secmlr
/

SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation

Instructions to use secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation with Transformers:

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

pipe = pipeline("text-generation", model="secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation")
model = AutoModelForCausalLM.from_pretrained("secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation

SGLang

How to use secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation 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 "secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation" \
    --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": "secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation" \
        --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": "secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation with Docker Model Runner:
```
docker model run hf.co/secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_code_32B_5k_first_2000_generation
```

yuzhounie commited on Apr 24, 2025

Commit

b4cc776

verified ·

1 Parent(s): 2f0e92c

Training in progress, step 180

Browse files

Files changed (15) hide show

model-00001-of-00014.safetensors +1 -1
model-00002-of-00014.safetensors +1 -1
model-00003-of-00014.safetensors +1 -1
model-00004-of-00014.safetensors +1 -1
model-00005-of-00014.safetensors +1 -1
model-00006-of-00014.safetensors +1 -1
model-00007-of-00014.safetensors +1 -1
model-00008-of-00014.safetensors +1 -1
model-00009-of-00014.safetensors +1 -1
model-00010-of-00014.safetensors +1 -1
model-00011-of-00014.safetensors +1 -1
model-00012-of-00014.safetensors +1 -1
model-00013-of-00014.safetensors +1 -1
model-00014-of-00014.safetensors +1 -1
trainer_log.jsonl +76 -0

model-00001-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:246a64ebae920dad9731582a0df746fe5cd2e1e95a89b03fed904aaae07abba7
 size 4891730992

 version https://git-lfs.github.com/spec/v1
+oid sha256:04785939aaed91228a2b40e4a096c892597d9388e579d68cb9f209992cfb7d25
 size 4891730992

model-00002-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a53f4a51c7be99dd91e5f3a871244251d521c7eb9c3978ea8f8ebe9e3d5f1a3
 size 4876059352

 version https://git-lfs.github.com/spec/v1
+oid sha256:7a5b59d89dc8d89a34effc9e86f515dac5503c578710aad515a47e3d0c0491bd
 size 4876059352

model-00003-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b2fed71ac59fcdf6bcc865ed93794feeb6d23772c70fb68d02c446d9ca34cf3
 size 4876059384

 version https://git-lfs.github.com/spec/v1
+oid sha256:2a98da4389573017527b7c4431ccd8498387fd7296474f993ecef9a4e5005785
 size 4876059384

model-00004-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05a6f625291f900605f431b062f0a7dc2724e9691c270c3b86c8fb50667aabc0
 size 4876059416

 version https://git-lfs.github.com/spec/v1
+oid sha256:3b12c9846569e13e5ee98dd555d4370236724c207661b408d369b55b3aec54b9
 size 4876059416

model-00005-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:734f92c80279f603ebf4d888e94ff47951e9d39810959c563a40620f41ff3056
 size 4876059416

 version https://git-lfs.github.com/spec/v1
+oid sha256:43042ad0f326b5363d041078270670e7bc46aa7b45831be296fde4052915b817
 size 4876059416

model-00006-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b612aa2648374221bdcf2bd895cb28c13b2991ea44385c3135338e0511e007ca
 size 4876059416

 version https://git-lfs.github.com/spec/v1
+oid sha256:7ddbe7f29badaa54cef5caf7f585dbd2e5cb314387cb8b13e4ae2148492721ff
 size 4876059416

model-00007-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94b7834330753d8579a478797141603529870c4b2fbd20d0e2464c912bab1591
 size 4876059416

 version https://git-lfs.github.com/spec/v1
+oid sha256:0a6b65084c233d4a66304644a1be6c7b5bc2cc9dc24c8ff674b740c66c96c89c
 size 4876059416

model-00008-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23e8a4a699f93335c37b29395d14ca027788223871e3b6501fa1e63d33ae0a94
 size 4876059416

