Upload folder using huggingface_hub

README.md

@@ -0,0 +1,84 @@
+---
+library_name: transformers
+license: other
+base_model: llava-hf/llava-v1.6-mistral-7b-hf
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Compcap_cosi_0_90
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Compcap_cosi_0_90
+
+This model is a fine-tuned version of [llava-hf/llava-v1.6-mistral-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf) on the Compcap_cosi_0_90 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7912
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9297        | 0.1505 | 50   | 0.9399          |
+| 0.8675        | 0.3010 | 100  | 0.8835          |
+| 0.8457        | 0.4515 | 150  | 0.8571          |
+| 0.8411        | 0.6020 | 200  | 0.8422          |
+| 0.8133        | 0.7524 | 250  | 0.8285          |
+| 0.8114        | 0.9029 | 300  | 0.8189          |
+| 0.7379        | 1.0534 | 350  | 0.8137          |
+| 0.7416        | 1.2039 | 400  | 0.8082          |
+| 0.7623        | 1.3544 | 450  | 0.8033          |
+| 0.7158        | 1.5049 | 500  | 0.7987          |
+| 0.7322        | 1.6554 | 550  | 0.7955          |
+| 0.7148        | 1.8059 | 600  | 0.7920          |
+| 0.71          | 1.9564 | 650  | 0.7894          |
+| 0.6651        | 2.1068 | 700  | 0.7947          |
+| 0.6684        | 2.2573 | 750  | 0.7936          |
+| 0.6826        | 2.4078 | 800  | 0.7928          |
+| 0.6711        | 2.5583 | 850  | 0.7920          |
+| 0.6757        | 2.7088 | 900  | 0.7915          |
+| 0.6791        | 2.8593 | 950  | 0.7913          |
+
+
+### 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": 2.9977426636568847,
+    "eval_loss": 0.7912431359291077,
+    "eval_runtime": 163.5036,
+    "eval_samples_per_second": 57.797,
+    "eval_steps_per_second": 0.905,
+    "total_flos": 5872633472090112.0,
+    "train_loss": 0.7687147306988996,
+    "train_runtime": 16194.6861,
+    "train_samples_per_second": 15.755,
+    "train_steps_per_second": 0.062
+}

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": 2.9977426636568847,
+    "eval_loss": 0.7912431359291077,
+    "eval_runtime": 163.5036,
+    "eval_samples_per_second": 57.797,
+    "eval_steps_per_second": 0.905
+}

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 sha256:83803a1876dfcc960b3fdfb8331405e695229fba61c1a4e07feb6de82ffb102d
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec8b0b909db8129d04d4f54122e791eb67ff51a3a6ac309b33a4130a6e4e46c8
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ba51ae356007a36a9807312611b0922be99b1b4da63b57673353a6beadd0b37
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b9581139dfd0dff59f36fc215618c6794b91bad3b9e14b05c6f09c60d6e631
+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": 2.9977426636568847,
+    "total_flos": 5872633472090112.0,
+    "train_loss": 0.7687147306988996,
+    "train_runtime": 16194.6861,
+    "train_samples_per_second": 15.755,
+    "train_steps_per_second": 0.062
+}

trainer_log.jsonl

@@ -0,0 +1,219 @@
+{"current_steps": 5, "total_steps": 996, "loss": 1.7355, "learning_rate": 5e-07, "epoch": 0.015048908954100828, "percentage": 0.5, "elapsed_time": "0:01:08", "remaining_time": "3:46:17"}
+{"current_steps": 10, "total_steps": 996, "loss": 1.5959, "learning_rate": 1e-06, "epoch": 0.030097817908201655, "percentage": 1.0, "elapsed_time": "0:02:13", "remaining_time": "3:39:23"}
+{"current_steps": 15, "total_steps": 996, "loss": 1.2852, "learning_rate": 9.999365521737421e-07, "epoch": 0.045146726862302484, "percentage": 1.51, "elapsed_time": "0:03:18", "remaining_time": "3:36:30"}
+{"current_steps": 20, "total_steps": 996, "loss": 1.1474, "learning_rate": 9.99746224797475e-07, "epoch": 0.06019563581640331, "percentage": 2.01, "elapsed_time": "0:04:23", "remaining_time": "3:34:38"}
+{"current_steps": 25, "total_steps": 996, "loss": 1.0775, "learning_rate": 9.99429066174632e-07, "epoch": 0.07524454477050414, "percentage": 2.51, "elapsed_time": "0:05:29", "remaining_time": "3:32:59"}
+{"current_steps": 30, "total_steps": 996, "loss": 1.0181, "learning_rate": 9.989851567973138e-07, "epoch": 0.09029345372460497, "percentage": 3.01, "elapsed_time": "0:06:33", "remaining_time": "3:31:15"}
+{"current_steps": 35, "total_steps": 996, "loss": 1.0061, "learning_rate": 9.984146093258608e-07, "epoch": 0.1053423626787058, "percentage": 3.51, "elapsed_time": "0:07:39", "remaining_time": "3:30:03"}
+{"current_steps": 40, "total_steps": 996, "loss": 0.9556, "learning_rate": 9.9771756856026e-07, "epoch": 0.12039127163280662, "percentage": 4.02, "elapsed_time": "0:08:43", "remaining_time": "3:28:42"}
+{"current_steps": 45, "total_steps": 996, "loss": 0.9456, "learning_rate": 9.968942114033973e-07, "epoch": 0.13544018058690746, "percentage": 4.52, "elapsed_time": "0:09:49", "remaining_time": "3:27:35"}
+{"current_steps": 50, "total_steps": 996, "loss": 0.9297, "learning_rate": 9.959447468161596e-07, "epoch": 0.1504890895410083, "percentage": 5.02, "elapsed_time": "0:10:54", "remaining_time": "3:26:16"}
+{"current_steps": 50, "total_steps": 996, "eval_loss": 0.939862847328186, "epoch": 0.1504890895410083, "percentage": 5.02, "elapsed_time": "0:13:38", "remaining_time": "4:18:04"}
+{"current_steps": 55, "total_steps": 996, "loss": 0.9204, "learning_rate": 9.948694157644042e-07, "epoch": 0.1655379984951091, "percentage": 5.52, "elapsed_time": "0:14:44", "remaining_time": "4:12:14"}
+{"current_steps": 60, "total_steps": 996, "loss": 0.8933, "learning_rate": 9.936684911578017e-07, "epoch": 0.18058690744920994, "percentage": 6.02, "elapsed_time": "0:15:49", "remaining_time": "4:06:50"}
+{"current_steps": 65, "total_steps": 996, "loss": 0.9219, "learning_rate": 9.923422777805751e-07, "epoch": 0.19563581640331076, "percentage": 6.53, "elapsed_time": "0:16:54", "remaining_time": "4:02:08"}
+{"current_steps": 70, "total_steps": 996, "loss": 0.8946, "learning_rate": 9.908911122141486e-07, "epoch": 0.2106847253574116, "percentage": 7.03, "elapsed_time": "0:18:00", "remaining_time": "3:58:08"}
+{"current_steps": 75, "total_steps": 996, "loss": 0.902, "learning_rate": 9.893153627517248e-07, "epoch": 0.22573363431151242, "percentage": 7.53, "elapsed_time": "0:19:05", "remaining_time": "3:54:26"}
+{"current_steps": 80, "total_steps": 996, "loss": 0.8924, "learning_rate": 9.876154293048163e-07, "epoch": 0.24078254326561324, "percentage": 8.03, "elapsed_time": "0:20:10", "remaining_time": "3:51:04"}
+{"current_steps": 85, "total_steps": 996, "loss": 0.8958, "learning_rate": 9.857917433017508e-07, "epoch": 0.2558314522197141, "percentage": 8.53, "elapsed_time": "0:21:16", "remaining_time": "3:47:57"}
+{"current_steps": 90, "total_steps": 996, "loss": 0.8881, "learning_rate": 9.838447675781793e-07, "epoch": 0.2708803611738149, "percentage": 9.04, "elapsed_time": "0:22:21", "remaining_time": "3:45:03"}
+{"current_steps": 95, "total_steps": 996, "loss": 0.882, "learning_rate": 9.817749962596114e-07, "epoch": 0.28592927012791575, "percentage": 9.54, "elapsed_time": "0:23:27", "remaining_time": "3:42:28"}
+{"current_steps": 100, "total_steps": 996, "loss": 0.8675, "learning_rate": 9.795829546360113e-07, "epoch": 0.3009781790820166, "percentage": 10.04, "elapsed_time": "0:24:33", "remaining_time": "3:39:59"}
+{"current_steps": 100, "total_steps": 996, "eval_loss": 0.8835354447364807, "epoch": 0.3009781790820166, "percentage": 10.04, "elapsed_time": "0:27:17", "remaining_time": "4:04:31"}
+{"current_steps": 105, "total_steps": 996, "loss": 0.8656, "learning_rate": 9.77269199028483e-07, "epoch": 0.3160270880361174, "percentage": 10.54, "elapsed_time": "0:28:23", "remaining_time": "4:00:53"}
+{"current_steps": 110, "total_steps": 996, "loss": 0.8907, "learning_rate": 9.748343166480822e-07, "epoch": 0.3310759969902182, "percentage": 11.04, "elapsed_time": "0:29:28", "remaining_time": "3:57:23"}
+{"current_steps": 115, "total_steps": 996, "loss": 0.8678, "learning_rate": 9.722789254467854e-07, "epoch": 0.34612490594431905, "percentage": 11.55, "elapsed_time": "0:30:33", "remaining_time": "3:54:07"}
+{"current_steps": 120, "total_steps": 996, "loss": 0.8634, "learning_rate": 9.696036739606606e-07, "epoch": 0.3611738148984199, "percentage": 12.05, "elapsed_time": "0:31:39", "remaining_time": "3:51:05"}
+{"current_steps": 125, "total_steps": 996, "loss": 0.8789, "learning_rate": 9.668092411452735e-07, "epoch": 0.3762227238525207, "percentage": 12.55, "elapsed_time": "0:32:45", "remaining_time": "3:48:12"}
+{"current_steps": 130, "total_steps": 996, "loss": 0.8592, "learning_rate": 9.638963362033756e-07, "epoch": 0.3912716328066215, "percentage": 13.05, "elapsed_time": "0:33:50", "remaining_time": "3:45:27"}
+{"current_steps": 135, "total_steps": 996, "loss": 0.8438, "learning_rate": 9.608656984049132e-07, "epoch": 0.40632054176072235, "percentage": 13.55, "elapsed_time": "0:34:55", "remaining_time": "3:42:44"}
+{"current_steps": 140, "total_steps": 996, "loss": 0.8544, "learning_rate": 9.577180968994081e-07, "epoch": 0.4213694507148232, "percentage": 14.06, "elapsed_time": "0:36:00", "remaining_time": "3:40:11"}
+{"current_steps": 145, "total_steps": 996, "loss": 0.8518, "learning_rate": 9.544543305207546e-07, "epoch": 0.436418359668924, "percentage": 14.56, "elapsed_time": "0:37:06", "remaining_time": "3:37:46"}
+{"current_steps": 150, "total_steps": 996, "loss": 0.8457, "learning_rate": 9.510752275844809e-07, "epoch": 0.45146726862302483, "percentage": 15.06, "elapsed_time": "0:38:12", "remaining_time": "3:35:28"}
+{"current_steps": 150, "total_steps": 996, "eval_loss": 0.857115626335144, "epoch": 0.45146726862302483, "percentage": 15.06, "elapsed_time": "0:40:56", "remaining_time": "3:50:54"}
+{"current_steps": 155, "total_steps": 996, "loss": 0.8595, "learning_rate": 9.475816456775312e-07, "epoch": 0.46651617757712566, "percentage": 15.56, "elapsed_time": "0:42:01", "remaining_time": "3:48:01"}
+{"current_steps": 160, "total_steps": 996, "loss": 0.8392, "learning_rate": 9.439744714406166e-07, "epoch": 0.4815650865312265, "percentage": 16.06, "elapsed_time": "0:43:06", "remaining_time": "3:45:17"}
+{"current_steps": 165, "total_steps": 996, "loss": 0.8323, "learning_rate": 9.402546203431947e-07, "epoch": 0.4966139954853273, "percentage": 16.57, "elapsed_time": "0:44:12", "remaining_time": "3:42:37"}
+{"current_steps": 170, "total_steps": 996, "loss": 0.8355, "learning_rate": 9.364230364511295e-07, "epoch": 0.5116629044394282, "percentage": 17.07, "elapsed_time": "0:45:17", "remaining_time": "3:40:02"}
+{"current_steps": 175, "total_steps": 996, "loss": 0.8537, "learning_rate": 9.324806921870975e-07, "epoch": 0.526711813393529, "percentage": 17.57, "elapsed_time": "0:46:23", "remaining_time": "3:37:37"}
+{"current_steps": 180, "total_steps": 996, "loss": 0.828, "learning_rate": 9.284285880837946e-07, "epoch": 0.5417607223476298, "percentage": 18.07, "elapsed_time": "0:47:29", "remaining_time": "3:35:17"}
+{"current_steps": 185, "total_steps": 996, "loss": 0.8346, "learning_rate": 9.242677525300088e-07, "epoch": 0.5568096313017307, "percentage": 18.57, "elapsed_time": "0:48:34", "remaining_time": "3:32:58"}
