Upload folder using huggingface_hub

README.md

@@ -0,0 +1,82 @@
+---
+library_name: transformers
+license: other
+base_model: llava-hf/llava-v1.6-mistral-7b-hf
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Compcap_l0_0_80
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Compcap_l0_0_80
+
+This model is a fine-tuned version of [llava-hf/llava-v1.6-mistral-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf) on the Compcap_l0_0_80 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7854
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9459        | 0.1692 | 50   | 0.9275          |
+| 0.8992        | 0.3384 | 100  | 0.8709          |
+| 0.8515        | 0.5076 | 150  | 0.8446          |
+| 0.8498        | 0.6768 | 200  | 0.8278          |
+| 0.8105        | 0.8460 | 250  | 0.8158          |
+| 0.7739        | 1.0152 | 300  | 0.8077          |
+| 0.7286        | 1.1844 | 350  | 0.8026          |
+| 0.7582        | 1.3536 | 400  | 0.7977          |
+| 0.7386        | 1.5228 | 450  | 0.7925          |
+| 0.7479        | 1.6920 | 500  | 0.7887          |
+| 0.7374        | 1.8613 | 550  | 0.7846          |
+| 0.7075        | 2.0305 | 600  | 0.7871          |
+| 0.6818        | 2.1997 | 650  | 0.7874          |
+| 0.6747        | 2.3689 | 700  | 0.7868          |
+| 0.6849        | 2.5381 | 750  | 0.7861          |
+| 0.6922        | 2.7073 | 800  | 0.7856          |
+| 0.6948        | 2.8765 | 850  | 0.7854          |
+
+
+### 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": 2.99492385786802,
+    "eval_loss": 0.7854011654853821,
+    "eval_runtime": 145.9597,
+    "eval_samples_per_second": 57.55,
+    "eval_steps_per_second": 0.904,
+    "total_flos": 5218127163949056.0,
+    "train_loss": 0.7771235016106213,
+    "train_runtime": 14098.017,
+    "train_samples_per_second": 16.087,
+    "train_steps_per_second": 0.063
+}

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": 2.99492385786802,
+    "eval_loss": 0.7854011654853821,
+    "eval_runtime": 145.9597,
+    "eval_samples_per_second": 57.55,
+    "eval_steps_per_second": 0.904
+}

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:fcafa333987d55c94f6440bf4c86e5da95c53066e5c9ea14836aebffb88fcd7e
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a497896d67939b013ce0734b1df8a151e09ef8217bdfc24030745e88f6bd34f
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f062f0054ecfd606c74d1aaf6d59591bcae7a16ddfa15e1698d4e7d71b8e863
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e57b38138fd77db292b995e713fa5e87b2a88bdf4aba2e2456728735da133db
+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": 2.99492385786802,
+    "total_flos": 5218127163949056.0,
+    "train_loss": 0.7771235016106213,
+    "train_runtime": 14098.017,
+    "train_samples_per_second": 16.087,
+    "train_steps_per_second": 0.063
+}

trainer_log.jsonl

@@ -0,0 +1,195 @@
+{"current_steps": 5, "total_steps": 885, "loss": 1.7331, "learning_rate": 5e-07, "epoch": 0.01692047377326565, "percentage": 0.56, "elapsed_time": "0:01:09", "remaining_time": "3:23:02"}
+{"current_steps": 10, "total_steps": 885, "loss": 1.5909, "learning_rate": 1e-06, "epoch": 0.0338409475465313, "percentage": 1.13, "elapsed_time": "0:02:14", "remaining_time": "3:16:42"}
+{"current_steps": 15, "total_steps": 885, "loss": 1.3028, "learning_rate": 9.99919433964529e-07, "epoch": 0.050761421319796954, "percentage": 1.69, "elapsed_time": "0:03:19", "remaining_time": "3:13:03"}
+{"current_steps": 20, "total_steps": 885, "loss": 1.1478, "learning_rate": 9.996777618216605e-07, "epoch": 0.0676818950930626, "percentage": 2.26, "elapsed_time": "0:04:25", "remaining_time": "3:11:32"}
+{"current_steps": 25, "total_steps": 885, "loss": 1.0675, "learning_rate": 9.992750614536604e-07, "epoch": 0.08460236886632826, "percentage": 2.82, "elapsed_time": "0:05:31", "remaining_time": "3:10:14"}
+{"current_steps": 30, "total_steps": 885, "loss": 1.0324, "learning_rate": 9.98711462636417e-07, "epoch": 0.10152284263959391, "percentage": 3.39, "elapsed_time": "0:06:37", "remaining_time": "3:08:53"}
+{"current_steps": 35, "total_steps": 885, "loss": 0.9783, "learning_rate": 9.979871469976195e-07, "epoch": 0.11844331641285956, "percentage": 3.95, "elapsed_time": "0:07:43", "remaining_time": "3:07:31"}
+{"current_steps": 40, "total_steps": 885, "loss": 0.9717, "learning_rate": 9.971023479582256e-07, "epoch": 0.1353637901861252, "percentage": 4.52, "elapsed_time": "0:08:49", "remaining_time": "3:06:16"}
+{"current_steps": 45, "total_steps": 885, "loss": 0.9541, "learning_rate": 9.960573506572389e-07, "epoch": 0.15228426395939088, "percentage": 5.08, "elapsed_time": "0:09:54", "remaining_time": "3:04:52"}
+{"current_steps": 50, "total_steps": 885, "loss": 0.9459, "learning_rate": 9.948524918598173e-07, "epoch": 0.1692047377326565, "percentage": 5.65, "elapsed_time": "0:10:59", "remaining_time": "3:03:28"}
+{"current_steps": 50, "total_steps": 885, "eval_loss": 0.9274849891662598, "epoch": 0.1692047377326565, "percentage": 5.65, "elapsed_time": "0:13:27", "remaining_time": "3:44:42"}
+{"current_steps": 55, "total_steps": 885, "loss": 0.9205, "learning_rate": 9.934881598487478e-07, "epoch": 0.18612521150592218, "percentage": 6.21, "elapsed_time": "0:14:32", "remaining_time": "3:39:22"}
+{"current_steps": 60, "total_steps": 885, "loss": 0.9129, "learning_rate": 9.919647942993147e-07, "epoch": 0.20304568527918782, "percentage": 6.78, "elapsed_time": "0:15:38", "remaining_time": "3:34:58"}
+{"current_steps": 65, "total_steps": 885, "loss": 0.893, "learning_rate": 9.9028288613761e-07, "epoch": 0.21996615905245348, "percentage": 7.34, "elapsed_time": "0:16:44", "remaining_time": "3:31:06"}
+{"current_steps": 70, "total_steps": 885, "loss": 0.9107, "learning_rate": 9.884429773823236e-07, "epoch": 0.23688663282571912, "percentage": 7.91, "elapsed_time": "0:17:48", "remaining_time": "3:27:24"}
+{"current_steps": 75, "total_steps": 885, "loss": 0.8996, "learning_rate": 9.864456609700723e-07, "epoch": 0.25380710659898476, "percentage": 8.47, "elapsed_time": "0:18:54", "remaining_time": "3:24:11"}
+{"current_steps": 80, "total_steps": 885, "loss": 0.897, "learning_rate": 9.842915805643156e-07, "epoch": 0.2707275803722504, "percentage": 9.04, "elapsed_time": "0:19:58", "remaining_time": "3:21:01"}
+{"current_steps": 85, "total_steps": 885, "loss": 0.8995, "learning_rate": 9.819814303479267e-07, "epoch": 0.2876480541455161, "percentage": 9.6, "elapsed_time": "0:21:04", "remaining_time": "3:18:25"}
+{"current_steps": 90, "total_steps": 885, "loss": 0.8845, "learning_rate": 9.795159547994828e-07, "epoch": 0.30456852791878175, "percentage": 10.17, "elapsed_time": "0:22:10", "remaining_time": "3:15:53"}
+{"current_steps": 95, "total_steps": 885, "loss": 0.8761, "learning_rate": 9.76895948453346e-07, "epoch": 0.32148900169204736, "percentage": 10.73, "elapsed_time": "0:23:15", "remaining_time": "3:13:26"}
+{"current_steps": 100, "total_steps": 885, "loss": 0.8992, "learning_rate": 9.74122255643613e-07, "epoch": 0.338409475465313, "percentage": 11.3, "elapsed_time": "0:24:20", "remaining_time": "3:11:03"}
+{"current_steps": 100, "total_steps": 885, "eval_loss": 0.8709495663642883, "epoch": 0.338409475465313, "percentage": 11.3, "elapsed_time": "0:26:46", "remaining_time": "3:30:11"}
+{"current_steps": 105, "total_steps": 885, "loss": 0.8915, "learning_rate": 9.711957702320174e-07, "epoch": 0.3553299492385787, "percentage": 11.86, "elapsed_time": "0:27:51", "remaining_time": "3:26:54"}
+{"current_steps": 110, "total_steps": 885, "loss": 0.8814, "learning_rate": 9.681174353198686e-07, "epoch": 0.37225042301184436, "percentage": 12.43, "elapsed_time": "0:28:56", "remaining_time": "3:23:56"}
+{"current_steps": 115, "total_steps": 885, "loss": 0.8661, "learning_rate": 9.648882429441256e-07, "epoch": 0.38917089678510997, "percentage": 12.99, "elapsed_time": "0:30:01", "remaining_time": "3:21:03"}
+{"current_steps": 120, "total_steps": 885, "loss": 0.8737, "learning_rate": 9.615092337576987e-07, "epoch": 0.40609137055837563, "percentage": 13.56, "elapsed_time": "0:31:07", "remaining_time": "3:18:22"}
+{"current_steps": 125, "total_steps": 885, "loss": 0.8585, "learning_rate": 9.579814966940833e-07, "epoch": 0.4230118443316413, "percentage": 14.12, "elapsed_time": "0:32:12", "remaining_time": "3:15:50"}
+{"current_steps": 130, "total_steps": 885, "loss": 0.8617, "learning_rate": 9.543061686164372e-07, "epoch": 0.43993231810490696, "percentage": 14.69, "elapsed_time": "0:33:18", "remaining_time": "3:13:24"}
+{"current_steps": 135, "total_steps": 885, "loss": 0.843, "learning_rate": 9.504844339512094e-07, "epoch": 0.45685279187817257, "percentage": 15.25, "elapsed_time": "0:34:24", "remaining_time": "3:11:07"}
+{"current_steps": 140, "total_steps": 885, "loss": 0.864, "learning_rate": 9.465175243064428e-07, "epoch": 0.47377326565143824, "percentage": 15.82, "elapsed_time": "0:35:29", "remaining_time": "3:08:52"}
+{"current_steps": 145, "total_steps": 885, "loss": 0.853, "learning_rate": 9.424067180748691e-07, "epoch": 0.4906937394247039, "percentage": 16.38, "elapsed_time": "0:36:35", "remaining_time": "3:06:43"}
+{"current_steps": 150, "total_steps": 885, "loss": 0.8515, "learning_rate": 9.381533400219317e-07, "epoch": 0.5076142131979695, "percentage": 16.95, "elapsed_time": "0:37:39", "remaining_time": "3:04:33"}
+{"current_steps": 150, "total_steps": 885, "eval_loss": 0.844601571559906, "epoch": 0.5076142131979695, "percentage": 16.95, "elapsed_time": "0:40:06", "remaining_time": "3:16:30"}
+{"current_steps": 155, "total_steps": 885, "loss": 0.8511, "learning_rate": 9.337587608588588e-07, "epoch": 0.5245346869712352, "percentage": 17.51, "elapsed_time": "0:41:11", "remaining_time": "3:14:01"}
