Upload folder using huggingface_hub

README.md

@@ -0,0 +1,88 @@
+---
+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-GPT4
+  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-GPT4
+
+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-GPT4 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7652
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9184        | 0.1296 | 50   | 0.9209          |
+| 0.8611        | 0.2592 | 100  | 0.8653          |
+| 0.8257        | 0.3889 | 150  | 0.8396          |
+| 0.8308        | 0.5185 | 200  | 0.8231          |
+| 0.8168        | 0.6481 | 250  | 0.8109          |
+| 0.8021        | 0.7777 | 300  | 0.8005          |
+| 0.7741        | 0.9073 | 350  | 0.7929          |
+| 0.7155        | 1.0369 | 400  | 0.7880          |
+| 0.7322        | 1.1666 | 450  | 0.7837          |
+| 0.7214        | 1.2962 | 500  | 0.7790          |
+| 0.6936        | 1.4258 | 550  | 0.7753          |
+| 0.7046        | 1.5554 | 600  | 0.7717          |
+| 0.6967        | 1.6850 | 650  | 0.7690          |
+| 0.7197        | 1.8146 | 700  | 0.7658          |
+| 0.704         | 1.9443 | 750  | 0.7633          |
+| 0.6546        | 2.0739 | 800  | 0.7677          |
+| 0.651         | 2.2035 | 850  | 0.7673          |
+| 0.6601        | 2.3331 | 900  | 0.7667          |
+| 0.6669        | 2.4627 | 950  | 0.7662          |
+| 0.6566        | 2.5924 | 1000 | 0.7657          |
+| 0.6654        | 2.7220 | 1050 | 0.7655          |
+| 0.6389        | 2.8516 | 1100 | 0.7653          |
+| 0.6574        | 2.9812 | 1150 | 0.7653          |
+
+
+### 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": 2.9941672067401166,
+    "eval_loss": 0.7652431726455688,
+    "eval_runtime": 190.3025,
+    "eval_samples_per_second": 57.64,
+    "eval_steps_per_second": 0.904,
+    "total_flos": 6810169535102976.0,
+    "train_loss": 0.7440064066932315,
+    "train_runtime": 19885.6035,
+    "train_samples_per_second": 14.893,
+    "train_steps_per_second": 0.058
+}

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": 2.9941672067401166,
+    "eval_loss": 0.7652431726455688,
+    "eval_runtime": 190.3025,
+    "eval_samples_per_second": 57.64,
+    "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:a8a13a25f36baa5d7b0eef8d5b22c4a933792f8f93d5482f7cb3dbf9716edcc8
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998c140e9902585332209e922875e180b05e9fd8f75ecd81028a739b3c92b6b9
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86841f439be362e986acfe18791d1578015e8e7e245ad1defb5e15f975519b1b
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dabbf9c07976ab9d80c4b17618038c9bd2916368d3a81119672dafeddd7f6f08
+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": 2.9941672067401166,
+    "total_flos": 6810169535102976.0,
+    "train_loss": 0.7440064066932315,
+    "train_runtime": 19885.6035,
+    "train_samples_per_second": 14.893,
+    "train_steps_per_second": 0.058
+}

trainer_log.jsonl

@@ -0,0 +1,255 @@
+{"current_steps": 5, "total_steps": 1155, "loss": 1.6823, "learning_rate": 5e-07, "epoch": 0.012961762799740765, "percentage": 0.43, "elapsed_time": "0:01:09", "remaining_time": "4:27:03"}
+{"current_steps": 10, "total_steps": 1155, "loss": 1.566, "learning_rate": 1e-06, "epoch": 0.02592352559948153, "percentage": 0.87, "elapsed_time": "0:02:14", "remaining_time": "4:17:03"}
+{"current_steps": 15, "total_steps": 1155, "loss": 1.2721, "learning_rate": 9.99952949745378e-07, "epoch": 0.03888528839922229, "percentage": 1.3, "elapsed_time": "0:03:20", "remaining_time": "4:13:20"}
+{"current_steps": 20, "total_steps": 1155, "loss": 1.1461, "learning_rate": 9.998118078364185e-07, "epoch": 0.05184705119896306, "percentage": 1.73, "elapsed_time": "0:04:25", "remaining_time": "4:11:05"}
+{"current_steps": 25, "total_steps": 1155, "loss": 1.0509, "learning_rate": 9.995766008361718e-07, "epoch": 0.06480881399870382, "percentage": 2.16, "elapsed_time": "0:05:31", "remaining_time": "4:09:26"}
+{"current_steps": 30, "total_steps": 1155, "loss": 0.9982, "learning_rate": 9.992473730108354e-07, "epoch": 0.07777057679844458, "percentage": 2.6, "elapsed_time": "0:06:36", "remaining_time": "4:08:05"}
+{"current_steps": 35, "total_steps": 1155, "loss": 0.9804, "learning_rate": 9.98824186321421e-07, "epoch": 0.09073233959818536, "percentage": 3.03, "elapsed_time": "0:07:42", "remaining_time": "4:06:30"}
+{"current_steps": 40, "total_steps": 1155, "loss": 0.954, "learning_rate": 9.98307120412095e-07, "epoch": 0.10369410239792612, "percentage": 3.46, "elapsed_time": "0:08:47", "remaining_time": "4:05:11"}
+{"current_steps": 45, "total_steps": 1155, "loss": 0.928, "learning_rate": 9.976962725951878e-07, "epoch": 0.11665586519766688, "percentage": 3.9, "elapsed_time": "0:09:53", "remaining_time": "4:04:01"}
+{"current_steps": 50, "total_steps": 1155, "loss": 0.9184, "learning_rate": 9.969917578328807e-07, "epoch": 0.12961762799740764, "percentage": 4.33, "elapsed_time": "0:10:58", "remaining_time": "4:02:32"}
+{"current_steps": 50, "total_steps": 1155, "eval_loss": 0.92087721824646, "epoch": 0.12961762799740764, "percentage": 4.33, "elapsed_time": "0:14:09", "remaining_time": "5:12:44"}
+{"current_steps": 55, "total_steps": 1155, "loss": 0.9194, "learning_rate": 9.961937087155695e-07, "epoch": 0.1425793907971484, "percentage": 4.76, "elapsed_time": "0:15:13", "remaining_time": "5:04:35"}
+{"current_steps": 60, "total_steps": 1155, "loss": 0.8832, "learning_rate": 9.953022754369114e-07, "epoch": 0.15554115359688916, "percentage": 5.19, "elapsed_time": "0:16:20", "remaining_time": "4:58:07"}
+{"current_steps": 65, "total_steps": 1155, "loss": 0.8923, "learning_rate": 9.943176257655565e-07, "epoch": 0.16850291639662995, "percentage": 5.63, "elapsed_time": "0:17:26", "remaining_time": "4:52:26"}
+{"current_steps": 70, "total_steps": 1155, "loss": 0.8883, "learning_rate": 9.932399450135765e-07, "epoch": 0.18146467919637072, "percentage": 6.06, "elapsed_time": "0:18:31", "remaining_time": "4:47:05"}
+{"current_steps": 75, "total_steps": 1155, "loss": 0.8639, "learning_rate": 9.920694360015862e-07, "epoch": 0.19442644199611148, "percentage": 6.49, "elapsed_time": "0:19:36", "remaining_time": "4:42:24"}
+{"current_steps": 80, "total_steps": 1155, "loss": 0.8732, "learning_rate": 9.908063190205739e-07, "epoch": 0.20738820479585224, "percentage": 6.93, "elapsed_time": "0:20:42", "remaining_time": "4:38:09"}
+{"current_steps": 85, "total_steps": 1155, "loss": 0.8883, "learning_rate": 9.894508317904417e-07, "epoch": 0.220349967595593, "percentage": 7.36, "elapsed_time": "0:21:47", "remaining_time": "4:34:23"}
+{"current_steps": 90, "total_steps": 1155, "loss": 0.8671, "learning_rate": 9.88003229415267e-07, "epoch": 0.23331173039533376, "percentage": 7.79, "elapsed_time": "0:22:53", "remaining_time": "4:30:52"}
+{"current_steps": 95, "total_steps": 1155, "loss": 0.8771, "learning_rate": 9.864637843352913e-07, "epoch": 0.24627349319507452, "percentage": 8.23, "elapsed_time": "0:23:59", "remaining_time": "4:27:37"}
+{"current_steps": 100, "total_steps": 1155, "loss": 0.8611, "learning_rate": 9.848327862756466e-07, "epoch": 0.2592352559948153, "percentage": 8.66, "elapsed_time": "0:25:04", "remaining_time": "4:24:31"}
+{"current_steps": 100, "total_steps": 1155, "eval_loss": 0.8652921915054321, "epoch": 0.2592352559948153, "percentage": 8.66, "elapsed_time": "0:28:14", "remaining_time": "4:57:59"}
+{"current_steps": 105, "total_steps": 1155, "loss": 0.8547, "learning_rate": 9.831105421918285e-07, "epoch": 0.27219701879455604, "percentage": 9.09, "elapsed_time": "0:29:50", "remaining_time": "4:58:25"}
+{"current_steps": 110, "total_steps": 1155, "loss": 0.8369, "learning_rate": 9.81297376211928e-07, "epoch": 0.2851587815942968, "percentage": 9.52, "elapsed_time": "0:30:55", "remaining_time": "4:53:47"}
+{"current_steps": 115, "total_steps": 1155, "loss": 0.8403, "learning_rate": 9.79393629575629e-07, "epoch": 0.29812054439403757, "percentage": 9.96, "elapsed_time": "0:32:00", "remaining_time": "4:49:24"}
+{"current_steps": 120, "total_steps": 1155, "loss": 0.8437, "learning_rate": 9.773996605699875e-07, "epoch": 0.31108230719377833, "percentage": 10.39, "elapsed_time": "0:33:05", "remaining_time": "4:45:27"}
+{"current_steps": 125, "total_steps": 1155, "loss": 0.8295, "learning_rate": 9.753158444620013e-07, "epoch": 0.32404406999351915, "percentage": 10.82, "elapsed_time": "0:34:10", "remaining_time": "4:41:39"}
+{"current_steps": 130, "total_steps": 1155, "loss": 0.8416, "learning_rate": 9.73142573427984e-07, "epoch": 0.3370058327932599, "percentage": 11.26, "elapsed_time": "0:35:16", "remaining_time": "4:38:09"}
+{"current_steps": 135, "total_steps": 1155, "loss": 0.8372, "learning_rate": 9.708802564797578e-07, "epoch": 0.34996759559300067, "percentage": 11.69, "elapsed_time": "0:36:22", "remaining_time": "4:34:46"}
+{"current_steps": 140, "total_steps": 1155, "loss": 0.8407, "learning_rate": 9.685293193876765e-07, "epoch": 0.36292935839274143, "percentage": 12.12, "elapsed_time": "0:37:27", "remaining_time": "4:31:34"}
+{"current_steps": 145, "total_steps": 1155, "loss": 0.8218, "learning_rate": 9.660902046004953e-07, "epoch": 0.3758911211924822, "percentage": 12.55, "elapsed_time": "0:38:33", "remaining_time": "4:28:31"}
+{"current_steps": 150, "total_steps": 1155, "loss": 0.8257, "learning_rate": 9.635633711621011e-07, "epoch": 0.38885288399222295, "percentage": 12.99, "elapsed_time": "0:39:37", "remaining_time": "4:25:25"}
+{"current_steps": 150, "total_steps": 1155, "eval_loss": 0.8396357893943787, "epoch": 0.38885288399222295, "percentage": 12.99, "elapsed_time": "0:42:47", "remaining_time": "4:46:40"}
+{"current_steps": 155, "total_steps": 1155, "loss": 0.8335, "learning_rate": 9.609492946251208e-07, "epoch": 0.4018146467919637, "percentage": 13.42, "elapsed_time": "0:43:52", "remaining_time": "4:43:06"}
+{"current_steps": 160, "total_steps": 1155, "loss": 0.8274, "learning_rate": 9.58248466961421e-07, "epoch": 0.4147764095917045, "percentage": 13.85, "elapsed_time": "0:44:58", "remaining_time": "4:39:41"}
+{"current_steps": 165, "total_steps": 1155, "loss": 0.8419, "learning_rate": 9.554613964695188e-07, "epoch": 0.42773817239144524, "percentage": 14.29, "elapsed_time": "0:46:03", "remaining_time": "4:36:19"}
+{"current_steps": 170, "total_steps": 1155, "loss": 0.8264, "learning_rate": 9.525886076789193e-07, "epoch": 0.440699935191186, "percentage": 14.72, "elapsed_time": "0:47:08", "remaining_time": "4:33:08"}
+{"current_steps": 175, "total_steps": 1155, "loss": 0.813, "learning_rate": 9.496306412513988e-07, "epoch": 0.45366169799092676, "percentage": 15.15, "elapsed_time": "0:48:13", "remaining_time": "4:30:04"}
+{"current_steps": 180, "total_steps": 1155, "loss": 0.8209, "learning_rate": 9.465880538792517e-07, "epoch": 0.4666234607906675, "percentage": 15.58, "elapsed_time": "0:49:19", "remaining_time": "4:27:09"}
+{"current_steps": 185, "total_steps": 1155, "loss": 0.8246, "learning_rate": 9.434614181805202e-07, "epoch": 0.4795852235904083, "percentage": 16.02, "elapsed_time": "0:50:24", "remaining_time": "4:24:19"}
+{"current_steps": 190, "total_steps": 1155, "loss": 0.8236, "learning_rate": 9.402513225912271e-07, "epoch": 0.49254698639014904, "percentage": 16.45, "elapsed_time": "0:51:30", "remaining_time": "4:21:35"}
+{"current_steps": 195, "total_steps": 1155, "loss": 0.8158, "learning_rate": 9.36958371254632e-07, "epoch": 0.5055087491898899, "percentage": 16.88, "elapsed_time": "0:52:35", "remaining_time": "4:18:55"}
+{"current_steps": 200, "total_steps": 1155, "loss": 0.8308, "learning_rate": 9.335831839075302e-07, "epoch": 0.5184705119896306, "percentage": 17.32, "elapsed_time": "0:53:40", "remaining_time": "4:16:18"}
+{"current_steps": 200, "total_steps": 1155, "eval_loss": 0.8231202960014343, "epoch": 0.5184705119896306, "percentage": 17.32, "elapsed_time": "0:56:51", "remaining_time": "4:31:27"}
+{"current_steps": 205, "total_steps": 1155, "loss": 0.8191, "learning_rate": 9.301263957636179e-07, "epoch": 0.5314322747893714, "percentage": 17.75, "elapsed_time": "0:58:27", "remaining_time": "4:30:52"}
+{"current_steps": 210, "total_steps": 1155, "loss": 0.8191, "learning_rate": 9.265886573939446e-07, "epoch": 0.5443940375891121, "percentage": 18.18, "elapsed_time": "0:59:32", "remaining_time": "4:27:56"}
+{"current_steps": 215, "total_steps": 1155, "loss": 0.8255, "learning_rate": 9.229706346044747e-07, "epoch": 0.5573558003888529, "percentage": 18.61, "elapsed_time": "1:00:37", "remaining_time": "4:25:05"}
+{"current_steps": 220, "total_steps": 1155, "loss": 0.8164, "learning_rate": 9.192730083107818e-07, "epoch": 0.5703175631885936, "percentage": 19.05, "elapsed_time": "1:01:43", "remaining_time": "4:22:18"}
