Instructions to use MANO066/Intervl3-1b-safety with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MANO066/Intervl3-1b-safety with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="MANO066/Intervl3-1b-safety", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MANO066/Intervl3-1b-safety", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MANO066/Intervl3-1b-safety with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MANO066/Intervl3-1b-safety"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MANO066/Intervl3-1b-safety",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/MANO066/Intervl3-1b-safety

SGLang

How to use MANO066/Intervl3-1b-safety with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "MANO066/Intervl3-1b-safety" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MANO066/Intervl3-1b-safety",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "MANO066/Intervl3-1b-safety" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MANO066/Intervl3-1b-safety",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use MANO066/Intervl3-1b-safety with Docker Model Runner:
```
docker model run hf.co/MANO066/Intervl3-1b-safety
```

MANO066 commited on Oct 13, 2025

Commit

b4af78c

verified ·

1 Parent(s): 9c43fb3

Upload folder using huggingface_hub

Browse files

Files changed (13) hide show

added_tokens.json +33 -0
all_results.json +8 -0
config.json +225 -0
generation_config.json +4 -0
merges.txt +0 -0
model.safetensors +3 -0
special_tokens_map.json +31 -0
tokenizer_config.json +281 -0
train_results.json +8 -0
trainer_state.json +1710 -0
training_args.bin +3 -0
training_log.txt +1 -0
vocab.json +0 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,33 @@

+{
+  "</box>": 151673,
+  "</img>": 151666,
+  "</quad>": 151669,
+  "</ref>": 151671,
+  "</tool_call>": 151658,
+  "<IMG_CONTEXT>": 151667,
+  "<box>": 151672,
+  "<img>": 151665,
+  "<quad>": 151668,
+  "<ref>": 151670,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 9.96,
+    "train_loss": 0.2612905190725412,
+    "train_runtime": 5871.1818,
+    "train_samples": 3600,
+    "train_samples_per_second": 6.132,
+    "train_steps_per_second": 0.048
+}

config.json ADDED Viewed

	@@ -0,0 +1,225 @@

+{
+  "_commit_hash": "4415a3b810e636d11dfa86b0e9ba40bb00535aa8",
+  "_name_or_path": "OpenGVLab/InternVL3-1B",
+  "architectures": [
+    "InternVLChatModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "OpenGVLab/InternVL3-1B--configuration_internvl_chat.InternVLChatConfig",
+    "AutoModel": "OpenGVLab/InternVL3-1B--modeling_internvl_chat.InternVLChatModel",
+    "AutoModelForCausalLM": "OpenGVLab/InternVL3-1B--modeling_internvl_chat.InternVLChatModel"
+  },
+  "downsample_ratio": 0.5,
+  "dynamic_image_size": true,
+  "force_image_size": 448,
+  "hidden_size": 896,
+  "image_fold": null,
+  "llm_config": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
+    "add_cross_attention": false,
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "attn_implementation": "flash_attention_2",
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 151643,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 151643,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 896,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4864,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 70,
+    "min_length": 0,
+    "model_type": "qwen2",
+    "moe_config": null,
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 14,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "factor": 2.0,
+      "rope_type": "dynamic",
+      "type": "dynamic"
+    },
+    "rope_theta": 1000000.0,
+    "sep_token_id": null,
+    "sliding_window": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.37.2",
+    "typical_p": 1.0,
+    "use_bfloat16": true,
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 151674
+  },
+  "max_dynamic_patch": 12,
+  "min_dynamic_patch": 1,
+  "model_type": "internvl_chat",
+  "pad2square": false,
+  "ps_version": "v2",
+  "select_layer": -1,
+  "system_message": null,
+  "template": "internvl2_5",
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": null,
+  "use_backbone_lora": 0,
+  "use_llm_lora": 0,
+  "use_thumbnail": true,
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
+    "add_cross_attention": false,
+    "architectures": [
+      "InternVisionModel"
+    ],
+    "attention_dropout": 0.0,
+    "auto_map": {
+      "AutoConfig": "configuration_intern_vit.InternVisionConfig",
+      "AutoModel": "modeling_intern_vit.InternVisionModel"
+    },
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "capacity_factor": 1.2,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.0,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "eval_capacity_factor": 1.4,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 448,
+    "initializer_factor": 0.1,
+    "initializer_range": 1e-10,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "laux_allreduce": "all_nodes",
+    "layer_norm_eps": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "intern_vit_6b",
+    "moe_coeff_ratio": 0.5,
+    "moe_intermediate_size": 768,
+    "moe_output_scale": 4.0,
+    "no_repeat_ngram_size": 0,
+    "noisy_gate_policy": "RSample_before",
+    "norm_type": "layer_norm",
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_experts": 8,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "num_routed_experts": 4,
+    "num_shared_experts": 4,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qk_normalization": false,
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "shared_expert_intermediate_size": 3072,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.37.2",
+    "typical_p": 1.0,
+    "use_bfloat16": true,
+    "use_flash_attn": true,
+    "use_moe": false,
+    "use_residual": true,
+    "use_rts": false,
+    "use_weighted_residual": false
+  }
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "_from_model_config": true,
+  "transformers_version": "4.37.2"
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:38dc0409f7418489b91325fa1154b568b3443a2840b9380ad16578a6e13d9a8c
+size 1876463472

