Upload folder using huggingface_hub

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: other
+base_model: llava-hf/llava-v1.6-mistral-7b-hf
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Compcap_cooccur_0_60
+  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_cooccur_0_60
+
+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_cooccur_0_60 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8070
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9196        | 0.2257 | 50   | 0.9317          |
+| 0.8737        | 0.4515 | 100  | 0.8765          |
+| 0.8557        | 0.6772 | 150  | 0.8530          |
+| 0.8242        | 0.9029 | 200  | 0.8354          |
+| 0.7715        | 1.1287 | 250  | 0.8278          |
+| 0.7752        | 1.3544 | 300  | 0.8197          |
+| 0.7359        | 1.5801 | 350  | 0.8135          |
+| 0.7467        | 1.8059 | 400  | 0.8078          |
+| 0.7024        | 2.0316 | 450  | 0.8078          |
+| 0.6984        | 2.2573 | 500  | 0.8086          |
+| 0.7063        | 2.4831 | 550  | 0.8080          |
+| 0.6873        | 2.7088 | 600  | 0.8071          |
+| 0.7067        | 2.9345 | 650  | 0.8070          |
+
+
+### 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": 2.9932279909706545,
+    "eval_loss": 0.807015597820282,
+    "eval_runtime": 109.2718,
+    "eval_samples_per_second": 57.654,
+    "eval_steps_per_second": 0.906,
+    "total_flos": 3909114547666944.0,
+    "train_loss": 0.7958762821928228,
+    "train_runtime": 10129.4465,
+    "train_samples_per_second": 16.793,
+    "train_steps_per_second": 0.065
+}

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": 2.9932279909706545,
+    "eval_loss": 0.807015597820282,
+    "eval_runtime": 109.2718,
+    "eval_samples_per_second": 57.654,
+    "eval_steps_per_second": 0.906
+}

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 sha256:7c5a788d6a5683a2b201070641a3f2b10131275e599d31da4965cd18a22517ad
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3262df162112a935a76072b504d556ddde0e9e851d943f7e7627d3b46643963
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effe32b69022f8b0af2c08b70a1281163b62e6134f52479f4d2e8517fd39ecfd
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8ecd5ba0fad12378f0d17b05894b25765ec73f7a5794f51d0a85c0d58518042
+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": 2.9932279909706545,
+    "total_flos": 3909114547666944.0,
+    "train_loss": 0.7958762821928228,
+    "train_runtime": 10129.4465,
+    "train_samples_per_second": 16.793,
+    "train_steps_per_second": 0.065
+}

trainer_log.jsonl

@@ -0,0 +1,146 @@
+{"current_steps": 5, "total_steps": 663, "loss": 1.7281, "learning_rate": 5e-07, "epoch": 0.022573363431151242, "percentage": 0.75, "elapsed_time": "0:01:09", "remaining_time": "2:32:08"}
+{"current_steps": 10, "total_steps": 663, "loss": 1.5872, "learning_rate": 1e-06, "epoch": 0.045146726862302484, "percentage": 1.51, "elapsed_time": "0:02:14", "remaining_time": "2:26:12"}
+{"current_steps": 15, "total_steps": 663, "loss": 1.2742, "learning_rate": 9.998553453302385e-07, "epoch": 0.06772009029345373, "percentage": 2.26, "elapsed_time": "0:03:19", "remaining_time": "2:23:58"}
+{"current_steps": 20, "total_steps": 663, "loss": 1.1293, "learning_rate": 9.99421465020848e-07, "epoch": 0.09029345372460497, "percentage": 3.02, "elapsed_time": "0:04:25", "remaining_time": "2:22:16"}
+{"current_steps": 25, "total_steps": 663, "loss": 1.0773, "learning_rate": 9.9869861012308e-07, "epoch": 0.11286681715575621, "percentage": 3.77, "elapsed_time": "0:05:30", "remaining_time": "2:20:34"}
+{"current_steps": 30, "total_steps": 663, "loss": 1.0241, "learning_rate": 9.976871988942804e-07, "epoch": 0.13544018058690746, "percentage": 4.52, "elapsed_time": "0:06:36", "remaining_time": "2:19:21"}
+{"current_steps": 35, "total_steps": 663, "loss": 0.9907, "learning_rate": 9.963878165558785e-07, "epoch": 0.1580135440180587, "percentage": 5.28, "elapsed_time": "0:07:41", "remaining_time": "2:18:08"}
+{"current_steps": 40, "total_steps": 663, "loss": 0.9535, "learning_rate": 9.948012149547666e-07, "epoch": 0.18058690744920994, "percentage": 6.03, "elapsed_time": "0:08:47", "remaining_time": "2:16:49"}
+{"current_steps": 45, "total_steps": 663, "loss": 0.9562, "learning_rate": 9.929283121282675e-07, "epoch": 0.20316027088036118, "percentage": 6.79, "elapsed_time": "0:09:52", "remaining_time": "2:15:37"}
+{"current_steps": 50, "total_steps": 663, "loss": 0.9196, "learning_rate": 9.9077019177294e-07, "epoch": 0.22573363431151242, "percentage": 7.54, "elapsed_time": "0:10:57", "remaining_time": "2:14:25"}
+{"current_steps": 50, "total_steps": 663, "eval_loss": 0.9316988587379456, "epoch": 0.22573363431151242, "percentage": 7.54, "elapsed_time": "0:12:47", "remaining_time": "2:36:54"}
+{"current_steps": 55, "total_steps": 663, "loss": 0.9367, "learning_rate": 9.88328102617534e-07, "epoch": 0.24830699774266365, "percentage": 8.3, "elapsed_time": "0:13:52", "remaining_time": "2:33:26"}
+{"current_steps": 60, "total_steps": 663, "loss": 0.9275, "learning_rate": 9.856034577004504e-07, "epoch": 0.2708803611738149, "percentage": 9.05, "elapsed_time": "0:14:58", "remaining_time": "2:30:26"}
+{"current_steps": 65, "total_steps": 663, "loss": 0.919, "learning_rate": 9.82597833552132e-07, "epoch": 0.29345372460496616, "percentage": 9.8, "elapsed_time": "0:16:03", "remaining_time": "2:27:48"}
+{"current_steps": 70, "total_steps": 663, "loss": 0.9057, "learning_rate": 9.793129692828533e-07, "epoch": 0.3160270880361174, "percentage": 10.56, "elapsed_time": "0:17:09", "remaining_time": "2:25:21"}
+{"current_steps": 75, "total_steps": 663, "loss": 0.8901, "learning_rate": 9.757507655764384e-07, "epoch": 0.33860045146726864, "percentage": 11.31, "elapsed_time": "0:18:14", "remaining_time": "2:23:04"}
+{"current_steps": 80, "total_steps": 663, "loss": 0.9147, "learning_rate": 9.719132835904906e-07, "epoch": 0.3611738148984199, "percentage": 12.07, "elapsed_time": "0:19:20", "remaining_time": "2:20:57"}
+{"current_steps": 85, "total_steps": 663, "loss": 0.8819, "learning_rate": 9.678027437637677e-07, "epoch": 0.3837471783295711, "percentage": 12.82, "elapsed_time": "0:20:26", "remaining_time": "2:19:01"}
+{"current_steps": 90, "total_steps": 663, "loss": 0.8867, "learning_rate": 9.634215245313939e-07, "epoch": 0.40632054176072235, "percentage": 13.57, "elapsed_time": "0:21:32", "remaining_time": "2:17:09"}
+{"current_steps": 95, "total_steps": 663, "loss": 0.8809, "learning_rate": 9.587721609486543e-07, "epoch": 0.4288939051918736, "percentage": 14.33, "elapsed_time": "0:22:37", "remaining_time": "2:15:17"}
+{"current_steps": 100, "total_steps": 663, "loss": 0.8737, "learning_rate": 9.538573432241637e-07, "epoch": 0.45146726862302483, "percentage": 15.08, "elapsed_time": "0:23:42", "remaining_time": "2:13:28"}
+{"current_steps": 100, "total_steps": 663, "eval_loss": 0.8765010833740234, "epoch": 0.45146726862302483, "percentage": 15.08, "elapsed_time": "0:25:32", "remaining_time": "2:23:45"}
+{"current_steps": 105, "total_steps": 663, "loss": 0.885, "learning_rate": 9.486799151632612e-07, "epoch": 0.47404063205417607, "percentage": 15.84, "elapsed_time": "0:26:37", "remaining_time": "2:21:27"}
+{"current_steps": 110, "total_steps": 663, "loss": 0.8814, "learning_rate": 9.432428725225326e-07, "epoch": 0.4966139954853273, "percentage": 16.59, "elapsed_time": "0:27:42", "remaining_time": "2:19:17"}
