File size: 5,324 Bytes
af3a60e |
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 |
0.00s - Debugger warning: It seems that frozen modules are being used, which may
0.00s - make the debugger miss breakpoints. Please pass -Xfrozen_modules=off
0.00s - to python to disable frozen modules.
0.00s - Note: Debugging will proceed. Set PYDEVD_DISABLE_FILE_VALIDATION=1 to disable this validation.
[INFO|tokenization_utils_base.py:2024] 2024-01-21 14:22:37,060 >> loading file tokenizer.model
[INFO|tokenization_utils_base.py:2024] 2024-01-21 14:22:37,061 >> loading file added_tokens.json
[INFO|tokenization_utils_base.py:2024] 2024-01-21 14:22:37,061 >> loading file special_tokens_map.json
[INFO|tokenization_utils_base.py:2024] 2024-01-21 14:22:37,061 >> loading file tokenizer_config.json
[INFO|tokenization_utils_base.py:2024] 2024-01-21 14:22:37,061 >> loading file tokenizer.json
[INFO|configuration_utils.py:737] 2024-01-21 14:22:37,440 >> loading configuration file ./models/dolphin-2.6-mistral-7b-dpo-laser/config.json
[INFO|configuration_utils.py:802] 2024-01-21 14:22:37,443 >> Model config MistralConfig {
"_name_or_path": "./models/dolphin-2.6-mistral-7b-dpo-laser",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.36.2",
"use_cache": false,
"vocab_size": 32001
}
[INFO|modeling_utils.py:3341] 2024-01-21 14:22:40,379 >> loading weights file ./models/dolphin-2.6-mistral-7b-dpo-laser/model.safetensors.index.json
[INFO|modeling_utils.py:1341] 2024-01-21 14:22:40,379 >> Instantiating MistralForCausalLM model under default dtype torch.bfloat16.
[INFO|configuration_utils.py:826] 2024-01-21 14:22:40,382 >> Generate config GenerationConfig {
"bos_token_id": 1,
"eos_token_id": 2,
"use_cache": false
}
Waiting for debugger attach
Backend TkAgg is interactive backend. Turning interactive mode on.
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards: 33%|███▎ | 1/3 [00:00<00:00, 5.50it/s]
Loading checkpoint shards: 67%|██████▋ | 2/3 [00:00<00:00, 5.45it/s]
Loading checkpoint shards: 100%|██████████| 3/3 [00:00<00:00, 5.57it/s]
Loading checkpoint shards: 100%|██████████| 3/3 [00:00<00:00, 5.53it/s]
[INFO|modeling_utils.py:4185] 2024-01-21 14:22:41,298 >> All model checkpoint weights were used when initializing MistralForCausalLM.
[INFO|modeling_utils.py:4193] 2024-01-21 14:22:41,298 >> All the weights of MistralForCausalLM were initialized from the model checkpoint at ./models/dolphin-2.6-mistral-7b-dpo-laser.
If your task is similar to the task the model of the checkpoint was trained on, you can already use MistralForCausalLM for predictions without further training.
[INFO|configuration_utils.py:779] 2024-01-21 14:22:41,311 >> loading configuration file ./models/dolphin-2.6-mistral-7b-dpo-laser/generation_config.json
[INFO|configuration_utils.py:826] 2024-01-21 14:22:41,312 >> Generate config GenerationConfig {
"bos_token_id": 1,
"eos_token_id": 2
}
01/21/2024 14:22:41 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA
01/21/2024 14:22:49 - INFO - llmtuner.model.adapter - Merged 1 adapter(s).
01/21/2024 14:22:49 - INFO - llmtuner.model.adapter - Loaded adapter(s): ./models/sft/dolphin-2.6-mistral-7b-dpo-laser-sft-glaive-function-calling-v2-ep1-lora
01/21/2024 14:22:49 - INFO - llmtuner.model.loader - trainable params: 0 || all params: 7241740288 || trainable%: 0.0000
01/21/2024 14:22:49 - 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] 2024-01-21 14:22:49,748 >> Configuration saved in ./models/export/dolphin-2.6-mistral-7b-dpo-laser-sft-glaive-function-calling-v2-ep1/config.json
[INFO|configuration_utils.py:594] 2024-01-21 14:22:49,749 >> Configuration saved in ./models/export/dolphin-2.6-mistral-7b-dpo-laser-sft-glaive-function-calling-v2-ep1/generation_config.json
[INFO|modeling_utils.py:2390] 2024-01-21 14:23:02,915 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 3 checkpoint shards. You can find where each parameters has been saved in the index located at ./models/export/dolphin-2.6-mistral-7b-dpo-laser-sft-glaive-function-calling-v2-ep1/model.safetensors.index.json.
[INFO|tokenization_utils_base.py:2432] 2024-01-21 14:23:03,311 >> tokenizer config file saved in ./models/export/dolphin-2.6-mistral-7b-dpo-laser-sft-glaive-function-calling-v2-ep1/tokenizer_config.json
[INFO|tokenization_utils_base.py:2441] 2024-01-21 14:23:03,312 >> Special tokens file saved in ./models/export/dolphin-2.6-mistral-7b-dpo-laser-sft-glaive-function-calling-v2-ep1/special_tokens_map.json
[INFO|tokenization_utils_base.py:2492] 2024-01-21 14:23:03,312 >> added tokens file saved in ./models/export/dolphin-2.6-mistral-7b-dpo-laser-sft-glaive-function-calling-v2-ep1/added_tokens.json
|