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,31 @@

+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,281 @@

+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "</img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<IMG_CONTEXT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "</quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "</ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "</box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}{%- else %}{{- '<|im_start|>system\n你是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。<|im_end|>\n' }}{%- endif %}{% for message in messages %}{%- if messages[0]['role'] != 'system' or not loop.first %}{{'<|im_start|>' + message['role'] + '\n'}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<image>\n' }}{% elif content['type'] == 'video' %}{{ '<video>\n' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>\n'}}{%- endif %}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 16384,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 9.96,
+    "train_loss": 0.2612905190725412,
+    "train_runtime": 5871.1818,
+    "train_samples": 3600,
+    "train_samples_per_second": 6.132,
+    "train_steps_per_second": 0.048
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,1710 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.955555555555556,
+  "eval_steps": 500,
+  "global_step": 280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 10.1618,
+      "step": 1
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 10.1939,
+      "step": 2
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 9.4951,
+      "step": 3
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 8.6598,
+      "step": 4
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 7.2393,
+      "step": 5
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 3.9581,
+      "step": 6
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 2.0577,
+      "step": 7
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.8907,
+      "step": 8
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1e-05,
+      "loss": 0.3646,
+      "step": 9
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.999664033241933e-06,
+      "loss": 0.3316,
+      "step": 10
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.998656178117193e-06,
+      "loss": 0.29,
+      "step": 11
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.99697657006811e-06,
+      "loss": 0.3072,
+      "step": 12
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.99462543481167e-06,
+      "loss": 0.2946,
+      "step": 13
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.991603088309195e-06,
+      "loss": 0.2903,
+      "step": 14
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.98790993672386e-06,
+      "loss": 0.2589,
+      "step": 15
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.983546476366133e-06,
+      "loss": 0.2576,
+      "step": 16
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.978513293627068e-06,
+      "loss": 0.2416,
+      "step": 17
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.9728110648995e-06,
+      "loss": 0.271,
+      "step": 18
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.966440556487149e-06,
+      "loss": 0.2381,
+      "step": 19
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.959402624501636e-06,
+      "loss": 0.236,
+      "step": 20
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 9.951698214747441e-06,
+      "loss": 0.251,
+      "step": 21
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.943328362594788e-06,
+      "loss": 0.2417,
+      "step": 22
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 9.934294192840518e-06,
+      "loss": 0.225,
+      "step": 23
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 9.924596919556917e-06,
+      "loss": 0.191,
+      "step": 24
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.914237845928574e-06,
+      "loss": 0.1782,
+      "step": 25
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.903218364077242e-06,
+      "loss": 0.1757,
+      "step": 26
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.891539954874758e-06,
+      "loss": 0.1771,
+      "step": 27
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.879204187744036e-06,
+      "loss": 0.2267,
+      "step": 28
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.866212720448149e-06,
+      "loss": 0.1946,
+      "step": 29
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.852567298867557e-06,
+      "loss": 0.1474,
+      "step": 30
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 9.838269756765483e-06,
+      "loss": 0.2083,
+      "step": 31
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 9.823322015541474e-06,
+      "loss": 0.1316,
+      "step": 32
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 9.807726083973192e-06,
+      "loss": 0.17,
+      "step": 33
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 9.791484057946465e-06,
+      "loss": 0.1188,
+      "step": 34
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 9.774598120173625e-06,
