Instructions to use KerwinFu/qwen3-vl-4b-sft1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KerwinFu/qwen3-vl-4b-sft1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="KerwinFu/qwen3-vl-4b-sft1")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("KerwinFu/qwen3-vl-4b-sft1")
model = AutoModelForMultimodalLM.from_pretrained("KerwinFu/qwen3-vl-4b-sft1")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KerwinFu/qwen3-vl-4b-sft1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KerwinFu/qwen3-vl-4b-sft1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KerwinFu/qwen3-vl-4b-sft1",
		"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/KerwinFu/qwen3-vl-4b-sft1

SGLang

How to use KerwinFu/qwen3-vl-4b-sft1 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 "KerwinFu/qwen3-vl-4b-sft1" \
    --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": "KerwinFu/qwen3-vl-4b-sft1",
		"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 "KerwinFu/qwen3-vl-4b-sft1" \
        --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": "KerwinFu/qwen3-vl-4b-sft1",
		"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 KerwinFu/qwen3-vl-4b-sft1 with Docker Model Runner:
```
docker model run hf.co/KerwinFu/qwen3-vl-4b-sft1
```

KerwinFu commited on Feb 11

Commit

f303f1f

verified ·

1 Parent(s): e20eceb

Upload folder using huggingface_hub

Browse files

Files changed (15) hide show

.gitattributes +1 -0
README.md +58 -0
all_results.json +8 -0
chat_template.jinja +120 -0
config.json +71 -0
generation_config.json +14 -0
model.safetensors +3 -0
processor_config.json +63 -0
tokenizer.json +3 -0
tokenizer_config.json +31 -0
train_results.json +8 -0
trainer_log.jsonl +151 -0
trainer_state.json +1093 -0
training_args.bin +3 -0
training_loss.png +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,58 @@

+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-VL-4B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft
+  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. -->
+# sft
+This model is a fine-tuned version of [Qwen/Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct) on the derm_instruct dataset.
+## 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-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 3.0
+### Training results
+### Framework versions
+- Transformers 5.0.0
+- Pytorch 2.10.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

all_results.json ADDED Viewed

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

+{
+    "epoch": 3.0,
+    "total_flos": 2.273097293733888e+16,
+    "train_loss": 1.3163418625195822,
+    "train_runtime": 1442.119,
+    "train_samples_per_second": 2.08,
+    "train_steps_per_second": 1.04
+}

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,120 @@

+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json ADDED Viewed

	@@ -0,0 +1,71 @@

+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_size": 2560,
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "pad_token_id": 151643,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_theta": 5000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": false,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,14 @@

+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.0,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.0.0"
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:961c0479a52b4a79b58a071c50c5549ea1aebe243e9d5bdfd8608622f926f02f
+size 16920656200

processor_config.json ADDED Viewed

	@@ -0,0 +1,63 @@

+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json ADDED Viewed

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

+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json ADDED Viewed

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

+{
+    "epoch": 3.0,
+    "total_flos": 2.273097293733888e+16,
+    "train_loss": 1.3163418625195822,
+    "train_runtime": 1442.119,
+    "train_samples_per_second": 2.08,
+    "train_steps_per_second": 1.04
+}

