Instructions to use alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-Z1-9B-0414")
model = PeftModel.from_pretrained(base_model, "alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles")

Transformers

How to use alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles with Transformers:

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

pipe = pipeline("text-generation", model="alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles

SGLang

How to use alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles 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 "alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles" \
    --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": "alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles",
		"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 "alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles" \
        --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": "alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles with Docker Model Runner:
```
docker model run hf.co/alexiaassis/Modelo-Treinado-GLM-Z1-9B-0414-Ingles
```

Modelo-Treinado-GLM-Z1-9B-0414-Ingles / running_log.txt

alexiaassis

Upload folder using huggingface_hub

326f143 verified 7 months ago

Raw

History Blame Contribute Delete

19 kB

	[INFO\|2026-02-08 23:10:53] configuration_utils.py:667 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--zai-org--GLM-Z1-9B-0414/snapshots/b221b06fefb23ca320922cf6e68ab5f2fb82de81/config.json
	[INFO\|2026-02-08 23:10:53] configuration_utils.py:739 >> Model config Glm4Config {
	"architectures": [
	"Glm4ForCausalLM"
	],
	"attention_bias": true,
	"attention_dropout": 0.0,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 13696,
	"max_position_embeddings": 32768,
	"model_type": "glm4",
	"num_attention_heads": 32,
	"num_hidden_layers": 40,
	"num_key_value_heads": 2,
	"pad_token_id": 151329,
	"partial_rotary_factor": 0.5,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"partial_rotary_factor": 0.5,
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.0.0",
	"use_cache": true,
	"vocab_size": 151552
	}

	[INFO\|2026-02-08 23:11:01] configuration_utils.py:667 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--zai-org--GLM-Z1-9B-0414/snapshots/b221b06fefb23ca320922cf6e68ab5f2fb82de81/config.json
	[INFO\|2026-02-08 23:11:01] configuration_utils.py:739 >> Model config Glm4Config {
	"architectures": [
	"Glm4ForCausalLM"
	],
	"attention_bias": true,
	"attention_dropout": 0.0,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 13696,
	"max_position_embeddings": 32768,
	"model_type": "glm4",
	"num_attention_heads": 32,
	"num_hidden_layers": 40,
	"num_key_value_heads": 2,
	"pad_token_id": 151329,
	"partial_rotary_factor": 0.5,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"partial_rotary_factor": 0.5,
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.0.0",
	"use_cache": true,
	"vocab_size": 151552
	}

	[INFO\|2026-02-08 23:11:01] configuration_utils.py:667 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--zai-org--GLM-Z1-9B-0414/snapshots/b221b06fefb23ca320922cf6e68ab5f2fb82de81/config.json
	[INFO\|2026-02-08 23:11:01] configuration_utils.py:739 >> Model config Glm4Config {
	"architectures": [
	"Glm4ForCausalLM"
	],
	"attention_bias": true,
	"attention_dropout": 0.0,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 13696,
	"max_position_embeddings": 32768,
	"model_type": "glm4",
	"num_attention_heads": 32,
	"num_hidden_layers": 40,
	"num_key_value_heads": 2,
	"pad_token_id": 151329,
	"partial_rotary_factor": 0.5,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"partial_rotary_factor": 0.5,
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.0.0",
	"use_cache": true,
	"vocab_size": 151552
	}

	[INFO\|2026-02-08 23:11:04] logging.py:144 >> Loading dataset train_split2.json...
	[INFO\|2026-02-08 23:11:12] configuration_utils.py:667 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--zai-org--GLM-Z1-9B-0414/snapshots/b221b06fefb23ca320922cf6e68ab5f2fb82de81/config.json
	[INFO\|2026-02-08 23:11:12] configuration_utils.py:739 >> Model config Glm4Config {
	"architectures": [
	"Glm4ForCausalLM"
	],
	"attention_bias": true,
	"attention_dropout": 0.0,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 13696,
	"max_position_embeddings": 32768,
	"model_type": "glm4",
	"num_attention_heads": 32,
	"num_hidden_layers": 40,
	"num_key_value_heads": 2,
	"pad_token_id": 151329,
	"partial_rotary_factor": 0.5,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"partial_rotary_factor": 0.5,
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.0.0",
	"use_cache": true,
	"vocab_size": 151552
	}