+{"current_steps": 190, "total_steps": 996, "loss": 0.832, "learning_rate": 9.199992415096259e-07, "epoch": 0.5718585402558315, "percentage": 19.08, "elapsed_time": "0:49:40", "remaining_time": "3:30:44"}
+{"current_steps": 195, "total_steps": 996, "loss": 0.8156, "learning_rate": 9.156241383336278e-07, "epoch": 0.5869074492099323, "percentage": 19.58, "elapsed_time": "0:50:45", "remaining_time": "3:28:30"}
+{"current_steps": 200, "total_steps": 996, "loss": 0.8411, "learning_rate": 9.111435533651595e-07, "epoch": 0.6019563581640331, "percentage": 20.08, "elapsed_time": "0:51:51", "remaining_time": "3:26:22"}
+{"current_steps": 200, "total_steps": 996, "eval_loss": 0.8422114253044128, "epoch": 0.6019563581640331, "percentage": 20.08, "elapsed_time": "0:54:35", "remaining_time": "3:37:15"}
+{"current_steps": 205, "total_steps": 996, "loss": 0.8255, "learning_rate": 9.065586237377274e-07, "epoch": 0.617005267118134, "percentage": 20.58, "elapsed_time": "0:55:40", "remaining_time": "3:34:48"}
+{"current_steps": 210, "total_steps": 996, "loss": 0.8355, "learning_rate": 9.018705130666049e-07, "epoch": 0.6320541760722348, "percentage": 21.08, "elapsed_time": "0:56:45", "remaining_time": "3:32:26"}
+{"current_steps": 215, "total_steps": 996, "loss": 0.8244, "learning_rate": 8.970804111535175e-07, "epoch": 0.6471030850263356, "percentage": 21.59, "elapsed_time": "0:57:51", "remaining_time": "3:30:10"}
+{"current_steps": 220, "total_steps": 996, "loss": 0.8336, "learning_rate": 8.921895336846812e-07, "epoch": 0.6621519939804364, "percentage": 22.09, "elapsed_time": "0:58:57", "remaining_time": "3:27:56"}
+{"current_steps": 225, "total_steps": 996, "loss": 0.8152, "learning_rate": 8.871991219222712e-07, "epoch": 0.6772009029345373, "percentage": 22.59, "elapsed_time": "1:00:02", "remaining_time": "3:25:45"}
+{"current_steps": 230, "total_steps": 996, "loss": 0.8235, "learning_rate": 8.821104423894014e-07, "epoch": 0.6922498118886381, "percentage": 23.09, "elapsed_time": "1:01:08", "remaining_time": "3:23:38"}
+{"current_steps": 235, "total_steps": 996, "loss": 0.8226, "learning_rate": 8.769247865486915e-07, "epoch": 0.7072987208427389, "percentage": 23.59, "elapsed_time": "1:02:13", "remaining_time": "3:21:31"}
+{"current_steps": 240, "total_steps": 996, "loss": 0.8341, "learning_rate": 8.716434704745046e-07, "epoch": 0.7223476297968398, "percentage": 24.1, "elapsed_time": "1:03:19", "remaining_time": "3:19:27"}
+{"current_steps": 245, "total_steps": 996, "loss": 0.825, "learning_rate": 8.662678345189396e-07, "epoch": 0.7373965387509406, "percentage": 24.6, "elapsed_time": "1:04:25", "remaining_time": "3:17:27"}
+{"current_steps": 250, "total_steps": 996, "loss": 0.8133, "learning_rate": 8.607992429716608e-07, "epoch": 0.7524454477050414, "percentage": 25.1, "elapsed_time": "1:05:30", "remaining_time": "3:15:29"}
+{"current_steps": 250, "total_steps": 996, "eval_loss": 0.828486442565918, "epoch": 0.7524454477050414, "percentage": 25.1, "elapsed_time": "1:08:15", "remaining_time": "3:23:39"}
+{"current_steps": 255, "total_steps": 996, "loss": 0.8267, "learning_rate": 8.55239083713654e-07, "epoch": 0.7674943566591422, "percentage": 25.6, "elapsed_time": "1:09:20", "remaining_time": "3:21:29"}
+{"current_steps": 260, "total_steps": 996, "loss": 0.8336, "learning_rate": 8.495887678649932e-07, "epoch": 0.782543265613243, "percentage": 26.1, "elapsed_time": "1:10:25", "remaining_time": "3:19:22"}
+{"current_steps": 265, "total_steps": 996, "loss": 0.8371, "learning_rate": 8.438497294267116e-07, "epoch": 0.7975921745673439, "percentage": 26.61, "elapsed_time": "1:11:31", "remaining_time": "3:17:17"}
+{"current_steps": 270, "total_steps": 996, "loss": 0.83, "learning_rate": 8.38023424916864e-07, "epoch": 0.8126410835214447, "percentage": 27.11, "elapsed_time": "1:12:36", "remaining_time": "3:15:15"}
+{"current_steps": 275, "total_steps": 996, "loss": 0.8231, "learning_rate": 8.321113330008756e-07, "epoch": 0.8276899924755455, "percentage": 27.61, "elapsed_time": "1:13:42", "remaining_time": "3:13:15"}
+{"current_steps": 280, "total_steps": 996, "loss": 0.8283, "learning_rate": 8.261149541162691e-07, "epoch": 0.8427389014296464, "percentage": 28.11, "elapsed_time": "1:14:47", "remaining_time": "3:11:16"}
+{"current_steps": 285, "total_steps": 996, "loss": 0.8333, "learning_rate": 8.20035810091867e-07, "epoch": 0.8577878103837472, "percentage": 28.61, "elapsed_time": "1:15:53", "remaining_time": "3:09:19"}
+{"current_steps": 290, "total_steps": 996, "loss": 0.8215, "learning_rate": 8.13875443761565e-07, "epoch": 0.872836719337848, "percentage": 29.12, "elapsed_time": "1:16:58", "remaining_time": "3:07:23"}
+{"current_steps": 295, "total_steps": 996, "loss": 0.8127, "learning_rate": 8.076354185727734e-07, "epoch": 0.8878856282919488, "percentage": 29.62, "elapsed_time": "1:18:03", "remaining_time": "3:05:30"}
+{"current_steps": 300, "total_steps": 996, "loss": 0.8114, "learning_rate": 8.013173181896282e-07, "epoch": 0.9029345372460497, "percentage": 30.12, "elapsed_time": "1:19:09", "remaining_time": "3:03:38"}
+{"current_steps": 300, "total_steps": 996, "eval_loss": 0.8188709616661072, "epoch": 0.9029345372460497, "percentage": 30.12, "elapsed_time": "1:21:53", "remaining_time": "3:09:58"}
+{"current_steps": 305, "total_steps": 996, "loss": 0.8245, "learning_rate": 7.94922746091071e-07, "epoch": 0.9179834462001505, "percentage": 30.62, "elapsed_time": "1:22:59", "remaining_time": "3:08:00"}
+{"current_steps": 310, "total_steps": 996, "loss": 0.8031, "learning_rate": 7.884533251638999e-07, "epoch": 0.9330323551542513, "percentage": 31.12, "elapsed_time": "1:24:04", "remaining_time": "3:06:02"}
+{"current_steps": 315, "total_steps": 996, "loss": 0.792, "learning_rate": 7.819106972908949e-07, "epoch": 0.9480812641083521, "percentage": 31.63, "elapsed_time": "1:25:09", "remaining_time": "3:04:05"}
+{"current_steps": 320, "total_steps": 996, "loss": 0.8073, "learning_rate": 7.752965229341219e-07, "epoch": 0.963130173062453, "percentage": 32.13, "elapsed_time": "1:26:14", "remaining_time": "3:02:11"}
+{"current_steps": 325, "total_steps": 996, "loss": 0.8091, "learning_rate": 7.686124807135228e-07, "epoch": 0.9781790820165538, "percentage": 32.63, "elapsed_time": "1:27:20", "remaining_time": "3:00:19"}
+{"current_steps": 330, "total_steps": 996, "loss": 0.812, "learning_rate": 7.618602669808957e-07, "epoch": 0.9932279909706546, "percentage": 33.13, "elapsed_time": "1:28:26", "remaining_time": "2:58:29"}
+{"current_steps": 335, "total_steps": 996, "loss": 0.7794, "learning_rate": 7.550415953893756e-07, "epoch": 1.0082768999247556, "percentage": 33.63, "elapsed_time": "1:29:31", "remaining_time": "2:56:38"}
+{"current_steps": 340, "total_steps": 996, "loss": 0.7534, "learning_rate": 7.481581964585244e-07, "epoch": 1.0233258088788564, "percentage": 34.14, "elapsed_time": "1:30:37", "remaining_time": "2:54:51"}
+{"current_steps": 345, "total_steps": 996, "loss": 0.7473, "learning_rate": 7.412118171351395e-07, "epoch": 1.0383747178329572, "percentage": 34.64, "elapsed_time": "1:31:43", "remaining_time": "2:53:04"}
+{"current_steps": 350, "total_steps": 996, "loss": 0.7379, "learning_rate": 7.342042203498951e-07, "epoch": 1.053423626787058, "percentage": 35.14, "elapsed_time": "1:32:48", "remaining_time": "2:51:18"}
+{"current_steps": 350, "total_steps": 996, "eval_loss": 0.8137179613113403, "epoch": 1.053423626787058, "percentage": 35.14, "elapsed_time": "1:35:32", "remaining_time": "2:56:20"}
+{"current_steps": 355, "total_steps": 996, "loss": 0.757, "learning_rate": 7.271371845699241e-07, "epoch": 1.0684725357411589, "percentage": 35.64, "elapsed_time": "1:36:38", "remaining_time": "2:54:30"}
+{"current_steps": 360, "total_steps": 996, "loss": 0.7405, "learning_rate": 7.200125033474598e-07, "epoch": 1.0835214446952597, "percentage": 36.14, "elapsed_time": "1:37:44", "remaining_time": "2:52:39"}
+{"current_steps": 365, "total_steps": 996, "loss": 0.7424, "learning_rate": 7.128319848646477e-07, "epoch": 1.0985703536493605, "percentage": 36.65, "elapsed_time": "1:38:49", "remaining_time": "2:50:51"}
+{"current_steps": 370, "total_steps": 996, "loss": 0.7557, "learning_rate": 7.055974514746445e-07, "epoch": 1.1136192626034613, "percentage": 37.15, "elapsed_time": "1:39:55", "remaining_time": "2:49:04"}
+{"current_steps": 375, "total_steps": 996, "loss": 0.7595, "learning_rate": 6.983107392391202e-07, "epoch": 1.1286681715575622, "percentage": 37.65, "elapsed_time": "1:41:00", "remaining_time": "2:47:16"}
+{"current_steps": 380, "total_steps": 996, "loss": 0.7411, "learning_rate": 6.909736974622826e-07, "epoch": 1.143717080511663, "percentage": 38.15, "elapsed_time": "1:42:05", "remaining_time": "2:45:30"}
+{"current_steps": 385, "total_steps": 996, "loss": 0.7415, "learning_rate": 6.835881882215395e-07, "epoch": 1.1587659894657638, "percentage": 38.65, "elapsed_time": "1:43:11", "remaining_time": "2:43:45"}
+{"current_steps": 390, "total_steps": 996, "loss": 0.7317, "learning_rate": 6.761560858949192e-07, "epoch": 1.1738148984198646, "percentage": 39.16, "elapsed_time": "1:44:17", "remaining_time": "2:42:02"}
+{"current_steps": 395, "total_steps": 996, "loss": 0.7537, "learning_rate": 6.686792766853705e-07, "epoch": 1.1888638073739655, "percentage": 39.66, "elapsed_time": "1:45:22", "remaining_time": "2:40:20"}
+{"current_steps": 400, "total_steps": 996, "loss": 0.7416, "learning_rate": 6.611596581420599e-07, "epoch": 1.2039127163280663, "percentage": 40.16, "elapsed_time": "1:46:27", "remaining_time": "2:38:37"}
+{"current_steps": 400, "total_steps": 996, "eval_loss": 0.8082437515258789, "epoch": 1.2039127163280663, "percentage": 40.16, "elapsed_time": "1:49:11", "remaining_time": "2:42:41"}
+{"current_steps": 405, "total_steps": 996, "loss": 0.7295, "learning_rate": 6.53599138678791e-07, "epoch": 1.2189616252821671, "percentage": 40.66, "elapsed_time": "1:50:16", "remaining_time": "2:40:54"}
+{"current_steps": 410, "total_steps": 996, "loss": 0.7419, "learning_rate": 6.459996370896652e-07, "epoch": 1.234010534236268, "percentage": 41.16, "elapsed_time": "1:51:21", "remaining_time": "2:39:09"}
+{"current_steps": 415, "total_steps": 996, "loss": 0.7348, "learning_rate": 6.383630820621081e-07, "epoch": 1.2490594431903688, "percentage": 41.67, "elapsed_time": "1:52:26", "remaining_time": "2:37:25"}
+{"current_steps": 420, "total_steps": 996, "loss": 0.7456, "learning_rate": 6.306914116873862e-07, "epoch": 1.2641083521444696, "percentage": 42.17, "elapsed_time": "1:53:31", "remaining_time": "2:35:41"}
+{"current_steps": 425, "total_steps": 996, "loss": 0.7399, "learning_rate": 6.22986572968736e-07, "epoch": 1.2791572610985704, "percentage": 42.67, "elapsed_time": "1:54:37", "remaining_time": "2:33:59"}
+{"current_steps": 430, "total_steps": 996, "loss": 0.7478, "learning_rate": 6.152505213272307e-07, "epoch": 1.2942061700526712, "percentage": 43.17, "elapsed_time": "1:55:42", "remaining_time": "2:32:18"}
