Upload folder using huggingface_hub

README.md

@@ -0,0 +1,84 @@
+---
+library_name: transformers
+license: other
+base_model: llava-hf/llava-v1.6-mistral-7b-hf
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Compcap_cooccur_0_90
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Compcap_cooccur_0_90
+
+This model is a fine-tuned version of [llava-hf/llava-v1.6-mistral-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf) on the Compcap_cooccur_0_90 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7879
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9273        | 0.1505 | 50   | 0.9361          |
+| 0.8938        | 0.3010 | 100  | 0.8805          |
+| 0.8476        | 0.4515 | 150  | 0.8552          |
+| 0.8413        | 0.6020 | 200  | 0.8378          |
+| 0.8254        | 0.7524 | 250  | 0.8255          |
+| 0.8091        | 0.9029 | 300  | 0.8149          |
+| 0.7271        | 1.0534 | 350  | 0.8105          |
+| 0.7383        | 1.2039 | 400  | 0.8056          |
+| 0.7543        | 1.3544 | 450  | 0.8005          |
+| 0.7373        | 1.5049 | 500  | 0.7961          |
+| 0.7145        | 1.6554 | 550  | 0.7924          |
+| 0.7176        | 1.8059 | 600  | 0.7887          |
+| 0.7384        | 1.9564 | 650  | 0.7858          |
+| 0.6877        | 2.1068 | 700  | 0.7907          |
+| 0.6796        | 2.2573 | 750  | 0.7899          |
+| 0.6837        | 2.4078 | 800  | 0.7888          |
+| 0.6653        | 2.5583 | 850  | 0.7885          |
+| 0.6563        | 2.7088 | 900  | 0.7879          |
+| 0.6829        | 2.8593 | 950  | 0.7879          |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9977426636568847,
+    "eval_loss": 0.7878820300102234,
+    "eval_runtime": 164.1569,
+    "eval_samples_per_second": 57.567,
+    "eval_steps_per_second": 0.902,
+    "total_flos": 5872633472090112.0,
+    "train_loss": 0.7696134887905006,
+    "train_runtime": 16213.1344,
+    "train_samples_per_second": 15.737,
+    "train_steps_per_second": 0.061
+}

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
+  "architectures": [
+    "LlavaNextForConditionalGeneration"
+  ],
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava_next",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "architectures": [
+      "MistralForCausalLM"
+    ],
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_image_newline_parameter": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9977426636568847,
+    "eval_loss": 0.7878820300102234,
+    "eval_runtime": 164.1569,
+    "eval_samples_per_second": 57.567,
+    "eval_steps_per_second": 0.902
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c258809e75b0f61aa49511a6387d1eec86d66f2e9741fccb1155b70f30aeeced
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82340a6d7523e69c3b4a38d0e8bdfbe41b459106c7906dc3408dd04e8cca12d
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2629d421c0562bae786386a545bad9835476300fb08e5a51b34c5443f32f3a1
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46b8c4b2d9584c0214e8b9f0d42b754b6f24929c7d5b44a13492226b19826944
+size 380134008

model.safetensors.index.json

@@ -0,0 +1,694 @@
+{
+  "metadata": {
+    "total_size": 15133495296
+  },
+  "weight_map": {
+    "image_newline": "model-00001-of-00004.safetensors",
+    "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00004.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,52 @@
+{
+  "aspect_ratio_setting": "anyres",
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaNextProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '`[INST] `' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {
+    "image_token": "<image>"
+  },
+  "image_token": "<image>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "LlavaNextProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9977426636568847,
+    "total_flos": 5872633472090112.0,
+    "train_loss": 0.7696134887905006,
+    "train_runtime": 16213.1344,
+    "train_samples_per_second": 15.737,
+    "train_steps_per_second": 0.061
+}

trainer_log.jsonl

@@ -0,0 +1,219 @@
+{"current_steps": 5, "total_steps": 996, "loss": 1.7267, "learning_rate": 5e-07, "epoch": 0.015048908954100828, "percentage": 0.5, "elapsed_time": "0:01:09", "remaining_time": "3:50:04"}
+{"current_steps": 10, "total_steps": 996, "loss": 1.5935, "learning_rate": 1e-06, "epoch": 0.030097817908201655, "percentage": 1.0, "elapsed_time": "0:02:15", "remaining_time": "3:42:40"}
+{"current_steps": 15, "total_steps": 996, "loss": 1.2846, "learning_rate": 9.999365521737421e-07, "epoch": 0.045146726862302484, "percentage": 1.51, "elapsed_time": "0:03:21", "remaining_time": "3:39:27"}
+{"current_steps": 20, "total_steps": 996, "loss": 1.147, "learning_rate": 9.99746224797475e-07, "epoch": 0.06019563581640331, "percentage": 2.01, "elapsed_time": "0:04:26", "remaining_time": "3:36:57"}
+{"current_steps": 25, "total_steps": 996, "loss": 1.0702, "learning_rate": 9.99429066174632e-07, "epoch": 0.07524454477050414, "percentage": 2.51, "elapsed_time": "0:05:32", "remaining_time": "3:35:29"}
+{"current_steps": 30, "total_steps": 996, "loss": 1.0299, "learning_rate": 9.989851567973138e-07, "epoch": 0.09029345372460497, "percentage": 3.01, "elapsed_time": "0:06:38", "remaining_time": "3:34:02"}
+{"current_steps": 35, "total_steps": 996, "loss": 0.996, "learning_rate": 9.984146093258608e-07, "epoch": 0.1053423626787058, "percentage": 3.51, "elapsed_time": "0:07:44", "remaining_time": "3:32:27"}
+{"current_steps": 40, "total_steps": 996, "loss": 0.9736, "learning_rate": 9.9771756856026e-07, "epoch": 0.12039127163280662, "percentage": 4.02, "elapsed_time": "0:08:50", "remaining_time": "3:31:10"}
+{"current_steps": 45, "total_steps": 996, "loss": 0.9431, "learning_rate": 9.968942114033973e-07, "epoch": 0.13544018058690746, "percentage": 4.52, "elapsed_time": "0:09:55", "remaining_time": "3:29:42"}
+{"current_steps": 50, "total_steps": 996, "loss": 0.9273, "learning_rate": 9.959447468161596e-07, "epoch": 0.1504890895410083, "percentage": 5.02, "elapsed_time": "0:11:00", "remaining_time": "3:28:24"}
+{"current_steps": 50, "total_steps": 996, "eval_loss": 0.936109185218811, "epoch": 0.1504890895410083, "percentage": 5.02, "elapsed_time": "0:13:47", "remaining_time": "4:20:54"}
+{"current_steps": 55, "total_steps": 996, "loss": 0.9287, "learning_rate": 9.948694157644042e-07, "epoch": 0.1655379984951091, "percentage": 5.52, "elapsed_time": "0:14:52", "remaining_time": "4:14:32"}
+{"current_steps": 60, "total_steps": 996, "loss": 0.9232, "learning_rate": 9.936684911578017e-07, "epoch": 0.18058690744920994, "percentage": 6.02, "elapsed_time": "0:15:58", "remaining_time": "4:09:14"}
+{"current_steps": 65, "total_steps": 996, "loss": 0.9329, "learning_rate": 9.923422777805751e-07, "epoch": 0.19563581640331076, "percentage": 6.53, "elapsed_time": "0:17:04", "remaining_time": "4:04:38"}
+{"current_steps": 70, "total_steps": 996, "loss": 0.8932, "learning_rate": 9.908911122141486e-07, "epoch": 0.2106847253574116, "percentage": 7.03, "elapsed_time": "0:18:10", "remaining_time": "4:00:27"}
+{"current_steps": 75, "total_steps": 996, "loss": 0.8696, "learning_rate": 9.893153627517248e-07, "epoch": 0.22573363431151242, "percentage": 7.53, "elapsed_time": "0:19:15", "remaining_time": "3:56:30"}
+{"current_steps": 80, "total_steps": 996, "loss": 0.8977, "learning_rate": 9.876154293048163e-07, "epoch": 0.24078254326561324, "percentage": 8.03, "elapsed_time": "0:20:20", "remaining_time": "3:52:58"}
+{"current_steps": 85, "total_steps": 996, "loss": 0.8997, "learning_rate": 9.857917433017508e-07, "epoch": 0.2558314522197141, "percentage": 8.53, "elapsed_time": "0:21:26", "remaining_time": "3:49:50"}
+{"current_steps": 90, "total_steps": 996, "loss": 0.8567, "learning_rate": 9.838447675781793e-07, "epoch": 0.2708803611738149, "percentage": 9.04, "elapsed_time": "0:22:32", "remaining_time": "3:46:52"}
+{"current_steps": 95, "total_steps": 996, "loss": 0.8692, "learning_rate": 9.817749962596114e-07, "epoch": 0.28592927012791575, "percentage": 9.54, "elapsed_time": "0:23:38", "remaining_time": "3:44:10"}
+{"current_steps": 100, "total_steps": 996, "loss": 0.8938, "learning_rate": 9.795829546360113e-07, "epoch": 0.3009781790820166, "percentage": 10.04, "elapsed_time": "0:24:43", "remaining_time": "3:41:34"}
+{"current_steps": 100, "total_steps": 996, "eval_loss": 0.8804982900619507, "epoch": 0.3009781790820166, "percentage": 10.04, "elapsed_time": "0:27:28", "remaining_time": "4:06:14"}
+{"current_steps": 105, "total_steps": 996, "loss": 0.8744, "learning_rate": 9.77269199028483e-07, "epoch": 0.3160270880361174, "percentage": 10.54, "elapsed_time": "0:28:33", "remaining_time": "4:02:22"}
+{"current_steps": 110, "total_steps": 996, "loss": 0.8506, "learning_rate": 9.748343166480822e-07, "epoch": 0.3310759969902182, "percentage": 11.04, "elapsed_time": "0:29:38", "remaining_time": "3:58:47"}
+{"current_steps": 115, "total_steps": 996, "loss": 0.8583, "learning_rate": 9.722789254467854e-07, "epoch": 0.34612490594431905, "percentage": 11.55, "elapsed_time": "0:30:44", "remaining_time": "3:55:27"}
+{"current_steps": 120, "total_steps": 996, "loss": 0.8699, "learning_rate": 9.696036739606606e-07, "epoch": 0.3611738148984199, "percentage": 12.05, "elapsed_time": "0:31:48", "remaining_time": "3:52:14"}
+{"current_steps": 125, "total_steps": 996, "loss": 0.87, "learning_rate": 9.668092411452735e-07, "epoch": 0.3762227238525207, "percentage": 12.55, "elapsed_time": "0:32:54", "remaining_time": "3:49:15"}
+{"current_steps": 130, "total_steps": 996, "loss": 0.8627, "learning_rate": 9.638963362033756e-07, "epoch": 0.3912716328066215, "percentage": 13.05, "elapsed_time": "0:33:59", "remaining_time": "3:46:29"}
+{"current_steps": 135, "total_steps": 996, "loss": 0.842, "learning_rate": 9.608656984049132e-07, "epoch": 0.40632054176072235, "percentage": 13.55, "elapsed_time": "0:35:05", "remaining_time": "3:43:47"}
+{"current_steps": 140, "total_steps": 996, "loss": 0.8367, "learning_rate": 9.577180968994081e-07, "epoch": 0.4213694507148232, "percentage": 14.06, "elapsed_time": "0:36:10", "remaining_time": "3:41:10"}
+{"current_steps": 145, "total_steps": 996, "loss": 0.8565, "learning_rate": 9.544543305207546e-07, "epoch": 0.436418359668924, "percentage": 14.56, "elapsed_time": "0:37:16", "remaining_time": "3:38:44"}
+{"current_steps": 150, "total_steps": 996, "loss": 0.8476, "learning_rate": 9.510752275844809e-07, "epoch": 0.45146726862302483, "percentage": 15.06, "elapsed_time": "0:38:21", "remaining_time": "3:36:21"}
+{"current_steps": 150, "total_steps": 996, "eval_loss": 0.8552336692810059, "epoch": 0.45146726862302483, "percentage": 15.06, "elapsed_time": "0:41:05", "remaining_time": "3:51:48"}
+{"current_steps": 155, "total_steps": 996, "loss": 0.8419, "learning_rate": 9.475816456775312e-07, "epoch": 0.46651617757712566, "percentage": 15.56, "elapsed_time": "0:42:11", "remaining_time": "3:48:57"}
+{"current_steps": 160, "total_steps": 996, "loss": 0.8571, "learning_rate": 9.439744714406166e-07, "epoch": 0.4815650865312265, "percentage": 16.06, "elapsed_time": "0:43:17", "remaining_time": "3:46:11"}