	[INFO\|2026-02-08 23:11:12] logging.py:144 >> Quantizing model to 4 bit with bitsandbytes.
	[INFO\|2026-02-08 23:11:12] logging.py:144 >> KV cache is disabled during training.
	[INFO\|2026-02-08 23:11:20] configuration_utils.py:667 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--zai-org--GLM-Z1-9B-0414/snapshots/b221b06fefb23ca320922cf6e68ab5f2fb82de81/config.json
	[INFO\|2026-02-08 23:11:20] configuration_utils.py:739 >> Model config Glm4Config {
	"architectures": [
	"Glm4ForCausalLM"
	],
	"attention_bias": true,
	"attention_dropout": 0.0,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 13696,
	"max_position_embeddings": 32768,
	"model_type": "glm4",
	"num_attention_heads": 32,
	"num_hidden_layers": 40,
	"num_key_value_heads": 2,
	"pad_token_id": 151329,
	"partial_rotary_factor": 0.5,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"partial_rotary_factor": 0.5,
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.0.0",
	"use_cache": true,
	"vocab_size": 151552
	}

	[INFO\|2026-02-08 23:11:22] configuration_utils.py:667 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--zai-org--GLM-Z1-9B-0414/snapshots/b221b06fefb23ca320922cf6e68ab5f2fb82de81/config.json
	[INFO\|2026-02-08 23:11:22] configuration_utils.py:739 >> Model config Glm4Config {
	"architectures": [
	"Glm4ForCausalLM"
	],
	"attention_bias": true,
	"attention_dropout": 0.0,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 13696,
	"max_position_embeddings": 32768,
	"model_type": "glm4",
	"num_attention_heads": 32,
	"num_hidden_layers": 40,
	"num_key_value_heads": 2,
	"pad_token_id": 151329,
	"partial_rotary_factor": 0.5,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"partial_rotary_factor": 0.5,
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.0.0",
	"use_cache": true,
	"vocab_size": 151552
	}

	[INFO\|2026-02-08 23:11:31] configuration_utils.py:667 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--zai-org--GLM-Z1-9B-0414/snapshots/b221b06fefb23ca320922cf6e68ab5f2fb82de81/config.json
	[INFO\|2026-02-08 23:11:31] configuration_utils.py:739 >> Model config Glm4Config {
	"architectures": [
	"Glm4ForCausalLM"
	],
	"attention_bias": true,
	"attention_dropout": 0.0,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 13696,
	"max_position_embeddings": 32768,
	"model_type": "glm4",
	"num_attention_heads": 32,
	"num_hidden_layers": 40,
	"num_key_value_heads": 2,
	"pad_token_id": 151329,
	"partial_rotary_factor": 0.5,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"partial_rotary_factor": 0.5,
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.0.0",
	"use_cache": true,
	"vocab_size": 151552
	}

	[INFO\|2026-02-08 23:11:31] modeling_utils.py:732 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--zai-org--GLM-Z1-9B-0414/snapshots/b221b06fefb23ca320922cf6e68ab5f2fb82de81/model.safetensors.index.json
	[INFO\|2026-02-08 23:12:17] configuration_utils.py:1014 >> Generate config GenerationConfig {
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"output_attentions": false,
	"output_hidden_states": false,
	"pad_token_id": 151329,
	"use_cache": true
	}

	[INFO\|2026-02-08 23:12:24] configuration_utils.py:967 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--zai-org--GLM-Z1-9B-0414/snapshots/b221b06fefb23ca320922cf6e68ab5f2fb82de81/generation_config.json
	[INFO\|2026-02-08 23:12:24] configuration_utils.py:1014 >> Generate config GenerationConfig {
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"pad_token_id": 151329
	}