+{"current_steps": 160, "total_steps": 885, "loss": 0.8405, "learning_rate": 9.29224396800933e-07, "epoch": 0.5414551607445008, "percentage": 18.08, "elapsed_time": "0:42:16", "remaining_time": "3:11:35"}
+{"current_steps": 165, "total_steps": 885, "loss": 0.8318, "learning_rate": 9.245517091110968e-07, "epoch": 0.5583756345177665, "percentage": 18.64, "elapsed_time": "0:43:22", "remaining_time": "3:09:16"}
+{"current_steps": 170, "total_steps": 885, "loss": 0.8507, "learning_rate": 9.197422036290386e-07, "epoch": 0.5752961082910322, "percentage": 19.21, "elapsed_time": "0:44:28", "remaining_time": "3:07:02"}
+{"current_steps": 175, "total_steps": 885, "loss": 0.8679, "learning_rate": 9.147974302859156e-07, "epoch": 0.5922165820642978, "percentage": 19.77, "elapsed_time": "0:45:34", "remaining_time": "3:04:55"}
+{"current_steps": 180, "total_steps": 885, "loss": 0.8422, "learning_rate": 9.097189826048659e-07, "epoch": 0.6091370558375635, "percentage": 20.34, "elapsed_time": "0:46:40", "remaining_time": "3:02:47"}
+{"current_steps": 185, "total_steps": 885, "loss": 0.8392, "learning_rate": 9.045084971874737e-07, "epoch": 0.626057529610829, "percentage": 20.9, "elapsed_time": "0:47:45", "remaining_time": "3:00:42"}
+{"current_steps": 190, "total_steps": 885, "loss": 0.8423, "learning_rate": 8.991676531863507e-07, "epoch": 0.6429780033840947, "percentage": 21.47, "elapsed_time": "0:48:50", "remaining_time": "2:58:40"}
+{"current_steps": 195, "total_steps": 885, "loss": 0.838, "learning_rate": 8.93698171764006e-07, "epoch": 0.6598984771573604, "percentage": 22.03, "elapsed_time": "0:49:56", "remaining_time": "2:56:42"}
+{"current_steps": 200, "total_steps": 885, "loss": 0.8498, "learning_rate": 8.881018155381765e-07, "epoch": 0.676818950930626, "percentage": 22.6, "elapsed_time": "0:51:02", "remaining_time": "2:54:49"}
+{"current_steps": 200, "total_steps": 885, "eval_loss": 0.8278397917747498, "epoch": 0.676818950930626, "percentage": 22.6, "elapsed_time": "0:53:28", "remaining_time": "3:03:09"}
+{"current_steps": 205, "total_steps": 885, "loss": 0.8466, "learning_rate": 8.823803880137992e-07, "epoch": 0.6937394247038917, "percentage": 23.16, "elapsed_time": "0:54:33", "remaining_time": "3:00:58"}
+{"current_steps": 210, "total_steps": 885, "loss": 0.8115, "learning_rate": 8.765357330018055e-07, "epoch": 0.7106598984771574, "percentage": 23.73, "elapsed_time": "0:55:37", "remaining_time": "2:58:48"}
+{"current_steps": 215, "total_steps": 885, "loss": 0.8325, "learning_rate": 8.705697340249274e-07, "epoch": 0.727580372250423, "percentage": 24.29, "elapsed_time": "0:56:43", "remaining_time": "2:56:45"}
+{"current_steps": 220, "total_steps": 885, "loss": 0.8204, "learning_rate": 8.644843137107057e-07, "epoch": 0.7445008460236887, "percentage": 24.86, "elapsed_time": "0:57:48", "remaining_time": "2:54:43"}
+{"current_steps": 225, "total_steps": 885, "loss": 0.8196, "learning_rate": 8.58281433171896e-07, "epoch": 0.7614213197969543, "percentage": 25.42, "elapsed_time": "0:58:53", "remaining_time": "2:52:45"}
+{"current_steps": 230, "total_steps": 885, "loss": 0.8173, "learning_rate": 8.519630913744724e-07, "epoch": 0.7783417935702199, "percentage": 25.99, "elapsed_time": "0:59:58", "remaining_time": "2:50:46"}
+{"current_steps": 235, "total_steps": 885, "loss": 0.8248, "learning_rate": 8.455313244934324e-07, "epoch": 0.7952622673434856, "percentage": 26.55, "elapsed_time": "1:01:02", "remaining_time": "2:48:51"}
+{"current_steps": 240, "total_steps": 885, "loss": 0.8138, "learning_rate": 8.389882052566105e-07, "epoch": 0.8121827411167513, "percentage": 27.12, "elapsed_time": "1:02:09", "remaining_time": "2:47:02"}
+{"current_steps": 245, "total_steps": 885, "loss": 0.8301, "learning_rate": 8.323358422767128e-07, "epoch": 0.8291032148900169, "percentage": 27.68, "elapsed_time": "1:03:14", "remaining_time": "2:45:11"}
+{"current_steps": 250, "total_steps": 885, "loss": 0.8105, "learning_rate": 8.255763793717867e-07, "epoch": 0.8460236886632826, "percentage": 28.25, "elapsed_time": "1:04:20", "remaining_time": "2:43:25"}
+{"current_steps": 250, "total_steps": 885, "eval_loss": 0.815843939781189, "epoch": 0.8460236886632826, "percentage": 28.25, "elapsed_time": "1:06:46", "remaining_time": "2:49:37"}
+{"current_steps": 255, "total_steps": 885, "loss": 0.8241, "learning_rate": 8.187119948743449e-07, "epoch": 0.8629441624365483, "percentage": 28.81, "elapsed_time": "1:07:51", "remaining_time": "2:47:39"}
+{"current_steps": 260, "total_steps": 885, "loss": 0.8147, "learning_rate": 8.117449009293668e-07, "epoch": 0.8798646362098139, "percentage": 29.38, "elapsed_time": "1:08:57", "remaining_time": "2:45:45"}
+{"current_steps": 265, "total_steps": 885, "loss": 0.8281, "learning_rate": 8.046773427814041e-07, "epoch": 0.8967851099830795, "percentage": 29.94, "elapsed_time": "1:10:03", "remaining_time": "2:43:54"}
+{"current_steps": 270, "total_steps": 885, "loss": 0.8243, "learning_rate": 7.975115980510185e-07, "epoch": 0.9137055837563451, "percentage": 30.51, "elapsed_time": "1:11:09", "remaining_time": "2:42:04"}
+{"current_steps": 275, "total_steps": 885, "loss": 0.8296, "learning_rate": 7.902499760007867e-07, "epoch": 0.9306260575296108, "percentage": 31.07, "elapsed_time": "1:12:15", "remaining_time": "2:40:16"}
+{"current_steps": 280, "total_steps": 885, "loss": 0.8113, "learning_rate": 7.828948167911073e-07, "epoch": 0.9475465313028765, "percentage": 31.64, "elapsed_time": "1:13:20", "remaining_time": "2:38:28"}
+{"current_steps": 285, "total_steps": 885, "loss": 0.8051, "learning_rate": 7.754484907260512e-07, "epoch": 0.9644670050761421, "percentage": 32.2, "elapsed_time": "1:14:26", "remaining_time": "2:36:43"}
+{"current_steps": 290, "total_steps": 885, "loss": 0.8208, "learning_rate": 7.679133974894982e-07, "epoch": 0.9813874788494078, "percentage": 32.77, "elapsed_time": "1:15:31", "remaining_time": "2:34:56"}
+{"current_steps": 295, "total_steps": 885, "loss": 0.8058, "learning_rate": 7.602919653718043e-07, "epoch": 0.9983079526226735, "percentage": 33.33, "elapsed_time": "1:16:36", "remaining_time": "2:33:13"}
+{"current_steps": 300, "total_steps": 885, "loss": 0.7739, "learning_rate": 7.525866504872506e-07, "epoch": 1.015228426395939, "percentage": 33.9, "elapsed_time": "1:17:42", "remaining_time": "2:31:31"}
+{"current_steps": 300, "total_steps": 885, "eval_loss": 0.8076632022857666, "epoch": 1.015228426395939, "percentage": 33.9, "elapsed_time": "1:20:08", "remaining_time": "2:36:16"}
+{"current_steps": 305, "total_steps": 885, "loss": 0.7588, "learning_rate": 7.447999359825262e-07, "epoch": 1.0321489001692048, "percentage": 34.46, "elapsed_time": "1:21:13", "remaining_time": "2:34:28"}
+{"current_steps": 310, "total_steps": 885, "loss": 0.7289, "learning_rate": 7.369343312364993e-07, "epoch": 1.0490693739424704, "percentage": 35.03, "elapsed_time": "1:22:18", "remaining_time": "2:32:40"}
+{"current_steps": 315, "total_steps": 885, "loss": 0.7482, "learning_rate": 7.289923710515338e-07, "epoch": 1.0659898477157361, "percentage": 35.59, "elapsed_time": "1:23:24", "remaining_time": "2:30:55"}
+{"current_steps": 320, "total_steps": 885, "loss": 0.7309, "learning_rate": 7.209766148366134e-07, "epoch": 1.0829103214890017, "percentage": 36.16, "elapsed_time": "1:24:29", "remaining_time": "2:29:10"}
+{"current_steps": 325, "total_steps": 885, "loss": 0.7371, "learning_rate": 7.128896457825363e-07, "epoch": 1.0998307952622675, "percentage": 36.72, "elapsed_time": "1:25:34", "remaining_time": "2:27:27"}
+{"current_steps": 330, "total_steps": 885, "loss": 0.75, "learning_rate": 7.047340700294453e-07, "epoch": 1.116751269035533, "percentage": 37.29, "elapsed_time": "1:26:39", "remaining_time": "2:25:45"}
+{"current_steps": 335, "total_steps": 885, "loss": 0.7582, "learning_rate": 6.965125158269618e-07, "epoch": 1.1336717428087986, "percentage": 37.85, "elapsed_time": "1:27:45", "remaining_time": "2:24:05"}
+{"current_steps": 340, "total_steps": 885, "loss": 0.7455, "learning_rate": 6.882276326871959e-07, "epoch": 1.1505922165820643, "percentage": 38.42, "elapsed_time": "1:28:51", "remaining_time": "2:22:25"}
+{"current_steps": 345, "total_steps": 885, "loss": 0.7327, "learning_rate": 6.798820905309035e-07, "epoch": 1.16751269035533, "percentage": 38.98, "elapsed_time": "1:29:56", "remaining_time": "2:20:47"}
+{"current_steps": 350, "total_steps": 885, "loss": 0.7286, "learning_rate": 6.714785788270657e-07, "epoch": 1.1844331641285957, "percentage": 39.55, "elapsed_time": "1:31:01", "remaining_time": "2:19:09"}
+{"current_steps": 350, "total_steps": 885, "eval_loss": 0.8026402592658997, "epoch": 1.1844331641285957, "percentage": 39.55, "elapsed_time": "1:33:28", "remaining_time": "2:22:52"}
+{"current_steps": 355, "total_steps": 885, "loss": 0.751, "learning_rate": 6.630198057261709e-07, "epoch": 1.2013536379018612, "percentage": 40.11, "elapsed_time": "1:34:32", "remaining_time": "2:21:09"}
+{"current_steps": 360, "total_steps": 885, "loss": 0.7379, "learning_rate": 6.545084971874736e-07, "epoch": 1.218274111675127, "percentage": 40.68, "elapsed_time": "1:35:37", "remaining_time": "2:19:27"}
+{"current_steps": 365, "total_steps": 885, "loss": 0.7451, "learning_rate": 6.459473961005168e-07, "epoch": 1.2351945854483926, "percentage": 41.24, "elapsed_time": "1:36:42", "remaining_time": "2:17:46"}
+{"current_steps": 370, "total_steps": 885, "loss": 0.745, "learning_rate": 6.373392614011951e-07, "epoch": 1.252115059221658, "percentage": 41.81, "elapsed_time": "1:37:47", "remaining_time": "2:16:07"}
+{"current_steps": 375, "total_steps": 885, "loss": 0.7508, "learning_rate": 6.286868671826511e-07, "epoch": 1.2690355329949239, "percentage": 42.37, "elapsed_time": "1:38:52", "remaining_time": "2:14:28"}
+{"current_steps": 380, "total_steps": 885, "loss": 0.7226, "learning_rate": 6.199930018012829e-07, "epoch": 1.2859560067681894, "percentage": 42.94, "elapsed_time": "1:39:58", "remaining_time": "2:12:51"}