+{"current_steps": 115, "total_steps": 663, "loss": 0.881, "learning_rate": 9.375493612764085e-07, "epoch": 0.5191873589164786, "percentage": 17.35, "elapsed_time": "0:28:48", "remaining_time": "2:17:14"}
+{"current_steps": 120, "total_steps": 663, "loss": 0.8572, "learning_rate": 9.316026757968454e-07, "epoch": 0.5417607223476298, "percentage": 18.1, "elapsed_time": "0:29:53", "remaining_time": "2:15:16"}
+{"current_steps": 125, "total_steps": 663, "loss": 0.8654, "learning_rate": 9.2540625694714e-07, "epoch": 0.5643340857787811, "percentage": 18.85, "elapsed_time": "0:30:59", "remaining_time": "2:13:22"}
+{"current_steps": 130, "total_steps": 663, "loss": 0.8603, "learning_rate": 9.189636900909817e-07, "epoch": 0.5869074492099323, "percentage": 19.61, "elapsed_time": "0:32:04", "remaining_time": "2:11:29"}
+{"current_steps": 135, "total_steps": 663, "loss": 0.8511, "learning_rate": 9.122787030178949e-07, "epoch": 0.6094808126410836, "percentage": 20.36, "elapsed_time": "0:33:09", "remaining_time": "2:09:42"}
+{"current_steps": 140, "total_steps": 663, "loss": 0.8622, "learning_rate": 9.053551637862692e-07, "epoch": 0.6320541760722348, "percentage": 21.12, "elapsed_time": "0:34:15", "remaining_time": "2:07:57"}
+{"current_steps": 145, "total_steps": 663, "loss": 0.8371, "learning_rate": 8.98197078485229e-07, "epoch": 0.654627539503386, "percentage": 21.87, "elapsed_time": "0:35:20", "remaining_time": "2:06:14"}
+{"current_steps": 150, "total_steps": 663, "loss": 0.8557, "learning_rate": 8.908085889166357e-07, "epoch": 0.6772009029345373, "percentage": 22.62, "elapsed_time": "0:36:25", "remaining_time": "2:04:34"}
+{"current_steps": 150, "total_steps": 663, "eval_loss": 0.8529915809631348, "epoch": 0.6772009029345373, "percentage": 22.62, "elapsed_time": "0:38:15", "remaining_time": "2:10:49"}
+{"current_steps": 155, "total_steps": 663, "loss": 0.8493, "learning_rate": 8.831939701985636e-07, "epoch": 0.6997742663656885, "percentage": 23.38, "elapsed_time": "0:39:20", "remaining_time": "2:08:56"}
+{"current_steps": 160, "total_steps": 663, "loss": 0.8561, "learning_rate": 8.75357628291637e-07, "epoch": 0.7223476297968398, "percentage": 24.13, "elapsed_time": "0:40:25", "remaining_time": "2:07:06"}
+{"current_steps": 165, "total_steps": 663, "loss": 0.8382, "learning_rate": 8.673040974496584e-07, "epoch": 0.744920993227991, "percentage": 24.89, "elapsed_time": "0:41:31", "remaining_time": "2:05:19"}
+{"current_steps": 170, "total_steps": 663, "loss": 0.8347, "learning_rate": 8.590380375960053e-07, "epoch": 0.7674943566591422, "percentage": 25.64, "elapsed_time": "0:42:36", "remaining_time": "2:03:34"}
+{"current_steps": 175, "total_steps": 663, "loss": 0.8421, "learning_rate": 8.505642316273111e-07, "epoch": 0.7900677200902935, "percentage": 26.4, "elapsed_time": "0:43:42", "remaining_time": "2:01:52"}
+{"current_steps": 180, "total_steps": 663, "loss": 0.8317, "learning_rate": 8.418875826459919e-07, "epoch": 0.8126410835214447, "percentage": 27.15, "elapsed_time": "0:44:47", "remaining_time": "2:00:11"}
+{"current_steps": 185, "total_steps": 663, "loss": 0.8407, "learning_rate": 8.330131111232201e-07, "epoch": 0.835214446952596, "percentage": 27.9, "elapsed_time": "0:45:53", "remaining_time": "1:58:34"}
+{"current_steps": 190, "total_steps": 663, "loss": 0.8539, "learning_rate": 8.239459519939851e-07, "epoch": 0.8577878103837472, "percentage": 28.66, "elapsed_time": "0:46:58", "remaining_time": "1:56:57"}
+{"current_steps": 195, "total_steps": 663, "loss": 0.8347, "learning_rate": 8.14691351685925e-07, "epoch": 0.8803611738148984, "percentage": 29.41, "elapsed_time": "0:48:04", "remaining_time": "1:55:23"}
+{"current_steps": 200, "total_steps": 663, "loss": 0.8242, "learning_rate": 8.052546650836453e-07, "epoch": 0.9029345372460497, "percentage": 30.17, "elapsed_time": "0:49:10", "remaining_time": "1:53:49"}
+{"current_steps": 200, "total_steps": 663, "eval_loss": 0.8354331254959106, "epoch": 0.9029345372460497, "percentage": 30.17, "elapsed_time": "0:50:59", "remaining_time": "1:58:02"}
+{"current_steps": 205, "total_steps": 663, "loss": 0.8204, "learning_rate": 7.956413524302823e-07, "epoch": 0.9255079006772009, "percentage": 30.92, "elapsed_time": "0:52:05", "remaining_time": "1:56:22"}
+{"current_steps": 210, "total_steps": 663, "loss": 0.8545, "learning_rate": 7.858569761681047e-07, "epoch": 0.9480812641083521, "percentage": 31.67, "elapsed_time": "0:53:10", "remaining_time": "1:54:41"}
+{"current_steps": 215, "total_steps": 663, "loss": 0.8431, "learning_rate": 7.759071977199806e-07, "epoch": 0.9706546275395034, "percentage": 32.43, "elapsed_time": "0:54:15", "remaining_time": "1:53:03"}
+{"current_steps": 220, "total_steps": 663, "loss": 0.8245, "learning_rate": 7.657977742135725e-07, "epoch": 0.9932279909706546, "percentage": 33.18, "elapsed_time": "0:55:20", "remaining_time": "1:51:25"}
+{"current_steps": 225, "total_steps": 663, "loss": 0.7956, "learning_rate": 7.555345551501557e-07, "epoch": 1.0158013544018059, "percentage": 33.94, "elapsed_time": "0:56:24", "remaining_time": "1:49:48"}
+{"current_steps": 230, "total_steps": 663, "loss": 0.7706, "learning_rate": 7.451234790199871e-07, "epoch": 1.0383747178329572, "percentage": 34.69, "elapsed_time": "0:57:30", "remaining_time": "1:48:15"}
+{"current_steps": 235, "total_steps": 663, "loss": 0.7521, "learning_rate": 7.345705698661852e-07, "epoch": 1.0609480812641083, "percentage": 35.44, "elapsed_time": "0:58:35", "remaining_time": "1:46:42"}
+{"current_steps": 240, "total_steps": 663, "loss": 0.7465, "learning_rate": 7.23881933799104e-07, "epoch": 1.0835214446952597, "percentage": 36.2, "elapsed_time": "0:59:40", "remaining_time": "1:45:10"}
+{"current_steps": 245, "total_steps": 663, "loss": 0.7727, "learning_rate": 7.130637554632257e-07, "epoch": 1.1060948081264108, "percentage": 36.95, "elapsed_time": "1:00:46", "remaining_time": "1:43:40"}
+{"current_steps": 250, "total_steps": 663, "loss": 0.7715, "learning_rate": 7.021222944586088e-07, "epoch": 1.1286681715575622, "percentage": 37.71, "elapsed_time": "1:01:51", "remaining_time": "1:42:11"}
+{"current_steps": 250, "total_steps": 663, "eval_loss": 0.8277800679206848, "epoch": 1.1286681715575622, "percentage": 37.71, "elapsed_time": "1:03:40", "remaining_time": "1:45:12"}
+{"current_steps": 255, "total_steps": 663, "loss": 0.7589, "learning_rate": 6.910638817189664e-07, "epoch": 1.1512415349887133, "percentage": 38.46, "elapsed_time": "1:04:46", "remaining_time": "1:43:37"}
+{"current_steps": 260, "total_steps": 663, "loss": 0.7784, "learning_rate": 6.798949158484705e-07, "epoch": 1.1738148984198646, "percentage": 39.22, "elapsed_time": "1:05:50", "remaining_time": "1:42:03"}
+{"current_steps": 265, "total_steps": 663, "loss": 0.7402, "learning_rate": 6.686218594193993e-07, "epoch": 1.1963882618510158, "percentage": 39.97, "elapsed_time": "1:06:56", "remaining_time": "1:40:32"}
+{"current_steps": 270, "total_steps": 663, "loss": 0.7759, "learning_rate": 6.572512352327726e-07, "epoch": 1.2189616252821671, "percentage": 40.72, "elapsed_time": "1:08:02", "remaining_time": "1:39:01"}
+{"current_steps": 275, "total_steps": 663, "loss": 0.7549, "learning_rate": 6.457896225441371e-07, "epoch": 1.2415349887133182, "percentage": 41.48, "elapsed_time": "1:09:07", "remaining_time": "1:37:32"}