+{"current_steps": 225, "total_steps": 1155, "loss": 0.7939, "learning_rate": 9.154964744099005e-07, "epoch": 0.5832793259883344, "percentage": 19.48, "elapsed_time": "1:02:48", "remaining_time": "4:19:35"}
+{"current_steps": 230, "total_steps": 1155, "loss": 0.8034, "learning_rate": 9.116417436493573e-07, "epoch": 0.5962410887880751, "percentage": 19.91, "elapsed_time": "1:03:54", "remaining_time": "4:17:00"}
+{"current_steps": 235, "total_steps": 1155, "loss": 0.8063, "learning_rate": 9.077095414934075e-07, "epoch": 0.609202851587816, "percentage": 20.35, "elapsed_time": "1:05:00", "remaining_time": "4:14:28"}
+{"current_steps": 240, "total_steps": 1155, "loss": 0.8233, "learning_rate": 9.037006079865015e-07, "epoch": 0.6221646143875567, "percentage": 20.78, "elapsed_time": "1:06:05", "remaining_time": "4:11:59"}
+{"current_steps": 245, "total_steps": 1155, "loss": 0.8283, "learning_rate": 8.996156976140086e-07, "epoch": 0.6351263771872975, "percentage": 21.21, "elapsed_time": "1:07:10", "remaining_time": "4:09:30"}
+{"current_steps": 250, "total_steps": 1155, "loss": 0.8168, "learning_rate": 8.95455579160221e-07, "epoch": 0.6480881399870383, "percentage": 21.65, "elapsed_time": "1:08:16", "remaining_time": "4:07:08"}
+{"current_steps": 250, "total_steps": 1155, "eval_loss": 0.810850977897644, "epoch": 0.6480881399870383, "percentage": 21.65, "elapsed_time": "1:11:26", "remaining_time": "4:18:36"}
+{"current_steps": 255, "total_steps": 1155, "loss": 0.7922, "learning_rate": 8.912210355636689e-07, "epoch": 0.661049902786779, "percentage": 22.08, "elapsed_time": "1:12:31", "remaining_time": "4:15:57"}
+{"current_steps": 260, "total_steps": 1155, "loss": 0.8044, "learning_rate": 8.8691286376977e-07, "epoch": 0.6740116655865198, "percentage": 22.51, "elapsed_time": "1:13:36", "remaining_time": "4:13:24"}
+{"current_steps": 265, "total_steps": 1155, "loss": 0.7933, "learning_rate": 8.825318745808439e-07, "epoch": 0.6869734283862605, "percentage": 22.94, "elapsed_time": "1:14:42", "remaining_time": "4:10:54"}
+{"current_steps": 270, "total_steps": 1155, "loss": 0.8018, "learning_rate": 8.780788925035177e-07, "epoch": 0.6999351911860013, "percentage": 23.38, "elapsed_time": "1:15:47", "remaining_time": "4:08:26"}
+{"current_steps": 275, "total_steps": 1155, "loss": 0.7961, "learning_rate": 8.735547555935537e-07, "epoch": 0.712896953985742, "percentage": 23.81, "elapsed_time": "1:16:53", "remaining_time": "4:06:02"}
+{"current_steps": 280, "total_steps": 1155, "loss": 0.812, "learning_rate": 8.689603152981262e-07, "epoch": 0.7258587167854829, "percentage": 24.24, "elapsed_time": "1:17:59", "remaining_time": "4:03:43"}
+{"current_steps": 285, "total_steps": 1155, "loss": 0.7971, "learning_rate": 8.64296436295578e-07, "epoch": 0.7388204795852236, "percentage": 24.68, "elapsed_time": "1:19:03", "remaining_time": "4:01:21"}
+{"current_steps": 290, "total_steps": 1155, "loss": 0.8067, "learning_rate": 8.595639963326879e-07, "epoch": 0.7517822423849644, "percentage": 25.11, "elapsed_time": "1:20:09", "remaining_time": "3:59:04"}
+{"current_steps": 295, "total_steps": 1155, "loss": 0.8155, "learning_rate": 8.547638860594764e-07, "epoch": 0.7647440051847051, "percentage": 25.54, "elapsed_time": "1:21:14", "remaining_time": "3:56:51"}
+{"current_steps": 300, "total_steps": 1155, "loss": 0.8021, "learning_rate": 8.49897008861586e-07, "epoch": 0.7777057679844459, "percentage": 25.97, "elapsed_time": "1:22:20", "remaining_time": "3:54:41"}
+{"current_steps": 300, "total_steps": 1155, "eval_loss": 0.800530195236206, "epoch": 0.7777057679844459, "percentage": 25.97, "elapsed_time": "1:25:31", "remaining_time": "4:03:44"}
+{"current_steps": 305, "total_steps": 1155, "loss": 0.7993, "learning_rate": 8.449642806902622e-07, "epoch": 0.7906675307841866, "percentage": 26.41, "elapsed_time": "1:27:08", "remaining_time": "4:02:51"}
+{"current_steps": 310, "total_steps": 1155, "loss": 0.7918, "learning_rate": 8.399666298899706e-07, "epoch": 0.8036292935839274, "percentage": 26.84, "elapsed_time": "1:28:14", "remaining_time": "4:00:31"}
+{"current_steps": 315, "total_steps": 1155, "loss": 0.7943, "learning_rate": 8.34904997023682e-07, "epoch": 0.8165910563836681, "percentage": 27.27, "elapsed_time": "1:29:20", "remaining_time": "3:58:14"}
+{"current_steps": 320, "total_steps": 1155, "loss": 0.783, "learning_rate": 8.297803346958569e-07, "epoch": 0.829552819183409, "percentage": 27.71, "elapsed_time": "1:30:25", "remaining_time": "3:55:57"}
+{"current_steps": 325, "total_steps": 1155, "loss": 0.7976, "learning_rate": 8.245936073731651e-07, "epoch": 0.8425145819831497, "percentage": 28.14, "elapsed_time": "1:31:29", "remaining_time": "3:53:40"}
+{"current_steps": 330, "total_steps": 1155, "loss": 0.7807, "learning_rate": 8.193457912029712e-07, "epoch": 0.8554763447828905, "percentage": 28.57, "elapsed_time": "1:32:36", "remaining_time": "3:51:30"}
+{"current_steps": 335, "total_steps": 1155, "loss": 0.7836, "learning_rate": 8.140378738296232e-07, "epoch": 0.8684381075826313, "percentage": 29.0, "elapsed_time": "1:33:41", "remaining_time": "3:49:20"}
+{"current_steps": 340, "total_steps": 1155, "loss": 0.8063, "learning_rate": 8.086708542085767e-07, "epoch": 0.881399870382372, "percentage": 29.44, "elapsed_time": "1:34:46", "remaining_time": "3:47:11"}
+{"current_steps": 345, "total_steps": 1155, "loss": 0.7911, "learning_rate": 8.032457424183909e-07, "epoch": 0.8943616331821128, "percentage": 29.87, "elapsed_time": "1:35:52", "remaining_time": "3:45:05"}
+{"current_steps": 350, "total_steps": 1155, "loss": 0.7741, "learning_rate": 7.977635594706298e-07, "epoch": 0.9073233959818535, "percentage": 30.3, "elapsed_time": "1:36:58", "remaining_time": "3:43:01"}
+{"current_steps": 350, "total_steps": 1155, "eval_loss": 0.7928882837295532, "epoch": 0.9073233959818535, "percentage": 30.3, "elapsed_time": "1:40:08", "remaining_time": "3:50:19"}
+{"current_steps": 355, "total_steps": 1155, "loss": 0.7932, "learning_rate": 7.922253371177082e-07, "epoch": 0.9202851587815943, "percentage": 30.74, "elapsed_time": "1:41:12", "remaining_time": "3:48:05"}
+{"current_steps": 360, "total_steps": 1155, "loss": 0.7871, "learning_rate": 7.866321176587128e-07, "epoch": 0.933246921581335, "percentage": 31.17, "elapsed_time": "1:42:18", "remaining_time": "3:45:56"}
+{"current_steps": 365, "total_steps": 1155, "loss": 0.7792, "learning_rate": 7.809849537432431e-07, "epoch": 0.9462086843810759, "percentage": 31.6, "elapsed_time": "1:43:24", "remaining_time": "3:43:48"}
+{"current_steps": 370, "total_steps": 1155, "loss": 0.788, "learning_rate": 7.752849081732991e-07, "epoch": 0.9591704471808166, "percentage": 32.03, "elapsed_time": "1:44:29", "remaining_time": "3:41:41"}
+{"current_steps": 375, "total_steps": 1155, "loss": 0.7614, "learning_rate": 7.695330537032627e-07, "epoch": 0.9721322099805574, "percentage": 32.47, "elapsed_time": "1:45:35", "remaining_time": "3:39:37"}
+{"current_steps": 380, "total_steps": 1155, "loss": 0.7964, "learning_rate": 7.637304728380037e-07, "epoch": 0.9850939727802981, "percentage": 32.9, "elapsed_time": "1:46:40", "remaining_time": "3:37:32"}
+{"current_steps": 385, "total_steps": 1155, "loss": 0.7659, "learning_rate": 7.5787825762915e-07, "epoch": 0.9980557355800389, "percentage": 33.33, "elapsed_time": "1:47:45", "remaining_time": "3:35:31"}
+{"current_steps": 390, "total_steps": 1155, "loss": 0.729, "learning_rate": 7.519775094695648e-07, "epoch": 1.0110174983797797, "percentage": 33.77, "elapsed_time": "1:48:50", "remaining_time": "3:33:29"}
+{"current_steps": 395, "total_steps": 1155, "loss": 0.7421, "learning_rate": 7.460293388860614e-07, "epoch": 1.0239792611795204, "percentage": 34.2, "elapsed_time": "1:49:55", "remaining_time": "3:31:30"}
+{"current_steps": 400, "total_steps": 1155, "loss": 0.7155, "learning_rate": 7.400348653304021e-07, "epoch": 1.0369410239792611, "percentage": 34.63, "elapsed_time": "1:51:00", "remaining_time": "3:29:31"}
+{"current_steps": 400, "total_steps": 1155, "eval_loss": 0.7879951596260071, "epoch": 1.0369410239792611, "percentage": 34.63, "elapsed_time": "1:54:11", "remaining_time": "3:35:31"}
+{"current_steps": 405, "total_steps": 1155, "loss": 0.721, "learning_rate": 7.33995216968615e-07, "epoch": 1.0499027867790018, "percentage": 35.06, "elapsed_time": "1:55:47", "remaining_time": "3:34:25"}
+{"current_steps": 410, "total_steps": 1155, "loss": 0.7251, "learning_rate": 7.279115304686733e-07, "epoch": 1.0628645495787428, "percentage": 35.5, "elapsed_time": "1:56:53", "remaining_time": "3:32:24"}
+{"current_steps": 415, "total_steps": 1155, "loss": 0.7079, "learning_rate": 7.217849507865723e-07, "epoch": 1.0758263123784835, "percentage": 35.93, "elapsed_time": "1:57:59", "remaining_time": "3:30:23"}
+{"current_steps": 420, "total_steps": 1155, "loss": 0.716, "learning_rate": 7.156166309508481e-07, "epoch": 1.0887880751782242, "percentage": 36.36, "elapsed_time": "1:59:04", "remaining_time": "3:28:22"}
+{"current_steps": 425, "total_steps": 1155, "loss": 0.7248, "learning_rate": 7.094077318455761e-07, "epoch": 1.101749837977965, "percentage": 36.8, "elapsed_time": "2:00:09", "remaining_time": "3:26:23"}
+{"current_steps": 430, "total_steps": 1155, "loss": 0.7282, "learning_rate": 7.031594219918915e-07, "epoch": 1.1147116007777058, "percentage": 37.23, "elapsed_time": "2:01:14", "remaining_time": "3:24:24"}
+{"current_steps": 435, "total_steps": 1155, "loss": 0.7214, "learning_rate": 6.968728773280729e-07, "epoch": 1.1276733635774465, "percentage": 37.66, "elapsed_time": "2:02:19", "remaining_time": "3:22:28"}
+{"current_steps": 440, "total_steps": 1155, "loss": 0.7149, "learning_rate": 6.905492809882285e-07, "epoch": 1.1406351263771872, "percentage": 38.1, "elapsed_time": "2:03:25", "remaining_time": "3:20:33"}
+{"current_steps": 445, "total_steps": 1155, "loss": 0.7118, "learning_rate": 6.841898230796302e-07, "epoch": 1.1535968891769282, "percentage": 38.53, "elapsed_time": "2:04:29", "remaining_time": "3:18:38"}
+{"current_steps": 450, "total_steps": 1155, "loss": 0.7322, "learning_rate": 6.777957004587331e-07, "epoch": 1.1665586519766689, "percentage": 38.96, "elapsed_time": "2:05:35", "remaining_time": "3:16:45"}
+{"current_steps": 450, "total_steps": 1155, "eval_loss": 0.7836564779281616, "epoch": 1.1665586519766689, "percentage": 38.96, "elapsed_time": "2:08:46", "remaining_time": "3:21:44"}
+{"current_steps": 455, "total_steps": 1155, "loss": 0.731, "learning_rate": 6.713681165059271e-07, "epoch": 1.1795204147764096, "percentage": 39.39, "elapsed_time": "2:09:51", "remaining_time": "3:19:46"}
+{"current_steps": 460, "total_steps": 1155, "loss": 0.7263, "learning_rate": 6.649082808990585e-07, "epoch": 1.1924821775761503, "percentage": 39.83, "elapsed_time": "2:10:56", "remaining_time": "3:17:49"}
+{"current_steps": 465, "total_steps": 1155, "loss": 0.7138, "learning_rate": 6.584174093857675e-07, "epoch": 1.2054439403758912, "percentage": 40.26, "elapsed_time": "2:12:00", "remaining_time": "3:15:53"}
+{"current_steps": 470, "total_steps": 1155, "loss": 0.7131, "learning_rate": 6.518967235546841e-07, "epoch": 1.218405703175632, "percentage": 40.69, "elapsed_time": "2:13:07", "remaining_time": "3:14:00"}
+{"current_steps": 475, "total_steps": 1155, "loss": 0.7056, "learning_rate": 6.453474506055227e-07, "epoch": 1.2313674659753726, "percentage": 41.13, "elapsed_time": "2:14:12", "remaining_time": "3:12:07"}
+{"current_steps": 480, "total_steps": 1155, "loss": 0.7142, "learning_rate": 6.387708231181228e-07, "epoch": 1.2443292287751135, "percentage": 41.56, "elapsed_time": "2:15:17", "remaining_time": "3:10:15"}
+{"current_steps": 485, "total_steps": 1155, "loss": 0.7295, "learning_rate": 6.321680788204757e-07, "epoch": 1.2572909915748542, "percentage": 41.99, "elapsed_time": "2:16:22", "remaining_time": "3:08:24"}
+{"current_steps": 490, "total_steps": 1155, "loss": 0.6984, "learning_rate": 6.255404603557833e-07, "epoch": 1.270252754374595, "percentage": 42.42, "elapsed_time": "2:17:28", "remaining_time": "3:06:33"}
+{"current_steps": 495, "total_steps": 1155, "loss": 0.7286, "learning_rate": 6.188892150485902e-07, "epoch": 1.2832145171743357, "percentage": 42.86, "elapsed_time": "2:18:33", "remaining_time": "3:04:44"}
+{"current_steps": 500, "total_steps": 1155, "loss": 0.7214, "learning_rate": 6.122155946700381e-07, "epoch": 1.2961762799740764, "percentage": 43.29, "elapsed_time": "2:19:38", "remaining_time": "3:02:56"}
+{"current_steps": 500, "total_steps": 1155, "eval_loss": 0.7790202498435974, "epoch": 1.2961762799740764, "percentage": 43.29, "elapsed_time": "2:22:48", "remaining_time": "3:07:05"}
+{"current_steps": 505, "total_steps": 1155, "loss": 0.7183, "learning_rate": 6.055208552022787e-07, "epoch": 1.3091380427738173, "percentage": 43.72, "elapsed_time": "2:24:24", "remaining_time": "3:05:52"}