+{"current_steps": 385, "total_steps": 885, "loss": 0.7295, "learning_rate": 6.112604669781572e-07, "epoch": 1.3028764805414552, "percentage": 43.5, "elapsed_time": "1:41:04", "remaining_time": "2:11:15"}
+{"current_steps": 390, "total_steps": 885, "loss": 0.7356, "learning_rate": 6.024920768961152e-07, "epoch": 1.3197969543147208, "percentage": 44.07, "elapsed_time": "1:42:10", "remaining_time": "2:09:40"}
+{"current_steps": 395, "total_steps": 885, "loss": 0.7556, "learning_rate": 5.936906572928624e-07, "epoch": 1.3367174280879865, "percentage": 44.63, "elapsed_time": "1:43:15", "remaining_time": "2:08:05"}
+{"current_steps": 400, "total_steps": 885, "loss": 0.7582, "learning_rate": 5.848590445503344e-07, "epoch": 1.353637901861252, "percentage": 45.2, "elapsed_time": "1:44:20", "remaining_time": "2:06:30"}
+{"current_steps": 400, "total_steps": 885, "eval_loss": 0.7977383732795715, "epoch": 1.353637901861252, "percentage": 45.2, "elapsed_time": "1:46:46", "remaining_time": "2:09:28"}
+{"current_steps": 405, "total_steps": 885, "loss": 0.7725, "learning_rate": 5.760000847806337e-07, "epoch": 1.3705583756345177, "percentage": 45.76, "elapsed_time": "1:47:51", "remaining_time": "2:07:49"}
+{"current_steps": 410, "total_steps": 885, "loss": 0.7514, "learning_rate": 5.671166329088277e-07, "epoch": 1.3874788494077834, "percentage": 46.33, "elapsed_time": "1:48:56", "remaining_time": "2:06:12"}
+{"current_steps": 415, "total_steps": 885, "loss": 0.7483, "learning_rate": 5.582115517529114e-07, "epoch": 1.404399323181049, "percentage": 46.89, "elapsed_time": "1:50:01", "remaining_time": "2:04:36"}
+{"current_steps": 420, "total_steps": 885, "loss": 0.7557, "learning_rate": 5.492877111012218e-07, "epoch": 1.4213197969543148, "percentage": 47.46, "elapsed_time": "1:51:07", "remaining_time": "2:03:01"}
+{"current_steps": 425, "total_steps": 885, "loss": 0.7436, "learning_rate": 5.403479867876087e-07, "epoch": 1.4382402707275803, "percentage": 48.02, "elapsed_time": "1:52:12", "remaining_time": "2:01:27"}
+{"current_steps": 430, "total_steps": 885, "loss": 0.7424, "learning_rate": 5.313952597646567e-07, "epoch": 1.455160744500846, "percentage": 48.59, "elapsed_time": "1:53:18", "remaining_time": "1:59:53"}
+{"current_steps": 435, "total_steps": 885, "loss": 0.7271, "learning_rate": 5.224324151752575e-07, "epoch": 1.4720812182741116, "percentage": 49.15, "elapsed_time": "1:54:24", "remaining_time": "1:58:21"}
+{"current_steps": 440, "total_steps": 885, "loss": 0.7609, "learning_rate": 5.134623414228315e-07, "epoch": 1.4890016920473772, "percentage": 49.72, "elapsed_time": "1:55:29", "remaining_time": "1:56:48"}
+{"current_steps": 445, "total_steps": 885, "loss": 0.7734, "learning_rate": 5.044879292404989e-07, "epoch": 1.505922165820643, "percentage": 50.28, "elapsed_time": "1:56:36", "remaining_time": "1:55:17"}
+{"current_steps": 450, "total_steps": 885, "loss": 0.7386, "learning_rate": 4.95512070759501e-07, "epoch": 1.5228426395939088, "percentage": 50.85, "elapsed_time": "1:57:41", "remaining_time": "1:53:45"}
+{"current_steps": 450, "total_steps": 885, "eval_loss": 0.7924867272377014, "epoch": 1.5228426395939088, "percentage": 50.85, "elapsed_time": "2:00:07", "remaining_time": "1:56:07"}
+{"current_steps": 455, "total_steps": 885, "loss": 0.7393, "learning_rate": 4.865376585771687e-07, "epoch": 1.5397631133671743, "percentage": 51.41, "elapsed_time": "2:01:12", "remaining_time": "1:54:32"}
+{"current_steps": 460, "total_steps": 885, "loss": 0.7362, "learning_rate": 4.775675848247427e-07, "epoch": 1.5566835871404399, "percentage": 51.98, "elapsed_time": "2:02:17", "remaining_time": "1:52:59"}
+{"current_steps": 465, "total_steps": 885, "loss": 0.7356, "learning_rate": 4.686047402353433e-07, "epoch": 1.5736040609137056, "percentage": 52.54, "elapsed_time": "2:03:22", "remaining_time": "1:51:26"}
+{"current_steps": 470, "total_steps": 885, "loss": 0.7284, "learning_rate": 4.596520132123914e-07, "epoch": 1.5905245346869712, "percentage": 53.11, "elapsed_time": "2:04:27", "remaining_time": "1:49:53"}
+{"current_steps": 475, "total_steps": 885, "loss": 0.7504, "learning_rate": 4.507122888987782e-07, "epoch": 1.6074450084602367, "percentage": 53.67, "elapsed_time": "2:05:31", "remaining_time": "1:48:21"}
+{"current_steps": 480, "total_steps": 885, "loss": 0.7505, "learning_rate": 4.417884482470886e-07, "epoch": 1.6243654822335025, "percentage": 54.24, "elapsed_time": "2:06:37", "remaining_time": "1:46:49"}
+{"current_steps": 485, "total_steps": 885, "loss": 0.7426, "learning_rate": 4.328833670911724e-07, "epoch": 1.6412859560067683, "percentage": 54.8, "elapsed_time": "2:07:42", "remaining_time": "1:45:19"}
+{"current_steps": 490, "total_steps": 885, "loss": 0.7299, "learning_rate": 4.239999152193664e-07, "epoch": 1.6582064297800339, "percentage": 55.37, "elapsed_time": "2:08:47", "remaining_time": "1:43:49"}
+{"current_steps": 495, "total_steps": 885, "loss": 0.7259, "learning_rate": 4.1514095544966557e-07, "epoch": 1.6751269035532994, "percentage": 55.93, "elapsed_time": "2:09:52", "remaining_time": "1:42:19"}
+{"current_steps": 500, "total_steps": 885, "loss": 0.7479, "learning_rate": 4.0630934270713755e-07, "epoch": 1.6920473773265652, "percentage": 56.5, "elapsed_time": "2:10:58", "remaining_time": "1:40:50"}
+{"current_steps": 500, "total_steps": 885, "eval_loss": 0.7887324690818787, "epoch": 1.6920473773265652, "percentage": 56.5, "elapsed_time": "2:13:24", "remaining_time": "1:42:43"}
+{"current_steps": 505, "total_steps": 885, "loss": 0.7429, "learning_rate": 3.9750792310388483e-07, "epoch": 1.708967851099831, "percentage": 57.06, "elapsed_time": "2:14:30", "remaining_time": "1:41:12"}
+{"current_steps": 510, "total_steps": 885, "loss": 0.7207, "learning_rate": 3.8873953302184283e-07, "epoch": 1.7258883248730963, "percentage": 57.63, "elapsed_time": "2:15:35", "remaining_time": "1:39:41"}
+{"current_steps": 515, "total_steps": 885, "loss": 0.7523, "learning_rate": 3.80006998198717e-07, "epoch": 1.742808798646362, "percentage": 58.19, "elapsed_time": "2:16:41", "remaining_time": "1:38:12"}
+{"current_steps": 520, "total_steps": 885, "loss": 0.7447, "learning_rate": 3.713131328173489e-07, "epoch": 1.7597292724196278, "percentage": 58.76, "elapsed_time": "2:17:46", "remaining_time": "1:36:42"}
+{"current_steps": 525, "total_steps": 885, "loss": 0.7406, "learning_rate": 3.62660738598805e-07, "epoch": 1.7766497461928934, "percentage": 59.32, "elapsed_time": "2:18:52", "remaining_time": "1:35:13"}
+{"current_steps": 530, "total_steps": 885, "loss": 0.7472, "learning_rate": 3.5405260389948333e-07, "epoch": 1.793570219966159, "percentage": 59.89, "elapsed_time": "2:19:57", "remaining_time": "1:33:44"}
+{"current_steps": 535, "total_steps": 885, "loss": 0.7269, "learning_rate": 3.454915028125263e-07, "epoch": 1.8104906937394247, "percentage": 60.45, "elapsed_time": "2:21:03", "remaining_time": "1:32:16"}
+{"current_steps": 540, "total_steps": 885, "loss": 0.7194, "learning_rate": 3.369801942738291e-07, "epoch": 1.8274111675126905, "percentage": 61.02, "elapsed_time": "2:22:08", "remaining_time": "1:30:49"}
+{"current_steps": 545, "total_steps": 885, "loss": 0.7161, "learning_rate": 3.285214211729343e-07, "epoch": 1.844331641285956, "percentage": 61.58, "elapsed_time": "2:23:13", "remaining_time": "1:29:21"}
+{"current_steps": 550, "total_steps": 885, "loss": 0.7374, "learning_rate": 3.2011790946909666e-07, "epoch": 1.8612521150592216, "percentage": 62.15, "elapsed_time": "2:24:18", "remaining_time": "1:27:53"}
+{"current_steps": 550, "total_steps": 885, "eval_loss": 0.7846313118934631, "epoch": 1.8612521150592216, "percentage": 62.15, "elapsed_time": "2:26:44", "remaining_time": "1:29:22"}
+{"current_steps": 555, "total_steps": 885, "loss": 0.7363, "learning_rate": 3.11772367312804e-07, "epoch": 1.8781725888324874, "percentage": 62.71, "elapsed_time": "2:27:50", "remaining_time": "1:27:54"}
+{"current_steps": 560, "total_steps": 885, "loss": 0.7205, "learning_rate": 3.034874841730382e-07, "epoch": 1.895093062605753, "percentage": 63.28, "elapsed_time": "2:28:55", "remaining_time": "1:26:25"}
+{"current_steps": 565, "total_steps": 885, "loss": 0.7405, "learning_rate": 2.9526592997055483e-07, "epoch": 1.9120135363790185, "percentage": 63.84, "elapsed_time": "2:30:01", "remaining_time": "1:24:58"}
+{"current_steps": 570, "total_steps": 885, "loss": 0.7262, "learning_rate": 2.8711035421746363e-07, "epoch": 1.9289340101522843, "percentage": 64.41, "elapsed_time": "2:31:06", "remaining_time": "1:23:30"}
+{"current_steps": 575, "total_steps": 885, "loss": 0.7321, "learning_rate": 2.7902338516338674e-07, "epoch": 1.94585448392555, "percentage": 64.97, "elapsed_time": "2:32:12", "remaining_time": "1:22:03"}
+{"current_steps": 580, "total_steps": 885, "loss": 0.7318, "learning_rate": 2.7100762894846627e-07, "epoch": 1.9627749576988156, "percentage": 65.54, "elapsed_time": "2:33:17", "remaining_time": "1:20:36"}
+{"current_steps": 585, "total_steps": 885, "loss": 0.7254, "learning_rate": 2.6306566876350067e-07, "epoch": 1.9796954314720812, "percentage": 66.1, "elapsed_time": "2:34:22", "remaining_time": "1:19:10"}
+{"current_steps": 590, "total_steps": 885, "loss": 0.7506, "learning_rate": 2.5520006401747395e-07, "epoch": 1.996615905245347, "percentage": 66.67, "elapsed_time": "2:35:28", "remaining_time": "1:17:44"}
+{"current_steps": 595, "total_steps": 885, "loss": 0.7056, "learning_rate": 2.474133495127494e-07, "epoch": 2.0135363790186127, "percentage": 67.23, "elapsed_time": "2:36:33", "remaining_time": "1:16:18"}
+{"current_steps": 600, "total_steps": 885, "loss": 0.7075, "learning_rate": 2.3970803462819583e-07, "epoch": 2.030456852791878, "percentage": 67.8, "elapsed_time": "2:37:39", "remaining_time": "1:14:53"}