	[INFO\|2026-02-08 23:12:24] dynamic_module_utils.py:406 >> Could not locate the custom_generate/generate.py inside zai-org/GLM-Z1-9B-0414.
	[INFO\|2026-02-08 23:12:25] configuration_utils.py:667 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--zai-org--GLM-Z1-9B-0414/snapshots/b221b06fefb23ca320922cf6e68ab5f2fb82de81/config.json
	[INFO\|2026-02-08 23:12:25] configuration_utils.py:739 >> Model config Glm4Config {
	"architectures": [
	"Glm4ForCausalLM"
	],
	"attention_bias": true,
	"attention_dropout": 0.0,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 13696,
	"max_position_embeddings": 32768,
	"model_type": "glm4",
	"num_attention_heads": 32,
	"num_hidden_layers": 40,
	"num_key_value_heads": 2,
	"pad_token_id": 151329,
	"partial_rotary_factor": 0.5,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"partial_rotary_factor": 0.5,
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.0.0",
	"use_cache": true,
	"vocab_size": 151552
	}

	[INFO\|2026-02-08 23:12:31] logging.py:144 >> Gradient checkpointing enabled.
	[INFO\|2026-02-08 23:12:31] logging.py:144 >> Upcasting trainable params to float32.
	[INFO\|2026-02-08 23:12:31] logging.py:144 >> Fine-tuning method: LoRA
	[INFO\|2026-02-08 23:12:31] logging.py:144 >> Found linear modules: v_proj,down_proj,k_proj,gate_up_proj,q_proj,o_proj
	[INFO\|2026-02-08 23:12:35] logging.py:144 >> trainable params: 95,191,040 \|\| all params: 9,495,470,080 \|\| trainable%: 1.0025
	[INFO\|2026-02-08 23:12:36] trainer.py:1260 >> skipped Embedding(151552, 4096, padding_idx=151329): 592.0M params
	[INFO\|2026-02-08 23:12:36] trainer.py:1263 >> skipped: 592.0M params
	[INFO\|2026-02-08 23:12:36] trainer.py:2383 >> *** Running training ***
	[INFO\|2026-02-08 23:12:36] trainer.py:2384 >> Num examples = 3,716
	[INFO\|2026-02-08 23:12:36] trainer.py:2385 >> Num Epochs = 3
	[INFO\|2026-02-08 23:12:36] trainer.py:2386 >> Instantaneous batch size per device = 4
	[INFO\|2026-02-08 23:12:36] trainer.py:2389 >> Total train batch size (w. parallel, distributed & accumulation) = 32
	[INFO\|2026-02-08 23:12:36] trainer.py:2390 >> Gradient Accumulation steps = 8
	[INFO\|2026-02-08 23:12:36] trainer.py:2391 >> Total optimization steps = 351
	[INFO\|2026-02-08 23:12:36] trainer.py:2392 >> Number of trainable parameters = 95,191,040
	[INFO\|2026-02-08 23:14:12] logging.py:144 >> {'loss': 9.8036, 'learning_rate': 9.0000e-07, 'epoch': 0.09, 'throughput': 933.70}
	[INFO\|2026-02-08 23:15:17] logging.py:144 >> {'loss': 7.2789, 'learning_rate': 1.9000e-06, 'epoch': 0.17, 'throughput': 1117.95}
	[INFO\|2026-02-08 23:16:21] logging.py:144 >> {'loss': 4.2772, 'learning_rate': 2.9000e-06, 'epoch': 0.26, 'throughput': 1201.30}
	[INFO\|2026-02-08 23:17:25] logging.py:144 >> {'loss': 1.2959, 'learning_rate': 3.9000e-06, 'epoch': 0.34, 'throughput': 1250.75}
	[INFO\|2026-02-08 23:18:30] logging.py:144 >> {'loss': 0.3324, 'learning_rate': 4.9000e-06, 'epoch': 0.43, 'throughput': 1278.65}
	[INFO\|2026-02-08 23:19:34] logging.py:144 >> {'loss': 0.2573, 'learning_rate': 5.9000e-06, 'epoch': 0.52, 'throughput': 1297.77}
	[INFO\|2026-02-08 23:20:38] logging.py:144 >> {'loss': 0.2211, 'learning_rate': 6.9000e-06, 'epoch': 0.60, 'throughput': 1314.50}
	[INFO\|2026-02-08 23:21:41] logging.py:144 >> {'loss': 0.2148, 'learning_rate': 7.9000e-06, 'epoch': 0.69, 'throughput': 1327.02}
	[INFO\|2026-02-08 23:22:45] logging.py:144 >> {'loss': 0.1861, 'learning_rate': 8.9000e-06, 'epoch': 0.78, 'throughput': 1338.10}
	[INFO\|2026-02-08 23:23:49] logging.py:144 >> {'loss': 0.1617, 'learning_rate': 9.9000e-06, 'epoch': 0.86, 'throughput': 1344.54}
	[INFO\|2026-02-08 23:24:54] logging.py:144 >> {'loss': 0.1681, 'learning_rate': 1.0900e-05, 'epoch': 0.95, 'throughput': 1348.73}
	[INFO\|2026-02-08 23:25:53] logging.py:144 >> {'loss': 0.1580, 'learning_rate': 1.1900e-05, 'epoch': 1.03, 'throughput': 1352.22}