+{"current_steps": 435, "total_steps": 996, "loss": 0.7348, "learning_rate": 6.074852201055121e-07, "epoch": 1.309255079006772, "percentage": 43.67, "elapsed_time": "1:56:48", "remaining_time": "2:30:38"}
+{"current_steps": 440, "total_steps": 996, "loss": 0.7367, "learning_rate": 5.996926400695113e-07, "epoch": 1.324303987960873, "percentage": 44.18, "elapsed_time": "1:57:53", "remaining_time": "2:28:58"}
+{"current_steps": 445, "total_steps": 996, "loss": 0.7452, "learning_rate": 5.918747589082852e-07, "epoch": 1.3393528969149737, "percentage": 44.68, "elapsed_time": "1:58:57", "remaining_time": "2:27:17"}
+{"current_steps": 450, "total_steps": 996, "loss": 0.7623, "learning_rate": 5.840335607320963e-07, "epoch": 1.3544018058690745, "percentage": 45.18, "elapsed_time": "2:00:03", "remaining_time": "2:25:39"}
+{"current_steps": 450, "total_steps": 996, "eval_loss": 0.8033472299575806, "epoch": 1.3544018058690745, "percentage": 45.18, "elapsed_time": "2:02:47", "remaining_time": "2:28:58"}
+{"current_steps": 455, "total_steps": 996, "loss": 0.7431, "learning_rate": 5.761710355688627e-07, "epoch": 1.3694507148231754, "percentage": 45.68, "elapsed_time": "2:03:53", "remaining_time": "2:27:18"}
+{"current_steps": 460, "total_steps": 996, "loss": 0.7464, "learning_rate": 5.682891788591065e-07, "epoch": 1.3844996237772762, "percentage": 46.18, "elapsed_time": "2:04:59", "remaining_time": "2:25:37"}
+{"current_steps": 465, "total_steps": 996, "loss": 0.7357, "learning_rate": 5.603899909495283e-07, "epoch": 1.399548532731377, "percentage": 46.69, "elapsed_time": "2:06:04", "remaining_time": "2:23:58"}
+{"current_steps": 470, "total_steps": 996, "loss": 0.735, "learning_rate": 5.52475476585336e-07, "epoch": 1.4145974416854779, "percentage": 47.19, "elapsed_time": "2:07:09", "remaining_time": "2:22:18"}
+{"current_steps": 475, "total_steps": 996, "loss": 0.7318, "learning_rate": 5.445476444014591e-07, "epoch": 1.4296463506395787, "percentage": 47.69, "elapsed_time": "2:08:15", "remaining_time": "2:20:40"}
+{"current_steps": 480, "total_steps": 996, "loss": 0.7484, "learning_rate": 5.366085064127734e-07, "epoch": 1.4446952595936795, "percentage": 48.19, "elapsed_time": "2:09:20", "remaining_time": "2:19:02"}
+{"current_steps": 485, "total_steps": 996, "loss": 0.7435, "learning_rate": 5.286600775034699e-07, "epoch": 1.4597441685477803, "percentage": 48.69, "elapsed_time": "2:10:26", "remaining_time": "2:17:25"}
+{"current_steps": 490, "total_steps": 996, "loss": 0.7378, "learning_rate": 5.207043749156944e-07, "epoch": 1.4747930775018812, "percentage": 49.2, "elapsed_time": "2:11:31", "remaining_time": "2:15:49"}
+{"current_steps": 495, "total_steps": 996, "loss": 0.7418, "learning_rate": 5.127434177375893e-07, "epoch": 1.489841986455982, "percentage": 49.7, "elapsed_time": "2:12:36", "remaining_time": "2:14:13"}
+{"current_steps": 500, "total_steps": 996, "loss": 0.7158, "learning_rate": 5.047792263908659e-07, "epoch": 1.5048908954100828, "percentage": 50.2, "elapsed_time": "2:13:42", "remaining_time": "2:12:38"}
+{"current_steps": 500, "total_steps": 996, "eval_loss": 0.7987317442893982, "epoch": 1.5048908954100828, "percentage": 50.2, "elapsed_time": "2:16:26", "remaining_time": "2:15:20"}
+{"current_steps": 505, "total_steps": 996, "loss": 0.7431, "learning_rate": 4.968138221180401e-07, "epoch": 1.5199398043641836, "percentage": 50.7, "elapsed_time": "2:17:31", "remaining_time": "2:13:42"}
+{"current_steps": 510, "total_steps": 996, "loss": 0.7007, "learning_rate": 4.888492264694565e-07, "epoch": 1.5349887133182845, "percentage": 51.2, "elapsed_time": "2:18:36", "remaining_time": "2:12:05"}
+{"current_steps": 515, "total_steps": 996, "loss": 0.7364, "learning_rate": 4.808874607902397e-07, "epoch": 1.5500376222723853, "percentage": 51.71, "elapsed_time": "2:19:42", "remaining_time": "2:10:28"}
+{"current_steps": 520, "total_steps": 996, "loss": 0.7267, "learning_rate": 4.7293054570729126e-07, "epoch": 1.565086531226486, "percentage": 52.21, "elapsed_time": "2:20:47", "remaining_time": "2:08:52"}
+{"current_steps": 525, "total_steps": 996, "loss": 0.7298, "learning_rate": 4.649805006164743e-07, "epoch": 1.580135440180587, "percentage": 52.71, "elapsed_time": "2:21:52", "remaining_time": "2:07:17"}
+{"current_steps": 530, "total_steps": 996, "loss": 0.7429, "learning_rate": 4.5703934317010727e-07, "epoch": 1.5951843491346878, "percentage": 53.21, "elapsed_time": "2:22:58", "remaining_time": "2:05:42"}
+{"current_steps": 535, "total_steps": 996, "loss": 0.7337, "learning_rate": 4.491090887649024e-07, "epoch": 1.6102332580887886, "percentage": 53.71, "elapsed_time": "2:24:03", "remaining_time": "2:04:08"}
+{"current_steps": 540, "total_steps": 996, "loss": 0.7299, "learning_rate": 4.4119175003047407e-07, "epoch": 1.6252821670428894, "percentage": 54.22, "elapsed_time": "2:25:08", "remaining_time": "2:02:33"}
+{"current_steps": 545, "total_steps": 996, "loss": 0.7321, "learning_rate": 4.3328933631855195e-07, "epoch": 1.6403310759969902, "percentage": 54.72, "elapsed_time": "2:26:12", "remaining_time": "2:00:59"}
+{"current_steps": 550, "total_steps": 996, "loss": 0.7322, "learning_rate": 4.2540385319302524e-07, "epoch": 1.655379984951091, "percentage": 55.22, "elapsed_time": "2:27:18", "remaining_time": "1:59:27"}
+{"current_steps": 550, "total_steps": 996, "eval_loss": 0.7954748272895813, "epoch": 1.655379984951091, "percentage": 55.22, "elapsed_time": "2:30:02", "remaining_time": "2:01:40"}
+{"current_steps": 555, "total_steps": 996, "loss": 0.7457, "learning_rate": 4.175373019209468e-07, "epoch": 1.670428893905192, "percentage": 55.72, "elapsed_time": "2:31:08", "remaining_time": "2:00:05"}
+{"current_steps": 560, "total_steps": 996, "loss": 0.7386, "learning_rate": 4.0969167896463046e-07, "epoch": 1.6854778028592927, "percentage": 56.22, "elapsed_time": "2:32:13", "remaining_time": "1:58:31"}
+{"current_steps": 565, "total_steps": 996, "loss": 0.724, "learning_rate": 4.018689754749648e-07, "epoch": 1.7005267118133935, "percentage": 56.73, "elapsed_time": "2:33:19", "remaining_time": "1:56:57"}
+{"current_steps": 570, "total_steps": 996, "loss": 0.7441, "learning_rate": 3.9407117678607756e-07, "epoch": 1.7155756207674944, "percentage": 57.23, "elapsed_time": "2:34:24", "remaining_time": "1:55:24"}
+{"current_steps": 575, "total_steps": 996, "loss": 0.7249, "learning_rate": 3.8630026191147405e-07, "epoch": 1.7306245297215952, "percentage": 57.73, "elapsed_time": "2:35:31", "remaining_time": "1:53:51"}
+{"current_steps": 580, "total_steps": 996, "loss": 0.6972, "learning_rate": 3.78558203041782e-07, "epoch": 1.745673438675696, "percentage": 58.23, "elapsed_time": "2:36:36", "remaining_time": "1:52:19"}
+{"current_steps": 585, "total_steps": 996, "loss": 0.7302, "learning_rate": 3.7084696504422525e-07, "epoch": 1.7607223476297968, "percentage": 58.73, "elapsed_time": "2:37:41", "remaining_time": "1:50:47"}
+{"current_steps": 590, "total_steps": 996, "loss": 0.7424, "learning_rate": 3.6316850496395855e-07, "epoch": 1.7757712565838977, "percentage": 59.24, "elapsed_time": "2:38:46", "remaining_time": "1:49:15"}
+{"current_steps": 595, "total_steps": 996, "loss": 0.7252, "learning_rate": 3.555247715273867e-07, "epoch": 1.7908201655379985, "percentage": 59.74, "elapsed_time": "2:39:51", "remaining_time": "1:47:44"}
+{"current_steps": 600, "total_steps": 996, "loss": 0.7148, "learning_rate": 3.4791770464759347e-07, "epoch": 1.8058690744920993, "percentage": 60.24, "elapsed_time": "2:40:57", "remaining_time": "1:46:13"}
+{"current_steps": 600, "total_steps": 996, "eval_loss": 0.7919732332229614, "epoch": 1.8058690744920993, "percentage": 60.24, "elapsed_time": "2:43:41", "remaining_time": "1:48:01"}
+{"current_steps": 605, "total_steps": 996, "loss": 0.7377, "learning_rate": 3.4034923493201007e-07, "epoch": 1.8209179834462002, "percentage": 60.74, "elapsed_time": "2:44:46", "remaining_time": "1:46:29"}
+{"current_steps": 610, "total_steps": 996, "loss": 0.7385, "learning_rate": 3.3282128319244237e-07, "epoch": 1.835966892400301, "percentage": 61.24, "elapsed_time": "2:45:52", "remaining_time": "1:44:57"}
+{"current_steps": 615, "total_steps": 996, "loss": 0.7197, "learning_rate": 3.2533575995758694e-07, "epoch": 1.8510158013544018, "percentage": 61.75, "elapsed_time": "2:46:57", "remaining_time": "1:43:26"}
+{"current_steps": 620, "total_steps": 996, "loss": 0.7018, "learning_rate": 3.178945649881543e-07, "epoch": 1.8660647103085026, "percentage": 62.25, "elapsed_time": "2:48:03", "remaining_time": "1:41:55"}
+{"current_steps": 625, "total_steps": 996, "loss": 0.7246, "learning_rate": 3.1049958679472645e-07, "epoch": 1.8811136192626035, "percentage": 62.75, "elapsed_time": "2:49:09", "remaining_time": "1:40:24"}
+{"current_steps": 630, "total_steps": 996, "loss": 0.7336, "learning_rate": 3.031527021584701e-07, "epoch": 1.8961625282167043, "percentage": 63.25, "elapsed_time": "2:50:14", "remaining_time": "1:38:54"}
+{"current_steps": 635, "total_steps": 996, "loss": 0.7169, "learning_rate": 2.9585577565482484e-07, "epoch": 1.911211437170805, "percentage": 63.76, "elapsed_time": "2:51:19", "remaining_time": "1:37:24"}
+{"current_steps": 640, "total_steps": 996, "loss": 0.7259, "learning_rate": 2.886106591802908e-07, "epoch": 1.926260346124906, "percentage": 64.26, "elapsed_time": "2:52:24", "remaining_time": "1:35:54"}
+{"current_steps": 645, "total_steps": 996, "loss": 0.7168, "learning_rate": 2.814191914824332e-07, "epoch": 1.9413092550790068, "percentage": 64.76, "elapsed_time": "2:53:29", "remaining_time": "1:34:24"}
+{"current_steps": 650, "total_steps": 996, "loss": 0.71, "learning_rate": 2.7428319769322415e-07, "epoch": 1.9563581640331076, "percentage": 65.26, "elapsed_time": "2:54:35", "remaining_time": "1:32:56"}
+{"current_steps": 650, "total_steps": 996, "eval_loss": 0.7893925309181213, "epoch": 1.9563581640331076, "percentage": 65.26, "elapsed_time": "2:57:19", "remaining_time": "1:34:23"}
+{"current_steps": 655, "total_steps": 996, "loss": 0.7041, "learning_rate": 2.672044888658399e-07, "epoch": 1.9714070729872084, "percentage": 65.76, "elapsed_time": "2:58:25", "remaining_time": "1:32:53"}
+{"current_steps": 660, "total_steps": 996, "loss": 0.7285, "learning_rate": 2.6018486151503213e-07, "epoch": 1.9864559819413092, "percentage": 66.27, "elapsed_time": "2:59:31", "remaining_time": "1:31:23"}
+{"current_steps": 665, "total_steps": 996, "loss": 0.7113, "learning_rate": 2.532260971611867e-07, "epoch": 2.00150489089541, "percentage": 66.77, "elapsed_time": "3:00:37", "remaining_time": "1:29:54"}
+{"current_steps": 670, "total_steps": 996, "loss": 0.6883, "learning_rate": 2.4632996187819034e-07, "epoch": 2.016553799849511, "percentage": 67.27, "elapsed_time": "3:01:42", "remaining_time": "1:28:24"}
+{"current_steps": 675, "total_steps": 996, "loss": 0.6756, "learning_rate": 2.394982058452165e-07, "epoch": 2.0316027088036117, "percentage": 67.77, "elapsed_time": "3:02:47", "remaining_time": "1:26:55"}