+{"current_steps": 510, "total_steps": 1155, "loss": 0.7188, "learning_rate": 5.988062566020986e-07, "epoch": 1.322099805573558, "percentage": 44.16, "elapsed_time": "2:25:29", "remaining_time": "3:04:00"}
+{"current_steps": 515, "total_steps": 1155, "loss": 0.6976, "learning_rate": 5.920730625637933e-07, "epoch": 1.3350615683732987, "percentage": 44.59, "elapsed_time": "2:26:35", "remaining_time": "3:02:09"}
+{"current_steps": 520, "total_steps": 1155, "loss": 0.7274, "learning_rate": 5.85322540281338e-07, "epoch": 1.3480233311730396, "percentage": 45.02, "elapsed_time": "2:27:40", "remaining_time": "3:00:19"}
+{"current_steps": 525, "total_steps": 1155, "loss": 0.7084, "learning_rate": 5.785559602099018e-07, "epoch": 1.3609850939727803, "percentage": 45.45, "elapsed_time": "2:28:45", "remaining_time": "2:58:30"}
+{"current_steps": 530, "total_steps": 1155, "loss": 0.7119, "learning_rate": 5.717745958267459e-07, "epoch": 1.373946856772521, "percentage": 45.89, "elapsed_time": "2:29:50", "remaining_time": "2:56:42"}
+{"current_steps": 535, "total_steps": 1155, "loss": 0.7086, "learning_rate": 5.649797233915538e-07, "epoch": 1.3869086195722617, "percentage": 46.32, "elapsed_time": "2:30:55", "remaining_time": "2:54:54"}
+{"current_steps": 540, "total_steps": 1155, "loss": 0.716, "learning_rate": 5.581726217062386e-07, "epoch": 1.3998703823720027, "percentage": 46.75, "elapsed_time": "2:32:01", "remaining_time": "2:53:08"}
+{"current_steps": 545, "total_steps": 1155, "loss": 0.7071, "learning_rate": 5.513545718742701e-07, "epoch": 1.4128321451717434, "percentage": 47.19, "elapsed_time": "2:33:06", "remaining_time": "2:51:22"}
+{"current_steps": 550, "total_steps": 1155, "loss": 0.6936, "learning_rate": 5.445268570595708e-07, "epoch": 1.425793907971484, "percentage": 47.62, "elapsed_time": "2:34:12", "remaining_time": "2:49:37"}
+{"current_steps": 550, "total_steps": 1155, "eval_loss": 0.7752651572227478, "epoch": 1.425793907971484, "percentage": 47.62, "elapsed_time": "2:37:22", "remaining_time": "2:53:07"}
+{"current_steps": 555, "total_steps": 1155, "loss": 0.7155, "learning_rate": 5.376907622450228e-07, "epoch": 1.4387556707712248, "percentage": 48.05, "elapsed_time": "2:38:28", "remaining_time": "2:51:19"}
+{"current_steps": 560, "total_steps": 1155, "loss": 0.7086, "learning_rate": 5.308475739906328e-07, "epoch": 1.4517174335709657, "percentage": 48.48, "elapsed_time": "2:39:33", "remaining_time": "2:49:31"}
+{"current_steps": 565, "total_steps": 1155, "loss": 0.7136, "learning_rate": 5.239985801913999e-07, "epoch": 1.4646791963707064, "percentage": 48.92, "elapsed_time": "2:40:38", "remaining_time": "2:47:45"}
+{"current_steps": 570, "total_steps": 1155, "loss": 0.7208, "learning_rate": 5.171450698349329e-07, "epoch": 1.4776409591704471, "percentage": 49.35, "elapsed_time": "2:41:44", "remaining_time": "2:45:59"}
+{"current_steps": 575, "total_steps": 1155, "loss": 0.7055, "learning_rate": 5.102883327588608e-07, "epoch": 1.490602721970188, "percentage": 49.78, "elapsed_time": "2:42:50", "remaining_time": "2:44:15"}
+{"current_steps": 580, "total_steps": 1155, "loss": 0.6824, "learning_rate": 5.034296594080848e-07, "epoch": 1.5035644847699285, "percentage": 50.22, "elapsed_time": "2:43:55", "remaining_time": "2:42:30"}
+{"current_steps": 585, "total_steps": 1155, "loss": 0.733, "learning_rate": 4.965703405919153e-07, "epoch": 1.5165262475696695, "percentage": 50.65, "elapsed_time": "2:45:00", "remaining_time": "2:40:46"}
+{"current_steps": 590, "total_steps": 1155, "loss": 0.7011, "learning_rate": 4.897116672411394e-07, "epoch": 1.5294880103694104, "percentage": 51.08, "elapsed_time": "2:46:06", "remaining_time": "2:39:03"}
+{"current_steps": 595, "total_steps": 1155, "loss": 0.7216, "learning_rate": 4.828549301650673e-07, "epoch": 1.5424497731691509, "percentage": 51.52, "elapsed_time": "2:47:10", "remaining_time": "2:37:20"}
+{"current_steps": 600, "total_steps": 1155, "loss": 0.7046, "learning_rate": 4.760014198086001e-07, "epoch": 1.5554115359688918, "percentage": 51.95, "elapsed_time": "2:48:16", "remaining_time": "2:35:39"}
+{"current_steps": 600, "total_steps": 1155, "eval_loss": 0.7716971039772034, "epoch": 1.5554115359688918, "percentage": 51.95, "elapsed_time": "2:51:26", "remaining_time": "2:38:35"}
+{"current_steps": 605, "total_steps": 1155, "loss": 0.7177, "learning_rate": 4.691524260093672e-07, "epoch": 1.5683732987686325, "percentage": 52.38, "elapsed_time": "2:53:04", "remaining_time": "2:37:20"}
+{"current_steps": 610, "total_steps": 1155, "loss": 0.698, "learning_rate": 4.6230923775497714e-07, "epoch": 1.5813350615683732, "percentage": 52.81, "elapsed_time": "2:54:09", "remaining_time": "2:35:36"}
+{"current_steps": 615, "total_steps": 1155, "loss": 0.7068, "learning_rate": 4.554731429404293e-07, "epoch": 1.5942968243681142, "percentage": 53.25, "elapsed_time": "2:55:14", "remaining_time": "2:33:52"}
+{"current_steps": 620, "total_steps": 1155, "loss": 0.7105, "learning_rate": 4.486454281257299e-07, "epoch": 1.6072585871678549, "percentage": 53.68, "elapsed_time": "2:56:20", "remaining_time": "2:32:10"}
+{"current_steps": 625, "total_steps": 1155, "loss": 0.7002, "learning_rate": 4.4182737829376135e-07, "epoch": 1.6202203499675956, "percentage": 54.11, "elapsed_time": "2:57:25", "remaining_time": "2:30:27"}
+{"current_steps": 630, "total_steps": 1155, "loss": 0.7132, "learning_rate": 4.35020276608446e-07, "epoch": 1.6331821127673365, "percentage": 54.55, "elapsed_time": "2:58:31", "remaining_time": "2:28:46"}
+{"current_steps": 635, "total_steps": 1155, "loss": 0.7239, "learning_rate": 4.2822540417325394e-07, "epoch": 1.646143875567077, "percentage": 54.98, "elapsed_time": "2:59:37", "remaining_time": "2:27:05"}
+{"current_steps": 640, "total_steps": 1155, "loss": 0.708, "learning_rate": 4.2144403979009823e-07, "epoch": 1.659105638366818, "percentage": 55.41, "elapsed_time": "3:00:42", "remaining_time": "2:25:25"}
+{"current_steps": 645, "total_steps": 1155, "loss": 0.7152, "learning_rate": 4.1467745971866214e-07, "epoch": 1.6720674011665586, "percentage": 55.84, "elapsed_time": "3:01:47", "remaining_time": "2:23:44"}
+{"current_steps": 650, "total_steps": 1155, "loss": 0.6967, "learning_rate": 4.0792693743620686e-07, "epoch": 1.6850291639662993, "percentage": 56.28, "elapsed_time": "3:02:53", "remaining_time": "2:22:05"}
+{"current_steps": 650, "total_steps": 1155, "eval_loss": 0.7689746618270874, "epoch": 1.6850291639662993, "percentage": 56.28, "elapsed_time": "3:06:04", "remaining_time": "2:24:34"}
+{"current_steps": 655, "total_steps": 1155, "loss": 0.7024, "learning_rate": 4.0119374339790133e-07, "epoch": 1.6979909267660402, "percentage": 56.71, "elapsed_time": "3:07:10", "remaining_time": "2:22:52"}
+{"current_steps": 660, "total_steps": 1155, "loss": 0.7242, "learning_rate": 3.944791447977213e-07, "epoch": 1.710952689565781, "percentage": 57.14, "elapsed_time": "3:08:15", "remaining_time": "2:21:11"}
+{"current_steps": 665, "total_steps": 1155, "loss": 0.7089, "learning_rate": 3.87784405329962e-07, "epoch": 1.7239144523655217, "percentage": 57.58, "elapsed_time": "3:09:21", "remaining_time": "2:19:31"}
+{"current_steps": 670, "total_steps": 1155, "loss": 0.7219, "learning_rate": 3.8111078495140973e-07, "epoch": 1.7368762151652626, "percentage": 58.01, "elapsed_time": "3:10:25", "remaining_time": "2:17:51"}
+{"current_steps": 675, "total_steps": 1155, "loss": 0.7078, "learning_rate": 3.7445953964421684e-07, "epoch": 1.7498379779650033, "percentage": 58.44, "elapsed_time": "3:11:31", "remaining_time": "2:16:11"}
+{"current_steps": 680, "total_steps": 1155, "loss": 0.7263, "learning_rate": 3.678319211795242e-07, "epoch": 1.762799740764744, "percentage": 58.87, "elapsed_time": "3:12:37", "remaining_time": "2:14:33"}
+{"current_steps": 685, "total_steps": 1155, "loss": 0.6994, "learning_rate": 3.6122917688187717e-07, "epoch": 1.775761503564485, "percentage": 59.31, "elapsed_time": "3:13:42", "remaining_time": "2:12:54"}
+{"current_steps": 690, "total_steps": 1155, "loss": 0.7112, "learning_rate": 3.546525493944773e-07, "epoch": 1.7887232663642254, "percentage": 59.74, "elapsed_time": "3:14:48", "remaining_time": "2:11:16"}
+{"current_steps": 695, "total_steps": 1155, "loss": 0.7145, "learning_rate": 3.48103276445316e-07, "epoch": 1.8016850291639663, "percentage": 60.17, "elapsed_time": "3:15:53", "remaining_time": "2:09:39"}
+{"current_steps": 700, "total_steps": 1155, "loss": 0.7197, "learning_rate": 3.4158259061423255e-07, "epoch": 1.814646791963707, "percentage": 60.61, "elapsed_time": "3:16:59", "remaining_time": "2:08:02"}
+{"current_steps": 700, "total_steps": 1155, "eval_loss": 0.765801727771759, "epoch": 1.814646791963707, "percentage": 60.61, "elapsed_time": "3:20:10", "remaining_time": "2:10:06"}
+{"current_steps": 705, "total_steps": 1155, "loss": 0.7008, "learning_rate": 3.3509171910094156e-07, "epoch": 1.8276085547634477, "percentage": 61.04, "elapsed_time": "3:21:48", "remaining_time": "2:08:48"}
+{"current_steps": 710, "total_steps": 1155, "loss": 0.7101, "learning_rate": 3.286318834940729e-07, "epoch": 1.8405703175631887, "percentage": 61.47, "elapsed_time": "3:22:53", "remaining_time": "2:07:10"}
+{"current_steps": 715, "total_steps": 1155, "loss": 0.6797, "learning_rate": 3.2220429954126686e-07, "epoch": 1.8535320803629294, "percentage": 61.9, "elapsed_time": "3:23:59", "remaining_time": "2:05:31"}
+{"current_steps": 720, "total_steps": 1155, "loss": 0.7056, "learning_rate": 3.158101769203698e-07, "epoch": 1.86649384316267, "percentage": 62.34, "elapsed_time": "3:25:04", "remaining_time": "2:03:53"}
+{"current_steps": 725, "total_steps": 1155, "loss": 0.7093, "learning_rate": 3.0945071901177145e-07, "epoch": 1.879455605962411, "percentage": 62.77, "elapsed_time": "3:26:10", "remaining_time": "2:02:16"}
+{"current_steps": 730, "total_steps": 1155, "loss": 0.7084, "learning_rate": 3.031271226719271e-07, "epoch": 1.8924173687621515, "percentage": 63.2, "elapsed_time": "3:27:15", "remaining_time": "2:00:40"}
+{"current_steps": 735, "total_steps": 1155, "loss": 0.7072, "learning_rate": 2.968405780081084e-07, "epoch": 1.9053791315618924, "percentage": 63.64, "elapsed_time": "3:28:21", "remaining_time": "1:59:03"}
+{"current_steps": 740, "total_steps": 1155, "loss": 0.6969, "learning_rate": 2.905922681544238e-07, "epoch": 1.9183408943616331, "percentage": 64.07, "elapsed_time": "3:29:27", "remaining_time": "1:57:27"}
+{"current_steps": 745, "total_steps": 1155, "loss": 0.6882, "learning_rate": 2.8438336904915184e-07, "epoch": 1.9313026571613738, "percentage": 64.5, "elapsed_time": "3:30:32", "remaining_time": "1:55:52"}
+{"current_steps": 750, "total_steps": 1155, "loss": 0.704, "learning_rate": 2.7821504921342774e-07, "epoch": 1.9442644199611148, "percentage": 64.94, "elapsed_time": "3:31:38", "remaining_time": "1:54:16"}
+{"current_steps": 750, "total_steps": 1155, "eval_loss": 0.7632837295532227, "epoch": 1.9442644199611148, "percentage": 64.94, "elapsed_time": "3:34:48", "remaining_time": "1:55:59"}
+{"current_steps": 755, "total_steps": 1155, "loss": 0.6927, "learning_rate": 2.7208846953132683e-07, "epoch": 1.9572261827608555, "percentage": 65.37, "elapsed_time": "3:35:54", "remaining_time": "1:54:23"}
+{"current_steps": 760, "total_steps": 1155, "loss": 0.7037, "learning_rate": 2.66004783031385e-07, "epoch": 1.9701879455605962, "percentage": 65.8, "elapsed_time": "3:36:59", "remaining_time": "1:52:46"}
+{"current_steps": 765, "total_steps": 1155, "loss": 0.6926, "learning_rate": 2.599651346695979e-07, "epoch": 1.983149708360337, "percentage": 66.23, "elapsed_time": "3:38:04", "remaining_time": "1:51:10"}
+{"current_steps": 770, "total_steps": 1155, "loss": 0.7111, "learning_rate": 2.539706611139385e-07, "epoch": 1.9961114711600778, "percentage": 66.67, "elapsed_time": "3:39:09", "remaining_time": "1:49:34"}
+{"current_steps": 775, "total_steps": 1155, "loss": 0.6801, "learning_rate": 2.480224905304352e-07, "epoch": 2.0090732339598185, "percentage": 67.1, "elapsed_time": "3:40:14", "remaining_time": "1:47:59"}
+{"current_steps": 780, "total_steps": 1155, "loss": 0.663, "learning_rate": 2.4212174237085005e-07, "epoch": 2.0220349967595594, "percentage": 67.53, "elapsed_time": "3:41:19", "remaining_time": "1:46:24"}
+{"current_steps": 785, "total_steps": 1155, "loss": 0.6784, "learning_rate": 2.3626952716199644e-07, "epoch": 2.0349967595593, "percentage": 67.97, "elapsed_time": "3:42:24", "remaining_time": "1:44:49"}
+{"current_steps": 790, "total_steps": 1155, "loss": 0.6293, "learning_rate": 2.3046694629673712e-07, "epoch": 2.047958522359041, "percentage": 68.4, "elapsed_time": "3:43:30", "remaining_time": "1:43:16"}
