Upload folder using huggingface_hub

README.md

@@ -0,0 +1,77 @@
+---
+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: RLAIF-V-Cosi-q0_75
+  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. -->
+
+# RLAIF-V-Cosi-q0_75
+
+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 RLAIF-V-Cosi-q0_75 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0076
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1181        | 0.2320 | 50   | 1.1215          |
+| 1.0765        | 0.4640 | 100  | 1.0775          |
+| 1.0639        | 0.6961 | 150  | 1.0502          |
+| 1.0308        | 0.9281 | 200  | 1.0282          |
+| 0.9038        | 1.1601 | 250  | 1.0220          |
+| 0.8973        | 1.3921 | 300  | 1.0114          |
+| 0.8747        | 1.6241 | 350  | 1.0039          |
+| 0.8818        | 1.8561 | 400  | 0.9965          |
+| 0.7851        | 2.0882 | 450  | 1.0085          |
+| 0.7784        | 2.3202 | 500  | 1.0107          |
+| 0.7773        | 2.5522 | 550  | 1.0086          |
+| 0.784         | 2.7842 | 600  | 1.0077          |
+
+
+### 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": 2.9930394431554523,
+    "eval_loss": 1.0076345205307007,
+    "eval_runtime": 105.188,
+    "eval_samples_per_second": 58.267,
+    "eval_steps_per_second": 0.913,
+    "total_flos": 3802978389590016.0,
+    "train_loss": 0.9273426562316658,
+    "train_runtime": 9552.8802,
+    "train_samples_per_second": 17.321,
+    "train_steps_per_second": 0.068
+}

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": 2.9930394431554523,
+    "eval_loss": 1.0076345205307007,
+    "eval_runtime": 105.188,
+    "eval_samples_per_second": 58.267,
+    "eval_steps_per_second": 0.913
+}

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 sha256:2456f127b6d1f2676902fffdf1968d0f6155fe4f5b838e7da5ee875177921e54
+size 4921618624

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d44c79bb29a11b1391964230f7d5bdc7472bc573341d452efa904df4641612
+size 4915917672

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:413052a9b8f311c76cd62bc6bdd5550175ec0ce2c0371fd89f09390d63666f16
+size 4915917680

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11de2fbf4557444dd7a280cdf4f7359629882d875504d65e23048aa445ce132f
+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": 2.9930394431554523,
+    "total_flos": 3802978389590016.0,
+    "train_loss": 0.9273426562316658,
+    "train_runtime": 9552.8802,
+    "train_samples_per_second": 17.321,
+    "train_steps_per_second": 0.068
+}

trainer_log.jsonl

@@ -0,0 +1,142 @@
+{"current_steps": 5, "total_steps": 645, "loss": 1.6569, "learning_rate": 5e-07, "epoch": 0.02320185614849188, "percentage": 0.78, "elapsed_time": "0:01:07", "remaining_time": "2:25:00"}
+{"current_steps": 10, "total_steps": 645, "loss": 1.5099, "learning_rate": 1e-06, "epoch": 0.04640371229698376, "percentage": 1.55, "elapsed_time": "0:02:10", "remaining_time": "2:18:08"}
+{"current_steps": 15, "total_steps": 645, "loss": 1.2782, "learning_rate": 9.998470286265414e-07, "epoch": 0.06960556844547564, "percentage": 2.33, "elapsed_time": "0:03:12", "remaining_time": "2:14:46"}
+{"current_steps": 20, "total_steps": 645, "loss": 1.2359, "learning_rate": 9.993882081071305e-07, "epoch": 0.09280742459396751, "percentage": 3.1, "elapsed_time": "0:04:14", "remaining_time": "2:12:45"}
+{"current_steps": 25, "total_steps": 645, "loss": 1.204, "learning_rate": 9.986238191873872e-07, "epoch": 0.11600928074245939, "percentage": 3.88, "elapsed_time": "0:05:16", "remaining_time": "2:10:58"}
+{"current_steps": 30, "total_steps": 645, "loss": 1.1627, "learning_rate": 9.975543295858033e-07, "epoch": 0.13921113689095127, "percentage": 4.65, "elapsed_time": "0:06:19", "remaining_time": "2:09:37"}
+{"current_steps": 35, "total_steps": 645, "loss": 1.1463, "learning_rate": 9.961803937075514e-07, "epoch": 0.16241299303944315, "percentage": 5.43, "elapsed_time": "0:07:21", "remaining_time": "2:08:21"}
+{"current_steps": 40, "total_steps": 645, "loss": 1.1394, "learning_rate": 9.945028522440653e-07, "epoch": 0.18561484918793503, "percentage": 6.2, "elapsed_time": "0:08:24", "remaining_time": "2:07:05"}
+{"current_steps": 45, "total_steps": 645, "loss": 1.1371, "learning_rate": 9.925227316586314e-07, "epoch": 0.2088167053364269, "percentage": 6.98, "elapsed_time": "0:09:26", "remaining_time": "2:05:50"}
+{"current_steps": 50, "total_steps": 645, "loss": 1.1181, "learning_rate": 9.902412435583125e-07, "epoch": 0.23201856148491878, "percentage": 7.75, "elapsed_time": "0:10:28", "remaining_time": "2:04:42"}
+{"current_steps": 50, "total_steps": 645, "eval_loss": 1.1214605569839478, "epoch": 0.23201856148491878, "percentage": 7.75, "elapsed_time": "0:12:14", "remaining_time": "2:25:42"}
+{"current_steps": 55, "total_steps": 645, "loss": 1.1163, "learning_rate": 9.876597839525813e-07, "epoch": 0.2552204176334107, "percentage": 8.53, "elapsed_time": "0:13:16", "remaining_time": "2:22:26"}
+{"current_steps": 60, "total_steps": 645, "loss": 1.1232, "learning_rate": 9.847799323991233e-07, "epoch": 0.27842227378190254, "percentage": 9.3, "elapsed_time": "0:14:18", "remaining_time": "2:19:33"}
+{"current_steps": 65, "total_steps": 645, "loss": 1.125, "learning_rate": 9.816034510373285e-07, "epoch": 0.30162412993039445, "percentage": 10.08, "elapsed_time": "0:15:21", "remaining_time": "2:17:02"}
+{"current_steps": 70, "total_steps": 645, "loss": 1.108, "learning_rate": 9.781322835100637e-07, "epoch": 0.3248259860788863, "percentage": 10.85, "elapsed_time": "0:16:24", "remaining_time": "2:14:47"}
+{"current_steps": 75, "total_steps": 645, "loss": 1.106, "learning_rate": 9.743685537743856e-07, "epoch": 0.3480278422273782, "percentage": 11.63, "elapsed_time": "0:17:27", "remaining_time": "2:12:39"}
+{"current_steps": 80, "total_steps": 645, "loss": 1.0973, "learning_rate": 9.70314564801922e-07, "epoch": 0.37122969837587005, "percentage": 12.4, "elapsed_time": "0:18:29", "remaining_time": "2:10:36"}
+{"current_steps": 85, "total_steps": 645, "loss": 1.0964, "learning_rate": 9.659727971697173e-07, "epoch": 0.39443155452436196, "percentage": 13.18, "elapsed_time": "0:19:31", "remaining_time": "2:08:39"}
+{"current_steps": 90, "total_steps": 645, "loss": 1.0956, "learning_rate": 9.613459075424033e-07, "epoch": 0.4176334106728538, "percentage": 13.95, "elapsed_time": "0:20:34", "remaining_time": "2:06:50"}
+{"current_steps": 95, "total_steps": 645, "loss": 1.0787, "learning_rate": 9.564367270466245e-07, "epoch": 0.4408352668213457, "percentage": 14.73, "elapsed_time": "0:21:36", "remaining_time": "2:05:06"}
+{"current_steps": 100, "total_steps": 645, "loss": 1.0765, "learning_rate": 9.51248259538713e-07, "epoch": 0.46403712296983757, "percentage": 15.5, "elapsed_time": "0:22:39", "remaining_time": "2:03:26"}
+{"current_steps": 100, "total_steps": 645, "eval_loss": 1.0775035619735718, "epoch": 0.46403712296983757, "percentage": 15.5, "elapsed_time": "0:24:24", "remaining_time": "2:13:01"}
+{"current_steps": 105, "total_steps": 645, "loss": 1.0903, "learning_rate": 9.457836797666721e-07, "epoch": 0.4872389791183295, "percentage": 16.28, "elapsed_time": "0:25:56", "remaining_time": "2:13:26"}