+      "loss": 0.1894,
+      "step": 35
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 9.75707053990018e-06,
+      "loss": 0.1519,
+      "step": 36
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 9.738903672599858e-06,
+      "loss": 0.131,
+      "step": 37
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 9.720099959658062e-06,
+      "loss": 0.1622,
+      "step": 38
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 9.700661928043787e-06,
+      "loss": 0.1607,
+      "step": 39
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 9.680592189970015e-06,
+      "loss": 0.149,
+      "step": 40
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 9.659893442542683e-06,
+      "loss": 0.1657,
+      "step": 41
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 9.638568467398215e-06,
+      "loss": 0.1577,
+      "step": 42
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.61662013032972e-06,
+      "loss": 0.1561,
+      "step": 43
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.59405138090186e-06,
+      "loss": 0.1406,
+      "step": 44
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.570865252054462e-06,
+      "loss": 0.1226,
+      "step": 45
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.547064859694943e-06,
+      "loss": 0.1818,
+      "step": 46
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 9.52265340227957e-06,
+      "loss": 0.1775,
+      "step": 47
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 9.497634160383627e-06,
+      "loss": 0.1414,
+      "step": 48
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 9.472010496260545e-06,
+      "loss": 0.131,
+      "step": 49
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 9.445785853390074e-06,
+      "loss": 0.1127,
+      "step": 50
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 9.418963756015511e-06,
+      "loss": 0.1325,
+      "step": 51
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 9.391547808670097e-06,
+      "loss": 0.0949,
+      "step": 52
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 9.36354169569261e-06,
+      "loss": 0.1333,
+      "step": 53
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 9.334949180732245e-06,
+      "loss": 0.1793,
+      "step": 54
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 9.305774106242825e-06,
+      "loss": 0.1489,
+      "step": 55
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 9.276020392966423e-06,
+      "loss": 0.1751,
+      "step": 56
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 9.24569203940648e-06,
+      "loss": 0.1151,
+      "step": 57
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 9.214793121290442e-06,
+      "loss": 0.0944,
+      "step": 58
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.183327791022048e-06,
+      "loss": 0.1047,
+      "step": 59
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 9.1513002771233e-06,
+      "loss": 0.083,
+      "step": 60
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 9.118714883666204e-06,
+      "loss": 0.1001,
+      "step": 61
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 9.085575989694358e-06,
+      "loss": 0.0604,
+      "step": 62
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 9.051888048634471e-06,
+      "loss": 0.1303,
+      "step": 63
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 9.017655587697885e-06,
+      "loss": 0.1208,
+      "step": 64
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.982883207272164e-06,
+      "loss": 0.1053,
+      "step": 65
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.947575580302879e-06,
+      "loss": 0.1324,
+      "step": 66
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 8.911737451665616e-06,
+      "loss": 0.0858,
+      "step": 67
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 8.875373637528336e-06,
+      "loss": 0.0868,
+      "step": 68
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 8.838489024704131e-06,
+      "loss": 0.1172,
+      "step": 69
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 8.801088569994523e-06,
+      "loss": 0.0814,
+      "step": 70
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 8.763177299523318e-06,
+      "loss": 0.0874,
+      "step": 71
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 8.724760308061172e-06,
+      "loss": 0.0579,
+      "step": 72
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 8.685842758340912e-06,
+      "loss": 0.1138,
+      "step": 73
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 8.646429880363746e-06,
+      "loss": 0.0584,
+      "step": 74
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 8.60652697069641e-06,
+      "loss": 0.1309,
+      "step": 75
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 8.566139391759378e-06,
+      "loss": 0.1021,
+      "step": 76
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 8.525272571106242e-06,
+      "loss": 0.1037,
+      "step": 77
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 8.483932000694295e-06,
+      "loss": 0.1086,
+      "step": 78