+{"current_steps": 680, "total_steps": 996, "loss": 0.6762, "learning_rate": 2.3273256290254402e-07, "epoch": 2.0466516177577128, "percentage": 68.27, "elapsed_time": "3:03:53", "remaining_time": "1:25:27"}
+{"current_steps": 685, "total_steps": 996, "loss": 0.6895, "learning_rate": 2.2603475011152517e-07, "epoch": 2.0617005267118134, "percentage": 68.78, "elapsed_time": "3:04:58", "remaining_time": "1:23:59"}
+{"current_steps": 690, "total_steps": 996, "loss": 0.6607, "learning_rate": 2.1940646731880885e-07, "epoch": 2.0767494356659144, "percentage": 69.28, "elapsed_time": "3:06:04", "remaining_time": "1:22:31"}
+{"current_steps": 695, "total_steps": 996, "loss": 0.6789, "learning_rate": 2.1284939672493506e-07, "epoch": 2.091798344620015, "percentage": 69.78, "elapsed_time": "3:07:10", "remaining_time": "1:21:03"}
+{"current_steps": 700, "total_steps": 996, "loss": 0.6651, "learning_rate": 2.0636520245740708e-07, "epoch": 2.106847253574116, "percentage": 70.28, "elapsed_time": "3:08:14", "remaining_time": "1:19:36"}
+{"current_steps": 700, "total_steps": 996, "eval_loss": 0.7947185039520264, "epoch": 2.106847253574116, "percentage": 70.28, "elapsed_time": "3:10:59", "remaining_time": "1:20:45"}
+{"current_steps": 705, "total_steps": 996, "loss": 0.6809, "learning_rate": 1.9995553014834986e-07, "epoch": 2.1218961625282167, "percentage": 70.78, "elapsed_time": "3:12:04", "remaining_time": "1:19:16"}
+{"current_steps": 710, "total_steps": 996, "loss": 0.6864, "learning_rate": 1.9362200651686406e-07, "epoch": 2.1369450714823177, "percentage": 71.29, "elapsed_time": "3:13:09", "remaining_time": "1:17:48"}
+{"current_steps": 715, "total_steps": 996, "loss": 0.6987, "learning_rate": 1.873662389561771e-07, "epoch": 2.1519939804364183, "percentage": 71.79, "elapsed_time": "3:14:15", "remaining_time": "1:16:20"}
+{"current_steps": 720, "total_steps": 996, "loss": 0.6801, "learning_rate": 1.8118981512570254e-07, "epoch": 2.1670428893905194, "percentage": 72.29, "elapsed_time": "3:15:20", "remaining_time": "1:14:52"}
+{"current_steps": 725, "total_steps": 996, "loss": 0.6826, "learning_rate": 1.750943025481046e-07, "epoch": 2.18209179834462, "percentage": 72.79, "elapsed_time": "3:16:25", "remaining_time": "1:13:25"}
+{"current_steps": 730, "total_steps": 996, "loss": 0.6904, "learning_rate": 1.6908124821147517e-07, "epoch": 2.197140707298721, "percentage": 73.29, "elapsed_time": "3:17:31", "remaining_time": "1:11:58"}
+{"current_steps": 735, "total_steps": 996, "loss": 0.6798, "learning_rate": 1.631521781767214e-07, "epoch": 2.2121896162528216, "percentage": 73.8, "elapsed_time": "3:18:36", "remaining_time": "1:10:31"}
+{"current_steps": 740, "total_steps": 996, "loss": 0.6776, "learning_rate": 1.5730859719026535e-07, "epoch": 2.2272385252069227, "percentage": 74.3, "elapsed_time": "3:19:42", "remaining_time": "1:09:05"}
+{"current_steps": 745, "total_steps": 996, "loss": 0.6805, "learning_rate": 1.5155198830215144e-07, "epoch": 2.2422874341610233, "percentage": 74.8, "elapsed_time": "3:20:48", "remaining_time": "1:07:39"}
+{"current_steps": 750, "total_steps": 996, "loss": 0.6684, "learning_rate": 1.4588381248966185e-07, "epoch": 2.2573363431151243, "percentage": 75.3, "elapsed_time": "3:21:53", "remaining_time": "1:06:13"}
+{"current_steps": 750, "total_steps": 996, "eval_loss": 0.7936417460441589, "epoch": 2.2573363431151243, "percentage": 75.3, "elapsed_time": "3:24:37", "remaining_time": "1:07:06"}
+{"current_steps": 755, "total_steps": 996, "loss": 0.7012, "learning_rate": 1.4030550828653354e-07, "epoch": 2.272385252069225, "percentage": 75.8, "elapsed_time": "3:25:43", "remaining_time": "1:05:40"}
+{"current_steps": 760, "total_steps": 996, "loss": 0.6778, "learning_rate": 1.3481849141786977e-07, "epoch": 2.287434161023326, "percentage": 76.31, "elapsed_time": "3:26:49", "remaining_time": "1:04:13"}
+{"current_steps": 765, "total_steps": 996, "loss": 0.6775, "learning_rate": 1.294241544408425e-07, "epoch": 2.3024830699774266, "percentage": 76.81, "elapsed_time": "3:27:54", "remaining_time": "1:02:46"}
+{"current_steps": 770, "total_steps": 996, "loss": 0.6868, "learning_rate": 1.241238663912727e-07, "epoch": 2.3175319789315276, "percentage": 77.31, "elapsed_time": "3:29:01", "remaining_time": "1:01:20"}
+{"current_steps": 775, "total_steps": 996, "loss": 0.6694, "learning_rate": 1.1891897243618183e-07, "epoch": 2.3325808878856282, "percentage": 77.81, "elapsed_time": "3:30:07", "remaining_time": "0:59:55"}
+{"current_steps": 780, "total_steps": 996, "loss": 0.6779, "learning_rate": 1.1381079353239915e-07, "epoch": 2.3476297968397293, "percentage": 78.31, "elapsed_time": "3:31:13", "remaining_time": "0:58:29"}
+{"current_steps": 785, "total_steps": 996, "loss": 0.6726, "learning_rate": 1.0880062609131485e-07, "epoch": 2.36267870579383, "percentage": 78.82, "elapsed_time": "3:32:18", "remaining_time": "0:57:03"}
+{"current_steps": 790, "total_steps": 996, "loss": 0.6796, "learning_rate": 1.0388974164986247e-07, "epoch": 2.377727614747931, "percentage": 79.32, "elapsed_time": "3:33:24", "remaining_time": "0:55:38"}
+{"current_steps": 795, "total_steps": 996, "loss": 0.6835, "learning_rate": 9.907938654781306e-08, "epoch": 2.3927765237020315, "percentage": 79.82, "elapsed_time": "3:34:29", "remaining_time": "0:54:13"}
+{"current_steps": 800, "total_steps": 996, "loss": 0.6826, "learning_rate": 9.437078161146589e-08, "epoch": 2.4078254326561326, "percentage": 80.32, "elapsed_time": "3:35:34", "remaining_time": "0:52:48"}
+{"current_steps": 800, "total_steps": 996, "eval_loss": 0.7927989363670349, "epoch": 2.4078254326561326, "percentage": 80.32, "elapsed_time": "3:38:22", "remaining_time": "0:53:30"}
+{"current_steps": 805, "total_steps": 996, "loss": 0.6795, "learning_rate": 8.976512184381246e-08, "epoch": 2.422874341610233, "percentage": 80.82, "elapsed_time": "3:39:28", "remaining_time": "0:52:04"}
+{"current_steps": 810, "total_steps": 996, "loss": 0.6898, "learning_rate": 8.526357612125573e-08, "epoch": 2.4379232505643342, "percentage": 81.33, "elapsed_time": "3:40:34", "remaining_time": "0:50:39"}
+{"current_steps": 815, "total_steps": 996, "loss": 0.7046, "learning_rate": 8.086728689695921e-08, "epoch": 2.452972159518435, "percentage": 81.83, "elapsed_time": "3:41:40", "remaining_time": "0:49:13"}
+{"current_steps": 820, "total_steps": 996, "loss": 0.661, "learning_rate": 7.657736991090263e-08, "epoch": 2.468021068472536, "percentage": 82.33, "elapsed_time": "3:42:46", "remaining_time": "0:47:48"}
+{"current_steps": 825, "total_steps": 996, "loss": 0.6742, "learning_rate": 7.239491390671631e-08, "epoch": 2.4830699774266365, "percentage": 82.83, "elapsed_time": "3:43:52", "remaining_time": "0:46:24"}
+{"current_steps": 830, "total_steps": 996, "loss": 0.6672, "learning_rate": 6.832098035536759e-08, "epoch": 2.4981188863807375, "percentage": 83.33, "elapsed_time": "3:44:58", "remaining_time": "0:44:59"}
+{"current_steps": 835, "total_steps": 996, "loss": 0.6754, "learning_rate": 6.435660318576935e-08, "epoch": 2.513167795334838, "percentage": 83.84, "elapsed_time": "3:46:04", "remaining_time": "0:43:35"}
+{"current_steps": 840, "total_steps": 996, "loss": 0.6824, "learning_rate": 6.0502788522377e-08, "epoch": 2.528216704288939, "percentage": 84.34, "elapsed_time": "3:47:10", "remaining_time": "0:42:11"}
+{"current_steps": 845, "total_steps": 996, "loss": 0.6716, "learning_rate": 5.676051442984325e-08, "epoch": 2.54326561324304, "percentage": 84.84, "elapsed_time": "3:48:14", "remaining_time": "0:40:47"}
+{"current_steps": 850, "total_steps": 996, "loss": 0.6711, "learning_rate": 5.313073066479379e-08, "epoch": 2.558314522197141, "percentage": 85.34, "elapsed_time": "3:49:19", "remaining_time": "0:39:23"}
+{"current_steps": 850, "total_steps": 996, "eval_loss": 0.7919635772705078, "epoch": 2.558314522197141, "percentage": 85.34, "elapsed_time": "3:52:03", "remaining_time": "0:39:51"}
+{"current_steps": 855, "total_steps": 996, "loss": 0.6806, "learning_rate": 4.961435843478751e-08, "epoch": 2.5733634311512414, "percentage": 85.84, "elapsed_time": "3:53:09", "remaining_time": "0:38:26"}
+{"current_steps": 860, "total_steps": 996, "loss": 0.6535, "learning_rate": 4.621229016452155e-08, "epoch": 2.5884123401053425, "percentage": 86.35, "elapsed_time": "3:54:14", "remaining_time": "0:37:02"}
+{"current_steps": 865, "total_steps": 996, "loss": 0.673, "learning_rate": 4.2925389269341916e-08, "epoch": 2.603461249059443, "percentage": 86.85, "elapsed_time": "3:55:20", "remaining_time": "0:35:38"}
+{"current_steps": 870, "total_steps": 996, "loss": 0.6709, "learning_rate": 3.975448993611652e-08, "epoch": 2.618510158013544, "percentage": 87.35, "elapsed_time": "3:56:26", "remaining_time": "0:34:14"}
+{"current_steps": 875, "total_steps": 996, "loss": 0.6619, "learning_rate": 3.67003969115251e-08, "epoch": 2.6335590669676447, "percentage": 87.85, "elapsed_time": "3:57:30", "remaining_time": "0:32:50"}
+{"current_steps": 880, "total_steps": 996, "loss": 0.6848, "learning_rate": 3.376388529782215e-08, "epoch": 2.648607975921746, "percentage": 88.35, "elapsed_time": "3:58:36", "remaining_time": "0:31:27"}
+{"current_steps": 885, "total_steps": 996, "loss": 0.6853, "learning_rate": 3.094570035612226e-08, "epoch": 2.6636568848758464, "percentage": 88.86, "elapsed_time": "3:59:42", "remaining_time": "0:30:03"}
+{"current_steps": 890, "total_steps": 996, "loss": 0.6745, "learning_rate": 2.8246557317259723e-08, "epoch": 2.6787057938299474, "percentage": 89.36, "elapsed_time": "4:00:48", "remaining_time": "0:28:40"}
+{"current_steps": 895, "total_steps": 996, "loss": 0.6577, "learning_rate": 2.5667141200268694e-08, "epoch": 2.693754702784048, "percentage": 89.86, "elapsed_time": "4:01:54", "remaining_time": "0:27:17"}
+{"current_steps": 900, "total_steps": 996, "loss": 0.6757, "learning_rate": 2.3208106638531842e-08, "epoch": 2.708803611738149, "percentage": 90.36, "elapsed_time": "4:02:59", "remaining_time": "0:25:55"}
+{"current_steps": 900, "total_steps": 996, "eval_loss": 0.7914727926254272, "epoch": 2.708803611738149, "percentage": 90.36, "elapsed_time": "4:05:44", "remaining_time": "0:26:12"}
+{"current_steps": 905, "total_steps": 996, "loss": 0.6736, "learning_rate": 2.087007771363969e-08, "epoch": 2.7238525206922497, "percentage": 90.86, "elapsed_time": "4:06:50", "remaining_time": "0:24:49"}
+{"current_steps": 910, "total_steps": 996, "loss": 0.6729, "learning_rate": 1.8653647797004236e-08, "epoch": 2.7389014296463507, "percentage": 91.37, "elapsed_time": "4:07:55", "remaining_time": "0:23:25"}
+{"current_steps": 915, "total_steps": 996, "loss": 0.6841, "learning_rate": 1.655937939926655e-08, "epoch": 2.7539503386004514, "percentage": 91.87, "elapsed_time": "4:08:59", "remaining_time": "0:22:02"}
+{"current_steps": 920, "total_steps": 996, "loss": 0.6917, "learning_rate": 1.4587804027536454e-08, "epoch": 2.7689992475545524, "percentage": 92.37, "elapsed_time": "4:10:04", "remaining_time": "0:20:39"}