+{"current_steps": 795, "total_steps": 1155, "loss": 0.6489, "learning_rate": 2.247150918267008e-07, "epoch": 2.060920285158782, "percentage": 68.83, "elapsed_time": "3:44:36", "remaining_time": "1:41:42"}
+{"current_steps": 800, "total_steps": 1155, "loss": 0.6546, "learning_rate": 2.1901504625675688e-07, "epoch": 2.0738820479585223, "percentage": 69.26, "elapsed_time": "3:45:41", "remaining_time": "1:40:09"}
+{"current_steps": 800, "total_steps": 1155, "eval_loss": 0.7677435874938965, "epoch": 2.0738820479585223, "percentage": 69.26, "elapsed_time": "3:48:52", "remaining_time": "1:41:33"}
+{"current_steps": 805, "total_steps": 1155, "loss": 0.6676, "learning_rate": 2.1336788234128729e-07, "epoch": 2.086843810758263, "percentage": 69.7, "elapsed_time": "3:50:34", "remaining_time": "1:40:14"}
+{"current_steps": 810, "total_steps": 1155, "loss": 0.6629, "learning_rate": 2.0777466288229205e-07, "epoch": 2.0998055735580037, "percentage": 70.13, "elapsed_time": "3:51:39", "remaining_time": "1:38:40"}
+{"current_steps": 815, "total_steps": 1155, "loss": 0.6418, "learning_rate": 2.0223644052937028e-07, "epoch": 2.1127673363577446, "percentage": 70.56, "elapsed_time": "3:52:44", "remaining_time": "1:37:05"}
+{"current_steps": 820, "total_steps": 1155, "loss": 0.6531, "learning_rate": 1.9675425758160924e-07, "epoch": 2.1257290991574855, "percentage": 71.0, "elapsed_time": "3:53:49", "remaining_time": "1:35:31"}
+{"current_steps": 825, "total_steps": 1155, "loss": 0.6346, "learning_rate": 1.9132914579142338e-07, "epoch": 2.138690861957226, "percentage": 71.43, "elapsed_time": "3:54:54", "remaining_time": "1:33:57"}
+{"current_steps": 830, "total_steps": 1155, "loss": 0.6654, "learning_rate": 1.8596212617037693e-07, "epoch": 2.151652624756967, "percentage": 71.86, "elapsed_time": "3:55:59", "remaining_time": "1:32:24"}
+{"current_steps": 835, "total_steps": 1155, "loss": 0.6649, "learning_rate": 1.8065420879702887e-07, "epoch": 2.164614387556708, "percentage": 72.29, "elapsed_time": "3:57:05", "remaining_time": "1:30:51"}
+{"current_steps": 840, "total_steps": 1155, "loss": 0.6433, "learning_rate": 1.7540639262683487e-07, "epoch": 2.1775761503564484, "percentage": 72.73, "elapsed_time": "3:58:11", "remaining_time": "1:29:19"}
+{"current_steps": 845, "total_steps": 1155, "loss": 0.6769, "learning_rate": 1.70219665304143e-07, "epoch": 2.1905379131561893, "percentage": 73.16, "elapsed_time": "3:59:16", "remaining_time": "1:27:46"}
+{"current_steps": 850, "total_steps": 1155, "loss": 0.651, "learning_rate": 1.6509500297631785e-07, "epoch": 2.20349967595593, "percentage": 73.59, "elapsed_time": "4:00:22", "remaining_time": "1:26:14"}
+{"current_steps": 850, "total_steps": 1155, "eval_loss": 0.7672791481018066, "epoch": 2.20349967595593, "percentage": 73.59, "elapsed_time": "4:03:32", "remaining_time": "1:27:23"}
+{"current_steps": 855, "total_steps": 1155, "loss": 0.6564, "learning_rate": 1.6003337011002927e-07, "epoch": 2.2164614387556707, "percentage": 74.03, "elapsed_time": "4:04:38", "remaining_time": "1:25:50"}
+{"current_steps": 860, "total_steps": 1155, "loss": 0.6426, "learning_rate": 1.5503571930973785e-07, "epoch": 2.2294232015554116, "percentage": 74.46, "elapsed_time": "4:05:43", "remaining_time": "1:24:17"}
+{"current_steps": 865, "total_steps": 1155, "loss": 0.6518, "learning_rate": 1.5010299113841397e-07, "epoch": 2.242384964355152, "percentage": 74.89, "elapsed_time": "4:06:48", "remaining_time": "1:22:44"}
+{"current_steps": 870, "total_steps": 1155, "loss": 0.6475, "learning_rate": 1.4523611394052355e-07, "epoch": 2.255346727154893, "percentage": 75.32, "elapsed_time": "4:07:54", "remaining_time": "1:21:12"}
+{"current_steps": 875, "total_steps": 1155, "loss": 0.662, "learning_rate": 1.4043600366731213e-07, "epoch": 2.268308489954634, "percentage": 75.76, "elapsed_time": "4:08:59", "remaining_time": "1:19:40"}
+{"current_steps": 880, "total_steps": 1155, "loss": 0.6552, "learning_rate": 1.3570356370442189e-07, "epoch": 2.2812702527543745, "percentage": 76.19, "elapsed_time": "4:10:04", "remaining_time": "1:18:08"}
+{"current_steps": 885, "total_steps": 1155, "loss": 0.6476, "learning_rate": 1.3103968470187382e-07, "epoch": 2.2942320155541154, "percentage": 76.62, "elapsed_time": "4:11:09", "remaining_time": "1:16:37"}
+{"current_steps": 890, "total_steps": 1155, "loss": 0.6685, "learning_rate": 1.2644524440644627e-07, "epoch": 2.3071937783538563, "percentage": 77.06, "elapsed_time": "4:12:14", "remaining_time": "1:15:06"}
+{"current_steps": 895, "total_steps": 1155, "loss": 0.6655, "learning_rate": 1.2192110749648232e-07, "epoch": 2.320155541153597, "percentage": 77.49, "elapsed_time": "4:13:19", "remaining_time": "1:13:35"}
+{"current_steps": 900, "total_steps": 1155, "loss": 0.6601, "learning_rate": 1.1746812541915607e-07, "epoch": 2.3331173039533377, "percentage": 77.92, "elapsed_time": "4:14:24", "remaining_time": "1:12:04"}
+{"current_steps": 900, "total_steps": 1155, "eval_loss": 0.7666835188865662, "epoch": 2.3331173039533377, "percentage": 77.92, "elapsed_time": "4:17:35", "remaining_time": "1:12:58"}
+{"current_steps": 905, "total_steps": 1155, "loss": 0.6627, "learning_rate": 1.1308713623022986e-07, "epoch": 2.346079066753078, "percentage": 78.35, "elapsed_time": "4:19:15", "remaining_time": "1:11:37"}
+{"current_steps": 910, "total_steps": 1155, "loss": 0.6593, "learning_rate": 1.0877896443633117e-07, "epoch": 2.359040829552819, "percentage": 78.79, "elapsed_time": "4:20:21", "remaining_time": "1:10:05"}
+{"current_steps": 915, "total_steps": 1155, "loss": 0.6709, "learning_rate": 1.045444208397791e-07, "epoch": 2.37200259235256, "percentage": 79.22, "elapsed_time": "4:21:26", "remaining_time": "1:08:34"}
+{"current_steps": 920, "total_steps": 1155, "loss": 0.651, "learning_rate": 1.0038430238599154e-07, "epoch": 2.3849643551523005, "percentage": 79.65, "elapsed_time": "4:22:31", "remaining_time": "1:07:03"}
+{"current_steps": 925, "total_steps": 1155, "loss": 0.6588, "learning_rate": 9.629939201349852e-08, "epoch": 2.3979261179520415, "percentage": 80.09, "elapsed_time": "4:23:36", "remaining_time": "1:05:32"}
+{"current_steps": 930, "total_steps": 1155, "loss": 0.656, "learning_rate": 9.229045850659251e-08, "epoch": 2.4108878807517824, "percentage": 80.52, "elapsed_time": "4:24:41", "remaining_time": "1:04:02"}
+{"current_steps": 935, "total_steps": 1155, "loss": 0.6603, "learning_rate": 8.835825635064265e-08, "epoch": 2.423849643551523, "percentage": 80.95, "elapsed_time": "4:25:46", "remaining_time": "1:02:32"}
+{"current_steps": 940, "total_steps": 1155, "loss": 0.6572, "learning_rate": 8.450352559009949e-08, "epoch": 2.436811406351264, "percentage": 81.39, "elapsed_time": "4:26:51", "remaining_time": "1:01:02"}
+{"current_steps": 945, "total_steps": 1155, "loss": 0.6523, "learning_rate": 8.072699168921825e-08, "epoch": 2.4497731691510047, "percentage": 81.82, "elapsed_time": "4:27:57", "remaining_time": "0:59:32"}
+{"current_steps": 950, "total_steps": 1155, "loss": 0.6669, "learning_rate": 7.70293653955254e-08, "epoch": 2.462734931950745, "percentage": 82.25, "elapsed_time": "4:29:01", "remaining_time": "0:58:03"}
+{"current_steps": 950, "total_steps": 1155, "eval_loss": 0.7661544680595398, "epoch": 2.462734931950745, "percentage": 82.25, "elapsed_time": "4:32:12", "remaining_time": "0:58:44"}
+{"current_steps": 955, "total_steps": 1155, "loss": 0.6467, "learning_rate": 7.341134260605536e-08, "epoch": 2.475696694750486, "percentage": 82.68, "elapsed_time": "4:33:18", "remaining_time": "0:57:14"}
+{"current_steps": 960, "total_steps": 1155, "loss": 0.6451, "learning_rate": 6.987360423638205e-08, "epoch": 2.488658457550227, "percentage": 83.12, "elapsed_time": "4:34:23", "remaining_time": "0:55:44"}
+{"current_steps": 965, "total_steps": 1155, "loss": 0.6499, "learning_rate": 6.641681609246979e-08, "epoch": 2.5016202203499676, "percentage": 83.55, "elapsed_time": "4:35:28", "remaining_time": "0:54:14"}
+{"current_steps": 970, "total_steps": 1155, "loss": 0.6381, "learning_rate": 6.304162874536795e-08, "epoch": 2.5145819831497085, "percentage": 83.98, "elapsed_time": "4:36:33", "remaining_time": "0:52:44"}
+{"current_steps": 975, "total_steps": 1155, "loss": 0.6611, "learning_rate": 5.974867740877281e-08, "epoch": 2.527543745949449, "percentage": 84.42, "elapsed_time": "4:37:39", "remaining_time": "0:51:15"}
+{"current_steps": 980, "total_steps": 1155, "loss": 0.6511, "learning_rate": 5.653858181947979e-08, "epoch": 2.54050550874919, "percentage": 84.85, "elapsed_time": "4:38:45", "remaining_time": "0:49:46"}
+{"current_steps": 985, "total_steps": 1155, "loss": 0.645, "learning_rate": 5.341194612074823e-08, "epoch": 2.5534672715489304, "percentage": 85.28, "elapsed_time": "4:39:50", "remaining_time": "0:48:17"}
+{"current_steps": 990, "total_steps": 1155, "loss": 0.664, "learning_rate": 5.0369358748601096e-08, "epoch": 2.5664290343486713, "percentage": 85.71, "elapsed_time": "4:40:55", "remaining_time": "0:46:49"}
+{"current_steps": 995, "total_steps": 1155, "loss": 0.6768, "learning_rate": 4.74113923210806e-08, "epoch": 2.5793907971484122, "percentage": 86.15, "elapsed_time": "4:42:01", "remaining_time": "0:45:21"}
+{"current_steps": 1000, "total_steps": 1155, "loss": 0.6566, "learning_rate": 4.453860353048111e-08, "epoch": 2.5923525599481527, "percentage": 86.58, "elapsed_time": "4:43:06", "remaining_time": "0:43:52"}
+{"current_steps": 1000, "total_steps": 1155, "eval_loss": 0.7657259702682495, "epoch": 2.5923525599481527, "percentage": 86.58, "elapsed_time": "4:46:17", "remaining_time": "0:44:22"}
+{"current_steps": 1005, "total_steps": 1155, "loss": 0.6588, "learning_rate": 4.1751533038578866e-08, "epoch": 2.6053143227478937, "percentage": 87.01, "elapsed_time": "4:47:56", "remaining_time": "0:42:58"}
+{"current_steps": 1010, "total_steps": 1155, "loss": 0.6451, "learning_rate": 3.9050705374879086e-08, "epoch": 2.6182760855476346, "percentage": 87.45, "elapsed_time": "4:49:01", "remaining_time": "0:41:29"}
+{"current_steps": 1015, "total_steps": 1155, "loss": 0.6537, "learning_rate": 3.6436628837898773e-08, "epoch": 2.631237848347375, "percentage": 87.88, "elapsed_time": "4:50:07", "remaining_time": "0:40:01"}
+{"current_steps": 1020, "total_steps": 1155, "loss": 0.6646, "learning_rate": 3.390979539950478e-08, "epoch": 2.644199611147116, "percentage": 88.31, "elapsed_time": "4:51:13", "remaining_time": "0:38:32"}
+{"current_steps": 1025, "total_steps": 1155, "loss": 0.6398, "learning_rate": 3.1470680612323494e-08, "epoch": 2.657161373946857, "percentage": 88.74, "elapsed_time": "4:52:18", "remaining_time": "0:37:04"}
+{"current_steps": 1030, "total_steps": 1155, "loss": 0.656, "learning_rate": 2.9119743520242213e-08, "epoch": 2.6701231367465974, "percentage": 89.18, "elapsed_time": "4:53:23", "remaining_time": "0:35:36"}
+{"current_steps": 1035, "total_steps": 1155, "loss": 0.6522, "learning_rate": 2.6857426572016007e-08, "epoch": 2.6830848995463383, "percentage": 89.61, "elapsed_time": "4:54:29", "remaining_time": "0:34:08"}
+{"current_steps": 1040, "total_steps": 1155, "loss": 0.661, "learning_rate": 2.468415553799874e-08, "epoch": 2.6960466623460793, "percentage": 90.04, "elapsed_time": "4:55:34", "remaining_time": "0:32:41"}
+{"current_steps": 1045, "total_steps": 1155, "loss": 0.6543, "learning_rate": 2.2600339430012438e-08, "epoch": 2.7090084251458197, "percentage": 90.48, "elapsed_time": "4:56:40", "remaining_time": "0:31:13"}
+{"current_steps": 1050, "total_steps": 1155, "loss": 0.6654, "learning_rate": 2.0606370424370966e-08, "epoch": 2.7219701879455607, "percentage": 90.91, "elapsed_time": "4:57:45", "remaining_time": "0:29:46"}
+{"current_steps": 1050, "total_steps": 1155, "eval_loss": 0.765480101108551, "epoch": 2.7219701879455607, "percentage": 90.91, "elapsed_time": "5:00:56", "remaining_time": "0:30:05"}
+{"current_steps": 1055, "total_steps": 1155, "loss": 0.6585, "learning_rate": 1.8702623788072024e-08, "epoch": 2.7349319507453016, "percentage": 91.34, "elapsed_time": "5:02:01", "remaining_time": "0:28:37"}
+{"current_steps": 1060, "total_steps": 1155, "loss": 0.6765, "learning_rate": 1.688945780817147e-08, "epoch": 2.747893713545042, "percentage": 91.77, "elapsed_time": "5:03:07", "remaining_time": "0:27:09"}
+{"current_steps": 1065, "total_steps": 1155, "loss": 0.6578, "learning_rate": 1.516721372435342e-08, "epoch": 2.760855476344783, "percentage": 92.21, "elapsed_time": "5:04:12", "remaining_time": "0:25:42"}
+{"current_steps": 1070, "total_steps": 1155, "loss": 0.6681, "learning_rate": 1.3536215664708583e-08, "epoch": 2.7738172391445235, "percentage": 92.64, "elapsed_time": "5:05:18", "remaining_time": "0:24:15"}
+{"current_steps": 1075, "total_steps": 1155, "loss": 0.6412, "learning_rate": 1.1996770584732919e-08, "epoch": 2.7867790019442644, "percentage": 93.07, "elapsed_time": "5:06:23", "remaining_time": "0:22:48"}