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 8.442123236146509e-06,
+      "loss": 0.1019,
+      "step": 79
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.399851896004914e-06,
+      "loss": 0.0721,
+      "step": 80
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 8.357123660975553e-06,
+      "loss": 0.1472,
+      "step": 81
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 8.313944273165068e-06,
+      "loss": 0.0891,
+      "step": 82
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.270319535309035e-06,
+      "loss": 0.1329,
+      "step": 83
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 8.22625530999215e-06,
+      "loss": 0.0898,
+      "step": 84
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 8.181757518860387e-06,
+      "loss": 0.0509,
+      "step": 85
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 8.136832141825197e-06,
+      "loss": 0.0711,
+      "step": 86
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 8.091485216259886e-06,
+      "loss": 0.1521,
+      "step": 87
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 8.04572283618829e-06,
+      "loss": 0.1137,
+      "step": 88
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 7.999551151465793e-06,
+      "loss": 0.1022,
+      "step": 89
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 7.952976366952888e-06,
+      "loss": 0.0479,
+      "step": 90
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 7.906004741681321e-06,
+      "loss": 0.0639,
+      "step": 91
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 7.858642588012957e-06,
+      "loss": 0.0604,
+      "step": 92
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 7.810896270791484e-06,
+      "loss": 0.0461,
+      "step": 93
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 7.762772206487066e-06,
+      "loss": 0.0758,
+      "step": 94
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 7.714276862334051e-06,
+      "loss": 0.0912,
+      "step": 95
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 7.66541675546186e-06,
+      "loss": 0.0638,
+      "step": 96
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 7.616198452019176e-06,
+      "loss": 0.0333,
+      "step": 97
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 7.566628566291537e-06,
+      "loss": 0.1232,
+      "step": 98
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 7.516713759812465e-06,
+      "loss": 0.0526,
+      "step": 99
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 7.466460740468246e-06,
+      "loss": 0.0772,
+      "step": 100
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 7.4158762615964744e-06,
+      "loss": 0.0282,
+      "step": 101
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 7.3649671210785024e-06,
+      "loss": 0.0691,
+      "step": 102
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 7.313740160425887e-06,
+      "loss": 0.0929,
+      "step": 103
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 7.262202263860989e-06,
+      "loss": 0.064,
+      "step": 104
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 7.210360357391818e-06,
+      "loss": 0.0312,
+      "step": 105
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 7.1582214078812715e-06,
+      "loss": 0.1029,
+      "step": 106
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 7.1057924221108856e-06,
+      "loss": 0.1044,
+      "step": 107
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 7.053080445839211e-06,
+      "loss": 0.0535,
+      "step": 108
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 7.0000925628549595e-06,
+      "loss": 0.0562,
+      "step": 109
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 6.946835894025037e-06,
+      "loss": 0.101,
+      "step": 110
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 6.893317596337592e-06,
+      "loss": 0.0882,
+      "step": 111
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 6.839544861940214e-06,
+      "loss": 0.0468,
+      "step": 112
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 6.7855249171734e-06,
+      "loss": 0.076,
+      "step": 113
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 6.731265021599437e-06,
+      "loss": 0.0579,
+      "step": 114
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 6.676772467026809e-06,
+      "loss": 0.0441,
+      "step": 115
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 6.622054576530275e-06,
+      "loss": 0.0615,
+      "step": 116
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 6.5671187034667465e-06,
+      "loss": 0.1432,
+      "step": 117
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 6.511972230487091e-06,
+      "loss": 0.0455,
+      "step": 118
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 6.456622568544012e-06,
+      "loss": 0.0569,
+      "step": 119
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 6.401077155896098e-06,
+      "loss": 0.0484,
+      "step": 120
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 6.345343457108238e-06,
+      "loss": 0.0493,
+      "step": 121