+{"current_steps": 925, "total_steps": 996, "loss": 0.6751, "learning_rate": 1.2739422050500436e-08, "epoch": 2.784048156508653, "percentage": 92.87, "elapsed_time": "4:11:09", "remaining_time": "0:19:16"}
+{"current_steps": 930, "total_steps": 996, "loss": 0.6738, "learning_rate": 1.101470257143261e-08, "epoch": 2.799097065462754, "percentage": 93.37, "elapsed_time": "4:12:13", "remaining_time": "0:17:54"}
+{"current_steps": 935, "total_steps": 996, "loss": 0.6952, "learning_rate": 9.414083309140453e-09, "epoch": 2.8141459744168547, "percentage": 93.88, "elapsed_time": "4:13:19", "remaining_time": "0:16:31"}
+{"current_steps": 940, "total_steps": 996, "loss": 0.6761, "learning_rate": 7.93797048687539e-09, "epoch": 2.8291948833709557, "percentage": 94.38, "elapsed_time": "4:14:24", "remaining_time": "0:15:09"}
+{"current_steps": 945, "total_steps": 996, "loss": 0.6932, "learning_rate": 6.5867387292369295e-09, "epoch": 2.8442437923250563, "percentage": 94.88, "elapsed_time": "4:15:29", "remaining_time": "0:13:47"}
+{"current_steps": 950, "total_steps": 996, "loss": 0.6791, "learning_rate": 5.360730967096272e-09, "epoch": 2.8592927012791574, "percentage": 95.38, "elapsed_time": "4:16:35", "remaining_time": "0:12:25"}
+{"current_steps": 950, "total_steps": 996, "eval_loss": 0.7912743091583252, "epoch": 2.8592927012791574, "percentage": 95.38, "elapsed_time": "4:19:19", "remaining_time": "0:12:33"}
+{"current_steps": 955, "total_steps": 996, "loss": 0.6716, "learning_rate": 4.260258350563317e-09, "epoch": 2.874341610233258, "percentage": 95.88, "elapsed_time": "4:20:25", "remaining_time": "0:11:10"}
+{"current_steps": 960, "total_steps": 996, "loss": 0.6917, "learning_rate": 3.285600170019609e-09, "epoch": 2.889390519187359, "percentage": 96.39, "elapsed_time": "4:21:31", "remaining_time": "0:09:48"}
+{"current_steps": 965, "total_steps": 996, "loss": 0.665, "learning_rate": 2.437003785236702e-09, "epoch": 2.9044394281414596, "percentage": 96.89, "elapsed_time": "4:22:36", "remaining_time": "0:08:26"}
+{"current_steps": 970, "total_steps": 996, "loss": 0.6845, "learning_rate": 1.714684562598545e-09, "epoch": 2.9194883370955607, "percentage": 97.39, "elapsed_time": "4:23:41", "remaining_time": "0:07:04"}
+{"current_steps": 975, "total_steps": 996, "loss": 0.6673, "learning_rate": 1.1188258204433144e-09, "epoch": 2.9345372460496613, "percentage": 97.89, "elapsed_time": "4:24:47", "remaining_time": "0:05:42"}
+{"current_steps": 980, "total_steps": 996, "loss": 0.6772, "learning_rate": 6.49578782538851e-10, "epoch": 2.9495861550037623, "percentage": 98.39, "elapsed_time": "4:25:52", "remaining_time": "0:04:20"}
+{"current_steps": 985, "total_steps": 996, "loss": 0.6743, "learning_rate": 3.070625397031401e-10, "epoch": 2.964635063957863, "percentage": 98.9, "elapsed_time": "4:26:57", "remaining_time": "0:02:58"}
+{"current_steps": 990, "total_steps": 996, "loss": 0.6633, "learning_rate": 9.136401958059759e-11, "epoch": 2.979683972911964, "percentage": 99.4, "elapsed_time": "4:28:02", "remaining_time": "0:01:37"}
+{"current_steps": 995, "total_steps": 996, "loss": 0.672, "learning_rate": 2.5379645800516215e-12, "epoch": 2.9947328818660646, "percentage": 99.9, "elapsed_time": "4:29:08", "remaining_time": "0:00:16"}
+{"current_steps": 996, "total_steps": 996, "epoch": 2.9977426636568847, "percentage": 100.0, "elapsed_time": "4:29:52", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1587 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9977426636568847,
+  "eval_steps": 50,
+  "global_step": 996,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015048908954100828,
+      "grad_norm": 18.47044613613669,
+      "learning_rate": 5e-07,
+      "loss": 1.7355,
+      "step": 5
+    },
+    {
+      "epoch": 0.030097817908201655,
+      "grad_norm": 12.86199157181735,
+      "learning_rate": 1e-06,
+      "loss": 1.5959,
+      "step": 10
+    },
+    {
+      "epoch": 0.045146726862302484,
+      "grad_norm": 7.557418173894333,
+      "learning_rate": 9.999365521737421e-07,
+      "loss": 1.2852,
+      "step": 15
+    },
+    {
+      "epoch": 0.06019563581640331,
+      "grad_norm": 4.370427039727891,
+      "learning_rate": 9.99746224797475e-07,
+      "loss": 1.1474,
+      "step": 20
+    },
+    {
+      "epoch": 0.07524454477050414,
+      "grad_norm": 3.7509821509698265,
+      "learning_rate": 9.99429066174632e-07,
+      "loss": 1.0775,
+      "step": 25
+    },
+    {
+      "epoch": 0.09029345372460497,
+      "grad_norm": 3.4862474442533076,
+      "learning_rate": 9.989851567973138e-07,
+      "loss": 1.0181,
+      "step": 30
+    },
+    {
+      "epoch": 0.1053423626787058,
+      "grad_norm": 3.6303816391691863,
+      "learning_rate": 9.984146093258608e-07,
+      "loss": 1.0061,
+      "step": 35
+    },
+    {
+      "epoch": 0.12039127163280662,
+      "grad_norm": 3.379335415407791,
+      "learning_rate": 9.9771756856026e-07,
+      "loss": 0.9556,
+      "step": 40
+    },
+    {
+      "epoch": 0.13544018058690746,
+      "grad_norm": 3.757214111120403,
+      "learning_rate": 9.968942114033973e-07,
+      "loss": 0.9456,
+      "step": 45
+    },
+    {
+      "epoch": 0.1504890895410083,
+      "grad_norm": 3.403304414146967,
+      "learning_rate": 9.959447468161596e-07,
+      "loss": 0.9297,
+      "step": 50
+    },
+    {
+      "epoch": 0.1504890895410083,
+      "eval_loss": 0.939862847328186,
+      "eval_runtime": 164.2799,
+      "eval_samples_per_second": 57.524,
+      "eval_steps_per_second": 0.901,
+      "step": 50
+    },
+    {
+      "epoch": 0.1655379984951091,
+      "grad_norm": 3.5204364554568266,
+      "learning_rate": 9.948694157644042e-07,
+      "loss": 0.9204,
+      "step": 55
+    },
+    {
+      "epoch": 0.18058690744920994,
+      "grad_norm": 3.318644271218084,
+      "learning_rate": 9.936684911578017e-07,
+      "loss": 0.8933,
+      "step": 60
+    },
+    {
+      "epoch": 0.19563581640331076,
+      "grad_norm": 3.7154382360141494,
+      "learning_rate": 9.923422777805751e-07,
+      "loss": 0.9219,
+      "step": 65
+    },
+    {
+      "epoch": 0.2106847253574116,
+      "grad_norm": 3.6290063947255926,
+      "learning_rate": 9.908911122141486e-07,
+      "loss": 0.8946,
+      "step": 70
+    },
+    {
+      "epoch": 0.22573363431151242,
+      "grad_norm": 3.6808742110099466,
+      "learning_rate": 9.893153627517248e-07,
+      "loss": 0.902,
+      "step": 75
+    },
+    {
+      "epoch": 0.24078254326561324,
+      "grad_norm": 3.5301295406592255,
+      "learning_rate": 9.876154293048163e-07,
+      "loss": 0.8924,
+      "step": 80
+    },
+    {
+      "epoch": 0.2558314522197141,
+      "grad_norm": 3.3462246475893123,
+      "learning_rate": 9.857917433017508e-07,
+      "loss": 0.8958,
+      "step": 85
+    },
+    {
+      "epoch": 0.2708803611738149,
+      "grad_norm": 3.487142176575527,
+      "learning_rate": 9.838447675781793e-07,
+      "loss": 0.8881,
+      "step": 90
+    },
+    {
+      "epoch": 0.28592927012791575,
+      "grad_norm": 3.3151772418217402,
+      "learning_rate": 9.817749962596114e-07,
+      "loss": 0.882,
+      "step": 95
+    },
+    {
+      "epoch": 0.3009781790820166,
+      "grad_norm": 3.4456571870576362,
+      "learning_rate": 9.795829546360113e-07,
+      "loss": 0.8675,
+      "step": 100
+    },
+    {
+      "epoch": 0.3009781790820166,
+      "eval_loss": 0.8835354447364807,
+      "eval_runtime": 164.3323,
+      "eval_samples_per_second": 57.505,
+      "eval_steps_per_second": 0.901,
+      "step": 100
+    },
+    {
+      "epoch": 0.3160270880361174,
+      "grad_norm": 3.68930117031382,
+      "learning_rate": 9.77269199028483e-07,
+      "loss": 0.8656,
+      "step": 105
+    },
+    {
+      "epoch": 0.3310759969902182,
+      "grad_norm": 3.7770729679447816,
+      "learning_rate": 9.748343166480822e-07,
+      "loss": 0.8907,
+      "step": 110
+    },
+    {
+      "epoch": 0.34612490594431905,
+      "grad_norm": 3.5934806142622104,
+      "learning_rate": 9.722789254467854e-07,
+      "loss": 0.8678,
+      "step": 115
+    },
+    {
+      "epoch": 0.3611738148984199,
+      "grad_norm": 3.4907829794302447,
+      "learning_rate": 9.696036739606606e-07,
+      "loss": 0.8634,
+      "step": 120
+    },
+    {
+      "epoch": 0.3762227238525207,
+      "grad_norm": 3.7214337808863798,
+      "learning_rate": 9.668092411452735e-07,
+      "loss": 0.8789,
+      "step": 125
+    },
+    {
+      "epoch": 0.3912716328066215,
+      "grad_norm": 3.510784238627902,
+      "learning_rate": 9.638963362033756e-07,
+      "loss": 0.8592,
+      "step": 130
+    },
+    {
+      "epoch": 0.40632054176072235,
+      "grad_norm": 3.3785797508677837,
+      "learning_rate": 9.608656984049132e-07,
+      "loss": 0.8438,
+      "step": 135
+    },
+    {
+      "epoch": 0.4213694507148232,
+      "grad_norm": 3.3458509178809854,
+      "learning_rate": 9.577180968994081e-07,
+      "loss": 0.8544,
+      "step": 140
+    },
+    {
+      "epoch": 0.436418359668924,
+      "grad_norm": 3.4920402952738656,
+      "learning_rate": 9.544543305207546e-07,
+      "loss": 0.8518,
+      "step": 145
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "grad_norm": 3.2912233930311627,
+      "learning_rate": 9.510752275844809e-07,
+      "loss": 0.8457,
+      "step": 150
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "eval_loss": 0.857115626335144,
+      "eval_runtime": 164.1562,
+      "eval_samples_per_second": 57.567,
+      "eval_steps_per_second": 0.902,
+      "step": 150
+    },
+    {
+      "epoch": 0.46651617757712566,
+      "grad_norm": 3.553467076040635,
+      "learning_rate": 9.475816456775312e-07,
+      "loss": 0.8595,
+      "step": 155
+    },
+    {
+      "epoch": 0.4815650865312265,
+      "grad_norm": 3.3686846297763116,
+      "learning_rate": 9.439744714406166e-07,
+      "loss": 0.8392,
+      "step": 160
+    },
+    {
+      "epoch": 0.4966139954853273,
+      "grad_norm": 3.45480960814811,
+      "learning_rate": 9.402546203431947e-07,
+      "loss": 0.8323,
+      "step": 165
+    },
+    {
+      "epoch": 0.5116629044394282,
+      "grad_norm": 3.459267285158168,
+      "learning_rate": 9.364230364511295e-07,
+      "loss": 0.8355,
+      "step": 170
+    },
+    {
+      "epoch": 0.526711813393529,
+      "grad_norm": 3.4121749327302378,
+      "learning_rate": 9.324806921870975e-07,
+      "loss": 0.8537,
+      "step": 175
+    },
+    {
+      "epoch": 0.5417607223476298,
+      "grad_norm": 3.5893222373958524,
+      "learning_rate": 9.284285880837946e-07,
+      "loss": 0.828,
+      "step": 180
+    },
+    {
+      "epoch": 0.5568096313017307,
+      "grad_norm": 3.7134185725142936,
+      "learning_rate": 9.242677525300088e-07,
+      "loss": 0.8346,
+      "step": 185
+    },
+    {
+      "epoch": 0.5718585402558315,
+      "grad_norm": 3.550721543432503,
+      "learning_rate": 9.199992415096259e-07,