+{"current_steps": 280, "total_steps": 663, "loss": 0.7564, "learning_rate": 6.342436532566865e-07, "epoch": 1.2641083521444696, "percentage": 42.23, "elapsed_time": "1:10:12", "remaining_time": "1:36:01"}
+{"current_steps": 285, "total_steps": 663, "loss": 0.7629, "learning_rate": 6.226200080839182e-07, "epoch": 1.2866817155756207, "percentage": 42.99, "elapsed_time": "1:11:17", "remaining_time": "1:34:33"}
+{"current_steps": 290, "total_steps": 663, "loss": 0.7531, "learning_rate": 6.109254126840479e-07, "epoch": 1.309255079006772, "percentage": 43.74, "elapsed_time": "1:12:23", "remaining_time": "1:33:06"}
+{"current_steps": 295, "total_steps": 663, "loss": 0.7572, "learning_rate": 5.991666337684176e-07, "epoch": 1.3318284424379232, "percentage": 44.49, "elapsed_time": "1:13:28", "remaining_time": "1:31:39"}
+{"current_steps": 300, "total_steps": 663, "loss": 0.7752, "learning_rate": 5.873504751861507e-07, "epoch": 1.3544018058690745, "percentage": 45.25, "elapsed_time": "1:14:33", "remaining_time": "1:30:12"}
+{"current_steps": 300, "total_steps": 663, "eval_loss": 0.819725513458252, "epoch": 1.3544018058690745, "percentage": 45.25, "elapsed_time": "1:16:23", "remaining_time": "1:32:25"}
+{"current_steps": 305, "total_steps": 663, "loss": 0.7622, "learning_rate": 5.754837739873178e-07, "epoch": 1.3769751693002257, "percentage": 46.0, "elapsed_time": "1:17:28", "remaining_time": "1:30:56"}
+{"current_steps": 310, "total_steps": 663, "loss": 0.7487, "learning_rate": 5.635733964668909e-07, "epoch": 1.399548532731377, "percentage": 46.76, "elapsed_time": "1:18:33", "remaining_time": "1:29:27"}
+{"current_steps": 315, "total_steps": 663, "loss": 0.7568, "learning_rate": 5.516262341917778e-07, "epoch": 1.4221218961625282, "percentage": 47.51, "elapsed_time": "1:19:39", "remaining_time": "1:28:00"}
+{"current_steps": 320, "total_steps": 663, "loss": 0.7584, "learning_rate": 5.396492000132325e-07, "epoch": 1.4446952595936795, "percentage": 48.27, "elapsed_time": "1:20:45", "remaining_time": "1:26:34"}
+{"current_steps": 325, "total_steps": 663, "loss": 0.7708, "learning_rate": 5.276492240669503e-07, "epoch": 1.4672686230248306, "percentage": 49.02, "elapsed_time": "1:21:50", "remaining_time": "1:25:06"}
+{"current_steps": 330, "total_steps": 663, "loss": 0.742, "learning_rate": 5.156332497631621e-07, "epoch": 1.489841986455982, "percentage": 49.77, "elapsed_time": "1:22:55", "remaining_time": "1:23:40"}
+{"current_steps": 335, "total_steps": 663, "loss": 0.7578, "learning_rate": 5.036082297690464e-07, "epoch": 1.5124153498871333, "percentage": 50.53, "elapsed_time": "1:24:01", "remaining_time": "1:22:15"}
+{"current_steps": 340, "total_steps": 663, "loss": 0.7542, "learning_rate": 4.915811219857882e-07, "epoch": 1.5349887133182845, "percentage": 51.28, "elapsed_time": "1:25:06", "remaining_time": "1:20:51"}
+{"current_steps": 345, "total_steps": 663, "loss": 0.7589, "learning_rate": 4.795588855226055e-07, "epoch": 1.5575620767494356, "percentage": 52.04, "elapsed_time": "1:26:11", "remaining_time": "1:19:27"}
+{"current_steps": 350, "total_steps": 663, "loss": 0.7359, "learning_rate": 4.6754847667008004e-07, "epoch": 1.580135440180587, "percentage": 52.79, "elapsed_time": "1:27:17", "remaining_time": "1:18:04"}
+{"current_steps": 350, "total_steps": 663, "eval_loss": 0.8135123252868652, "epoch": 1.580135440180587, "percentage": 52.79, "elapsed_time": "1:29:07", "remaining_time": "1:19:42"}
+{"current_steps": 355, "total_steps": 663, "loss": 0.7674, "learning_rate": 4.5555684487511693e-07, "epoch": 1.6027088036117383, "percentage": 53.54, "elapsed_time": "1:30:12", "remaining_time": "1:18:16"}
+{"current_steps": 360, "total_steps": 663, "loss": 0.7565, "learning_rate": 4.435909287198646e-07, "epoch": 1.6252821670428894, "percentage": 54.3, "elapsed_time": "1:31:18", "remaining_time": "1:16:51"}
+{"current_steps": 365, "total_steps": 663, "loss": 0.7578, "learning_rate": 4.316576519069226e-07, "epoch": 1.6478555304740405, "percentage": 55.05, "elapsed_time": "1:32:23", "remaining_time": "1:15:26"}
+{"current_steps": 370, "total_steps": 663, "loss": 0.7533, "learning_rate": 4.197639192531573e-07, "epoch": 1.670428893905192, "percentage": 55.81, "elapsed_time": "1:33:28", "remaining_time": "1:14:01"}
+{"current_steps": 375, "total_steps": 663, "loss": 0.7674, "learning_rate": 4.079166126944453e-07, "epoch": 1.6930022573363432, "percentage": 56.56, "elapsed_time": "1:34:34", "remaining_time": "1:12:37"}
+{"current_steps": 380, "total_steps": 663, "loss": 0.7355, "learning_rate": 3.9612258730365823e-07, "epoch": 1.7155756207674944, "percentage": 57.32, "elapsed_time": "1:35:39", "remaining_time": "1:11:14"}
+{"current_steps": 385, "total_steps": 663, "loss": 0.7512, "learning_rate": 3.843886673241883e-07, "epoch": 1.7381489841986455, "percentage": 58.07, "elapsed_time": "1:36:44", "remaining_time": "1:09:51"}
+{"current_steps": 390, "total_steps": 663, "loss": 0.7544, "learning_rate": 3.7272164222131387e-07, "epoch": 1.7607223476297968, "percentage": 58.82, "elapsed_time": "1:37:50", "remaining_time": "1:08:29"}
+{"current_steps": 395, "total_steps": 663, "loss": 0.7572, "learning_rate": 3.611282627536887e-07, "epoch": 1.7832957110609482, "percentage": 59.58, "elapsed_time": "1:38:56", "remaining_time": "1:07:07"}
+{"current_steps": 400, "total_steps": 663, "loss": 0.7467, "learning_rate": 3.496152370672255e-07, "epoch": 1.8058690744920993, "percentage": 60.33, "elapsed_time": "1:40:00", "remaining_time": "1:05:45"}
+{"current_steps": 400, "total_steps": 663, "eval_loss": 0.8077942132949829, "epoch": 1.8058690744920993, "percentage": 60.33, "elapsed_time": "1:41:50", "remaining_time": "1:06:57"}
+{"current_steps": 405, "total_steps": 663, "loss": 0.7387, "learning_rate": 3.381892268136392e-07, "epoch": 1.8284424379232505, "percentage": 61.09, "elapsed_time": "1:42:55", "remaining_time": "1:05:34"}
+{"current_steps": 410, "total_steps": 663, "loss": 0.7459, "learning_rate": 3.2685684329588956e-07, "epoch": 1.8510158013544018, "percentage": 61.84, "elapsed_time": "1:44:01", "remaining_time": "1:04:11"}
+{"current_steps": 415, "total_steps": 663, "loss": 0.755, "learning_rate": 3.1562464364275774e-07, "epoch": 1.8735891647855532, "percentage": 62.59, "elapsed_time": "1:45:07", "remaining_time": "1:02:49"}
+{"current_steps": 420, "total_steps": 663, "loss": 0.7485, "learning_rate": 3.044991270147699e-07, "epoch": 1.8961625282167043, "percentage": 63.35, "elapsed_time": "1:46:13", "remaining_time": "1:01:27"}
+{"current_steps": 425, "total_steps": 663, "loss": 0.7457, "learning_rate": 2.934867308436613e-07, "epoch": 1.9187358916478554, "percentage": 64.1, "elapsed_time": "1:47:18", "remaining_time": "1:00:05"}
+{"current_steps": 430, "total_steps": 663, "loss": 0.7456, "learning_rate": 2.825938271075572e-07, "epoch": 1.9413092550790068, "percentage": 64.86, "elapsed_time": "1:48:23", "remaining_time": "0:58:44"}
+{"current_steps": 435, "total_steps": 663, "loss": 0.7367, "learning_rate": 2.7182671864402856e-07, "epoch": 1.963882618510158, "percentage": 65.61, "elapsed_time": "1:49:28", "remaining_time": "0:57:22"}
+{"current_steps": 440, "total_steps": 663, "loss": 0.7605, "learning_rate": 2.6119163550315194e-07, "epoch": 1.9864559819413092, "percentage": 66.37, "elapsed_time": "1:50:34", "remaining_time": "0:56:02"}
+{"current_steps": 445, "total_steps": 663, "loss": 0.7443, "learning_rate": 2.506947313426854e-07, "epoch": 2.0090293453724604, "percentage": 67.12, "elapsed_time": "1:51:40", "remaining_time": "0:54:42"}
