| [INFO|2025-02-04 16:53:04] configuration_utils.py:696 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json | |
| [INFO|2025-02-04 16:53:04] configuration_utils.py:768 >> Model config LlamaConfig { | |
| "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.2", | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } | |
| [INFO|2025-02-04 16:53:04] tokenization_utils_base.py:2034 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/tokenizer.json | |
| [INFO|2025-02-04 16:53:04] tokenization_utils_base.py:2034 >> loading file tokenizer.model from cache at None | |
| [INFO|2025-02-04 16:53:04] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at None | |
| [INFO|2025-02-04 16:53:04] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/special_tokens_map.json | |
| [INFO|2025-02-04 16:53:04] tokenization_utils_base.py:2034 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/tokenizer_config.json | |
| [INFO|2025-02-04 16:53:04] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None | |
| [INFO|2025-02-04 16:53:04] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| [INFO|2025-02-04 16:53:05] configuration_utils.py:696 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json | |
| [INFO|2025-02-04 16:53:05] configuration_utils.py:768 >> Model config LlamaConfig { | |
| "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.2", | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } | |
| [INFO|2025-02-04 16:53:06] tokenization_utils_base.py:2034 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/tokenizer.json | |
| [INFO|2025-02-04 16:53:06] tokenization_utils_base.py:2034 >> loading file tokenizer.model from cache at None | |
| [INFO|2025-02-04 16:53:06] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at None | |
| [INFO|2025-02-04 16:53:06] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/special_tokens_map.json | |
| [INFO|2025-02-04 16:53:06] tokenization_utils_base.py:2034 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/tokenizer_config.json | |
| [INFO|2025-02-04 16:53:06] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None | |
| [INFO|2025-02-04 16:53:06] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| [INFO|2025-02-04 16:53:06] logging.py:157 >> Add pad token: <|eot_id|> | |
| [INFO|2025-02-04 16:53:06] logging.py:157 >> Add <|eot_id|>,<|eom_id|> to stop words. | |
| [INFO|2025-02-04 16:53:06] logging.py:157 >> Loading dataset identity.json... | |
| [INFO|2025-02-04 16:53:07] configuration_utils.py:696 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json | |
| [INFO|2025-02-04 16:53:07] configuration_utils.py:768 >> Model config LlamaConfig { | |
| "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.2", | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } | |
| [WARNING|2025-02-04 16:53:07] logging.py:162 >> FlashAttention-2 is not installed. | |
| [WARNING|2025-02-04 16:53:07] logging.py:162 >> Input length is smaller than max length. Consider increase input length. | |
| [INFO|2025-02-04 16:53:07] logging.py:157 >> Using linear scaling strategy and setting scaling factor to 1.0. | |
| [INFO|2025-02-04 16:53:07] modeling_utils.py:3904 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/model.safetensors | |
| [INFO|2025-02-04 16:53:07] modeling_utils.py:1582 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16. | |
| [INFO|2025-02-04 16:53:07] configuration_utils.py:1140 >> Generate config GenerationConfig { | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ] | |
| } | |
| [INFO|2025-02-04 16:53:08] modeling_utils.py:4888 >> All model checkpoint weights were used when initializing LlamaForCausalLM. | |
| [INFO|2025-02-04 16:53:08] modeling_utils.py:4896 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at meta-llama/Llama-3.2-1B-Instruct. | |
| If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training. | |