trainer_log.jsonl ADDED Viewed

	@@ -0,0 +1,151 @@

+{"current_steps": 10, "total_steps": 1500, "loss": 8.791841125488281, "lr": 6.000000000000001e-07, "epoch": 0.02, "percentage": 0.67, "elapsed_time": "0:00:11", "remaining_time": "0:29:25"}
+{"current_steps": 20, "total_steps": 1500, "loss": 6.186199951171875, "lr": 1.2666666666666669e-06, "epoch": 0.04, "percentage": 1.33, "elapsed_time": "0:00:20", "remaining_time": "0:25:44"}
+{"current_steps": 30, "total_steps": 1500, "loss": 5.037051010131836, "lr": 1.9333333333333336e-06, "epoch": 0.06, "percentage": 2.0, "elapsed_time": "0:00:29", "remaining_time": "0:24:25"}
+{"current_steps": 40, "total_steps": 1500, "loss": 3.229383850097656, "lr": 2.6e-06, "epoch": 0.08, "percentage": 2.67, "elapsed_time": "0:00:38", "remaining_time": "0:23:33"}
+{"current_steps": 50, "total_steps": 1500, "loss": 2.6033956527709963, "lr": 3.266666666666667e-06, "epoch": 0.1, "percentage": 3.33, "elapsed_time": "0:00:47", "remaining_time": "0:22:53"}
+{"current_steps": 60, "total_steps": 1500, "loss": 2.942063903808594, "lr": 3.9333333333333335e-06, "epoch": 0.12, "percentage": 4.0, "elapsed_time": "0:00:55", "remaining_time": "0:22:18"}
+{"current_steps": 70, "total_steps": 1500, "loss": 2.450759506225586, "lr": 4.600000000000001e-06, "epoch": 0.14, "percentage": 4.67, "elapsed_time": "0:01:04", "remaining_time": "0:21:57"}
+{"current_steps": 80, "total_steps": 1500, "loss": 2.3624486923217773, "lr": 5.2666666666666665e-06, "epoch": 0.16, "percentage": 5.33, "elapsed_time": "0:01:13", "remaining_time": "0:21:46"}
+{"current_steps": 90, "total_steps": 1500, "loss": 1.8120697021484375, "lr": 5.933333333333335e-06, "epoch": 0.18, "percentage": 6.0, "elapsed_time": "0:01:22", "remaining_time": "0:21:33"}
+{"current_steps": 100, "total_steps": 1500, "loss": 2.04521484375, "lr": 6.600000000000001e-06, "epoch": 0.2, "percentage": 6.67, "elapsed_time": "0:01:31", "remaining_time": "0:21:17"}
+{"current_steps": 110, "total_steps": 1500, "loss": 2.3016538619995117, "lr": 7.266666666666668e-06, "epoch": 0.22, "percentage": 7.33, "elapsed_time": "0:01:40", "remaining_time": "0:21:04"}
+{"current_steps": 120, "total_steps": 1500, "loss": 2.394601821899414, "lr": 7.933333333333334e-06, "epoch": 0.24, "percentage": 8.0, "elapsed_time": "0:01:48", "remaining_time": "0:20:46"}
+{"current_steps": 130, "total_steps": 1500, "loss": 2.0336360931396484, "lr": 8.6e-06, "epoch": 0.26, "percentage": 8.67, "elapsed_time": "0:01:57", "remaining_time": "0:20:33"}
+{"current_steps": 140, "total_steps": 1500, "loss": 2.5297100067138674, "lr": 9.266666666666667e-06, "epoch": 0.28, "percentage": 9.33, "elapsed_time": "0:02:05", "remaining_time": "0:20:18"}
+{"current_steps": 150, "total_steps": 1500, "loss": 2.532087707519531, "lr": 9.933333333333334e-06, "epoch": 0.3, "percentage": 10.0, "elapsed_time": "0:02:14", "remaining_time": "0:20:11"}
+{"current_steps": 160, "total_steps": 1500, "loss": 2.106338310241699, "lr": 9.998903417374228e-06, "epoch": 0.32, "percentage": 10.67, "elapsed_time": "0:02:23", "remaining_time": "0:20:00"}
+{"current_steps": 170, "total_steps": 1500, "loss": 1.8893505096435548, "lr": 9.995113378907791e-06, "epoch": 0.34, "percentage": 11.33, "elapsed_time": "0:02:32", "remaining_time": "0:19:49"}
+{"current_steps": 180, "total_steps": 1500, "loss": 2.187959671020508, "lr": 9.988618398427495e-06, "epoch": 0.36, "percentage": 12.0, "elapsed_time": "0:02:40", "remaining_time": "0:19:37"}
+{"current_steps": 190, "total_steps": 1500, "loss": 2.390948677062988, "lr": 9.979421993079853e-06, "epoch": 0.38, "percentage": 12.67, "elapsed_time": "0:02:49", "remaining_time": "0:19:26"}
+{"current_steps": 200, "total_steps": 1500, "loss": 2.4106063842773438, "lr": 9.967529142880592e-06, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "0:02:57", "remaining_time": "0:19:14"}
+{"current_steps": 210, "total_steps": 1500, "loss": 2.082447624206543, "lr": 9.952946288017899e-06, "epoch": 0.42, "percentage": 14.0, "elapsed_time": "0:03:06", "remaining_time": "0:19:05"}
+{"current_steps": 220, "total_steps": 1500, "loss": 2.0642595291137695, "lr": 9.93568132536494e-06, "epoch": 0.44, "percentage": 14.67, "elapsed_time": "0:03:15", "remaining_time": "0:18:58"}
+{"current_steps": 230, "total_steps": 1500, "loss": 2.5710067749023438, "lr": 9.915743604203563e-06, "epoch": 0.46, "percentage": 15.33, "elapsed_time": "0:03:24", "remaining_time": "0:18:49"}
+{"current_steps": 240, "total_steps": 1500, "loss": 2.123330307006836, "lr": 9.893143921161501e-06, "epoch": 0.48, "percentage": 16.0, "elapsed_time": "0:03:33", "remaining_time": "0:18:40"}
+{"current_steps": 250, "total_steps": 1500, "loss": 2.516407012939453, "lr": 9.867894514365802e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:03:41", "remaining_time": "0:18:29"}
+{"current_steps": 260, "total_steps": 1500, "loss": 2.5996524810791017, "lr": 9.840009056815674e-06, "epoch": 0.52, "percentage": 17.33, "elapsed_time": "0:03:50", "remaining_time": "0:18:20"}
+{"current_steps": 270, "total_steps": 1500, "loss": 2.2154964447021483, "lr": 9.809502648978311e-06, "epoch": 0.54, "percentage": 18.0, "elapsed_time": "0:03:59", "remaining_time": "0:18:09"}
+{"current_steps": 280, "total_steps": 1500, "loss": 2.7604133605957033, "lr": 9.776391810611719e-06, "epoch": 0.56, "percentage": 18.67, "elapsed_time": "0:04:07", "remaining_time": "0:17:59"}
+{"current_steps": 290, "total_steps": 1500, "loss": 2.422298240661621, "lr": 9.740694471818988e-06, "epoch": 0.58, "percentage": 19.33, "elapsed_time": "0:04:16", "remaining_time": "0:17:50"}
+{"current_steps": 300, "total_steps": 1500, "loss": 1.9244077682495118, "lr": 9.702429963338812e-06, "epoch": 0.6, "percentage": 20.0, "elapsed_time": "0:04:25", "remaining_time": "0:17:41"}
+{"current_steps": 310, "total_steps": 1500, "loss": 1.9998054504394531, "lr": 9.661619006077562e-06, "epoch": 0.62, "percentage": 20.67, "elapsed_time": "0:04:34", "remaining_time": "0:17:31"}
+{"current_steps": 320, "total_steps": 1500, "loss": 2.256130027770996, "lr": 9.618283699888543e-06, "epoch": 0.64, "percentage": 21.33, "elapsed_time": "0:04:42", "remaining_time": "0:17:22"}
+{"current_steps": 330, "total_steps": 1500, "loss": 2.06947021484375, "lr": 9.572447511604536e-06, "epoch": 0.66, "percentage": 22.0, "elapsed_time": "0:04:51", "remaining_time": "0:17:13"}
+{"current_steps": 340, "total_steps": 1500, "loss": 2.0332563400268553, "lr": 9.524135262330098e-06, "epoch": 0.68, "percentage": 22.67, "elapsed_time": "0:05:00", "remaining_time": "0:17:04"}
+{"current_steps": 350, "total_steps": 1500, "loss": 2.068455696105957, "lr": 9.473373114000493e-06, "epoch": 0.7, "percentage": 23.33, "elapsed_time": "0:05:09", "remaining_time": "0:16:56"}
+{"current_steps": 360, "total_steps": 1500, "loss": 2.32584171295166, "lr": 9.420188555214537e-06, "epoch": 0.72, "percentage": 24.0, "elapsed_time": "0:05:17", "remaining_time": "0:16:45"}
+{"current_steps": 370, "total_steps": 1500, "loss": 2.5027301788330076, "lr": 9.364610386349048e-06, "epoch": 0.74, "percentage": 24.67, "elapsed_time": "0:05:26", "remaining_time": "0:16:36"}
+{"current_steps": 380, "total_steps": 1500, "loss": 2.2121116638183596, "lr": 9.306668703962927e-06, "epoch": 0.76, "percentage": 25.33, "elapsed_time": "0:05:35", "remaining_time": "0:16:28"}
+{"current_steps": 390, "total_steps": 1500, "loss": 2.542919158935547, "lr": 9.246394884499334e-06, "epoch": 0.78, "percentage": 26.0, "elapsed_time": "0:05:44", "remaining_time": "0:16:19"}
+{"current_steps": 400, "total_steps": 1500, "loss": 1.9286565780639648, "lr": 9.18382156729481e-06, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "0:05:52", "remaining_time": "0:16:09"}
+{"current_steps": 410, "total_steps": 1500, "loss": 2.313096809387207, "lr": 9.118982636904476e-06, "epoch": 0.82, "percentage": 27.33, "elapsed_time": "0:06:01", "remaining_time": "0:16:00"}