+{"current_steps": 165, "total_steps": 996, "loss": 0.8552, "learning_rate": 9.402546203431947e-07, "epoch": 0.4966139954853273, "percentage": 16.57, "elapsed_time": "0:44:23", "remaining_time": "3:43:32"}
+{"current_steps": 170, "total_steps": 996, "loss": 0.8284, "learning_rate": 9.364230364511295e-07, "epoch": 0.5116629044394282, "percentage": 17.07, "elapsed_time": "0:45:28", "remaining_time": "3:40:58"}
+{"current_steps": 175, "total_steps": 996, "loss": 0.8445, "learning_rate": 9.324806921870975e-07, "epoch": 0.526711813393529, "percentage": 17.57, "elapsed_time": "0:46:34", "remaining_time": "3:38:28"}
+{"current_steps": 180, "total_steps": 996, "loss": 0.8467, "learning_rate": 9.284285880837946e-07, "epoch": 0.5417607223476298, "percentage": 18.07, "elapsed_time": "0:47:39", "remaining_time": "3:36:03"}
+{"current_steps": 185, "total_steps": 996, "loss": 0.8444, "learning_rate": 9.242677525300088e-07, "epoch": 0.5568096313017307, "percentage": 18.57, "elapsed_time": "0:48:44", "remaining_time": "3:33:38"}
+{"current_steps": 190, "total_steps": 996, "loss": 0.8329, "learning_rate": 9.199992415096259e-07, "epoch": 0.5718585402558315, "percentage": 19.08, "elapsed_time": "0:49:49", "remaining_time": "3:31:23"}
+{"current_steps": 195, "total_steps": 996, "loss": 0.8393, "learning_rate": 9.156241383336278e-07, "epoch": 0.5869074492099323, "percentage": 19.58, "elapsed_time": "0:50:55", "remaining_time": "3:29:10"}
+{"current_steps": 200, "total_steps": 996, "loss": 0.8413, "learning_rate": 9.111435533651595e-07, "epoch": 0.6019563581640331, "percentage": 20.08, "elapsed_time": "0:52:01", "remaining_time": "3:27:01"}
+{"current_steps": 200, "total_steps": 996, "eval_loss": 0.8378457427024841, "epoch": 0.6019563581640331, "percentage": 20.08, "elapsed_time": "0:54:45", "remaining_time": "3:37:55"}
+{"current_steps": 205, "total_steps": 996, "loss": 0.8383, "learning_rate": 9.065586237377274e-07, "epoch": 0.617005267118134, "percentage": 20.58, "elapsed_time": "0:55:50", "remaining_time": "3:35:29"}
+{"current_steps": 210, "total_steps": 996, "loss": 0.846, "learning_rate": 9.018705130666049e-07, "epoch": 0.6320541760722348, "percentage": 21.08, "elapsed_time": "0:56:55", "remaining_time": "3:33:04"}
+{"current_steps": 215, "total_steps": 996, "loss": 0.8348, "learning_rate": 8.970804111535175e-07, "epoch": 0.6471030850263356, "percentage": 21.59, "elapsed_time": "0:58:01", "remaining_time": "3:30:46"}
+{"current_steps": 220, "total_steps": 996, "loss": 0.8237, "learning_rate": 8.921895336846812e-07, "epoch": 0.6621519939804364, "percentage": 22.09, "elapsed_time": "0:59:05", "remaining_time": "3:28:27"}
+{"current_steps": 225, "total_steps": 996, "loss": 0.8363, "learning_rate": 8.871991219222712e-07, "epoch": 0.6772009029345373, "percentage": 22.59, "elapsed_time": "1:00:10", "remaining_time": "3:26:13"}
+{"current_steps": 230, "total_steps": 996, "loss": 0.8115, "learning_rate": 8.821104423894014e-07, "epoch": 0.6922498118886381, "percentage": 23.09, "elapsed_time": "1:01:16", "remaining_time": "3:24:04"}
+{"current_steps": 235, "total_steps": 996, "loss": 0.8129, "learning_rate": 8.769247865486915e-07, "epoch": 0.7072987208427389, "percentage": 23.59, "elapsed_time": "1:02:22", "remaining_time": "3:21:59"}
+{"current_steps": 240, "total_steps": 996, "loss": 0.8243, "learning_rate": 8.716434704745046e-07, "epoch": 0.7223476297968398, "percentage": 24.1, "elapsed_time": "1:03:28", "remaining_time": "3:19:56"}
+{"current_steps": 245, "total_steps": 996, "loss": 0.8394, "learning_rate": 8.662678345189396e-07, "epoch": 0.7373965387509406, "percentage": 24.6, "elapsed_time": "1:04:33", "remaining_time": "3:17:54"}
+{"current_steps": 250, "total_steps": 996, "loss": 0.8254, "learning_rate": 8.607992429716608e-07, "epoch": 0.7524454477050414, "percentage": 25.1, "elapsed_time": "1:05:39", "remaining_time": "3:15:55"}
+{"current_steps": 250, "total_steps": 996, "eval_loss": 0.8255200982093811, "epoch": 0.7524454477050414, "percentage": 25.1, "elapsed_time": "1:08:24", "remaining_time": "3:24:06"}
+{"current_steps": 255, "total_steps": 996, "loss": 0.8209, "learning_rate": 8.55239083713654e-07, "epoch": 0.7674943566591422, "percentage": 25.6, "elapsed_time": "1:09:30", "remaining_time": "3:21:58"}
+{"current_steps": 260, "total_steps": 996, "loss": 0.8235, "learning_rate": 8.495887678649932e-07, "epoch": 0.782543265613243, "percentage": 26.1, "elapsed_time": "1:10:34", "remaining_time": "3:19:48"}
+{"current_steps": 265, "total_steps": 996, "loss": 0.8148, "learning_rate": 8.438497294267116e-07, "epoch": 0.7975921745673439, "percentage": 26.61, "elapsed_time": "1:11:39", "remaining_time": "3:17:40"}
+{"current_steps": 270, "total_steps": 996, "loss": 0.8237, "learning_rate": 8.38023424916864e-07, "epoch": 0.8126410835214447, "percentage": 27.11, "elapsed_time": "1:12:44", "remaining_time": "3:15:36"}
+{"current_steps": 275, "total_steps": 996, "loss": 0.8199, "learning_rate": 8.321113330008756e-07, "epoch": 0.8276899924755455, "percentage": 27.61, "elapsed_time": "1:13:50", "remaining_time": "3:13:36"}
+{"current_steps": 280, "total_steps": 996, "loss": 0.8198, "learning_rate": 8.261149541162691e-07, "epoch": 0.8427389014296464, "percentage": 28.11, "elapsed_time": "1:14:56", "remaining_time": "3:11:38"}
+{"current_steps": 285, "total_steps": 996, "loss": 0.833, "learning_rate": 8.20035810091867e-07, "epoch": 0.8577878103837472, "percentage": 28.61, "elapsed_time": "1:16:02", "remaining_time": "3:09:41"}
+{"current_steps": 290, "total_steps": 996, "loss": 0.8336, "learning_rate": 8.13875443761565e-07, "epoch": 0.872836719337848, "percentage": 29.12, "elapsed_time": "1:17:08", "remaining_time": "3:07:47"}
+{"current_steps": 295, "total_steps": 996, "loss": 0.8211, "learning_rate": 8.076354185727734e-07, "epoch": 0.8878856282919488, "percentage": 29.62, "elapsed_time": "1:18:13", "remaining_time": "3:05:53"}
+{"current_steps": 300, "total_steps": 996, "loss": 0.8091, "learning_rate": 8.013173181896282e-07, "epoch": 0.9029345372460497, "percentage": 30.12, "elapsed_time": "1:19:19", "remaining_time": "3:04:01"}
+{"current_steps": 300, "total_steps": 996, "eval_loss": 0.8148868680000305, "epoch": 0.9029345372460497, "percentage": 30.12, "elapsed_time": "1:22:03", "remaining_time": "3:10:23"}
+{"current_steps": 305, "total_steps": 996, "loss": 0.8271, "learning_rate": 7.94922746091071e-07, "epoch": 0.9179834462001505, "percentage": 30.62, "elapsed_time": "1:23:09", "remaining_time": "3:08:23"}
+{"current_steps": 310, "total_steps": 996, "loss": 0.7997, "learning_rate": 7.884533251638999e-07, "epoch": 0.9330323551542513, "percentage": 31.12, "elapsed_time": "1:24:15", "remaining_time": "3:06:26"}
+{"current_steps": 315, "total_steps": 996, "loss": 0.8131, "learning_rate": 7.819106972908949e-07, "epoch": 0.9480812641083521, "percentage": 31.63, "elapsed_time": "1:25:20", "remaining_time": "3:04:30"}
+{"current_steps": 320, "total_steps": 996, "loss": 0.8244, "learning_rate": 7.752965229341219e-07, "epoch": 0.963130173062453, "percentage": 32.13, "elapsed_time": "1:26:25", "remaining_time": "3:02:35"}
+{"current_steps": 325, "total_steps": 996, "loss": 0.8056, "learning_rate": 7.686124807135228e-07, "epoch": 0.9781790820165538, "percentage": 32.63, "elapsed_time": "1:27:30", "remaining_time": "3:00:40"}
+{"current_steps": 330, "total_steps": 996, "loss": 0.8193, "learning_rate": 7.618602669808957e-07, "epoch": 0.9932279909706546, "percentage": 33.13, "elapsed_time": "1:28:36", "remaining_time": "2:58:49"}
+{"current_steps": 335, "total_steps": 996, "loss": 0.781, "learning_rate": 7.550415953893756e-07, "epoch": 1.0082768999247556, "percentage": 33.63, "elapsed_time": "1:29:42", "remaining_time": "2:56:59"}
+{"current_steps": 340, "total_steps": 996, "loss": 0.7508, "learning_rate": 7.481581964585244e-07, "epoch": 1.0233258088788564, "percentage": 34.14, "elapsed_time": "1:30:47", "remaining_time": "2:55:10"}
+{"current_steps": 345, "total_steps": 996, "loss": 0.7483, "learning_rate": 7.412118171351395e-07, "epoch": 1.0383747178329572, "percentage": 34.64, "elapsed_time": "1:31:52", "remaining_time": "2:53:22"}
+{"current_steps": 350, "total_steps": 996, "loss": 0.7271, "learning_rate": 7.342042203498951e-07, "epoch": 1.053423626787058, "percentage": 35.14, "elapsed_time": "1:32:58", "remaining_time": "2:51:36"}
+{"current_steps": 350, "total_steps": 996, "eval_loss": 0.8104769587516785, "epoch": 1.053423626787058, "percentage": 35.14, "elapsed_time": "1:35:43", "remaining_time": "2:56:40"}
+{"current_steps": 355, "total_steps": 996, "loss": 0.7538, "learning_rate": 7.271371845699241e-07, "epoch": 1.0684725357411589, "percentage": 35.64, "elapsed_time": "1:36:48", "remaining_time": "2:54:48"}
+{"current_steps": 360, "total_steps": 996, "loss": 0.7428, "learning_rate": 7.200125033474598e-07, "epoch": 1.0835214446952597, "percentage": 36.14, "elapsed_time": "1:37:54", "remaining_time": "2:52:58"}
+{"current_steps": 365, "total_steps": 996, "loss": 0.7528, "learning_rate": 7.128319848646477e-07, "epoch": 1.0985703536493605, "percentage": 36.65, "elapsed_time": "1:38:59", "remaining_time": "2:51:08"}
+{"current_steps": 370, "total_steps": 996, "loss": 0.7583, "learning_rate": 7.055974514746445e-07, "epoch": 1.1136192626034613, "percentage": 37.15, "elapsed_time": "1:40:05", "remaining_time": "2:49:20"}
+{"current_steps": 375, "total_steps": 996, "loss": 0.7333, "learning_rate": 6.983107392391202e-07, "epoch": 1.1286681715575622, "percentage": 37.65, "elapsed_time": "1:41:11", "remaining_time": "2:47:33"}
+{"current_steps": 380, "total_steps": 996, "loss": 0.7367, "learning_rate": 6.909736974622826e-07, "epoch": 1.143717080511663, "percentage": 38.15, "elapsed_time": "1:42:16", "remaining_time": "2:45:47"}
+{"current_steps": 385, "total_steps": 996, "loss": 0.7389, "learning_rate": 6.835881882215395e-07, "epoch": 1.1587659894657638, "percentage": 38.65, "elapsed_time": "1:43:21", "remaining_time": "2:44:02"}
+{"current_steps": 390, "total_steps": 996, "loss": 0.7272, "learning_rate": 6.761560858949192e-07, "epoch": 1.1738148984198646, "percentage": 39.16, "elapsed_time": "1:44:27", "remaining_time": "2:42:18"}
+{"current_steps": 395, "total_steps": 996, "loss": 0.7411, "learning_rate": 6.686792766853705e-07, "epoch": 1.1888638073739655, "percentage": 39.66, "elapsed_time": "1:45:32", "remaining_time": "2:40:35"}
+{"current_steps": 400, "total_steps": 996, "loss": 0.7383, "learning_rate": 6.611596581420599e-07, "epoch": 1.2039127163280663, "percentage": 40.16, "elapsed_time": "1:46:38", "remaining_time": "2:38:53"}
+{"current_steps": 400, "total_steps": 996, "eval_loss": 0.8055551648139954, "epoch": 1.2039127163280663, "percentage": 40.16, "elapsed_time": "1:49:23", "remaining_time": "2:42:59"}
+{"current_steps": 405, "total_steps": 996, "loss": 0.7447, "learning_rate": 6.53599138678791e-07, "epoch": 1.2189616252821671, "percentage": 40.66, "elapsed_time": "1:50:28", "remaining_time": "2:41:13"}
+{"current_steps": 410, "total_steps": 996, "loss": 0.7143, "learning_rate": 6.459996370896652e-07, "epoch": 1.234010534236268, "percentage": 41.16, "elapsed_time": "1:51:34", "remaining_time": "2:39:27"}
