File size: 5,527 Bytes
570fea4 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
/home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/trl/trainer/ppo_config.py:141: UserWarning: The `optimize_cuda_cache` arguement will be deprecated soon, please use `optimize_device_cache` instead.
warnings.warn(
[INFO|tokenization_utils_base.py:2024] 2023-12-22 17:17:06,207 >> loading file vocab.json
[INFO|tokenization_utils_base.py:2024] 2023-12-22 17:17:06,207 >> loading file merges.txt
[INFO|tokenization_utils_base.py:2024] 2023-12-22 17:17:06,207 >> loading file added_tokens.json
[INFO|tokenization_utils_base.py:2024] 2023-12-22 17:17:06,207 >> loading file special_tokens_map.json
[INFO|tokenization_utils_base.py:2024] 2023-12-22 17:17:06,207 >> loading file tokenizer_config.json
[INFO|tokenization_utils_base.py:2024] 2023-12-22 17:17:06,207 >> loading file tokenizer.json
[WARNING|logging.py:314] 2023-12-22 17:17:06,301 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
[INFO|configuration_utils.py:737] 2023-12-22 17:17:06,302 >> loading configuration file ./models/phi-2-sft-alpaca_gpt4_en-ep1/config.json
[INFO|configuration_utils.py:737] 2023-12-22 17:17:06,314 >> loading configuration file ./models/phi-2-sft-alpaca_gpt4_en-ep1/config.json
[INFO|configuration_utils.py:802] 2023-12-22 17:17:06,315 >> Model config PhiConfig {
"_name_or_path": "./models/phi-2-sft-alpaca_gpt4_en-ep1",
"activation_function": "gelu_new",
"architectures": [
"PhiForCausalLM"
],
"attn_pdrop": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi.PhiConfig",
"AutoModel": "modeling_phi.PhiForCausalLM",
"AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
},
"embd_pdrop": 0.0,
"flash_attn": false,
"flash_rotary": false,
"fused_dense": false,
"img_processor": null,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "phi-msft",
"n_embd": 2560,
"n_head": 32,
"n_head_kv": null,
"n_inner": null,
"n_layer": 32,
"n_positions": 2048,
"resid_pdrop": 0.1,
"rotary_dim": 32,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.36.2",
"use_cache": true,
"vocab_size": 51200
}
[INFO|modeling_utils.py:3341] 2023-12-22 17:17:06,553 >> loading weights file ./models/phi-2-sft-alpaca_gpt4_en-ep1/model.safetensors.index.json
[INFO|modeling_utils.py:1341] 2023-12-22 17:17:06,560 >> Instantiating PhiForCausalLM model under default dtype torch.float16.
[INFO|configuration_utils.py:826] 2023-12-22 17:17:06,561 >> Generate config GenerationConfig {}
[INFO|configuration_utils.py:826] 2023-12-22 17:17:06,562 >> Generate config GenerationConfig {}
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 5.06it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 5.58it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 5.49it/s]
[INFO|modeling_utils.py:4185] 2023-12-22 17:17:07,056 >> All model checkpoint weights were used when initializing PhiForCausalLM.
[INFO|modeling_utils.py:4193] 2023-12-22 17:17:07,056 >> All the weights of PhiForCausalLM were initialized from the model checkpoint at ./models/phi-2-sft-alpaca_gpt4_en-ep1.
If your task is similar to the task the model of the checkpoint was trained on, you can already use PhiForCausalLM for predictions without further training.
[INFO|configuration_utils.py:779] 2023-12-22 17:17:07,059 >> loading configuration file ./models/phi-2-sft-alpaca_gpt4_en-ep1/generation_config.json
[INFO|configuration_utils.py:826] 2023-12-22 17:17:07,059 >> Generate config GenerationConfig {}
12/22/2023 17:17:07 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA
12/22/2023 17:17:08 - INFO - llmtuner.model.adapter - Merged 1 adapter(s).
12/22/2023 17:17:08 - INFO - llmtuner.model.adapter - Loaded adapter(s): ./models/dpo/phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1-lora
12/22/2023 17:17:08 - INFO - llmtuner.model.loader - trainable params: 0 || all params: 2779683840 || trainable%: 0.0000
12/22/2023 17:17:08 - INFO - llmtuner.model.loader - This IS expected that the trainable params is 0 if you are using model for inference only.
[INFO|configuration_utils.py:483] 2023-12-22 17:17:08,317 >> Configuration saved in ./models/export/phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1/config.json
[INFO|configuration_utils.py:594] 2023-12-22 17:17:08,317 >> Configuration saved in ./models/export/phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1/generation_config.json
[INFO|modeling_utils.py:2390] 2023-12-22 17:17:15,004 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 2 checkpoint shards. You can find where each parameters has been saved in the index located at ./models/export/phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1/model.safetensors.index.json.
[INFO|tokenization_utils_base.py:2432] 2023-12-22 17:17:15,005 >> tokenizer config file saved in ./models/export/phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1/tokenizer_config.json
[INFO|tokenization_utils_base.py:2441] 2023-12-22 17:17:15,006 >> Special tokens file saved in ./models/export/phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1/special_tokens_map.json
[INFO|tokenization_utils_base.py:2492] 2023-12-22 17:17:15,006 >> added tokens file saved in ./models/export/phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1/added_tokens.json
|