+{"current_steps": 450, "total_steps": 663, "loss": 0.7024, "learning_rate": 2.4034207986744847e-07, "epoch": 2.0316027088036117, "percentage": 67.87, "elapsed_time": "1:52:45", "remaining_time": "0:53:22"}
+{"current_steps": 450, "total_steps": 663, "eval_loss": 0.8078460097312927, "epoch": 2.0316027088036117, "percentage": 67.87, "elapsed_time": "1:54:34", "remaining_time": "0:54:14"}
+{"current_steps": 455, "total_steps": 663, "loss": 0.7042, "learning_rate": 2.301396713149627e-07, "epoch": 2.054176072234763, "percentage": 68.63, "elapsed_time": "1:55:40", "remaining_time": "0:52:52"}
+{"current_steps": 460, "total_steps": 663, "loss": 0.6819, "learning_rate": 2.2009340898938738e-07, "epoch": 2.0767494356659144, "percentage": 69.38, "elapsed_time": "1:56:46", "remaining_time": "0:51:31"}
+{"current_steps": 465, "total_steps": 663, "loss": 0.7138, "learning_rate": 2.1020910584575891e-07, "epoch": 2.0993227990970653, "percentage": 70.14, "elapsed_time": "1:57:51", "remaining_time": "0:50:11"}
+{"current_steps": 470, "total_steps": 663, "loss": 0.6967, "learning_rate": 2.0049248112650563e-07, "epoch": 2.1218961625282167, "percentage": 70.89, "elapsed_time": "1:58:56", "remaining_time": "0:48:50"}
+{"current_steps": 475, "total_steps": 663, "loss": 0.6911, "learning_rate": 1.9094915705218711e-07, "epoch": 2.144469525959368, "percentage": 71.64, "elapsed_time": "2:00:02", "remaining_time": "0:47:30"}
+{"current_steps": 480, "total_steps": 663, "loss": 0.6825, "learning_rate": 1.8158465556837304e-07, "epoch": 2.1670428893905194, "percentage": 72.4, "elapsed_time": "2:01:08", "remaining_time": "0:46:10"}
+{"current_steps": 485, "total_steps": 663, "loss": 0.6957, "learning_rate": 1.7240439515054218e-07, "epoch": 2.1896162528216703, "percentage": 73.15, "elapsed_time": "2:02:13", "remaining_time": "0:44:51"}
+{"current_steps": 490, "total_steps": 663, "loss": 0.7123, "learning_rate": 1.634136876688504e-07, "epoch": 2.2121896162528216, "percentage": 73.91, "elapsed_time": "2:03:18", "remaining_time": "0:43:32"}
+{"current_steps": 495, "total_steps": 663, "loss": 0.7014, "learning_rate": 1.5461773531458455e-07, "epoch": 2.234762979683973, "percentage": 74.66, "elapsed_time": "2:04:24", "remaining_time": "0:42:13"}
+{"current_steps": 500, "total_steps": 663, "loss": 0.6984, "learning_rate": 1.460216275900769e-07, "epoch": 2.2573363431151243, "percentage": 75.41, "elapsed_time": "2:05:29", "remaining_time": "0:40:54"}
+{"current_steps": 500, "total_steps": 663, "eval_loss": 0.8086156249046326, "epoch": 2.2573363431151243, "percentage": 75.41, "elapsed_time": "2:07:19", "remaining_time": "0:41:30"}
+{"current_steps": 505, "total_steps": 663, "loss": 0.6953, "learning_rate": 1.3763033836382392e-07, "epoch": 2.2799097065462752, "percentage": 76.17, "elapsed_time": "2:08:24", "remaining_time": "0:40:10"}
+{"current_steps": 510, "total_steps": 663, "loss": 0.7049, "learning_rate": 1.294487229925132e-07, "epoch": 2.3024830699774266, "percentage": 76.92, "elapsed_time": "2:09:30", "remaining_time": "0:38:51"}
+{"current_steps": 515, "total_steps": 663, "loss": 0.6996, "learning_rate": 1.2148151551162345e-07, "epoch": 2.325056433408578, "percentage": 77.68, "elapsed_time": "2:10:35", "remaining_time": "0:37:31"}
+{"current_steps": 520, "total_steps": 663, "loss": 0.7046, "learning_rate": 1.137333258962227e-07, "epoch": 2.3476297968397293, "percentage": 78.43, "elapsed_time": "2:11:40", "remaining_time": "0:36:12"}
+{"current_steps": 525, "total_steps": 663, "loss": 0.7038, "learning_rate": 1.0620863739355135e-07, "epoch": 2.37020316027088, "percentage": 79.19, "elapsed_time": "2:12:45", "remaining_time": "0:34:53"}
+{"current_steps": 530, "total_steps": 663, "loss": 0.684, "learning_rate": 9.891180392893117e-08, "epoch": 2.3927765237020315, "percentage": 79.94, "elapsed_time": "2:13:51", "remaining_time": "0:33:35"}
+{"current_steps": 535, "total_steps": 663, "loss": 0.7056, "learning_rate": 9.184704758650241e-08, "epoch": 2.415349887133183, "percentage": 80.69, "elapsed_time": "2:14:57", "remaining_time": "0:32:17"}
+{"current_steps": 540, "total_steps": 663, "loss": 0.6876, "learning_rate": 8.501845616624798e-08, "epoch": 2.4379232505643342, "percentage": 81.45, "elapsed_time": "2:16:02", "remaining_time": "0:30:59"}
+{"current_steps": 545, "total_steps": 663, "loss": 0.7139, "learning_rate": 7.842998081871493e-08, "epoch": 2.460496613995485, "percentage": 82.2, "elapsed_time": "2:17:06", "remaining_time": "0:29:41"}
+{"current_steps": 550, "total_steps": 663, "loss": 0.7063, "learning_rate": 7.208543375880594e-08, "epoch": 2.4830699774266365, "percentage": 82.96, "elapsed_time": "2:18:12", "remaining_time": "0:28:23"}
+{"current_steps": 550, "total_steps": 663, "eval_loss": 0.8080305457115173, "epoch": 2.4830699774266365, "percentage": 82.96, "elapsed_time": "2:20:01", "remaining_time": "0:28:46"}
+{"current_steps": 555, "total_steps": 663, "loss": 0.6922, "learning_rate": 6.598848605996004e-08, "epoch": 2.505643340857788, "percentage": 83.71, "elapsed_time": "2:21:06", "remaining_time": "0:27:27"}
+{"current_steps": 560, "total_steps": 663, "loss": 0.7121, "learning_rate": 6.014266553000074e-08, "epoch": 2.528216704288939, "percentage": 84.46, "elapsed_time": "2:22:11", "remaining_time": "0:26:09"}
+{"current_steps": 565, "total_steps": 663, "loss": 0.6944, "learning_rate": 5.4551354669881145e-08, "epoch": 2.55079006772009, "percentage": 85.22, "elapsed_time": "2:23:17", "remaining_time": "0:24:51"}
+{"current_steps": 570, "total_steps": 663, "loss": 0.703, "learning_rate": 4.921778871650539e-08, "epoch": 2.5733634311512414, "percentage": 85.97, "elapsed_time": "2:24:22", "remaining_time": "0:23:33"}
+{"current_steps": 575, "total_steps": 663, "loss": 0.692, "learning_rate": 4.414505377075978e-08, "epoch": 2.595936794582393, "percentage": 86.73, "elapsed_time": "2:25:27", "remaining_time": "0:22:15"}
+{"current_steps": 580, "total_steps": 663, "loss": 0.6901, "learning_rate": 3.933608501183788e-08, "epoch": 2.618510158013544, "percentage": 87.48, "elapsed_time": "2:26:33", "remaining_time": "0:20:58"}
+{"current_steps": 585, "total_steps": 663, "loss": 0.6997, "learning_rate": 3.479366499889058e-08, "epoch": 2.6410835214446955, "percentage": 88.24, "elapsed_time": "2:27:39", "remaining_time": "0:19:41"}
+{"current_steps": 590, "total_steps": 663, "loss": 0.6826, "learning_rate": 3.052042206098537e-08, "epoch": 2.6636568848758464, "percentage": 88.99, "elapsed_time": "2:28:44", "remaining_time": "0:18:24"}
+{"current_steps": 595, "total_steps": 663, "loss": 0.6909, "learning_rate": 2.6518828776306347e-08, "epoch": 2.6862302483069977, "percentage": 89.74, "elapsed_time": "2:29:49", "remaining_time": "0:17:07"}
+{"current_steps": 600, "total_steps": 663, "loss": 0.6873, "learning_rate": 2.279120054147393e-08, "epoch": 2.708803611738149, "percentage": 90.5, "elapsed_time": "2:30:55", "remaining_time": "0:15:50"}
+{"current_steps": 600, "total_steps": 663, "eval_loss": 0.80707848072052, "epoch": 2.708803611738149, "percentage": 90.5, "elapsed_time": "2:32:45", "remaining_time": "0:16:02"}
+{"current_steps": 605, "total_steps": 663, "loss": 0.6997, "learning_rate": 1.9339694231813252e-08, "epoch": 2.7313769751693, "percentage": 91.25, "elapsed_time": "2:33:50", "remaining_time": "0:14:44"}
+{"current_steps": 610, "total_steps": 663, "loss": 0.7078, "learning_rate": 1.616630695334592e-08, "epoch": 2.7539503386004514, "percentage": 92.01, "elapsed_time": "2:34:55", "remaining_time": "0:13:27"}