+{"current_steps": 420, "total_steps": 1500, "loss": 2.0929283142089843, "lr": 9.051913204752972e-06, "epoch": 0.84, "percentage": 28.0, "elapsed_time": "0:06:09", "remaining_time": "0:15:50"}
+{"current_steps": 430, "total_steps": 1500, "loss": 2.0113702774047852, "lr": 8.982649590120982e-06, "epoch": 0.86, "percentage": 28.67, "elapsed_time": "0:06:18", "remaining_time": "0:15:41"}
+{"current_steps": 440, "total_steps": 1500, "loss": 1.6521787643432617, "lr": 8.911229300477716e-06, "epoch": 0.88, "percentage": 29.33, "elapsed_time": "0:06:27", "remaining_time": "0:15:32"}
+{"current_steps": 450, "total_steps": 1500, "loss": 2.2836629867553713, "lr": 8.837691011169944e-06, "epoch": 0.9, "percentage": 30.0, "elapsed_time": "0:06:35", "remaining_time": "0:15:23"}
+{"current_steps": 460, "total_steps": 1500, "loss": 1.705312156677246, "lr": 8.762074544478622e-06, "epoch": 0.92, "percentage": 30.67, "elapsed_time": "0:06:44", "remaining_time": "0:15:15"}
+{"current_steps": 470, "total_steps": 1500, "loss": 1.4402057647705078, "lr": 8.68442084805442e-06, "epoch": 0.94, "percentage": 31.33, "elapsed_time": "0:06:53", "remaining_time": "0:15:06"}
+{"current_steps": 480, "total_steps": 1500, "loss": 1.9172407150268556, "lr": 8.604771972743848e-06, "epoch": 0.96, "percentage": 32.0, "elapsed_time": "0:07:02", "remaining_time": "0:14:57"}
+{"current_steps": 490, "total_steps": 1500, "loss": 1.5030399322509767, "lr": 8.523171049817974e-06, "epoch": 0.98, "percentage": 32.67, "elapsed_time": "0:07:11", "remaining_time": "0:14:48"}
+{"current_steps": 500, "total_steps": 1500, "loss": 1.9837615966796875, "lr": 8.439662267616093e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:07:18", "remaining_time": "0:14:37"}
+{"current_steps": 510, "total_steps": 1500, "loss": 1.2435311317443847, "lr": 8.354290847616954e-06, "epoch": 1.02, "percentage": 34.0, "elapsed_time": "0:08:11", "remaining_time": "0:15:53"}
+{"current_steps": 520, "total_steps": 1500, "loss": 1.23653564453125, "lr": 8.267103019950529e-06, "epoch": 1.04, "percentage": 34.67, "elapsed_time": "0:08:20", "remaining_time": "0:15:42"}
+{"current_steps": 530, "total_steps": 1500, "loss": 0.8462669372558593, "lr": 8.178145998363585e-06, "epoch": 1.06, "percentage": 35.33, "elapsed_time": "0:08:28", "remaining_time": "0:15:30"}
+{"current_steps": 540, "total_steps": 1500, "loss": 1.2925146102905274, "lr": 8.087467954652608e-06, "epoch": 1.08, "percentage": 36.0, "elapsed_time": "0:08:37", "remaining_time": "0:15:19"}
+{"current_steps": 550, "total_steps": 1500, "loss": 0.901913833618164, "lr": 7.99511799257793e-06, "epoch": 1.1, "percentage": 36.67, "elapsed_time": "0:08:46", "remaining_time": "0:15:09"}
+{"current_steps": 560, "total_steps": 1500, "loss": 1.3357799530029297, "lr": 7.901146121273165e-06, "epoch": 1.12, "percentage": 37.33, "elapsed_time": "0:08:54", "remaining_time": "0:14:57"}
+{"current_steps": 570, "total_steps": 1500, "loss": 1.3306777954101563, "lr": 7.80560322816439e-06, "epoch": 1.1400000000000001, "percentage": 38.0, "elapsed_time": "0:09:03", "remaining_time": "0:14:47"}
+{"current_steps": 580, "total_steps": 1500, "loss": 0.944632625579834, "lr": 7.7085410514137e-06, "epoch": 1.16, "percentage": 38.67, "elapsed_time": "0:09:12", "remaining_time": "0:14:36"}
+{"current_steps": 590, "total_steps": 1500, "loss": 1.3212141036987304, "lr": 7.610012151902091e-06, "epoch": 1.18, "percentage": 39.33, "elapsed_time": "0:09:21", "remaining_time": "0:14:26"}
+{"current_steps": 600, "total_steps": 1500, "loss": 1.2321388244628906, "lr": 7.510069884766802e-06, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "0:09:30", "remaining_time": "0:14:16"}
+{"current_steps": 610, "total_steps": 1500, "loss": 1.3100163459777832, "lr": 7.408768370508577e-06, "epoch": 1.22, "percentage": 40.67, "elapsed_time": "0:09:39", "remaining_time": "0:14:05"}
+{"current_steps": 620, "total_steps": 1500, "loss": 1.179959774017334, "lr": 7.3061624656844544e-06, "epoch": 1.24, "percentage": 41.33, "elapsed_time": "0:09:47", "remaining_time": "0:13:54"}
+{"current_steps": 630, "total_steps": 1500, "loss": 0.8590527534484863, "lr": 7.2023077332019755e-06, "epoch": 1.26, "percentage": 42.0, "elapsed_time": "0:09:56", "remaining_time": "0:13:43"}
+{"current_steps": 640, "total_steps": 1500, "loss": 1.3245353698730469, "lr": 7.0972604122308865e-06, "epoch": 1.28, "percentage": 42.67, "elapsed_time": "0:10:05", "remaining_time": "0:13:33"}
+{"current_steps": 650, "total_steps": 1500, "loss": 0.9064340591430664, "lr": 6.991077387748643e-06, "epoch": 1.3, "percentage": 43.33, "elapsed_time": "0:10:14", "remaining_time": "0:13:23"}
+{"current_steps": 660, "total_steps": 1500, "loss": 1.3220383644104003, "lr": 6.883816159736187e-06, "epoch": 1.32, "percentage": 44.0, "elapsed_time": "0:10:22", "remaining_time": "0:13:12"}
+{"current_steps": 670, "total_steps": 1500, "loss": 0.7077834129333496, "lr": 6.775534812040686e-06, "epoch": 1.34, "percentage": 44.67, "elapsed_time": "0:10:31", "remaining_time": "0:13:02"}
+{"current_steps": 680, "total_steps": 1500, "loss": 0.9919247627258301, "lr": 6.666291980922122e-06, "epoch": 1.3599999999999999, "percentage": 45.33, "elapsed_time": "0:10:40", "remaining_time": "0:12:51"}
+{"current_steps": 690, "total_steps": 1500, "loss": 1.6220426559448242, "lr": 6.556146823300701e-06, "epoch": 1.38, "percentage": 46.0, "elapsed_time": "0:10:49", "remaining_time": "0:12:42"}
+{"current_steps": 700, "total_steps": 1500, "loss": 1.3412548065185548, "lr": 6.445158984722358e-06, "epoch": 1.4, "percentage": 46.67, "elapsed_time": "0:10:57", "remaining_time": "0:12:31"}
+{"current_steps": 710, "total_steps": 1500, "loss": 1.2461795806884766, "lr": 6.3333885670596285e-06, "epoch": 1.42, "percentage": 47.33, "elapsed_time": "0:11:06", "remaining_time": "0:12:21"}
+{"current_steps": 720, "total_steps": 1500, "loss": 1.0722078323364257, "lr": 6.220896095965428e-06, "epoch": 1.44, "percentage": 48.0, "elapsed_time": "0:11:15", "remaining_time": "0:12:11"}
+{"current_steps": 730, "total_steps": 1500, "loss": 0.83670015335083, "lr": 6.107742488097338e-06, "epoch": 1.46, "percentage": 48.67, "elapsed_time": "0:11:24", "remaining_time": "0:12:01"}
+{"current_steps": 740, "total_steps": 1500, "loss": 1.1005640029907227, "lr": 5.993989018130173e-06, "epoch": 1.48, "percentage": 49.33, "elapsed_time": "0:11:33", "remaining_time": "0:11:52"}
+{"current_steps": 750, "total_steps": 1500, "loss": 1.5326812744140625, "lr": 5.879697285574655e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:11:42", "remaining_time": "0:11:42"}
+{"current_steps": 760, "total_steps": 1500, "loss": 1.028077983856201, "lr": 5.764929181420191e-06, "epoch": 1.52, "percentage": 50.67, "elapsed_time": "0:11:50", "remaining_time": "0:11:32"}
+{"current_steps": 770, "total_steps": 1500, "loss": 1.1157980918884278, "lr": 5.649746854619814e-06, "epoch": 1.54, "percentage": 51.33, "elapsed_time": "0:11:59", "remaining_time": "0:11:22"}
+{"current_steps": 780, "total_steps": 1500, "loss": 1.2585329055786132, "lr": 5.5342126784354265e-06, "epoch": 1.56, "percentage": 52.0, "elapsed_time": "0:12:08", "remaining_time": "0:11:12"}
+{"current_steps": 790, "total_steps": 1500, "loss": 1.1203573226928711, "lr": 5.41838921666158e-06, "epoch": 1.58, "percentage": 52.67, "elapsed_time": "0:12:17", "remaining_time": "0:11:02"}
+{"current_steps": 800, "total_steps": 1500, "loss": 1.0436135292053224, "lr": 5.3023391897460715e-06, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "0:12:26", "remaining_time": "0:10:52"}
+{"current_steps": 810, "total_steps": 1500, "loss": 0.9347926139831543, "lr": 5.18612544082573e-06, "epoch": 1.62, "percentage": 54.0, "elapsed_time": "0:12:34", "remaining_time": "0:10:42"}
+{"current_steps": 820, "total_steps": 1500, "loss": 1.5266364097595215, "lr": 5.069810901695727e-06, "epoch": 1.6400000000000001, "percentage": 54.67, "elapsed_time": "0:12:43", "remaining_time": "0:10:33"}
+{"current_steps": 830, "total_steps": 1500, "loss": 1.1257129669189454, "lr": 4.953458558730917e-06, "epoch": 1.6600000000000001, "percentage": 55.33, "elapsed_time": "0:12:52", "remaining_time": "0:10:23"}