	[INFO\|2026-02-08 23:26:57] logging.py:144 >> {'loss': 0.1583, 'learning_rate': 1.2900e-05, 'epoch': 1.11, 'throughput': 1357.20}
	[INFO\|2026-02-08 23:28:01] logging.py:144 >> {'loss': 0.1407, 'learning_rate': 1.3900e-05, 'epoch': 1.20, 'throughput': 1360.95}
	[INFO\|2026-02-08 23:29:05] logging.py:144 >> {'loss': 0.1532, 'learning_rate': 1.4900e-05, 'epoch': 1.28, 'throughput': 1363.36}
	[INFO\|2026-02-08 23:30:09] logging.py:144 >> {'loss': 0.1475, 'learning_rate': 1.5900e-05, 'epoch': 1.37, 'throughput': 1365.75}
	[INFO\|2026-02-08 23:31:14] logging.py:144 >> {'loss': 0.1475, 'learning_rate': 1.6900e-05, 'epoch': 1.46, 'throughput': 1368.17}
	[INFO\|2026-02-08 23:32:18] logging.py:144 >> {'loss': 0.1384, 'learning_rate': 1.7900e-05, 'epoch': 1.54, 'throughput': 1370.15}
	[INFO\|2026-02-08 23:33:22] logging.py:144 >> {'loss': 0.1406, 'learning_rate': 1.8900e-05, 'epoch': 1.63, 'throughput': 1371.30}
	[INFO\|2026-02-08 23:34:26] logging.py:144 >> {'loss': 0.1450, 'learning_rate': 1.9900e-05, 'epoch': 1.71, 'throughput': 1373.15}
	[INFO\|2026-02-08 23:35:30] logging.py:144 >> {'loss': 0.1431, 'learning_rate': 2.0900e-05, 'epoch': 1.80, 'throughput': 1375.58}
	[INFO\|2026-02-08 23:36:34] logging.py:144 >> {'loss': 0.1484, 'learning_rate': 2.1900e-05, 'epoch': 1.89, 'throughput': 1377.21}
	[INFO\|2026-02-08 23:37:38] logging.py:144 >> {'loss': 0.1294, 'learning_rate': 2.2900e-05, 'epoch': 1.97, 'throughput': 1378.08}
	[INFO\|2026-02-08 23:38:38] logging.py:144 >> {'loss': 0.1000, 'learning_rate': 2.3900e-05, 'epoch': 2.05, 'throughput': 1378.78}
	[INFO\|2026-02-08 23:39:42] logging.py:144 >> {'loss': 0.0867, 'learning_rate': 2.4900e-05, 'epoch': 2.14, 'throughput': 1379.78}
	[INFO\|2026-02-08 23:40:46] logging.py:144 >> {'loss': 0.0835, 'learning_rate': 2.5900e-05, 'epoch': 2.22, 'throughput': 1381.74}
	[INFO\|2026-02-08 23:41:50] logging.py:144 >> {'loss': 0.0989, 'learning_rate': 2.6900e-05, 'epoch': 2.31, 'throughput': 1382.71}
	[INFO\|2026-02-08 23:42:54] logging.py:144 >> {'loss': 0.1173, 'learning_rate': 2.7900e-05, 'epoch': 2.40, 'throughput': 1383.72}
	[INFO\|2026-02-08 23:43:59] logging.py:144 >> {'loss': 0.1075, 'learning_rate': 2.8900e-05, 'epoch': 2.48, 'throughput': 1384.55}
	[INFO\|2026-02-08 23:45:03] logging.py:144 >> {'loss': 0.0904, 'learning_rate': 2.9900e-05, 'epoch': 2.57, 'throughput': 1385.48}
	[INFO\|2026-02-08 23:46:07] logging.py:144 >> {'loss': 0.1165, 'learning_rate': 3.0900e-05, 'epoch': 2.65, 'throughput': 1386.15}
	[INFO\|2026-02-08 23:47:11] logging.py:144 >> {'loss': 0.0846, 'learning_rate': 3.1900e-05, 'epoch': 2.74, 'throughput': 1386.83}
	[INFO\|2026-02-08 23:48:16] logging.py:144 >> {'loss': 0.0945, 'learning_rate': 3.2900e-05, 'epoch': 2.83, 'throughput': 1387.38}
	[INFO\|2026-02-08 23:49:19] logging.py:144 >> {'loss': 0.1040, 'learning_rate': 3.3900e-05, 'epoch': 2.91, 'throughput': 1387.74}
	[INFO\|2026-02-08 23:50:24] logging.py:144 >> {'loss': 0.0984, 'learning_rate': 3.4900e-05, 'epoch': 3.00, 'throughput': 1388.27}
	[INFO\|2026-02-08 23:50:24] trainer.py:4115 >> Saving model checkpoint to saves/GLM-Z1-0414-9B-Chat/lora/glm-treinado/checkpoint-351
	[INFO\|2026-02-08 23:50:25] configuration_utils.py:667 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--zai-org--GLM-Z1-9B-0414/snapshots/b221b06fefb23ca320922cf6e68ab5f2fb82de81/config.json
	[INFO\|2026-02-08 23:50:25] configuration_utils.py:739 >> Model config Glm4Config {
	"architectures": [
	"Glm4ForCausalLM"
	],
	"attention_bias": true,
	"attention_dropout": 0.0,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 13696,
	"max_position_embeddings": 32768,
	"model_type": "glm4",
	"num_attention_heads": 32,
	"num_hidden_layers": 40,
	"num_key_value_heads": 2,
	"pad_token_id": 151329,
	"partial_rotary_factor": 0.5,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"partial_rotary_factor": 0.5,
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.0.0",
	"use_cache": true,
	"vocab_size": 151552
	}