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 6.289428962048467e-06,
+      "loss": 0.0627,
+      "step": 122
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 6.2333411848814415e-06,
+      "loss": 0.0393,
+      "step": 123
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 6.177087663058626e-06,
+      "loss": 0.0403,
+      "step": 124
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 6.120675956305363e-06,
+      "loss": 0.0705,
+      "step": 125
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 6.064113645604945e-06,
+      "loss": 0.0325,
+      "step": 126
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 6.007408332179836e-06,
+      "loss": 0.0549,
+      "step": 127
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 5.95056763647016e-06,
+      "loss": 0.0532,
+      "step": 128
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 5.893599197109625e-06,
+      "loss": 0.0659,
+      "step": 129
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 5.836510669898984e-06,
+      "loss": 0.0271,
+      "step": 130
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 5.7793097267772e-06,
+      "loss": 0.0657,
+      "step": 131
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 5.722004054790442e-06,
+      "loss": 0.0663,
+      "step": 132
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 5.664601355059044e-06,
+      "loss": 0.0398,
+      "step": 133
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 5.607109341742579e-06,
+      "loss": 0.0443,
+      "step": 134
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 5.5495357410031805e-06,
+      "loss": 0.0351,
+      "step": 135
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 5.491888289967241e-06,
+      "loss": 0.0328,
+      "step": 136
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 5.434174735685658e-06,
+      "loss": 0.0611,
+      "step": 137
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 5.376402834092721e-06,
+      "loss": 0.0557,
+      "step": 138
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 5.318580348963826e-06,
+      "loss": 0.0547,
+      "step": 139
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 5.260715050872119e-06,
+      "loss": 0.0421,
+      "step": 140
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 5.202814716144245e-06,
+      "loss": 0.083,
+      "step": 141
+    },
+    {
+      "epoch": 5.05,
+      "learning_rate": 5.144887125815301e-06,
+      "loss": 0.0348,
+      "step": 142
+    },
+    {
+      "epoch": 5.08,
+      "learning_rate": 5.086940064583179e-06,
+      "loss": 0.0231,
+      "step": 143
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 5.028981319762399e-06,
+      "loss": 0.0217,
+      "step": 144
+    },
+    {
+      "epoch": 5.16,
+      "learning_rate": 4.971018680237602e-06,
+      "loss": 0.0149,
+      "step": 145
+    },
+    {
+      "epoch": 5.19,
+      "learning_rate": 4.913059935416822e-06,
+      "loss": 0.0315,
+      "step": 146
+    },
+    {
+      "epoch": 5.23,
+      "learning_rate": 4.855112874184701e-06,
+      "loss": 0.0287,
+      "step": 147
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 4.797185283855756e-06,
+      "loss": 0.042,
+      "step": 148
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 4.7392849491278825e-06,
+      "loss": 0.0369,
+      "step": 149
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 4.681419651036177e-06,
+      "loss": 0.0249,
+      "step": 150
+    },
+    {
+      "epoch": 5.37,
+      "learning_rate": 4.6235971659072806e-06,
+      "loss": 0.0515,
+      "step": 151
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 4.565825264314344e-06,
+      "loss": 0.0617,
+      "step": 152
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 4.5081117100327594e-06,
+      "loss": 0.0519,
+      "step": 153
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 4.450464258996822e-06,
+      "loss": 0.0411,
+      "step": 154
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 4.392890658257421e-06,
+      "loss": 0.0644,
+      "step": 155
+    },
+    {
+      "epoch": 5.55,
+      "learning_rate": 4.335398644940958e-06,
+      "loss": 0.0709,
+      "step": 156
+    },
+    {
+      "epoch": 5.58,
+      "learning_rate": 4.277995945209558e-06,
+      "loss": 0.0558,
+      "step": 157
+    },
+    {
+      "epoch": 5.62,
+      "learning_rate": 4.220690273222802e-06,
+      "loss": 0.0335,
+      "step": 158
+    },
+    {
+      "epoch": 5.65,
+      "learning_rate": 4.163489330101017e-06,
+      "loss": 0.0496,
+      "step": 159
+    },
+    {
+      "epoch": 5.69,
+      "learning_rate": 4.106400802890377e-06,
+      "loss": 0.0252,
+      "step": 160
+    },
+    {
+      "epoch": 5.72,
+      "learning_rate": 4.049432363529842e-06,
+      "loss": 0.0379,
+      "step": 161
+    },
+    {
+      "epoch": 5.76,
+      "learning_rate": 3.992591667820166e-06,
+      "loss": 0.0435,
+      "step": 162
+    },
+    {
+      "epoch": 5.8,
+      "learning_rate": 3.935886354395057e-06,
+      "loss": 0.0253,
+      "step": 163