+{"current_steps": 840, "total_steps": 1500, "loss": 0.9643683433532715, "lr": 4.837131418777595e-06, "epoch": 1.6800000000000002, "percentage": 56.0, "elapsed_time": "0:13:00", "remaining_time": "0:10:13"}
+{"current_steps": 850, "total_steps": 1500, "loss": 1.3242192268371582, "lr": 4.720892475034181e-06, "epoch": 1.7, "percentage": 56.67, "elapsed_time": "0:13:09", "remaining_time": "0:10:03"}
+{"current_steps": 860, "total_steps": 1500, "loss": 1.251343059539795, "lr": 4.604804672939295e-06, "epoch": 1.72, "percentage": 57.33, "elapsed_time": "0:13:17", "remaining_time": "0:09:53"}
+{"current_steps": 870, "total_steps": 1500, "loss": 1.1028053283691406, "lr": 4.4889308760856826e-06, "epoch": 1.74, "percentage": 58.0, "elapsed_time": "0:13:26", "remaining_time": "0:09:43"}
+{"current_steps": 880, "total_steps": 1500, "loss": 0.8769556045532226, "lr": 4.373333832178478e-06, "epoch": 1.76, "percentage": 58.67, "elapsed_time": "0:13:35", "remaining_time": "0:09:34"}
+{"current_steps": 890, "total_steps": 1500, "loss": 1.1681681632995606, "lr": 4.258076139056217e-06, "epoch": 1.78, "percentage": 59.33, "elapsed_time": "0:13:44", "remaining_time": "0:09:24"}
+{"current_steps": 900, "total_steps": 1500, "loss": 0.9344164848327636, "lr": 4.143220210792993e-06, "epoch": 1.8, "percentage": 60.0, "elapsed_time": "0:13:53", "remaining_time": "0:09:15"}
+{"current_steps": 910, "total_steps": 1500, "loss": 1.634626579284668, "lr": 4.028828243900141e-06, "epoch": 1.8199999999999998, "percentage": 60.67, "elapsed_time": "0:14:02", "remaining_time": "0:09:06"}
+{"current_steps": 920, "total_steps": 1500, "loss": 1.0626420974731445, "lr": 3.914962183645733e-06, "epoch": 1.8399999999999999, "percentage": 61.33, "elapsed_time": "0:14:10", "remaining_time": "0:08:56"}
+{"current_steps": 930, "total_steps": 1500, "loss": 1.375041389465332, "lr": 3.8016836905101157e-06, "epoch": 1.8599999999999999, "percentage": 62.0, "elapsed_time": "0:14:19", "remaining_time": "0:08:46"}
+{"current_steps": 940, "total_steps": 1500, "loss": 0.9415129661560059, "lr": 3.6890541067956775e-06, "epoch": 1.88, "percentage": 62.67, "elapsed_time": "0:14:28", "remaining_time": "0:08:37"}
+{"current_steps": 950, "total_steps": 1500, "loss": 0.8620157241821289, "lr": 3.577134423408906e-06, "epoch": 1.9, "percentage": 63.33, "elapsed_time": "0:14:36", "remaining_time": "0:08:27"}
+{"current_steps": 960, "total_steps": 1500, "loss": 1.1039237976074219, "lr": 3.465985246832739e-06, "epoch": 1.92, "percentage": 64.0, "elapsed_time": "0:14:45", "remaining_time": "0:08:18"}
+{"current_steps": 970, "total_steps": 1500, "loss": 0.8490506172180176, "lr": 3.355666766307084e-06, "epoch": 1.94, "percentage": 64.67, "elapsed_time": "0:14:54", "remaining_time": "0:08:08"}
+{"current_steps": 980, "total_steps": 1500, "loss": 1.2799974441528321, "lr": 3.246238721235283e-06, "epoch": 1.96, "percentage": 65.33, "elapsed_time": "0:15:02", "remaining_time": "0:07:59"}
+{"current_steps": 990, "total_steps": 1500, "loss": 0.8015480995178222, "lr": 3.137760368834169e-06, "epoch": 1.98, "percentage": 66.0, "elapsed_time": "0:15:11", "remaining_time": "0:07:49"}
+{"current_steps": 1000, "total_steps": 1500, "loss": 1.091315746307373, "lr": 3.030290452045245e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:15:19", "remaining_time": "0:07:39"}
+{"current_steps": 1010, "total_steps": 1500, "loss": 0.47315549850463867, "lr": 2.9238871677243354e-06, "epoch": 2.02, "percentage": 67.33, "elapsed_time": "0:16:11", "remaining_time": "0:07:51"}
+{"current_steps": 1020, "total_steps": 1500, "loss": 0.3728752613067627, "lr": 2.818608135126967e-06, "epoch": 2.04, "percentage": 68.0, "elapsed_time": "0:16:20", "remaining_time": "0:07:41"}
+{"current_steps": 1030, "total_steps": 1500, "loss": 0.33084559440612793, "lr": 2.714510364706531e-06, "epoch": 2.06, "percentage": 68.67, "elapsed_time": "0:16:29", "remaining_time": "0:07:31"}
+{"current_steps": 1040, "total_steps": 1500, "loss": 0.32590973377227783, "lr": 2.611650227242102e-06, "epoch": 2.08, "percentage": 69.33, "elapsed_time": "0:16:38", "remaining_time": "0:07:21"}
+{"current_steps": 1050, "total_steps": 1500, "loss": 0.4684451580047607, "lr": 2.5100834233126827e-06, "epoch": 2.1, "percentage": 70.0, "elapsed_time": "0:16:47", "remaining_time": "0:07:11"}
+{"current_steps": 1060, "total_steps": 1500, "loss": 0.26931188106536863, "lr": 2.40986495313435e-06, "epoch": 2.12, "percentage": 70.67, "elapsed_time": "0:16:56", "remaining_time": "0:07:01"}
+{"current_steps": 1070, "total_steps": 1500, "loss": 0.499393892288208, "lr": 2.3110490867766644e-06, "epoch": 2.14, "percentage": 71.33, "elapsed_time": "0:17:04", "remaining_time": "0:06:51"}
+{"current_steps": 1080, "total_steps": 1500, "loss": 0.3078450202941895, "lr": 2.213689334774479e-06, "epoch": 2.16, "percentage": 72.0, "elapsed_time": "0:17:13", "remaining_time": "0:06:41"}
+{"current_steps": 1090, "total_steps": 1500, "loss": 0.47670416831970214, "lr": 2.1178384191510344e-06, "epoch": 2.18, "percentage": 72.67, "elapsed_time": "0:17:22", "remaining_time": "0:06:31"}
+{"current_steps": 1100, "total_steps": 1500, "loss": 0.47382168769836425, "lr": 2.023548244868051e-06, "epoch": 2.2, "percentage": 73.33, "elapsed_time": "0:17:31", "remaining_time": "0:06:22"}
+{"current_steps": 1110, "total_steps": 1500, "loss": 0.19442765712738036, "lr": 1.9308698717182874e-06, "epoch": 2.22, "percentage": 74.0, "elapsed_time": "0:17:39", "remaining_time": "0:06:12"}
+{"current_steps": 1120, "total_steps": 1500, "loss": 0.44660329818725586, "lr": 1.8398534866757455e-06, "epoch": 2.24, "percentage": 74.67, "elapsed_time": "0:17:49", "remaining_time": "0:06:02"}
+{"current_steps": 1130, "total_steps": 1500, "loss": 0.36274888515472414, "lr": 1.7505483767185583e-06, "epoch": 2.26, "percentage": 75.33, "elapsed_time": "0:17:57", "remaining_time": "0:05:52"}
+{"current_steps": 1140, "total_steps": 1500, "loss": 0.24480688571929932, "lr": 1.6630029021392007e-06, "epoch": 2.2800000000000002, "percentage": 76.0, "elapsed_time": "0:18:06", "remaining_time": "0:05:43"}
+{"current_steps": 1150, "total_steps": 1500, "loss": 0.14373520612716675, "lr": 1.5772644703565564e-06, "epoch": 2.3, "percentage": 76.67, "elapsed_time": "0:18:15", "remaining_time": "0:05:33"}
+{"current_steps": 1160, "total_steps": 1500, "loss": 0.34253692626953125, "lr": 1.4933795102439558e-06, "epoch": 2.32, "percentage": 77.33, "elapsed_time": "0:18:24", "remaining_time": "0:05:23"}
+{"current_steps": 1170, "total_steps": 1500, "loss": 0.1978028893470764, "lr": 1.4113934469871166e-06, "epoch": 2.34, "percentage": 78.0, "elapsed_time": "0:18:33", "remaining_time": "0:05:13"}
+{"current_steps": 1180, "total_steps": 1500, "loss": 0.29554598331451415, "lr": 1.3313506774856177e-06, "epoch": 2.36, "percentage": 78.67, "elapsed_time": "0:18:41", "remaining_time": "0:05:04"}
+{"current_steps": 1190, "total_steps": 1500, "loss": 0.3423331260681152, "lr": 1.2532945463111856e-06, "epoch": 2.38, "percentage": 79.33, "elapsed_time": "0:18:49", "remaining_time": "0:04:54"}
+{"current_steps": 1200, "total_steps": 1500, "loss": 0.3274805784225464, "lr": 1.1772673222358421e-06, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "0:18:58", "remaining_time": "0:04:44"}
+{"current_steps": 1210, "total_steps": 1500, "loss": 0.29171273708343504, "lr": 1.1033101753426285e-06, "epoch": 2.42, "percentage": 80.67, "elapsed_time": "0:19:07", "remaining_time": "0:04:34"}
+{"current_steps": 1220, "total_steps": 1500, "loss": 0.2250969171524048, "lr": 1.0314631547312738e-06, "epoch": 2.44, "percentage": 81.33, "elapsed_time": "0:19:15", "remaining_time": "0:04:25"}
+{"current_steps": 1230, "total_steps": 1500, "loss": 0.2975991487503052, "lr": 9.617651668308914e-07, "epoch": 2.46, "percentage": 82.0, "elapsed_time": "0:19:24", "remaining_time": "0:04:15"}