 version https://git-lfs.github.com/spec/v1
+oid sha256:850110ebe855cea0c6f6fb33dccc4b6c372472a80167636de0080e3524b1e39d
 size 4876059416

model-00009-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa4fded350b920c92ccfa1cc03d4fdc2a5f5eda4b394bb51efe4c3e3a3e435c7
 size 4876059416

 version https://git-lfs.github.com/spec/v1
+oid sha256:b3058042f232460ecb4a0f5c3e9476bed8bf5fbf0c7814cd2b26320567e26f69
 size 4876059416

model-00010-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa2d22bcf07e772756bbf9930e62ae62bb24b283eaba9bd85da18e6da6167d9
 size 4876059416

 version https://git-lfs.github.com/spec/v1
+oid sha256:1a19feaf250d7645a802bdd26aa79b6bb6f7b8375abc6de4198a913da8eea0a7
 size 4876059416

model-00011-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25d2ba082e5115d485de816219cfc6112c49c9ef8af25472fd7972e386f2f5b3
 size 4876059416

 version https://git-lfs.github.com/spec/v1
+oid sha256:170d93b902e2f7c3e3981562999214ea8495e7aa42bff9b026d86f5abb10fb27
 size 4876059416

model-00012-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da8d43be4ce8f98205fb0bb826e31cba0c02d60504ec91adf54a3264d51104c
 size 4876059416

 version https://git-lfs.github.com/spec/v1
+oid sha256:1916a4fcdb7f2fe26f7faf400139090d2b549edb06f78678335828613b6acc5e
 size 4876059416

model-00013-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fb187e5194de2c8f71e0de69d77c7ad64bebcbffd07ab59150c800df3835a47
 size 4876059416

 version https://git-lfs.github.com/spec/v1
+oid sha256:3e32118b8ea3e13d656310a3d7328804419c21dd8271ccfe4304ebf6e820f260
 size 4876059416

model-00014-of-00014.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:116705d0bf73cff942babe22edd1e9f376db6067876e3a4ff9b2d85b97c1785b
 size 2123397800

 version https://git-lfs.github.com/spec/v1
+oid sha256:6a9d29978e533264fdcef5fd6a45af0027b61aff5a1cb16282c6d3e19d9ad682
 size 2123397800

trainer_log.jsonl CHANGED Viewed

@@ -103,3 +103,79 @@
 {"current_steps": 103, "total_steps": 180, "loss": 0.3378, "lr": 4.7092758554476215e-06, "epoch": 1.6980609418282548, "percentage": 57.22, "elapsed_time": "3:49:21", "remaining_time": "2:51:27"}
 {"current_steps": 104, "total_steps": 180, "loss": 0.3915, "lr": 4.6125378966403465e-06, "epoch": 1.7146814404432131, "percentage": 57.78, "elapsed_time": "3:51:55", "remaining_time": "2:49:28"}
 {"current_steps": 105, "total_steps": 180, "loss": 0.3484, "lr": 4.515945646484105e-06, "epoch": 1.7313019390581719, "percentage": 58.33, "elapsed_time": "3:54:13", "remaining_time": "2:47:18"}