+{"current_steps": 600, "total_steps": 885, "eval_loss": 0.7871306538581848, "epoch": 2.030456852791878, "percentage": 67.8, "elapsed_time": "2:40:05", "remaining_time": "1:16:02"}
+{"current_steps": 605, "total_steps": 885, "loss": 0.6935, "learning_rate": 2.3208660251050156e-07, "epoch": 2.047377326565144, "percentage": 68.36, "elapsed_time": "2:41:11", "remaining_time": "1:14:36"}
+{"current_steps": 610, "total_steps": 885, "loss": 0.6892, "learning_rate": 2.2455150927394878e-07, "epoch": 2.0642978003384096, "percentage": 68.93, "elapsed_time": "2:42:17", "remaining_time": "1:13:09"}
+{"current_steps": 615, "total_steps": 885, "loss": 0.6762, "learning_rate": 2.1710518320889276e-07, "epoch": 2.081218274111675, "percentage": 69.49, "elapsed_time": "2:43:21", "remaining_time": "1:11:43"}
+{"current_steps": 620, "total_steps": 885, "loss": 0.6789, "learning_rate": 2.097500239992132e-07, "epoch": 2.0981387478849407, "percentage": 70.06, "elapsed_time": "2:44:26", "remaining_time": "1:10:17"}
+{"current_steps": 625, "total_steps": 885, "loss": 0.6782, "learning_rate": 2.0248840194898155e-07, "epoch": 2.1150592216582065, "percentage": 70.62, "elapsed_time": "2:45:32", "remaining_time": "1:08:51"}
+{"current_steps": 630, "total_steps": 885, "loss": 0.6694, "learning_rate": 1.9532265721859597e-07, "epoch": 2.1319796954314723, "percentage": 71.19, "elapsed_time": "2:46:38", "remaining_time": "1:07:27"}
+{"current_steps": 635, "total_steps": 885, "loss": 0.6848, "learning_rate": 1.8825509907063326e-07, "epoch": 2.1489001692047376, "percentage": 71.75, "elapsed_time": "2:47:44", "remaining_time": "1:06:02"}
+{"current_steps": 640, "total_steps": 885, "loss": 0.6742, "learning_rate": 1.812880051256551e-07, "epoch": 2.1658206429780034, "percentage": 72.32, "elapsed_time": "2:48:49", "remaining_time": "1:04:37"}
+{"current_steps": 645, "total_steps": 885, "loss": 0.6949, "learning_rate": 1.744236206282132e-07, "epoch": 2.182741116751269, "percentage": 72.88, "elapsed_time": "2:49:54", "remaining_time": "1:03:13"}
+{"current_steps": 650, "total_steps": 885, "loss": 0.6818, "learning_rate": 1.6766415772328728e-07, "epoch": 2.199661590524535, "percentage": 73.45, "elapsed_time": "2:51:00", "remaining_time": "1:01:49"}
+{"current_steps": 650, "total_steps": 885, "eval_loss": 0.7874469757080078, "epoch": 2.199661590524535, "percentage": 73.45, "elapsed_time": "2:53:26", "remaining_time": "1:02:42"}
+{"current_steps": 655, "total_steps": 885, "loss": 0.698, "learning_rate": 1.6101179474338966e-07, "epoch": 2.2165820642978002, "percentage": 74.01, "elapsed_time": "2:54:32", "remaining_time": "1:01:17"}
+{"current_steps": 660, "total_steps": 885, "loss": 0.6951, "learning_rate": 1.5446867550656767e-07, "epoch": 2.233502538071066, "percentage": 74.58, "elapsed_time": "2:55:37", "remaining_time": "0:59:52"}
+{"current_steps": 665, "total_steps": 885, "loss": 0.6736, "learning_rate": 1.4803690862552753e-07, "epoch": 2.250423011844332, "percentage": 75.14, "elapsed_time": "2:56:43", "remaining_time": "0:58:27"}
+{"current_steps": 670, "total_steps": 885, "loss": 0.6796, "learning_rate": 1.4171856682810384e-07, "epoch": 2.267343485617597, "percentage": 75.71, "elapsed_time": "2:57:48", "remaining_time": "0:57:03"}
+{"current_steps": 675, "total_steps": 885, "loss": 0.673, "learning_rate": 1.3551568628929432e-07, "epoch": 2.284263959390863, "percentage": 76.27, "elapsed_time": "2:58:53", "remaining_time": "0:55:39"}
+{"current_steps": 680, "total_steps": 885, "loss": 0.6729, "learning_rate": 1.2943026597507267e-07, "epoch": 2.3011844331641287, "percentage": 76.84, "elapsed_time": "2:59:58", "remaining_time": "0:54:15"}
+{"current_steps": 685, "total_steps": 885, "loss": 0.6919, "learning_rate": 1.2346426699819456e-07, "epoch": 2.3181049069373945, "percentage": 77.4, "elapsed_time": "3:01:03", "remaining_time": "0:52:51"}
+{"current_steps": 690, "total_steps": 885, "loss": 0.6808, "learning_rate": 1.176196119862008e-07, "epoch": 2.33502538071066, "percentage": 77.97, "elapsed_time": "3:02:09", "remaining_time": "0:51:28"}
+{"current_steps": 695, "total_steps": 885, "loss": 0.6817, "learning_rate": 1.1189818446182358e-07, "epoch": 2.3519458544839256, "percentage": 78.53, "elapsed_time": "3:03:14", "remaining_time": "0:50:05"}
+{"current_steps": 700, "total_steps": 885, "loss": 0.6747, "learning_rate": 1.0630182823599399e-07, "epoch": 2.3688663282571913, "percentage": 79.1, "elapsed_time": "3:04:19", "remaining_time": "0:48:42"}
+{"current_steps": 700, "total_steps": 885, "eval_loss": 0.7868276834487915, "epoch": 2.3688663282571913, "percentage": 79.1, "elapsed_time": "3:06:45", "remaining_time": "0:49:21"}
+{"current_steps": 705, "total_steps": 885, "loss": 0.6816, "learning_rate": 1.0083234681364932e-07, "epoch": 2.3857868020304567, "percentage": 79.66, "elapsed_time": "3:07:50", "remaining_time": "0:47:57"}
+{"current_steps": 710, "total_steps": 885, "loss": 0.6798, "learning_rate": 9.549150281252632e-08, "epoch": 2.4027072758037225, "percentage": 80.23, "elapsed_time": "3:08:56", "remaining_time": "0:46:34"}
+{"current_steps": 715, "total_steps": 885, "loss": 0.6767, "learning_rate": 9.028101739513405e-08, "epoch": 2.4196277495769882, "percentage": 80.79, "elapsed_time": "3:10:02", "remaining_time": "0:45:11"}
+{"current_steps": 720, "total_steps": 885, "loss": 0.6864, "learning_rate": 8.520256971408452e-08, "epoch": 2.436548223350254, "percentage": 81.36, "elapsed_time": "3:11:07", "remaining_time": "0:43:47"}
+{"current_steps": 725, "total_steps": 885, "loss": 0.6879, "learning_rate": 8.025779637096137e-08, "epoch": 2.4534686971235193, "percentage": 81.92, "elapsed_time": "3:12:13", "remaining_time": "0:42:25"}
+{"current_steps": 730, "total_steps": 885, "loss": 0.6955, "learning_rate": 7.544829088890325e-08, "epoch": 2.470389170896785, "percentage": 82.49, "elapsed_time": "3:13:17", "remaining_time": "0:41:02"}
+{"current_steps": 735, "total_steps": 885, "loss": 0.68, "learning_rate": 7.077560319906694e-08, "epoch": 2.487309644670051, "percentage": 83.05, "elapsed_time": "3:14:21", "remaining_time": "0:39:39"}
+{"current_steps": 740, "total_steps": 885, "loss": 0.6914, "learning_rate": 6.624123914114122e-08, "epoch": 2.504230118443316, "percentage": 83.62, "elapsed_time": "3:15:27", "remaining_time": "0:38:17"}
+{"current_steps": 745, "total_steps": 885, "loss": 0.6944, "learning_rate": 6.184665997806831e-08, "epoch": 2.521150592216582, "percentage": 84.18, "elapsed_time": "3:16:33", "remaining_time": "0:36:56"}
+{"current_steps": 750, "total_steps": 885, "loss": 0.6849, "learning_rate": 5.759328192513074e-08, "epoch": 2.5380710659898478, "percentage": 84.75, "elapsed_time": "3:17:39", "remaining_time": "0:35:34"}
+{"current_steps": 750, "total_steps": 885, "eval_loss": 0.7860944271087646, "epoch": 2.5380710659898478, "percentage": 84.75, "elapsed_time": "3:20:05", "remaining_time": "0:36:00"}
+{"current_steps": 755, "total_steps": 885, "loss": 0.6915, "learning_rate": 5.348247569355735e-08, "epoch": 2.5549915397631136, "percentage": 85.31, "elapsed_time": "3:21:11", "remaining_time": "0:34:38"}
+{"current_steps": 760, "total_steps": 885, "loss": 0.6753, "learning_rate": 4.951556604879048e-08, "epoch": 2.571912013536379, "percentage": 85.88, "elapsed_time": "3:22:16", "remaining_time": "0:33:16"}
+{"current_steps": 765, "total_steps": 885, "loss": 0.6839, "learning_rate": 4.569383138356275e-08, "epoch": 2.5888324873096447, "percentage": 86.44, "elapsed_time": "3:23:21", "remaining_time": "0:31:54"}
+{"current_steps": 770, "total_steps": 885, "loss": 0.6748, "learning_rate": 4.201850330591677e-08, "epoch": 2.6057529610829104, "percentage": 87.01, "elapsed_time": "3:24:27", "remaining_time": "0:30:32"}
+{"current_steps": 775, "total_steps": 885, "loss": 0.6832, "learning_rate": 3.8490766242301353e-08, "epoch": 2.6226734348561758, "percentage": 87.57, "elapsed_time": "3:25:32", "remaining_time": "0:29:10"}
+{"current_steps": 780, "total_steps": 885, "loss": 0.6902, "learning_rate": 3.5111757055874326e-08, "epoch": 2.6395939086294415, "percentage": 88.14, "elapsed_time": "3:26:38", "remaining_time": "0:27:49"}
+{"current_steps": 785, "total_steps": 885, "loss": 0.6742, "learning_rate": 3.188256468013139e-08, "epoch": 2.6565143824027073, "percentage": 88.7, "elapsed_time": "3:27:43", "remaining_time": "0:26:27"}
+{"current_steps": 790, "total_steps": 885, "loss": 0.6769, "learning_rate": 2.8804229767982636e-08, "epoch": 2.673434856175973, "percentage": 89.27, "elapsed_time": "3:28:48", "remaining_time": "0:25:06"}
+{"current_steps": 795, "total_steps": 885, "loss": 0.6962, "learning_rate": 2.587774435638679e-08, "epoch": 2.6903553299492384, "percentage": 89.83, "elapsed_time": "3:29:53", "remaining_time": "0:23:45"}
+{"current_steps": 800, "total_steps": 885, "loss": 0.6922, "learning_rate": 2.3104051546654013e-08, "epoch": 2.707275803722504, "percentage": 90.4, "elapsed_time": "3:30:58", "remaining_time": "0:22:24"}
+{"current_steps": 800, "total_steps": 885, "eval_loss": 0.7856406569480896, "epoch": 2.707275803722504, "percentage": 90.4, "elapsed_time": "3:33:24", "remaining_time": "0:22:40"}
+{"current_steps": 805, "total_steps": 885, "loss": 0.6888, "learning_rate": 2.048404520051722e-08, "epoch": 2.72419627749577, "percentage": 90.96, "elapsed_time": "3:34:30", "remaining_time": "0:21:19"}
+{"current_steps": 810, "total_steps": 885, "loss": 0.6814, "learning_rate": 1.8018569652073378e-08, "epoch": 2.7411167512690353, "percentage": 91.53, "elapsed_time": "3:35:35", "remaining_time": "0:19:57"}
+{"current_steps": 815, "total_steps": 885, "loss": 0.6807, "learning_rate": 1.570841943568446e-08, "epoch": 2.758037225042301, "percentage": 92.09, "elapsed_time": "3:36:41", "remaining_time": "0:18:36"}