+{"current_steps": 1240, "total_steps": 1500, "loss": 0.3745620012283325, "lr": 8.942539543314799e-07, "epoch": 2.48, "percentage": 82.67, "elapsed_time": "0:19:33", "remaining_time": "0:04:05"}
+{"current_steps": 1250, "total_steps": 1500, "loss": 0.3142155885696411, "lr": 8.289660757455803e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:19:41", "remaining_time": "0:03:56"}
+{"current_steps": 1260, "total_steps": 1500, "loss": 0.4468146800994873, "lr": 7.659368856111926e-07, "epoch": 2.52, "percentage": 84.0, "elapsed_time": "0:19:49", "remaining_time": "0:03:46"}
+{"current_steps": 1270, "total_steps": 1500, "loss": 0.514287281036377, "lr": 7.052005153466779e-07, "epoch": 2.54, "percentage": 84.67, "elapsed_time": "0:19:58", "remaining_time": "0:03:37"}
+{"current_steps": 1280, "total_steps": 1500, "loss": 0.21953434944152833, "lr": 6.467898547679913e-07, "epoch": 2.56, "percentage": 85.33, "elapsed_time": "0:20:07", "remaining_time": "0:03:27"}
+{"current_steps": 1290, "total_steps": 1500, "loss": 0.3766503095626831, "lr": 5.9073653427826e-07, "epoch": 2.58, "percentage": 86.0, "elapsed_time": "0:20:16", "remaining_time": "0:03:18"}
+{"current_steps": 1300, "total_steps": 1500, "loss": 0.3407785892486572, "lr": 5.370709077393721e-07, "epoch": 2.6, "percentage": 86.67, "elapsed_time": "0:20:24", "remaining_time": "0:03:08"}
+{"current_steps": 1310, "total_steps": 1500, "loss": 0.2537382125854492, "lr": 4.858220360348187e-07, "epoch": 2.62, "percentage": 87.33, "elapsed_time": "0:20:33", "remaining_time": "0:02:58"}
+{"current_steps": 1320, "total_steps": 1500, "loss": 0.25959508419036864, "lr": 4.370176713327118e-07, "epoch": 2.64, "percentage": 88.0, "elapsed_time": "0:20:42", "remaining_time": "0:02:49"}
+{"current_steps": 1330, "total_steps": 1500, "loss": 0.43554534912109377, "lr": 3.90684242057498e-07, "epoch": 2.66, "percentage": 88.67, "elapsed_time": "0:20:51", "remaining_time": "0:02:39"}
+{"current_steps": 1340, "total_steps": 1500, "loss": 0.5232177257537842, "lr": 3.468468385785023e-07, "epoch": 2.68, "percentage": 89.33, "elapsed_time": "0:21:00", "remaining_time": "0:02:30"}
+{"current_steps": 1350, "total_steps": 1500, "loss": 0.2125147581100464, "lr": 3.055291996230492e-07, "epoch": 2.7, "percentage": 90.0, "elapsed_time": "0:21:09", "remaining_time": "0:02:21"}
+{"current_steps": 1360, "total_steps": 1500, "loss": 0.21367454528808594, "lr": 2.6675369942151864e-07, "epoch": 2.7199999999999998, "percentage": 90.67, "elapsed_time": "0:21:17", "remaining_time": "0:02:11"}
+{"current_steps": 1370, "total_steps": 1500, "loss": 0.1693113088607788, "lr": 2.3054133559131163e-07, "epoch": 2.74, "percentage": 91.33, "elapsed_time": "0:21:26", "remaining_time": "0:02:02"}
+{"current_steps": 1380, "total_steps": 1500, "loss": 0.2792075157165527, "lr": 1.9691171776626882e-07, "epoch": 2.76, "percentage": 92.0, "elapsed_time": "0:21:35", "remaining_time": "0:01:52"}
+{"current_steps": 1390, "total_steps": 1500, "loss": 0.13291265964508056, "lr": 1.6588305697770313e-07, "epoch": 2.7800000000000002, "percentage": 92.67, "elapsed_time": "0:21:44", "remaining_time": "0:01:43"}
+{"current_steps": 1400, "total_steps": 1500, "loss": 0.4104594707489014, "lr": 1.374721557928116e-07, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "0:21:53", "remaining_time": "0:01:33"}
+{"current_steps": 1410, "total_steps": 1500, "loss": 0.5142350196838379, "lr": 1.1169439921578485e-07, "epoch": 2.82, "percentage": 94.0, "elapsed_time": "0:22:01", "remaining_time": "0:01:24"}
+{"current_steps": 1420, "total_steps": 1500, "loss": 0.31447272300720214, "lr": 8.856374635655696e-08, "epoch": 2.84, "percentage": 94.67, "elapsed_time": "0:22:11", "remaining_time": "0:01:14"}
+{"current_steps": 1430, "total_steps": 1500, "loss": 0.32525787353515623, "lr": 6.809272287169988e-08, "epoch": 2.86, "percentage": 95.33, "elapsed_time": "0:22:20", "remaining_time": "0:01:05"}
+{"current_steps": 1440, "total_steps": 1500, "loss": 0.1824193000793457, "lr": 5.029241418156139e-08, "epoch": 2.88, "percentage": 96.0, "elapsed_time": "0:22:28", "remaining_time": "0:00:56"}
+{"current_steps": 1450, "total_steps": 1500, "loss": 0.2836474895477295, "lr": 3.517245946731529e-08, "epoch": 2.9, "percentage": 96.67, "elapsed_time": "0:22:37", "remaining_time": "0:00:46"}
+{"current_steps": 1460, "total_steps": 1500, "loss": 0.20449333190917968, "lr": 2.27410464511707e-08, "epoch": 2.92, "percentage": 97.33, "elapsed_time": "0:22:46", "remaining_time": "0:00:37"}
+{"current_steps": 1470, "total_steps": 1500, "loss": 0.30746448040008545, "lr": 1.3004906962578723e-08, "epoch": 2.94, "percentage": 98.0, "elapsed_time": "0:22:55", "remaining_time": "0:00:28"}
+{"current_steps": 1480, "total_steps": 1500, "loss": 0.2320650577545166, "lr": 5.969313292830126e-09, "epoch": 2.96, "percentage": 98.67, "elapsed_time": "0:23:03", "remaining_time": "0:00:18"}
+{"current_steps": 1490, "total_steps": 1500, "loss": 0.39888916015625, "lr": 1.638075340010814e-09, "epoch": 2.98, "percentage": 99.33, "elapsed_time": "0:23:12", "remaining_time": "0:00:09"}
+{"current_steps": 1500, "total_steps": 1500, "loss": 0.3253091096878052, "lr": 1.3538545881042198e-11, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:23:19", "remaining_time": "0:00:00"}
+{"current_steps": 1500, "total_steps": 1500, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:24:02", "remaining_time": "0:00:00"}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,1093 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 210.173828125,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 8.791841125488281,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 161.85198974609375,
+      "learning_rate": 1.2666666666666669e-06,
+      "loss": 6.186199951171875,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 79.59968566894531,
+      "learning_rate": 1.9333333333333336e-06,
+      "loss": 5.037051010131836,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 77.91535949707031,
+      "learning_rate": 2.6e-06,
+      "loss": 3.229383850097656,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 45.42420959472656,
+      "learning_rate": 3.266666666666667e-06,
+      "loss": 2.6033956527709963,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 41.46728515625,
+      "learning_rate": 3.9333333333333335e-06,
+      "loss": 2.942063903808594,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 78.79148864746094,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 2.450759506225586,
+      "step": 70
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 62.13072967529297,
+      "learning_rate": 5.2666666666666665e-06,
+      "loss": 2.3624486923217773,
+      "step": 80
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 52.63612747192383,
+      "learning_rate": 5.933333333333335e-06,
+      "loss": 1.8120697021484375,
+      "step": 90
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 67.64952850341797,
+      "learning_rate": 6.600000000000001e-06,
+      "loss": 2.04521484375,
+      "step": 100
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 43.48116683959961,
+      "learning_rate": 7.266666666666668e-06,
+      "loss": 2.3016538619995117,
+      "step": 110
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 51.687042236328125,
+      "learning_rate": 7.933333333333334e-06,
+      "loss": 2.394601821899414,
+      "step": 120
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 66.71311950683594,
+      "learning_rate": 8.6e-06,
+      "loss": 2.0336360931396484,
+      "step": 130
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 44.05624771118164,
+      "learning_rate": 9.266666666666667e-06,
+      "loss": 2.5297100067138674,
+      "step": 140
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 43.44951629638672,
+      "learning_rate": 9.933333333333334e-06,
+      "loss": 2.532087707519531,
+      "step": 150
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 39.6384162902832,
+      "learning_rate": 9.998903417374228e-06,
+      "loss": 2.106338310241699,
+      "step": 160