+{"current_steps": 415, "total_steps": 996, "loss": 0.7486, "learning_rate": 6.383630820621081e-07, "epoch": 1.2490594431903688, "percentage": 41.67, "elapsed_time": "1:52:39", "remaining_time": "2:37:43"}
+{"current_steps": 420, "total_steps": 996, "loss": 0.7428, "learning_rate": 6.306914116873862e-07, "epoch": 1.2641083521444696, "percentage": 42.17, "elapsed_time": "1:53:44", "remaining_time": "2:35:59"}
+{"current_steps": 425, "total_steps": 996, "loss": 0.7466, "learning_rate": 6.22986572968736e-07, "epoch": 1.2791572610985704, "percentage": 42.67, "elapsed_time": "1:54:48", "remaining_time": "2:34:15"}
+{"current_steps": 430, "total_steps": 996, "loss": 0.7568, "learning_rate": 6.152505213272307e-07, "epoch": 1.2942061700526712, "percentage": 43.17, "elapsed_time": "1:55:54", "remaining_time": "2:32:34"}
+{"current_steps": 435, "total_steps": 996, "loss": 0.7345, "learning_rate": 6.074852201055121e-07, "epoch": 1.309255079006772, "percentage": 43.67, "elapsed_time": "1:57:00", "remaining_time": "2:30:54"}
+{"current_steps": 440, "total_steps": 996, "loss": 0.7423, "learning_rate": 5.996926400695113e-07, "epoch": 1.324303987960873, "percentage": 44.18, "elapsed_time": "1:58:06", "remaining_time": "2:29:14"}
+{"current_steps": 445, "total_steps": 996, "loss": 0.7435, "learning_rate": 5.918747589082852e-07, "epoch": 1.3393528969149737, "percentage": 44.68, "elapsed_time": "1:59:11", "remaining_time": "2:27:35"}
+{"current_steps": 450, "total_steps": 996, "loss": 0.7543, "learning_rate": 5.840335607320963e-07, "epoch": 1.3544018058690745, "percentage": 45.18, "elapsed_time": "2:00:17", "remaining_time": "2:25:57"}
+{"current_steps": 450, "total_steps": 996, "eval_loss": 0.8005452752113342, "epoch": 1.3544018058690745, "percentage": 45.18, "elapsed_time": "2:03:02", "remaining_time": "2:29:17"}
+{"current_steps": 455, "total_steps": 996, "loss": 0.7147, "learning_rate": 5.761710355688627e-07, "epoch": 1.3694507148231754, "percentage": 45.68, "elapsed_time": "2:04:07", "remaining_time": "2:27:35"}
+{"current_steps": 460, "total_steps": 996, "loss": 0.7449, "learning_rate": 5.682891788591065e-07, "epoch": 1.3844996237772762, "percentage": 46.18, "elapsed_time": "2:05:12", "remaining_time": "2:25:53"}
+{"current_steps": 465, "total_steps": 996, "loss": 0.7245, "learning_rate": 5.603899909495283e-07, "epoch": 1.399548532731377, "percentage": 46.69, "elapsed_time": "2:06:17", "remaining_time": "2:24:13"}
+{"current_steps": 470, "total_steps": 996, "loss": 0.7431, "learning_rate": 5.52475476585336e-07, "epoch": 1.4145974416854779, "percentage": 47.19, "elapsed_time": "2:07:23", "remaining_time": "2:22:33"}
+{"current_steps": 475, "total_steps": 996, "loss": 0.7467, "learning_rate": 5.445476444014591e-07, "epoch": 1.4296463506395787, "percentage": 47.69, "elapsed_time": "2:08:29", "remaining_time": "2:20:55"}
+{"current_steps": 480, "total_steps": 996, "loss": 0.7494, "learning_rate": 5.366085064127734e-07, "epoch": 1.4446952595936795, "percentage": 48.19, "elapsed_time": "2:09:34", "remaining_time": "2:19:17"}
+{"current_steps": 485, "total_steps": 996, "loss": 0.7488, "learning_rate": 5.286600775034699e-07, "epoch": 1.4597441685477803, "percentage": 48.69, "elapsed_time": "2:10:39", "remaining_time": "2:17:39"}
+{"current_steps": 490, "total_steps": 996, "loss": 0.7455, "learning_rate": 5.207043749156944e-07, "epoch": 1.4747930775018812, "percentage": 49.2, "elapsed_time": "2:11:45", "remaining_time": "2:16:03"}
+{"current_steps": 495, "total_steps": 996, "loss": 0.7245, "learning_rate": 5.127434177375893e-07, "epoch": 1.489841986455982, "percentage": 49.7, "elapsed_time": "2:12:50", "remaining_time": "2:14:27"}
+{"current_steps": 500, "total_steps": 996, "loss": 0.7373, "learning_rate": 5.047792263908659e-07, "epoch": 1.5048908954100828, "percentage": 50.2, "elapsed_time": "2:14:06", "remaining_time": "2:13:02"}
+{"current_steps": 500, "total_steps": 996, "eval_loss": 0.7960706949234009, "epoch": 1.5048908954100828, "percentage": 50.2, "elapsed_time": "2:16:51", "remaining_time": "2:15:45"}
+{"current_steps": 505, "total_steps": 996, "loss": 0.7177, "learning_rate": 4.968138221180401e-07, "epoch": 1.5199398043641836, "percentage": 50.7, "elapsed_time": "2:17:57", "remaining_time": "2:14:07"}
+{"current_steps": 510, "total_steps": 996, "loss": 0.7274, "learning_rate": 4.888492264694565e-07, "epoch": 1.5349887133182845, "percentage": 51.2, "elapsed_time": "2:19:03", "remaining_time": "2:12:30"}
+{"current_steps": 515, "total_steps": 996, "loss": 0.7248, "learning_rate": 4.808874607902397e-07, "epoch": 1.5500376222723853, "percentage": 51.71, "elapsed_time": "2:20:08", "remaining_time": "2:10:53"}
+{"current_steps": 520, "total_steps": 996, "loss": 0.7228, "learning_rate": 4.7293054570729126e-07, "epoch": 1.565086531226486, "percentage": 52.21, "elapsed_time": "2:21:14", "remaining_time": "2:09:17"}
+{"current_steps": 525, "total_steps": 996, "loss": 0.7345, "learning_rate": 4.649805006164743e-07, "epoch": 1.580135440180587, "percentage": 52.71, "elapsed_time": "2:22:20", "remaining_time": "2:07:41"}
+{"current_steps": 530, "total_steps": 996, "loss": 0.7336, "learning_rate": 4.5703934317010727e-07, "epoch": 1.5951843491346878, "percentage": 53.21, "elapsed_time": "2:23:25", "remaining_time": "2:06:06"}
+{"current_steps": 535, "total_steps": 996, "loss": 0.7402, "learning_rate": 4.491090887649024e-07, "epoch": 1.6102332580887886, "percentage": 53.71, "elapsed_time": "2:24:31", "remaining_time": "2:04:31"}
+{"current_steps": 540, "total_steps": 996, "loss": 0.7417, "learning_rate": 4.4119175003047407e-07, "epoch": 1.6252821670428894, "percentage": 54.22, "elapsed_time": "2:25:36", "remaining_time": "2:02:57"}
+{"current_steps": 545, "total_steps": 996, "loss": 0.7414, "learning_rate": 4.3328933631855195e-07, "epoch": 1.6403310759969902, "percentage": 54.72, "elapsed_time": "2:26:42", "remaining_time": "2:01:24"}
+{"current_steps": 550, "total_steps": 996, "loss": 0.7145, "learning_rate": 4.2540385319302524e-07, "epoch": 1.655379984951091, "percentage": 55.22, "elapsed_time": "2:27:48", "remaining_time": "1:59:51"}
+{"current_steps": 550, "total_steps": 996, "eval_loss": 0.7923677563667297, "epoch": 1.655379984951091, "percentage": 55.22, "elapsed_time": "2:30:32", "remaining_time": "2:02:04"}
+{"current_steps": 555, "total_steps": 996, "loss": 0.736, "learning_rate": 4.175373019209468e-07, "epoch": 1.670428893905192, "percentage": 55.72, "elapsed_time": "2:31:38", "remaining_time": "2:00:29"}
+{"current_steps": 560, "total_steps": 996, "loss": 0.7271, "learning_rate": 4.0969167896463046e-07, "epoch": 1.6854778028592927, "percentage": 56.22, "elapsed_time": "2:32:44", "remaining_time": "1:58:55"}
+{"current_steps": 565, "total_steps": 996, "loss": 0.7381, "learning_rate": 4.018689754749648e-07, "epoch": 1.7005267118133935, "percentage": 56.73, "elapsed_time": "2:33:50", "remaining_time": "1:57:21"}
+{"current_steps": 570, "total_steps": 996, "loss": 0.7131, "learning_rate": 3.9407117678607756e-07, "epoch": 1.7155756207674944, "percentage": 57.23, "elapsed_time": "2:34:55", "remaining_time": "1:55:46"}
+{"current_steps": 575, "total_steps": 996, "loss": 0.7202, "learning_rate": 3.8630026191147405e-07, "epoch": 1.7306245297215952, "percentage": 57.73, "elapsed_time": "2:35:59", "remaining_time": "1:54:13"}
+{"current_steps": 580, "total_steps": 996, "loss": 0.7279, "learning_rate": 3.78558203041782e-07, "epoch": 1.745673438675696, "percentage": 58.23, "elapsed_time": "2:37:05", "remaining_time": "1:52:40"}
+{"current_steps": 585, "total_steps": 996, "loss": 0.7217, "learning_rate": 3.7084696504422525e-07, "epoch": 1.7607223476297968, "percentage": 58.73, "elapsed_time": "2:38:11", "remaining_time": "1:51:08"}
+{"current_steps": 590, "total_steps": 996, "loss": 0.7405, "learning_rate": 3.6316850496395855e-07, "epoch": 1.7757712565838977, "percentage": 59.24, "elapsed_time": "2:39:16", "remaining_time": "1:49:35"}
+{"current_steps": 595, "total_steps": 996, "loss": 0.7349, "learning_rate": 3.555247715273867e-07, "epoch": 1.7908201655379985, "percentage": 59.74, "elapsed_time": "2:40:21", "remaining_time": "1:48:04"}
+{"current_steps": 600, "total_steps": 996, "loss": 0.7176, "learning_rate": 3.4791770464759347e-07, "epoch": 1.8058690744920993, "percentage": 60.24, "elapsed_time": "2:41:26", "remaining_time": "1:46:32"}
+{"current_steps": 600, "total_steps": 996, "eval_loss": 0.7886707186698914, "epoch": 1.8058690744920993, "percentage": 60.24, "elapsed_time": "2:44:10", "remaining_time": "1:48:21"}
+{"current_steps": 605, "total_steps": 996, "loss": 0.7286, "learning_rate": 3.4034923493201007e-07, "epoch": 1.8209179834462002, "percentage": 60.74, "elapsed_time": "2:45:16", "remaining_time": "1:46:48"}
+{"current_steps": 610, "total_steps": 996, "loss": 0.7274, "learning_rate": 3.3282128319244237e-07, "epoch": 1.835966892400301, "percentage": 61.24, "elapsed_time": "2:46:21", "remaining_time": "1:45:16"}
+{"current_steps": 615, "total_steps": 996, "loss": 0.7503, "learning_rate": 3.2533575995758694e-07, "epoch": 1.8510158013544018, "percentage": 61.75, "elapsed_time": "2:47:26", "remaining_time": "1:43:43"}
+{"current_steps": 620, "total_steps": 996, "loss": 0.7278, "learning_rate": 3.178945649881543e-07, "epoch": 1.8660647103085026, "percentage": 62.25, "elapsed_time": "2:48:31", "remaining_time": "1:42:12"}
+{"current_steps": 625, "total_steps": 996, "loss": 0.7189, "learning_rate": 3.1049958679472645e-07, "epoch": 1.8811136192626035, "percentage": 62.75, "elapsed_time": "2:49:37", "remaining_time": "1:40:41"}
+{"current_steps": 630, "total_steps": 996, "loss": 0.7344, "learning_rate": 3.031527021584701e-07, "epoch": 1.8961625282167043, "percentage": 63.25, "elapsed_time": "2:50:43", "remaining_time": "1:39:10"}
+{"current_steps": 635, "total_steps": 996, "loss": 0.7278, "learning_rate": 2.9585577565482484e-07, "epoch": 1.911211437170805, "percentage": 63.76, "elapsed_time": "2:51:47", "remaining_time": "1:37:40"}
+{"current_steps": 640, "total_steps": 996, "loss": 0.7482, "learning_rate": 2.886106591802908e-07, "epoch": 1.926260346124906, "percentage": 64.26, "elapsed_time": "2:52:53", "remaining_time": "1:36:10"}
+{"current_steps": 645, "total_steps": 996, "loss": 0.71, "learning_rate": 2.814191914824332e-07, "epoch": 1.9413092550790068, "percentage": 64.76, "elapsed_time": "2:53:59", "remaining_time": "1:34:40"}
+{"current_steps": 650, "total_steps": 996, "loss": 0.7384, "learning_rate": 2.7428319769322415e-07, "epoch": 1.9563581640331076, "percentage": 65.26, "elapsed_time": "2:55:05", "remaining_time": "1:33:12"}
+{"current_steps": 650, "total_steps": 996, "eval_loss": 0.7857681512832642, "epoch": 1.9563581640331076, "percentage": 65.26, "elapsed_time": "2:57:49", "remaining_time": "1:34:39"}
+{"current_steps": 655, "total_steps": 996, "loss": 0.7152, "learning_rate": 2.672044888658399e-07, "epoch": 1.9714070729872084, "percentage": 65.76, "elapsed_time": "2:58:54", "remaining_time": "1:33:08"}
+{"current_steps": 660, "total_steps": 996, "loss": 0.715, "learning_rate": 2.6018486151503213e-07, "epoch": 1.9864559819413092, "percentage": 66.27, "elapsed_time": "2:59:59", "remaining_time": "1:31:38"}