+{"current_steps": 1080, "total_steps": 1155, "loss": 0.6748, "learning_rate": 1.0549168209558312e-08, "epoch": 2.7997407647440054, "percentage": 93.51, "elapsed_time": "5:07:29", "remaining_time": "0:21:21"}
+{"current_steps": 1085, "total_steps": 1155, "loss": 0.6433, "learning_rate": 9.193680979426189e-09, "epoch": 2.812702527543746, "percentage": 93.94, "elapsed_time": "5:08:33", "remaining_time": "0:19:54"}
+{"current_steps": 1090, "total_steps": 1155, "loss": 0.6621, "learning_rate": 7.930563998413797e-09, "epoch": 2.8256642903434868, "percentage": 94.37, "elapsed_time": "5:09:39", "remaining_time": "0:18:27"}
+{"current_steps": 1095, "total_steps": 1155, "loss": 0.6623, "learning_rate": 6.760054986423458e-09, "epoch": 2.8386260531432272, "percentage": 94.81, "elapsed_time": "5:10:44", "remaining_time": "0:17:01"}
+{"current_steps": 1100, "total_steps": 1155, "loss": 0.6389, "learning_rate": 5.6823742344433435e-09, "epoch": 2.851587815942968, "percentage": 95.24, "elapsed_time": "5:11:50", "remaining_time": "0:15:35"}
+{"current_steps": 1100, "total_steps": 1155, "eval_loss": 0.7652862668037415, "epoch": 2.851587815942968, "percentage": 95.24, "elapsed_time": "5:15:00", "remaining_time": "0:15:45"}
+{"current_steps": 1105, "total_steps": 1155, "loss": 0.6616, "learning_rate": 4.697724563088645e-09, "epoch": 2.864549578742709, "percentage": 95.67, "elapsed_time": "5:16:43", "remaining_time": "0:14:19"}
+{"current_steps": 1110, "total_steps": 1155, "loss": 0.6678, "learning_rate": 3.806291284430274e-09, "epoch": 2.8775113415424496, "percentage": 96.1, "elapsed_time": "5:17:48", "remaining_time": "0:12:53"}
+{"current_steps": 1115, "total_steps": 1155, "loss": 0.6533, "learning_rate": 3.008242167119257e-09, "epoch": 2.8904731043421905, "percentage": 96.54, "elapsed_time": "5:18:55", "remaining_time": "0:11:26"}
+{"current_steps": 1120, "total_steps": 1155, "loss": 0.6568, "learning_rate": 2.303727404812217e-09, "epoch": 2.9034348671419314, "percentage": 96.97, "elapsed_time": "5:19:59", "remaining_time": "0:09:59"}
+{"current_steps": 1125, "total_steps": 1155, "loss": 0.658, "learning_rate": 1.6928795879049828e-09, "epoch": 2.916396629941672, "percentage": 97.4, "elapsed_time": "5:21:05", "remaining_time": "0:08:33"}
+{"current_steps": 1130, "total_steps": 1155, "loss": 0.6591, "learning_rate": 1.1758136785788853e-09, "epoch": 2.929358392741413, "percentage": 97.84, "elapsed_time": "5:22:10", "remaining_time": "0:07:07"}
+{"current_steps": 1135, "total_steps": 1155, "loss": 0.6448, "learning_rate": 7.526269891646175e-10, "epoch": 2.942320155541154, "percentage": 98.27, "elapsed_time": "5:23:15", "remaining_time": "0:05:41"}
+{"current_steps": 1140, "total_steps": 1155, "loss": 0.6421, "learning_rate": 4.233991638281642e-10, "epoch": 2.9552819183408943, "percentage": 98.7, "elapsed_time": "5:24:20", "remaining_time": "0:04:16"}
+{"current_steps": 1145, "total_steps": 1155, "loss": 0.6606, "learning_rate": 1.8819216358156865e-10, "epoch": 2.968243681140635, "percentage": 99.13, "elapsed_time": "5:25:25", "remaining_time": "0:02:50"}
+{"current_steps": 1150, "total_steps": 1155, "loss": 0.6574, "learning_rate": 4.7050254621872064e-11, "epoch": 2.981205443940376, "percentage": 99.57, "elapsed_time": "5:26:31", "remaining_time": "0:01:25"}
+{"current_steps": 1150, "total_steps": 1155, "eval_loss": 0.7652673125267029, "epoch": 2.981205443940376, "percentage": 99.57, "elapsed_time": "5:29:42", "remaining_time": "0:01:26"}
+{"current_steps": 1155, "total_steps": 1155, "loss": 0.6573, "learning_rate": 0.0, "epoch": 2.9941672067401166, "percentage": 100.0, "elapsed_time": "5:30:47", "remaining_time": "0:00:00"}
+{"current_steps": 1155, "total_steps": 1155, "epoch": 2.9941672067401166, "percentage": 100.0, "elapsed_time": "5:31:23", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1843 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9941672067401166,
+  "eval_steps": 50,
+  "global_step": 1155,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012961762799740765,
+      "grad_norm": 17.21252896134672,
+      "learning_rate": 5e-07,
+      "loss": 1.6823,
+      "step": 5
+    },
+    {
+      "epoch": 0.02592352559948153,
+      "grad_norm": 12.008964700255303,
+      "learning_rate": 1e-06,
+      "loss": 1.566,
+      "step": 10
+    },
+    {
+      "epoch": 0.03888528839922229,
+      "grad_norm": 7.9698215919555055,
+      "learning_rate": 9.99952949745378e-07,
+      "loss": 1.2721,
+      "step": 15
+    },
+    {
+      "epoch": 0.05184705119896306,
+      "grad_norm": 4.447326184155441,
+      "learning_rate": 9.998118078364185e-07,
+      "loss": 1.1461,
+      "step": 20
+    },
+    {
+      "epoch": 0.06480881399870382,
+      "grad_norm": 3.9602084655818675,
+      "learning_rate": 9.995766008361718e-07,
+      "loss": 1.0509,
+      "step": 25
+    },
+    {
+      "epoch": 0.07777057679844458,
+      "grad_norm": 3.524237361034851,
+      "learning_rate": 9.992473730108354e-07,
+      "loss": 0.9982,
+      "step": 30
+    },
+    {
+      "epoch": 0.09073233959818536,
+      "grad_norm": 3.633387524272681,
+      "learning_rate": 9.98824186321421e-07,
+      "loss": 0.9804,
+      "step": 35
+    },
+    {
+      "epoch": 0.10369410239792612,
+      "grad_norm": 3.4822921075242577,
+      "learning_rate": 9.98307120412095e-07,
+      "loss": 0.954,
+      "step": 40
+    },
+    {
+      "epoch": 0.11665586519766688,
+      "grad_norm": 3.519195574393169,
+      "learning_rate": 9.976962725951878e-07,
+      "loss": 0.928,
+      "step": 45
+    },
+    {
+      "epoch": 0.12961762799740764,
+      "grad_norm": 3.3308237206179423,
+      "learning_rate": 9.969917578328807e-07,
+      "loss": 0.9184,
+      "step": 50
+    },
+    {
+      "epoch": 0.12961762799740764,
+      "eval_loss": 0.92087721824646,
+      "eval_runtime": 190.61,
+      "eval_samples_per_second": 57.547,
+      "eval_steps_per_second": 0.902,
+      "step": 50
+    },
+    {
+      "epoch": 0.1425793907971484,
+      "grad_norm": 3.343853179925445,
+      "learning_rate": 9.961937087155695e-07,
+      "loss": 0.9194,
+      "step": 55
+    },
+    {
+      "epoch": 0.15554115359688916,
+      "grad_norm": 3.368850277351612,
+      "learning_rate": 9.953022754369114e-07,
+      "loss": 0.8832,
+      "step": 60
+    },
+    {
+      "epoch": 0.16850291639662995,
+      "grad_norm": 3.3163787130271003,
+      "learning_rate": 9.943176257655565e-07,
+      "loss": 0.8923,
+      "step": 65
+    },
+    {
+      "epoch": 0.18146467919637072,
+      "grad_norm": 3.242609823802845,
+      "learning_rate": 9.932399450135765e-07,
+      "loss": 0.8883,
+      "step": 70
+    },
+    {
+      "epoch": 0.19442644199611148,
+      "grad_norm": 3.402686266652709,
+      "learning_rate": 9.920694360015862e-07,
+      "loss": 0.8639,
+      "step": 75
+    },
+    {
+      "epoch": 0.20738820479585224,
+      "grad_norm": 3.404608035399376,
+      "learning_rate": 9.908063190205739e-07,
+      "loss": 0.8732,
+      "step": 80
+    },
+    {
+      "epoch": 0.220349967595593,
+      "grad_norm": 3.3975642435264732,
+      "learning_rate": 9.894508317904417e-07,
+      "loss": 0.8883,
+      "step": 85
+    },
+    {
+      "epoch": 0.23331173039533376,
+      "grad_norm": 3.558535819762842,
+      "learning_rate": 9.88003229415267e-07,
+      "loss": 0.8671,
+      "step": 90
+    },
+    {
+      "epoch": 0.24627349319507452,
+      "grad_norm": 3.6228022238357815,
+      "learning_rate": 9.864637843352913e-07,
+      "loss": 0.8771,
+      "step": 95
+    },
+    {
+      "epoch": 0.2592352559948153,
+      "grad_norm": 3.6210872209063174,
+      "learning_rate": 9.848327862756466e-07,
+      "loss": 0.8611,
+      "step": 100
+    },
+    {
+      "epoch": 0.2592352559948153,
+      "eval_loss": 0.8652921915054321,
+      "eval_runtime": 190.2747,
+      "eval_samples_per_second": 57.648,
+      "eval_steps_per_second": 0.904,
+      "step": 100
+    },
+    {
+      "epoch": 0.27219701879455604,
+      "grad_norm": 3.312411561694666,
+      "learning_rate": 9.831105421918285e-07,
+      "loss": 0.8547,
+      "step": 105
+    },
+    {
+      "epoch": 0.2851587815942968,
+      "grad_norm": 3.4066727133401598,
+      "learning_rate": 9.81297376211928e-07,
+      "loss": 0.8369,
+      "step": 110
+    },
+    {
+      "epoch": 0.29812054439403757,
+      "grad_norm": 3.2867314575644575,
+      "learning_rate": 9.79393629575629e-07,
+      "loss": 0.8403,
+      "step": 115
+    },
+    {
+      "epoch": 0.31108230719377833,
+      "grad_norm": 3.599628911972995,
+      "learning_rate": 9.773996605699875e-07,
+      "loss": 0.8437,
+      "step": 120
+    },
+    {
+      "epoch": 0.32404406999351915,
+      "grad_norm": 3.3280113051932183,
+      "learning_rate": 9.753158444620013e-07,
+      "loss": 0.8295,
+      "step": 125
+    },
+    {
+      "epoch": 0.3370058327932599,
+      "grad_norm": 3.3041114591018035,
+      "learning_rate": 9.73142573427984e-07,
+      "loss": 0.8416,
+      "step": 130
+    },
+    {
+      "epoch": 0.34996759559300067,
+      "grad_norm": 3.1677202986884647,
+      "learning_rate": 9.708802564797578e-07,
+      "loss": 0.8372,
+      "step": 135
+    },
+    {
+      "epoch": 0.36292935839274143,
+      "grad_norm": 3.4261833858436126,
+      "learning_rate": 9.685293193876765e-07,
+      "loss": 0.8407,
+      "step": 140
+    },
+    {
+      "epoch": 0.3758911211924822,
+      "grad_norm": 3.2025888685071995,
+      "learning_rate": 9.660902046004953e-07,
+      "loss": 0.8218,
+      "step": 145
+    },
+    {
+      "epoch": 0.38885288399222295,
+      "grad_norm": 3.3672158659218945,
+      "learning_rate": 9.635633711621011e-07,
+      "loss": 0.8257,
+      "step": 150
+    },
+    {
+      "epoch": 0.38885288399222295,
+      "eval_loss": 0.8396357893943787,
+      "eval_runtime": 190.236,
+      "eval_samples_per_second": 57.66,
+      "eval_steps_per_second": 0.904,
+      "step": 150
+    },
+    {
+      "epoch": 0.4018146467919637,
+      "grad_norm": 3.5382812532295653,
+      "learning_rate": 9.609492946251208e-07,
+      "loss": 0.8335,
+      "step": 155
+    },
+    {
+      "epoch": 0.4147764095917045,
+      "grad_norm": 3.2987076575989396,
+      "learning_rate": 9.58248466961421e-07,
+      "loss": 0.8274,
+      "step": 160
+    },
+    {
+      "epoch": 0.42773817239144524,
+      "grad_norm": 3.209384087480358,
+      "learning_rate": 9.554613964695188e-07,
+      "loss": 0.8419,
+      "step": 165
+    },
+    {
+      "epoch": 0.440699935191186,
+      "grad_norm": 3.2525057388499867,
+      "learning_rate": 9.525886076789193e-07,
+      "loss": 0.8264,
+      "step": 170
+    },
+    {
+      "epoch": 0.45366169799092676,
+      "grad_norm": 3.2659862173369225,
+      "learning_rate": 9.496306412513988e-07,
+      "loss": 0.813,
+      "step": 175
+    },
+    {
+      "epoch": 0.4666234607906675,
+      "grad_norm": 3.617112426560761,
+      "learning_rate": 9.465880538792517e-07,
+      "loss": 0.8209,
+      "step": 180
+    },
+    {
+      "epoch": 0.4795852235904083,
+      "grad_norm": 3.8241965496757055,
+      "learning_rate": 9.434614181805202e-07,
+      "loss": 0.8246,
+      "step": 185
+    },
+    {
+      "epoch": 0.49254698639014904,
+      "grad_norm": 3.389966079797953,
+      "learning_rate": 9.402513225912271e-07,
+      "loss": 0.8236,
+      "step": 190
+    },
+    {
+      "epoch": 0.5055087491898899,
+      "grad_norm": 3.31422039420999,
+      "learning_rate": 9.36958371254632e-07,
+      "loss": 0.8158,
+      "step": 195
+    },
+    {
+      "epoch": 0.5184705119896306,
+      "grad_norm": 3.365373850064581,
+      "learning_rate": 9.335831839075302e-07,
+      "loss": 0.8308,
+      "step": 200
+    },
+    {
+      "epoch": 0.5184705119896306,
+      "eval_loss": 0.8231202960014343,
+      "eval_runtime": 190.2867,
+      "eval_samples_per_second": 57.645,
+      "eval_steps_per_second": 0.904,
+      "step": 200
+    },
+    {
+      "epoch": 0.5314322747893714,
+      "grad_norm": 3.441006121650103,
+      "learning_rate": 9.301263957636179e-07,
+      "loss": 0.8191,
+      "step": 205
+    },
+    {
+      "epoch": 0.5443940375891121,
+      "grad_norm": 3.428707563220311,
+      "learning_rate": 9.265886573939446e-07,
+      "loss": 0.8191,
+      "step": 210
+    },
+    {
+      "epoch": 0.5573558003888529,
+      "grad_norm": 3.5640266455568166,
+      "learning_rate": 9.229706346044747e-07,
+      "loss": 0.8255,
+      "step": 215
+    },
+    {
+      "epoch": 0.5703175631885936,
+      "grad_norm": 3.551803069534866,
+      "learning_rate": 9.192730083107818e-07,