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 38.4444694519043,
+      "learning_rate": 9.995113378907791e-06,
+      "loss": 1.8893505096435548,
+      "step": 170
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 40.845069885253906,
+      "learning_rate": 9.988618398427495e-06,
+      "loss": 2.187959671020508,
+      "step": 180
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 32.24748611450195,
+      "learning_rate": 9.979421993079853e-06,
+      "loss": 2.390948677062988,
+      "step": 190
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 47.72621536254883,
+      "learning_rate": 9.967529142880592e-06,
+      "loss": 2.4106063842773438,
+      "step": 200
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 25.50874137878418,
+      "learning_rate": 9.952946288017899e-06,
+      "loss": 2.082447624206543,
+      "step": 210
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 51.26837158203125,
+      "learning_rate": 9.93568132536494e-06,
+      "loss": 2.0642595291137695,
+      "step": 220
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 65.230712890625,
+      "learning_rate": 9.915743604203563e-06,
+      "loss": 2.5710067749023438,
+      "step": 230
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 37.009708404541016,
+      "learning_rate": 9.893143921161501e-06,
+      "loss": 2.123330307006836,
+      "step": 240
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 42.43490982055664,
+      "learning_rate": 9.867894514365802e-06,
+      "loss": 2.516407012939453,
+      "step": 250
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 33.466773986816406,
+      "learning_rate": 9.840009056815674e-06,
+      "loss": 2.5996524810791017,
+      "step": 260
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 38.300453186035156,
+      "learning_rate": 9.809502648978311e-06,
+      "loss": 2.2154964447021483,
+      "step": 270
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 41.977272033691406,
+      "learning_rate": 9.776391810611719e-06,
+      "loss": 2.7604133605957033,
+      "step": 280
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 39.470916748046875,
+      "learning_rate": 9.740694471818988e-06,
+      "loss": 2.422298240661621,
+      "step": 290
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 25.746841430664062,
+      "learning_rate": 9.702429963338812e-06,
+      "loss": 1.9244077682495118,
+      "step": 300
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 61.744041442871094,
+      "learning_rate": 9.661619006077562e-06,
+      "loss": 1.9998054504394531,
+      "step": 310
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 81.94461822509766,
+      "learning_rate": 9.618283699888543e-06,
+      "loss": 2.256130027770996,
+      "step": 320
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 35.797786712646484,
+      "learning_rate": 9.572447511604536e-06,
+      "loss": 2.06947021484375,
+      "step": 330
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 32.96639633178711,
+      "learning_rate": 9.524135262330098e-06,
+      "loss": 2.0332563400268553,
+      "step": 340
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 32.352699279785156,
+      "learning_rate": 9.473373114000493e-06,
+      "loss": 2.068455696105957,
+      "step": 350
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 38.09100341796875,
+      "learning_rate": 9.420188555214537e-06,
+      "loss": 2.32584171295166,
+      "step": 360
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 50.007049560546875,
+      "learning_rate": 9.364610386349048e-06,
+      "loss": 2.5027301788330076,
+      "step": 370
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 27.599956512451172,
+      "learning_rate": 9.306668703962927e-06,
+      "loss": 2.2121116638183596,
+      "step": 380
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 36.08063507080078,
+      "learning_rate": 9.246394884499334e-06,
+      "loss": 2.542919158935547,
+      "step": 390
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 49.41411209106445,
+      "learning_rate": 9.18382156729481e-06,
+      "loss": 1.9286565780639648,
+      "step": 400
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 54.925540924072266,
+      "learning_rate": 9.118982636904476e-06,
+      "loss": 2.313096809387207,
+      "step": 410
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 56.74051284790039,
+      "learning_rate": 9.051913204752972e-06,
+      "loss": 2.0929283142089843,
+      "step": 420
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 24.994333267211914,
+      "learning_rate": 8.982649590120982e-06,
+      "loss": 2.0113702774047852,
+      "step": 430
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 41.89128494262695,
+      "learning_rate": 8.911229300477716e-06,
+      "loss": 1.6521787643432617,
+      "step": 440
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 44.65105438232422,
+      "learning_rate": 8.837691011169944e-06,
+      "loss": 2.2836629867553713,
+      "step": 450
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 42.151737213134766,
+      "learning_rate": 8.762074544478622e-06,
+      "loss": 1.705312156677246,
+      "step": 460
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 36.330989837646484,
+      "learning_rate": 8.68442084805442e-06,
+      "loss": 1.4402057647705078,
+      "step": 470
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 27.495149612426758,
+      "learning_rate": 8.604771972743848e-06,
+      "loss": 1.9172407150268556,
+      "step": 480
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 17.782899856567383,
+      "learning_rate": 8.523171049817974e-06,
+      "loss": 1.5030399322509767,
+      "step": 490
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 34.83807373046875,
+      "learning_rate": 8.439662267616093e-06,
+      "loss": 1.9837615966796875,
+      "step": 500
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 13.142373085021973,
+      "learning_rate": 8.354290847616954e-06,
+      "loss": 1.2435311317443847,
+      "step": 510
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 37.417720794677734,
+      "learning_rate": 8.267103019950529e-06,
+      "loss": 1.23653564453125,
+      "step": 520
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 18.470767974853516,
+      "learning_rate": 8.178145998363585e-06,
+      "loss": 0.8462669372558593,
+      "step": 530
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 27.512048721313477,
+      "learning_rate": 8.087467954652608e-06,
+      "loss": 1.2925146102905274,
+      "step": 540
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 37.81305694580078,
+      "learning_rate": 7.99511799257793e-06,
+      "loss": 0.901913833618164,
+      "step": 550
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 37.69697570800781,
+      "learning_rate": 7.901146121273165e-06,
+      "loss": 1.3357799530029297,
+      "step": 560
+    },
+    {
+      "epoch": 1.1400000000000001,
+      "grad_norm": 34.828433990478516,
+      "learning_rate": 7.80560322816439e-06,
+      "loss": 1.3306777954101563,
+      "step": 570
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 38.92500305175781,
+      "learning_rate": 7.7085410514137e-06,
+      "loss": 0.944632625579834,
+      "step": 580
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 19.071941375732422,
+      "learning_rate": 7.610012151902091e-06,
+      "loss": 1.3212141036987304,
+      "step": 590
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 34.952938079833984,
+      "learning_rate": 7.510069884766802e-06,
+      "loss": 1.2321388244628906,
+      "step": 600
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 32.1840934753418,
+      "learning_rate": 7.408768370508577e-06,
+      "loss": 1.3100163459777832,
+      "step": 610
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 23.4957275390625,
+      "learning_rate": 7.3061624656844544e-06,
+      "loss": 1.179959774017334,