+{"current_steps": 110, "total_steps": 645, "loss": 1.0697, "learning_rate": 9.400463314275941e-07, "epoch": 0.5104408352668214, "percentage": 17.05, "elapsed_time": "0:26:59", "remaining_time": "2:11:18"}
+{"current_steps": 115, "total_steps": 645, "loss": 1.0668, "learning_rate": 9.340397251217008e-07, "epoch": 0.5336426914153132, "percentage": 17.83, "elapsed_time": "0:28:02", "remaining_time": "2:09:14"}
+{"current_steps": 120, "total_steps": 645, "loss": 1.0676, "learning_rate": 9.27767536204258e-07, "epoch": 0.5568445475638051, "percentage": 18.6, "elapsed_time": "0:29:04", "remaining_time": "2:07:13"}
+{"current_steps": 125, "total_steps": 645, "loss": 1.0746, "learning_rate": 9.212336025366787e-07, "epoch": 0.580046403712297, "percentage": 19.38, "elapsed_time": "0:30:08", "remaining_time": "2:05:21"}
+{"current_steps": 130, "total_steps": 645, "loss": 1.0724, "learning_rate": 9.144419221381918e-07, "epoch": 0.6032482598607889, "percentage": 20.16, "elapsed_time": "0:31:10", "remaining_time": "2:03:30"}
+{"current_steps": 135, "total_steps": 645, "loss": 1.0745, "learning_rate": 9.073966507395121e-07, "epoch": 0.6264501160092807, "percentage": 20.93, "elapsed_time": "0:32:12", "remaining_time": "2:01:41"}
+{"current_steps": 140, "total_steps": 645, "loss": 1.0559, "learning_rate": 9.001020992400085e-07, "epoch": 0.6496519721577726, "percentage": 21.71, "elapsed_time": "0:33:15", "remaining_time": "1:59:59"}
+{"current_steps": 145, "total_steps": 645, "loss": 1.0705, "learning_rate": 8.925627310699274e-07, "epoch": 0.6728538283062645, "percentage": 22.48, "elapsed_time": "0:34:18", "remaining_time": "1:58:19"}
+{"current_steps": 150, "total_steps": 645, "loss": 1.0639, "learning_rate": 8.84783159459285e-07, "epoch": 0.6960556844547564, "percentage": 23.26, "elapsed_time": "0:35:20", "remaining_time": "1:56:38"}
+{"current_steps": 150, "total_steps": 645, "eval_loss": 1.0501643419265747, "epoch": 0.6960556844547564, "percentage": 23.26, "elapsed_time": "0:37:06", "remaining_time": "2:02:26"}
+{"current_steps": 155, "total_steps": 645, "loss": 1.0472, "learning_rate": 8.767681446150976e-07, "epoch": 0.7192575406032483, "percentage": 24.03, "elapsed_time": "0:38:08", "remaining_time": "2:00:33"}
+{"current_steps": 160, "total_steps": 645, "loss": 1.0645, "learning_rate": 8.68522590808682e-07, "epoch": 0.7424593967517401, "percentage": 24.81, "elapsed_time": "0:39:10", "remaining_time": "1:58:44"}
+{"current_steps": 165, "total_steps": 645, "loss": 1.0416, "learning_rate": 8.600515433748001e-07, "epoch": 0.765661252900232, "percentage": 25.58, "elapsed_time": "0:40:12", "remaining_time": "1:56:58"}
+{"current_steps": 170, "total_steps": 645, "loss": 1.0478, "learning_rate": 8.51360185624495e-07, "epoch": 0.7888631090487239, "percentage": 26.36, "elapsed_time": "0:41:14", "remaining_time": "1:55:15"}
+{"current_steps": 175, "total_steps": 645, "loss": 1.0383, "learning_rate": 8.424538356734956e-07, "epoch": 0.8120649651972158, "percentage": 27.13, "elapsed_time": "0:42:17", "remaining_time": "1:53:34"}
+{"current_steps": 180, "total_steps": 645, "loss": 1.0342, "learning_rate": 8.333379431881397e-07, "epoch": 0.8352668213457076, "percentage": 27.91, "elapsed_time": "0:43:19", "remaining_time": "1:51:55"}
+{"current_steps": 185, "total_steps": 645, "loss": 1.0413, "learning_rate": 8.240180860508026e-07, "epoch": 0.8584686774941995, "percentage": 28.68, "elapsed_time": "0:44:21", "remaining_time": "1:50:18"}
+{"current_steps": 190, "total_steps": 645, "loss": 1.0264, "learning_rate": 8.144999669468713e-07, "epoch": 0.8816705336426914, "percentage": 29.46, "elapsed_time": "0:45:25", "remaining_time": "1:48:46"}
+{"current_steps": 195, "total_steps": 645, "loss": 1.028, "learning_rate": 8.047894098753539e-07, "epoch": 0.9048723897911833, "percentage": 30.23, "elapsed_time": "0:46:27", "remaining_time": "1:47:12"}
+{"current_steps": 200, "total_steps": 645, "loss": 1.0308, "learning_rate": 7.948923565852597e-07, "epoch": 0.9280742459396751, "percentage": 31.01, "elapsed_time": "0:47:30", "remaining_time": "1:45:42"}
+{"current_steps": 200, "total_steps": 645, "eval_loss": 1.0281875133514404, "epoch": 0.9280742459396751, "percentage": 31.01, "elapsed_time": "0:49:16", "remaining_time": "1:49:37"}
+{"current_steps": 205, "total_steps": 645, "loss": 1.0262, "learning_rate": 7.848148629399285e-07, "epoch": 0.951276102088167, "percentage": 31.78, "elapsed_time": "0:50:51", "remaining_time": "1:49:09"}
+{"current_steps": 210, "total_steps": 645, "loss": 1.0349, "learning_rate": 7.745630952115363e-07, "epoch": 0.974477958236659, "percentage": 32.56, "elapsed_time": "0:51:53", "remaining_time": "1:47:29"}
+{"current_steps": 215, "total_steps": 645, "loss": 1.0216, "learning_rate": 7.641433263080418e-07, "epoch": 0.9976798143851509, "percentage": 33.33, "elapsed_time": "0:52:55", "remaining_time": "1:45:51"}
+{"current_steps": 220, "total_steps": 645, "loss": 0.9241, "learning_rate": 7.535619319348865e-07, "epoch": 1.0208816705336428, "percentage": 34.11, "elapsed_time": "0:53:58", "remaining_time": "1:44:16"}
+{"current_steps": 225, "total_steps": 645, "loss": 0.9001, "learning_rate": 7.428253866937918e-07, "epoch": 1.0440835266821347, "percentage": 34.88, "elapsed_time": "0:55:01", "remaining_time": "1:42:42"}
+{"current_steps": 230, "total_steps": 645, "loss": 0.8916, "learning_rate": 7.319402601210447e-07, "epoch": 1.0672853828306264, "percentage": 35.66, "elapsed_time": "0:56:03", "remaining_time": "1:41:09"}
+{"current_steps": 235, "total_steps": 645, "loss": 0.8876, "learning_rate": 7.209132126676933e-07, "epoch": 1.0904872389791183, "percentage": 36.43, "elapsed_time": "0:57:05", "remaining_time": "1:39:37"}
+{"current_steps": 240, "total_steps": 645, "loss": 0.8931, "learning_rate": 7.097509916241145e-07, "epoch": 1.1136890951276102, "percentage": 37.21, "elapsed_time": "0:58:08", "remaining_time": "1:38:06"}
+{"current_steps": 245, "total_steps": 645, "loss": 0.905, "learning_rate": 6.984604269914436e-07, "epoch": 1.136890951276102, "percentage": 37.98, "elapsed_time": "0:59:10", "remaining_time": "1:36:36"}
+{"current_steps": 250, "total_steps": 645, "loss": 0.9038, "learning_rate": 6.870484273023967e-07, "epoch": 1.160092807424594, "percentage": 38.76, "elapsed_time": "1:00:12", "remaining_time": "1:35:07"}
+{"current_steps": 250, "total_steps": 645, "eval_loss": 1.0220295190811157, "epoch": 1.160092807424594, "percentage": 38.76, "elapsed_time": "1:01:58", "remaining_time": "1:37:55"}
+{"current_steps": 255, "total_steps": 645, "loss": 0.8964, "learning_rate": 6.755219753940388e-07, "epoch": 1.1832946635730859, "percentage": 39.53, "elapsed_time": "1:03:00", "remaining_time": "1:36:22"}
+{"current_steps": 260, "total_steps": 645, "loss": 0.8898, "learning_rate": 6.638881241350883e-07, "epoch": 1.2064965197215778, "percentage": 40.31, "elapsed_time": "1:04:03", "remaining_time": "1:34:50"}
+{"current_steps": 265, "total_steps": 645, "loss": 0.8951, "learning_rate": 6.52153992110368e-07, "epoch": 1.2296983758700697, "percentage": 41.09, "elapsed_time": "1:05:06", "remaining_time": "1:33:21"}
+{"current_steps": 270, "total_steps": 645, "loss": 0.8961, "learning_rate": 6.403267592650466e-07, "epoch": 1.2529002320185616, "percentage": 41.86, "elapsed_time": "1:06:09", "remaining_time": "1:31:52"}