+{"current_steps": 820, "total_steps": 885, "loss": 0.6719, "learning_rate": 1.3554339029927531e-08, "epoch": 2.774957698815567, "percentage": 92.66, "elapsed_time": "3:37:47", "remaining_time": "0:17:15"}
+{"current_steps": 825, "total_steps": 885, "loss": 0.6869, "learning_rate": 1.1557022617676216e-08, "epoch": 2.7918781725888326, "percentage": 93.22, "elapsed_time": "3:38:52", "remaining_time": "0:15:55"}
+{"current_steps": 830, "total_steps": 885, "loss": 0.6805, "learning_rate": 9.717113862389992e-09, "epoch": 2.808798646362098, "percentage": 93.79, "elapsed_time": "3:39:57", "remaining_time": "0:14:34"}
+{"current_steps": 835, "total_steps": 885, "loss": 0.6712, "learning_rate": 8.035205700685165e-09, "epoch": 2.8257191201353637, "percentage": 94.35, "elapsed_time": "3:41:03", "remaining_time": "0:13:14"}
+{"current_steps": 840, "total_steps": 885, "loss": 0.6857, "learning_rate": 6.511840151252168e-09, "epoch": 2.8426395939086295, "percentage": 94.92, "elapsed_time": "3:42:09", "remaining_time": "0:11:54"}
+{"current_steps": 845, "total_steps": 885, "loss": 0.6891, "learning_rate": 5.147508140182555e-09, "epoch": 2.859560067681895, "percentage": 95.48, "elapsed_time": "3:43:14", "remaining_time": "0:10:34"}
+{"current_steps": 850, "total_steps": 885, "loss": 0.6948, "learning_rate": 3.9426493427611175e-09, "epoch": 2.8764805414551606, "percentage": 96.05, "elapsed_time": "3:44:18", "remaining_time": "0:09:14"}
+{"current_steps": 850, "total_steps": 885, "eval_loss": 0.7854181528091431, "epoch": 2.8764805414551606, "percentage": 96.05, "elapsed_time": "3:46:45", "remaining_time": "0:09:20"}
+{"current_steps": 855, "total_steps": 885, "loss": 0.6828, "learning_rate": 2.897652041774279e-09, "epoch": 2.8934010152284264, "percentage": 96.61, "elapsed_time": "3:47:50", "remaining_time": "0:07:59"}
+{"current_steps": 860, "total_steps": 885, "loss": 0.6912, "learning_rate": 2.0128530023804656e-09, "epoch": 2.910321489001692, "percentage": 97.18, "elapsed_time": "3:48:55", "remaining_time": "0:06:39"}
+{"current_steps": 865, "total_steps": 885, "loss": 0.6955, "learning_rate": 1.2885373635829754e-09, "epoch": 2.927241962774958, "percentage": 97.74, "elapsed_time": "3:50:01", "remaining_time": "0:05:19"}
+{"current_steps": 870, "total_steps": 885, "loss": 0.691, "learning_rate": 7.249385463395374e-10, "epoch": 2.9441624365482233, "percentage": 98.31, "elapsed_time": "3:51:06", "remaining_time": "0:03:59"}
+{"current_steps": 875, "total_steps": 885, "loss": 0.6855, "learning_rate": 3.22238178339318e-10, "epoch": 2.961082910321489, "percentage": 98.87, "elapsed_time": "3:52:11", "remaining_time": "0:02:39"}
+{"current_steps": 880, "total_steps": 885, "loss": 0.692, "learning_rate": 8.056603547090812e-11, "epoch": 2.9780033840947544, "percentage": 99.44, "elapsed_time": "3:53:16", "remaining_time": "0:01:19"}
+{"current_steps": 885, "total_steps": 885, "loss": 0.6867, "learning_rate": 0.0, "epoch": 2.99492385786802, "percentage": 100.0, "elapsed_time": "3:54:22", "remaining_time": "0:00:00"}
+{"current_steps": 885, "total_steps": 885, "epoch": 2.99492385786802, "percentage": 100.0, "elapsed_time": "3:54:55", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1417 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.99492385786802,
+  "eval_steps": 50,
+  "global_step": 885,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01692047377326565,
+      "grad_norm": 18.89720056709149,
+      "learning_rate": 5e-07,
+      "loss": 1.7331,
+      "step": 5
+    },
+    {
+      "epoch": 0.0338409475465313,
+      "grad_norm": 12.380230951490994,
+      "learning_rate": 1e-06,
+      "loss": 1.5909,
+      "step": 10
+    },
+    {
+      "epoch": 0.050761421319796954,
+      "grad_norm": 7.703103534110165,
+      "learning_rate": 9.99919433964529e-07,
+      "loss": 1.3028,
+      "step": 15
+    },
+    {
+      "epoch": 0.0676818950930626,
+      "grad_norm": 4.2630631588076096,
+      "learning_rate": 9.996777618216605e-07,
+      "loss": 1.1478,
+      "step": 20
+    },
+    {
+      "epoch": 0.08460236886632826,
+      "grad_norm": 3.9048597217577643,
+      "learning_rate": 9.992750614536604e-07,
+      "loss": 1.0675,
+      "step": 25
+    },
+    {
+      "epoch": 0.10152284263959391,
+      "grad_norm": 4.006647373245602,
+      "learning_rate": 9.98711462636417e-07,
+      "loss": 1.0324,
+      "step": 30
+    },
+    {
+      "epoch": 0.11844331641285956,
+      "grad_norm": 3.5760575012528384,
+      "learning_rate": 9.979871469976195e-07,
+      "loss": 0.9783,
+      "step": 35
+    },
+    {
+      "epoch": 0.1353637901861252,
+      "grad_norm": 3.7598475655002166,
+      "learning_rate": 9.971023479582256e-07,
+      "loss": 0.9717,
+      "step": 40
+    },
+    {
+      "epoch": 0.15228426395939088,
+      "grad_norm": 3.841087015616369,
+      "learning_rate": 9.960573506572389e-07,
+      "loss": 0.9541,
+      "step": 45
+    },
+    {
+      "epoch": 0.1692047377326565,
+      "grad_norm": 3.3432807772469215,
+      "learning_rate": 9.948524918598173e-07,
+      "loss": 0.9459,
+      "step": 50
+    },
+    {
+      "epoch": 0.1692047377326565,
+      "eval_loss": 0.9274849891662598,
+      "eval_runtime": 148.0955,
+      "eval_samples_per_second": 56.72,
+      "eval_steps_per_second": 0.891,
+      "step": 50
+    },
+    {
+      "epoch": 0.18612521150592218,
+      "grad_norm": 3.3571009660316427,
+      "learning_rate": 9.934881598487478e-07,
+      "loss": 0.9205,
+      "step": 55
+    },
+    {
+      "epoch": 0.20304568527918782,
+      "grad_norm": 3.658058336105581,
+      "learning_rate": 9.919647942993147e-07,
+      "loss": 0.9129,
+      "step": 60
+    },
+    {
+      "epoch": 0.21996615905245348,
+      "grad_norm": 3.5170771780637082,
+      "learning_rate": 9.9028288613761e-07,
+      "loss": 0.893,
+      "step": 65
+    },
+    {
+      "epoch": 0.23688663282571912,
+      "grad_norm": 3.4488412657588325,
+      "learning_rate": 9.884429773823236e-07,
+      "loss": 0.9107,
+      "step": 70
+    },
+    {
+      "epoch": 0.25380710659898476,
+      "grad_norm": 3.5097568943852737,
+      "learning_rate": 9.864456609700723e-07,
+      "loss": 0.8996,
+      "step": 75
+    },
+    {
+      "epoch": 0.2707275803722504,
+      "grad_norm": 3.3607900424314705,
+      "learning_rate": 9.842915805643156e-07,
+      "loss": 0.897,
+      "step": 80
+    },
+    {
+      "epoch": 0.2876480541455161,
+      "grad_norm": 3.5364404109551226,
+      "learning_rate": 9.819814303479267e-07,
+      "loss": 0.8995,
+      "step": 85
+    },
+    {
+      "epoch": 0.30456852791878175,
+      "grad_norm": 3.6326997998059873,
+      "learning_rate": 9.795159547994828e-07,
+      "loss": 0.8845,
+      "step": 90
+    },
+    {
+      "epoch": 0.32148900169204736,
+      "grad_norm": 3.342400707382201,
+      "learning_rate": 9.76895948453346e-07,
+      "loss": 0.8761,
+      "step": 95
+    },
+    {
+      "epoch": 0.338409475465313,
+      "grad_norm": 3.5106421873680307,
+      "learning_rate": 9.74122255643613e-07,
+      "loss": 0.8992,
+      "step": 100
+    },
+    {
+      "epoch": 0.338409475465313,
+      "eval_loss": 0.8709495663642883,
+      "eval_runtime": 146.2171,
+      "eval_samples_per_second": 57.449,
+      "eval_steps_per_second": 0.903,
+      "step": 100
+    },
+    {
+      "epoch": 0.3553299492385787,
+      "grad_norm": 3.412793355215337,
+      "learning_rate": 9.711957702320174e-07,
+      "loss": 0.8915,
+      "step": 105
+    },
+    {
+      "epoch": 0.37225042301184436,
+      "grad_norm": 3.4690823915126363,
+      "learning_rate": 9.681174353198686e-07,
+      "loss": 0.8814,
+      "step": 110
+    },
+    {
+      "epoch": 0.38917089678510997,
+      "grad_norm": 3.370071251369415,
+      "learning_rate": 9.648882429441256e-07,
+      "loss": 0.8661,
+      "step": 115
+    },
+    {
+      "epoch": 0.40609137055837563,
+      "grad_norm": 3.687286677170038,
+      "learning_rate": 9.615092337576987e-07,
+      "loss": 0.8737,
+      "step": 120
+    },
+    {
+      "epoch": 0.4230118443316413,
+      "grad_norm": 3.4414847568273346,
+      "learning_rate": 9.579814966940833e-07,
+      "loss": 0.8585,
+      "step": 125
+    },
+    {
+      "epoch": 0.43993231810490696,
+      "grad_norm": 3.555637933684099,
+      "learning_rate": 9.543061686164372e-07,
+      "loss": 0.8617,
+      "step": 130
+    },
+    {
+      "epoch": 0.45685279187817257,
+      "grad_norm": 3.364839125431491,
+      "learning_rate": 9.504844339512094e-07,
+      "loss": 0.843,
+      "step": 135
+    },
+    {
+      "epoch": 0.47377326565143824,
+      "grad_norm": 3.5040756898524745,
+      "learning_rate": 9.465175243064428e-07,
+      "loss": 0.864,
+      "step": 140
+    },
+    {
+      "epoch": 0.4906937394247039,
+      "grad_norm": 3.4002571057955366,
+      "learning_rate": 9.424067180748691e-07,
+      "loss": 0.853,
+      "step": 145
+    },
+    {
+      "epoch": 0.5076142131979695,
+      "grad_norm": 3.5879355202073193,
+      "learning_rate": 9.381533400219317e-07,
+      "loss": 0.8515,
+      "step": 150
+    },
+    {
+      "epoch": 0.5076142131979695,
+      "eval_loss": 0.844601571559906,
+      "eval_runtime": 146.2138,
+      "eval_samples_per_second": 57.45,
+      "eval_steps_per_second": 0.903,
+      "step": 150
+    },
+    {
+      "epoch": 0.5245346869712352,
+      "grad_norm": 3.3747757696246925,
+      "learning_rate": 9.337587608588588e-07,
+      "loss": 0.8511,
+      "step": 155
+    },
+    {
+      "epoch": 0.5414551607445008,
+      "grad_norm": 3.5565216959326644,
+      "learning_rate": 9.29224396800933e-07,
+      "loss": 0.8405,
+      "step": 160
+    },
+    {
+      "epoch": 0.5583756345177665,
+      "grad_norm": 4.512291872844238,
+      "learning_rate": 9.245517091110968e-07,
+      "loss": 0.8318,