+      "loss": 0.832,
+      "step": 190
+    },
+    {
+      "epoch": 0.5869074492099323,
+      "grad_norm": 3.7325735346120728,
+      "learning_rate": 9.156241383336278e-07,
+      "loss": 0.8156,
+      "step": 195
+    },
+    {
+      "epoch": 0.6019563581640331,
+      "grad_norm": 3.6426263387830535,
+      "learning_rate": 9.111435533651595e-07,
+      "loss": 0.8411,
+      "step": 200
+    },
+    {
+      "epoch": 0.6019563581640331,
+      "eval_loss": 0.8422114253044128,
+      "eval_runtime": 164.0752,
+      "eval_samples_per_second": 57.596,
+      "eval_steps_per_second": 0.902,
+      "step": 200
+    },
+    {
+      "epoch": 0.617005267118134,
+      "grad_norm": 3.978063196207494,
+      "learning_rate": 9.065586237377274e-07,
+      "loss": 0.8255,
+      "step": 205
+    },
+    {
+      "epoch": 0.6320541760722348,
+      "grad_norm": 3.536724916036319,
+      "learning_rate": 9.018705130666049e-07,
+      "loss": 0.8355,
+      "step": 210
+    },
+    {
+      "epoch": 0.6471030850263356,
+      "grad_norm": 3.7576883800972243,
+      "learning_rate": 8.970804111535175e-07,
+      "loss": 0.8244,
+      "step": 215
+    },
+    {
+      "epoch": 0.6621519939804364,
+      "grad_norm": 3.413329114828355,
+      "learning_rate": 8.921895336846812e-07,
+      "loss": 0.8336,
+      "step": 220
+    },
+    {
+      "epoch": 0.6772009029345373,
+      "grad_norm": 3.477984800656738,
+      "learning_rate": 8.871991219222712e-07,
+      "loss": 0.8152,
+      "step": 225
+    },
+    {
+      "epoch": 0.6922498118886381,
+      "grad_norm": 3.6780798309273233,
+      "learning_rate": 8.821104423894014e-07,
+      "loss": 0.8235,
+      "step": 230
+    },
+    {
+      "epoch": 0.7072987208427389,
+      "grad_norm": 3.4820310206949383,
+      "learning_rate": 8.769247865486915e-07,
+      "loss": 0.8226,
+      "step": 235
+    },
+    {
+      "epoch": 0.7223476297968398,
+      "grad_norm": 3.3478327176800224,
+      "learning_rate": 8.716434704745046e-07,
+      "loss": 0.8341,
+      "step": 240
+    },
+    {
+      "epoch": 0.7373965387509406,
+      "grad_norm": 3.540341298435034,
+      "learning_rate": 8.662678345189396e-07,
+      "loss": 0.825,
+      "step": 245
+    },
+    {
+      "epoch": 0.7524454477050414,
+      "grad_norm": 3.658518292411783,
+      "learning_rate": 8.607992429716608e-07,
+      "loss": 0.8133,
+      "step": 250
+    },
+    {
+      "epoch": 0.7524454477050414,
+      "eval_loss": 0.828486442565918,
+      "eval_runtime": 164.1931,
+      "eval_samples_per_second": 57.554,
+      "eval_steps_per_second": 0.901,
+      "step": 250
+    },
+    {
+      "epoch": 0.7674943566591422,
+      "grad_norm": 3.3210348798020797,
+      "learning_rate": 8.55239083713654e-07,
+      "loss": 0.8267,
+      "step": 255
+    },
+    {
+      "epoch": 0.782543265613243,
+      "grad_norm": 3.2928105286016867,
+      "learning_rate": 8.495887678649932e-07,
+      "loss": 0.8336,
+      "step": 260
+    },
+    {
+      "epoch": 0.7975921745673439,
+      "grad_norm": 3.7993668860558567,
+      "learning_rate": 8.438497294267116e-07,
+      "loss": 0.8371,
+      "step": 265
+    },
+    {
+      "epoch": 0.8126410835214447,
+      "grad_norm": 3.7491461546658456,
+      "learning_rate": 8.38023424916864e-07,
+      "loss": 0.83,
+      "step": 270
+    },
+    {
+      "epoch": 0.8276899924755455,
+      "grad_norm": 3.335971213466453,
+      "learning_rate": 8.321113330008756e-07,
+      "loss": 0.8231,
+      "step": 275
+    },
+    {
+      "epoch": 0.8427389014296464,
+      "grad_norm": 3.50538153645489,
+      "learning_rate": 8.261149541162691e-07,
+      "loss": 0.8283,
+      "step": 280
+    },
+    {
+      "epoch": 0.8577878103837472,
+      "grad_norm": 3.405552551438381,
+      "learning_rate": 8.20035810091867e-07,
+      "loss": 0.8333,
+      "step": 285
+    },
+    {
+      "epoch": 0.872836719337848,
+      "grad_norm": 3.5518417970408036,
+      "learning_rate": 8.13875443761565e-07,
+      "loss": 0.8215,
+      "step": 290
+    },
+    {
+      "epoch": 0.8878856282919488,
+      "grad_norm": 3.346948128373629,
+      "learning_rate": 8.076354185727734e-07,
+      "loss": 0.8127,
+      "step": 295
+    },
+    {
+      "epoch": 0.9029345372460497,
+      "grad_norm": 3.472824409308143,
+      "learning_rate": 8.013173181896282e-07,
+      "loss": 0.8114,
+      "step": 300
+    },
+    {
+      "epoch": 0.9029345372460497,
+      "eval_loss": 0.8188709616661072,
+      "eval_runtime": 163.9398,
+      "eval_samples_per_second": 57.643,
+      "eval_steps_per_second": 0.903,
+      "step": 300
+    },
+    {
+      "epoch": 0.9179834462001505,
+      "grad_norm": 3.535029645974378,
+      "learning_rate": 7.94922746091071e-07,
+      "loss": 0.8245,
+      "step": 305
+    },
+    {
+      "epoch": 0.9330323551542513,
+      "grad_norm": 3.350512530278651,
+      "learning_rate": 7.884533251638999e-07,
+      "loss": 0.8031,
+      "step": 310
+    },
+    {
+      "epoch": 0.9480812641083521,
+      "grad_norm": 3.1272224593692903,
+      "learning_rate": 7.819106972908949e-07,
+      "loss": 0.792,
+      "step": 315
+    },
+    {
+      "epoch": 0.963130173062453,
+      "grad_norm": 3.3082625072971066,
+      "learning_rate": 7.752965229341219e-07,
+      "loss": 0.8073,
+      "step": 320
+    },
+    {
+      "epoch": 0.9781790820165538,
+      "grad_norm": 3.6472654100125674,
+      "learning_rate": 7.686124807135228e-07,
+      "loss": 0.8091,
+      "step": 325
+    },
+    {
+      "epoch": 0.9932279909706546,
+      "grad_norm": 3.4227050519519184,
+      "learning_rate": 7.618602669808957e-07,
+      "loss": 0.812,
+      "step": 330
+    },
+    {
+      "epoch": 1.0082768999247556,
+      "grad_norm": 3.63643107405423,
+      "learning_rate": 7.550415953893756e-07,
+      "loss": 0.7794,
+      "step": 335
+    },
+    {
+      "epoch": 1.0233258088788564,
+      "grad_norm": 3.5111108810888307,
+      "learning_rate": 7.481581964585244e-07,
+      "loss": 0.7534,
+      "step": 340
+    },
+    {
+      "epoch": 1.0383747178329572,
+      "grad_norm": 3.738034258550528,
+      "learning_rate": 7.412118171351395e-07,
+      "loss": 0.7473,
+      "step": 345
+    },
+    {
+      "epoch": 1.053423626787058,
+      "grad_norm": 3.511742644224616,
+      "learning_rate": 7.342042203498951e-07,
+      "loss": 0.7379,
+      "step": 350
+    },
+    {
+      "epoch": 1.053423626787058,
+      "eval_loss": 0.8137179613113403,
+      "eval_runtime": 163.9091,
+      "eval_samples_per_second": 57.654,
+      "eval_steps_per_second": 0.903,
+      "step": 350
+    },
+    {
+      "epoch": 1.0684725357411589,
+      "grad_norm": 3.482412652291007,
+      "learning_rate": 7.271371845699241e-07,
+      "loss": 0.757,
+      "step": 355
+    },
+    {
+      "epoch": 1.0835214446952597,
+      "grad_norm": 3.57693306476351,
+      "learning_rate": 7.200125033474598e-07,
+      "loss": 0.7405,
+      "step": 360
+    },
+    {
+      "epoch": 1.0985703536493605,
+      "grad_norm": 3.551987518468492,
+      "learning_rate": 7.128319848646477e-07,
+      "loss": 0.7424,
+      "step": 365
+    },
+    {
+      "epoch": 1.1136192626034613,
+      "grad_norm": 3.644980029199069,
+      "learning_rate": 7.055974514746445e-07,
+      "loss": 0.7557,
+      "step": 370
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "grad_norm": 3.661260327693092,
+      "learning_rate": 6.983107392391202e-07,
+      "loss": 0.7595,
+      "step": 375
+    },
+    {
+      "epoch": 1.143717080511663,
+      "grad_norm": 3.6520213924338867,
+      "learning_rate": 6.909736974622826e-07,
+      "loss": 0.7411,
+      "step": 380
+    },
+    {
+      "epoch": 1.1587659894657638,
+      "grad_norm": 3.341094037190979,
+      "learning_rate": 6.835881882215395e-07,
+      "loss": 0.7415,
+      "step": 385
+    },
+    {
+      "epoch": 1.1738148984198646,
+      "grad_norm": 3.4808910667039803,
+      "learning_rate": 6.761560858949192e-07,
+      "loss": 0.7317,
+      "step": 390
+    },
+    {
+      "epoch": 1.1888638073739655,
+      "grad_norm": 3.6539416517236076,
+      "learning_rate": 6.686792766853705e-07,
+      "loss": 0.7537,
+      "step": 395
+    },
+    {
+      "epoch": 1.2039127163280663,
+      "grad_norm": 3.4648582888257002,
+      "learning_rate": 6.611596581420599e-07,
+      "loss": 0.7416,
+      "step": 400
+    },
+    {
+      "epoch": 1.2039127163280663,
+      "eval_loss": 0.8082437515258789,
+      "eval_runtime": 163.785,
+      "eval_samples_per_second": 57.698,
+      "eval_steps_per_second": 0.904,
+      "step": 400
+    },
+    {
+      "epoch": 1.2189616252821671,
+      "grad_norm": 3.3756134153833433,
+      "learning_rate": 6.53599138678791e-07,
+      "loss": 0.7295,
+      "step": 405
+    },
+    {
+      "epoch": 1.234010534236268,
+      "grad_norm": 3.5366994024401093,
+      "learning_rate": 6.459996370896652e-07,
+      "loss": 0.7419,
+      "step": 410
+    },
+    {
+      "epoch": 1.2490594431903688,
+      "grad_norm": 3.6126358863182118,
+      "learning_rate": 6.383630820621081e-07,
+      "loss": 0.7348,
+      "step": 415
+    },
+    {
+      "epoch": 1.2641083521444696,
+      "grad_norm": 3.329040929496611,
+      "learning_rate": 6.306914116873862e-07,
+      "loss": 0.7456,
+      "step": 420
+    },
+    {
+      "epoch": 1.2791572610985704,
+      "grad_norm": 3.389626369376778,
+      "learning_rate": 6.22986572968736e-07,
+      "loss": 0.7399,
+      "step": 425
+    },
+    {
+      "epoch": 1.2942061700526712,
+      "grad_norm": 3.640732106094957,
+      "learning_rate": 6.152505213272307e-07,
+      "loss": 0.7478,
+      "step": 430
+    },
+    {
+      "epoch": 1.309255079006772,
+      "grad_norm": 3.678659612980298,
+      "learning_rate": 6.074852201055121e-07,
+      "loss": 0.7348,
+      "step": 435
+    },
+    {
+      "epoch": 1.324303987960873,
+      "grad_norm": 3.456540220241952,
+      "learning_rate": 5.996926400695113e-07,
+      "loss": 0.7367,
+      "step": 440
+    },
+    {
+      "epoch": 1.3393528969149737,
+      "grad_norm": 3.598565981484491,
+      "learning_rate": 5.918747589082852e-07,
+      "loss": 0.7452,
+      "step": 445
+    },
+    {
+      "epoch": 1.3544018058690745,
+      "grad_norm": 3.6204936371770584,
+      "learning_rate": 5.840335607320963e-07,
+      "loss": 0.7623,
+      "step": 450
+    },
+    {
+      "epoch": 1.3544018058690745,
+      "eval_loss": 0.8033472299575806,
+      "eval_runtime": 163.9716,
+      "eval_samples_per_second": 57.632,
+      "eval_steps_per_second": 0.903,
+      "step": 450
+    },
+    {
+      "epoch": 1.3694507148231754,
+      "grad_norm": 3.5876675484160927,
+      "learning_rate": 5.761710355688627e-07,
+      "loss": 0.7431,
+      "step": 455
+    },
+    {
+      "epoch": 1.3844996237772762,
+      "grad_norm": 3.619019215155952,
+      "learning_rate": 5.682891788591065e-07,