 {"current_steps": 103, "total_steps": 180, "loss": 0.3378, "lr": 4.7092758554476215e-06, "epoch": 1.6980609418282548, "percentage": 57.22, "elapsed_time": "3:49:21", "remaining_time": "2:51:27"}
 {"current_steps": 104, "total_steps": 180, "loss": 0.3915, "lr": 4.6125378966403465e-06, "epoch": 1.7146814404432131, "percentage": 57.78, "elapsed_time": "3:51:55", "remaining_time": "2:49:28"}
 {"current_steps": 105, "total_steps": 180, "loss": 0.3484, "lr": 4.515945646484105e-06, "epoch": 1.7313019390581719, "percentage": 58.33, "elapsed_time": "3:54:13", "remaining_time": "2:47:18"}
+{"current_steps": 106, "total_steps": 180, "loss": 0.3501, "lr": 4.4195354293738484e-06, "epoch": 1.7479224376731302, "percentage": 58.89, "elapsed_time": "3:56:42", "remaining_time": "2:45:14"}
+{"current_steps": 107, "total_steps": 180, "loss": 0.3818, "lr": 4.323343501249346e-06, "epoch": 1.7645429362880887, "percentage": 59.44, "elapsed_time": "3:59:09", "remaining_time": "2:43:09"}
+{"current_steps": 108, "total_steps": 180, "loss": 0.4027, "lr": 4.227406035960798e-06, "epoch": 1.7811634349030472, "percentage": 60.0, "elapsed_time": "4:01:31", "remaining_time": "2:41:00"}
+{"current_steps": 109, "total_steps": 180, "loss": 0.3295, "lr": 4.131759111665349e-06, "epoch": 1.7977839335180055, "percentage": 60.56, "elapsed_time": "4:05:37", "remaining_time": "2:39:59"}
+{"current_steps": 110, "total_steps": 180, "loss": 0.3339, "lr": 4.036438697259551e-06, "epoch": 1.814404432132964, "percentage": 61.11, "elapsed_time": "4:07:59", "remaining_time": "2:37:48"}
+{"current_steps": 111, "total_steps": 180, "loss": 0.3519, "lr": 3.941480638852948e-06, "epoch": 1.8310249307479225, "percentage": 61.67, "elapsed_time": "4:10:40", "remaining_time": "2:35:49"}
+{"current_steps": 112, "total_steps": 180, "loss": 0.328, "lr": 3.8469206462878e-06, "epoch": 1.8476454293628808, "percentage": 62.22, "elapsed_time": "4:12:54", "remaining_time": "2:33:32"}
+{"current_steps": 113, "total_steps": 180, "loss": 0.3753, "lr": 3.752794279710094e-06, "epoch": 1.8642659279778393, "percentage": 62.78, "elapsed_time": "4:15:40", "remaining_time": "2:31:35"}
+{"current_steps": 114, "total_steps": 180, "loss": 0.393, "lr": 3.6591369361968127e-06, "epoch": 1.8808864265927978, "percentage": 63.33, "elapsed_time": "4:17:37", "remaining_time": "2:29:09"}
+{"current_steps": 115, "total_steps": 180, "loss": 0.3182, "lr": 3.5659838364445505e-06, "epoch": 1.897506925207756, "percentage": 63.89, "elapsed_time": "4:19:44", "remaining_time": "2:26:48"}
+{"current_steps": 116, "total_steps": 180, "loss": 0.3463, "lr": 3.473370011524435e-06, "epoch": 1.9141274238227148, "percentage": 64.44, "elapsed_time": "4:21:44", "remaining_time": "2:24:24"}
+{"current_steps": 117, "total_steps": 180, "loss": 0.3694, "lr": 3.3813302897083955e-06, "epoch": 1.9307479224376731, "percentage": 65.0, "elapsed_time": "4:23:35", "remaining_time": "2:21:56"}
+{"current_steps": 118, "total_steps": 180, "loss": 0.3693, "lr": 3.289899283371657e-06, "epoch": 1.9473684210526314, "percentage": 65.56, "elapsed_time": "4:25:40", "remaining_time": "2:19:35"}