| [INFO|2025-02-04 16:53:08] configuration_utils.py:1095 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/generation_config.json | |
| [INFO|2025-02-04 16:53:08] configuration_utils.py:1140 >> Generate config GenerationConfig { | |
| "bos_token_id": 128000, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "temperature": 0.6, | |
| "top_p": 0.9 | |
| } | |
| [INFO|2025-02-04 16:53:08] logging.py:157 >> Gradient checkpointing enabled. | |
| [INFO|2025-02-04 16:53:08] logging.py:157 >> Using torch SDPA for faster training and inference. | |
| [INFO|2025-02-04 16:53:08] logging.py:157 >> Upcasting trainable params to float32. | |
| [INFO|2025-02-04 16:53:08] logging.py:157 >> Fine-tuning method: LoRA | |
| [INFO|2025-02-04 16:53:08] logging.py:157 >> Found linear modules: v_proj,down_proj,gate_proj,up_proj,k_proj,o_proj,q_proj | |
| [INFO|2025-02-04 16:53:09] logging.py:157 >> trainable params: 5,636,096 || all params: 1,241,450,496 || trainable%: 0.4540 | |
| [INFO|2025-02-04 16:53:09] trainer.py:741 >> Using auto half precision backend | |
| [INFO|2025-02-04 16:53:09] trainer.py:2369 >> ***** Running training ***** | |
| [INFO|2025-02-04 16:53:09] trainer.py:2370 >> Num examples = 1,000 | |
| [INFO|2025-02-04 16:53:09] trainer.py:2371 >> Num Epochs = 3 | |
| [INFO|2025-02-04 16:53:09] trainer.py:2372 >> Instantaneous batch size per device = 3 | |
| [INFO|2025-02-04 16:53:09] trainer.py:2375 >> Total train batch size (w. parallel, distributed & accumulation) = 24 | |
| [INFO|2025-02-04 16:53:09] trainer.py:2376 >> Gradient Accumulation steps = 8 | |
| [INFO|2025-02-04 16:53:09] trainer.py:2377 >> Total optimization steps = 123 | |
| [INFO|2025-02-04 16:53:09] trainer.py:2378 >> Number of trainable parameters = 5,636,096 | |
| [INFO|2025-02-04 16:53:13] logging.py:157 >> {'loss': 2.7298, 'learning_rate': 4.9796e-05, 'epoch': 0.12, 'throughput': 1726.74} | |
| [INFO|2025-02-04 16:53:17] logging.py:157 >> {'loss': 1.9630, 'learning_rate': 4.9189e-05, 'epoch': 0.24, 'throughput': 1895.22} | |
| [INFO|2025-02-04 16:53:20] logging.py:157 >> {'loss': 1.3739, 'learning_rate': 4.8188e-05, 'epoch': 0.36, 'throughput': 1973.05} | |
| [INFO|2025-02-04 16:53:23] logging.py:157 >> {'loss': 0.9519, 'learning_rate': 4.6808e-05, 'epoch': 0.48, 'throughput': 2002.04} | |
| [INFO|2025-02-04 16:53:27] logging.py:157 >> {'loss': 0.7551, 'learning_rate': 4.5074e-05, 'epoch': 0.60, 'throughput': 2016.19} | |
| [INFO|2025-02-04 16:53:30] logging.py:157 >> {'loss': 0.6738, 'learning_rate': 4.3013e-05, 'epoch': 0.72, 'throughput': 2020.18} | |
| [INFO|2025-02-04 16:53:33] logging.py:157 >> {'loss': 0.6185, 'learning_rate': 4.0658e-05, 'epoch': 0.84, 'throughput': 2032.39} | |
| [INFO|2025-02-04 16:53:36] logging.py:157 >> {'loss': 0.5870, 'learning_rate': 3.8049e-05, 'epoch': 0.96, 'throughput': 2052.06} | |
| [INFO|2025-02-04 16:53:39] logging.py:157 >> {'loss': 0.4555, 'learning_rate': 3.5227e-05, 'epoch': 1.07, 'throughput': 2055.69} | |
| [INFO|2025-02-04 16:53:43] logging.py:157 >> {'loss': 0.5047, 'learning_rate': 3.2238e-05, 'epoch': 1.19, 'throughput': 2052.18} | |
| [INFO|2025-02-04 16:53:46] logging.py:157 >> {'loss': 0.4530, 'learning_rate': 2.9131e-05, 'epoch': 1.31, 'throughput': 2058.26} | |
| [INFO|2025-02-04 16:53:49] logging.py:157 >> {'loss': 0.5011, 'learning_rate': 2.5958e-05, 'epoch': 1.43, 'throughput': 2057.88} | |
| [INFO|2025-02-04 16:53:52] logging.py:157 >> {'loss': 0.4825, 'learning_rate': 2.2768e-05, 'epoch': 1.55, 'throughput': 2069.16} | |
| [INFO|2025-02-04 16:53:56] logging.py:157 >> {'loss': 0.5319, 'learning_rate': 1.9615e-05, 'epoch': 1.67, 'throughput': 2079.40} | |
| [INFO|2025-02-04 16:53:59] logging.py:157 >> {'loss': 0.4653, 'learning_rate': 1.6550e-05, 'epoch': 1.79, 'throughput': 2076.20} | |
| [INFO|2025-02-04 16:54:02] logging.py:157 >> {'loss': 0.4396, 'learning_rate': 1.3622e-05, 'epoch': 1.91, 'throughput': 2083.24} | |