+      "loss": 0.7464,
+      "step": 460
+    },
+    {
+      "epoch": 1.399548532731377,
+      "grad_norm": 3.5444023840644237,
+      "learning_rate": 5.603899909495283e-07,
+      "loss": 0.7357,
+      "step": 465
+    },
+    {
+      "epoch": 1.4145974416854779,
+      "grad_norm": 3.4447315407410266,
+      "learning_rate": 5.52475476585336e-07,
+      "loss": 0.735,
+      "step": 470
+    },
+    {
+      "epoch": 1.4296463506395787,
+      "grad_norm": 3.8423796002300983,
+      "learning_rate": 5.445476444014591e-07,
+      "loss": 0.7318,
+      "step": 475
+    },
+    {
+      "epoch": 1.4446952595936795,
+      "grad_norm": 3.594078636376061,
+      "learning_rate": 5.366085064127734e-07,
+      "loss": 0.7484,
+      "step": 480
+    },
+    {
+      "epoch": 1.4597441685477803,
+      "grad_norm": 3.607424426488508,
+      "learning_rate": 5.286600775034699e-07,
+      "loss": 0.7435,
+      "step": 485
+    },
+    {
+      "epoch": 1.4747930775018812,
+      "grad_norm": 3.7328475918869715,
+      "learning_rate": 5.207043749156944e-07,
+      "loss": 0.7378,
+      "step": 490
+    },
+    {
+      "epoch": 1.489841986455982,
+      "grad_norm": 3.443608577698693,
+      "learning_rate": 5.127434177375893e-07,
+      "loss": 0.7418,
+      "step": 495
+    },
+    {
+      "epoch": 1.5048908954100828,
+      "grad_norm": 3.5186913080533637,
+      "learning_rate": 5.047792263908659e-07,
+      "loss": 0.7158,
+      "step": 500
+    },
+    {
+      "epoch": 1.5048908954100828,
+      "eval_loss": 0.7987317442893982,
+      "eval_runtime": 163.9794,
+      "eval_samples_per_second": 57.629,
+      "eval_steps_per_second": 0.903,
+      "step": 500
+    },
+    {
+      "epoch": 1.5199398043641836,
+      "grad_norm": 3.865883308748703,
+      "learning_rate": 4.968138221180401e-07,
+      "loss": 0.7431,
+      "step": 505
+    },
+    {
+      "epoch": 1.5349887133182845,
+      "grad_norm": 3.710215468774283,
+      "learning_rate": 4.888492264694565e-07,
+      "loss": 0.7007,
+      "step": 510
+    },
+    {
+      "epoch": 1.5500376222723853,
+      "grad_norm": 3.6132015362670145,
+      "learning_rate": 4.808874607902397e-07,
+      "loss": 0.7364,
+      "step": 515
+    },
+    {
+      "epoch": 1.565086531226486,
+      "grad_norm": 3.7199884506401593,
+      "learning_rate": 4.7293054570729126e-07,
+      "loss": 0.7267,
+      "step": 520
+    },
+    {
+      "epoch": 1.580135440180587,
+      "grad_norm": 3.9105644710376457,
+      "learning_rate": 4.649805006164743e-07,
+      "loss": 0.7298,
+      "step": 525
+    },
+    {
+      "epoch": 1.5951843491346878,
+      "grad_norm": 3.5526438869005292,
+      "learning_rate": 4.5703934317010727e-07,
+      "loss": 0.7429,
+      "step": 530
+    },
+    {
+      "epoch": 1.6102332580887886,
+      "grad_norm": 3.502575386275301,
+      "learning_rate": 4.491090887649024e-07,
+      "loss": 0.7337,
+      "step": 535
+    },
+    {
+      "epoch": 1.6252821670428894,
+      "grad_norm": 3.794160344449478,
+      "learning_rate": 4.4119175003047407e-07,
+      "loss": 0.7299,
+      "step": 540
+    },
+    {
+      "epoch": 1.6403310759969902,
+      "grad_norm": 3.2770795614619237,
+      "learning_rate": 4.3328933631855195e-07,
+      "loss": 0.7321,
+      "step": 545
+    },
+    {
+      "epoch": 1.655379984951091,
+      "grad_norm": 3.6119103240995263,
+      "learning_rate": 4.2540385319302524e-07,
+      "loss": 0.7322,
+      "step": 550
+    },
+    {
+      "epoch": 1.655379984951091,
+      "eval_loss": 0.7954748272895813,
+      "eval_runtime": 164.5155,
+      "eval_samples_per_second": 57.441,
+      "eval_steps_per_second": 0.9,
+      "step": 550
+    },
+    {
+      "epoch": 1.670428893905192,
+      "grad_norm": 3.5947026375482944,
+      "learning_rate": 4.175373019209468e-07,
+      "loss": 0.7457,
+      "step": 555
+    },
+    {
+      "epoch": 1.6854778028592927,
+      "grad_norm": 3.761848976466262,
+      "learning_rate": 4.0969167896463046e-07,
+      "loss": 0.7386,
+      "step": 560
+    },
+    {
+      "epoch": 1.7005267118133935,
+      "grad_norm": 3.439361811338972,
+      "learning_rate": 4.018689754749648e-07,
+      "loss": 0.724,
+      "step": 565
+    },
+    {
+      "epoch": 1.7155756207674944,
+      "grad_norm": 3.4555454207422858,
+      "learning_rate": 3.9407117678607756e-07,
+      "loss": 0.7441,
+      "step": 570
+    },
+    {
+      "epoch": 1.7306245297215952,
+      "grad_norm": 3.5617425595455177,
+      "learning_rate": 3.8630026191147405e-07,
+      "loss": 0.7249,
+      "step": 575
+    },
+    {
+      "epoch": 1.745673438675696,
+      "grad_norm": 3.448724415418216,
+      "learning_rate": 3.78558203041782e-07,
+      "loss": 0.6972,
+      "step": 580
+    },
+    {
+      "epoch": 1.7607223476297968,
+      "grad_norm": 3.6943962689825827,
+      "learning_rate": 3.7084696504422525e-07,
+      "loss": 0.7302,
+      "step": 585
+    },
+    {
+      "epoch": 1.7757712565838977,
+      "grad_norm": 3.6561881604475945,
+      "learning_rate": 3.6316850496395855e-07,
+      "loss": 0.7424,
+      "step": 590
+    },
+    {
+      "epoch": 1.7908201655379985,
+      "grad_norm": 3.625068299425613,
+      "learning_rate": 3.555247715273867e-07,
+      "loss": 0.7252,
+      "step": 595
+    },
+    {
+      "epoch": 1.8058690744920993,
+      "grad_norm": 3.519787303173951,
+      "learning_rate": 3.4791770464759347e-07,
+      "loss": 0.7148,
+      "step": 600
+    },
+    {
+      "epoch": 1.8058690744920993,
+      "eval_loss": 0.7919732332229614,
+      "eval_runtime": 163.9475,
+      "eval_samples_per_second": 57.64,
+      "eval_steps_per_second": 0.903,
+      "step": 600
+    },
+    {
+      "epoch": 1.8209179834462002,
+      "grad_norm": 3.8300888994459306,
+      "learning_rate": 3.4034923493201007e-07,
+      "loss": 0.7377,
+      "step": 605
+    },
+    {
+      "epoch": 1.835966892400301,
+      "grad_norm": 3.400875766754663,
+      "learning_rate": 3.3282128319244237e-07,
+      "loss": 0.7385,
+      "step": 610
+    },
+    {
+      "epoch": 1.8510158013544018,
+      "grad_norm": 3.6182045725169325,
+      "learning_rate": 3.2533575995758694e-07,
+      "loss": 0.7197,
+      "step": 615
+    },
+    {
+      "epoch": 1.8660647103085026,
+      "grad_norm": 3.904119144772108,
+      "learning_rate": 3.178945649881543e-07,
+      "loss": 0.7018,
+      "step": 620
+    },
+    {
+      "epoch": 1.8811136192626035,
+      "grad_norm": 3.8565228264688822,
+      "learning_rate": 3.1049958679472645e-07,
+      "loss": 0.7246,
+      "step": 625
+    },
+    {
+      "epoch": 1.8961625282167043,
+      "grad_norm": 3.422783362651409,
+      "learning_rate": 3.031527021584701e-07,
+      "loss": 0.7336,
+      "step": 630
+    },
+    {
+      "epoch": 1.911211437170805,
+      "grad_norm": 3.675919325226495,
+      "learning_rate": 2.9585577565482484e-07,
+      "loss": 0.7169,
+      "step": 635
+    },
+    {
+      "epoch": 1.926260346124906,
+      "grad_norm": 3.726914018119805,
+      "learning_rate": 2.886106591802908e-07,
+      "loss": 0.7259,
+      "step": 640
+    },
+    {
+      "epoch": 1.9413092550790068,
+      "grad_norm": 3.5805352508835333,
+      "learning_rate": 2.814191914824332e-07,
+      "loss": 0.7168,
+      "step": 645
+    },
+    {
+      "epoch": 1.9563581640331076,
+      "grad_norm": 3.60649172674426,
+      "learning_rate": 2.7428319769322415e-07,
+      "loss": 0.71,
+      "step": 650
+    },
+    {
+      "epoch": 1.9563581640331076,
+      "eval_loss": 0.7893925309181213,
+      "eval_runtime": 164.1237,
+      "eval_samples_per_second": 57.579,
+      "eval_steps_per_second": 0.902,
+      "step": 650
+    },
+    {
+      "epoch": 1.9714070729872084,
+      "grad_norm": 3.614812754262687,
+      "learning_rate": 2.672044888658399e-07,
+      "loss": 0.7041,
+      "step": 655
+    },
+    {
+      "epoch": 1.9864559819413092,
+      "grad_norm": 3.7073968028896473,
+      "learning_rate": 2.6018486151503213e-07,
+      "loss": 0.7285,
+      "step": 660
+    },
+    {
+      "epoch": 2.00150489089541,
+      "grad_norm": 3.647866320725029,
+      "learning_rate": 2.532260971611867e-07,
+      "loss": 0.7113,
+      "step": 665
+    },
+    {
+      "epoch": 2.016553799849511,
+      "grad_norm": 3.699708580061935,
+      "learning_rate": 2.4632996187819034e-07,
+      "loss": 0.6883,
+      "step": 670
+    },
+    {
+      "epoch": 2.0316027088036117,
+      "grad_norm": 3.936748692781072,
+      "learning_rate": 2.394982058452165e-07,
+      "loss": 0.6756,
+      "step": 675
+    },
+    {
+      "epoch": 2.0466516177577128,
+      "grad_norm": 3.716518462078895,
+      "learning_rate": 2.3273256290254402e-07,
+      "loss": 0.6762,
+      "step": 680
+    },
+    {
+      "epoch": 2.0617005267118134,
+      "grad_norm": 3.702081977847743,
+      "learning_rate": 2.2603475011152517e-07,
+      "loss": 0.6895,
+      "step": 685
+    },
+    {
+      "epoch": 2.0767494356659144,
+      "grad_norm": 3.605178078795864,
+      "learning_rate": 2.1940646731880885e-07,
+      "loss": 0.6607,
+      "step": 690
+    },
+    {
+      "epoch": 2.091798344620015,
+      "grad_norm": 3.7196889182496733,
+      "learning_rate": 2.1284939672493506e-07,
+      "loss": 0.6789,
+      "step": 695
+    },
+    {
+      "epoch": 2.106847253574116,
+      "grad_norm": 3.7090327815341753,
+      "learning_rate": 2.0636520245740708e-07,
+      "loss": 0.6651,
+      "step": 700
+    },
+    {
+      "epoch": 2.106847253574116,
+      "eval_loss": 0.7947185039520264,
+      "eval_runtime": 164.1101,
+      "eval_samples_per_second": 57.583,
+      "eval_steps_per_second": 0.902,
+      "step": 700
+    },
+    {
+      "epoch": 2.1218961625282167,
+      "grad_norm": 3.736696447237514,
+      "learning_rate": 1.9995553014834986e-07,
+      "loss": 0.6809,
+      "step": 705
+    },
+    {
+      "epoch": 2.1369450714823177,
+      "grad_norm": 3.6458918889335865,
+      "learning_rate": 1.9362200651686406e-07,
+      "loss": 0.6864,
+      "step": 710
+    },
+    {
+      "epoch": 2.1519939804364183,
+      "grad_norm": 4.002063868688003,
+      "learning_rate": 1.873662389561771e-07,
+      "loss": 0.6987,
+      "step": 715
+    },
+    {
+      "epoch": 2.1670428893905194,
+      "grad_norm": 3.8698599662856714,
+      "learning_rate": 1.8118981512570254e-07,
+      "loss": 0.6801,
+      "step": 720
+    },
+    {
+      "epoch": 2.18209179834462,
+      "grad_norm": 3.6230492953936677,
+      "learning_rate": 1.750943025481046e-07,
+      "loss": 0.6826,
+      "step": 725
+    },
+    {
+      "epoch": 2.197140707298721,
+      "grad_norm": 3.7726470306057953,
+      "learning_rate": 1.6908124821147517e-07,
+      "loss": 0.6904,
+      "step": 730
+    },
+    {
+      "epoch": 2.2121896162528216,
+      "grad_norm": 3.787910233434616,
+      "learning_rate": 1.631521781767214e-07,