+{"current_steps": 615, "total_steps": 663, "loss": 0.6966, "learning_rate": 1.3272874887227281e-08, "epoch": 2.7765237020316027, "percentage": 92.76, "elapsed_time": "2:36:00", "remaining_time": "0:12:10"}
+{"current_steps": 620, "total_steps": 663, "loss": 0.7013, "learning_rate": 1.066107222729712e-08, "epoch": 2.799097065462754, "percentage": 93.51, "elapsed_time": "2:37:05", "remaining_time": "0:10:53"}
+{"current_steps": 625, "total_steps": 663, "loss": 0.7107, "learning_rate": 8.332410211360608e-09, "epoch": 2.8216704288939054, "percentage": 94.27, "elapsed_time": "2:38:10", "remaining_time": "0:09:37"}
+{"current_steps": 630, "total_steps": 663, "loss": 0.6907, "learning_rate": 6.288236246757284e-09, "epoch": 2.8442437923250563, "percentage": 95.02, "elapsed_time": "2:39:15", "remaining_time": "0:08:20"}
+{"current_steps": 635, "total_steps": 663, "loss": 0.7125, "learning_rate": 4.529733130726299e-09, "epoch": 2.8668171557562077, "percentage": 95.78, "elapsed_time": "2:40:21", "remaining_time": "0:07:04"}
+{"current_steps": 640, "total_steps": 663, "loss": 0.6974, "learning_rate": 3.0579183660177086e-09, "epoch": 2.889390519187359, "percentage": 96.53, "elapsed_time": "2:41:26", "remaining_time": "0:05:48"}
+{"current_steps": 645, "total_steps": 663, "loss": 0.695, "learning_rate": 1.8736435721465326e-09, "epoch": 2.91196388261851, "percentage": 97.29, "elapsed_time": "2:42:32", "remaining_time": "0:04:32"}
+{"current_steps": 650, "total_steps": 663, "loss": 0.7067, "learning_rate": 9.775939926296439e-10, "epoch": 2.9345372460496613, "percentage": 98.04, "elapsed_time": "2:43:37", "remaining_time": "0:03:16"}
+{"current_steps": 650, "total_steps": 663, "eval_loss": 0.8069904446601868, "epoch": 2.9345372460496613, "percentage": 98.04, "elapsed_time": "2:45:27", "remaining_time": "0:03:18"}
+{"current_steps": 655, "total_steps": 663, "loss": 0.705, "learning_rate": 3.7028809849098954e-10, "epoch": 2.9571106094808126, "percentage": 98.79, "elapsed_time": "2:46:32", "remaining_time": "0:02:02"}
+{"current_steps": 660, "total_steps": 663, "loss": 0.6905, "learning_rate": 5.2077288264951166e-11, "epoch": 2.979683972911964, "percentage": 99.55, "elapsed_time": "2:47:38", "remaining_time": "0:00:45"}
+{"current_steps": 663, "total_steps": 663, "epoch": 2.9932279909706545, "percentage": 100.0, "elapsed_time": "2:48:47", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1070 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9932279909706545,
+  "eval_steps": 50,
+  "global_step": 663,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022573363431151242,
+      "grad_norm": 18.10373149143315,
+      "learning_rate": 5e-07,
+      "loss": 1.7281,
+      "step": 5
+    },
+    {
+      "epoch": 0.045146726862302484,
+      "grad_norm": 12.098369998439862,
+      "learning_rate": 1e-06,
+      "loss": 1.5872,
+      "step": 10
+    },
+    {
+      "epoch": 0.06772009029345373,
+      "grad_norm": 7.799480392523437,
+      "learning_rate": 9.998553453302385e-07,
+      "loss": 1.2742,
+      "step": 15
+    },
+    {
+      "epoch": 0.09029345372460497,
+      "grad_norm": 4.3243576184049015,
+      "learning_rate": 9.99421465020848e-07,
+      "loss": 1.1293,
+      "step": 20
+    },
+    {
+      "epoch": 0.11286681715575621,
+      "grad_norm": 3.8123521250599035,
+      "learning_rate": 9.9869861012308e-07,
+      "loss": 1.0773,
+      "step": 25
+    },
+    {
+      "epoch": 0.13544018058690746,
+      "grad_norm": 3.7302202580496955,
+      "learning_rate": 9.976871988942804e-07,
+      "loss": 1.0241,
+      "step": 30
+    },
+    {
+      "epoch": 0.1580135440180587,
+      "grad_norm": 3.6817019638097315,
+      "learning_rate": 9.963878165558785e-07,
+      "loss": 0.9907,
+      "step": 35
+    },
+    {
+      "epoch": 0.18058690744920994,
+      "grad_norm": 3.6570665491053798,
+      "learning_rate": 9.948012149547666e-07,
+      "loss": 0.9535,
+      "step": 40
+    },
+    {
+      "epoch": 0.20316027088036118,
+      "grad_norm": 3.5815310725056895,
+      "learning_rate": 9.929283121282675e-07,
+      "loss": 0.9562,
+      "step": 45
+    },
+    {
+      "epoch": 0.22573363431151242,
+      "grad_norm": 3.5857342727356256,
+      "learning_rate": 9.9077019177294e-07,
+      "loss": 0.9196,
+      "step": 50
+    },
+    {
+      "epoch": 0.22573363431151242,
+      "eval_loss": 0.9316988587379456,
+      "eval_runtime": 110.0444,
+      "eval_samples_per_second": 57.25,
+      "eval_steps_per_second": 0.9,
+      "step": 50
+    },
+    {
+      "epoch": 0.24830699774266365,
+      "grad_norm": 3.8011407294134836,
+      "learning_rate": 9.88328102617534e-07,
+      "loss": 0.9367,
+      "step": 55
+    },
+    {
+      "epoch": 0.2708803611738149,
+      "grad_norm": 3.4590500642130086,
+      "learning_rate": 9.856034577004504e-07,
+      "loss": 0.9275,
+      "step": 60
+    },
+    {
+      "epoch": 0.29345372460496616,
+      "grad_norm": 3.576144528772592,
+      "learning_rate": 9.82597833552132e-07,
+      "loss": 0.919,
+      "step": 65
+    },
+    {
+      "epoch": 0.3160270880361174,
+      "grad_norm": 3.324174107907928,
+      "learning_rate": 9.793129692828533e-07,
+      "loss": 0.9057,
+      "step": 70
+    },
+    {
+      "epoch": 0.33860045146726864,
+      "grad_norm": 3.8855820879993144,
+      "learning_rate": 9.757507655764384e-07,
+      "loss": 0.8901,
+      "step": 75
+    },
+    {
+      "epoch": 0.3611738148984199,
+      "grad_norm": 3.469991558293526,
+      "learning_rate": 9.719132835904906e-07,
+      "loss": 0.9147,
+      "step": 80
+    },
+    {
+      "epoch": 0.3837471783295711,
+      "grad_norm": 3.514613408390947,
+      "learning_rate": 9.678027437637677e-07,
+      "loss": 0.8819,
+      "step": 85
+    },
+    {
+      "epoch": 0.40632054176072235,
+      "grad_norm": 3.648475056062095,
+      "learning_rate": 9.634215245313939e-07,
+      "loss": 0.8867,
+      "step": 90
+    },
+    {
+      "epoch": 0.4288939051918736,
+      "grad_norm": 3.5559364392174695,
+      "learning_rate": 9.587721609486543e-07,
+      "loss": 0.8809,
+      "step": 95
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "grad_norm": 3.4130223122860843,
+      "learning_rate": 9.538573432241637e-07,
+      "loss": 0.8737,
+      "step": 100
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "eval_loss": 0.8765010833740234,
+      "eval_runtime": 109.5348,
+      "eval_samples_per_second": 57.516,
+      "eval_steps_per_second": 0.904,
+      "step": 100
+    },
+    {
+      "epoch": 0.47404063205417607,
+      "grad_norm": 3.787400905783148,
+      "learning_rate": 9.486799151632612e-07,
+      "loss": 0.885,
+      "step": 105
+    },
+    {
+      "epoch": 0.4966139954853273,
+      "grad_norm": 3.535608347392897,
+      "learning_rate": 9.432428725225326e-07,
+      "loss": 0.8814,
+      "step": 110
+    },
+    {
+      "epoch": 0.5191873589164786,
+      "grad_norm": 3.6894303777250927,
+      "learning_rate": 9.375493612764085e-07,
+      "loss": 0.881,
+      "step": 115
+    },
+    {
+      "epoch": 0.5417607223476298,
+      "grad_norm": 3.577445458553245,
+      "learning_rate": 9.316026757968454e-07,
+      "loss": 0.8572,
+      "step": 120
+    },
+    {
+      "epoch": 0.5643340857787811,
+      "grad_norm": 3.5992375922791284,