+      "loss": 0.8164,
+      "step": 220
+    },
+    {
+      "epoch": 0.5832793259883344,
+      "grad_norm": 3.414031666969802,
+      "learning_rate": 9.154964744099005e-07,
+      "loss": 0.7939,
+      "step": 225
+    },
+    {
+      "epoch": 0.5962410887880751,
+      "grad_norm": 3.442613850161029,
+      "learning_rate": 9.116417436493573e-07,
+      "loss": 0.8034,
+      "step": 230
+    },
+    {
+      "epoch": 0.609202851587816,
+      "grad_norm": 3.462275139287757,
+      "learning_rate": 9.077095414934075e-07,
+      "loss": 0.8063,
+      "step": 235
+    },
+    {
+      "epoch": 0.6221646143875567,
+      "grad_norm": 3.447345184549608,
+      "learning_rate": 9.037006079865015e-07,
+      "loss": 0.8233,
+      "step": 240
+    },
+    {
+      "epoch": 0.6351263771872975,
+      "grad_norm": 3.5938927981457933,
+      "learning_rate": 8.996156976140086e-07,
+      "loss": 0.8283,
+      "step": 245
+    },
+    {
+      "epoch": 0.6480881399870383,
+      "grad_norm": 3.5811512536833523,
+      "learning_rate": 8.95455579160221e-07,
+      "loss": 0.8168,
+      "step": 250
+    },
+    {
+      "epoch": 0.6480881399870383,
+      "eval_loss": 0.810850977897644,
+      "eval_runtime": 190.2136,
+      "eval_samples_per_second": 57.667,
+      "eval_steps_per_second": 0.904,
+      "step": 250
+    },
+    {
+      "epoch": 0.661049902786779,
+      "grad_norm": 3.3124363238635715,
+      "learning_rate": 8.912210355636689e-07,
+      "loss": 0.7922,
+      "step": 255
+    },
+    {
+      "epoch": 0.6740116655865198,
+      "grad_norm": 3.3955357238579693,
+      "learning_rate": 8.8691286376977e-07,
+      "loss": 0.8044,
+      "step": 260
+    },
+    {
+      "epoch": 0.6869734283862605,
+      "grad_norm": 3.1989325895717053,
+      "learning_rate": 8.825318745808439e-07,
+      "loss": 0.7933,
+      "step": 265
+    },
+    {
+      "epoch": 0.6999351911860013,
+      "grad_norm": 3.393447117563635,
+      "learning_rate": 8.780788925035177e-07,
+      "loss": 0.8018,
+      "step": 270
+    },
+    {
+      "epoch": 0.712896953985742,
+      "grad_norm": 3.2831528447418132,
+      "learning_rate": 8.735547555935537e-07,
+      "loss": 0.7961,
+      "step": 275
+    },
+    {
+      "epoch": 0.7258587167854829,
+      "grad_norm": 3.4250845276838486,
+      "learning_rate": 8.689603152981262e-07,
+      "loss": 0.812,
+      "step": 280
+    },
+    {
+      "epoch": 0.7388204795852236,
+      "grad_norm": 3.2575625313957035,
+      "learning_rate": 8.64296436295578e-07,
+      "loss": 0.7971,
+      "step": 285
+    },
+    {
+      "epoch": 0.7517822423849644,
+      "grad_norm": 3.5149123785883014,
+      "learning_rate": 8.595639963326879e-07,
+      "loss": 0.8067,
+      "step": 290
+    },
+    {
+      "epoch": 0.7647440051847051,
+      "grad_norm": 3.5091201056207533,
+      "learning_rate": 8.547638860594764e-07,
+      "loss": 0.8155,
+      "step": 295
+    },
+    {
+      "epoch": 0.7777057679844459,
+      "grad_norm": 3.5343144588793036,
+      "learning_rate": 8.49897008861586e-07,
+      "loss": 0.8021,
+      "step": 300
+    },
+    {
+      "epoch": 0.7777057679844459,
+      "eval_loss": 0.800530195236206,
+      "eval_runtime": 190.6317,
+      "eval_samples_per_second": 57.54,
+      "eval_steps_per_second": 0.902,
+      "step": 300
+    },
+    {
+      "epoch": 0.7906675307841866,
+      "grad_norm": 3.3863012076670542,
+      "learning_rate": 8.449642806902622e-07,
+      "loss": 0.7993,
+      "step": 305
+    },
+    {
+      "epoch": 0.8036292935839274,
+      "grad_norm": 3.5586423328389585,
+      "learning_rate": 8.399666298899706e-07,
+      "loss": 0.7918,
+      "step": 310
+    },
+    {
+      "epoch": 0.8165910563836681,
+      "grad_norm": 3.12605831331216,
+      "learning_rate": 8.34904997023682e-07,
+      "loss": 0.7943,
+      "step": 315
+    },
+    {
+      "epoch": 0.829552819183409,
+      "grad_norm": 3.365606947704741,
+      "learning_rate": 8.297803346958569e-07,
+      "loss": 0.783,
+      "step": 320
+    },
+    {
+      "epoch": 0.8425145819831497,
+      "grad_norm": 3.525340806653281,
+      "learning_rate": 8.245936073731651e-07,
+      "loss": 0.7976,
+      "step": 325
+    },
+    {
+      "epoch": 0.8554763447828905,
+      "grad_norm": 3.244247748765073,
+      "learning_rate": 8.193457912029712e-07,
+      "loss": 0.7807,
+      "step": 330
+    },
+    {
+      "epoch": 0.8684381075826313,
+      "grad_norm": 3.299152179523224,
+      "learning_rate": 8.140378738296232e-07,
+      "loss": 0.7836,
+      "step": 335
+    },
+    {
+      "epoch": 0.881399870382372,
+      "grad_norm": 3.6966297262494683,
+      "learning_rate": 8.086708542085767e-07,
+      "loss": 0.8063,
+      "step": 340
+    },
+    {
+      "epoch": 0.8943616331821128,
+      "grad_norm": 3.459714731085819,
+      "learning_rate": 8.032457424183909e-07,
+      "loss": 0.7911,
+      "step": 345
+    },
+    {
+      "epoch": 0.9073233959818535,
+      "grad_norm": 3.0350617290741373,
+      "learning_rate": 7.977635594706298e-07,
+      "loss": 0.7741,
+      "step": 350
+    },
+    {
+      "epoch": 0.9073233959818535,
+      "eval_loss": 0.7928882837295532,
+      "eval_runtime": 190.396,
+      "eval_samples_per_second": 57.612,
+      "eval_steps_per_second": 0.903,
+      "step": 350
+    },
+    {
+      "epoch": 0.9202851587815943,
+      "grad_norm": 3.3620653686755686,
+      "learning_rate": 7.922253371177082e-07,
+      "loss": 0.7932,
+      "step": 355
+    },
+    {
+      "epoch": 0.933246921581335,
+      "grad_norm": 3.278928351388705,
+      "learning_rate": 7.866321176587128e-07,
+      "loss": 0.7871,
+      "step": 360
+    },
+    {
+      "epoch": 0.9462086843810759,
+      "grad_norm": 3.296771284934289,
+      "learning_rate": 7.809849537432431e-07,
+      "loss": 0.7792,
+      "step": 365
+    },
+    {
+      "epoch": 0.9591704471808166,
+      "grad_norm": 4.571766433220969,
+      "learning_rate": 7.752849081732991e-07,
+      "loss": 0.788,
+      "step": 370
+    },
+    {
+      "epoch": 0.9721322099805574,
+      "grad_norm": 3.4508851083525007,
+      "learning_rate": 7.695330537032627e-07,
+      "loss": 0.7614,
+      "step": 375
+    },
+    {
+      "epoch": 0.9850939727802981,
+      "grad_norm": 3.4026555887076433,
+      "learning_rate": 7.637304728380037e-07,
+      "loss": 0.7964,
+      "step": 380
+    },
+    {
+      "epoch": 0.9980557355800389,
+      "grad_norm": 3.4049969426822644,
+      "learning_rate": 7.5787825762915e-07,
+      "loss": 0.7659,
+      "step": 385
+    },
+    {
+      "epoch": 1.0110174983797797,
+      "grad_norm": 3.7467236394334593,
+      "learning_rate": 7.519775094695648e-07,
+      "loss": 0.729,
+      "step": 390
+    },
+    {
+      "epoch": 1.0239792611795204,
+      "grad_norm": 3.3057229188741797,
+      "learning_rate": 7.460293388860614e-07,
+      "loss": 0.7421,
+      "step": 395
+    },
+    {
+      "epoch": 1.0369410239792611,
+      "grad_norm": 3.1846298307152545,
+      "learning_rate": 7.400348653304021e-07,
+      "loss": 0.7155,
+      "step": 400
+    },
+    {
+      "epoch": 1.0369410239792611,
+      "eval_loss": 0.7879951596260071,
+      "eval_runtime": 190.5219,
+      "eval_samples_per_second": 57.573,
+      "eval_steps_per_second": 0.903,
+      "step": 400
+    },
+    {
+      "epoch": 1.0499027867790018,
+      "grad_norm": 3.555528496823252,
+      "learning_rate": 7.33995216968615e-07,
+      "loss": 0.721,
+      "step": 405
+    },
+    {
+      "epoch": 1.0628645495787428,
+      "grad_norm": 3.17101772663646,
+      "learning_rate": 7.279115304686733e-07,
+      "loss": 0.7251,
+      "step": 410
+    },
+    {
+      "epoch": 1.0758263123784835,
+      "grad_norm": 3.4524740982989575,
+      "learning_rate": 7.217849507865723e-07,
+      "loss": 0.7079,
+      "step": 415
+    },
+    {
+      "epoch": 1.0887880751782242,
+      "grad_norm": 3.5488503758648604,
+      "learning_rate": 7.156166309508481e-07,
+      "loss": 0.716,
+      "step": 420
+    },
+    {
+      "epoch": 1.101749837977965,
+      "grad_norm": 3.2843814722509754,
+      "learning_rate": 7.094077318455761e-07,
+      "loss": 0.7248,
+      "step": 425
+    },
+    {
+      "epoch": 1.1147116007777058,
+      "grad_norm": 3.5818373829792436,
+      "learning_rate": 7.031594219918915e-07,
+      "loss": 0.7282,
+      "step": 430
+    },
+    {
+      "epoch": 1.1276733635774465,
+      "grad_norm": 3.545436547315646,
+      "learning_rate": 6.968728773280729e-07,
+      "loss": 0.7214,
+      "step": 435
+    },
+    {
+      "epoch": 1.1406351263771872,
+      "grad_norm": 3.7309987258945956,
+      "learning_rate": 6.905492809882285e-07,
+      "loss": 0.7149,
+      "step": 440
+    },
+    {
+      "epoch": 1.1535968891769282,
+      "grad_norm": 3.342264257213339,
+      "learning_rate": 6.841898230796302e-07,
+      "loss": 0.7118,
+      "step": 445
+    },
+    {
+      "epoch": 1.1665586519766689,
+      "grad_norm": 3.5498283019941668,
+      "learning_rate": 6.777957004587331e-07,
+      "loss": 0.7322,
+      "step": 450
+    },
+    {
+      "epoch": 1.1665586519766689,
+      "eval_loss": 0.7836564779281616,
+      "eval_runtime": 190.524,
+      "eval_samples_per_second": 57.573,
+      "eval_steps_per_second": 0.903,
+      "step": 450
+    },
+    {
+      "epoch": 1.1795204147764096,
+      "grad_norm": 3.4407614110968274,
+      "learning_rate": 6.713681165059271e-07,
+      "loss": 0.731,
+      "step": 455
+    },
+    {
+      "epoch": 1.1924821775761503,
+      "grad_norm": 3.606482531048048,
+      "learning_rate": 6.649082808990585e-07,
+      "loss": 0.7263,
+      "step": 460
+    },
+    {
+      "epoch": 1.2054439403758912,
+      "grad_norm": 3.4160389968965834,
+      "learning_rate": 6.584174093857675e-07,
+      "loss": 0.7138,
+      "step": 465
+    },
+    {
+      "epoch": 1.218405703175632,
+      "grad_norm": 3.6414465107657885,
+      "learning_rate": 6.518967235546841e-07,
+      "loss": 0.7131,
+      "step": 470
+    },
+    {
+      "epoch": 1.2313674659753726,
+      "grad_norm": 3.5928947738604835,
+      "learning_rate": 6.453474506055227e-07,
+      "loss": 0.7056,
+      "step": 475
+    },
+    {
+      "epoch": 1.2443292287751135,
+      "grad_norm": 3.3876054178886337,
+      "learning_rate": 6.387708231181228e-07,
+      "loss": 0.7142,
+      "step": 480
+    },
+    {
+      "epoch": 1.2572909915748542,
+      "grad_norm": 3.9025269357210606,
+      "learning_rate": 6.321680788204757e-07,
+      "loss": 0.7295,
+      "step": 485
+    },
+    {
+      "epoch": 1.270252754374595,
+      "grad_norm": 3.6340219528437747,
+      "learning_rate": 6.255404603557833e-07,
+      "loss": 0.6984,
+      "step": 490
+    },
+    {
+      "epoch": 1.2832145171743357,
+      "grad_norm": 3.441153025186208,
+      "learning_rate": 6.188892150485902e-07,
+      "loss": 0.7286,
+      "step": 495
+    },
+    {
+      "epoch": 1.2961762799740764,
+      "grad_norm": 3.509621524777449,
+      "learning_rate": 6.122155946700381e-07,
+      "loss": 0.7214,
+      "step": 500
+    },
+    {
+      "epoch": 1.2961762799740764,
+      "eval_loss": 0.7790202498435974,
+      "eval_runtime": 190.1439,
+      "eval_samples_per_second": 57.688,
+      "eval_steps_per_second": 0.905,
+      "step": 500
+    },
+    {
+      "epoch": 1.3091380427738173,
+      "grad_norm": 3.9718306817617957,
+      "learning_rate": 6.055208552022787e-07,
+      "loss": 0.7183,
+      "step": 505
+    },
+    {
+      "epoch": 1.322099805573558,
+      "grad_norm": 3.6250018779596203,
+      "learning_rate": 5.988062566020986e-07,
+      "loss": 0.7188,
+      "step": 510
+    },
+    {
+      "epoch": 1.3350615683732987,
+      "grad_norm": 3.58876192132372,
+      "learning_rate": 5.920730625637933e-07,
+      "loss": 0.6976,
+      "step": 515
+    },
+    {
+      "epoch": 1.3480233311730396,
+      "grad_norm": 3.463594237695507,
+      "learning_rate": 5.85322540281338e-07,
+      "loss": 0.7274,
+      "step": 520
+    },
+    {
+      "epoch": 1.3609850939727803,
+      "grad_norm": 3.755952042482129,
+      "learning_rate": 5.785559602099018e-07,
+      "loss": 0.7084,
+      "step": 525
+    },
+    {
+      "epoch": 1.373946856772521,
+      "grad_norm": 3.306784860944235,
+      "learning_rate": 5.717745958267459e-07,
+      "loss": 0.7119,
+      "step": 530
+    },
+    {
+      "epoch": 1.3869086195722617,
+      "grad_norm": 3.534119314182442,
+      "learning_rate": 5.649797233915538e-07,
+      "loss": 0.7086,
+      "step": 535
+    },
+    {
+      "epoch": 1.3998703823720027,
+      "grad_norm": 3.236567266341926,
+      "learning_rate": 5.581726217062386e-07,