+{"current_steps": 119, "total_steps": 180, "loss": 0.3325, "lr": 3.1991113759764493e-06, "epoch": 1.9639889196675901, "percentage": 66.11, "elapsed_time": "4:27:32", "remaining_time": "2:17:08"}
+{"current_steps": 120, "total_steps": 180, "loss": 0.3497, "lr": 3.1090007091417884e-06, "epoch": 1.9806094182825484, "percentage": 66.67, "elapsed_time": "4:29:28", "remaining_time": "2:14:44"}
+{"current_steps": 121, "total_steps": 180, "loss": 0.4239, "lr": 3.019601169804216e-06, "epoch": 1.997229916897507, "percentage": 67.22, "elapsed_time": "4:31:29", "remaining_time": "2:12:22"}
+{"current_steps": 122, "total_steps": 180, "loss": 0.302, "lr": 2.9309463774743047e-06, "epoch": 2.0, "percentage": 67.78, "elapsed_time": "4:31:37", "remaining_time": "2:09:07"}
+{"current_steps": 123, "total_steps": 180, "loss": 0.2255, "lr": 2.843069671593734e-06, "epoch": 2.0166204986149583, "percentage": 68.33, "elapsed_time": "4:33:38", "remaining_time": "2:06:48"}
+{"current_steps": 124, "total_steps": 180, "loss": 0.2275, "lr": 2.7560040989976894e-06, "epoch": 2.033240997229917, "percentage": 68.89, "elapsed_time": "4:35:39", "remaining_time": "2:04:29"}
+{"current_steps": 125, "total_steps": 180, "loss": 0.2648, "lr": 2.6697824014873076e-06, "epoch": 2.0498614958448753, "percentage": 69.44, "elapsed_time": "4:37:37", "remaining_time": "2:02:09"}
+{"current_steps": 126, "total_steps": 180, "loss": 0.2707, "lr": 2.5844370035168077e-06, "epoch": 2.0664819944598336, "percentage": 70.0, "elapsed_time": "4:39:27", "remaining_time": "1:59:46"}
+{"current_steps": 127, "total_steps": 180, "loss": 0.2764, "lr": 2.5000000000000015e-06, "epoch": 2.0831024930747923, "percentage": 70.56, "elapsed_time": "4:41:23", "remaining_time": "1:57:25"}
+{"current_steps": 128, "total_steps": 180, "loss": 0.2503, "lr": 2.4165031442406857e-06, "epoch": 2.0997229916897506, "percentage": 71.11, "elapsed_time": "4:43:10", "remaining_time": "1:55:02"}
+{"current_steps": 129, "total_steps": 180, "loss": 0.2406, "lr": 2.333977835991545e-06, "epoch": 2.1163434903047094, "percentage": 71.67, "elapsed_time": "4:45:02", "remaining_time": "1:52:41"}
+{"current_steps": 130, "total_steps": 180, "loss": 0.2155, "lr": 2.2524551096459703e-06, "epoch": 2.1329639889196677, "percentage": 72.22, "elapsed_time": "4:47:31", "remaining_time": "1:50:35"}
+{"current_steps": 131, "total_steps": 180, "loss": 0.2787, "lr": 2.171965622567308e-06, "epoch": 2.149584487534626, "percentage": 72.78, "elapsed_time": "4:49:31", "remaining_time": "1:48:17"}
+{"current_steps": 132, "total_steps": 180, "loss": 0.246, "lr": 2.0925396435598665e-06, "epoch": 2.1662049861495847, "percentage": 73.33, "elapsed_time": "4:51:21", "remaining_time": "1:45:56"}
+{"current_steps": 133, "total_steps": 180, "loss": 0.2609, "lr": 2.0142070414860704e-06, "epoch": 2.182825484764543, "percentage": 73.89, "elapsed_time": "4:53:29", "remaining_time": "1:43:42"}
+{"current_steps": 134, "total_steps": 180, "loss": 0.2876, "lr": 1.936997274033986e-06, "epoch": 2.1994459833795013, "percentage": 74.44, "elapsed_time": "4:55:24", "remaining_time": "1:41:24"}