+      "learning_rate": 9.2540625694714e-07,
+      "loss": 0.8654,
+      "step": 125
+    },
+    {
+      "epoch": 0.5869074492099323,
+      "grad_norm": 3.4939966180593824,
+      "learning_rate": 9.189636900909817e-07,
+      "loss": 0.8603,
+      "step": 130
+    },
+    {
+      "epoch": 0.6094808126410836,
+      "grad_norm": 3.815700262637612,
+      "learning_rate": 9.122787030178949e-07,
+      "loss": 0.8511,
+      "step": 135
+    },
+    {
+      "epoch": 0.6320541760722348,
+      "grad_norm": 3.7360996720156314,
+      "learning_rate": 9.053551637862692e-07,
+      "loss": 0.8622,
+      "step": 140
+    },
+    {
+      "epoch": 0.654627539503386,
+      "grad_norm": 3.7059514280124,
+      "learning_rate": 8.98197078485229e-07,
+      "loss": 0.8371,
+      "step": 145
+    },
+    {
+      "epoch": 0.6772009029345373,
+      "grad_norm": 3.4566197799411778,
+      "learning_rate": 8.908085889166357e-07,
+      "loss": 0.8557,
+      "step": 150
+    },
+    {
+      "epoch": 0.6772009029345373,
+      "eval_loss": 0.8529915809631348,
+      "eval_runtime": 109.5763,
+      "eval_samples_per_second": 57.494,
+      "eval_steps_per_second": 0.903,
+      "step": 150
+    },
+    {
+      "epoch": 0.6997742663656885,
+      "grad_norm": 4.108966235237678,
+      "learning_rate": 8.831939701985636e-07,
+      "loss": 0.8493,
+      "step": 155
+    },
+    {
+      "epoch": 0.7223476297968398,
+      "grad_norm": 3.500706471908252,
+      "learning_rate": 8.75357628291637e-07,
+      "loss": 0.8561,
+      "step": 160
+    },
+    {
+      "epoch": 0.744920993227991,
+      "grad_norm": 3.465064110849232,
+      "learning_rate": 8.673040974496584e-07,
+      "loss": 0.8382,
+      "step": 165
+    },
+    {
+      "epoch": 0.7674943566591422,
+      "grad_norm": 3.4468913764280824,
+      "learning_rate": 8.590380375960053e-07,
+      "loss": 0.8347,
+      "step": 170
+    },
+    {
+      "epoch": 0.7900677200902935,
+      "grad_norm": 3.689915124175266,
+      "learning_rate": 8.505642316273111e-07,
+      "loss": 0.8421,
+      "step": 175
+    },
+    {
+      "epoch": 0.8126410835214447,
+      "grad_norm": 3.380084999051841,
+      "learning_rate": 8.418875826459919e-07,
+      "loss": 0.8317,
+      "step": 180
+    },
+    {
+      "epoch": 0.835214446952596,
+      "grad_norm": 3.6696844138559808,
+      "learning_rate": 8.330131111232201e-07,
+      "loss": 0.8407,
+      "step": 185
+    },
+    {
+      "epoch": 0.8577878103837472,
+      "grad_norm": 3.4940832177035293,
+      "learning_rate": 8.239459519939851e-07,
+      "loss": 0.8539,
+      "step": 190
+    },
+    {
+      "epoch": 0.8803611738148984,
+      "grad_norm": 3.214918919448116,
+      "learning_rate": 8.14691351685925e-07,
+      "loss": 0.8347,
+      "step": 195
+    },
+    {
+      "epoch": 0.9029345372460497,
+      "grad_norm": 3.427510592132526,
+      "learning_rate": 8.052546650836453e-07,
+      "loss": 0.8242,
+      "step": 200
+    },
+    {
+      "epoch": 0.9029345372460497,
+      "eval_loss": 0.8354331254959106,
+      "eval_runtime": 109.4188,
+      "eval_samples_per_second": 57.577,
+      "eval_steps_per_second": 0.905,
+      "step": 200
+    },
+    {
+      "epoch": 0.9255079006772009,
+      "grad_norm": 3.6927117939398886,
+      "learning_rate": 7.956413524302823e-07,
+      "loss": 0.8204,
+      "step": 205
+    },
+    {
+      "epoch": 0.9480812641083521,
+      "grad_norm": 3.6666105985738606,
+      "learning_rate": 7.858569761681047e-07,
+      "loss": 0.8545,
+      "step": 210
+    },
+    {
+      "epoch": 0.9706546275395034,
+      "grad_norm": 3.875619463407146,
+      "learning_rate": 7.759071977199806e-07,
+      "loss": 0.8431,
+      "step": 215
+    },
+    {
+      "epoch": 0.9932279909706546,
+      "grad_norm": 3.2790864439936875,
+      "learning_rate": 7.657977742135725e-07,
+      "loss": 0.8245,
+      "step": 220
+    },
+    {
+      "epoch": 1.0158013544018059,
+      "grad_norm": 3.3063820393602876,
+      "learning_rate": 7.555345551501557e-07,
+      "loss": 0.7956,
+      "step": 225
+    },
+    {
+      "epoch": 1.0383747178329572,
+      "grad_norm": 3.707635627262872,
+      "learning_rate": 7.451234790199871e-07,
+      "loss": 0.7706,
+      "step": 230
+    },
+    {
+      "epoch": 1.0609480812641083,
+      "grad_norm": 3.6504981451650096,
+      "learning_rate": 7.345705698661852e-07,
+      "loss": 0.7521,
+      "step": 235
+    },
+    {
+      "epoch": 1.0835214446952597,
+      "grad_norm": 3.4617956642188097,
+      "learning_rate": 7.23881933799104e-07,
+      "loss": 0.7465,
+      "step": 240
+    },
+    {
+      "epoch": 1.1060948081264108,
+      "grad_norm": 3.6172380022954935,
+      "learning_rate": 7.130637554632257e-07,
+      "loss": 0.7727,
+      "step": 245
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "grad_norm": 3.793915550967959,
+      "learning_rate": 7.021222944586088e-07,
+      "loss": 0.7715,
+      "step": 250
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "eval_loss": 0.8277800679206848,
+      "eval_runtime": 109.5657,
+      "eval_samples_per_second": 57.5,
+      "eval_steps_per_second": 0.904,
+      "step": 250
+    },
+    {
+      "epoch": 1.1512415349887133,
+      "grad_norm": 3.4955286501011735,
+      "learning_rate": 6.910638817189664e-07,
+      "loss": 0.7589,
+      "step": 255
+    },
+    {
+      "epoch": 1.1738148984198646,
+      "grad_norm": 3.5834856426118615,
+      "learning_rate": 6.798949158484705e-07,
+      "loss": 0.7784,
+      "step": 260
+    },
+    {
+      "epoch": 1.1963882618510158,
+      "grad_norm": 3.655680306693504,
+      "learning_rate": 6.686218594193993e-07,
+      "loss": 0.7402,
+      "step": 265
+    },
+    {
+      "epoch": 1.2189616252821671,
+      "grad_norm": 3.86229701873481,
+      "learning_rate": 6.572512352327726e-07,
+      "loss": 0.7759,
+      "step": 270
+    },
+    {
+      "epoch": 1.2415349887133182,
+      "grad_norm": 3.5211869951686983,
+      "learning_rate": 6.457896225441371e-07,
+      "loss": 0.7549,
+      "step": 275
+    },
+    {
+      "epoch": 1.2641083521444696,
+      "grad_norm": 3.5889293223377208,
+      "learning_rate": 6.342436532566865e-07,
+      "loss": 0.7564,
+      "step": 280
+    },
+    {
+      "epoch": 1.2866817155756207,
+      "grad_norm": 3.607920044891375,
+      "learning_rate": 6.226200080839182e-07,
+      "loss": 0.7629,
+      "step": 285
+    },
+    {
+      "epoch": 1.309255079006772,
+      "grad_norm": 3.553446162126762,
+      "learning_rate": 6.109254126840479e-07,
+      "loss": 0.7531,
+      "step": 290
+    },
+    {
+      "epoch": 1.3318284424379232,
+      "grad_norm": 3.5301798790372207,
+      "learning_rate": 5.991666337684176e-07,
+      "loss": 0.7572,
+      "step": 295
+    },
+    {
+      "epoch": 1.3544018058690745,
+      "grad_norm": 3.627738643773189,
+      "learning_rate": 5.873504751861507e-07,
+      "loss": 0.7752,
+      "step": 300
+    },
+    {
+      "epoch": 1.3544018058690745,
+      "eval_loss": 0.819725513458252,
+      "eval_runtime": 109.6357,
+      "eval_samples_per_second": 57.463,
+      "eval_steps_per_second": 0.903,
+      "step": 300
+    },
+    {
+      "epoch": 1.3769751693002257,
+      "grad_norm": 3.609521496977633,
+      "learning_rate": 5.754837739873178e-07,
+      "loss": 0.7622,
+      "step": 305