+    },
+    {
+      "epoch": 5.83,
+      "learning_rate": 3.8793240436946385e-06,
+      "loss": 0.0348,
+      "step": 164
+    },
+    {
+      "epoch": 5.87,
+      "learning_rate": 3.822912336941375e-06,
+      "loss": 0.0742,
+      "step": 165
+    },
+    {
+      "epoch": 5.9,
+      "learning_rate": 3.7666588151185584e-06,
+      "loss": 0.0388,
+      "step": 166
+    },
+    {
+      "epoch": 5.94,
+      "learning_rate": 3.7105710379515335e-06,
+      "loss": 0.045,
+      "step": 167
+    },
+    {
+      "epoch": 5.97,
+      "learning_rate": 3.6546565428917623e-06,
+      "loss": 0.0836,
+      "step": 168
+    },
+    {
+      "epoch": 6.01,
+      "learning_rate": 3.5989228441039024e-06,
+      "loss": 0.0301,
+      "step": 169
+    },
+    {
+      "epoch": 6.04,
+      "learning_rate": 3.543377431455991e-06,
+      "loss": 0.0243,
+      "step": 170
+    },
+    {
+      "epoch": 6.08,
+      "learning_rate": 3.4880277695129095e-06,
+      "loss": 0.0473,
+      "step": 171
+    },
+    {
+      "epoch": 6.12,
+      "learning_rate": 3.432881296533257e-06,
+      "loss": 0.0413,
+      "step": 172
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 3.377945423469727e-06,
+      "loss": 0.0394,
+      "step": 173
+    },
+    {
+      "epoch": 6.19,
+      "learning_rate": 3.323227532973193e-06,
+      "loss": 0.043,
+      "step": 174
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 3.268734978400564e-06,
+      "loss": 0.053,
+      "step": 175
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 3.214475082826602e-06,
+      "loss": 0.0172,
+      "step": 176
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 3.160455138059788e-06,
+      "loss": 0.0445,
+      "step": 177
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 3.1066824036624086e-06,
+      "loss": 0.0601,
+      "step": 178
+    },
+    {
+      "epoch": 6.36,
+      "learning_rate": 3.053164105974964e-06,
+      "loss": 0.0182,
+      "step": 179
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 2.999907437145042e-06,
+      "loss": 0.0437,
+      "step": 180
+    },
+    {
+      "epoch": 6.44,
+      "learning_rate": 2.946919554160792e-06,
+      "loss": 0.0159,
+      "step": 181
+    },
+    {
+      "epoch": 6.47,
+      "learning_rate": 2.8942075778891153e-06,
+      "loss": 0.0147,
+      "step": 182
+    },
+    {
+      "epoch": 6.51,
+      "learning_rate": 2.84177859211873e-06,
+      "loss": 0.0345,
+      "step": 183
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 2.7896396426081844e-06,
+      "loss": 0.0125,
+      "step": 184
+    },
+    {
+      "epoch": 6.58,
+      "learning_rate": 2.7377977361390118e-06,
+      "loss": 0.0198,
+      "step": 185
+    },
+    {
+      "epoch": 6.61,
+      "learning_rate": 2.6862598395741136e-06,
+      "loss": 0.0363,
+      "step": 186
+    },
+    {
+      "epoch": 6.65,
+      "learning_rate": 2.6350328789215e-06,
+      "loss": 0.0411,
+      "step": 187
+    },
+    {
+      "epoch": 6.68,
+      "learning_rate": 2.584123738403527e-06,
+      "loss": 0.0116,
+      "step": 188
+    },
+    {
+      "epoch": 6.72,
+      "learning_rate": 2.533539259531757e-06,
+      "loss": 0.032,
+      "step": 189
+    },
+    {
+      "epoch": 6.76,
+      "learning_rate": 2.483286240187538e-06,
+      "loss": 0.0145,
+      "step": 190
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 2.433371433708465e-06,
+      "loss": 0.0464,
+      "step": 191
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 2.383801547980826e-06,
+      "loss": 0.0168,
+      "step": 192
+    },
+    {
+      "epoch": 6.86,
+      "learning_rate": 2.3345832445381415e-06,
+      "loss": 0.0271,
+      "step": 193
+    },
+    {
+      "epoch": 6.9,
+      "learning_rate": 2.2857231376659517e-06,
+      "loss": 0.0575,
+      "step": 194
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 2.237227793512935e-06,
+      "loss": 0.0713,
+      "step": 195
+    },
+    {
+      "epoch": 6.97,
+      "learning_rate": 2.1891037292085177e-06,
+      "loss": 0.036,
+      "step": 196
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.141357411987044e-06,
+      "loss": 0.0475,
+      "step": 197
+    },
+    {
+      "epoch": 7.04,
+      "learning_rate": 2.0939952583186806e-06,
+      "loss": 0.0223,
+      "step": 198
+    },
+    {
+      "epoch": 7.08,
+      "learning_rate": 2.0470236330471125e-06,
+      "loss": 0.0453,
+      "step": 199
+    },
+    {
+      "epoch": 7.11,
+      "learning_rate": 2.000448848534209e-06,
+      "loss": 0.0248,
+      "step": 200
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 1.9542771638117124e-06,
+      "loss": 0.0239,
+      "step": 201
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 1.908514783740114e-06,
+      "loss": 0.0474,
+      "step": 202
+    },
+    {
+      "epoch": 7.22,
+      "learning_rate": 1.8631678581748059e-06,
+      "loss": 0.0674,
+      "step": 203
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 1.8182424811396131e-06,
+      "loss": 0.0091,
+      "step": 204
+    },
+    {