+      "step": 165
+    },
+    {
+      "epoch": 0.5752961082910322,
+      "grad_norm": 3.332018798468554,
+      "learning_rate": 9.197422036290386e-07,
+      "loss": 0.8507,
+      "step": 170
+    },
+    {
+      "epoch": 0.5922165820642978,
+      "grad_norm": 3.5149539879760603,
+      "learning_rate": 9.147974302859156e-07,
+      "loss": 0.8679,
+      "step": 175
+    },
+    {
+      "epoch": 0.6091370558375635,
+      "grad_norm": 3.5792424943759924,
+      "learning_rate": 9.097189826048659e-07,
+      "loss": 0.8422,
+      "step": 180
+    },
+    {
+      "epoch": 0.626057529610829,
+      "grad_norm": 3.6495743743155806,
+      "learning_rate": 9.045084971874737e-07,
+      "loss": 0.8392,
+      "step": 185
+    },
+    {
+      "epoch": 0.6429780033840947,
+      "grad_norm": 3.4613931720229836,
+      "learning_rate": 8.991676531863507e-07,
+      "loss": 0.8423,
+      "step": 190
+    },
+    {
+      "epoch": 0.6598984771573604,
+      "grad_norm": 3.552450649531331,
+      "learning_rate": 8.93698171764006e-07,
+      "loss": 0.838,
+      "step": 195
+    },
+    {
+      "epoch": 0.676818950930626,
+      "grad_norm": 3.4396681594412057,
+      "learning_rate": 8.881018155381765e-07,
+      "loss": 0.8498,
+      "step": 200
+    },
+    {
+      "epoch": 0.676818950930626,
+      "eval_loss": 0.8278397917747498,
+      "eval_runtime": 146.1617,
+      "eval_samples_per_second": 57.471,
+      "eval_steps_per_second": 0.903,
+      "step": 200
+    },
+    {
+      "epoch": 0.6937394247038917,
+      "grad_norm": 3.395442461461206,
+      "learning_rate": 8.823803880137992e-07,
+      "loss": 0.8466,
+      "step": 205
+    },
+    {
+      "epoch": 0.7106598984771574,
+      "grad_norm": 3.3738365361465825,
+      "learning_rate": 8.765357330018055e-07,
+      "loss": 0.8115,
+      "step": 210
+    },
+    {
+      "epoch": 0.727580372250423,
+      "grad_norm": 3.492914457997946,
+      "learning_rate": 8.705697340249274e-07,
+      "loss": 0.8325,
+      "step": 215
+    },
+    {
+      "epoch": 0.7445008460236887,
+      "grad_norm": 3.8131605424361084,
+      "learning_rate": 8.644843137107057e-07,
+      "loss": 0.8204,
+      "step": 220
+    },
+    {
+      "epoch": 0.7614213197969543,
+      "grad_norm": 3.243553096025284,
+      "learning_rate": 8.58281433171896e-07,
+      "loss": 0.8196,
+      "step": 225
+    },
+    {
+      "epoch": 0.7783417935702199,
+      "grad_norm": 3.6561787618198625,
+      "learning_rate": 8.519630913744724e-07,
+      "loss": 0.8173,
+      "step": 230
+    },
+    {
+      "epoch": 0.7952622673434856,
+      "grad_norm": 3.411165657715004,
+      "learning_rate": 8.455313244934324e-07,
+      "loss": 0.8248,
+      "step": 235
+    },
+    {
+      "epoch": 0.8121827411167513,
+      "grad_norm": 3.302331738504403,
+      "learning_rate": 8.389882052566105e-07,
+      "loss": 0.8138,
+      "step": 240
+    },
+    {
+      "epoch": 0.8291032148900169,
+      "grad_norm": 3.8604845681587605,
+      "learning_rate": 8.323358422767128e-07,
+      "loss": 0.8301,
+      "step": 245
+    },
+    {
+      "epoch": 0.8460236886632826,
+      "grad_norm": 3.3819331633437617,
+      "learning_rate": 8.255763793717867e-07,
+      "loss": 0.8105,
+      "step": 250
+    },
+    {
+      "epoch": 0.8460236886632826,
+      "eval_loss": 0.815843939781189,
+      "eval_runtime": 146.2558,
+      "eval_samples_per_second": 57.434,
+      "eval_steps_per_second": 0.903,
+      "step": 250
+    },
+    {
+      "epoch": 0.8629441624365483,
+      "grad_norm": 3.693173177209318,
+      "learning_rate": 8.187119948743449e-07,
+      "loss": 0.8241,
+      "step": 255
+    },
+    {
+      "epoch": 0.8798646362098139,
+      "grad_norm": 3.557032123737138,
+      "learning_rate": 8.117449009293668e-07,
+      "loss": 0.8147,
+      "step": 260
+    },
+    {
+      "epoch": 0.8967851099830795,
+      "grad_norm": 3.681990028371156,
+      "learning_rate": 8.046773427814041e-07,
+      "loss": 0.8281,
+      "step": 265
+    },
+    {
+      "epoch": 0.9137055837563451,
+      "grad_norm": 3.472801541082773,
+      "learning_rate": 7.975115980510185e-07,
+      "loss": 0.8243,
+      "step": 270
+    },
+    {
+      "epoch": 0.9306260575296108,
+      "grad_norm": 3.421718448250381,
+      "learning_rate": 7.902499760007867e-07,
+      "loss": 0.8296,
+      "step": 275
+    },
+    {
+      "epoch": 0.9475465313028765,
+      "grad_norm": 3.3839679140101864,
+      "learning_rate": 7.828948167911073e-07,
+      "loss": 0.8113,
+      "step": 280
+    },
+    {
+      "epoch": 0.9644670050761421,
+      "grad_norm": 3.368606848173354,
+      "learning_rate": 7.754484907260512e-07,
+      "loss": 0.8051,
+      "step": 285
+    },
+    {
+      "epoch": 0.9813874788494078,
+      "grad_norm": 3.6569030875938027,
+      "learning_rate": 7.679133974894982e-07,
+      "loss": 0.8208,
+      "step": 290
+    },
+    {
+      "epoch": 0.9983079526226735,
+      "grad_norm": 3.425142212232347,
+      "learning_rate": 7.602919653718043e-07,
+      "loss": 0.8058,
+      "step": 295
+    },
+    {
+      "epoch": 1.015228426395939,
+      "grad_norm": 3.456597451379273,
+      "learning_rate": 7.525866504872506e-07,
+      "loss": 0.7739,
+      "step": 300
+    },
+    {
+      "epoch": 1.015228426395939,
+      "eval_loss": 0.8076632022857666,
+      "eval_runtime": 146.1422,
+      "eval_samples_per_second": 57.478,
+      "eval_steps_per_second": 0.903,
+      "step": 300
+    },
+    {
+      "epoch": 1.0321489001692048,
+      "grad_norm": 3.4266068907750933,
+      "learning_rate": 7.447999359825262e-07,
+      "loss": 0.7588,
+      "step": 305
+    },
+    {
+      "epoch": 1.0490693739424704,
+      "grad_norm": 3.4868988018143354,
+      "learning_rate": 7.369343312364993e-07,
+      "loss": 0.7289,
+      "step": 310
+    },
+    {
+      "epoch": 1.0659898477157361,
+      "grad_norm": 3.4449977296428105,
+      "learning_rate": 7.289923710515338e-07,
+      "loss": 0.7482,
+      "step": 315
+    },
+    {
+      "epoch": 1.0829103214890017,
+      "grad_norm": 3.658957259722615,
+      "learning_rate": 7.209766148366134e-07,
+      "loss": 0.7309,
+      "step": 320
+    },
+    {
+      "epoch": 1.0998307952622675,
+      "grad_norm": 3.359992422940204,
+      "learning_rate": 7.128896457825363e-07,
+      "loss": 0.7371,
+      "step": 325
+    },
+    {
+      "epoch": 1.116751269035533,
+      "grad_norm": 3.7951723668245902,
+      "learning_rate": 7.047340700294453e-07,
+      "loss": 0.75,
+      "step": 330
+    },
+    {
+      "epoch": 1.1336717428087986,
+      "grad_norm": 3.5347910519960837,
+      "learning_rate": 6.965125158269618e-07,
+      "loss": 0.7582,
+      "step": 335
+    },
+    {
+      "epoch": 1.1505922165820643,
+      "grad_norm": 3.5966614567208928,
+      "learning_rate": 6.882276326871959e-07,
+      "loss": 0.7455,
+      "step": 340
+    },
+    {
+      "epoch": 1.16751269035533,
+      "grad_norm": 3.488331150730137,
+      "learning_rate": 6.798820905309035e-07,
+      "loss": 0.7327,
+      "step": 345
+    },
+    {
+      "epoch": 1.1844331641285957,
+      "grad_norm": 3.5101724849934444,
+      "learning_rate": 6.714785788270657e-07,
+      "loss": 0.7286,
+      "step": 350
+    },
+    {
+      "epoch": 1.1844331641285957,
+      "eval_loss": 0.8026402592658997,
+      "eval_runtime": 146.1899,
+      "eval_samples_per_second": 57.459,
+      "eval_steps_per_second": 0.903,
+      "step": 350
+    },
+    {
+      "epoch": 1.2013536379018612,
+      "grad_norm": 3.6348180590276526,
+      "learning_rate": 6.630198057261709e-07,
+      "loss": 0.751,
+      "step": 355
+    },
+    {
+      "epoch": 1.218274111675127,
+      "grad_norm": 3.7503514910524793,
+      "learning_rate": 6.545084971874736e-07,
+      "loss": 0.7379,
+      "step": 360
+    },
+    {
+      "epoch": 1.2351945854483926,
+      "grad_norm": 3.5989366875197244,
+      "learning_rate": 6.459473961005168e-07,
+      "loss": 0.7451,
+      "step": 365
+    },
+    {
+      "epoch": 1.252115059221658,
+      "grad_norm": 3.522773718959504,
+      "learning_rate": 6.373392614011951e-07,
+      "loss": 0.745,
+      "step": 370
+    },
+    {
+      "epoch": 1.2690355329949239,
+      "grad_norm": 3.44987123406693,
+      "learning_rate": 6.286868671826511e-07,
+      "loss": 0.7508,
+      "step": 375
+    },
+    {
+      "epoch": 1.2859560067681894,
+      "grad_norm": 4.122111211031723,
+      "learning_rate": 6.199930018012829e-07,
+      "loss": 0.7226,
+      "step": 380
+    },
+    {
+      "epoch": 1.3028764805414552,
+      "grad_norm": 3.73599818619215,
+      "learning_rate": 6.112604669781572e-07,
+      "loss": 0.7295,
+      "step": 385
+    },
+    {
+      "epoch": 1.3197969543147208,
+      "grad_norm": 3.529190177869209,
+      "learning_rate": 6.024920768961152e-07,
+      "loss": 0.7356,
+      "step": 390
+    },
+    {
+      "epoch": 1.3367174280879865,
+      "grad_norm": 3.461330446213272,
+      "learning_rate": 5.936906572928624e-07,
+      "loss": 0.7556,
+      "step": 395
+    },
+    {
+      "epoch": 1.353637901861252,
+      "grad_norm": 3.571724685541136,
+      "learning_rate": 5.848590445503344e-07,
+      "loss": 0.7582,
+      "step": 400
+    },
+    {
+      "epoch": 1.353637901861252,
+      "eval_loss": 0.7977383732795715,
+      "eval_runtime": 146.2021,
+      "eval_samples_per_second": 57.455,
+      "eval_steps_per_second": 0.903,
+      "step": 400
+    },
+    {
+      "epoch": 1.3705583756345177,
+      "grad_norm": 3.6572559945618304,
+      "learning_rate": 5.760000847806337e-07,
+      "loss": 0.7725,
+      "step": 405
+    },
+    {
+      "epoch": 1.3874788494077834,
+      "grad_norm": 3.697093126496799,