+{"current_steps": 135, "total_steps": 180, "loss": 0.288, "lr": 1.8609393766395083e-06, "epoch": 2.21606648199446, "percentage": 75.0, "elapsed_time": "4:57:16", "remaining_time": "1:39:05"}
+{"current_steps": 136, "total_steps": 180, "loss": 0.2958, "lr": 1.7860619515673034e-06, "epoch": 2.2326869806094183, "percentage": 75.56, "elapsed_time": "4:59:07", "remaining_time": "1:36:46"}
+{"current_steps": 137, "total_steps": 180, "loss": 0.2506, "lr": 1.7123931571546826e-06, "epoch": 2.2493074792243766, "percentage": 76.11, "elapsed_time": "5:01:06", "remaining_time": "1:34:30"}
+{"current_steps": 138, "total_steps": 180, "loss": 0.2166, "lr": 1.639960697222388e-06, "epoch": 2.2659279778393353, "percentage": 76.67, "elapsed_time": "5:03:08", "remaining_time": "1:32:15"}
+{"current_steps": 139, "total_steps": 180, "loss": 0.2558, "lr": 1.5687918106563326e-06, "epoch": 2.2825484764542936, "percentage": 77.22, "elapsed_time": "5:04:55", "remaining_time": "1:29:56"}
+{"current_steps": 140, "total_steps": 180, "loss": 0.2315, "lr": 1.4989132611641576e-06, "epoch": 2.299168975069252, "percentage": 77.78, "elapsed_time": "5:06:49", "remaining_time": "1:27:39"}
+{"current_steps": 141, "total_steps": 180, "loss": 0.278, "lr": 1.4303513272105057e-06, "epoch": 2.3157894736842106, "percentage": 78.33, "elapsed_time": "5:08:56", "remaining_time": "1:25:27"}
+{"current_steps": 142, "total_steps": 180, "loss": 0.2469, "lr": 1.3631317921347564e-06, "epoch": 2.332409972299169, "percentage": 78.89, "elapsed_time": "5:10:59", "remaining_time": "1:23:13"}
+{"current_steps": 143, "total_steps": 180, "loss": 0.2363, "lr": 1.297279934454978e-06, "epoch": 2.349030470914127, "percentage": 79.44, "elapsed_time": "5:13:01", "remaining_time": "1:20:59"}
+{"current_steps": 144, "total_steps": 180, "loss": 0.2582, "lr": 1.2328205183616964e-06, "epoch": 2.365650969529086, "percentage": 80.0, "elapsed_time": "5:14:58", "remaining_time": "1:18:44"}
+{"current_steps": 145, "total_steps": 180, "loss": 0.2354, "lr": 1.1697777844051105e-06, "epoch": 2.3822714681440442, "percentage": 80.56, "elapsed_time": "5:17:00", "remaining_time": "1:16:31"}
+{"current_steps": 146, "total_steps": 180, "loss": 0.2628, "lr": 1.1081754403792e-06, "epoch": 2.398891966759003, "percentage": 81.11, "elapsed_time": "5:18:55", "remaining_time": "1:14:16"}
+{"current_steps": 147, "total_steps": 180, "loss": 0.2465, "lr": 1.0480366524062041e-06, "epoch": 2.4155124653739612, "percentage": 81.67, "elapsed_time": "5:20:49", "remaining_time": "1:12:01"}
+{"current_steps": 148, "total_steps": 180, "loss": 0.2494, "lr": 9.893840362247809e-07, "epoch": 2.4321329639889195, "percentage": 82.22, "elapsed_time": "5:22:40", "remaining_time": "1:09:46"}
+{"current_steps": 149, "total_steps": 180, "loss": 0.2572, "lr": 9.322396486851626e-07, "epoch": 2.4487534626038783, "percentage": 82.78, "elapsed_time": "5:24:39", "remaining_time": "1:07:32"}