+      "loss": 0.6798,
+      "step": 735
+    },
+    {
+      "epoch": 2.2272385252069227,
+      "grad_norm": 3.9836210259763023,
+      "learning_rate": 1.5730859719026535e-07,
+      "loss": 0.6776,
+      "step": 740
+    },
+    {
+      "epoch": 2.2422874341610233,
+      "grad_norm": 3.763373496609544,
+      "learning_rate": 1.5155198830215144e-07,
+      "loss": 0.6805,
+      "step": 745
+    },
+    {
+      "epoch": 2.2573363431151243,
+      "grad_norm": 3.8572405199189466,
+      "learning_rate": 1.4588381248966185e-07,
+      "loss": 0.6684,
+      "step": 750
+    },
+    {
+      "epoch": 2.2573363431151243,
+      "eval_loss": 0.7936417460441589,
+      "eval_runtime": 163.9206,
+      "eval_samples_per_second": 57.65,
+      "eval_steps_per_second": 0.903,
+      "step": 750
+    },
+    {
+      "epoch": 2.272385252069225,
+      "grad_norm": 3.8388172371691924,
+      "learning_rate": 1.4030550828653354e-07,
+      "loss": 0.7012,
+      "step": 755
+    },
+    {
+      "epoch": 2.287434161023326,
+      "grad_norm": 3.8523292354815823,
+      "learning_rate": 1.3481849141786977e-07,
+      "loss": 0.6778,
+      "step": 760
+    },
+    {
+      "epoch": 2.3024830699774266,
+      "grad_norm": 3.937046633996997,
+      "learning_rate": 1.294241544408425e-07,
+      "loss": 0.6775,
+      "step": 765
+    },
+    {
+      "epoch": 2.3175319789315276,
+      "grad_norm": 3.953239589293332,
+      "learning_rate": 1.241238663912727e-07,
+      "loss": 0.6868,
+      "step": 770
+    },
+    {
+      "epoch": 2.3325808878856282,
+      "grad_norm": 4.089219915268593,
+      "learning_rate": 1.1891897243618183e-07,
+      "loss": 0.6694,
+      "step": 775
+    },
+    {
+      "epoch": 2.3476297968397293,
+      "grad_norm": 3.846961987007966,
+      "learning_rate": 1.1381079353239915e-07,
+      "loss": 0.6779,
+      "step": 780
+    },
+    {
+      "epoch": 2.36267870579383,
+      "grad_norm": 3.7397027273861885,
+      "learning_rate": 1.0880062609131485e-07,
+      "loss": 0.6726,
+      "step": 785
+    },
+    {
+      "epoch": 2.377727614747931,
+      "grad_norm": 3.921668306186131,
+      "learning_rate": 1.0388974164986247e-07,
+      "loss": 0.6796,
+      "step": 790
+    },
+    {
+      "epoch": 2.3927765237020315,
+      "grad_norm": 3.8468336671320853,
+      "learning_rate": 9.907938654781306e-08,
+      "loss": 0.6835,
+      "step": 795
+    },
+    {
+      "epoch": 2.4078254326561326,
+      "grad_norm": 3.7410679007377854,
+      "learning_rate": 9.437078161146589e-08,
+      "loss": 0.6826,
+      "step": 800
+    },
+    {
+      "epoch": 2.4078254326561326,
+      "eval_loss": 0.7927989363670349,
+      "eval_runtime": 167.9966,
+      "eval_samples_per_second": 56.251,
+      "eval_steps_per_second": 0.881,
+      "step": 800
+    },
+    {
+      "epoch": 2.422874341610233,
+      "grad_norm": 4.079995858636958,
+      "learning_rate": 8.976512184381246e-08,
+      "loss": 0.6795,
+      "step": 805
+    },
+    {
+      "epoch": 2.4379232505643342,
+      "grad_norm": 3.735129398089214,
+      "learning_rate": 8.526357612125573e-08,
+      "loss": 0.6898,
+      "step": 810
+    },
+    {
+      "epoch": 2.452972159518435,
+      "grad_norm": 3.8390441333226817,
+      "learning_rate": 8.086728689695921e-08,
+      "loss": 0.7046,
+      "step": 815
+    },
+    {
+      "epoch": 2.468021068472536,
+      "grad_norm": 3.9049522755901362,
+      "learning_rate": 7.657736991090263e-08,
+      "loss": 0.661,
+      "step": 820
+    },
+    {
+      "epoch": 2.4830699774266365,
+      "grad_norm": 3.880401857930606,
+      "learning_rate": 7.239491390671631e-08,
+      "loss": 0.6742,
+      "step": 825
+    },
+    {
+      "epoch": 2.4981188863807375,
+      "grad_norm": 3.912207039826943,
+      "learning_rate": 6.832098035536759e-08,
+      "loss": 0.6672,
+      "step": 830
+    },
+    {
+      "epoch": 2.513167795334838,
+      "grad_norm": 3.922109823682805,
+      "learning_rate": 6.435660318576935e-08,
+      "loss": 0.6754,
+      "step": 835
+    },
+    {
+      "epoch": 2.528216704288939,
+      "grad_norm": 3.8537847324852224,
+      "learning_rate": 6.0502788522377e-08,
+      "loss": 0.6824,
+      "step": 840
+    },
+    {
+      "epoch": 2.54326561324304,
+      "grad_norm": 4.033607009118544,
+      "learning_rate": 5.676051442984325e-08,
+      "loss": 0.6716,
+      "step": 845
+    },
+    {
+      "epoch": 2.558314522197141,
+      "grad_norm": 3.6539091883922423,
+      "learning_rate": 5.313073066479379e-08,
+      "loss": 0.6711,
+      "step": 850
+    },
+    {
+      "epoch": 2.558314522197141,
+      "eval_loss": 0.7919635772705078,
+      "eval_runtime": 164.1041,
+      "eval_samples_per_second": 57.585,
+      "eval_steps_per_second": 0.902,
+      "step": 850
+    },
+    {
+      "epoch": 2.5733634311512414,
+      "grad_norm": 3.876589664826218,
+      "learning_rate": 4.961435843478751e-08,
+      "loss": 0.6806,
+      "step": 855
+    },
+    {
+      "epoch": 2.5884123401053425,
+      "grad_norm": 3.655653854351189,
+      "learning_rate": 4.621229016452155e-08,
+      "loss": 0.6535,
+      "step": 860
+    },
+    {
+      "epoch": 2.603461249059443,
+      "grad_norm": 4.079997158323887,
+      "learning_rate": 4.2925389269341916e-08,
+      "loss": 0.673,
+      "step": 865
+    },
+    {
+      "epoch": 2.618510158013544,
+      "grad_norm": 3.8325795147951207,
+      "learning_rate": 3.975448993611652e-08,
+      "loss": 0.6709,
+      "step": 870
+    },
+    {
+      "epoch": 2.6335590669676447,
+      "grad_norm": 3.778742993294259,
+      "learning_rate": 3.67003969115251e-08,
+      "loss": 0.6619,
+      "step": 875
+    },
+    {
+      "epoch": 2.648607975921746,
+      "grad_norm": 4.10366570220581,
+      "learning_rate": 3.376388529782215e-08,
+      "loss": 0.6848,
+      "step": 880
+    },
+    {
+      "epoch": 2.6636568848758464,
+      "grad_norm": 3.8699319815585236,
+      "learning_rate": 3.094570035612226e-08,
+      "loss": 0.6853,
+      "step": 885
+    },
+    {
+      "epoch": 2.6787057938299474,
+      "grad_norm": 4.043194008918937,
+      "learning_rate": 2.8246557317259723e-08,
+      "loss": 0.6745,
+      "step": 890
+    },
+    {
+      "epoch": 2.693754702784048,
+      "grad_norm": 3.99392087783422,
+      "learning_rate": 2.5667141200268694e-08,
+      "loss": 0.6577,
+      "step": 895
+    },
+    {
+      "epoch": 2.708803611738149,
+      "grad_norm": 3.6631248500731814,
+      "learning_rate": 2.3208106638531842e-08,
+      "loss": 0.6757,
+      "step": 900
+    },
+    {
+      "epoch": 2.708803611738149,
+      "eval_loss": 0.7914727926254272,
+      "eval_runtime": 164.3819,
+      "eval_samples_per_second": 57.488,
+      "eval_steps_per_second": 0.9,
+      "step": 900
+    },
+    {
+      "epoch": 2.7238525206922497,
+      "grad_norm": 3.9578522639967537,
+      "learning_rate": 2.087007771363969e-08,
+      "loss": 0.6736,
+      "step": 905
+    },
+    {
+      "epoch": 2.7389014296463507,
+      "grad_norm": 3.739728228760654,
+      "learning_rate": 1.8653647797004236e-08,
+      "loss": 0.6729,
+      "step": 910
+    },
+    {
+      "epoch": 2.7539503386004514,
+      "grad_norm": 3.8722809533250326,
+      "learning_rate": 1.655937939926655e-08,
+      "loss": 0.6841,
+      "step": 915
+    },
+    {
+      "epoch": 2.7689992475545524,
+      "grad_norm": 3.8241600199550945,
+      "learning_rate": 1.4587804027536454e-08,
+      "loss": 0.6917,
+      "step": 920
+    },
+    {
+      "epoch": 2.784048156508653,
+      "grad_norm": 3.7138354028978506,
+      "learning_rate": 1.2739422050500436e-08,
+      "loss": 0.6751,
+      "step": 925
+    },
+    {
+      "epoch": 2.799097065462754,
+      "grad_norm": 3.790111519043104,
+      "learning_rate": 1.101470257143261e-08,
+      "loss": 0.6738,
+      "step": 930
+    },
+    {
+      "epoch": 2.8141459744168547,
+      "grad_norm": 3.561873269533578,
+      "learning_rate": 9.414083309140453e-09,
+      "loss": 0.6952,
+      "step": 935
+    },
+    {
+      "epoch": 2.8291948833709557,
+      "grad_norm": 3.6893556293107364,
+      "learning_rate": 7.93797048687539e-09,
+      "loss": 0.6761,
+      "step": 940
+    },
+    {
+      "epoch": 2.8442437923250563,
+      "grad_norm": 3.8751112944911412,
+      "learning_rate": 6.5867387292369295e-09,
+      "loss": 0.6932,
+      "step": 945
+    },
+    {
+      "epoch": 2.8592927012791574,
+      "grad_norm": 4.004750596943983,
+      "learning_rate": 5.360730967096272e-09,
+      "loss": 0.6791,
+      "step": 950
+    },
+    {
+      "epoch": 2.8592927012791574,
+      "eval_loss": 0.7912743091583252,
+      "eval_runtime": 164.3927,
+      "eval_samples_per_second": 57.484,
+      "eval_steps_per_second": 0.9,
+      "step": 950
+    },
+    {
+      "epoch": 2.874341610233258,
+      "grad_norm": 3.8028887659361637,
+      "learning_rate": 4.260258350563317e-09,
+      "loss": 0.6716,
+      "step": 955
+    },
+    {
+      "epoch": 2.889390519187359,
+      "grad_norm": 3.8634306165906107,
+      "learning_rate": 3.285600170019609e-09,
+      "loss": 0.6917,
+      "step": 960
+    },
+    {
+      "epoch": 2.9044394281414596,
+      "grad_norm": 3.6280717262306363,
+      "learning_rate": 2.437003785236702e-09,
+      "loss": 0.665,
+      "step": 965
+    },
+    {
+      "epoch": 2.9194883370955607,
+      "grad_norm": 4.013775538099351,
+      "learning_rate": 1.714684562598545e-09,
+      "loss": 0.6845,
+      "step": 970
+    },
+    {
+      "epoch": 2.9345372460496613,
+      "grad_norm": 3.8102208297791,
+      "learning_rate": 1.1188258204433144e-09,
+      "loss": 0.6673,
+      "step": 975
+    },
+    {
+      "epoch": 2.9495861550037623,
+      "grad_norm": 3.649482883492926,
+      "learning_rate": 6.49578782538851e-10,
+      "loss": 0.6772,
+      "step": 980
+    },
+    {
+      "epoch": 2.964635063957863,
+      "grad_norm": 3.9407869896383483,
+      "learning_rate": 3.070625397031401e-10,
+      "loss": 0.6743,
+      "step": 985
+    },
+    {
+      "epoch": 2.979683972911964,
+      "grad_norm": 3.857935656292572,
+      "learning_rate": 9.136401958059759e-11,
+      "loss": 0.6633,
+      "step": 990
+    },
+    {
+      "epoch": 2.9947328818660646,
+      "grad_norm": 3.934124028791183,
+      "learning_rate": 2.5379645800516215e-12,
+      "loss": 0.672,
+      "step": 995
+    },
+    {
+      "epoch": 2.9977426636568847,
+      "step": 996,
+      "total_flos": 5872633472090112.0,
+      "train_loss": 0.7687147306988996,
+      "train_runtime": 16194.6861,
+      "train_samples_per_second": 15.755,
+      "train_steps_per_second": 0.062
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 996,
+  "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": 5872633472090112.0,
+  "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 sha256:3143570be44a0801e6666f69af84b86218ea4b70cc6d73bb276e05ed5565b4c9
+size 7096