+      "step": 620
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 40.54483413696289,
+      "learning_rate": 7.2023077332019755e-06,
+      "loss": 0.8590527534484863,
+      "step": 630
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 42.49688720703125,
+      "learning_rate": 7.0972604122308865e-06,
+      "loss": 1.3245353698730469,
+      "step": 640
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 38.857479095458984,
+      "learning_rate": 6.991077387748643e-06,
+      "loss": 0.9064340591430664,
+      "step": 650
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 24.489877700805664,
+      "learning_rate": 6.883816159736187e-06,
+      "loss": 1.3220383644104003,
+      "step": 660
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 18.46355628967285,
+      "learning_rate": 6.775534812040686e-06,
+      "loss": 0.7077834129333496,
+      "step": 670
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 24.25245475769043,
+      "learning_rate": 6.666291980922122e-06,
+      "loss": 0.9919247627258301,
+      "step": 680
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 48.17041778564453,
+      "learning_rate": 6.556146823300701e-06,
+      "loss": 1.6220426559448242,
+      "step": 690
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 47.63260269165039,
+      "learning_rate": 6.445158984722358e-06,
+      "loss": 1.3412548065185548,
+      "step": 700
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 24.807323455810547,
+      "learning_rate": 6.3333885670596285e-06,
+      "loss": 1.2461795806884766,
+      "step": 710
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 11.098411560058594,
+      "learning_rate": 6.220896095965428e-06,
+      "loss": 1.0722078323364257,
+      "step": 720
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 36.12248611450195,
+      "learning_rate": 6.107742488097338e-06,
+      "loss": 0.83670015335083,
+      "step": 730
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 39.64963150024414,
+      "learning_rate": 5.993989018130173e-06,
+      "loss": 1.1005640029907227,
+      "step": 740
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 35.805389404296875,
+      "learning_rate": 5.879697285574655e-06,
+      "loss": 1.5326812744140625,
+      "step": 750
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 20.854694366455078,
+      "learning_rate": 5.764929181420191e-06,
+      "loss": 1.028077983856201,
+      "step": 760
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 19.16396141052246,
+      "learning_rate": 5.649746854619814e-06,
+      "loss": 1.1157980918884278,
+      "step": 770
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 26.597848892211914,
+      "learning_rate": 5.5342126784354265e-06,
+      "loss": 1.2585329055786132,
+      "step": 780
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 43.42577362060547,
+      "learning_rate": 5.41838921666158e-06,
+      "loss": 1.1203573226928711,
+      "step": 790
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 63.867942810058594,
+      "learning_rate": 5.3023391897460715e-06,
+      "loss": 1.0436135292053224,
+      "step": 800
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 36.27252960205078,
+      "learning_rate": 5.18612544082573e-06,
+      "loss": 0.9347926139831543,
+      "step": 810
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 33.137611389160156,
+      "learning_rate": 5.069810901695727e-06,
+      "loss": 1.5266364097595215,
+      "step": 820
+    },
+    {
+      "epoch": 1.6600000000000001,
+      "grad_norm": 46.118202209472656,
+      "learning_rate": 4.953458558730917e-06,
+      "loss": 1.1257129669189454,
+      "step": 830
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 31.607257843017578,
+      "learning_rate": 4.837131418777595e-06,
+      "loss": 0.9643683433532715,
+      "step": 840
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 50.87643814086914,
+      "learning_rate": 4.720892475034181e-06,
+      "loss": 1.3242192268371582,
+      "step": 850
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 27.850143432617188,
+      "learning_rate": 4.604804672939295e-06,
+      "loss": 1.251343059539795,
+      "step": 860
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 45.26017379760742,
+      "learning_rate": 4.4889308760856826e-06,
+      "loss": 1.1028053283691406,
+      "step": 870
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 3.31717586517334,
+      "learning_rate": 4.373333832178478e-06,
+      "loss": 0.8769556045532226,
+      "step": 880
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 26.864580154418945,
+      "learning_rate": 4.258076139056217e-06,
+      "loss": 1.1681681632995606,
+      "step": 890
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 33.86524200439453,
+      "learning_rate": 4.143220210792993e-06,
+      "loss": 0.9344164848327636,
+      "step": 900
+    },
+    {
+      "epoch": 1.8199999999999998,
+      "grad_norm": 25.299028396606445,
+      "learning_rate": 4.028828243900141e-06,
+      "loss": 1.634626579284668,
+      "step": 910
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 28.403207778930664,
+      "learning_rate": 3.914962183645733e-06,
+      "loss": 1.0626420974731445,
+      "step": 920
+    },
+    {
+      "epoch": 1.8599999999999999,
+      "grad_norm": 29.372901916503906,
+      "learning_rate": 3.8016836905101157e-06,
+      "loss": 1.375041389465332,
+      "step": 930
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 21.600330352783203,
+      "learning_rate": 3.6890541067956775e-06,
+      "loss": 0.9415129661560059,
+      "step": 940
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 20.263734817504883,
+      "learning_rate": 3.577134423408906e-06,
+      "loss": 0.8620157241821289,
+      "step": 950
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 37.88676834106445,
+      "learning_rate": 3.465985246832739e-06,
+      "loss": 1.1039237976074219,
+      "step": 960
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 8.769469261169434,
+      "learning_rate": 3.355666766307084e-06,
+      "loss": 0.8490506172180176,
+      "step": 970
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 44.77504348754883,
+      "learning_rate": 3.246238721235283e-06,
+      "loss": 1.2799974441528321,
+      "step": 980
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 15.338781356811523,
+      "learning_rate": 3.137760368834169e-06,
+      "loss": 0.8015480995178222,
+      "step": 990
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 33.2166748046875,
+      "learning_rate": 3.030290452045245e-06,
+      "loss": 1.091315746307373,
+      "step": 1000
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 4.909487247467041,
+      "learning_rate": 2.9238871677243354e-06,
+      "loss": 0.47315549850463867,
+      "step": 1010
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 39.29719161987305,
+      "learning_rate": 2.818608135126967e-06,
+      "loss": 0.3728752613067627,
+      "step": 1020
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 21.967544555664062,
+      "learning_rate": 2.714510364706531e-06,
+      "loss": 0.33084559440612793,
+      "step": 1030
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 25.645288467407227,
+      "learning_rate": 2.611650227242102e-06,
+      "loss": 0.32590973377227783,
+      "step": 1040
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 18.202743530273438,
+      "learning_rate": 2.5100834233126827e-06,
+      "loss": 0.4684451580047607,
+      "step": 1050
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.5234746336936951,
+      "learning_rate": 2.40986495313435e-06,
+      "loss": 0.26931188106536863,
+      "step": 1060
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 21.24897575378418,
+      "learning_rate": 2.3110490867766644e-06,
+      "loss": 0.499393892288208,
+      "step": 1070
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 13.816218376159668,