+{"current_steps": 150, "total_steps": 180, "loss": 0.2473, "lr": 8.766249794544662e-07, "epoch": 2.4653739612188366, "percentage": 83.33, "elapsed_time": "5:26:37", "remaining_time": "1:05:19"}
+{"current_steps": 151, "total_steps": 180, "loss": 0.2334, "lr": 8.225609429353187e-07, "epoch": 2.481994459833795, "percentage": 83.89, "elapsed_time": "5:28:31", "remaining_time": "1:03:05"}
+{"current_steps": 152, "total_steps": 180, "loss": 0.2464, "lr": 7.700678704007947e-07, "epoch": 2.4986149584487536, "percentage": 84.44, "elapsed_time": "5:30:40", "remaining_time": "1:00:54"}
+{"current_steps": 153, "total_steps": 180, "loss": 0.2386, "lr": 7.191655023486682e-07, "epoch": 2.515235457063712, "percentage": 85.0, "elapsed_time": "5:32:36", "remaining_time": "0:58:41"}
+{"current_steps": 154, "total_steps": 180, "loss": 0.2231, "lr": 6.698729810778065e-07, "epoch": 2.5318559556786706, "percentage": 85.56, "elapsed_time": "5:34:39", "remaining_time": "0:56:30"}
+{"current_steps": 155, "total_steps": 180, "loss": 0.2746, "lr": 6.222088434895462e-07, "epoch": 2.548476454293629, "percentage": 86.11, "elapsed_time": "5:36:41", "remaining_time": "0:54:18"}
+{"current_steps": 156, "total_steps": 180, "loss": 0.2753, "lr": 5.76191014116711e-07, "epoch": 2.565096952908587, "percentage": 86.67, "elapsed_time": "5:38:35", "remaining_time": "0:52:05"}
+{"current_steps": 157, "total_steps": 180, "loss": 0.2295, "lr": 5.318367983829393e-07, "epoch": 2.581717451523546, "percentage": 87.22, "elapsed_time": "5:40:34", "remaining_time": "0:49:53"}
+{"current_steps": 158, "total_steps": 180, "loss": 0.2623, "lr": 4.891628760948114e-07, "epoch": 2.598337950138504, "percentage": 87.78, "elapsed_time": "5:42:33", "remaining_time": "0:47:41"}
+{"current_steps": 159, "total_steps": 180, "loss": 0.2505, "lr": 4.481852951692672e-07, "epoch": 2.6149584487534625, "percentage": 88.33, "elapsed_time": "5:44:24", "remaining_time": "0:45:29"}
+{"current_steps": 160, "total_steps": 180, "loss": 0.2944, "lr": 4.089194655986306e-07, "epoch": 2.6315789473684212, "percentage": 88.89, "elapsed_time": "5:47:37", "remaining_time": "0:43:27"}
+{"current_steps": 161, "total_steps": 180, "loss": 0.2929, "lr": 3.7138015365554834e-07, "epoch": 2.6481994459833795, "percentage": 89.44, "elapsed_time": "5:49:34", "remaining_time": "0:41:15"}
+{"current_steps": 162, "total_steps": 180, "loss": 0.2669, "lr": 3.355814763399973e-07, "epoch": 2.664819944598338, "percentage": 90.0, "elapsed_time": "5:51:36", "remaining_time": "0:39:04"}
+{"current_steps": 163, "total_steps": 180, "loss": 0.2464, "lr": 3.015368960704584e-07, "epoch": 2.6814404432132966, "percentage": 90.56, "elapsed_time": "5:53:37", "remaining_time": "0:36:52"}
+{"current_steps": 164, "total_steps": 180, "loss": 0.233, "lr": 2.6925921562124867e-07, "epoch": 2.698060941828255, "percentage": 91.11, "elapsed_time": "5:55:41", "remaining_time": "0:34:42"}
+{"current_steps": 165, "total_steps": 180, "loss": 0.2115, "lr": 2.3876057330792344e-07, "epoch": 2.714681440443213, "percentage": 91.67, "elapsed_time": "5:57:48", "remaining_time": "0:32:31"}
