval_steps_per_second": 0.899,
+      "step": 550
+    },
+    {
+      "epoch": 2.9878213802435725,
+      "step": 552,
+      "total_flos": 3254608239525888.0,
+      "train_loss": 0.8072819815597673,
+      "train_runtime": 8267.6947,
+      "train_samples_per_second": 17.145,
+      "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 sha256:9fad150427f989d754e18a08ef735dc3cf3ec692c4a1d279454c06def33eab54
+size 7096