+      "learning_rate": 2.213689334774479e-06,
+      "loss": 0.3078450202941895,
+      "step": 1080
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 23.9191837310791,
+      "learning_rate": 2.1178384191510344e-06,
+      "loss": 0.47670416831970214,
+      "step": 1090
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 34.2762451171875,
+      "learning_rate": 2.023548244868051e-06,
+      "loss": 0.47382168769836425,
+      "step": 1100
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 19.34497833251953,
+      "learning_rate": 1.9308698717182874e-06,
+      "loss": 0.19442765712738036,
+      "step": 1110
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 28.95246124267578,
+      "learning_rate": 1.8398534866757455e-06,
+      "loss": 0.44660329818725586,
+      "step": 1120
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 1.9053665399551392,
+      "learning_rate": 1.7505483767185583e-06,
+      "loss": 0.36274888515472414,
+      "step": 1130
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 31.379884719848633,
+      "learning_rate": 1.6630029021392007e-06,
+      "loss": 0.24480688571929932,
+      "step": 1140
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 17.360788345336914,
+      "learning_rate": 1.5772644703565564e-06,
+      "loss": 0.14373520612716675,
+      "step": 1150
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 36.79311752319336,
+      "learning_rate": 1.4933795102439558e-06,
+      "loss": 0.34253692626953125,
+      "step": 1160
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 9.673837661743164,
+      "learning_rate": 1.4113934469871166e-06,
+      "loss": 0.1978028893470764,
+      "step": 1170
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.5280386805534363,
+      "learning_rate": 1.3313506774856177e-06,
+      "loss": 0.29554598331451415,
+      "step": 1180
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 1.7119940519332886,
+      "learning_rate": 1.2532945463111856e-06,
+      "loss": 0.3423331260681152,
+      "step": 1190
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 9.490172386169434,
+      "learning_rate": 1.1772673222358421e-06,
+      "loss": 0.3274805784225464,
+      "step": 1200
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.7689626216888428,
+      "learning_rate": 1.1033101753426285e-06,
+      "loss": 0.29171273708343504,
+      "step": 1210
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.009632566943764687,
+      "learning_rate": 1.0314631547312738e-06,
+      "loss": 0.2250969171524048,
+      "step": 1220
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 46.948333740234375,
+      "learning_rate": 9.617651668308914e-07,
+      "loss": 0.2975991487503052,
+      "step": 1230
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.1608089804649353,
+      "learning_rate": 8.942539543314799e-07,
+      "loss": 0.3745620012283325,
+      "step": 1240
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 41.225494384765625,
+      "learning_rate": 8.289660757455803e-07,
+      "loss": 0.3142155885696411,
+      "step": 1250
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 38.09383010864258,
+      "learning_rate": 7.659368856111926e-07,
+      "loss": 0.4468146800994873,
+      "step": 1260
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 25.196218490600586,
+      "learning_rate": 7.052005153466779e-07,
+      "loss": 0.514287281036377,
+      "step": 1270
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 22.963035583496094,
+      "learning_rate": 6.467898547679913e-07,
+      "loss": 0.21953434944152833,
+      "step": 1280
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 17.07082176208496,
+      "learning_rate": 5.9073653427826e-07,
+      "loss": 0.3766503095626831,
+      "step": 1290
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 38.808040618896484,
+      "learning_rate": 5.370709077393721e-07,
+      "loss": 0.3407785892486572,
+      "step": 1300
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 52.602874755859375,
+      "learning_rate": 4.858220360348187e-07,
+      "loss": 0.2537382125854492,
+      "step": 1310
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 19.56964874267578,
+      "learning_rate": 4.370176713327118e-07,
+      "loss": 0.25959508419036864,
+      "step": 1320
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 5.28275203704834,
+      "learning_rate": 3.90684242057498e-07,
+      "loss": 0.43554534912109377,
+      "step": 1330
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 31.416179656982422,
+      "learning_rate": 3.468468385785023e-07,
+      "loss": 0.5232177257537842,
+      "step": 1340
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 46.08461380004883,
+      "learning_rate": 3.055291996230492e-07,
+      "loss": 0.2125147581100464,
+      "step": 1350
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 11.485236167907715,
+      "learning_rate": 2.6675369942151864e-07,
+      "loss": 0.21367454528808594,
+      "step": 1360
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 31.298377990722656,
+      "learning_rate": 2.3054133559131163e-07,
+      "loss": 0.1693113088607788,
+      "step": 1370
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 30.015377044677734,
+      "learning_rate": 1.9691171776626882e-07,
+      "loss": 0.2792075157165527,
+      "step": 1380
+    },
+    {
+      "epoch": 2.7800000000000002,
+      "grad_norm": 0.11436483263969421,
+      "learning_rate": 1.6588305697770313e-07,
+      "loss": 0.13291265964508056,
+      "step": 1390
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 54.67913818359375,
+      "learning_rate": 1.374721557928116e-07,
+      "loss": 0.4104594707489014,
+      "step": 1400
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 29.346342086791992,
+      "learning_rate": 1.1169439921578485e-07,
+      "loss": 0.5142350196838379,
+      "step": 1410
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.025704028084874153,
+      "learning_rate": 8.856374635655696e-08,
+      "loss": 0.31447272300720214,
+      "step": 1420
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 14.04995059967041,
+      "learning_rate": 6.809272287169988e-08,
+      "loss": 0.32525787353515623,
+      "step": 1430
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 5.467782020568848,
+      "learning_rate": 5.029241418156139e-08,
+      "loss": 0.1824193000793457,
+      "step": 1440
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 14.223469734191895,
+      "learning_rate": 3.517245946731529e-08,
+      "loss": 0.2836474895477295,
+      "step": 1450
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 18.699003219604492,
+      "learning_rate": 2.27410464511707e-08,
+      "loss": 0.20449333190917968,
+      "step": 1460
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 12.462102890014648,
+      "learning_rate": 1.3004906962578723e-08,
+      "loss": 0.30746448040008545,
+      "step": 1470
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 2.1692745685577393,
+      "learning_rate": 5.969313292830126e-09,
+      "loss": 0.2320650577545166,
+      "step": 1480
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 30.105022430419922,
+      "learning_rate": 1.638075340010814e-09,
+      "loss": 0.39888916015625,
+      "step": 1490
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 50.01400375366211,
+      "learning_rate": 1.3538545881042198e-11,
+      "loss": 0.3253091096878052,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "step": 1500,
+      "total_flos": 2.273097293733888e+16,
+      "train_loss": 1.3163418625195822,
+      "train_runtime": 1442.119,
+      "train_samples_per_second": 2.08,
+      "train_steps_per_second": 1.04
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.273097293733888e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:15c16c89e0248601489fb73306460d82edc45f2ae6fbf494d55091ad081eec56
+size 5521

training_loss.png ADDED Viewed