+{"current_steps": 166, "total_steps": 180, "loss": 0.2419, "lr": 2.1005243842255552e-07, "epoch": 2.731301939058172, "percentage": 92.22, "elapsed_time": "5:59:52", "remaining_time": "0:30:21"}
+{"current_steps": 167, "total_steps": 180, "loss": 0.2442, "lr": 1.8314560692059836e-07, "epoch": 2.74792243767313, "percentage": 92.78, "elapsed_time": "6:01:55", "remaining_time": "0:28:10"}
+{"current_steps": 168, "total_steps": 180, "loss": 0.304, "lr": 1.5805019736097105e-07, "epoch": 2.7645429362880884, "percentage": 93.33, "elapsed_time": "6:04:05", "remaining_time": "0:26:00"}
+{"current_steps": 169, "total_steps": 180, "loss": 0.2604, "lr": 1.3477564710088097e-07, "epoch": 2.781163434903047, "percentage": 93.89, "elapsed_time": "6:06:06", "remaining_time": "0:23:49"}
+{"current_steps": 170, "total_steps": 180, "loss": 0.2319, "lr": 1.1333070874682217e-07, "epoch": 2.7977839335180055, "percentage": 94.44, "elapsed_time": "6:08:07", "remaining_time": "0:21:39"}
+{"current_steps": 171, "total_steps": 180, "loss": 0.2648, "lr": 9.372344686307655e-08, "epoch": 2.8144044321329638, "percentage": 95.0, "elapsed_time": "6:10:09", "remaining_time": "0:19:28"}
+{"current_steps": 172, "total_steps": 180, "loss": 0.2671, "lr": 7.59612349389599e-08, "epoch": 2.8310249307479225, "percentage": 95.56, "elapsed_time": "6:12:12", "remaining_time": "0:17:18"}
+{"current_steps": 173, "total_steps": 180, "loss": 0.2219, "lr": 6.005075261595495e-08, "epoch": 2.847645429362881, "percentage": 96.11, "elapsed_time": "6:14:30", "remaining_time": "0:15:09"}
+{"current_steps": 174, "total_steps": 180, "loss": 0.2981, "lr": 4.599798317577342e-08, "epoch": 2.864265927977839, "percentage": 96.67, "elapsed_time": "6:16:30", "remaining_time": "0:12:58"}
+{"current_steps": 175, "total_steps": 180, "loss": 0.2574, "lr": 3.3808211290284886e-08, "epoch": 2.880886426592798, "percentage": 97.22, "elapsed_time": "6:18:40", "remaining_time": "0:10:49"}
+{"current_steps": 176, "total_steps": 180, "loss": 0.2584, "lr": 2.3486021034170857e-08, "epoch": 2.897506925207756, "percentage": 97.78, "elapsed_time": "6:20:53", "remaining_time": "0:08:39"}
+{"current_steps": 177, "total_steps": 180, "loss": 0.2785, "lr": 1.5035294161039882e-08, "epoch": 2.914127423822715, "percentage": 98.33, "elapsed_time": "6:22:50", "remaining_time": "0:06:29"}
+{"current_steps": 178, "total_steps": 180, "loss": 0.2572, "lr": 8.459208643659122e-09, "epoch": 2.930747922437673, "percentage": 98.89, "elapsed_time": "6:24:46", "remaining_time": "0:04:19"}
+{"current_steps": 179, "total_steps": 180, "loss": 0.2964, "lr": 3.760237478849793e-09, "epoch": 2.9473684210526314, "percentage": 99.44, "elapsed_time": "6:26:45", "remaining_time": "0:02:09"}
+{"current_steps": 180, "total_steps": 180, "loss": 0.2896, "lr": 9.401477574932927e-10, "epoch": 2.96398891966759, "percentage": 100.0, "elapsed_time": "6:28:40", "remaining_time": "0:00:00"}
+{"current_steps": 180, "total_steps": 180, "epoch": 2.96398891966759, "percentage": 100.0, "elapsed_time": "6:42:22", "remaining_time": "0:00:00"}