+    },
+    {
+      "epoch": 1.399548532731377,
+      "grad_norm": 3.556720507344035,
+      "learning_rate": 5.635733964668909e-07,
+      "loss": 0.7487,
+      "step": 310
+    },
+    {
+      "epoch": 1.4221218961625282,
+      "grad_norm": 3.8469023502440756,
+      "learning_rate": 5.516262341917778e-07,
+      "loss": 0.7568,
+      "step": 315
+    },
+    {
+      "epoch": 1.4446952595936795,
+      "grad_norm": 3.553420846727805,
+      "learning_rate": 5.396492000132325e-07,
+      "loss": 0.7584,
+      "step": 320
+    },
+    {
+      "epoch": 1.4672686230248306,
+      "grad_norm": 3.671248637273475,
+      "learning_rate": 5.276492240669503e-07,
+      "loss": 0.7708,
+      "step": 325
+    },
+    {
+      "epoch": 1.489841986455982,
+      "grad_norm": 3.4883623820641922,
+      "learning_rate": 5.156332497631621e-07,
+      "loss": 0.742,
+      "step": 330
+    },
+    {
+      "epoch": 1.5124153498871333,
+      "grad_norm": 3.5733319503202776,
+      "learning_rate": 5.036082297690464e-07,
+      "loss": 0.7578,
+      "step": 335
+    },
+    {
+      "epoch": 1.5349887133182845,
+      "grad_norm": 3.453860123250934,
+      "learning_rate": 4.915811219857882e-07,
+      "loss": 0.7542,
+      "step": 340
+    },
+    {
+      "epoch": 1.5575620767494356,
+      "grad_norm": 3.6891903258202206,
+      "learning_rate": 4.795588855226055e-07,
+      "loss": 0.7589,
+      "step": 345
+    },
+    {
+      "epoch": 1.580135440180587,
+      "grad_norm": 3.647875532185229,
+      "learning_rate": 4.6754847667008004e-07,
+      "loss": 0.7359,
+      "step": 350
+    },
+    {
+      "epoch": 1.580135440180587,
+      "eval_loss": 0.8135123252868652,
+      "eval_runtime": 109.5806,
+      "eval_samples_per_second": 57.492,
+      "eval_steps_per_second": 0.903,
+      "step": 350
+    },
+    {
+      "epoch": 1.6027088036117383,
+      "grad_norm": 3.5680267072205427,
+      "learning_rate": 4.5555684487511693e-07,
+      "loss": 0.7674,
+      "step": 355
+    },
+    {
+      "epoch": 1.6252821670428894,
+      "grad_norm": 3.281054570962508,
+      "learning_rate": 4.435909287198646e-07,
+      "loss": 0.7565,
+      "step": 360
+    },
+    {
+      "epoch": 1.6478555304740405,
+      "grad_norm": 3.3765578443383224,
+      "learning_rate": 4.316576519069226e-07,
+      "loss": 0.7578,
+      "step": 365
+    },
+    {
+      "epoch": 1.670428893905192,
+      "grad_norm": 3.536076248505112,
+      "learning_rate": 4.197639192531573e-07,
+      "loss": 0.7533,
+      "step": 370
+    },
+    {
+      "epoch": 1.6930022573363432,
+      "grad_norm": 3.9641281540021023,
+      "learning_rate": 4.079166126944453e-07,
+      "loss": 0.7674,
+      "step": 375
+    },
+    {
+      "epoch": 1.7155756207674944,
+      "grad_norm": 3.777058403651495,
+      "learning_rate": 3.9612258730365823e-07,
+      "loss": 0.7355,
+      "step": 380
+    },
+    {
+      "epoch": 1.7381489841986455,
+      "grad_norm": 3.7311845269819783,
+      "learning_rate": 3.843886673241883e-07,
+      "loss": 0.7512,
+      "step": 385
+    },
+    {
+      "epoch": 1.7607223476297968,
+      "grad_norm": 3.5531260457665073,
+      "learning_rate": 3.7272164222131387e-07,
+      "loss": 0.7544,
+      "step": 390
+    },
+    {
+      "epoch": 1.7832957110609482,
+      "grad_norm": 3.815873779507455,
+      "learning_rate": 3.611282627536887e-07,
+      "loss": 0.7572,
+      "step": 395
+    },
+    {
+      "epoch": 1.8058690744920993,
+      "grad_norm": 3.5694044492417034,
+      "learning_rate": 3.496152370672255e-07,
+      "loss": 0.7467,
+      "step": 400
+    },
+    {
+      "epoch": 1.8058690744920993,
+      "eval_loss": 0.8077942132949829,
+      "eval_runtime": 109.5421,
+      "eval_samples_per_second": 57.512,
+      "eval_steps_per_second": 0.904,
+      "step": 400
+    },
+    {
+      "epoch": 1.8284424379232505,
+      "grad_norm": 3.5715817669773866,
+      "learning_rate": 3.381892268136392e-07,
+      "loss": 0.7387,
+      "step": 405
+    },
+    {
+      "epoch": 1.8510158013544018,
+      "grad_norm": 3.632625798422972,
+      "learning_rate": 3.2685684329588956e-07,
+      "loss": 0.7459,
+      "step": 410
+    },
+    {
+      "epoch": 1.8735891647855532,
+      "grad_norm": 3.4083610886198614,
+      "learning_rate": 3.1562464364275774e-07,
+      "loss": 0.755,
+      "step": 415
+    },
+    {
+      "epoch": 1.8961625282167043,
+      "grad_norm": 3.5098768134992255,
+      "learning_rate": 3.044991270147699e-07,
+      "loss": 0.7485,
+      "step": 420
+    },
+    {
+      "epoch": 1.9187358916478554,
+      "grad_norm": 3.570449170370788,
+      "learning_rate": 2.934867308436613e-07,
+      "loss": 0.7457,
+      "step": 425
+    },
+    {
+      "epoch": 1.9413092550790068,
+      "grad_norm": 3.5437186541935386,
+      "learning_rate": 2.825938271075572e-07,
+      "loss": 0.7456,
+      "step": 430
+    },
+    {
+      "epoch": 1.963882618510158,
+      "grad_norm": 3.6156752309028244,
+      "learning_rate": 2.7182671864402856e-07,
+      "loss": 0.7367,
+      "step": 435
+    },
+    {
+      "epoch": 1.9864559819413092,
+      "grad_norm": 3.541183052041991,
+      "learning_rate": 2.6119163550315194e-07,
+      "loss": 0.7605,
+      "step": 440
+    },
+    {
+      "epoch": 2.0090293453724604,
+      "grad_norm": 3.668354373946963,
+      "learning_rate": 2.506947313426854e-07,
+      "loss": 0.7443,
+      "step": 445
+    },
+    {
+      "epoch": 2.0316027088036117,
+      "grad_norm": 3.6174990546812342,
+      "learning_rate": 2.4034207986744847e-07,
+      "loss": 0.7024,
+      "step": 450
+    },
+    {
+      "epoch": 2.0316027088036117,
+      "eval_loss": 0.8078460097312927,
+      "eval_runtime": 109.5409,
+      "eval_samples_per_second": 57.513,
+      "eval_steps_per_second": 0.904,
+      "step": 450
+    },
+    {
+      "epoch": 2.054176072234763,
+      "grad_norm": 3.6197344117961983,
+      "learning_rate": 2.301396713149627e-07,
+      "loss": 0.7042,
+      "step": 455
+    },
+    {
+      "epoch": 2.0767494356659144,
+      "grad_norm": 3.6219776063121687,
+      "learning_rate": 2.2009340898938738e-07,
+      "loss": 0.6819,
+      "step": 460
+    },
+    {
+      "epoch": 2.0993227990970653,
+      "grad_norm": 3.749685991397984,
+      "learning_rate": 2.1020910584575891e-07,
+      "loss": 0.7138,
+      "step": 465
+    },
+    {
+      "epoch": 2.1218961625282167,
+      "grad_norm": 3.686378460444093,
+      "learning_rate": 2.0049248112650563e-07,
+      "loss": 0.6967,
+      "step": 470
+    },
+    {
+      "epoch": 2.144469525959368,
+      "grad_norm": 3.8202046159252903,
+      "learning_rate": 1.9094915705218711e-07,
+      "loss": 0.6911,
+      "step": 475
+    },
+    {
+      "epoch": 2.1670428893905194,
+      "grad_norm": 4.093386454062259,
+      "learning_rate": 1.8158465556837304e-07,
+      "loss": 0.6825,
+      "step": 480
+    },
+    {
+      "epoch": 2.1896162528216703,
+      "grad_norm": 3.6669210094430875,
+      "learning_rate": 1.7240439515054218e-07,
+      "loss": 0.6957,
+      "step": 485
+    },
+    {
+      "epoch": 2.2121896162528216,
+      "grad_norm": 3.7920265300049887,
+      "learning_rate": 1.634136876688504e-07,
+      "loss": 0.7123,
+      "step": 490
+    },
+    {
+      "epoch": 2.234762979683973,
+      "grad_norm": 3.8406082616032484,