+      "loss": 0.716,
+      "step": 540
+    },
+    {
+      "epoch": 1.4128321451717434,
+      "grad_norm": 3.4785698979562456,
+      "learning_rate": 5.513545718742701e-07,
+      "loss": 0.7071,
+      "step": 545
+    },
+    {
+      "epoch": 1.425793907971484,
+      "grad_norm": 3.675603397627949,
+      "learning_rate": 5.445268570595708e-07,
+      "loss": 0.6936,
+      "step": 550
+    },
+    {
+      "epoch": 1.425793907971484,
+      "eval_loss": 0.7752651572227478,
+      "eval_runtime": 190.3759,
+      "eval_samples_per_second": 57.618,
+      "eval_steps_per_second": 0.903,
+      "step": 550
+    },
+    {
+      "epoch": 1.4387556707712248,
+      "grad_norm": 3.399382435225056,
+      "learning_rate": 5.376907622450228e-07,
+      "loss": 0.7155,
+      "step": 555
+    },
+    {
+      "epoch": 1.4517174335709657,
+      "grad_norm": 3.564747777066771,
+      "learning_rate": 5.308475739906328e-07,
+      "loss": 0.7086,
+      "step": 560
+    },
+    {
+      "epoch": 1.4646791963707064,
+      "grad_norm": 3.346047715273763,
+      "learning_rate": 5.239985801913999e-07,
+      "loss": 0.7136,
+      "step": 565
+    },
+    {
+      "epoch": 1.4776409591704471,
+      "grad_norm": 3.716468641603961,
+      "learning_rate": 5.171450698349329e-07,
+      "loss": 0.7208,
+      "step": 570
+    },
+    {
+      "epoch": 1.490602721970188,
+      "grad_norm": 3.8457195513896703,
+      "learning_rate": 5.102883327588608e-07,
+      "loss": 0.7055,
+      "step": 575
+    },
+    {
+      "epoch": 1.5035644847699285,
+      "grad_norm": 3.6398948460452325,
+      "learning_rate": 5.034296594080848e-07,
+      "loss": 0.6824,
+      "step": 580
+    },
+    {
+      "epoch": 1.5165262475696695,
+      "grad_norm": 3.3427427312285425,
+      "learning_rate": 4.965703405919153e-07,
+      "loss": 0.733,
+      "step": 585
+    },
+    {
+      "epoch": 1.5294880103694104,
+      "grad_norm": 3.7140860027489504,
+      "learning_rate": 4.897116672411394e-07,
+      "loss": 0.7011,
+      "step": 590
+    },
+    {
+      "epoch": 1.5424497731691509,
+      "grad_norm": 3.810495577054968,
+      "learning_rate": 4.828549301650673e-07,
+      "loss": 0.7216,
+      "step": 595
+    },
+    {
+      "epoch": 1.5554115359688918,
+      "grad_norm": 3.4920510717873925,
+      "learning_rate": 4.760014198086001e-07,
+      "loss": 0.7046,
+      "step": 600
+    },
+    {
+      "epoch": 1.5554115359688918,
+      "eval_loss": 0.7716971039772034,
+      "eval_runtime": 190.4272,
+      "eval_samples_per_second": 57.602,
+      "eval_steps_per_second": 0.903,
+      "step": 600
+    },
+    {
+      "epoch": 1.5683732987686325,
+      "grad_norm": 3.7379962063873244,
+      "learning_rate": 4.691524260093672e-07,
+      "loss": 0.7177,
+      "step": 605
+    },
+    {
+      "epoch": 1.5813350615683732,
+      "grad_norm": 3.5163342715426493,
+      "learning_rate": 4.6230923775497714e-07,
+      "loss": 0.698,
+      "step": 610
+    },
+    {
+      "epoch": 1.5942968243681142,
+      "grad_norm": 3.7752520950220316,
+      "learning_rate": 4.554731429404293e-07,
+      "loss": 0.7068,
+      "step": 615
+    },
+    {
+      "epoch": 1.6072585871678549,
+      "grad_norm": 3.6497035959305637,
+      "learning_rate": 4.486454281257299e-07,
+      "loss": 0.7105,
+      "step": 620
+    },
+    {
+      "epoch": 1.6202203499675956,
+      "grad_norm": 3.3786220834131817,
+      "learning_rate": 4.4182737829376135e-07,
+      "loss": 0.7002,
+      "step": 625
+    },
+    {
+      "epoch": 1.6331821127673365,
+      "grad_norm": 3.745654045093921,
+      "learning_rate": 4.35020276608446e-07,
+      "loss": 0.7132,
+      "step": 630
+    },
+    {
+      "epoch": 1.646143875567077,
+      "grad_norm": 3.7550095562633294,
+      "learning_rate": 4.2822540417325394e-07,
+      "loss": 0.7239,
+      "step": 635
+    },
+    {
+      "epoch": 1.659105638366818,
+      "grad_norm": 3.6978911774202743,
+      "learning_rate": 4.2144403979009823e-07,
+      "loss": 0.708,
+      "step": 640
+    },
+    {
+      "epoch": 1.6720674011665586,
+      "grad_norm": 3.380536692165867,
+      "learning_rate": 4.1467745971866214e-07,
+      "loss": 0.7152,
+      "step": 645
+    },
+    {
+      "epoch": 1.6850291639662993,
+      "grad_norm": 3.7325575613565922,
+      "learning_rate": 4.0792693743620686e-07,
+      "loss": 0.6967,
+      "step": 650
+    },
+    {
+      "epoch": 1.6850291639662993,
+      "eval_loss": 0.7689746618270874,
+      "eval_runtime": 191.11,
+      "eval_samples_per_second": 57.396,
+      "eval_steps_per_second": 0.9,
+      "step": 650
+    },
+    {
+      "epoch": 1.6979909267660402,
+      "grad_norm": 3.51032707119909,
+      "learning_rate": 4.0119374339790133e-07,
+      "loss": 0.7024,
+      "step": 655
+    },
+    {
+      "epoch": 1.710952689565781,
+      "grad_norm": 3.6309443687197933,
+      "learning_rate": 3.944791447977213e-07,
+      "loss": 0.7242,
+      "step": 660
+    },
+    {
+      "epoch": 1.7239144523655217,
+      "grad_norm": 3.4720213982057175,
+      "learning_rate": 3.87784405329962e-07,
+      "loss": 0.7089,
+      "step": 665
+    },
+    {
+      "epoch": 1.7368762151652626,
+      "grad_norm": 3.503078080597499,
+      "learning_rate": 3.8111078495140973e-07,
+      "loss": 0.7219,
+      "step": 670
+    },
+    {
+      "epoch": 1.7498379779650033,
+      "grad_norm": 3.801326705711802,
+      "learning_rate": 3.7445953964421684e-07,
+      "loss": 0.7078,
+      "step": 675
+    },
+    {
+      "epoch": 1.762799740764744,
+      "grad_norm": 3.673701397433746,
+      "learning_rate": 3.678319211795242e-07,
+      "loss": 0.7263,
+      "step": 680
+    },
+    {
+      "epoch": 1.775761503564485,
+      "grad_norm": 3.4237663715763023,
+      "learning_rate": 3.6122917688187717e-07,
+      "loss": 0.6994,
+      "step": 685
+    },
+    {
+      "epoch": 1.7887232663642254,
+      "grad_norm": 3.705157971233802,
+      "learning_rate": 3.546525493944773e-07,
+      "loss": 0.7112,
+      "step": 690
+    },
+    {
+      "epoch": 1.8016850291639663,
+      "grad_norm": 3.785127652648907,
+      "learning_rate": 3.48103276445316e-07,
+      "loss": 0.7145,
+      "step": 695
+    },
+    {
+      "epoch": 1.814646791963707,
+      "grad_norm": 3.3911683616136177,
+      "learning_rate": 3.4158259061423255e-07,
+      "loss": 0.7197,
+      "step": 700
+    },
+    {
+      "epoch": 1.814646791963707,
+      "eval_loss": 0.765801727771759,
+      "eval_runtime": 190.378,
+      "eval_samples_per_second": 57.617,
+      "eval_steps_per_second": 0.903,
+      "step": 700
+    },
+    {
+      "epoch": 1.8276085547634477,
+      "grad_norm": 3.3840783324475994,
+      "learning_rate": 3.3509171910094156e-07,
+      "loss": 0.7008,
+      "step": 705
+    },
+    {
+      "epoch": 1.8405703175631887,
+      "grad_norm": 3.612580310866905,
+      "learning_rate": 3.286318834940729e-07,
+      "loss": 0.7101,
+      "step": 710
+    },
+    {
+      "epoch": 1.8535320803629294,
+      "grad_norm": 3.7400467933207557,
+      "learning_rate": 3.2220429954126686e-07,
+      "loss": 0.6797,
+      "step": 715
+    },
+    {
+      "epoch": 1.86649384316267,
+      "grad_norm": 3.6560156110852464,
+      "learning_rate": 3.158101769203698e-07,
+      "loss": 0.7056,
+      "step": 720
+    },
+    {
+      "epoch": 1.879455605962411,
+      "grad_norm": 3.707238700659647,
+      "learning_rate": 3.0945071901177145e-07,
+      "loss": 0.7093,
+      "step": 725
+    },
+    {
+      "epoch": 1.8924173687621515,
+      "grad_norm": 3.606777649061402,
+      "learning_rate": 3.031271226719271e-07,
+      "loss": 0.7084,
+      "step": 730
+    },
+    {
+      "epoch": 1.9053791315618924,
+      "grad_norm": 3.582291971931833,
+      "learning_rate": 2.968405780081084e-07,
+      "loss": 0.7072,
+      "step": 735
+    },
+    {
+      "epoch": 1.9183408943616331,
+      "grad_norm": 3.6451496181338103,
+      "learning_rate": 2.905922681544238e-07,
+      "loss": 0.6969,
+      "step": 740
+    },
+    {
+      "epoch": 1.9313026571613738,
+      "grad_norm": 3.4586471118745656,
+      "learning_rate": 2.8438336904915184e-07,
+      "loss": 0.6882,
+      "step": 745
+    },
+    {
+      "epoch": 1.9442644199611148,
+      "grad_norm": 3.7194825643308853,
+      "learning_rate": 2.7821504921342774e-07,
+      "loss": 0.704,
+      "step": 750
+    },
+    {
+      "epoch": 1.9442644199611148,
+      "eval_loss": 0.7632837295532227,
+      "eval_runtime": 190.2948,
+      "eval_samples_per_second": 57.642,
+      "eval_steps_per_second": 0.904,
+      "step": 750
+    },
+    {
+      "epoch": 1.9572261827608555,
+      "grad_norm": 3.5452530896647696,
+      "learning_rate": 2.7208846953132683e-07,
+      "loss": 0.6927,
+      "step": 755
+    },
+    {
+      "epoch": 1.9701879455605962,
+      "grad_norm": 3.5705371811039504,
+      "learning_rate": 2.66004783031385e-07,
+      "loss": 0.7037,
+      "step": 760
+    },
+    {
+      "epoch": 1.983149708360337,
+      "grad_norm": 3.4298716866923624,
+      "learning_rate": 2.599651346695979e-07,
+      "loss": 0.6926,
+      "step": 765
+    },
+    {
+      "epoch": 1.9961114711600778,
+      "grad_norm": 3.7912871601195284,
+      "learning_rate": 2.539706611139385e-07,
+      "loss": 0.7111,
+      "step": 770
+    },
+    {
+      "epoch": 2.0090732339598185,
+      "grad_norm": 3.769564370048527,
+      "learning_rate": 2.480224905304352e-07,
+      "loss": 0.6801,
+      "step": 775
+    },
+    {
+      "epoch": 2.0220349967595594,
+      "grad_norm": 3.418564384607543,
+      "learning_rate": 2.4212174237085005e-07,
+      "loss": 0.663,
+      "step": 780
+    },
+    {
+      "epoch": 2.0349967595593,
+      "grad_norm": 3.730605140988728,
+      "learning_rate": 2.3626952716199644e-07,
+      "loss": 0.6784,
+      "step": 785
+    },
+    {
+      "epoch": 2.047958522359041,
+      "grad_norm": 3.7129740066342882,
+      "learning_rate": 2.3046694629673712e-07,
+      "loss": 0.6293,
+      "step": 790
+    },
+    {
+      "epoch": 2.060920285158782,
+      "grad_norm": 3.6275068157375108,
+      "learning_rate": 2.247150918267008e-07,
+      "loss": 0.6489,
+      "step": 795
+    },
+    {
+      "epoch": 2.0738820479585223,
+      "grad_norm": 3.625813889475341,
+      "learning_rate": 2.1901504625675688e-07,
+      "loss": 0.6546,
+      "step": 800
+    },
+    {
+      "epoch": 2.0738820479585223,
+      "eval_loss": 0.7677435874938965,
+      "eval_runtime": 190.4024,
+      "eval_samples_per_second": 57.61,
+      "eval_steps_per_second": 0.903,
+      "step": 800
+    },
+    {
+      "epoch": 2.086843810758263,
+      "grad_norm": 3.4182137647327764,
+      "learning_rate": 2.1336788234128729e-07,
+      "loss": 0.6676,
+      "step": 805
+    },
+    {
+      "epoch": 2.0998055735580037,
+      "grad_norm": 3.6556183671319293,
+      "learning_rate": 2.0777466288229205e-07,
+      "loss": 0.6629,
+      "step": 810
+    },
+    {
+      "epoch": 2.1127673363577446,
+      "grad_norm": 3.744401914160934,
+      "learning_rate": 2.0223644052937028e-07,
+      "loss": 0.6418,
+      "step": 815
+    },
+    {
+      "epoch": 2.1257290991574855,
+      "grad_norm": 3.865359361945009,
+      "learning_rate": 1.9675425758160924e-07,
+      "loss": 0.6531,
+      "step": 820
+    },
+    {
+      "epoch": 2.138690861957226,
+      "grad_norm": 3.69643616461443,
+      "learning_rate": 1.9132914579142338e-07,
+      "loss": 0.6346,
+      "step": 825
+    },
+    {
+      "epoch": 2.151652624756967,
+      "grad_norm": 3.7535585023145797,
+      "learning_rate": 1.8596212617037693e-07,
+      "loss": 0.6654,
+      "step": 830
+    },
+    {
+      "epoch": 2.164614387556708,
+      "grad_norm": 4.0159793685962475,
+      "learning_rate": 1.8065420879702887e-07,
+      "loss": 0.6649,
+      "step": 835
+    },
+    {
+      "epoch": 2.1775761503564484,
+      "grad_norm": 3.644285842038128,
+      "learning_rate": 1.7540639262683487e-07,
+      "loss": 0.6433,
+      "step": 840
+    },
+    {
+      "epoch": 2.1905379131561893,
+      "grad_norm": 3.9056650075753665,
+      "learning_rate": 1.70219665304143e-07,
+      "loss": 0.6769,
+      "step": 845
+    },
+    {
+      "epoch": 2.20349967595593,
+      "grad_norm": 3.7184862818541933,
+      "learning_rate": 1.6509500297631785e-07,
+      "loss": 0.651,
+      "step": 850
+    },
+    {
+      "epoch": 2.20349967595593,
+      "eval_loss": 0.7672791481018066,
+      "eval_runtime": 190.5782,
+      "eval_samples_per_second": 57.556,
+      "eval_steps_per_second": 0.903,
+      "step": 850
+    },
+    {
+      "epoch": 2.2164614387556707,