| [INFO|2025-02-04 16:54:05] logging.py:157 >> {'loss': 0.3965, 'learning_rate': 1.0879e-05, 'epoch': 2.02, 'throughput': 2079.59} | |
| [INFO|2025-02-04 16:54:09] logging.py:157 >> {'loss': 0.4697, 'learning_rate': 8.3669e-06, 'epoch': 2.14, 'throughput': 2086.94} | |
| [INFO|2025-02-04 16:54:12] logging.py:157 >> {'loss': 0.4242, 'learning_rate': 6.1253e-06, 'epoch': 2.26, 'throughput': 2083.87} | |
| [INFO|2025-02-04 16:54:15] logging.py:157 >> {'loss': 0.3814, 'learning_rate': 4.1911e-06, 'epoch': 2.38, 'throughput': 2081.62} | |
| [INFO|2025-02-04 16:54:15] trainer.py:3910 >> Saving model checkpoint to saves/Llama-3.2-1B-Instruct/lora/identity2/checkpoint-100 | |
| [INFO|2025-02-04 16:54:16] configuration_utils.py:696 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json | |
| [INFO|2025-02-04 16:54:16] configuration_utils.py:768 >> Model config LlamaConfig { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.2", | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } | |
| [INFO|2025-02-04 16:54:16] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves/Llama-3.2-1B-Instruct/lora/identity2/checkpoint-100/tokenizer_config.json | |
| [INFO|2025-02-04 16:54:16] tokenization_utils_base.py:2500 >> Special tokens file saved in saves/Llama-3.2-1B-Instruct/lora/identity2/checkpoint-100/special_tokens_map.json | |
| [INFO|2025-02-04 16:54:19] logging.py:157 >> {'loss': 0.3991, 'learning_rate': 2.5959e-06, 'epoch': 2.50, 'throughput': 2059.99} | |
| [INFO|2025-02-04 16:54:22] logging.py:157 >> {'loss': 0.4522, 'learning_rate': 1.3655e-06, 'epoch': 2.62, 'throughput': 2061.82} | |
| [INFO|2025-02-04 16:54:26] logging.py:157 >> {'loss': 0.3812, 'learning_rate': 5.2008e-07, 'epoch': 2.74, 'throughput': 2061.99} | |
| [INFO|2025-02-04 16:54:29] logging.py:157 >> {'loss': 0.4344, 'learning_rate': 7.3355e-08, 'epoch': 2.86, 'throughput': 2066.37} | |
| [INFO|2025-02-04 16:54:31] trainer.py:3910 >> Saving model checkpoint to saves/Llama-3.2-1B-Instruct/lora/identity2/checkpoint-123 | |
| [INFO|2025-02-04 16:54:32] configuration_utils.py:696 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json | |
| [INFO|2025-02-04 16:54:32] configuration_utils.py:768 >> Model config LlamaConfig { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.2", | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } | |
| [INFO|2025-02-04 16:54:32] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves/Llama-3.2-1B-Instruct/lora/identity2/checkpoint-123/tokenizer_config.json | |
| [INFO|2025-02-04 16:54:32] tokenization_utils_base.py:2500 >> Special tokens file saved in saves/Llama-3.2-1B-Instruct/lora/identity2/checkpoint-123/special_tokens_map.json | |
| [INFO|2025-02-04 16:54:32] trainer.py:2643 >> | |
| Training completed. Do not forget to share your model on huggingface.co/models =) | |
| [INFO|2025-02-04 16:54:32] trainer.py:3910 >> Saving model checkpoint to saves/Llama-3.2-1B-Instruct/lora/identity2 | |
| [INFO|2025-02-04 16:54:32] configuration_utils.py:696 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B-Instruct/snapshots/9213176726f574b556790deb65791e0c5aa438b6/config.json | |
| [INFO|2025-02-04 16:54:32] configuration_utils.py:768 >> Model config LlamaConfig { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.2", | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } | |
| [INFO|2025-02-04 16:54:32] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves/Llama-3.2-1B-Instruct/lora/identity2/tokenizer_config.json | |
| [INFO|2025-02-04 16:54:32] tokenization_utils_base.py:2500 >> Special tokens file saved in saves/Llama-3.2-1B-Instruct/lora/identity2/special_tokens_map.json | |
| [WARNING|2025-02-04 16:54:33] logging.py:162 >> No metric eval_loss to plot. | |
| [WARNING|2025-02-04 16:54:33] logging.py:162 >> No metric eval_accuracy to plot. | |
| [INFO|2025-02-04 16:54:33] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields: | |
| {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} | |