+      "learning_rate": 1.5461773531458455e-07,
+      "loss": 0.7014,
+      "step": 495
+    },
+    {
+      "epoch": 2.2573363431151243,
+      "grad_norm": 3.7396677582411995,
+      "learning_rate": 1.460216275900769e-07,
+      "loss": 0.6984,
+      "step": 500
+    },
+    {
+      "epoch": 2.2573363431151243,
+      "eval_loss": 0.8086156249046326,
+      "eval_runtime": 109.6842,
+      "eval_samples_per_second": 57.438,
+      "eval_steps_per_second": 0.903,
+      "step": 500
+    },
+    {
+      "epoch": 2.2799097065462752,
+      "grad_norm": 3.810172890487716,
+      "learning_rate": 1.3763033836382392e-07,
+      "loss": 0.6953,
+      "step": 505
+    },
+    {
+      "epoch": 2.3024830699774266,
+      "grad_norm": 3.7650154233741318,
+      "learning_rate": 1.294487229925132e-07,
+      "loss": 0.7049,
+      "step": 510
+    },
+    {
+      "epoch": 2.325056433408578,
+      "grad_norm": 3.7977324434068622,
+      "learning_rate": 1.2148151551162345e-07,
+      "loss": 0.6996,
+      "step": 515
+    },
+    {
+      "epoch": 2.3476297968397293,
+      "grad_norm": 3.7271690299752636,
+      "learning_rate": 1.137333258962227e-07,
+      "loss": 0.7046,
+      "step": 520
+    },
+    {
+      "epoch": 2.37020316027088,
+      "grad_norm": 3.7696874152910693,
+      "learning_rate": 1.0620863739355135e-07,
+      "loss": 0.7038,
+      "step": 525
+    },
+    {
+      "epoch": 2.3927765237020315,
+      "grad_norm": 3.6784969120555937,
+      "learning_rate": 9.891180392893117e-08,
+      "loss": 0.684,
+      "step": 530
+    },
+    {
+      "epoch": 2.415349887133183,
+      "grad_norm": 3.923781431171795,
+      "learning_rate": 9.184704758650241e-08,
+      "loss": 0.7056,
+      "step": 535
+    },
+    {
+      "epoch": 2.4379232505643342,
+      "grad_norm": 3.8228025983942624,
+      "learning_rate": 8.501845616624798e-08,
+      "loss": 0.6876,
+      "step": 540
+    },
+    {
+      "epoch": 2.460496613995485,
+      "grad_norm": 3.9688517448973624,
+      "learning_rate": 7.842998081871493e-08,
+      "loss": 0.7139,
+      "step": 545
+    },
+    {
+      "epoch": 2.4830699774266365,
+      "grad_norm": 3.909192582651566,
+      "learning_rate": 7.208543375880594e-08,
+      "loss": 0.7063,
+      "step": 550
+    },
+    {
+      "epoch": 2.4830699774266365,
+      "eval_loss": 0.8080305457115173,
+      "eval_runtime": 109.6111,
+      "eval_samples_per_second": 57.476,
+      "eval_steps_per_second": 0.903,
+      "step": 550
+    },
+    {
+      "epoch": 2.505643340857788,
+      "grad_norm": 3.6883752732106125,
+      "learning_rate": 6.598848605996004e-08,
+      "loss": 0.6922,
+      "step": 555
+    },
+    {
+      "epoch": 2.528216704288939,
+      "grad_norm": 3.8586414745206814,
+      "learning_rate": 6.014266553000074e-08,
+      "loss": 0.7121,
+      "step": 560
+    },
+    {
+      "epoch": 2.55079006772009,
+      "grad_norm": 3.6987869873044725,
+      "learning_rate": 5.4551354669881145e-08,
+      "loss": 0.6944,
+      "step": 565
+    },
+    {
+      "epoch": 2.5733634311512414,
+      "grad_norm": 3.7083356878972222,
+      "learning_rate": 4.921778871650539e-08,
+      "loss": 0.703,
+      "step": 570
+    },
+    {
+      "epoch": 2.595936794582393,
+      "grad_norm": 3.7810271982778305,
+      "learning_rate": 4.414505377075978e-08,
+      "loss": 0.692,
+      "step": 575
+    },
+    {
+      "epoch": 2.618510158013544,
+      "grad_norm": 4.00249924161769,
+      "learning_rate": 3.933608501183788e-08,
+      "loss": 0.6901,
+      "step": 580
+    },
+    {
+      "epoch": 2.6410835214446955,
+      "grad_norm": 3.790359559860126,
+      "learning_rate": 3.479366499889058e-08,
+      "loss": 0.6997,
+      "step": 585
+    },
+    {
+      "epoch": 2.6636568848758464,
+      "grad_norm": 3.588096321178088,
+      "learning_rate": 3.052042206098537e-08,
+      "loss": 0.6826,
+      "step": 590
+    },
+    {
+      "epoch": 2.6862302483069977,
+      "grad_norm": 3.7054037608925148,
+      "learning_rate": 2.6518828776306347e-08,
+      "loss": 0.6909,
+      "step": 595
+    },
+    {
+      "epoch": 2.708803611738149,
+      "grad_norm": 3.703171492172673,
+      "learning_rate": 2.279120054147393e-08,
+      "loss": 0.6873,
+      "step": 600
+    },
+    {
+      "epoch": 2.708803611738149,
+      "eval_loss": 0.80707848072052,
+      "eval_runtime": 109.463,
+      "eval_samples_per_second": 57.554,
+      "eval_steps_per_second": 0.904,
+      "step": 600
+    },
+    {
+      "epoch": 2.7313769751693,
+      "grad_norm": 3.9293753380698884,
+      "learning_rate": 1.9339694231813252e-08,
+      "loss": 0.6997,
+      "step": 605
+    },
+    {
+      "epoch": 2.7539503386004514,
+      "grad_norm": 4.137942412644628,
+      "learning_rate": 1.616630695334592e-08,
+      "loss": 0.7078,
+      "step": 610
+    },
+    {
+      "epoch": 2.7765237020316027,
+      "grad_norm": 3.9534669915381877,
+      "learning_rate": 1.3272874887227281e-08,
+      "loss": 0.6966,
+      "step": 615
+    },
+    {
+      "epoch": 2.799097065462754,
+      "grad_norm": 3.7231816025762168,
+      "learning_rate": 1.066107222729712e-08,
+      "loss": 0.7013,
+      "step": 620
+    },
+    {
+      "epoch": 2.8216704288939054,
+      "grad_norm": 3.58992452351805,
+      "learning_rate": 8.332410211360608e-09,
+      "loss": 0.7107,
+      "step": 625
+    },
+    {
+      "epoch": 2.8442437923250563,
+      "grad_norm": 3.744424909335921,
+      "learning_rate": 6.288236246757284e-09,
+      "loss": 0.6907,
+      "step": 630
+    },
+    {
+      "epoch": 2.8668171557562077,
+      "grad_norm": 3.9524208371805956,
+      "learning_rate": 4.529733130726299e-09,
+      "loss": 0.7125,
+      "step": 635
+    },
+    {
+      "epoch": 2.889390519187359,
+      "grad_norm": 3.7901367668148027,
+      "learning_rate": 3.0579183660177086e-09,
+      "loss": 0.6974,
+      "step": 640
+    },
+    {
+      "epoch": 2.91196388261851,
+      "grad_norm": 3.6006642909643714,
+      "learning_rate": 1.8736435721465326e-09,
+      "loss": 0.695,
+      "step": 645
+    },
+    {
+      "epoch": 2.9345372460496613,
+      "grad_norm": 3.671968035371273,
+      "learning_rate": 9.775939926296439e-10,
+      "loss": 0.7067,
+      "step": 650
+    },
+    {
+      "epoch": 2.9345372460496613,
+      "eval_loss": 0.8069904446601868,
+      "eval_runtime": 109.6344,
+      "eval_samples_per_second": 57.464,
+      "eval_steps_per_second": 0.903,
+      "step": 650
+    },
+    {
+      "epoch": 2.9571106094808126,
+      "grad_norm": 3.6036456106402284,
+      "learning_rate": 3.7028809849098954e-10,
+      "loss": 0.705,
+      "step": 655
+    },
+    {
+      "epoch": 2.979683972911964,
+      "grad_norm": 3.7354799118910087,
+      "learning_rate": 5.2077288264951166e-11,
+      "loss": 0.6905,
+      "step": 660
+    },
+    {
+      "epoch": 2.9932279909706545,
+      "step": 663,
+      "total_flos": 3909114547666944.0,
+      "train_loss": 0.7958762821928228,
+      "train_runtime": 10129.4465,
+      "train_samples_per_second": 16.793,
+      "train_steps_per_second": 0.065
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 663,
+  "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": 3909114547666944.0,
+  "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 sha256:9b9660083b73d21ccb922a1d91dfcec02f022497ecc87e5bc78415b86f9ed154
+size 7096