+      "learning_rate": 5.671166329088277e-07,
+      "loss": 0.7514,
+      "step": 410
+    },
+    {
+      "epoch": 1.404399323181049,
+      "grad_norm": 3.836867403357349,
+      "learning_rate": 5.582115517529114e-07,
+      "loss": 0.7483,
+      "step": 415
+    },
+    {
+      "epoch": 1.4213197969543148,
+      "grad_norm": 3.4989314616970764,
+      "learning_rate": 5.492877111012218e-07,
+      "loss": 0.7557,
+      "step": 420
+    },
+    {
+      "epoch": 1.4382402707275803,
+      "grad_norm": 3.597183035056808,
+      "learning_rate": 5.403479867876087e-07,
+      "loss": 0.7436,
+      "step": 425
+    },
+    {
+      "epoch": 1.455160744500846,
+      "grad_norm": 3.7802523149502734,
+      "learning_rate": 5.313952597646567e-07,
+      "loss": 0.7424,
+      "step": 430
+    },
+    {
+      "epoch": 1.4720812182741116,
+      "grad_norm": 3.5635818578964344,
+      "learning_rate": 5.224324151752575e-07,
+      "loss": 0.7271,
+      "step": 435
+    },
+    {
+      "epoch": 1.4890016920473772,
+      "grad_norm": 3.577963950120742,
+      "learning_rate": 5.134623414228315e-07,
+      "loss": 0.7609,
+      "step": 440
+    },
+    {
+      "epoch": 1.505922165820643,
+      "grad_norm": 3.54002403050294,
+      "learning_rate": 5.044879292404989e-07,
+      "loss": 0.7734,
+      "step": 445
+    },
+    {
+      "epoch": 1.5228426395939088,
+      "grad_norm": 3.6965077572035665,
+      "learning_rate": 4.95512070759501e-07,
+      "loss": 0.7386,
+      "step": 450
+    },
+    {
+      "epoch": 1.5228426395939088,
+      "eval_loss": 0.7924867272377014,
+      "eval_runtime": 146.1132,
+      "eval_samples_per_second": 57.49,
+      "eval_steps_per_second": 0.903,
+      "step": 450
+    },
+    {
+      "epoch": 1.5397631133671743,
+      "grad_norm": 3.731715501345578,
+      "learning_rate": 4.865376585771687e-07,
+      "loss": 0.7393,
+      "step": 455
+    },
+    {
+      "epoch": 1.5566835871404399,
+      "grad_norm": 3.5303543042860452,
+      "learning_rate": 4.775675848247427e-07,
+      "loss": 0.7362,
+      "step": 460
+    },
+    {
+      "epoch": 1.5736040609137056,
+      "grad_norm": 3.6723372038452693,
+      "learning_rate": 4.686047402353433e-07,
+      "loss": 0.7356,
+      "step": 465
+    },
+    {
+      "epoch": 1.5905245346869712,
+      "grad_norm": 3.3963951427952694,
+      "learning_rate": 4.596520132123914e-07,
+      "loss": 0.7284,
+      "step": 470
+    },
+    {
+      "epoch": 1.6074450084602367,
+      "grad_norm": 3.654129078679521,
+      "learning_rate": 4.507122888987782e-07,
+      "loss": 0.7504,
+      "step": 475
+    },
+    {
+      "epoch": 1.6243654822335025,
+      "grad_norm": 3.5729221837567438,
+      "learning_rate": 4.417884482470886e-07,
+      "loss": 0.7505,
+      "step": 480
+    },
+    {
+      "epoch": 1.6412859560067683,
+      "grad_norm": 3.7212291449669457,
+      "learning_rate": 4.328833670911724e-07,
+      "loss": 0.7426,
+      "step": 485
+    },
+    {
+      "epoch": 1.6582064297800339,
+      "grad_norm": 3.6827531820047894,
+      "learning_rate": 4.239999152193664e-07,
+      "loss": 0.7299,
+      "step": 490
+    },
+    {
+      "epoch": 1.6751269035532994,
+      "grad_norm": 3.5324806419119805,
+      "learning_rate": 4.1514095544966557e-07,
+      "loss": 0.7259,
+      "step": 495
+    },
+    {
+      "epoch": 1.6920473773265652,
+      "grad_norm": 3.3737883396364463,
+      "learning_rate": 4.0630934270713755e-07,
+      "loss": 0.7479,
+      "step": 500
+    },
+    {
+      "epoch": 1.6920473773265652,
+      "eval_loss": 0.7887324690818787,
+      "eval_runtime": 146.106,
+      "eval_samples_per_second": 57.493,
+      "eval_steps_per_second": 0.903,
+      "step": 500
+    },
+    {
+      "epoch": 1.708967851099831,
+      "grad_norm": 3.645393673633237,
+      "learning_rate": 3.9750792310388483e-07,
+      "loss": 0.7429,
+      "step": 505
+    },
+    {
+      "epoch": 1.7258883248730963,
+      "grad_norm": 3.826381146162921,
+      "learning_rate": 3.8873953302184283e-07,
+      "loss": 0.7207,
+      "step": 510
+    },
+    {
+      "epoch": 1.742808798646362,
+      "grad_norm": 3.6852464302004786,
+      "learning_rate": 3.80006998198717e-07,
+      "loss": 0.7523,
+      "step": 515
+    },
+    {
+      "epoch": 1.7597292724196278,
+      "grad_norm": 3.53598971920285,
+      "learning_rate": 3.713131328173489e-07,
+      "loss": 0.7447,
+      "step": 520
+    },
+    {
+      "epoch": 1.7766497461928934,
+      "grad_norm": 3.468275223623456,
+      "learning_rate": 3.62660738598805e-07,
+      "loss": 0.7406,
+      "step": 525
+    },
+    {
+      "epoch": 1.793570219966159,
+      "grad_norm": 3.750572464422938,
+      "learning_rate": 3.5405260389948333e-07,
+      "loss": 0.7472,
+      "step": 530
+    },
+    {
+      "epoch": 1.8104906937394247,
+      "grad_norm": 3.804608232839517,
+      "learning_rate": 3.454915028125263e-07,
+      "loss": 0.7269,
+      "step": 535
+    },
+    {
+      "epoch": 1.8274111675126905,
+      "grad_norm": 3.6798567744235626,
+      "learning_rate": 3.369801942738291e-07,
+      "loss": 0.7194,
+      "step": 540
+    },
+    {
+      "epoch": 1.844331641285956,
+      "grad_norm": 3.5376430558792604,
+      "learning_rate": 3.285214211729343e-07,
+      "loss": 0.7161,
+      "step": 545
+    },
+    {
+      "epoch": 1.8612521150592216,
+      "grad_norm": 3.508281360828586,
+      "learning_rate": 3.2011790946909666e-07,
+      "loss": 0.7374,
+      "step": 550
+    },
+    {
+      "epoch": 1.8612521150592216,
+      "eval_loss": 0.7846313118934631,
+      "eval_runtime": 146.1979,
+      "eval_samples_per_second": 57.456,
+      "eval_steps_per_second": 0.903,
+      "step": 550
+    },
+    {
+      "epoch": 1.8781725888324874,
+      "grad_norm": 3.6370839999982794,
+      "learning_rate": 3.11772367312804e-07,
+      "loss": 0.7363,
+      "step": 555
+    },
+    {
+      "epoch": 1.895093062605753,
+      "grad_norm": 3.6667447920505767,
+      "learning_rate": 3.034874841730382e-07,
+      "loss": 0.7205,
+      "step": 560
+    },
+    {
+      "epoch": 1.9120135363790185,
+      "grad_norm": 3.6329553320121333,
+      "learning_rate": 2.9526592997055483e-07,
+      "loss": 0.7405,
+      "step": 565
+    },
+    {
+      "epoch": 1.9289340101522843,
+      "grad_norm": 3.625112558207132,
+      "learning_rate": 2.8711035421746363e-07,
+      "loss": 0.7262,
+      "step": 570
+    },
+    {
+      "epoch": 1.94585448392555,
+      "grad_norm": 3.593092005119921,
+      "learning_rate": 2.7902338516338674e-07,
+      "loss": 0.7321,
+      "step": 575
+    },
+    {
+      "epoch": 1.9627749576988156,
+      "grad_norm": 3.8305447044984087,
+      "learning_rate": 2.7100762894846627e-07,
+      "loss": 0.7318,
+      "step": 580
+    },
+    {
+      "epoch": 1.9796954314720812,
+      "grad_norm": 3.7348260486234075,
+      "learning_rate": 2.6306566876350067e-07,
+      "loss": 0.7254,
+      "step": 585
+    },
+    {
+      "epoch": 1.996615905245347,
+      "grad_norm": 3.575785573364731,
+      "learning_rate": 2.5520006401747395e-07,
+      "loss": 0.7506,
+      "step": 590
+    },
+    {
+      "epoch": 2.0135363790186127,
+      "grad_norm": 3.91770848066435,
+      "learning_rate": 2.474133495127494e-07,
+      "loss": 0.7056,
+      "step": 595
+    },
+    {
+      "epoch": 2.030456852791878,
+      "grad_norm": 3.5555997135824184,
+      "learning_rate": 2.3970803462819583e-07,
+      "loss": 0.7075,
+      "step": 600
+    },
+    {
+      "epoch": 2.030456852791878,
+      "eval_loss": 0.7871306538581848,
+      "eval_runtime": 146.0491,
+      "eval_samples_per_second": 57.515,
+      "eval_steps_per_second": 0.904,
+      "step": 600
+    },
+    {
+      "epoch": 2.047377326565144,
+      "grad_norm": 3.7633202447201377,
+      "learning_rate": 2.3208660251050156e-07,
+      "loss": 0.6935,
+      "step": 605
+    },
+    {
+      "epoch": 2.0642978003384096,
+      "grad_norm": 3.671976347169534,
+      "learning_rate": 2.2455150927394878e-07,
+      "loss": 0.6892,
+      "step": 610
+    },
+    {
+      "epoch": 2.081218274111675,
+      "grad_norm": 3.7546761949911165,
+      "learning_rate": 2.1710518320889276e-07,
+      "loss": 0.6762,
+      "step": 615
+    },
+    {
+      "epoch": 2.0981387478849407,
+      "grad_norm": 3.6517301083486684,
+      "learning_rate": 2.097500239992132e-07,
+      "loss": 0.6789,
+      "step": 620
+    },
+    {
+      "epoch": 2.1150592216582065,
+      "grad_norm": 3.8614591719892286,
+      "learning_rate": 2.0248840194898155e-07,
+      "loss": 0.6782,
+      "step": 625
+    },
+    {
+      "epoch": 2.1319796954314723,
+      "grad_norm": 3.7437837099098137,
+      "learning_rate": 1.9532265721859597e-07,
+      "loss": 0.6694,
+      "step": 630
+    },
+    {
+      "epoch": 2.1489001692047376,
+      "grad_norm": 3.7205556217713482,
+      "learning_rate": 1.8825509907063326e-07,
+      "loss": 0.6848,
+      "step": 635
+    },
+    {
+      "epoch": 2.1658206429780034,
+      "grad_norm": 3.957502578909951,
+      "learning_rate": 1.812880051256551e-07,
+      "loss": 0.6742,
+      "step": 640
+    },
+    {
+      "epoch": 2.182741116751269,
+      "grad_norm": 3.764749715334981,
+      "learning_rate": 1.744236206282132e-07,
+      "loss": 0.6949,
+      "step": 645
+    },
+    {
+      "epoch": 2.199661590524535,
+      "grad_norm": 3.6886209727019326,
+      "learning_rate": 1.6766415772328728e-07,
+      "loss": 0.6818,
+      "step": 650
+    },
+    {
+      "epoch": 2.199661590524535,
+      "eval_loss": 0.7874469757080078,
+      "eval_runtime": 146.2957,
+      "eval_samples_per_second": 57.418,
+      "eval_steps_per_second": 0.902,
+      "step": 650
+    },
+    {