	[INFO\|2026-02-08 23:50:26] trainer.py:2657 >>

	Training completed. Do not forget to share your model on huggingface.co/models =)


	[INFO\|2026-02-08 23:50:26] trainer.py:4115 >> Saving model checkpoint to saves/GLM-Z1-0414-9B-Chat/lora/glm-treinado
	[INFO\|2026-02-08 23:50:27] configuration_utils.py:667 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--zai-org--GLM-Z1-9B-0414/snapshots/b221b06fefb23ca320922cf6e68ab5f2fb82de81/config.json
	[INFO\|2026-02-08 23:50:27] configuration_utils.py:739 >> Model config Glm4Config {
	"architectures": [
	"Glm4ForCausalLM"
	],
	"attention_bias": true,
	"attention_dropout": 0.0,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 13696,
	"max_position_embeddings": 32768,
	"model_type": "glm4",
	"num_attention_heads": 32,
	"num_hidden_layers": 40,
	"num_key_value_heads": 2,
	"pad_token_id": 151329,
	"partial_rotary_factor": 0.5,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"partial_rotary_factor": 0.5,
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.0.0",
	"use_cache": true,
	"vocab_size": 151552
	}

	[WARNING\|2026-02-08 23:50:28] logging.py:149 >> No metric eval_loss to plot.
	[WARNING\|2026-02-08 23:50:28] logging.py:149 >> No metric eval_accuracy to plot.
	[INFO\|2026-02-08 23:50:28] modelcard.py:266 >> Dropping the following result as it does not have all the necessary fields:
	{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}