+{"current_steps": 275, "total_steps": 645, "loss": 0.8919, "learning_rate": 6.28413662511334e-07, "epoch": 1.2761020881670533, "percentage": 42.64, "elapsed_time": "1:07:12", "remaining_time": "1:30:25"}
+{"current_steps": 280, "total_steps": 645, "loss": 0.8931, "learning_rate": 6.164219913003207e-07, "epoch": 1.2993039443155452, "percentage": 43.41, "elapsed_time": "1:08:15", "remaining_time": "1:28:58"}
+{"current_steps": 285, "total_steps": 645, "loss": 0.8792, "learning_rate": 6.043590831616676e-07, "epoch": 1.322505800464037, "percentage": 44.19, "elapsed_time": "1:09:17", "remaining_time": "1:27:31"}
+{"current_steps": 290, "total_steps": 645, "loss": 0.8768, "learning_rate": 5.92232319213878e-07, "epoch": 1.345707656612529, "percentage": 44.96, "elapsed_time": "1:10:19", "remaining_time": "1:26:05"}
+{"current_steps": 295, "total_steps": 645, "loss": 0.8788, "learning_rate": 5.800491196478988e-07, "epoch": 1.368909512761021, "percentage": 45.74, "elapsed_time": "1:11:22", "remaining_time": "1:24:40"}
+{"current_steps": 300, "total_steps": 645, "loss": 0.8973, "learning_rate": 5.678169391868127e-07, "epoch": 1.3921113689095128, "percentage": 46.51, "elapsed_time": "1:12:25", "remaining_time": "1:23:17"}
+{"current_steps": 300, "total_steps": 645, "eval_loss": 1.0114275217056274, "epoch": 1.3921113689095128, "percentage": 46.51, "elapsed_time": "1:14:11", "remaining_time": "1:25:19"}
+{"current_steps": 305, "total_steps": 645, "loss": 0.8831, "learning_rate": 5.555432625244023e-07, "epoch": 1.4153132250580047, "percentage": 47.29, "elapsed_time": "1:15:45", "remaining_time": "1:24:27"}
+{"current_steps": 310, "total_steps": 645, "loss": 0.8848, "learning_rate": 5.432355997453728e-07, "epoch": 1.4385150812064964, "percentage": 48.06, "elapsed_time": "1:16:48", "remaining_time": "1:22:59"}
+{"current_steps": 315, "total_steps": 645, "loss": 0.8999, "learning_rate": 5.309014817300421e-07, "epoch": 1.4617169373549883, "percentage": 48.84, "elapsed_time": "1:17:50", "remaining_time": "1:21:33"}
+{"current_steps": 320, "total_steps": 645, "loss": 0.8901, "learning_rate": 5.185484555463026e-07, "epoch": 1.4849187935034802, "percentage": 49.61, "elapsed_time": "1:18:53", "remaining_time": "1:20:06"}
+{"current_steps": 325, "total_steps": 645, "loss": 0.8909, "learning_rate": 5.061840798316814e-07, "epoch": 1.5081206496519721, "percentage": 50.39, "elapsed_time": "1:19:55", "remaining_time": "1:18:41"}
+{"current_steps": 330, "total_steps": 645, "loss": 0.8829, "learning_rate": 4.938159201683186e-07, "epoch": 1.531322505800464, "percentage": 51.16, "elapsed_time": "1:20:57", "remaining_time": "1:17:17"}
+{"current_steps": 335, "total_steps": 645, "loss": 0.8867, "learning_rate": 4.814515444536974e-07, "epoch": 1.554524361948956, "percentage": 51.94, "elapsed_time": "1:21:59", "remaining_time": "1:15:52"}
+{"current_steps": 340, "total_steps": 645, "loss": 0.892, "learning_rate": 4.69098518269958e-07, "epoch": 1.5777262180974478, "percentage": 52.71, "elapsed_time": "1:23:02", "remaining_time": "1:14:29"}
+{"current_steps": 345, "total_steps": 645, "loss": 0.8775, "learning_rate": 4.5676440025462726e-07, "epoch": 1.6009280742459397, "percentage": 53.49, "elapsed_time": "1:24:04", "remaining_time": "1:13:06"}
+{"current_steps": 350, "total_steps": 645, "loss": 0.8747, "learning_rate": 4.444567374755977e-07, "epoch": 1.6241299303944317, "percentage": 54.26, "elapsed_time": "1:25:06", "remaining_time": "1:11:44"}
+{"current_steps": 350, "total_steps": 645, "eval_loss": 1.0039345026016235, "epoch": 1.6241299303944317, "percentage": 54.26, "elapsed_time": "1:26:52", "remaining_time": "1:13:13"}
+{"current_steps": 355, "total_steps": 645, "loss": 0.884, "learning_rate": 4.3218306081318713e-07, "epoch": 1.6473317865429236, "percentage": 55.04, "elapsed_time": "1:27:54", "remaining_time": "1:11:48"}
+{"current_steps": 360, "total_steps": 645, "loss": 0.8945, "learning_rate": 4.199508803521012e-07, "epoch": 1.6705336426914155, "percentage": 55.81, "elapsed_time": "1:28:56", "remaining_time": "1:10:25"}
+{"current_steps": 365, "total_steps": 645, "loss": 0.8793, "learning_rate": 4.0776768078612207e-07, "epoch": 1.6937354988399071, "percentage": 56.59, "elapsed_time": "1:29:58", "remaining_time": "1:09:01"}
+{"current_steps": 370, "total_steps": 645, "loss": 0.8785, "learning_rate": 3.9564091683833244e-07, "epoch": 1.716937354988399, "percentage": 57.36, "elapsed_time": "1:31:01", "remaining_time": "1:07:38"}
+{"current_steps": 375, "total_steps": 645, "loss": 0.8772, "learning_rate": 3.835780086996793e-07, "epoch": 1.740139211136891, "percentage": 58.14, "elapsed_time": "1:32:03", "remaining_time": "1:06:16"}
+{"current_steps": 380, "total_steps": 645, "loss": 0.8701, "learning_rate": 3.7158633748866607e-07, "epoch": 1.7633410672853829, "percentage": 58.91, "elapsed_time": "1:33:06", "remaining_time": "1:04:55"}
+{"current_steps": 385, "total_steps": 645, "loss": 0.871, "learning_rate": 3.596732407349536e-07, "epoch": 1.7865429234338746, "percentage": 59.69, "elapsed_time": "1:34:08", "remaining_time": "1:03:34"}
+{"current_steps": 390, "total_steps": 645, "loss": 0.8751, "learning_rate": 3.4784600788963193e-07, "epoch": 1.8097447795823665, "percentage": 60.47, "elapsed_time": "1:35:10", "remaining_time": "1:02:13"}
+{"current_steps": 395, "total_steps": 645, "loss": 0.8687, "learning_rate": 3.3611187586491157e-07, "epoch": 1.8329466357308584, "percentage": 61.24, "elapsed_time": "1:36:12", "remaining_time": "1:00:53"}
+{"current_steps": 400, "total_steps": 645, "loss": 0.8818, "learning_rate": 3.244780246059612e-07, "epoch": 1.8561484918793503, "percentage": 62.02, "elapsed_time": "1:37:15", "remaining_time": "0:59:34"}
+{"current_steps": 400, "total_steps": 645, "eval_loss": 0.996471107006073, "epoch": 1.8561484918793503, "percentage": 62.02, "elapsed_time": "1:39:01", "remaining_time": "1:00:39"}
+{"current_steps": 405, "total_steps": 645, "loss": 0.8753, "learning_rate": 3.129515726976034e-07, "epoch": 1.8793503480278422, "percentage": 62.79, "elapsed_time": "1:40:35", "remaining_time": "0:59:36"}
+{"current_steps": 410, "total_steps": 645, "loss": 0.8731, "learning_rate": 3.015395730085565e-07, "epoch": 1.902552204176334, "percentage": 63.57, "elapsed_time": "1:41:37", "remaining_time": "0:58:14"}
+{"current_steps": 415, "total_steps": 645, "loss": 0.8752, "learning_rate": 2.902490083758856e-07, "epoch": 1.925754060324826, "percentage": 64.34, "elapsed_time": "1:42:39", "remaining_time": "0:56:53"}
+{"current_steps": 420, "total_steps": 645, "loss": 0.8879, "learning_rate": 2.790867873323067e-07, "epoch": 1.948955916473318, "percentage": 65.12, "elapsed_time": "1:43:41", "remaining_time": "0:55:32"}
+{"current_steps": 425, "total_steps": 645, "loss": 0.8728, "learning_rate": 2.680597398789554e-07, "epoch": 1.9721577726218098, "percentage": 65.89, "elapsed_time": "1:44:43", "remaining_time": "0:54:12"}
+{"current_steps": 430, "total_steps": 645, "loss": 0.8786, "learning_rate": 2.5717461330620815e-07, "epoch": 1.9953596287703017, "percentage": 66.67, "elapsed_time": "1:45:46", "remaining_time": "0:52:53"}