+      "grad_norm": 3.8299853960357906,
+      "learning_rate": 1.6003337011002927e-07,
+      "loss": 0.6564,
+      "step": 855
+    },
+    {
+      "epoch": 2.2294232015554116,
+      "grad_norm": 3.8417509954938085,
+      "learning_rate": 1.5503571930973785e-07,
+      "loss": 0.6426,
+      "step": 860
+    },
+    {
+      "epoch": 2.242384964355152,
+      "grad_norm": 3.647265480928013,
+      "learning_rate": 1.5010299113841397e-07,
+      "loss": 0.6518,
+      "step": 865
+    },
+    {
+      "epoch": 2.255346727154893,
+      "grad_norm": 3.5486365560504827,
+      "learning_rate": 1.4523611394052355e-07,
+      "loss": 0.6475,
+      "step": 870
+    },
+    {
+      "epoch": 2.268308489954634,
+      "grad_norm": 3.4682735371792526,
+      "learning_rate": 1.4043600366731213e-07,
+      "loss": 0.662,
+      "step": 875
+    },
+    {
+      "epoch": 2.2812702527543745,
+      "grad_norm": 3.824875125016563,
+      "learning_rate": 1.3570356370442189e-07,
+      "loss": 0.6552,
+      "step": 880
+    },
+    {
+      "epoch": 2.2942320155541154,
+      "grad_norm": 3.828027807398829,
+      "learning_rate": 1.3103968470187382e-07,
+      "loss": 0.6476,
+      "step": 885
+    },
+    {
+      "epoch": 2.3071937783538563,
+      "grad_norm": 3.842354090272816,
+      "learning_rate": 1.2644524440644627e-07,
+      "loss": 0.6685,
+      "step": 890
+    },
+    {
+      "epoch": 2.320155541153597,
+      "grad_norm": 3.6920011302134044,
+      "learning_rate": 1.2192110749648232e-07,
+      "loss": 0.6655,
+      "step": 895
+    },
+    {
+      "epoch": 2.3331173039533377,
+      "grad_norm": 3.7425896847607256,
+      "learning_rate": 1.1746812541915607e-07,
+      "loss": 0.6601,
+      "step": 900
+    },
+    {
+      "epoch": 2.3331173039533377,
+      "eval_loss": 0.7666835188865662,
+      "eval_runtime": 190.628,
+      "eval_samples_per_second": 57.541,
+      "eval_steps_per_second": 0.902,
+      "step": 900
+    },
+    {
+      "epoch": 2.346079066753078,
+      "grad_norm": 3.9070327756742107,
+      "learning_rate": 1.1308713623022986e-07,
+      "loss": 0.6627,
+      "step": 905
+    },
+    {
+      "epoch": 2.359040829552819,
+      "grad_norm": 3.7802235911895217,
+      "learning_rate": 1.0877896443633117e-07,
+      "loss": 0.6593,
+      "step": 910
+    },
+    {
+      "epoch": 2.37200259235256,
+      "grad_norm": 3.61433280563944,
+      "learning_rate": 1.045444208397791e-07,
+      "loss": 0.6709,
+      "step": 915
+    },
+    {
+      "epoch": 2.3849643551523005,
+      "grad_norm": 3.972094909530566,
+      "learning_rate": 1.0038430238599154e-07,
+      "loss": 0.651,
+      "step": 920
+    },
+    {
+      "epoch": 2.3979261179520415,
+      "grad_norm": 3.796273978107305,
+      "learning_rate": 9.629939201349852e-08,
+      "loss": 0.6588,
+      "step": 925
+    },
+    {
+      "epoch": 2.4108878807517824,
+      "grad_norm": 3.7293416826903525,
+      "learning_rate": 9.229045850659251e-08,
+      "loss": 0.656,
+      "step": 930
+    },
+    {
+      "epoch": 2.423849643551523,
+      "grad_norm": 3.6150556912476945,
+      "learning_rate": 8.835825635064265e-08,
+      "loss": 0.6603,
+      "step": 935
+    },
+    {
+      "epoch": 2.436811406351264,
+      "grad_norm": 3.5117438967831145,
+      "learning_rate": 8.450352559009949e-08,
+      "loss": 0.6572,
+      "step": 940
+    },
+    {
+      "epoch": 2.4497731691510047,
+      "grad_norm": 3.599439277396364,
+      "learning_rate": 8.072699168921825e-08,
+      "loss": 0.6523,
+      "step": 945
+    },
+    {
+      "epoch": 2.462734931950745,
+      "grad_norm": 3.815395750371357,
+      "learning_rate": 7.70293653955254e-08,
+      "loss": 0.6669,
+      "step": 950
+    },
+    {
+      "epoch": 2.462734931950745,
+      "eval_loss": 0.7661544680595398,
+      "eval_runtime": 190.5379,
+      "eval_samples_per_second": 57.569,
+      "eval_steps_per_second": 0.903,
+      "step": 950
+    },
+    {
+      "epoch": 2.475696694750486,
+      "grad_norm": 3.83907673537174,
+      "learning_rate": 7.341134260605536e-08,
+      "loss": 0.6467,
+      "step": 955
+    },
+    {
+      "epoch": 2.488658457550227,
+      "grad_norm": 3.71914525200344,
+      "learning_rate": 6.987360423638205e-08,
+      "loss": 0.6451,
+      "step": 960
+    },
+    {
+      "epoch": 2.5016202203499676,
+      "grad_norm": 3.8744678609767926,
+      "learning_rate": 6.641681609246979e-08,
+      "loss": 0.6499,
+      "step": 965
+    },
+    {
+      "epoch": 2.5145819831497085,
+      "grad_norm": 3.839049543501993,
+      "learning_rate": 6.304162874536795e-08,
+      "loss": 0.6381,
+      "step": 970
+    },
+    {
+      "epoch": 2.527543745949449,
+      "grad_norm": 3.890978467270095,
+      "learning_rate": 5.974867740877281e-08,
+      "loss": 0.6611,
+      "step": 975
+    },
+    {
+      "epoch": 2.54050550874919,
+      "grad_norm": 3.655850976914982,
+      "learning_rate": 5.653858181947979e-08,
+      "loss": 0.6511,
+      "step": 980
+    },
+    {
+      "epoch": 2.5534672715489304,
+      "grad_norm": 3.553408249450878,
+      "learning_rate": 5.341194612074823e-08,
+      "loss": 0.645,
+      "step": 985
+    },
+    {
+      "epoch": 2.5664290343486713,
+      "grad_norm": 3.772171071477516,
+      "learning_rate": 5.0369358748601096e-08,
+      "loss": 0.664,
+      "step": 990
+    },
+    {
+      "epoch": 2.5793907971484122,
+      "grad_norm": 3.9844066962823783,
+      "learning_rate": 4.74113923210806e-08,
+      "loss": 0.6768,
+      "step": 995
+    },
+    {
+      "epoch": 2.5923525599481527,
+      "grad_norm": 3.709224867062063,
+      "learning_rate": 4.453860353048111e-08,
+      "loss": 0.6566,
+      "step": 1000
+    },
+    {
+      "epoch": 2.5923525599481527,
+      "eval_loss": 0.7657259702682495,
+      "eval_runtime": 190.4841,
+      "eval_samples_per_second": 57.585,
+      "eval_steps_per_second": 0.903,
+      "step": 1000
+    },
+    {
+      "epoch": 2.6053143227478937,
+      "grad_norm": 3.6125710008133014,
+      "learning_rate": 4.1751533038578866e-08,
+      "loss": 0.6588,
+      "step": 1005
+    },
+    {
+      "epoch": 2.6182760855476346,
+      "grad_norm": 3.9281818636928305,
+      "learning_rate": 3.9050705374879086e-08,
+      "loss": 0.6451,
+      "step": 1010
+    },
+    {
+      "epoch": 2.631237848347375,
+      "grad_norm": 3.6915219360218794,
+      "learning_rate": 3.6436628837898773e-08,
+      "loss": 0.6537,
+      "step": 1015
+    },
+    {
+      "epoch": 2.644199611147116,
+      "grad_norm": 3.8956742656352756,
+      "learning_rate": 3.390979539950478e-08,
+      "loss": 0.6646,
+      "step": 1020
+    },
+    {
+      "epoch": 2.657161373946857,
+      "grad_norm": 3.693338526233881,
+      "learning_rate": 3.1470680612323494e-08,
+      "loss": 0.6398,
+      "step": 1025
+    },
+    {
+      "epoch": 2.6701231367465974,
+      "grad_norm": 3.676860096119893,
+      "learning_rate": 2.9119743520242213e-08,
+      "loss": 0.656,
+      "step": 1030
+    },
+    {
+      "epoch": 2.6830848995463383,
+      "grad_norm": 3.839586455095117,
+      "learning_rate": 2.6857426572016007e-08,
+      "loss": 0.6522,
+      "step": 1035
+    },
+    {
+      "epoch": 2.6960466623460793,
+      "grad_norm": 3.7505570827639754,
+      "learning_rate": 2.468415553799874e-08,
+      "loss": 0.661,
+      "step": 1040
+    },
+    {
+      "epoch": 2.7090084251458197,
+      "grad_norm": 3.74016254328062,
+      "learning_rate": 2.2600339430012438e-08,
+      "loss": 0.6543,
+      "step": 1045
+    },
+    {
+      "epoch": 2.7219701879455607,
+      "grad_norm": 4.044963430877048,
+      "learning_rate": 2.0606370424370966e-08,
+      "loss": 0.6654,
+      "step": 1050
+    },
+    {
+      "epoch": 2.7219701879455607,
+      "eval_loss": 0.765480101108551,
+      "eval_runtime": 190.595,
+      "eval_samples_per_second": 57.551,
+      "eval_steps_per_second": 0.902,
+      "step": 1050
+    },
+    {
+      "epoch": 2.7349319507453016,
+      "grad_norm": 3.8050950373574115,
+      "learning_rate": 1.8702623788072024e-08,
+      "loss": 0.6585,
+      "step": 1055
+    },
+    {
+      "epoch": 2.747893713545042,
+      "grad_norm": 3.7424493675710604,
+      "learning_rate": 1.688945780817147e-08,
+      "loss": 0.6765,
+      "step": 1060
+    },
+    {
+      "epoch": 2.760855476344783,
+      "grad_norm": 3.7803862294906496,
+      "learning_rate": 1.516721372435342e-08,
+      "loss": 0.6578,
+      "step": 1065
+    },
+    {
+      "epoch": 2.7738172391445235,
+      "grad_norm": 3.7879361506176332,
+      "learning_rate": 1.3536215664708583e-08,
+      "loss": 0.6681,
+      "step": 1070
+    },
+    {
+      "epoch": 2.7867790019442644,
+      "grad_norm": 3.8430280460507524,
+      "learning_rate": 1.1996770584732919e-08,
+      "loss": 0.6412,
+      "step": 1075
+    },
+    {
+      "epoch": 2.7997407647440054,
+      "grad_norm": 3.741428860483068,
+      "learning_rate": 1.0549168209558312e-08,
+      "loss": 0.6748,
+      "step": 1080
+    },
+    {
+      "epoch": 2.812702527543746,
+      "grad_norm": 3.7122256590189564,
+      "learning_rate": 9.193680979426189e-09,
+      "loss": 0.6433,
+      "step": 1085
+    },
+    {
+      "epoch": 2.8256642903434868,
+      "grad_norm": 3.6981576894413415,
+      "learning_rate": 7.930563998413797e-09,
+      "loss": 0.6621,
+      "step": 1090
+    },
+    {
+      "epoch": 2.8386260531432272,
+      "grad_norm": 3.7162009738597526,
+      "learning_rate": 6.760054986423458e-09,
+      "loss": 0.6623,
+      "step": 1095
+    },
+    {
+      "epoch": 2.851587815942968,
+      "grad_norm": 3.76189814784874,
+      "learning_rate": 5.6823742344433435e-09,
+      "loss": 0.6389,
+      "step": 1100
+    },
+    {
+      "epoch": 2.851587815942968,
+      "eval_loss": 0.7652862668037415,
+      "eval_runtime": 190.4719,
+      "eval_samples_per_second": 57.589,
+      "eval_steps_per_second": 0.903,
+      "step": 1100
+    },
+    {
+      "epoch": 2.864549578742709,
+      "grad_norm": 4.07593882169201,
+      "learning_rate": 4.697724563088645e-09,
+      "loss": 0.6616,
+      "step": 1105
+    },
+    {
+      "epoch": 2.8775113415424496,
+      "grad_norm": 3.95049669925965,
+      "learning_rate": 3.806291284430274e-09,
+      "loss": 0.6678,
+      "step": 1110
+    },
+    {
+      "epoch": 2.8904731043421905,
+      "grad_norm": 3.692127174629793,
+      "learning_rate": 3.008242167119257e-09,
+      "loss": 0.6533,
+      "step": 1115
+    },
+    {
+      "epoch": 2.9034348671419314,
+      "grad_norm": 3.9224928557653254,
+      "learning_rate": 2.303727404812217e-09,
+      "loss": 0.6568,
+      "step": 1120
+    },
+    {
+      "epoch": 2.916396629941672,
+      "grad_norm": 3.700977024408014,
+      "learning_rate": 1.6928795879049828e-09,
+      "loss": 0.658,
+      "step": 1125
+    },
+    {
+      "epoch": 2.929358392741413,
+      "grad_norm": 3.671559049022848,
+      "learning_rate": 1.1758136785788853e-09,
+      "loss": 0.6591,
+      "step": 1130
+    },
+    {
+      "epoch": 2.942320155541154,
+      "grad_norm": 3.9515548315685107,
+      "learning_rate": 7.526269891646175e-10,
+      "loss": 0.6448,
+      "step": 1135
+    },
+    {
+      "epoch": 2.9552819183408943,
+      "grad_norm": 3.6083444577524615,
+      "learning_rate": 4.233991638281642e-10,
+      "loss": 0.6421,
+      "step": 1140
+    },
+    {
+      "epoch": 2.968243681140635,
+      "grad_norm": 3.6842766767841733,
+      "learning_rate": 1.8819216358156865e-10,
+      "loss": 0.6606,
+      "step": 1145
+    },
+    {
+      "epoch": 2.981205443940376,
+      "grad_norm": 4.03690890015612,
+      "learning_rate": 4.7050254621872064e-11,
+      "loss": 0.6574,
+      "step": 1150
+    },
+    {
+      "epoch": 2.981205443940376,
+      "eval_loss": 0.7652673125267029,
+      "eval_runtime": 190.6904,
+      "eval_samples_per_second": 57.523,
+      "eval_steps_per_second": 0.902,
+      "step": 1150
+    },
+    {
+      "epoch": 2.9941672067401166,
+      "grad_norm": 4.036929712704943,
+      "learning_rate": 0.0,
+      "loss": 0.6573,
+      "step": 1155
+    },
+    {
+      "epoch": 2.9941672067401166,
+      "step": 1155,
+      "total_flos": 6810169535102976.0,
+      "train_loss": 0.7440064066932315,
+      "train_runtime": 19885.6035,
+      "train_samples_per_second": 14.893,
+      "train_steps_per_second": 0.058
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1155,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6810169535102976.0,
+  "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 sha256:28fa504463dfeaf203fb49ea5c5a4898f2010658b2df3587d46d0f38e983cedc
+size 7096