+      "epoch": 7.29,
+      "learning_rate": 1.7737446900078503e-06,
+      "loss": 0.0438,
+      "step": 205
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 1.7296804646909654e-06,
+      "loss": 0.0415,
+      "step": 206
+    },
+    {
+      "epoch": 7.36,
+      "learning_rate": 1.686055726834932e-06,
+      "loss": 0.008,
+      "step": 207
+    },
+    {
+      "epoch": 7.4,
+      "learning_rate": 1.6428763390244462e-06,
+      "loss": 0.0612,
+      "step": 208
+    },
+    {
+      "epoch": 7.43,
+      "learning_rate": 1.6001481039950872e-06,
+      "loss": 0.0166,
+      "step": 209
+    },
+    {
+      "epoch": 7.47,
+      "learning_rate": 1.557876763853493e-06,
+      "loss": 0.0299,
+      "step": 210
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 1.5160679993057048e-06,
+      "loss": 0.0218,
+      "step": 211
+    },
+    {
+      "epoch": 7.54,
+      "learning_rate": 1.4747274288937597e-06,
+      "loss": 0.0469,
+      "step": 212
+    },
+    {
+      "epoch": 7.57,
+      "learning_rate": 1.4338606082406232e-06,
+      "loss": 0.0185,
+      "step": 213
+    },
+    {
+      "epoch": 7.61,
+      "learning_rate": 1.3934730293035935e-06,
+      "loss": 0.0105,
+      "step": 214
+    },
+    {
+      "epoch": 7.64,
+      "learning_rate": 1.353570119636255e-06,
+      "loss": 0.0178,
+      "step": 215
+    },
+    {
+      "epoch": 7.68,
+      "learning_rate": 1.314157241659089e-06,
+      "loss": 0.0219,
+      "step": 216
+    },
+    {
+      "epoch": 7.72,
+      "learning_rate": 1.2752396919388293e-06,
+      "loss": 0.0536,
+      "step": 217
+    },
+    {
+      "epoch": 7.75,
+      "learning_rate": 1.236822700476683e-06,
+      "loss": 0.0254,
+      "step": 218
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 1.1989114300054782e-06,
+      "loss": 0.012,
+      "step": 219
+    },
+    {
+      "epoch": 7.82,
+      "learning_rate": 1.1615109752958715e-06,
+      "loss": 0.0375,
+      "step": 220
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 1.124626362471668e-06,
+      "loss": 0.0367,
+      "step": 221
+    },
+    {
+      "epoch": 7.89,
+      "learning_rate": 1.0882625483343846e-06,
+      "loss": 0.0383,
+      "step": 222
+    },
+    {
+      "epoch": 7.93,
+      "learning_rate": 1.0524244196971228e-06,
+      "loss": 0.037,
+      "step": 223
+    },
+    {
+      "epoch": 7.96,
+      "learning_rate": 1.0171167927278369e-06,
+      "loss": 0.0348,
+      "step": 224
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 9.82344412302117e-07,
+      "loss": 0.0205,
+      "step": 225
+    },
+    {
+      "epoch": 8.04,
+      "learning_rate": 9.48111951365529e-07,
+      "loss": 0.047,
+      "step": 226
+    },
+    {
+      "epoch": 8.07,
+      "learning_rate": 9.144240103056439e-07,
+      "loss": 0.0519,
+      "step": 227
+    },
+    {
+      "epoch": 8.11,
+      "learning_rate": 8.812851163337976e-07,
+      "loss": 0.0138,
+      "step": 228
+    },
+    {
+      "epoch": 8.14,
+      "learning_rate": 8.486997228767013e-07,
+      "loss": 0.0184,
+      "step": 229
+    },
+    {
+      "epoch": 8.18,
+      "learning_rate": 8.166722089779539e-07,
+      "loss": 0.0108,
+      "step": 230
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 7.852068787095601e-07,
+      "loss": 0.0372,
+      "step": 231
+    },
+    {
+      "epoch": 8.25,
+      "learning_rate": 7.543079605935222e-07,
+      "loss": 0.0203,
+      "step": 232
+    },
+    {
+      "epoch": 8.28,
+      "learning_rate": 7.239796070335775e-07,
+      "loss": 0.0109,
+      "step": 233
+    },
+    {
+      "epoch": 8.32,
+      "learning_rate": 6.942258937571772e-07,
+      "loss": 0.0257,
+      "step": 234
+    },
+    {
+      "epoch": 8.36,
+      "learning_rate": 6.650508192677546e-07,
+      "loss": 0.0596,
+      "step": 235
+    },
+    {
+      "epoch": 8.39,
+      "learning_rate": 6.364583043073902e-07,
+      "loss": 0.0165,
+      "step": 236
+    },
+    {
+      "epoch": 8.43,
+      "learning_rate": 6.08452191329903e-07,
+      "loss": 0.021,
+      "step": 237
+    },
+    {
+      "epoch": 8.46,
+      "learning_rate": 5.810362439844897e-07,
+      "loss": 0.0186,
+      "step": 238
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 5.542141466099271e-07,
+      "loss": 0.0444,
+      "step": 239
+    },
+    {
+      "epoch": 8.53,
+      "learning_rate": 5.279895037394567e-07,
+      "loss": 0.0403,
+      "step": 240
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 5.02365839616375e-07,
+      "loss": 0.0164,
+      "step": 241
+    },
+    {
+      "epoch": 8.6,
+      "learning_rate": 4.773465977204311e-07,
+      "loss": 0.0173,
+      "step": 242
+    },
+    {
+      "epoch": 8.64,
+      "learning_rate": 4.529351403050586e-07,
+      "loss": 0.0195,
+      "step": 243
+    },
+    {
+      "epoch": 8.68,
+      "learning_rate": 4.2913474794554044e-07,
+      "loss": 0.0156,
+      "step": 244
+    },
+    {
+      "epoch": 8.71,
+      "learning_rate": 4.0594861909814266e-07,
+      "loss": 0.0299,