+{"current_steps": 435, "total_steps": 645, "loss": 0.8171, "learning_rate": 2.464380680651134e-07, "epoch": 2.0185614849187936, "percentage": 67.44, "elapsed_time": "1:46:49", "remaining_time": "0:51:34"}
+{"current_steps": 440, "total_steps": 645, "loss": 0.7862, "learning_rate": 2.358566736919581e-07, "epoch": 2.0417633410672855, "percentage": 68.22, "elapsed_time": "1:47:52", "remaining_time": "0:50:15"}
+{"current_steps": 445, "total_steps": 645, "loss": 0.789, "learning_rate": 2.2543690478846388e-07, "epoch": 2.0649651972157774, "percentage": 68.99, "elapsed_time": "1:48:54", "remaining_time": "0:48:56"}
+{"current_steps": 450, "total_steps": 645, "loss": 0.7851, "learning_rate": 2.1518513706007152e-07, "epoch": 2.0881670533642693, "percentage": 69.77, "elapsed_time": "1:49:57", "remaining_time": "0:47:38"}
+{"current_steps": 450, "total_steps": 645, "eval_loss": 1.0085411071777344, "epoch": 2.0881670533642693, "percentage": 69.77, "elapsed_time": "1:51:42", "remaining_time": "0:48:24"}
+{"current_steps": 455, "total_steps": 645, "loss": 0.8027, "learning_rate": 2.051076434147403e-07, "epoch": 2.111368909512761, "percentage": 70.54, "elapsed_time": "1:52:45", "remaining_time": "0:47:05"}
+{"current_steps": 460, "total_steps": 645, "loss": 0.7961, "learning_rate": 1.9521059012464607e-07, "epoch": 2.1345707656612527, "percentage": 71.32, "elapsed_time": "1:53:47", "remaining_time": "0:45:45"}
+{"current_steps": 465, "total_steps": 645, "loss": 0.7881, "learning_rate": 1.855000330531289e-07, "epoch": 2.1577726218097446, "percentage": 72.09, "elapsed_time": "1:54:50", "remaining_time": "0:44:27"}
+{"current_steps": 470, "total_steps": 645, "loss": 0.794, "learning_rate": 1.7598191394919737e-07, "epoch": 2.1809744779582365, "percentage": 72.87, "elapsed_time": "1:55:52", "remaining_time": "0:43:08"}
+{"current_steps": 475, "total_steps": 645, "loss": 0.7766, "learning_rate": 1.666620568118603e-07, "epoch": 2.2041763341067284, "percentage": 73.64, "elapsed_time": "1:56:55", "remaining_time": "0:41:50"}
+{"current_steps": 480, "total_steps": 645, "loss": 0.775, "learning_rate": 1.5754616432650443e-07, "epoch": 2.2273781902552203, "percentage": 74.42, "elapsed_time": "1:57:57", "remaining_time": "0:40:32"}
+{"current_steps": 485, "total_steps": 645, "loss": 0.784, "learning_rate": 1.4863981437550498e-07, "epoch": 2.2505800464037122, "percentage": 75.19, "elapsed_time": "1:59:00", "remaining_time": "0:39:15"}
+{"current_steps": 490, "total_steps": 645, "loss": 0.7858, "learning_rate": 1.3994845662519983e-07, "epoch": 2.273781902552204, "percentage": 75.97, "elapsed_time": "2:00:03", "remaining_time": "0:37:58"}
+{"current_steps": 495, "total_steps": 645, "loss": 0.7676, "learning_rate": 1.3147740919131812e-07, "epoch": 2.296983758700696, "percentage": 76.74, "elapsed_time": "2:01:05", "remaining_time": "0:36:41"}
+{"current_steps": 500, "total_steps": 645, "loss": 0.7784, "learning_rate": 1.2323185538490228e-07, "epoch": 2.320185614849188, "percentage": 77.52, "elapsed_time": "2:02:08", "remaining_time": "0:35:25"}
+{"current_steps": 500, "total_steps": 645, "eval_loss": 1.0106791257858276, "epoch": 2.320185614849188, "percentage": 77.52, "elapsed_time": "2:03:53", "remaining_time": "0:35:55"}
+{"current_steps": 505, "total_steps": 645, "loss": 0.7911, "learning_rate": 1.1521684054071523e-07, "epoch": 2.34338747099768, "percentage": 78.29, "elapsed_time": "2:05:27", "remaining_time": "0:34:46"}
+{"current_steps": 510, "total_steps": 645, "loss": 0.7845, "learning_rate": 1.0743726893007254e-07, "epoch": 2.3665893271461718, "percentage": 79.07, "elapsed_time": "2:06:29", "remaining_time": "0:33:29"}
+{"current_steps": 515, "total_steps": 645, "loss": 0.7839, "learning_rate": 9.989790075999144e-08, "epoch": 2.3897911832946637, "percentage": 79.84, "elapsed_time": "2:07:32", "remaining_time": "0:32:11"}
+{"current_steps": 520, "total_steps": 645, "loss": 0.7797, "learning_rate": 9.260334926048785e-08, "epoch": 2.4129930394431556, "percentage": 80.62, "elapsed_time": "2:08:34", "remaining_time": "0:30:54"}
+{"current_steps": 525, "total_steps": 645, "loss": 0.7886, "learning_rate": 8.555807786180813e-08, "epoch": 2.4361948955916475, "percentage": 81.4, "elapsed_time": "2:09:37", "remaining_time": "0:29:37"}
+{"current_steps": 530, "total_steps": 645, "loss": 0.7798, "learning_rate": 7.876639746332131e-08, "epoch": 2.4593967517401394, "percentage": 82.17, "elapsed_time": "2:10:39", "remaining_time": "0:28:21"}
+{"current_steps": 535, "total_steps": 645, "loss": 0.779, "learning_rate": 7.223246379574205e-08, "epoch": 2.4825986078886313, "percentage": 82.95, "elapsed_time": "2:11:41", "remaining_time": "0:27:04"}
+{"current_steps": 540, "total_steps": 645, "loss": 0.7865, "learning_rate": 6.596027487829913e-08, "epoch": 2.505800464037123, "percentage": 83.72, "elapsed_time": "2:12:44", "remaining_time": "0:25:48"}
+{"current_steps": 545, "total_steps": 645, "loss": 0.7677, "learning_rate": 5.995366857240591e-08, "epoch": 2.529002320185615, "percentage": 84.5, "elapsed_time": "2:13:47", "remaining_time": "0:24:32"}
+{"current_steps": 550, "total_steps": 645, "loss": 0.7773, "learning_rate": 5.421632023332778e-08, "epoch": 2.5522041763341066, "percentage": 85.27, "elapsed_time": "2:14:49", "remaining_time": "0:23:17"}
+{"current_steps": 550, "total_steps": 645, "eval_loss": 1.0086498260498047, "epoch": 2.5522041763341066, "percentage": 85.27, "elapsed_time": "2:16:35", "remaining_time": "0:23:35"}
+{"current_steps": 555, "total_steps": 645, "loss": 0.7898, "learning_rate": 4.8751740461286826e-08, "epoch": 2.5754060324825985, "percentage": 86.05, "elapsed_time": "2:17:38", "remaining_time": "0:22:19"}
+{"current_steps": 560, "total_steps": 645, "loss": 0.789, "learning_rate": 4.356327295337542e-08, "epoch": 2.5986078886310904, "percentage": 86.82, "elapsed_time": "2:18:40", "remaining_time": "0:21:02"}
+{"current_steps": 565, "total_steps": 645, "loss": 0.7859, "learning_rate": 3.865409245759671e-08, "epoch": 2.6218097447795823, "percentage": 87.6, "elapsed_time": "2:19:43", "remaining_time": "0:19:47"}
+{"current_steps": 570, "total_steps": 645, "loss": 0.7909, "learning_rate": 3.402720283028277e-08, "epoch": 2.645011600928074, "percentage": 88.37, "elapsed_time": "2:20:46", "remaining_time": "0:18:31"}
+{"current_steps": 575, "total_steps": 645, "loss": 0.7861, "learning_rate": 2.968543519807809e-08, "epoch": 2.668213457076566, "percentage": 89.15, "elapsed_time": "2:21:48", "remaining_time": "0:17:15"}
+{"current_steps": 580, "total_steps": 645, "loss": 0.782, "learning_rate": 2.5631446225614527e-08, "epoch": 2.691415313225058, "percentage": 89.92, "elapsed_time": "2:22:51", "remaining_time": "0:16:00"}
+{"current_steps": 585, "total_steps": 645, "loss": 0.7801, "learning_rate": 2.1867716489936294e-08, "epoch": 2.71461716937355, "percentage": 90.7, "elapsed_time": "2:23:53", "remaining_time": "0:14:45"}
+{"current_steps": 590, "total_steps": 645, "loss": 0.7855, "learning_rate": 1.8396548962671454e-08, "epoch": 2.737819025522042, "percentage": 91.47, "elapsed_time": "2:24:55", "remaining_time": "0:13:30"}
+{"current_steps": 595, "total_steps": 645, "loss": 0.7837, "learning_rate": 1.5220067600876684e-08, "epoch": 2.7610208816705337, "percentage": 92.25, "elapsed_time": "2:25:57", "remaining_time": "0:12:15"}
+{"current_steps": 600, "total_steps": 645, "loss": 0.784, "learning_rate": 1.2340216047418694e-08, "epoch": 2.7842227378190256, "percentage": 93.02, "elapsed_time": "2:27:00", "remaining_time": "0:11:01"}
+{"current_steps": 600, "total_steps": 645, "eval_loss": 1.0076881647109985, "epoch": 2.7842227378190256, "percentage": 93.02, "elapsed_time": "2:28:45", "remaining_time": "0:11:09"}
+{"current_steps": 605, "total_steps": 645, "loss": 0.789, "learning_rate": 9.758756441687332e-09, "epoch": 2.8074245939675175, "percentage": 93.8, "elapsed_time": "2:30:19", "remaining_time": "0:09:56"}
+{"current_steps": 610, "total_steps": 645, "loss": 0.7827, "learning_rate": 7.477268341368359e-09, "epoch": 2.8306264501160094, "percentage": 94.57, "elapsed_time": "2:31:21", "remaining_time": "0:08:41"}
+{"current_steps": 615, "total_steps": 645, "loss": 0.7729, "learning_rate": 5.497147755934628e-09, "epoch": 2.853828306264501, "percentage": 95.35, "elapsed_time": "2:32:23", "remaining_time": "0:07:26"}
+{"current_steps": 620, "total_steps": 645, "loss": 0.7741, "learning_rate": 3.819606292448541e-09, "epoch": 2.877030162412993, "percentage": 96.12, "elapsed_time": "2:33:26", "remaining_time": "0:06:11"}
+{"current_steps": 625, "total_steps": 645, "loss": 0.7799, "learning_rate": 2.4456704141967433e-09, "epoch": 2.9002320185614847, "percentage": 96.9, "elapsed_time": "2:34:28", "remaining_time": "0:04:56"}
+{"current_steps": 630, "total_steps": 645, "loss": 0.7855, "learning_rate": 1.3761808126126483e-09, "epoch": 2.9234338747099766, "percentage": 97.67, "elapsed_time": "2:35:31", "remaining_time": "0:03:42"}
+{"current_steps": 635, "total_steps": 645, "loss": 0.7758, "learning_rate": 6.117918928693622e-10, "epoch": 2.9466357308584685, "percentage": 98.45, "elapsed_time": "2:36:33", "remaining_time": "0:02:27"}
+{"current_steps": 640, "total_steps": 645, "loss": 0.7781, "learning_rate": 1.529713734584326e-10, "epoch": 2.9698375870069604, "percentage": 99.22, "elapsed_time": "2:37:36", "remaining_time": "0:01:13"}
+{"current_steps": 645, "total_steps": 645, "loss": 0.782, "learning_rate": 0.0, "epoch": 2.9930394431554523, "percentage": 100.0, "elapsed_time": "2:38:38", "remaining_time": "0:00:00"}
+{"current_steps": 645, "total_steps": 645, "epoch": 2.9930394431554523, "percentage": 100.0, "elapsed_time": "2:39:10", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1041 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9930394431554523,
+  "eval_steps": 50,
+  "global_step": 645,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02320185614849188,
+      "grad_norm": 26.745355095184312,
+      "learning_rate": 5e-07,
+      "loss": 1.6569,
+      "step": 5
+    },
+    {
+      "epoch": 0.04640371229698376,
+      "grad_norm": 13.080188660738868,
+      "learning_rate": 1e-06,
+      "loss": 1.5099,
+      "step": 10
+    },
+    {
+      "epoch": 0.06960556844547564,
+      "grad_norm": 7.775505635686351,
+      "learning_rate": 9.998470286265414e-07,
+      "loss": 1.2782,
+      "step": 15
+    },
+    {
+      "epoch": 0.09280742459396751,
+      "grad_norm": 6.492859712313467,
+      "learning_rate": 9.993882081071305e-07,
+      "loss": 1.2359,
+      "step": 20
+    },
+    {
+      "epoch": 0.11600928074245939,
+      "grad_norm": 5.355551984540261,
+      "learning_rate": 9.986238191873872e-07,
+      "loss": 1.204,
+      "step": 25
+    },
+    {
+      "epoch": 0.13921113689095127,
+      "grad_norm": 5.125393165293572,
+      "learning_rate": 9.975543295858033e-07,
+      "loss": 1.1627,
+      "step": 30
+    },
+    {
+      "epoch": 0.16241299303944315,
+      "grad_norm": 4.710071299991241,
+      "learning_rate": 9.961803937075514e-07,
+      "loss": 1.1463,
+      "step": 35
+    },
+    {
+      "epoch": 0.18561484918793503,
+      "grad_norm": 5.029376799191572,
+      "learning_rate": 9.945028522440653e-07,
+      "loss": 1.1394,
+      "step": 40
+    },
+    {
+      "epoch": 0.2088167053364269,
+      "grad_norm": 4.763291242870039,
+      "learning_rate": 9.925227316586314e-07,
+      "loss": 1.1371,
+      "step": 45
+    },
+    {
+      "epoch": 0.23201856148491878,
+      "grad_norm": 4.903033982523367,
+      "learning_rate": 9.902412435583125e-07,
+      "loss": 1.1181,
+      "step": 50
+    },
+    {
+      "epoch": 0.23201856148491878,
+      "eval_loss": 1.1214605569839478,
+      "eval_runtime": 105.8329,
+      "eval_samples_per_second": 57.912,
+      "eval_steps_per_second": 0.907,
+      "step": 50
+    },
+    {
+      "epoch": 0.2552204176334107,
+      "grad_norm": 4.785575700738186,
+      "learning_rate": 9.876597839525813e-07,
+      "loss": 1.1163,
+      "step": 55
+    },
+    {
+      "epoch": 0.27842227378190254,
+      "grad_norm": 4.600727000401806,
+      "learning_rate": 9.847799323991233e-07,
+      "loss": 1.1232,
+      "step": 60
+    },
+    {
+      "epoch": 0.30162412993039445,
+      "grad_norm": 4.8200416840356315,
+      "learning_rate": 9.816034510373285e-07,
+      "loss": 1.125,
+      "step": 65
+    },
+    {
+      "epoch": 0.3248259860788863,
+      "grad_norm": 4.958997518359378,
+      "learning_rate": 9.781322835100637e-07,
+      "loss": 1.108,
+      "step": 70
+    },
+    {
+      "epoch": 0.3480278422273782,
+      "grad_norm": 4.883541365508776,
+      "learning_rate": 9.743685537743856e-07,
+      "loss": 1.106,
+      "step": 75
+    },
+    {
+      "epoch": 0.37122969837587005,
+      "grad_norm": 4.973507458353338,
+      "learning_rate": 9.70314564801922e-07,
+      "loss": 1.0973,
+      "step": 80
+    },
+    {
+      "epoch": 0.39443155452436196,
+      "grad_norm": 4.704415990191669,
+      "learning_rate": 9.659727971697173e-07,
+      "loss": 1.0964,
+      "step": 85
+    },
+    {
+      "epoch": 0.4176334106728538,
+      "grad_norm": 4.759885977268913,
+      "learning_rate": 9.613459075424033e-07,
+      "loss": 1.0956,
+      "step": 90
+    },
+    {
+      "epoch": 0.4408352668213457,
+      "grad_norm": 4.868535908803129,
+      "learning_rate": 9.564367270466245e-07,
+      "loss": 1.0787,
+      "step": 95
+    },
+    {
+      "epoch": 0.46403712296983757,
+      "grad_norm": 5.180286116736628,
+      "learning_rate": 9.51248259538713e-07,
+      "loss": 1.0765,
+      "step": 100
+    },
+    {
+      "epoch": 0.46403712296983757,
+      "eval_loss": 1.0775035619735718,
+      "eval_runtime": 105.5293,
+      "eval_samples_per_second": 58.079,
+      "eval_steps_per_second": 0.91,
+      "step": 100
+    },
+    {
+      "epoch": 0.4872389791183295,
+      "grad_norm": 5.290465762761348,
+      "learning_rate": 9.457836797666721e-07,
+      "loss": 1.0903,
+      "step": 105
+    },
+    {
+      "epoch": 0.5104408352668214,
+      "grad_norm": 4.81291157554945,
+      "learning_rate": 9.400463314275941e-07,
+      "loss": 1.0697,
+      "step": 110
+    },
+    {
+      "epoch": 0.5336426914153132,
+      "grad_norm": 4.914554202012043,
+      "learning_rate": 9.340397251217008e-07,
+      "loss": 1.0668,
+      "step": 115
+    },
+    {
+      "epoch": 0.5568445475638051,