+{"current_steps": 665, "total_steps": 996, "loss": 0.7306, "learning_rate": 2.532260971611867e-07, "epoch": 2.00150489089541, "percentage": 66.77, "elapsed_time": "3:01:04", "remaining_time": "1:30:07"}
+{"current_steps": 670, "total_steps": 996, "loss": 0.6819, "learning_rate": 2.4632996187819034e-07, "epoch": 2.016553799849511, "percentage": 67.27, "elapsed_time": "3:02:09", "remaining_time": "1:28:38"}
+{"current_steps": 675, "total_steps": 996, "loss": 0.6779, "learning_rate": 2.394982058452165e-07, "epoch": 2.0316027088036117, "percentage": 67.77, "elapsed_time": "3:03:14", "remaining_time": "1:27:08"}
+{"current_steps": 680, "total_steps": 996, "loss": 0.6818, "learning_rate": 2.3273256290254402e-07, "epoch": 2.0466516177577128, "percentage": 68.27, "elapsed_time": "3:04:21", "remaining_time": "1:25:40"}
+{"current_steps": 685, "total_steps": 996, "loss": 0.701, "learning_rate": 2.2603475011152517e-07, "epoch": 2.0617005267118134, "percentage": 68.78, "elapsed_time": "3:05:26", "remaining_time": "1:24:11"}
+{"current_steps": 690, "total_steps": 996, "loss": 0.6814, "learning_rate": 2.1940646731880885e-07, "epoch": 2.0767494356659144, "percentage": 69.28, "elapsed_time": "3:06:32", "remaining_time": "1:22:43"}
+{"current_steps": 695, "total_steps": 996, "loss": 0.6986, "learning_rate": 2.1284939672493506e-07, "epoch": 2.091798344620015, "percentage": 69.78, "elapsed_time": "3:07:37", "remaining_time": "1:21:15"}
+{"current_steps": 700, "total_steps": 996, "loss": 0.6877, "learning_rate": 2.0636520245740708e-07, "epoch": 2.106847253574116, "percentage": 70.28, "elapsed_time": "3:08:43", "remaining_time": "1:19:48"}
+{"current_steps": 700, "total_steps": 996, "eval_loss": 0.7906577587127686, "epoch": 2.106847253574116, "percentage": 70.28, "elapsed_time": "3:11:27", "remaining_time": "1:20:57"}
+{"current_steps": 705, "total_steps": 996, "loss": 0.6616, "learning_rate": 1.9995553014834986e-07, "epoch": 2.1218961625282167, "percentage": 70.78, "elapsed_time": "3:12:33", "remaining_time": "1:19:28"}
+{"current_steps": 710, "total_steps": 996, "loss": 0.6807, "learning_rate": 1.9362200651686406e-07, "epoch": 2.1369450714823177, "percentage": 71.29, "elapsed_time": "3:13:38", "remaining_time": "1:18:00"}
+{"current_steps": 715, "total_steps": 996, "loss": 0.6789, "learning_rate": 1.873662389561771e-07, "epoch": 2.1519939804364183, "percentage": 71.79, "elapsed_time": "3:14:44", "remaining_time": "1:16:31"}
+{"current_steps": 720, "total_steps": 996, "loss": 0.6798, "learning_rate": 1.8118981512570254e-07, "epoch": 2.1670428893905194, "percentage": 72.29, "elapsed_time": "3:15:49", "remaining_time": "1:15:04"}
+{"current_steps": 725, "total_steps": 996, "loss": 0.6752, "learning_rate": 1.750943025481046e-07, "epoch": 2.18209179834462, "percentage": 72.79, "elapsed_time": "3:16:55", "remaining_time": "1:13:36"}
+{"current_steps": 730, "total_steps": 996, "loss": 0.6593, "learning_rate": 1.6908124821147517e-07, "epoch": 2.197140707298721, "percentage": 73.29, "elapsed_time": "3:18:00", "remaining_time": "1:12:09"}
+{"current_steps": 735, "total_steps": 996, "loss": 0.6708, "learning_rate": 1.631521781767214e-07, "epoch": 2.2121896162528216, "percentage": 73.8, "elapsed_time": "3:19:06", "remaining_time": "1:10:42"}
+{"current_steps": 740, "total_steps": 996, "loss": 0.67, "learning_rate": 1.5730859719026535e-07, "epoch": 2.2272385252069227, "percentage": 74.3, "elapsed_time": "3:20:12", "remaining_time": "1:09:15"}
+{"current_steps": 745, "total_steps": 996, "loss": 0.668, "learning_rate": 1.5155198830215144e-07, "epoch": 2.2422874341610233, "percentage": 74.8, "elapsed_time": "3:21:18", "remaining_time": "1:07:49"}
+{"current_steps": 750, "total_steps": 996, "loss": 0.6796, "learning_rate": 1.4588381248966185e-07, "epoch": 2.2573363431151243, "percentage": 75.3, "elapsed_time": "3:22:23", "remaining_time": "1:06:23"}
+{"current_steps": 750, "total_steps": 996, "eval_loss": 0.7899430990219116, "epoch": 2.2573363431151243, "percentage": 75.3, "elapsed_time": "3:25:08", "remaining_time": "1:07:17"}
+{"current_steps": 755, "total_steps": 996, "loss": 0.6911, "learning_rate": 1.4030550828653354e-07, "epoch": 2.272385252069225, "percentage": 75.8, "elapsed_time": "3:26:12", "remaining_time": "1:05:49"}
+{"current_steps": 760, "total_steps": 996, "loss": 0.6795, "learning_rate": 1.3481849141786977e-07, "epoch": 2.287434161023326, "percentage": 76.31, "elapsed_time": "3:27:17", "remaining_time": "1:04:22"}
+{"current_steps": 765, "total_steps": 996, "loss": 0.6694, "learning_rate": 1.294241544408425e-07, "epoch": 2.3024830699774266, "percentage": 76.81, "elapsed_time": "3:28:23", "remaining_time": "1:02:55"}
+{"current_steps": 770, "total_steps": 996, "loss": 0.7048, "learning_rate": 1.241238663912727e-07, "epoch": 2.3175319789315276, "percentage": 77.31, "elapsed_time": "3:29:29", "remaining_time": "1:01:29"}
+{"current_steps": 775, "total_steps": 996, "loss": 0.6814, "learning_rate": 1.1891897243618183e-07, "epoch": 2.3325808878856282, "percentage": 77.81, "elapsed_time": "3:30:34", "remaining_time": "1:00:02"}
+{"current_steps": 780, "total_steps": 996, "loss": 0.6822, "learning_rate": 1.1381079353239915e-07, "epoch": 2.3476297968397293, "percentage": 78.31, "elapsed_time": "3:31:40", "remaining_time": "0:58:36"}
+{"current_steps": 785, "total_steps": 996, "loss": 0.689, "learning_rate": 1.0880062609131485e-07, "epoch": 2.36267870579383, "percentage": 78.82, "elapsed_time": "3:32:45", "remaining_time": "0:57:11"}
+{"current_steps": 790, "total_steps": 996, "loss": 0.6743, "learning_rate": 1.0388974164986247e-07, "epoch": 2.377727614747931, "percentage": 79.32, "elapsed_time": "3:33:50", "remaining_time": "0:55:45"}
+{"current_steps": 795, "total_steps": 996, "loss": 0.6926, "learning_rate": 9.907938654781306e-08, "epoch": 2.3927765237020315, "percentage": 79.82, "elapsed_time": "3:34:56", "remaining_time": "0:54:20"}
+{"current_steps": 800, "total_steps": 996, "loss": 0.6837, "learning_rate": 9.437078161146589e-08, "epoch": 2.4078254326561326, "percentage": 80.32, "elapsed_time": "3:36:01", "remaining_time": "0:52:55"}
+{"current_steps": 800, "total_steps": 996, "eval_loss": 0.788821280002594, "epoch": 2.4078254326561326, "percentage": 80.32, "elapsed_time": "3:38:46", "remaining_time": "0:53:35"}
+{"current_steps": 805, "total_steps": 996, "loss": 0.6791, "learning_rate": 8.976512184381246e-08, "epoch": 2.422874341610233, "percentage": 80.82, "elapsed_time": "3:39:50", "remaining_time": "0:52:09"}
+{"current_steps": 810, "total_steps": 996, "loss": 0.6858, "learning_rate": 8.526357612125573e-08, "epoch": 2.4379232505643342, "percentage": 81.33, "elapsed_time": "3:40:56", "remaining_time": "0:50:44"}
+{"current_steps": 815, "total_steps": 996, "loss": 0.6946, "learning_rate": 8.086728689695921e-08, "epoch": 2.452972159518435, "percentage": 81.83, "elapsed_time": "3:42:02", "remaining_time": "0:49:18"}
+{"current_steps": 820, "total_steps": 996, "loss": 0.6841, "learning_rate": 7.657736991090263e-08, "epoch": 2.468021068472536, "percentage": 82.33, "elapsed_time": "3:43:06", "remaining_time": "0:47:53"}
+{"current_steps": 825, "total_steps": 996, "loss": 0.6812, "learning_rate": 7.239491390671631e-08, "epoch": 2.4830699774266365, "percentage": 82.83, "elapsed_time": "3:44:12", "remaining_time": "0:46:28"}
+{"current_steps": 830, "total_steps": 996, "loss": 0.6757, "learning_rate": 6.832098035536759e-08, "epoch": 2.4981188863807375, "percentage": 83.33, "elapsed_time": "3:45:17", "remaining_time": "0:45:03"}
+{"current_steps": 835, "total_steps": 996, "loss": 0.6754, "learning_rate": 6.435660318576935e-08, "epoch": 2.513167795334838, "percentage": 83.84, "elapsed_time": "3:46:23", "remaining_time": "0:43:39"}
+{"current_steps": 840, "total_steps": 996, "loss": 0.6729, "learning_rate": 6.0502788522377e-08, "epoch": 2.528216704288939, "percentage": 84.34, "elapsed_time": "3:47:29", "remaining_time": "0:42:14"}
+{"current_steps": 845, "total_steps": 996, "loss": 0.6832, "learning_rate": 5.676051442984325e-08, "epoch": 2.54326561324304, "percentage": 84.84, "elapsed_time": "3:48:34", "remaining_time": "0:40:50"}
+{"current_steps": 850, "total_steps": 996, "loss": 0.6653, "learning_rate": 5.313073066479379e-08, "epoch": 2.558314522197141, "percentage": 85.34, "elapsed_time": "3:49:40", "remaining_time": "0:39:26"}
+{"current_steps": 850, "total_steps": 996, "eval_loss": 0.7885056138038635, "epoch": 2.558314522197141, "percentage": 85.34, "elapsed_time": "3:52:24", "remaining_time": "0:39:55"}
+{"current_steps": 855, "total_steps": 996, "loss": 0.6845, "learning_rate": 4.961435843478751e-08, "epoch": 2.5733634311512414, "percentage": 85.84, "elapsed_time": "3:53:28", "remaining_time": "0:38:30"}
+{"current_steps": 860, "total_steps": 996, "loss": 0.6734, "learning_rate": 4.621229016452155e-08, "epoch": 2.5884123401053425, "percentage": 86.35, "elapsed_time": "3:54:33", "remaining_time": "0:37:05"}
+{"current_steps": 865, "total_steps": 996, "loss": 0.6777, "learning_rate": 4.2925389269341916e-08, "epoch": 2.603461249059443, "percentage": 86.85, "elapsed_time": "3:55:39", "remaining_time": "0:35:41"}
+{"current_steps": 870, "total_steps": 996, "loss": 0.6719, "learning_rate": 3.975448993611652e-08, "epoch": 2.618510158013544, "percentage": 87.35, "elapsed_time": "3:56:45", "remaining_time": "0:34:17"}
+{"current_steps": 875, "total_steps": 996, "loss": 0.6779, "learning_rate": 3.67003969115251e-08, "epoch": 2.6335590669676447, "percentage": 87.85, "elapsed_time": "3:57:49", "remaining_time": "0:32:53"}
+{"current_steps": 880, "total_steps": 996, "loss": 0.6781, "learning_rate": 3.376388529782215e-08, "epoch": 2.648607975921746, "percentage": 88.35, "elapsed_time": "3:58:55", "remaining_time": "0:31:29"}
+{"current_steps": 885, "total_steps": 996, "loss": 0.6942, "learning_rate": 3.094570035612226e-08, "epoch": 2.6636568848758464, "percentage": 88.86, "elapsed_time": "4:00:00", "remaining_time": "0:30:06"}
+{"current_steps": 890, "total_steps": 996, "loss": 0.6914, "learning_rate": 2.8246557317259723e-08, "epoch": 2.6787057938299474, "percentage": 89.36, "elapsed_time": "4:01:05", "remaining_time": "0:28:42"}
+{"current_steps": 895, "total_steps": 996, "loss": 0.6892, "learning_rate": 2.5667141200268694e-08, "epoch": 2.693754702784048, "percentage": 89.86, "elapsed_time": "4:02:10", "remaining_time": "0:27:19"}
+{"current_steps": 900, "total_steps": 996, "loss": 0.6563, "learning_rate": 2.3208106638531842e-08, "epoch": 2.708803611738149, "percentage": 90.36, "elapsed_time": "4:03:14", "remaining_time": "0:25:56"}
+{"current_steps": 900, "total_steps": 996, "eval_loss": 0.7879343032836914, "epoch": 2.708803611738149, "percentage": 90.36, "elapsed_time": "4:05:59", "remaining_time": "0:26:14"}
+{"current_steps": 905, "total_steps": 996, "loss": 0.6736, "learning_rate": 2.087007771363969e-08, "epoch": 2.7238525206922497, "percentage": 90.86, "elapsed_time": "4:07:04", "remaining_time": "0:24:50"}
+{"current_steps": 910, "total_steps": 996, "loss": 0.6797, "learning_rate": 1.8653647797004236e-08, "epoch": 2.7389014296463507, "percentage": 91.37, "elapsed_time": "4:08:09", "remaining_time": "0:23:27"}
+{"current_steps": 915, "total_steps": 996, "loss": 0.6666, "learning_rate": 1.655937939926655e-08, "epoch": 2.7539503386004514, "percentage": 91.87, "elapsed_time": "4:09:14", "remaining_time": "0:22:03"}
+{"current_steps": 920, "total_steps": 996, "loss": 0.6797, "learning_rate": 1.4587804027536454e-08, "epoch": 2.7689992475545524, "percentage": 92.37, "elapsed_time": "4:10:20", "remaining_time": "0:20:40"}
+{"current_steps": 925, "total_steps": 996, "loss": 0.6643, "learning_rate": 1.2739422050500436e-08, "epoch": 2.784048156508653, "percentage": 92.87, "elapsed_time": "4:11:25", "remaining_time": "0:19:17"}
+{"current_steps": 930, "total_steps": 996, "loss": 0.6811, "learning_rate": 1.101470257143261e-08, "epoch": 2.799097065462754, "percentage": 93.37, "elapsed_time": "4:12:31", "remaining_time": "0:17:55"}
+{"current_steps": 935, "total_steps": 996, "loss": 0.691, "learning_rate": 9.414083309140453e-09, "epoch": 2.8141459744168547, "percentage": 93.88, "elapsed_time": "4:13:36", "remaining_time": "0:16:32"}
+{"current_steps": 940, "total_steps": 996, "loss": 0.6758, "learning_rate": 7.93797048687539e-09, "epoch": 2.8291948833709557, "percentage": 94.38, "elapsed_time": "4:14:41", "remaining_time": "0:15:10"}
+{"current_steps": 945, "total_steps": 996, "loss": 0.6712, "learning_rate": 6.5867387292369295e-09, "epoch": 2.8442437923250563, "percentage": 94.88, "elapsed_time": "4:15:45", "remaining_time": "0:13:48"}
+{"current_steps": 950, "total_steps": 996, "loss": 0.6829, "learning_rate": 5.360730967096272e-09, "epoch": 2.8592927012791574, "percentage": 95.38, "elapsed_time": "4:16:51", "remaining_time": "0:12:26"}
+{"current_steps": 950, "total_steps": 996, "eval_loss": 0.7878710031509399, "epoch": 2.8592927012791574, "percentage": 95.38, "elapsed_time": "4:19:35", "remaining_time": "0:12:34"}
+{"current_steps": 955, "total_steps": 996, "loss": 0.6704, "learning_rate": 4.260258350563317e-09, "epoch": 2.874341610233258, "percentage": 95.88, "elapsed_time": "4:20:41", "remaining_time": "0:11:11"}
+{"current_steps": 960, "total_steps": 996, "loss": 0.6802, "learning_rate": 3.285600170019609e-09, "epoch": 2.889390519187359, "percentage": 96.39, "elapsed_time": "4:21:47", "remaining_time": "0:09:49"}
+{"current_steps": 965, "total_steps": 996, "loss": 0.6778, "learning_rate": 2.437003785236702e-09, "epoch": 2.9044394281414596, "percentage": 96.89, "elapsed_time": "4:22:51", "remaining_time": "0:08:26"}
+{"current_steps": 970, "total_steps": 996, "loss": 0.6714, "learning_rate": 1.714684562598545e-09, "epoch": 2.9194883370955607, "percentage": 97.39, "elapsed_time": "4:23:56", "remaining_time": "0:07:04"}
+{"current_steps": 975, "total_steps": 996, "loss": 0.6755, "learning_rate": 1.1188258204433144e-09, "epoch": 2.9345372460496613, "percentage": 97.89, "elapsed_time": "4:25:02", "remaining_time": "0:05:42"}
+{"current_steps": 980, "total_steps": 996, "loss": 0.6792, "learning_rate": 6.49578782538851e-10, "epoch": 2.9495861550037623, "percentage": 98.39, "elapsed_time": "4:26:07", "remaining_time": "0:04:20"}
+{"current_steps": 985, "total_steps": 996, "loss": 0.6723, "learning_rate": 3.070625397031401e-10, "epoch": 2.964635063957863, "percentage": 98.9, "elapsed_time": "4:27:13", "remaining_time": "0:02:59"}
+{"current_steps": 990, "total_steps": 996, "loss": 0.6766, "learning_rate": 9.136401958059759e-11, "epoch": 2.979683972911964, "percentage": 99.4, "elapsed_time": "4:28:18", "remaining_time": "0:01:37"}
+{"current_steps": 995, "total_steps": 996, "loss": 0.6835, "learning_rate": 2.5379645800516215e-12, "epoch": 2.9947328818660646, "percentage": 99.9, "elapsed_time": "4:29:24", "remaining_time": "0:00:16"}
+{"current_steps": 996, "total_steps": 996, "epoch": 2.9977426636568847, "percentage": 100.0, "elapsed_time": "4:30:10", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1587 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9977426636568847,
+  "eval_steps": 50,
+  "global_step": 996,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015048908954100828,
+      "grad_norm": 18.3067113765928,
+      "learning_rate": 5e-07,
+      "loss": 1.7267,
+      "step": 5
+    },
+    {
+      "epoch": 0.030097817908201655,
+      "grad_norm": 12.425894386937017,
+      "learning_rate": 1e-06,
+      "loss": 1.5935,
+      "step": 10
+    },
+    {
+      "epoch": 0.045146726862302484,
+      "grad_norm": 7.656122541492926,
+      "learning_rate": 9.999365521737421e-07,
+      "loss": 1.2846,
+      "step": 15
+    },
+    {
+      "epoch": 0.06019563581640331,
+      "grad_norm": 4.2346112922619135,
+      "learning_rate": 9.99746224797475e-07,
+      "loss": 1.147,
+      "step": 20
+    },
+    {
+      "epoch": 0.07524454477050414,
+      "grad_norm": 3.7327484351825992,
+      "learning_rate": 9.99429066174632e-07,
+      "loss": 1.0702,
+      "step": 25
+    },
+    {
+      "epoch": 0.09029345372460497,
+      "grad_norm": 3.53430215111439,
+      "learning_rate": 9.989851567973138e-07,
+      "loss": 1.0299,
+      "step": 30
+    },
+    {
+      "epoch": 0.1053423626787058,
+      "grad_norm": 3.65219200982227,
+      "learning_rate": 9.984146093258608e-07,
+      "loss": 0.996,
+      "step": 35
+    },
+    {
+      "epoch": 0.12039127163280662,
+      "grad_norm": 3.475510536585853,
+      "learning_rate": 9.9771756856026e-07,
+      "loss": 0.9736,
+      "step": 40
+    },
+    {
+      "epoch": 0.13544018058690746,
+      "grad_norm": 3.5641491900715456,
+      "learning_rate": 9.968942114033973e-07,
+      "loss": 0.9431,
+      "step": 45
+    },
+    {
+      "epoch": 0.1504890895410083,
+      "grad_norm": 3.310177183723562,
+      "learning_rate": 9.959447468161596e-07,
+      "loss": 0.9273,
+      "step": 50
+    },
+    {
+      "epoch": 0.1504890895410083,
+      "eval_loss": 0.936109185218811,
+      "eval_runtime": 166.5093,
+      "eval_samples_per_second": 56.754,
+      "eval_steps_per_second": 0.889,
+      "step": 50
+    },
+    {
+      "epoch": 0.1655379984951091,
+      "grad_norm": 3.7634083628541792,
+      "learning_rate": 9.948694157644042e-07,
+      "loss": 0.9287,
+      "step": 55
+    },
+    {
+      "epoch": 0.18058690744920994,
+      "grad_norm": 3.4603396193970557,
+      "learning_rate": 9.936684911578017e-07,
+      "loss": 0.9232,
+      "step": 60
+    },
+    {
+      "epoch": 0.19563581640331076,
+      "grad_norm": 3.709365715188229,
+      "learning_rate": 9.923422777805751e-07,
+      "loss": 0.9329,
+      "step": 65
+    },
+    {
+      "epoch": 0.2106847253574116,
+      "grad_norm": 3.3261104359806892,
+      "learning_rate": 9.908911122141486e-07,
+      "loss": 0.8932,
+      "step": 70
+    },
+    {
+      "epoch": 0.22573363431151242,
+      "grad_norm": 3.333593966518852,
+      "learning_rate": 9.893153627517248e-07,
+      "loss": 0.8696,
+      "step": 75
+    },
+    {
+      "epoch": 0.24078254326561324,
+      "grad_norm": 3.75439485313761,
+      "learning_rate": 9.876154293048163e-07,
+      "loss": 0.8977,
+      "step": 80
+    },
+    {
+      "epoch": 0.2558314522197141,
+      "grad_norm": 3.665753400039767,
+      "learning_rate": 9.857917433017508e-07,
+      "loss": 0.8997,
+      "step": 85
+    },
+    {
+      "epoch": 0.2708803611738149,
+      "grad_norm": 3.8591465347932377,
+      "learning_rate": 9.838447675781793e-07,
+      "loss": 0.8567,
+      "step": 90
+    },
+    {
+      "epoch": 0.28592927012791575,
+      "grad_norm": 3.4759441065159047,
+      "learning_rate": 9.817749962596114e-07,
+      "loss": 0.8692,
+      "step": 95
+    },
+    {
+      "epoch": 0.3009781790820166,
+      "grad_norm": 3.5256398646315157,
+      "learning_rate": 9.795829546360113e-07,
+      "loss": 0.8938,
+      "step": 100
+    },
+    {
+      "epoch": 0.3009781790820166,
+      "eval_loss": 0.8804982900619507,
+      "eval_runtime": 165.1088,
+      "eval_samples_per_second": 57.235,
+      "eval_steps_per_second": 0.896,
+      "step": 100
+    },
+    {
+      "epoch": 0.3160270880361174,
+      "grad_norm": 3.1624855062390287,
+      "learning_rate": 9.77269199028483e-07,
+      "loss": 0.8744,
+      "step": 105
+    },
+    {
+      "epoch": 0.3310759969902182,
+      "grad_norm": 3.483610150725716,
+      "learning_rate": 9.748343166480822e-07,
+      "loss": 0.8506,
+      "step": 110
+    },
+    {
+      "epoch": 0.34612490594431905,
+      "grad_norm": 3.530971931358358,
+      "learning_rate": 9.722789254467854e-07,
+      "loss": 0.8583,
+      "step": 115
+    },
+    {
+      "epoch": 0.3611738148984199,
+      "grad_norm": 3.6587864102748275,
+      "learning_rate": 9.696036739606606e-07,
+      "loss": 0.8699,
+      "step": 120
+    },
+    {
+      "epoch": 0.3762227238525207,
+      "grad_norm": 3.559601017867941,
+      "learning_rate": 9.668092411452735e-07,
+      "loss": 0.87,
+      "step": 125
+    },
+    {
+      "epoch": 0.3912716328066215,
+      "grad_norm": 3.470737417836157,
+      "learning_rate": 9.638963362033756e-07,
+      "loss": 0.8627,
+      "step": 130
+    },
+    {
+      "epoch": 0.40632054176072235,
+      "grad_norm": 3.688913494188485,
+      "learning_rate": 9.608656984049132e-07,
+      "loss": 0.842,
+      "step": 135
+    },
+    {
+      "epoch": 0.4213694507148232,
+      "grad_norm": 3.5434282594897843,
+      "learning_rate": 9.577180968994081e-07,
+      "loss": 0.8367,
+      "step": 140
+    },
+    {
+      "epoch": 0.436418359668924,
+      "grad_norm": 3.5450302290364517,
+      "learning_rate": 9.544543305207546e-07,
+      "loss": 0.8565,
+      "step": 145
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "grad_norm": 3.6995845437807677,
+      "learning_rate": 9.510752275844809e-07,
+      "loss": 0.8476,
+      "step": 150
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "eval_loss": 0.8552336692810059,
+      "eval_runtime": 164.2631,
+      "eval_samples_per_second": 57.53,
+      "eval_steps_per_second": 0.901,
+      "step": 150
+    },
+    {
+      "epoch": 0.46651617757712566,
+      "grad_norm": 3.5832071794600626,
+      "learning_rate": 9.475816456775312e-07,
+      "loss": 0.8419,
+      "step": 155
+    },
+    {
+      "epoch": 0.4815650865312265,
+      "grad_norm": 3.4551108533194355,
+      "learning_rate": 9.439744714406166e-07,
+      "loss": 0.8571,
+      "step": 160
+    },
+    {
+      "epoch": 0.4966139954853273,
+      "grad_norm": 3.463691802146643,
+      "learning_rate": 9.402546203431947e-07,
+      "loss": 0.8552,
+      "step": 165
+    },
+    {
+      "epoch": 0.5116629044394282,
+      "grad_norm": 3.6122617820665965,
+      "learning_rate": 9.364230364511295e-07,
+      "loss": 0.8284,
+      "step": 170
+    },
+    {
+      "epoch": 0.526711813393529,
+      "grad_norm": 3.5227479646686626,
+      "learning_rate": 9.324806921870975e-07,
+      "loss": 0.8445,
+      "step": 175
+    },
+    {
+      "epoch": 0.5417607223476298,
+      "grad_norm": 3.1608919125871213,
+      "learning_rate": 9.284285880837946e-07,
+      "loss": 0.8467,
+      "step": 180
+    },
+    {
+      "epoch": 0.5568096313017307,
+      "grad_norm": 3.397778366526389,
+      "learning_rate": 9.242677525300088e-07,
+      "loss": 0.8444,
+      "step": 185
+    },
+    {
+      "epoch": 0.5718585402558315,
+      "grad_norm": 3.623712344003,
+      "learning_rate": 9.199992415096259e-07,
+      "loss": 0.8329,
+      "step": 190
+    },
+    {
+      "epoch": 0.5869074492099323,
+      "grad_norm": 3.6817969267423,
+      "learning_rate": 9.156241383336278e-07,
+      "loss": 0.8393,
+      "step": 195
+    },
+    {
+      "epoch": 0.6019563581640331,
+      "grad_norm": 3.7179065033691803,
+      "learning_rate": 9.111435533651595e-07,
+      "loss": 0.8413,
+      "step": 200
+    },
+    {
+      "epoch": 0.6019563581640331,
+      "eval_loss": 0.8378457427024841,
+      "eval_runtime": 164.1905,
+      "eval_samples_per_second": 57.555,
+      "eval_steps_per_second": 0.901,
+      "step": 200
+    },
+    {
+      "epoch": 0.617005267118134,
+      "grad_norm": 3.461402352739981,
+      "learning_rate": 9.065586237377274e-07,
+      "loss": 0.8383,
+      "step": 205
+    },
+    {
+      "epoch": 0.6320541760722348,
+      "grad_norm": 3.6508042748668013,
+      "learning_rate": 9.018705130666049e-07,
+      "loss": 0.846,
+      "step": 210
+    },
+    {
+      "epoch": 0.6471030850263356,
+      "grad_norm": 3.860811653516243,
+      "learning_rate": 8.970804111535175e-07,
+      "loss": 0.8348,
+      "step": 215
+    },
+    {
+      "epoch": 0.6621519939804364,
+      "grad_norm": 3.503371889729855,
+      "learning_rate": 8.921895336846812e-07,
+      "loss": 0.8237,
+      "step": 220
+    },
+    {
+      "epoch": 0.6772009029345373,
+      "grad_norm": 3.534504520782972,
+      "learning_rate": 8.871991219222712e-07,
+      "loss": 0.8363,
+      "step": 225
+    },
+    {
+      "epoch": 0.6922498118886381,
+      "grad_norm": 3.4768514044708128,
+      "learning_rate": 8.821104423894014e-07,
+      "loss": 0.8115,
+      "step": 230
+    },
+    {
+      "epoch": 0.7072987208427389,
+      "grad_norm": 3.364918499512913,
+      "learning_rate": 8.769247865486915e-07,
+      "loss": 0.8129,
+      "step": 235
+    },
+    {
+      "epoch": 0.7223476297968398,
+      "grad_norm": 3.76176938510827,
+      "learning_rate": 8.716434704745046e-07,
+      "loss": 0.8243,
+      "step": 240
+    },
+    {
+      "epoch": 0.7373965387509406,
+      "grad_norm": 3.4565749939546704,
+      "learning_rate": 8.662678345189396e-07,
+      "loss": 0.8394,
+      "step": 245
+    },
+    {
+      "epoch": 0.7524454477050414,
+      "grad_norm": 3.246463585410726,
+      "learning_rate": 8.607992429716608e-07,
+      "loss": 0.8254,
+      "step": 250
+    },
+    {
+      "epoch": 0.7524454477050414,
+      "eval_loss": 0.8255200982093811,
+      "eval_runtime": 164.5909,
+      "eval_samples_per_second": 57.415,
+      "eval_steps_per_second": 0.899,
+      "step": 250
+    },
+    {
+      "epoch": 0.7674943566591422,
+      "grad_norm": 3.5687284671280004,
+      "learning_rate": 8.55239083713654e-07,
+      "loss": 0.8209,
+      "step": 255
+    },
+    {
+      "epoch": 0.782543265613243,
+      "grad_norm": 3.309161579948898,
+      "learning_rate": 8.495887678649932e-07,
+      "loss": 0.8235,
+      "step": 260
+    },
+    {
+      "epoch": 0.7975921745673439,
+      "grad_norm": 3.6601438215929787,
+      "learning_rate": 8.438497294267116e-07,
+      "loss": 0.8148,
+      "step": 265
+    },
+    {
+      "epoch": 0.8126410835214447,
+      "grad_norm": 3.424592236767194,
+      "learning_rate": 8.38023424916864e-07,
+      "loss": 0.8237,
+      "step": 270
+    },
+    {
+      "epoch": 0.8276899924755455,
+      "grad_norm": 3.658233989032351,
+      "learning_rate": 8.321113330008756e-07,
+      "loss": 0.8199,
+      "step": 275
+    },
+    {
+      "epoch": 0.8427389014296464,
+      "grad_norm": 3.6686108116776386,
+      "learning_rate": 8.261149541162691e-07,
+      "loss": 0.8198,
+      "step": 280
+    },
+    {
+      "epoch": 0.8577878103837472,
+      "grad_norm": 3.564688018245365,
+      "learning_rate": 8.20035810091867e-07,
+      "loss": 0.833,
+      "step": 285
+    },
+    {
+      "epoch": 0.872836719337848,
+      "grad_norm": 3.4267054682208222,
+      "learning_rate": 8.13875443761565e-07,
+      "loss": 0.8336,
+      "step": 290
+    },
+    {
+      "epoch": 0.8878856282919488,
+      "grad_norm": 3.625662003888318,
+      "learning_rate": 8.076354185727734e-07,
+      "loss": 0.8211,
+      "step": 295
+    },
+    {
+      "epoch": 0.9029345372460497,
+      "grad_norm": 3.659547833287384,
+      "learning_rate": 8.013173181896282e-07,
+      "loss": 0.8091,
+      "step": 300
+    },
+    {
+      "epoch": 0.9029345372460497,
+      "eval_loss": 0.8148868680000305,
+      "eval_runtime": 164.4984,
+      "eval_samples_per_second": 57.447,
+      "eval_steps_per_second": 0.9,
+      "step": 300
+    },
+    {
+      "epoch": 0.9179834462001505,
+      "grad_norm": 3.415432660275148,
+      "learning_rate": 7.94922746091071e-07,
+      "loss": 0.8271,
+      "step": 305
+    },
+    {
+      "epoch": 0.9330323551542513,
+      "grad_norm": 3.433626617159138,
+      "learning_rate": 7.884533251638999e-07,
+      "loss": 0.7997,
+      "step": 310
+    },
+    {
+      "epoch": 0.9480812641083521,
+      "grad_norm": 3.4616411740611226,
+      "learning_rate": 7.819106972908949e-07,
+      "loss": 0.8131,
+      "step": 315
+    },
+    {
+      "epoch": 0.963130173062453,
+      "grad_norm": 3.595962547526837,
+      "learning_rate": 7.752965229341219e-07,
+      "loss": 0.8244,
+      "step": 320
+    },
+    {
+      "epoch": 0.9781790820165538,
+      "grad_norm": 3.5100709203373666,
+      "learning_rate": 7.686124807135228e-07,
+      "loss": 0.8056,
+      "step": 325
+    },
+    {
+      "epoch": 0.9932279909706546,
+      "grad_norm": 3.7018983277934456,
+      "learning_rate": 7.618602669808957e-07,
+      "loss": 0.8193,
+      "step": 330
+    },
+    {
+      "epoch": 1.0082768999247556,
+      "grad_norm": 3.5410406166783015,
+      "learning_rate": 7.550415953893756e-07,
+      "loss": 0.781,
+      "step": 335
+    },
+    {
+      "epoch": 1.0233258088788564,
+      "grad_norm": 3.576616810803158,
+      "learning_rate": 7.481581964585244e-07,
+      "loss": 0.7508,
+      "step": 340
+    },
+    {
+      "epoch": 1.0383747178329572,
+      "grad_norm": 3.5692261780454806,
+      "learning_rate": 7.412118171351395e-07,
+      "loss": 0.7483,
+      "step": 345
+    },
+    {
+      "epoch": 1.053423626787058,
+      "grad_norm": 3.364552676871854,
+      "learning_rate": 7.342042203498951e-07,
+      "loss": 0.7271,
+      "step": 350
+    },
+    {
+      "epoch": 1.053423626787058,
+      "eval_loss": 0.8104769587516785,
+      "eval_runtime": 164.6059,
+      "eval_samples_per_second": 57.41,
+      "eval_steps_per_second": 0.899,
+      "step": 350
+    },
+    {
+      "epoch": 1.0684725357411589,
+      "grad_norm": 3.5560550995930544,
+      "learning_rate": 7.271371845699241e-07,
+      "loss": 0.7538,
+      "step": 355
+    },
+    {
+      "epoch": 1.0835214446952597,
+      "grad_norm": 3.6783603046250546,
+      "learning_rate": 7.200125033474598e-07,
+      "loss": 0.7428,
+      "step": 360
+    },
+    {
+      "epoch": 1.0985703536493605,
+      "grad_norm": 3.4366708935207977,
+      "learning_rate": 7.128319848646477e-07,
+      "loss": 0.7528,
+      "step": 365
+    },
+    {
+      "epoch": 1.1136192626034613,
+      "grad_norm": 3.5209701182053026,
+      "learning_rate": 7.055974514746445e-07,
+      "loss": 0.7583,
+      "step": 370
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "grad_norm": 3.7508612585686234,
+      "learning_rate": 6.983107392391202e-07,
+      "loss": 0.7333,
+      "step": 375
+    },
+    {
+      "epoch": 1.143717080511663,
+      "grad_norm": 3.804536934008722,
+      "learning_rate": 6.909736974622826e-07,
+      "loss": 0.7367,
+      "step": 380
+    },
+    {
+      "epoch": 1.1587659894657638,
+      "grad_norm": 3.380810090226087,
+      "learning_rate": 6.835881882215395e-07,
+      "loss": 0.7389,
+      "step": 385
+    },
+    {
+      "epoch": 1.1738148984198646,
+      "grad_norm": 3.50522357566982,
+      "learning_rate": 6.761560858949192e-07,
+      "loss": 0.7272,
+      "step": 390
+    },
+    {
+      "epoch": 1.1888638073739655,
+      "grad_norm": 3.8495609198880003,
+      "learning_rate": 6.686792766853705e-07,
+      "loss": 0.7411,
+      "step": 395
+    },
+    {
+      "epoch": 1.2039127163280663,
+      "grad_norm": 3.4673446441183264,
+      "learning_rate": 6.611596581420599e-07,
+      "loss": 0.7383,
+      "step": 400
+    },
+    {
+      "epoch": 1.2039127163280663,
+      "eval_loss": 0.8055551648139954,
+      "eval_runtime": 164.521,
+      "eval_samples_per_second": 57.439,
+      "eval_steps_per_second": 0.9,
+      "step": 400
+    },
+    {
+      "epoch": 1.2189616252821671,
+      "grad_norm": 3.703622757288821,
+      "learning_rate": 6.53599138678791e-07,
+      "loss": 0.7447,
+      "step": 405
+    },
+    {
+      "epoch": 1.234010534236268,
+      "grad_norm": 3.5785402373111386,
+      "learning_rate": 6.459996370896652e-07,
+      "loss": 0.7143,
+      "step": 410
+    },
+    {
+      "epoch": 1.2490594431903688,
+      "grad_norm": 3.5402461359971684,
+      "learning_rate": 6.383630820621081e-07,
+      "loss": 0.7486,
+      "step": 415
+    },
+    {
+      "epoch": 1.2641083521444696,
+      "grad_norm": 3.243470804610217,
+      "learning_rate": 6.306914116873862e-07,
+      "loss": 0.7428,
+      "step": 420
+    },
+    {
+      "epoch": 1.2791572610985704,
+      "grad_norm": 3.431888635712123,
+      "learning_rate": 6.22986572968736e-07,
+      "loss": 0.7466,
+      "step": 425
+    },
+    {
+      "epoch": 1.2942061700526712,
+      "grad_norm": 3.6294844548998335,
+      "learning_rate": 6.152505213272307e-07,
+      "loss": 0.7568,
+      "step": 430
+    },
+    {
+      "epoch": 1.309255079006772,
+      "grad_norm": 3.5614062494190653,
+      "learning_rate": 6.074852201055121e-07,
+      "loss": 0.7345,
+      "step": 435
+    },
+    {
+      "epoch": 1.324303987960873,
+      "grad_norm": 3.3812248567300762,
+      "learning_rate": 5.996926400695113e-07,
+      "loss": 0.7423,
+      "step": 440
+    },
+    {
+      "epoch": 1.3393528969149737,
+      "grad_norm": 3.641361393772205,
+      "learning_rate": 5.918747589082852e-07,
+      "loss": 0.7435,
+      "step": 445
+    },
+    {
+      "epoch": 1.3544018058690745,
+      "grad_norm": 3.6883754790740704,
+      "learning_rate": 5.840335607320963e-07,
+      "loss": 0.7543,
+      "step": 450
+    },
+    {
+      "epoch": 1.3544018058690745,
+      "eval_loss": 0.8005452752113342,
+      "eval_runtime": 164.8286,
+      "eval_samples_per_second": 57.332,
+      "eval_steps_per_second": 0.898,
+      "step": 450
+    },
+    {
+      "epoch": 1.3694507148231754,
+      "grad_norm": 3.624423891962332,
+      "learning_rate": 5.761710355688627e-07,
+      "loss": 0.7147,
+      "step": 455
+    },
+    {
+      "epoch": 1.3844996237772762,
+      "grad_norm": 3.493220831680645,
+      "learning_rate": 5.682891788591065e-07,
+      "loss": 0.7449,
+      "step": 460
+    },
+    {
+      "epoch": 1.399548532731377,
+      "grad_norm": 3.5099359704812483,
+      "learning_rate": 5.603899909495283e-07,
+      "loss": 0.7245,
+      "step": 465
+    },
+    {
+      "epoch": 1.4145974416854779,
+      "grad_norm": 3.4941852068840817,
+      "learning_rate": 5.52475476585336e-07,
+      "loss": 0.7431,
+      "step": 470
+    },
+    {
+      "epoch": 1.4296463506395787,
+      "grad_norm": 3.6975807488475083,
+      "learning_rate": 5.445476444014591e-07,
+      "loss": 0.7467,
+      "step": 475
+    },
+    {
+      "epoch": 1.4446952595936795,
+      "grad_norm": 3.8488861949889817,
+      "learning_rate": 5.366085064127734e-07,
+      "loss": 0.7494,
+      "step": 480
+    },
+    {
+      "epoch": 1.4597441685477803,
+      "grad_norm": 3.7475349702165035,
+      "learning_rate": 5.286600775034699e-07,
+      "loss": 0.7488,
+      "step": 485
+    },
+    {
+      "epoch": 1.4747930775018812,
+      "grad_norm": 3.536002827555251,
+      "learning_rate": 5.207043749156944e-07,
+      "loss": 0.7455,
+      "step": 490
+    },
+    {
+      "epoch": 1.489841986455982,
+      "grad_norm": 3.5359647799654454,
+      "learning_rate": 5.127434177375893e-07,
+      "loss": 0.7245,
+      "step": 495
+    },
+    {
+      "epoch": 1.5048908954100828,
+      "grad_norm": 3.530405750992252,
+      "learning_rate": 5.047792263908659e-07,
+      "loss": 0.7373,
+      "step": 500
+    },
+    {
+      "epoch": 1.5048908954100828,
+      "eval_loss": 0.7960706949234009,
+      "eval_runtime": 164.4972,
+      "eval_samples_per_second": 57.448,
+      "eval_steps_per_second": 0.9,
+      "step": 500
+    },
+    {
+      "epoch": 1.5199398043641836,
+      "grad_norm": 3.6777960709655773,
+      "learning_rate": 4.968138221180401e-07,
+      "loss": 0.7177,
+      "step": 505
+    },
+    {
+      "epoch": 1.5349887133182845,
+      "grad_norm": 3.640353250330635,
+      "learning_rate": 4.888492264694565e-07,
+      "loss": 0.7274,
+      "step": 510
+    },
+    {
+      "epoch": 1.5500376222723853,
+      "grad_norm": 3.573323133504263,
+      "learning_rate": 4.808874607902397e-07,
+      "loss": 0.7248,
+      "step": 515
+    },
+    {
+      "epoch": 1.565086531226486,
+      "grad_norm": 3.758313365256897,
+      "learning_rate": 4.7293054570729126e-07,
+      "loss": 0.7228,
+      "step": 520
+    },
+    {
+      "epoch": 1.580135440180587,
+      "grad_norm": 3.482110494824545,
+      "learning_rate": 4.649805006164743e-07,
+      "loss": 0.7345,
+      "step": 525
+    },
+    {
+      "epoch": 1.5951843491346878,
+      "grad_norm": 3.5548114132456803,
+      "learning_rate": 4.5703934317010727e-07,
+      "loss": 0.7336,
+      "step": 530
+    },
+    {
+      "epoch": 1.6102332580887886,
+      "grad_norm": 3.47435512141577,
+      "learning_rate": 4.491090887649024e-07,
+      "loss": 0.7402,
+      "step": 535
+    },
+    {
+      "epoch": 1.6252821670428894,
+      "grad_norm": 3.6201869053811877,
+      "learning_rate": 4.4119175003047407e-07,
+      "loss": 0.7417,
+      "step": 540
+    },
+    {
+      "epoch": 1.6403310759969902,
+      "grad_norm": 3.5658610125401236,
+      "learning_rate": 4.3328933631855195e-07,
+      "loss": 0.7414,
+      "step": 545
+    },
+    {
+      "epoch": 1.655379984951091,
+      "grad_norm": 3.6931102044498787,
+      "learning_rate": 4.2540385319302524e-07,
+      "loss": 0.7145,
+      "step": 550
+    },
+    {
+      "epoch": 1.655379984951091,
+      "eval_loss": 0.7923677563667297,
+      "eval_runtime": 164.3846,
+      "eval_samples_per_second": 57.487,
+      "eval_steps_per_second": 0.9,
+      "step": 550
+    },
+    {
+      "epoch": 1.670428893905192,
+      "grad_norm": 3.6634192829178778,
+      "learning_rate": 4.175373019209468e-07,
+      "loss": 0.736,
+      "step": 555
+    },
+    {
+      "epoch": 1.6854778028592927,
+      "grad_norm": 3.663246949776699,
+      "learning_rate": 4.0969167896463046e-07,
+      "loss": 0.7271,
+      "step": 560
+    },
+    {
+      "epoch": 1.7005267118133935,
+      "grad_norm": 3.833602468227867,
+      "learning_rate": 4.018689754749648e-07,
+      "loss": 0.7381,
+      "step": 565
+    },
+    {
+      "epoch": 1.7155756207674944,
+      "grad_norm": 3.599494624246003,
+      "learning_rate": 3.9407117678607756e-07,
+      "loss": 0.7131,
+      "step": 570
+    },
+    {
+      "epoch": 1.7306245297215952,
+      "grad_norm": 3.496269655645928,
+      "learning_rate": 3.8630026191147405e-07,
+      "loss": 0.7202,
+      "step": 575
+    },
+    {
+      "epoch": 1.745673438675696,
+      "grad_norm": 3.7034173777972894,
+      "learning_rate": 3.78558203041782e-07,
+      "loss": 0.7279,
+      "step": 580
+    },
+    {
+      "epoch": 1.7607223476297968,
+      "grad_norm": 4.001879136240641,
+      "learning_rate": 3.7084696504422525e-07,
+      "loss": 0.7217,
+      "step": 585
+    },
+    {
+      "epoch": 1.7757712565838977,
+      "grad_norm": 3.8933985790258343,
+      "learning_rate": 3.6316850496395855e-07,
+      "loss": 0.7405,
+      "step": 590
+    },
+    {
+      "epoch": 1.7908201655379985,
+      "grad_norm": 3.6403289474674567,
+      "learning_rate": 3.555247715273867e-07,
+      "loss": 0.7349,
+      "step": 595
+    },
+    {
+      "epoch": 1.8058690744920993,
+      "grad_norm": 3.5876701469901375,
+      "learning_rate": 3.4791770464759347e-07,
+      "loss": 0.7176,
+      "step": 600
+    },
+    {
+      "epoch": 1.8058690744920993,
+      "eval_loss": 0.7886707186698914,
+      "eval_runtime": 164.4006,
+      "eval_samples_per_second": 57.482,
+      "eval_steps_per_second": 0.9,
+      "step": 600
+    },
+    {
+      "epoch": 1.8209179834462002,
+      "grad_norm": 3.511529577298137,
+      "learning_rate": 3.4034923493201007e-07,
+      "loss": 0.7286,
+      "step": 605
+    },
+    {
+      "epoch": 1.835966892400301,
+      "grad_norm": 3.5025696000503546,
+      "learning_rate": 3.3282128319244237e-07,
+      "loss": 0.7274,
+      "step": 610
+    },
+    {
+      "epoch": 1.8510158013544018,
+      "grad_norm": 3.7129442617829587,
+      "learning_rate": 3.2533575995758694e-07,
+      "loss": 0.7503,
+      "step": 615
+    },
+    {
+      "epoch": 1.8660647103085026,
+      "grad_norm": 3.323612660156572,
+      "learning_rate": 3.178945649881543e-07,
+      "loss": 0.7278,
+      "step": 620
+    },
+    {
+      "epoch": 1.8811136192626035,
+      "grad_norm": 3.651561344831796,
+      "learning_rate": 3.1049958679472645e-07,
+      "loss": 0.7189,
+      "step": 625
+    },
+    {
+      "epoch": 1.8961625282167043,
+      "grad_norm": 3.5915287409182843,
+      "learning_rate": 3.031527021584701e-07,
+      "loss": 0.7344,
+      "step": 630
+    },
+    {
+      "epoch": 1.911211437170805,
+      "grad_norm": 3.7127611003852317,
+      "learning_rate": 2.9585577565482484e-07,
+      "loss": 0.7278,
+      "step": 635
+    },
+    {
+      "epoch": 1.926260346124906,
+      "grad_norm": 3.6103190459559844,
+      "learning_rate": 2.886106591802908e-07,
+      "loss": 0.7482,
+      "step": 640
+    },
+    {
+      "epoch": 1.9413092550790068,
+      "grad_norm": 3.629391029578448,
+      "learning_rate": 2.814191914824332e-07,
+      "loss": 0.71,
+      "step": 645
+    },
+    {
+      "epoch": 1.9563581640331076,
+      "grad_norm": 3.876524735419322,
+      "learning_rate": 2.7428319769322415e-07,
+      "loss": 0.7384,
+      "step": 650
+    },
+    {
+      "epoch": 1.9563581640331076,
+      "eval_loss": 0.7857681512832642,
+      "eval_runtime": 164.3713,
+      "eval_samples_per_second": 57.492,
+      "eval_steps_per_second": 0.9,
+      "step": 650
+    },
+    {
+      "epoch": 1.9714070729872084,
+      "grad_norm": 3.3899320851149786,
+      "learning_rate": 2.672044888658399e-07,
+      "loss": 0.7152,
+      "step": 655
+    },
+    {
+      "epoch": 1.9864559819413092,
+      "grad_norm": 3.496799757255535,
+      "learning_rate": 2.6018486151503213e-07,
+      "loss": 0.715,
+      "step": 660
+    },
+    {
+      "epoch": 2.00150489089541,
+      "grad_norm": 3.848643688599015,
+      "learning_rate": 2.532260971611867e-07,
+      "loss": 0.7306,
+      "step": 665
+    },
+    {
+      "epoch": 2.016553799849511,
+      "grad_norm": 3.700900714630044,
+      "learning_rate": 2.4632996187819034e-07,
+      "loss": 0.6819,
+      "step": 670
+    },
+    {
+      "epoch": 2.0316027088036117,
+      "grad_norm": 3.6340025634573396,
+      "learning_rate": 2.394982058452165e-07,
+      "loss": 0.6779,
+      "step": 675
+    },
+    {
+      "epoch": 2.0466516177577128,
+      "grad_norm": 3.9705869092986608,
+      "learning_rate": 2.3273256290254402e-07,
+      "loss": 0.6818,
+      "step": 680
+    },
+    {
+      "epoch": 2.0617005267118134,
+      "grad_norm": 3.7843167139607377,
+      "learning_rate": 2.2603475011152517e-07,
+      "loss": 0.701,
+      "step": 685
+    },
+    {
+      "epoch": 2.0767494356659144,
+      "grad_norm": 3.69408051045692,
+      "learning_rate": 2.1940646731880885e-07,
+      "loss": 0.6814,
+      "step": 690
+    },
+    {
+      "epoch": 2.091798344620015,
+      "grad_norm": 3.822497413729019,
+      "learning_rate": 2.1284939672493506e-07,
+      "loss": 0.6986,
+      "step": 695
+    },
+    {
+      "epoch": 2.106847253574116,
+      "grad_norm": 3.7297282781569816,
+      "learning_rate": 2.0636520245740708e-07,
+      "loss": 0.6877,
+      "step": 700
+    },
+    {
+      "epoch": 2.106847253574116,
+      "eval_loss": 0.7906577587127686,
+      "eval_runtime": 164.5279,
+      "eval_samples_per_second": 57.437,
+      "eval_steps_per_second": 0.9,
+      "step": 700
+    },
+    {
+      "epoch": 2.1218961625282167,
+      "grad_norm": 3.653634589505017,
+      "learning_rate": 1.9995553014834986e-07,
+      "loss": 0.6616,
+      "step": 705
+    },
+    {
+      "epoch": 2.1369450714823177,
+      "grad_norm": 3.6094055740564577,
+      "learning_rate": 1.9362200651686406e-07,
+      "loss": 0.6807,
+      "step": 710
+    },
+    {
+      "epoch": 2.1519939804364183,
+      "grad_norm": 3.7245551119478484,
+      "learning_rate": 1.873662389561771e-07,
+      "loss": 0.6789,
+      "step": 715
+    },
+    {
+      "epoch": 2.1670428893905194,
+      "grad_norm": 3.8994746222238943,
+      "learning_rate": 1.8118981512570254e-07,
+      "loss": 0.6798,
+      "step": 720
+    },
+    {
+      "epoch": 2.18209179834462,
+      "grad_norm": 3.9399523583825657,
+      "learning_rate": 1.750943025481046e-07,
+      "loss": 0.6752,
+      "step": 725
+    },
+    {
+      "epoch": 2.197140707298721,
+      "grad_norm": 3.9639982002498435,
+      "learning_rate": 1.6908124821147517e-07,
+      "loss": 0.6593,
+      "step": 730
+    },
+    {
+      "epoch": 2.2121896162528216,
+      "grad_norm": 3.686217265583731,
+      "learning_rate": 1.631521781767214e-07,
+      "loss": 0.6708,
+      "step": 735
+    },
+    {
+      "epoch": 2.2272385252069227,
+      "grad_norm": 3.839667134049121,
+      "learning_rate": 1.5730859719026535e-07,
+      "loss": 0.67,
+      "step": 740
+    },
+    {
+      "epoch": 2.2422874341610233,
+      "grad_norm": 3.61654343340027,
+      "learning_rate": 1.5155198830215144e-07,
+      "loss": 0.668,
+      "step": 745
+    },
+    {
+      "epoch": 2.2573363431151243,
+      "grad_norm": 3.621797995269719,
+      "learning_rate": 1.4588381248966185e-07,
+      "loss": 0.6796,
+      "step": 750
+    },
+    {
+      "epoch": 2.2573363431151243,
+      "eval_loss": 0.7899430990219116,
+      "eval_runtime": 164.4792,
+      "eval_samples_per_second": 57.454,
+      "eval_steps_per_second": 0.9,
+      "step": 750
+    },
+    {
+      "epoch": 2.272385252069225,
+      "grad_norm": 4.012254837738426,
+      "learning_rate": 1.4030550828653354e-07,
+      "loss": 0.6911,
+      "step": 755
+    },
+    {
+      "epoch": 2.287434161023326,
+      "grad_norm": 3.9520876419590256,
+      "learning_rate": 1.3481849141786977e-07,
+      "loss": 0.6795,
+      "step": 760
+    },
+    {
+      "epoch": 2.3024830699774266,
+      "grad_norm": 3.883255647541917,
+      "learning_rate": 1.294241544408425e-07,
+      "loss": 0.6694,
+      "step": 765
+    },
+    {
+      "epoch": 2.3175319789315276,
+      "grad_norm": 3.799844419656149,
+      "learning_rate": 1.241238663912727e-07,
+      "loss": 0.7048,
+      "step": 770
+    },
+    {
+      "epoch": 2.3325808878856282,
+      "grad_norm": 3.8884134747643793,
+      "learning_rate": 1.1891897243618183e-07,
+      "loss": 0.6814,
+      "step": 775
+    },
+    {
+      "epoch": 2.3476297968397293,
+      "grad_norm": 3.5975780782982825,
+      "learning_rate": 1.1381079353239915e-07,
+      "loss": 0.6822,
+      "step": 780
+    },
+    {
+      "epoch": 2.36267870579383,
+      "grad_norm": 3.992733447714394,
+      "learning_rate": 1.0880062609131485e-07,
+      "loss": 0.689,
+      "step": 785
+    },
+    {
+      "epoch": 2.377727614747931,
+      "grad_norm": 3.613464796202204,
+      "learning_rate": 1.0388974164986247e-07,
+      "loss": 0.6743,
+      "step": 790
+    },
+    {
+      "epoch": 2.3927765237020315,
+      "grad_norm": 3.659276093531672,
+      "learning_rate": 9.907938654781306e-08,
+      "loss": 0.6926,
+      "step": 795
+    },
+    {
+      "epoch": 2.4078254326561326,
+      "grad_norm": 3.9248896041140897,
+      "learning_rate": 9.437078161146589e-08,
+      "loss": 0.6837,
+      "step": 800
+    },
+    {
+      "epoch": 2.4078254326561326,
+      "eval_loss": 0.788821280002594,
+      "eval_runtime": 164.5032,
+      "eval_samples_per_second": 57.446,
+      "eval_steps_per_second": 0.9,
+      "step": 800
+    },
+    {
+      "epoch": 2.422874341610233,
+      "grad_norm": 3.876935336075608,
+      "learning_rate": 8.976512184381246e-08,
+      "loss": 0.6791,
+      "step": 805
+    },
+    {
+      "epoch": 2.4379232505643342,
+      "grad_norm": 3.7240893931507033,
+      "learning_rate": 8.526357612125573e-08,
+      "loss": 0.6858,
+      "step": 810
+    },
+    {
+      "epoch": 2.452972159518435,
+      "grad_norm": 3.8422906773804293,
+      "learning_rate": 8.086728689695921e-08,
+      "loss": 0.6946,
+      "step": 815
+    },
+    {
+      "epoch": 2.468021068472536,
+      "grad_norm": 3.8826146265577135,
+      "learning_rate": 7.657736991090263e-08,
+      "loss": 0.6841,
+      "step": 820
+    },
+    {
+      "epoch": 2.4830699774266365,
+      "grad_norm": 3.9083521097106693,
+      "learning_rate": 7.239491390671631e-08,
+      "loss": 0.6812,
+      "step": 825
+    },
+    {
+      "epoch": 2.4981188863807375,
+      "grad_norm": 3.9311253338807477,
+      "learning_rate": 6.832098035536759e-08,
+      "loss": 0.6757,
+      "step": 830
+    },
+    {
+      "epoch": 2.513167795334838,
+      "grad_norm": 3.829030585152858,
+      "learning_rate": 6.435660318576935e-08,
+      "loss": 0.6754,
+      "step": 835
+    },
+    {
+      "epoch": 2.528216704288939,
+      "grad_norm": 3.8440317620257582,
+      "learning_rate": 6.0502788522377e-08,
+      "loss": 0.6729,
+      "step": 840
+    },
+    {
+      "epoch": 2.54326561324304,
+      "grad_norm": 4.046477181331474,
+      "learning_rate": 5.676051442984325e-08,
+      "loss": 0.6832,
+      "step": 845
+    },
+    {
+      "epoch": 2.558314522197141,
+      "grad_norm": 3.8109396018056083,
+      "learning_rate": 5.313073066479379e-08,
+      "loss": 0.6653,
+      "step": 850
+    },
+    {
+      "epoch": 2.558314522197141,
+      "eval_loss": 0.7885056138038635,
+      "eval_runtime": 164.2633,
+      "eval_samples_per_second": 57.53,
+      "eval_steps_per_second": 0.901,
+      "step": 850
+    },
+    {
+      "epoch": 2.5733634311512414,
+      "grad_norm": 4.016744376255009,
+      "learning_rate": 4.961435843478751e-08,
+      "loss": 0.6845,
+      "step": 855
+    },
+    {
+      "epoch": 2.5884123401053425,
+      "grad_norm": 3.736617322184166,
+      "learning_rate": 4.621229016452155e-08,
+      "loss": 0.6734,
+      "step": 860
+    },
+    {
+      "epoch": 2.603461249059443,
+      "grad_norm": 3.86816117493287,
+      "learning_rate": 4.2925389269341916e-08,
+      "loss": 0.6777,
+      "step": 865
+    },
+    {
+      "epoch": 2.618510158013544,
+      "grad_norm": 3.7170069049525596,
+      "learning_rate": 3.975448993611652e-08,
+      "loss": 0.6719,
+      "step": 870
+    },
+    {
+      "epoch": 2.6335590669676447,
+      "grad_norm": 3.7507043912522664,
+      "learning_rate": 3.67003969115251e-08,
+      "loss": 0.6779,
+      "step": 875
+    },
+    {
+      "epoch": 2.648607975921746,
+      "grad_norm": 3.941235995809754,
+      "learning_rate": 3.376388529782215e-08,
+      "loss": 0.6781,
+      "step": 880
+    },
+    {
+      "epoch": 2.6636568848758464,
+      "grad_norm": 3.9252013397629355,
+      "learning_rate": 3.094570035612226e-08,
+      "loss": 0.6942,
+      "step": 885
+    },
+    {
+      "epoch": 2.6787057938299474,
+      "grad_norm": 3.8180128091085748,
+      "learning_rate": 2.8246557317259723e-08,
+      "loss": 0.6914,
+      "step": 890
+    },
+    {
+      "epoch": 2.693754702784048,
+      "grad_norm": 3.6630851255135166,
+      "learning_rate": 2.5667141200268694e-08,
+      "loss": 0.6892,
+      "step": 895
+    },
+    {
+      "epoch": 2.708803611738149,
+      "grad_norm": 3.80576717661997,
+      "learning_rate": 2.3208106638531842e-08,
+      "loss": 0.6563,
+      "step": 900
+    },
+    {
+      "epoch": 2.708803611738149,
+      "eval_loss": 0.7879343032836914,
+      "eval_runtime": 164.5206,
+      "eval_samples_per_second": 57.44,
+      "eval_steps_per_second": 0.9,
+      "step": 900
+    },
+    {
+      "epoch": 2.7238525206922497,
+      "grad_norm": 3.6414312258428794,
+      "learning_rate": 2.087007771363969e-08,
+      "loss": 0.6736,
+      "step": 905
+    },
+    {
+      "epoch": 2.7389014296463507,
+      "grad_norm": 4.106134375603198,
+      "learning_rate": 1.8653647797004236e-08,
+      "loss": 0.6797,
+      "step": 910
+    },
+    {
+      "epoch": 2.7539503386004514,
+      "grad_norm": 3.7480063289957264,
+      "learning_rate": 1.655937939926655e-08,
+      "loss": 0.6666,
+      "step": 915
+    },
+    {
+      "epoch": 2.7689992475545524,
+      "grad_norm": 3.806194015893575,
+      "learning_rate": 1.4587804027536454e-08,
+      "loss": 0.6797,
+      "step": 920
+    },
+    {
+      "epoch": 2.784048156508653,
+      "grad_norm": 3.850885472228141,
+      "learning_rate": 1.2739422050500436e-08,
+      "loss": 0.6643,
+      "step": 925
+    },
+    {
+      "epoch": 2.799097065462754,
+      "grad_norm": 3.8694606829300593,
+      "learning_rate": 1.101470257143261e-08,
+      "loss": 0.6811,
+      "step": 930
+    },
+    {
+      "epoch": 2.8141459744168547,
+      "grad_norm": 3.7451798850830484,
+      "learning_rate": 9.414083309140453e-09,
+      "loss": 0.691,
+      "step": 935
+    },
+    {
+      "epoch": 2.8291948833709557,
+      "grad_norm": 3.805433129820117,
+      "learning_rate": 7.93797048687539e-09,
+      "loss": 0.6758,
+      "step": 940
+    },
+    {
+      "epoch": 2.8442437923250563,
+      "grad_norm": 3.848550417844875,
+      "learning_rate": 6.5867387292369295e-09,
+      "loss": 0.6712,
+      "step": 945
+    },
+    {
+      "epoch": 2.8592927012791574,
+      "grad_norm": 3.8372836117275524,
+      "learning_rate": 5.360730967096272e-09,
+      "loss": 0.6829,
+      "step": 950
+    },
+    {
+      "epoch": 2.8592927012791574,
+      "eval_loss": 0.7878710031509399,
+      "eval_runtime": 164.3818,
+      "eval_samples_per_second": 57.488,
+      "eval_steps_per_second": 0.9,
+      "step": 950
+    },
+    {
+      "epoch": 2.874341610233258,
+      "grad_norm": 3.690622616479554,
+      "learning_rate": 4.260258350563317e-09,
+      "loss": 0.6704,
+      "step": 955
+    },
+    {
+      "epoch": 2.889390519187359,
+      "grad_norm": 3.9735203009322824,
+      "learning_rate": 3.285600170019609e-09,
+      "loss": 0.6802,
+      "step": 960
+    },
+    {
+      "epoch": 2.9044394281414596,
+      "grad_norm": 3.9338847655040836,
+      "learning_rate": 2.437003785236702e-09,
+      "loss": 0.6778,
+      "step": 965
+    },
+    {
+      "epoch": 2.9194883370955607,
+      "grad_norm": 3.828474240996448,
+      "learning_rate": 1.714684562598545e-09,
+      "loss": 0.6714,
+      "step": 970
+    },
+    {
+      "epoch": 2.9345372460496613,
+      "grad_norm": 3.819052850746861,
+      "learning_rate": 1.1188258204433144e-09,
+      "loss": 0.6755,
+      "step": 975
+    },
+    {
+      "epoch": 2.9495861550037623,
+      "grad_norm": 3.6976061918723917,
+      "learning_rate": 6.49578782538851e-10,
+      "loss": 0.6792,
+      "step": 980
+    },
+    {
+      "epoch": 2.964635063957863,
+      "grad_norm": 3.964592057252041,
+      "learning_rate": 3.070625397031401e-10,
+      "loss": 0.6723,
+      "step": 985
+    },
+    {
+      "epoch": 2.979683972911964,
+      "grad_norm": 4.047836254173495,
+      "learning_rate": 9.136401958059759e-11,
+      "loss": 0.6766,
+      "step": 990
+    },
+    {
+      "epoch": 2.9947328818660646,
+      "grad_norm": 4.038781331246751,
+      "learning_rate": 2.5379645800516215e-12,
+      "loss": 0.6835,
+      "step": 995
+    },
+    {
+      "epoch": 2.9977426636568847,
+      "step": 996,
+      "total_flos": 5872633472090112.0,
+      "train_loss": 0.7696134887905006,
+      "train_runtime": 16213.1344,
+      "train_samples_per_second": 15.737,
+      "train_steps_per_second": 0.061
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 996,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5872633472090112.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dad14bd8f0dcb83dc826736d34b7749c749a722b80cafb513467c4ee91f5047
+size 7096