+      "step": 245
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 3.833798696702801e-07,
+      "loss": 0.0563,
+      "step": 246
+    },
+    {
+      "epoch": 8.78,
+      "learning_rate": 3.6143153260178586e-07,
+      "loss": 0.0224,
+      "step": 247
+    },
+    {
+      "epoch": 8.82,
+      "learning_rate": 3.401065574573187e-07,
+      "loss": 0.0621,
+      "step": 248
+    },
+    {
+      "epoch": 8.85,
+      "learning_rate": 3.194078100299863e-07,
+      "loss": 0.0432,
+      "step": 249
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 2.9933807195621446e-07,
+      "loss": 0.0469,
+      "step": 250
+    },
+    {
+      "epoch": 8.92,
+      "learning_rate": 2.799000403419383e-07,
+      "loss": 0.0176,
+      "step": 251
+    },
+    {
+      "epoch": 8.96,
+      "learning_rate": 2.610963274001438e-07,
+      "loss": 0.0515,
+      "step": 252
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.4292946009982163e-07,
+      "loss": 0.013,
+      "step": 253
+    },
+    {
+      "epoch": 9.03,
+      "learning_rate": 2.2540187982637628e-07,
+      "loss": 0.0077,
+      "step": 254
+    },
+    {
+      "epoch": 9.07,
+      "learning_rate": 2.0851594205353543e-07,
+      "loss": 0.0332,
+      "step": 255
+    },
+    {
+      "epoch": 9.1,
+      "learning_rate": 1.922739160268089e-07,
+      "loss": 0.0073,
+      "step": 256
+    },
+    {
+      "epoch": 9.14,
+      "learning_rate": 1.7667798445852703e-07,
+      "loss": 0.0232,
+      "step": 257
+    },
+    {
+      "epoch": 9.17,
+      "learning_rate": 1.6173024323451747e-07,
+      "loss": 0.0402,
+      "step": 258
+    },
+    {
+      "epoch": 9.21,
+      "learning_rate": 1.4743270113244278e-07,
+      "loss": 0.0296,
+      "step": 259
+    },
+    {
+      "epoch": 9.24,
+      "learning_rate": 1.3378727955185243e-07,
+      "loss": 0.0391,
+      "step": 260
+    },
+    {
+      "epoch": 9.28,
+      "learning_rate": 1.207958122559655e-07,
+      "loss": 0.0077,
+      "step": 261
+    },
+    {
+      "epoch": 9.32,
+      "learning_rate": 1.084600451252421e-07,
+      "loss": 0.0473,
+      "step": 262
+    },
+    {
+      "epoch": 9.35,
+      "learning_rate": 9.678163592275858e-08,
+      "loss": 0.0264,
+      "step": 263
+    },
+    {
+      "epoch": 9.39,
+      "learning_rate": 8.576215407142652e-08,
+      "loss": 0.0283,
+      "step": 264
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 7.540308044308442e-08,
+      "loss": 0.0337,
+      "step": 265
+    },
+    {
+      "epoch": 9.46,
+      "learning_rate": 6.570580715948404e-08,
+      "loss": 0.0344,
+      "step": 266
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 5.6671637405212865e-08,
+      "loss": 0.0269,
+      "step": 267
+    },
+    {
+      "epoch": 9.53,
+      "learning_rate": 4.830178525256079e-08,
+      "loss": 0.0306,
+      "step": 268
+    },
+    {
+      "epoch": 9.56,
+      "learning_rate": 4.0597375498365175e-08,
+      "loss": 0.016,
+      "step": 269
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 3.355944351285278e-08,
+      "loss": 0.0409,
+      "step": 270
+    },
+    {
+      "epoch": 9.64,
+      "learning_rate": 2.718893510050058e-08,
+      "loss": 0.0232,
+      "step": 271
+    },
+    {
+      "epoch": 9.67,
+      "learning_rate": 2.1486706372932375e-08,
+      "loss": 0.0145,
+      "step": 272
+    },
+    {
+      "epoch": 9.71,
+      "learning_rate": 1.6453523633868096e-08,
+      "loss": 0.0374,
+      "step": 273
+    },
+    {
+      "epoch": 9.74,
+      "learning_rate": 1.2090063276142261e-08,
+      "loss": 0.0485,
+      "step": 274
+    },
+    {
+      "epoch": 9.78,
+      "learning_rate": 8.396911690807253e-09,
+      "loss": 0.0471,
+      "step": 275
+    },
+    {
+      "epoch": 9.81,
+      "learning_rate": 5.374565188329683e-09,
+      "loss": 0.0492,
+      "step": 276
+    },
+    {
+      "epoch": 9.85,
+      "learning_rate": 3.0234299318909755e-09,
+      "loss": 0.0523,
+      "step": 277
+    },
+    {
+      "epoch": 9.88,
+      "learning_rate": 1.3438218828076831e-09,
+      "loss": 0.0252,
+      "step": 278
+    },
+    {
+      "epoch": 9.92,
+      "learning_rate": 3.359667580682402e-10,
+      "loss": 0.0394,
+      "step": 279
+    },
+    {
+      "epoch": 9.96,
+      "learning_rate": 0.0,
+      "loss": 0.0269,
+      "step": 280
+    },
+    {
+      "epoch": 9.96,
+      "step": 280,
+      "total_flos": 1.0363597546666391e+21,
+      "train_loss": 0.2612905190725412,
+      "train_runtime": 5871.1818,
+      "train_samples_per_second": 6.132,
+      "train_steps_per_second": 0.048
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 200,
+  "total_flos": 1.0363597546666391e+21,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:733c3ddc7b62363867c8dd8a49c0ae1e288eff8873cc480d48f60fac14cd43d0
+size 5265

training_log.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ shell/internvl3.0/2nd_finetune/internvl3_1b_dynamic_res_2nd_finetune_full.sh: 68: --report_to: not found

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff