SpecAI / running_log.txt
gtonkov's picture
Upload 22 files
9278d39 verified
[INFO|configuration_utils.py:731] 2024-09-25 21:54:48,859 >> loading configuration file /mnt/c/checkout/Phi-3.5-mini-instruct/config.json
[INFO|configuration_utils.py:731] 2024-09-25 21:54:48,876 >> loading configuration file /mnt/c/checkout/Phi-3.5-mini-instruct/config.json
[INFO|configuration_utils.py:800] 2024-09-25 21:54:48,877 >> Model config Phi3Config {
"_name_or_path": "/mnt/c/checkout/Phi-3.5-mini-instruct",
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
},
"bos_token_id": 1,
"embd_pdrop": 0.0,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"model_type": "phi3",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"original_max_position_embeddings": 4096,
"pad_token_id": 32000,
"resid_pdrop": 0.0,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"long_factor": [
1.0800000429153442,
1.1100000143051147,
1.1399999856948853,
1.340000033378601,
1.5899999141693115,
1.600000023841858,
1.6200000047683716,
2.620000123977661,
3.2300000190734863,
3.2300000190734863,
4.789999961853027,
7.400000095367432,
7.700000286102295,
9.09000015258789,
12.199999809265137,
17.670000076293945,
24.46000099182129,
28.57000160217285,
30.420001983642578,
30.840002059936523,
32.590003967285156,
32.93000411987305,
42.320003509521484,
44.96000289916992,
50.340003967285156,
50.45000457763672,
57.55000305175781,
57.93000411987305,
58.21000289916992,
60.1400032043457,
62.61000442504883,
62.62000274658203,
62.71000289916992,
63.1400032043457,
63.1400032043457,
63.77000427246094,
63.93000411987305,
63.96000289916992,
63.970001220703125,
64.02999877929688,
64.06999969482422,
64.08000183105469,
64.12000274658203,
64.41000366210938,
64.4800033569336,
64.51000213623047,
64.52999877929688,
64.83999633789062
],
"short_factor": [
1.0,
1.0199999809265137,
1.0299999713897705,
1.0299999713897705,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0699999332427979,
1.0999999046325684,
1.1099998950958252,
1.1599998474121094,
1.1599998474121094,
1.1699998378753662,
1.2899998426437378,
1.339999794960022,
1.679999828338623,
1.7899998426437378,
1.8199998140335083,
1.8499997854232788,
1.8799997568130493,
1.9099997282028198,
1.9399996995925903,
1.9899996519088745,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0799996852874756,
2.0899996757507324,
2.189999580383301,
2.2199995517730713,
2.5899994373321533,
2.729999542236328,
2.749999523162842,
2.8399994373321533
],
"type": "longrope"
},
"rope_theta": 10000.0,
"sliding_window": 262144,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.2",
"use_cache": true,
"vocab_size": 32064
}
[INFO|tokenization_utils_base.py:2267] 2024-09-25 21:54:48,919 >> loading file tokenizer.model
[INFO|tokenization_utils_base.py:2267] 2024-09-25 21:54:48,919 >> loading file tokenizer.json
[INFO|tokenization_utils_base.py:2267] 2024-09-25 21:54:48,919 >> loading file added_tokens.json
[INFO|tokenization_utils_base.py:2267] 2024-09-25 21:54:48,919 >> loading file special_tokens_map.json
[INFO|tokenization_utils_base.py:2267] 2024-09-25 21:54:48,919 >> loading file tokenizer_config.json
[INFO|tokenization_utils_base.py:2513] 2024-09-25 21:54:48,960 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
[INFO|configuration_utils.py:731] 2024-09-25 21:54:48,969 >> loading configuration file /mnt/c/checkout/Phi-3.5-mini-instruct/config.json
[INFO|configuration_utils.py:731] 2024-09-25 21:54:48,979 >> loading configuration file /mnt/c/checkout/Phi-3.5-mini-instruct/config.json
[INFO|configuration_utils.py:800] 2024-09-25 21:54:48,979 >> Model config Phi3Config {
"_name_or_path": "/mnt/c/checkout/Phi-3.5-mini-instruct",
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
},
"bos_token_id": 1,
"embd_pdrop": 0.0,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"model_type": "phi3",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"original_max_position_embeddings": 4096,
"pad_token_id": 32000,
"resid_pdrop": 0.0,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"long_factor": [
1.0800000429153442,
1.1100000143051147,
1.1399999856948853,
1.340000033378601,
1.5899999141693115,
1.600000023841858,
1.6200000047683716,
2.620000123977661,
3.2300000190734863,
3.2300000190734863,
4.789999961853027,
7.400000095367432,
7.700000286102295,
9.09000015258789,
12.199999809265137,
17.670000076293945,
24.46000099182129,
28.57000160217285,
30.420001983642578,
30.840002059936523,
32.590003967285156,
32.93000411987305,
42.320003509521484,
44.96000289916992,
50.340003967285156,
50.45000457763672,
57.55000305175781,
57.93000411987305,
58.21000289916992,
60.1400032043457,
62.61000442504883,
62.62000274658203,
62.71000289916992,
63.1400032043457,
63.1400032043457,
63.77000427246094,
63.93000411987305,
63.96000289916992,
63.970001220703125,
64.02999877929688,
64.06999969482422,
64.08000183105469,
64.12000274658203,
64.41000366210938,
64.4800033569336,
64.51000213623047,
64.52999877929688,
64.83999633789062
],
"short_factor": [
1.0,
1.0199999809265137,
1.0299999713897705,
1.0299999713897705,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0699999332427979,
1.0999999046325684,
1.1099998950958252,
1.1599998474121094,
1.1599998474121094,
1.1699998378753662,
1.2899998426437378,
1.339999794960022,
1.679999828338623,
1.7899998426437378,
1.8199998140335083,
1.8499997854232788,
1.8799997568130493,
1.9099997282028198,
1.9399996995925903,
1.9899996519088745,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0799996852874756,
2.0899996757507324,
2.189999580383301,
2.2199995517730713,
2.5899994373321533,
2.729999542236328,
2.749999523162842,
2.8399994373321533
],
"type": "longrope"
},
"rope_theta": 10000.0,
"sliding_window": 262144,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.2",
"use_cache": true,
"vocab_size": 32064
}
[INFO|tokenization_utils_base.py:2267] 2024-09-25 21:54:48,992 >> loading file tokenizer.model
[INFO|tokenization_utils_base.py:2267] 2024-09-25 21:54:48,992 >> loading file tokenizer.json
[INFO|tokenization_utils_base.py:2267] 2024-09-25 21:54:48,993 >> loading file added_tokens.json
[INFO|tokenization_utils_base.py:2267] 2024-09-25 21:54:48,993 >> loading file special_tokens_map.json
[INFO|tokenization_utils_base.py:2267] 2024-09-25 21:54:48,993 >> loading file tokenizer_config.json
[INFO|tokenization_utils_base.py:2513] 2024-09-25 21:54:49,030 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
[INFO|configuration_utils.py:731] 2024-09-25 21:54:49,791 >> loading configuration file /mnt/c/checkout/Phi-3.5-mini-instruct/config.json
[INFO|configuration_utils.py:731] 2024-09-25 21:54:49,799 >> loading configuration file /mnt/c/checkout/Phi-3.5-mini-instruct/config.json
[INFO|configuration_utils.py:800] 2024-09-25 21:54:49,800 >> Model config Phi3Config {
"_name_or_path": "/mnt/c/checkout/Phi-3.5-mini-instruct",
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
},
"bos_token_id": 1,
"embd_pdrop": 0.0,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"model_type": "phi3",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"original_max_position_embeddings": 4096,
"pad_token_id": 32000,
"resid_pdrop": 0.0,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"long_factor": [
1.0800000429153442,
1.1100000143051147,
1.1399999856948853,
1.340000033378601,
1.5899999141693115,
1.600000023841858,
1.6200000047683716,
2.620000123977661,
3.2300000190734863,
3.2300000190734863,
4.789999961853027,
7.400000095367432,
7.700000286102295,
9.09000015258789,
12.199999809265137,
17.670000076293945,
24.46000099182129,
28.57000160217285,
30.420001983642578,
30.840002059936523,
32.590003967285156,
32.93000411987305,
42.320003509521484,
44.96000289916992,
50.340003967285156,
50.45000457763672,
57.55000305175781,
57.93000411987305,
58.21000289916992,
60.1400032043457,
62.61000442504883,
62.62000274658203,
62.71000289916992,
63.1400032043457,
63.1400032043457,
63.77000427246094,
63.93000411987305,
63.96000289916992,
63.970001220703125,
64.02999877929688,
64.06999969482422,
64.08000183105469,
64.12000274658203,
64.41000366210938,
64.4800033569336,
64.51000213623047,
64.52999877929688,
64.83999633789062
],
"short_factor": [
1.0,
1.0199999809265137,
1.0299999713897705,
1.0299999713897705,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0699999332427979,
1.0999999046325684,
1.1099998950958252,
1.1599998474121094,
1.1599998474121094,
1.1699998378753662,
1.2899998426437378,
1.339999794960022,
1.679999828338623,
1.7899998426437378,
1.8199998140335083,
1.8499997854232788,
1.8799997568130493,
1.9099997282028198,
1.9399996995925903,
1.9899996519088745,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0799996852874756,
2.0899996757507324,
2.189999580383301,
2.2199995517730713,
2.5899994373321533,
2.729999542236328,
2.749999523162842,
2.8399994373321533
],
"type": "longrope"
},
"rope_theta": 10000.0,
"sliding_window": 262144,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.2",
"use_cache": true,
"vocab_size": 32064
}
[WARNING|modeling_phi3.py:62] 2024-09-25 21:54:51,178 >> `flash-attention` package not found, consider installing for better performance: No module named 'flash_attn'.
[WARNING|modeling_phi3.py:66] 2024-09-25 21:54:51,178 >> Current `flash-attention` does not support `window_size`. Either upgrade or use `attn_implementation='eager'`.
[INFO|modeling_utils.py:3675] 2024-09-25 21:54:51,183 >> loading weights file /mnt/c/checkout/Phi-3.5-mini-instruct/model.safetensors.index.json
[INFO|modeling_utils.py:1606] 2024-09-25 21:54:51,191 >> Instantiating Phi3ForCausalLM model under default dtype torch.bfloat16.
[INFO|configuration_utils.py:1038] 2024-09-25 21:54:51,191 >> Generate config GenerationConfig {
"bos_token_id": 1,
"eos_token_id": 32000,
"pad_token_id": 32000
}
[INFO|modeling_utils.py:4507] 2024-09-25 21:56:43,132 >> All model checkpoint weights were used when initializing Phi3ForCausalLM.
[INFO|modeling_utils.py:4515] 2024-09-25 21:56:43,132 >> All the weights of Phi3ForCausalLM were initialized from the model checkpoint at /mnt/c/checkout/Phi-3.5-mini-instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use Phi3ForCausalLM for predictions without further training.
[INFO|configuration_utils.py:991] 2024-09-25 21:56:43,142 >> loading configuration file /mnt/c/checkout/Phi-3.5-mini-instruct/generation_config.json
[INFO|configuration_utils.py:1038] 2024-09-25 21:56:43,142 >> Generate config GenerationConfig {
"bos_token_id": 1,
"eos_token_id": [
32007,
32001,
32000
],
"pad_token_id": 32000
}
[INFO|trainer.py:648] 2024-09-25 21:56:43,208 >> Using auto half precision backend
[INFO|trainer.py:2134] 2024-09-25 21:57:01,081 >> ***** Running training *****
[INFO|trainer.py:2135] 2024-09-25 21:57:01,081 >> Num examples = 3,900
[INFO|trainer.py:2136] 2024-09-25 21:57:01,081 >> Num Epochs = 32
[INFO|trainer.py:2137] 2024-09-25 21:57:01,081 >> Instantaneous batch size per device = 4
[INFO|trainer.py:2140] 2024-09-25 21:57:01,081 >> Total train batch size (w. parallel, distributed & accumulation) = 16
[INFO|trainer.py:2141] 2024-09-25 21:57:01,081 >> Gradient Accumulation steps = 4
[INFO|trainer.py:2142] 2024-09-25 21:57:01,081 >> Total optimization steps = 7,776
[INFO|trainer.py:2143] 2024-09-25 21:57:01,082 >> Number of trainable parameters = 113,252,352
[WARNING|logging.py:328] 2024-09-25 21:57:01,353 >> You are not running the flash-attention implementation, expect numerical differences.
[INFO|trainer.py:3503] 2024-09-26 01:55:14,826 >> Saving model checkpoint to saves/Custom/full/SpecAI/checkpoint-2000
[INFO|configuration_utils.py:472] 2024-09-26 01:55:14,876 >> Configuration saved in saves/Custom/full/SpecAI/checkpoint-2000/config.json
[INFO|configuration_utils.py:807] 2024-09-26 01:55:14,882 >> Configuration saved in saves/Custom/full/SpecAI/checkpoint-2000/generation_config.json
[INFO|modeling_utils.py:2807] 2024-09-26 01:55:31,164 >> 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 saves/Custom/full/SpecAI/checkpoint-2000/model.safetensors.index.json.
[INFO|tokenization_utils_base.py:2684] 2024-09-26 01:55:31,171 >> tokenizer config file saved in saves/Custom/full/SpecAI/checkpoint-2000/tokenizer_config.json
[INFO|tokenization_utils_base.py:2693] 2024-09-26 01:55:31,175 >> Special tokens file saved in saves/Custom/full/SpecAI/checkpoint-2000/special_tokens_map.json
[INFO|trainer.py:3503] 2024-09-26 06:01:21,589 >> Saving model checkpoint to saves/Custom/full/SpecAI/checkpoint-4000
[INFO|configuration_utils.py:472] 2024-09-26 06:01:21,634 >> Configuration saved in saves/Custom/full/SpecAI/checkpoint-4000/config.json
[INFO|configuration_utils.py:807] 2024-09-26 06:01:21,639 >> Configuration saved in saves/Custom/full/SpecAI/checkpoint-4000/generation_config.json
[INFO|modeling_utils.py:2807] 2024-09-26 06:01:33,186 >> 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 saves/Custom/full/SpecAI/checkpoint-4000/model.safetensors.index.json.
[INFO|tokenization_utils_base.py:2684] 2024-09-26 06:01:33,193 >> tokenizer config file saved in saves/Custom/full/SpecAI/checkpoint-4000/tokenizer_config.json
[INFO|tokenization_utils_base.py:2693] 2024-09-26 06:01:33,196 >> Special tokens file saved in saves/Custom/full/SpecAI/checkpoint-4000/special_tokens_map.json
[INFO|trainer.py:2394] 2024-09-26 07:57:18,192 >>
Training completed. Do not forget to share your model on huggingface.co/models =)
[INFO|trainer.py:3503] 2024-09-26 07:57:18,202 >> Saving model checkpoint to saves/Custom/full/SpecAI
[INFO|configuration_utils.py:472] 2024-09-26 07:57:18,244 >> Configuration saved in saves/Custom/full/SpecAI/config.json
[INFO|configuration_utils.py:807] 2024-09-26 07:57:18,247 >> Configuration saved in saves/Custom/full/SpecAI/generation_config.json
[INFO|modeling_utils.py:2807] 2024-09-26 07:57:29,353 >> 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 saves/Custom/full/SpecAI/model.safetensors.index.json.
[INFO|tokenization_utils_base.py:2684] 2024-09-26 07:57:29,357 >> tokenizer config file saved in saves/Custom/full/SpecAI/tokenizer_config.json
[INFO|tokenization_utils_base.py:2693] 2024-09-26 07:57:29,359 >> Special tokens file saved in saves/Custom/full/SpecAI/special_tokens_map.json
[INFO|modelcard.py:449] 2024-09-26 07:57:29,626 >> Dropping the following result as it does not have all the necessary fields:
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}