+      "grad_norm": 5.240457841494325,
+      "learning_rate": 9.27767536204258e-07,
+      "loss": 1.0676,
+      "step": 120
+    },
+    {
+      "epoch": 0.580046403712297,
+      "grad_norm": 4.957459385263701,
+      "learning_rate": 9.212336025366787e-07,
+      "loss": 1.0746,
+      "step": 125
+    },
+    {
+      "epoch": 0.6032482598607889,
+      "grad_norm": 5.29032668711839,
+      "learning_rate": 9.144419221381918e-07,
+      "loss": 1.0724,
+      "step": 130
+    },
+    {
+      "epoch": 0.6264501160092807,
+      "grad_norm": 4.908560953587426,
+      "learning_rate": 9.073966507395121e-07,
+      "loss": 1.0745,
+      "step": 135
+    },
+    {
+      "epoch": 0.6496519721577726,
+      "grad_norm": 4.912842113728852,
+      "learning_rate": 9.001020992400085e-07,
+      "loss": 1.0559,
+      "step": 140
+    },
+    {
+      "epoch": 0.6728538283062645,
+      "grad_norm": 5.088585906783296,
+      "learning_rate": 8.925627310699274e-07,
+      "loss": 1.0705,
+      "step": 145
+    },
+    {
+      "epoch": 0.6960556844547564,
+      "grad_norm": 5.140684832177941,
+      "learning_rate": 8.84783159459285e-07,
+      "loss": 1.0639,
+      "step": 150
+    },
+    {
+      "epoch": 0.6960556844547564,
+      "eval_loss": 1.0501643419265747,
+      "eval_runtime": 105.4561,
+      "eval_samples_per_second": 58.119,
+      "eval_steps_per_second": 0.91,
+      "step": 150
+    },
+    {
+      "epoch": 0.7192575406032483,
+      "grad_norm": 5.311257433234373,
+      "learning_rate": 8.767681446150976e-07,
+      "loss": 1.0472,
+      "step": 155
+    },
+    {
+      "epoch": 0.7424593967517401,
+      "grad_norm": 5.091539509688025,
+      "learning_rate": 8.68522590808682e-07,
+      "loss": 1.0645,
+      "step": 160
+    },
+    {
+      "epoch": 0.765661252900232,
+      "grad_norm": 5.132013982763288,
+      "learning_rate": 8.600515433748001e-07,
+      "loss": 1.0416,
+      "step": 165
+    },
+    {
+      "epoch": 0.7888631090487239,
+      "grad_norm": 4.753354098230195,
+      "learning_rate": 8.51360185624495e-07,
+      "loss": 1.0478,
+      "step": 170
+    },
+    {
+      "epoch": 0.8120649651972158,
+      "grad_norm": 5.029473978539478,
+      "learning_rate": 8.424538356734956e-07,
+      "loss": 1.0383,
+      "step": 175
+    },
+    {
+      "epoch": 0.8352668213457076,
+      "grad_norm": 4.9588553004593345,
+      "learning_rate": 8.333379431881397e-07,
+      "loss": 1.0342,
+      "step": 180
+    },
+    {
+      "epoch": 0.8584686774941995,
+      "grad_norm": 5.234591483099779,
+      "learning_rate": 8.240180860508026e-07,
+      "loss": 1.0413,
+      "step": 185
+    },
+    {
+      "epoch": 0.8816705336426914,
+      "grad_norm": 5.121566469508508,
+      "learning_rate": 8.144999669468713e-07,
+      "loss": 1.0264,
+      "step": 190
+    },
+    {
+      "epoch": 0.9048723897911833,
+      "grad_norm": 5.0479045768726305,
+      "learning_rate": 8.047894098753539e-07,
+      "loss": 1.028,
+      "step": 195
+    },
+    {
+      "epoch": 0.9280742459396751,
+      "grad_norm": 5.0838098259091185,
+      "learning_rate": 7.948923565852597e-07,
+      "loss": 1.0308,
+      "step": 200
+    },
+    {
+      "epoch": 0.9280742459396751,
+      "eval_loss": 1.0281875133514404,
+      "eval_runtime": 105.8568,
+      "eval_samples_per_second": 57.899,
+      "eval_steps_per_second": 0.907,
+      "step": 200
+    },
+    {
+      "epoch": 0.951276102088167,
+      "grad_norm": 5.3244675969022826,
+      "learning_rate": 7.848148629399285e-07,
+      "loss": 1.0262,
+      "step": 205
+    },
+    {
+      "epoch": 0.974477958236659,
+      "grad_norm": 4.9307215762355305,
+      "learning_rate": 7.745630952115363e-07,
+      "loss": 1.0349,
+      "step": 210
+    },
+    {
+      "epoch": 0.9976798143851509,
+      "grad_norm": 4.994203203030838,
+      "learning_rate": 7.641433263080418e-07,
+      "loss": 1.0216,
+      "step": 215
+    },
+    {
+      "epoch": 1.0208816705336428,
+      "grad_norm": 5.112958880673586,
+      "learning_rate": 7.535619319348865e-07,
+      "loss": 0.9241,
+      "step": 220
+    },
+    {
+      "epoch": 1.0440835266821347,
+      "grad_norm": 5.264187445397404,
+      "learning_rate": 7.428253866937918e-07,
+      "loss": 0.9001,
+      "step": 225
+    },
+    {
+      "epoch": 1.0672853828306264,
+      "grad_norm": 5.645584402922182,
+      "learning_rate": 7.319402601210447e-07,
+      "loss": 0.8916,
+      "step": 230
+    },
+    {
+      "epoch": 1.0904872389791183,
+      "grad_norm": 5.655360994963379,
+      "learning_rate": 7.209132126676933e-07,
+      "loss": 0.8876,
+      "step": 235
+    },
+    {
+      "epoch": 1.1136890951276102,
+      "grad_norm": 5.3773890810778795,
+      "learning_rate": 7.097509916241145e-07,
+      "loss": 0.8931,
+      "step": 240
+    },
+    {
+      "epoch": 1.136890951276102,
+      "grad_norm": 5.658881203794,
+      "learning_rate": 6.984604269914436e-07,
+      "loss": 0.905,
+      "step": 245
+    },
+    {
+      "epoch": 1.160092807424594,
+      "grad_norm": 5.966282577193694,
+      "learning_rate": 6.870484273023967e-07,
+      "loss": 0.9038,
+      "step": 250
+    },
+    {
+      "epoch": 1.160092807424594,
+      "eval_loss": 1.0220295190811157,
+      "eval_runtime": 105.8362,
+      "eval_samples_per_second": 57.91,
+      "eval_steps_per_second": 0.907,
+      "step": 250
+    },
+    {
+      "epoch": 1.1832946635730859,
+      "grad_norm": 5.794176185315156,
+      "learning_rate": 6.755219753940388e-07,
+      "loss": 0.8964,
+      "step": 255
+    },
+    {
+      "epoch": 1.2064965197215778,
+      "grad_norm": 6.603391500331007,
+      "learning_rate": 6.638881241350883e-07,
+      "loss": 0.8898,
+      "step": 260
+    },
+    {
+      "epoch": 1.2296983758700697,
+      "grad_norm": 5.5914639272443205,
+      "learning_rate": 6.52153992110368e-07,
+      "loss": 0.8951,
+      "step": 265
+    },
+    {
+      "epoch": 1.2529002320185616,
+      "grad_norm": 5.339661007608592,
+      "learning_rate": 6.403267592650466e-07,
+      "loss": 0.8961,
+      "step": 270
+    },
+    {
+      "epoch": 1.2761020881670533,
+      "grad_norm": 5.448280965038798,
+      "learning_rate": 6.28413662511334e-07,
+      "loss": 0.8919,
+      "step": 275
+    },
+    {
+      "epoch": 1.2993039443155452,
+      "grad_norm": 5.476822697700394,
+      "learning_rate": 6.164219913003207e-07,
+      "loss": 0.8931,
+      "step": 280
+    },
+    {
+      "epoch": 1.322505800464037,
+      "grad_norm": 5.783548079343189,
+      "learning_rate": 6.043590831616676e-07,
+      "loss": 0.8792,
+      "step": 285
+    },
+    {
+      "epoch": 1.345707656612529,
+      "grad_norm": 5.59782698134665,
+      "learning_rate": 5.92232319213878e-07,
+      "loss": 0.8768,
+      "step": 290
+    },
+    {
+      "epoch": 1.368909512761021,
+      "grad_norm": 5.193853086769952,
+      "learning_rate": 5.800491196478988e-07,
+      "loss": 0.8788,
+      "step": 295
+    },
+    {
+      "epoch": 1.3921113689095128,
+      "grad_norm": 5.539347488257,
+      "learning_rate": 5.678169391868127e-07,
+      "loss": 0.8973,
+      "step": 300
+    },
+    {
+      "epoch": 1.3921113689095128,
+      "eval_loss": 1.0114275217056274,
+      "eval_runtime": 106.216,
+      "eval_samples_per_second": 57.703,
+      "eval_steps_per_second": 0.904,
+      "step": 300
+    },
+    {
+      "epoch": 1.4153132250580047,
+      "grad_norm": 5.567338787725618,
+      "learning_rate": 5.555432625244023e-07,
+      "loss": 0.8831,
+      "step": 305
+    },
+    {
+      "epoch": 1.4385150812064964,
+      "grad_norm": 5.412598997121907,
+      "learning_rate": 5.432355997453728e-07,
+      "loss": 0.8848,
+      "step": 310
+    },
+    {
+      "epoch": 1.4617169373549883,
+      "grad_norm": 5.4356510240439775,
+      "learning_rate": 5.309014817300421e-07,
+      "loss": 0.8999,
+      "step": 315
+    },
+    {
+      "epoch": 1.4849187935034802,
+      "grad_norm": 5.525607667062919,
+      "learning_rate": 5.185484555463026e-07,
+      "loss": 0.8901,
+      "step": 320
+    },
+    {
+      "epoch": 1.5081206496519721,
+      "grad_norm": 5.583006624663847,
+      "learning_rate": 5.061840798316814e-07,
+      "loss": 0.8909,
+      "step": 325
+    },
+    {
+      "epoch": 1.531322505800464,
+      "grad_norm": 5.822776934487761,
+      "learning_rate": 4.938159201683186e-07,
+      "loss": 0.8829,
+      "step": 330
+    },
+    {
+      "epoch": 1.554524361948956,
+      "grad_norm": 5.427885443572571,
+      "learning_rate": 4.814515444536974e-07,
+      "loss": 0.8867,
+      "step": 335
+    },
+    {
+      "epoch": 1.5777262180974478,
+      "grad_norm": 5.513594905050496,
+      "learning_rate": 4.69098518269958e-07,
+      "loss": 0.892,
+      "step": 340
+    },
+    {
+      "epoch": 1.6009280742459397,
+      "grad_norm": 5.785273130658459,
+      "learning_rate": 4.5676440025462726e-07,
+      "loss": 0.8775,
+      "step": 345
+    },
+    {
+      "epoch": 1.6241299303944317,
+      "grad_norm": 5.494906178164733,
+      "learning_rate": 4.444567374755977e-07,
+      "loss": 0.8747,
+      "step": 350
+    },
+    {
+      "epoch": 1.6241299303944317,
+      "eval_loss": 1.0039345026016235,
+      "eval_runtime": 105.8025,
+      "eval_samples_per_second": 57.929,
+      "eval_steps_per_second": 0.907,
+      "step": 350
+    },
+    {
+      "epoch": 1.6473317865429236,
+      "grad_norm": 5.49251321009188,
+      "learning_rate": 4.3218306081318713e-07,
+      "loss": 0.884,
+      "step": 355
+    },
+    {
+      "epoch": 1.6705336426914155,
+      "grad_norm": 5.618196571147986,
+      "learning_rate": 4.199508803521012e-07,
+      "loss": 0.8945,
+      "step": 360
+    },
+    {
+      "epoch": 1.6937354988399071,
+      "grad_norm": 5.908619967180135,
+      "learning_rate": 4.0776768078612207e-07,
+      "loss": 0.8793,
+      "step": 365
+    },
+    {
+      "epoch": 1.716937354988399,
+      "grad_norm": 5.822870470090775,
+      "learning_rate": 3.9564091683833244e-07,
+      "loss": 0.8785,
+      "step": 370
+    },
+    {
+      "epoch": 1.740139211136891,
+      "grad_norm": 5.685661727934108,
+      "learning_rate": 3.835780086996793e-07,
+      "loss": 0.8772,
+      "step": 375
+    },
+    {
+      "epoch": 1.7633410672853829,
+      "grad_norm": 5.692617224399981,
+      "learning_rate": 3.7158633748866607e-07,
+      "loss": 0.8701,
+      "step": 380
+    },
+    {
+      "epoch": 1.7865429234338746,
+      "grad_norm": 5.6393286368292355,
+      "learning_rate": 3.596732407349536e-07,
+      "loss": 0.871,
+      "step": 385
+    },
+    {
+      "epoch": 1.8097447795823665,
+      "grad_norm": 5.672110777773612,
+      "learning_rate": 3.4784600788963193e-07,
+      "loss": 0.8751,
+      "step": 390
+    },
+    {
+      "epoch": 1.8329466357308584,
+      "grad_norm": 5.835389029793195,
+      "learning_rate": 3.3611187586491157e-07,
+      "loss": 0.8687,
+      "step": 395
+    },
+    {
+      "epoch": 1.8561484918793503,
+      "grad_norm": 5.386053225084359,
+      "learning_rate": 3.244780246059612e-07,
+      "loss": 0.8818,
+      "step": 400
+    },
+    {
+      "epoch": 1.8561484918793503,
+      "eval_loss": 0.996471107006073,
+      "eval_runtime": 105.8008,
+      "eval_samples_per_second": 57.93,
+      "eval_steps_per_second": 0.907,
+      "step": 400
+    },
+    {
+      "epoch": 1.8793503480278422,
+      "grad_norm": 5.480011457003802,
+      "learning_rate": 3.129515726976034e-07,
+      "loss": 0.8753,
+      "step": 405
+    },
+    {
+      "epoch": 1.902552204176334,
+      "grad_norm": 5.823910567007799,
+      "learning_rate": 3.015395730085565e-07,
+      "loss": 0.8731,
+      "step": 410
+    },
+    {
+      "epoch": 1.925754060324826,
+      "grad_norm": 5.629571730016235,
+      "learning_rate": 2.902490083758856e-07,
+      "loss": 0.8752,
+      "step": 415
+    },
+    {
+      "epoch": 1.948955916473318,
+      "grad_norm": 5.503089045781313,
+      "learning_rate": 2.790867873323067e-07,
+      "loss": 0.8879,
+      "step": 420
+    },
+    {
+      "epoch": 1.9721577726218098,
+      "grad_norm": 5.385767782543798,
+      "learning_rate": 2.680597398789554e-07,
+      "loss": 0.8728,
+      "step": 425
+    },
+    {
+      "epoch": 1.9953596287703017,
+      "grad_norm": 5.747520951511272,
+      "learning_rate": 2.5717461330620815e-07,
+      "loss": 0.8786,
+      "step": 430
+    },
+    {
+      "epoch": 2.0185614849187936,
+      "grad_norm": 6.233985626421451,
+      "learning_rate": 2.464380680651134e-07,
+      "loss": 0.8171,
+      "step": 435
+    },
+    {
+      "epoch": 2.0417633410672855,
+      "grad_norm": 6.389834673239529,
+      "learning_rate": 2.358566736919581e-07,
+      "loss": 0.7862,
+      "step": 440
+    },
+    {
+      "epoch": 2.0649651972157774,
+      "grad_norm": 5.666671581642326,
+      "learning_rate": 2.2543690478846388e-07,
+      "loss": 0.789,
+      "step": 445
+    },
+    {
+      "epoch": 2.0881670533642693,
+      "grad_norm": 5.935817576452604,
+      "learning_rate": 2.1518513706007152e-07,
+      "loss": 0.7851,
+      "step": 450
+    },
+    {
+      "epoch": 2.0881670533642693,
+      "eval_loss": 1.0085411071777344,
+      "eval_runtime": 105.7628,
+      "eval_samples_per_second": 57.95,
+      "eval_steps_per_second": 0.908,
+      "step": 450
+    },
+    {
+      "epoch": 2.111368909512761,
+      "grad_norm": 6.090381517467198,
+      "learning_rate": 2.051076434147403e-07,
+      "loss": 0.8027,
+      "step": 455
+    },
+    {
+      "epoch": 2.1345707656612527,
+      "grad_norm": 6.054221465181829,
+      "learning_rate": 1.9521059012464607e-07,
+      "loss": 0.7961,
+      "step": 460
+    },
+    {
+      "epoch": 2.1577726218097446,
+      "grad_norm": 6.13881987352279,
+      "learning_rate": 1.855000330531289e-07,
+      "loss": 0.7881,
+      "step": 465
+    },
+    {
+      "epoch": 2.1809744779582365,
+      "grad_norm": 5.9538509573599105,
+      "learning_rate": 1.7598191394919737e-07,
+      "loss": 0.794,
+      "step": 470
+    },
+    {
+      "epoch": 2.2041763341067284,
+      "grad_norm": 6.097297386772382,
+      "learning_rate": 1.666620568118603e-07,
+      "loss": 0.7766,
+      "step": 475
+    },
+    {
+      "epoch": 2.2273781902552203,
+      "grad_norm": 6.054056527354383,
+      "learning_rate": 1.5754616432650443e-07,
+      "loss": 0.775,
+      "step": 480
+    },
+    {
+      "epoch": 2.2505800464037122,
+      "grad_norm": 6.615286727024051,
+      "learning_rate": 1.4863981437550498e-07,
+      "loss": 0.784,
+      "step": 485
+    },
+    {
+      "epoch": 2.273781902552204,
+      "grad_norm": 6.027054222640892,
+      "learning_rate": 1.3994845662519983e-07,
+      "loss": 0.7858,
+      "step": 490
+    },
+    {
+      "epoch": 2.296983758700696,
+      "grad_norm": 6.07483919257801,
+      "learning_rate": 1.3147740919131812e-07,
+      "loss": 0.7676,
+      "step": 495
+    },
+    {
+      "epoch": 2.320185614849188,
+      "grad_norm": 5.967675794639106,
+      "learning_rate": 1.2323185538490228e-07,
+      "loss": 0.7784,
+      "step": 500
+    },
+    {
+      "epoch": 2.320185614849188,
+      "eval_loss": 1.0106791257858276,
+      "eval_runtime": 105.5124,
+      "eval_samples_per_second": 58.088,
+      "eval_steps_per_second": 0.91,
+      "step": 500
+    },
+    {
+      "epoch": 2.34338747099768,
+      "grad_norm": 6.054810430525525,
+      "learning_rate": 1.1521684054071523e-07,
+      "loss": 0.7911,
+      "step": 505
+    },
+    {
+      "epoch": 2.3665893271461718,
+      "grad_norm": 6.138500387539917,
+      "learning_rate": 1.0743726893007254e-07,
+      "loss": 0.7845,
+      "step": 510
+    },
+    {
+      "epoch": 2.3897911832946637,
+      "grad_norm": 6.348927557753904,
+      "learning_rate": 9.989790075999144e-08,
+      "loss": 0.7839,
+      "step": 515
+    },
+    {
+      "epoch": 2.4129930394431556,
+      "grad_norm": 6.417849773781747,
+      "learning_rate": 9.260334926048785e-08,
+      "loss": 0.7797,
+      "step": 520
+    },
+    {
+      "epoch": 2.4361948955916475,
+      "grad_norm": 5.884674838799749,
+      "learning_rate": 8.555807786180813e-08,
+      "loss": 0.7886,
+      "step": 525
+    },
+    {
+      "epoch": 2.4593967517401394,
+      "grad_norm": 5.804544655789366,
+      "learning_rate": 7.876639746332131e-08,
+      "loss": 0.7798,
+      "step": 530
+    },
+    {
+      "epoch": 2.4825986078886313,
+      "grad_norm": 5.958627298561463,
+      "learning_rate": 7.223246379574205e-08,
+      "loss": 0.779,
+      "step": 535
+    },
+    {
+      "epoch": 2.505800464037123,
+      "grad_norm": 6.388817649378131,
+      "learning_rate": 6.596027487829913e-08,
+      "loss": 0.7865,
+      "step": 540
+    },
+    {
+      "epoch": 2.529002320185615,
+      "grad_norm": 6.003273390035336,
+      "learning_rate": 5.995366857240591e-08,
+      "loss": 0.7677,
+      "step": 545
+    },
+    {
+      "epoch": 2.5522041763341066,
+      "grad_norm": 5.825668962659247,
+      "learning_rate": 5.421632023332778e-08,
+      "loss": 0.7773,
+      "step": 550
+    },
+    {
+      "epoch": 2.5522041763341066,
+      "eval_loss": 1.0086498260498047,
+      "eval_runtime": 105.6712,
+      "eval_samples_per_second": 58.001,
+      "eval_steps_per_second": 0.908,
+      "step": 550
+    },
+    {
+      "epoch": 2.5754060324825985,
+      "grad_norm": 5.802127812425504,
+      "learning_rate": 4.8751740461286826e-08,
+      "loss": 0.7898,
+      "step": 555
+    },
+    {
+      "epoch": 2.5986078886310904,
+      "grad_norm": 6.325532075096703,
+      "learning_rate": 4.356327295337542e-08,
+      "loss": 0.789,
+      "step": 560
+    },
+    {
+      "epoch": 2.6218097447795823,
+      "grad_norm": 5.941260110564892,
+      "learning_rate": 3.865409245759671e-08,
+      "loss": 0.7859,
+      "step": 565
+    },
+    {
+      "epoch": 2.645011600928074,
+      "grad_norm": 6.37567880053289,
+      "learning_rate": 3.402720283028277e-08,
+      "loss": 0.7909,
+      "step": 570
+    },
+    {
+      "epoch": 2.668213457076566,
+      "grad_norm": 6.239205173519981,
+      "learning_rate": 2.968543519807809e-08,
+      "loss": 0.7861,
+      "step": 575
+    },
+    {
+      "epoch": 2.691415313225058,
+      "grad_norm": 5.933276204870584,
+      "learning_rate": 2.5631446225614527e-08,
+      "loss": 0.782,
+      "step": 580
+    },
+    {
+      "epoch": 2.71461716937355,
+      "grad_norm": 5.950522022327479,
+      "learning_rate": 2.1867716489936294e-08,
+      "loss": 0.7801,
+      "step": 585
+    },
+    {
+      "epoch": 2.737819025522042,
+      "grad_norm": 5.995755253270831,
+      "learning_rate": 1.8396548962671454e-08,
+      "loss": 0.7855,
+      "step": 590
+    },
+    {
+      "epoch": 2.7610208816705337,
+      "grad_norm": 5.805329755980229,
+      "learning_rate": 1.5220067600876684e-08,
+      "loss": 0.7837,
+      "step": 595
+    },
+    {
+      "epoch": 2.7842227378190256,
+      "grad_norm": 5.774699503150204,
+      "learning_rate": 1.2340216047418694e-08,
+      "loss": 0.784,
+      "step": 600
+    },
+    {
+      "epoch": 2.7842227378190256,
+      "eval_loss": 1.0076881647109985,
+      "eval_runtime": 105.502,
+      "eval_samples_per_second": 58.094,
+      "eval_steps_per_second": 0.91,
+      "step": 600
+    },
+    {
+      "epoch": 2.8074245939675175,
+      "grad_norm": 5.826083780753947,
+      "learning_rate": 9.758756441687332e-09,
+      "loss": 0.789,
+      "step": 605
+    },
+    {
+      "epoch": 2.8306264501160094,
+      "grad_norm": 6.2351189691440165,
+      "learning_rate": 7.477268341368359e-09,
+      "loss": 0.7827,
+      "step": 610
+    },
+    {
+      "epoch": 2.853828306264501,
+      "grad_norm": 6.240042624521366,
+      "learning_rate": 5.497147755934628e-09,
+      "loss": 0.7729,
+      "step": 615
+    },
+    {
+      "epoch": 2.877030162412993,
+      "grad_norm": 6.055045568235345,
+      "learning_rate": 3.819606292448541e-09,
+      "loss": 0.7741,
+      "step": 620
+    },
+    {
+      "epoch": 2.9002320185614847,
+      "grad_norm": 6.022458929092381,
+      "learning_rate": 2.4456704141967433e-09,
+      "loss": 0.7799,
+      "step": 625
+    },
+    {
+      "epoch": 2.9234338747099766,
+      "grad_norm": 5.799562136804793,
+      "learning_rate": 1.3761808126126483e-09,
+      "loss": 0.7855,
+      "step": 630
+    },
+    {
+      "epoch": 2.9466357308584685,
+      "grad_norm": 5.88567918164354,
+      "learning_rate": 6.117918928693622e-10,
+      "loss": 0.7758,
+      "step": 635
+    },
+    {
+      "epoch": 2.9698375870069604,
+      "grad_norm": 6.126328207666765,
+      "learning_rate": 1.529713734584326e-10,
+      "loss": 0.7781,
+      "step": 640
+    },
+    {
+      "epoch": 2.9930394431554523,
+      "grad_norm": 5.625571183866048,
+      "learning_rate": 0.0,
+      "loss": 0.782,
+      "step": 645
+    },
+    {
+      "epoch": 2.9930394431554523,
+      "step": 645,
+      "total_flos": 3802978389590016.0,
+      "train_loss": 0.9273426562316658,
+      "train_runtime": 9552.8802,
+      "train_samples_per_second": 17.321,
+      "train_steps_per_second": 0.068
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 645,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3802978389590016.0,
+  "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:f3ceb7d9bafeb733e83af4f3f58148b0b871fe4b72416e89af0f3fa9f1f422b1
+size 7096