+      "epoch": 2.2165820642978002,
+      "grad_norm": 3.8767093338924434,
+      "learning_rate": 1.6101179474338966e-07,
+      "loss": 0.698,
+      "step": 655
+    },
+    {
+      "epoch": 2.233502538071066,
+      "grad_norm": 3.9008502666439955,
+      "learning_rate": 1.5446867550656767e-07,
+      "loss": 0.6951,
+      "step": 660
+    },
+    {
+      "epoch": 2.250423011844332,
+      "grad_norm": 3.600044317004702,
+      "learning_rate": 1.4803690862552753e-07,
+      "loss": 0.6736,
+      "step": 665
+    },
+    {
+      "epoch": 2.267343485617597,
+      "grad_norm": 3.8954074320863623,
+      "learning_rate": 1.4171856682810384e-07,
+      "loss": 0.6796,
+      "step": 670
+    },
+    {
+      "epoch": 2.284263959390863,
+      "grad_norm": 4.011977846573959,
+      "learning_rate": 1.3551568628929432e-07,
+      "loss": 0.673,
+      "step": 675
+    },
+    {
+      "epoch": 2.3011844331641287,
+      "grad_norm": 3.823282280716888,
+      "learning_rate": 1.2943026597507267e-07,
+      "loss": 0.6729,
+      "step": 680
+    },
+    {
+      "epoch": 2.3181049069373945,
+      "grad_norm": 3.992535275167548,
+      "learning_rate": 1.2346426699819456e-07,
+      "loss": 0.6919,
+      "step": 685
+    },
+    {
+      "epoch": 2.33502538071066,
+      "grad_norm": 3.7501814671126255,
+      "learning_rate": 1.176196119862008e-07,
+      "loss": 0.6808,
+      "step": 690
+    },
+    {
+      "epoch": 2.3519458544839256,
+      "grad_norm": 3.886306791969186,
+      "learning_rate": 1.1189818446182358e-07,
+      "loss": 0.6817,
+      "step": 695
+    },
+    {
+      "epoch": 2.3688663282571913,
+      "grad_norm": 3.795337541416798,
+      "learning_rate": 1.0630182823599399e-07,
+      "loss": 0.6747,
+      "step": 700
+    },
+    {
+      "epoch": 2.3688663282571913,
+      "eval_loss": 0.7868276834487915,
+      "eval_runtime": 146.1359,
+      "eval_samples_per_second": 57.481,
+      "eval_steps_per_second": 0.903,
+      "step": 700
+    },
+    {
+      "epoch": 2.3857868020304567,
+      "grad_norm": 3.9750084710216482,
+      "learning_rate": 1.0083234681364932e-07,
+      "loss": 0.6816,
+      "step": 705
+    },
+    {
+      "epoch": 2.4027072758037225,
+      "grad_norm": 3.8888332091113544,
+      "learning_rate": 9.549150281252632e-08,
+      "loss": 0.6798,
+      "step": 710
+    },
+    {
+      "epoch": 2.4196277495769882,
+      "grad_norm": 3.8260776584323786,
+      "learning_rate": 9.028101739513405e-08,
+      "loss": 0.6767,
+      "step": 715
+    },
+    {
+      "epoch": 2.436548223350254,
+      "grad_norm": 3.9871840761205415,
+      "learning_rate": 8.520256971408452e-08,
+      "loss": 0.6864,
+      "step": 720
+    },
+    {
+      "epoch": 2.4534686971235193,
+      "grad_norm": 3.689159095170659,
+      "learning_rate": 8.025779637096137e-08,
+      "loss": 0.6879,
+      "step": 725
+    },
+    {
+      "epoch": 2.470389170896785,
+      "grad_norm": 4.029588500065508,
+      "learning_rate": 7.544829088890325e-08,
+      "loss": 0.6955,
+      "step": 730
+    },
+    {
+      "epoch": 2.487309644670051,
+      "grad_norm": 3.911239676026825,
+      "learning_rate": 7.077560319906694e-08,
+      "loss": 0.68,
+      "step": 735
+    },
+    {
+      "epoch": 2.504230118443316,
+      "grad_norm": 3.9088480475319742,
+      "learning_rate": 6.624123914114122e-08,
+      "loss": 0.6914,
+      "step": 740
+    },
+    {
+      "epoch": 2.521150592216582,
+      "grad_norm": 3.8604080998201677,
+      "learning_rate": 6.184665997806831e-08,
+      "loss": 0.6944,
+      "step": 745
+    },
+    {
+      "epoch": 2.5380710659898478,
+      "grad_norm": 3.7419532051364546,
+      "learning_rate": 5.759328192513074e-08,
+      "loss": 0.6849,
+      "step": 750
+    },
+    {
+      "epoch": 2.5380710659898478,
+      "eval_loss": 0.7860944271087646,
+      "eval_runtime": 146.2056,
+      "eval_samples_per_second": 57.453,
+      "eval_steps_per_second": 0.903,
+      "step": 750
+    },
+    {
+      "epoch": 2.5549915397631136,
+      "grad_norm": 3.8511488857625675,
+      "learning_rate": 5.348247569355735e-08,
+      "loss": 0.6915,
+      "step": 755
+    },
+    {
+      "epoch": 2.571912013536379,
+      "grad_norm": 3.820407730040828,
+      "learning_rate": 4.951556604879048e-08,
+      "loss": 0.6753,
+      "step": 760
+    },
+    {
+      "epoch": 2.5888324873096447,
+      "grad_norm": 4.10704692193588,
+      "learning_rate": 4.569383138356275e-08,
+      "loss": 0.6839,
+      "step": 765
+    },
+    {
+      "epoch": 2.6057529610829104,
+      "grad_norm": 3.8660705841934315,
+      "learning_rate": 4.201850330591677e-08,
+      "loss": 0.6748,
+      "step": 770
+    },
+    {
+      "epoch": 2.6226734348561758,
+      "grad_norm": 3.7908753446624086,
+      "learning_rate": 3.8490766242301353e-08,
+      "loss": 0.6832,
+      "step": 775
+    },
+    {
+      "epoch": 2.6395939086294415,
+      "grad_norm": 3.8661392064625137,
+      "learning_rate": 3.5111757055874326e-08,
+      "loss": 0.6902,
+      "step": 780
+    },
+    {
+      "epoch": 2.6565143824027073,
+      "grad_norm": 3.7157772134571623,
+      "learning_rate": 3.188256468013139e-08,
+      "loss": 0.6742,
+      "step": 785
+    },
+    {
+      "epoch": 2.673434856175973,
+      "grad_norm": 3.6900269313746743,
+      "learning_rate": 2.8804229767982636e-08,
+      "loss": 0.6769,
+      "step": 790
+    },
+    {
+      "epoch": 2.6903553299492384,
+      "grad_norm": 3.8096781294038538,
+      "learning_rate": 2.587774435638679e-08,
+      "loss": 0.6962,
+      "step": 795
+    },
+    {
+      "epoch": 2.707275803722504,
+      "grad_norm": 3.790546594792546,
+      "learning_rate": 2.3104051546654013e-08,
+      "loss": 0.6922,
+      "step": 800
+    },
+    {
+      "epoch": 2.707275803722504,
+      "eval_loss": 0.7856406569480896,
+      "eval_runtime": 146.2171,
+      "eval_samples_per_second": 57.449,
+      "eval_steps_per_second": 0.903,
+      "step": 800
+    },
+    {
+      "epoch": 2.72419627749577,
+      "grad_norm": 3.8429877767556664,
+      "learning_rate": 2.048404520051722e-08,
+      "loss": 0.6888,
+      "step": 805
+    },
+    {
+      "epoch": 2.7411167512690353,
+      "grad_norm": 3.6312764917444165,
+      "learning_rate": 1.8018569652073378e-08,
+      "loss": 0.6814,
+      "step": 810
+    },
+    {
+      "epoch": 2.758037225042301,
+      "grad_norm": 3.787975571643184,
+      "learning_rate": 1.570841943568446e-08,
+      "loss": 0.6807,
+      "step": 815
+    },
+    {
+      "epoch": 2.774957698815567,
+      "grad_norm": 3.9473751919547055,
+      "learning_rate": 1.3554339029927531e-08,
+      "loss": 0.6719,
+      "step": 820
+    },
+    {
+      "epoch": 2.7918781725888326,
+      "grad_norm": 4.009002167477452,
+      "learning_rate": 1.1557022617676216e-08,
+      "loss": 0.6869,
+      "step": 825
+    },
+    {
+      "epoch": 2.808798646362098,
+      "grad_norm": 3.8014391891380934,
+      "learning_rate": 9.717113862389992e-09,
+      "loss": 0.6805,
+      "step": 830
+    },
+    {
+      "epoch": 2.8257191201353637,
+      "grad_norm": 3.6206775186302282,
+      "learning_rate": 8.035205700685165e-09,
+      "loss": 0.6712,
+      "step": 835
+    },
+    {
+      "epoch": 2.8426395939086295,
+      "grad_norm": 3.7790956293706195,
+      "learning_rate": 6.511840151252168e-09,
+      "loss": 0.6857,
+      "step": 840
+    },
+    {
+      "epoch": 2.859560067681895,
+      "grad_norm": 3.946872462701907,
+      "learning_rate": 5.147508140182555e-09,
+      "loss": 0.6891,
+      "step": 845
+    },
+    {
+      "epoch": 2.8764805414551606,
+      "grad_norm": 4.188561175850185,
+      "learning_rate": 3.9426493427611175e-09,
+      "loss": 0.6948,
+      "step": 850
+    },
+    {
+      "epoch": 2.8764805414551606,
+      "eval_loss": 0.7854181528091431,
+      "eval_runtime": 146.4648,
+      "eval_samples_per_second": 57.352,
+      "eval_steps_per_second": 0.901,
+      "step": 850
+    },
+    {
+      "epoch": 2.8934010152284264,
+      "grad_norm": 3.9493971658293505,
+      "learning_rate": 2.897652041774279e-09,
+      "loss": 0.6828,
+      "step": 855
+    },
+    {
+      "epoch": 2.910321489001692,
+      "grad_norm": 3.921042083811142,
+      "learning_rate": 2.0128530023804656e-09,
+      "loss": 0.6912,
+      "step": 860
+    },
+    {
+      "epoch": 2.927241962774958,
+      "grad_norm": 3.765705430002199,
+      "learning_rate": 1.2885373635829754e-09,
+      "loss": 0.6955,
+      "step": 865
+    },
+    {
+      "epoch": 2.9441624365482233,
+      "grad_norm": 3.7974861126821366,
+      "learning_rate": 7.249385463395374e-10,
+      "loss": 0.691,
+      "step": 870
+    },
+    {
+      "epoch": 2.961082910321489,
+      "grad_norm": 3.7353656428622743,
+      "learning_rate": 3.22238178339318e-10,
+      "loss": 0.6855,
+      "step": 875
+    },
+    {
+      "epoch": 2.9780033840947544,
+      "grad_norm": 3.7079032515430557,
+      "learning_rate": 8.056603547090812e-11,
+      "loss": 0.692,
+      "step": 880
+    },
+    {
+      "epoch": 2.99492385786802,
+      "grad_norm": 3.6976604610814037,
+      "learning_rate": 0.0,
+      "loss": 0.6867,
+      "step": 885
+    },
+    {
+      "epoch": 2.99492385786802,
+      "step": 885,
+      "total_flos": 5218127163949056.0,
+      "train_loss": 0.7771235016106213,
+      "train_runtime": 14098.017,
+      "train_samples_per_second": 16.087,
+      "train_steps_per_second": 0.063
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 885,
+  "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": 5218127163949056.0,
+  "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 sha256:35b478bcd53be4ecddbe8843b62bc6e9fc08cd36c07ed30c473a75e464b018ea
+size 7096