cheeseRadical commited on
Commit
192b58c
·
verified ·
1 Parent(s): aeb863b

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. autotimes_config.json +57 -0
  2. config.json +85 -0
  3. model.safetensors +3 -0
autotimes_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "ETH_5m_tempnorm",
3
+ "root_path": "/content/drive/MyDrive/eth_autotimes/",
4
+ "data_path": "eth_5m.csv",
5
+ "llm_type": "llama",
6
+ "model_id": "eth_5m",
7
+ "model": "AutoTimes_Llama",
8
+ "data": "ETH",
9
+ "features": null,
10
+ "seq_len": 480,
11
+ "label_len": 384,
12
+ "token_len": 96,
13
+ "tokenize_marks": [
14
+ true
15
+ ],
16
+ "pred_len": 96,
17
+ "minutes": [
18
+ 5
19
+ ],
20
+ "test_seq_len": 480,
21
+ "test_label_len": 384,
22
+ "test_pred_len": 96,
23
+ "batch_size": 64,
24
+ "learning_rate": 0.0005,
25
+ "weight_decay": 0,
26
+ "train_epochs": 10,
27
+ "tmax": 10,
28
+ "gpu": 0,
29
+ "use_amp": true,
30
+ "cosine": true,
31
+ "val_set_shuffle": false,
32
+ "drop_last": false,
33
+ "num_workers": 4,
34
+ "checkpoints": "./checkpoints",
35
+ "test_dir": "./test",
36
+ "test_file_name": "best_model.pth",
37
+ "visualize": false,
38
+ "loss": "MSE",
39
+ "use_multi_gpu": false,
40
+ "local_rank": null,
41
+ "seasonal_patterns": null,
42
+ "frequency_map": null,
43
+ "des": "test",
44
+ "lradj": "type1",
45
+ "patience": 3,
46
+ "dropout": 0.1,
47
+ "llm_ckp_dir": "./llama",
48
+ "mlp_hidden_dim": 512,
49
+ "mlp_hidden_layers": 4,
50
+ "mlp_activation": "gelu",
51
+ "mix_embeds": true,
52
+ "scale": true,
53
+ "train_fraction": 0.7,
54
+ "test_fraction": 0.25,
55
+ "scaler_type": "standard",
56
+ "extra_kwargs": {}
57
+ }
config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 32000,
3
+ "max_position_embeddings": 4096,
4
+ "hidden_size": 4096,
5
+ "intermediate_size": 11008,
6
+ "num_hidden_layers": 32,
7
+ "num_attention_heads": 32,
8
+ "num_key_value_heads": 32,
9
+ "hidden_act": "silu",
10
+ "initializer_range": 0.02,
11
+ "rms_norm_eps": 1e-05,
12
+ "pretraining_tp": 1,
13
+ "use_cache": true,
14
+ "rope_theta": 10000.0,
15
+ "rope_scaling": null,
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "mlp_bias": false,
19
+ "head_dim": 128,
20
+ "return_dict": true,
21
+ "output_hidden_states": false,
22
+ "output_attentions": false,
23
+ "torchscript": false,
24
+ "torch_dtype": "float16",
25
+ "use_bfloat16": false,
26
+ "tf_legacy_loss": false,
27
+ "pruned_heads": {},
28
+ "tie_word_embeddings": false,
29
+ "chunk_size_feed_forward": 0,
30
+ "is_encoder_decoder": false,
31
+ "is_decoder": false,
32
+ "cross_attention_hidden_size": null,
33
+ "add_cross_attention": false,
34
+ "tie_encoder_decoder": false,
35
+ "max_length": 20,
36
+ "min_length": 0,
37
+ "do_sample": false,
38
+ "early_stopping": false,
39
+ "num_beams": 1,
40
+ "num_beam_groups": 1,
41
+ "diversity_penalty": 0.0,
42
+ "temperature": 1.0,
43
+ "top_k": 50,
44
+ "top_p": 1.0,
45
+ "typical_p": 1.0,
46
+ "repetition_penalty": 1.0,
47
+ "length_penalty": 1.0,
48
+ "no_repeat_ngram_size": 0,
49
+ "encoder_no_repeat_ngram_size": 0,
50
+ "bad_words_ids": null,
51
+ "num_return_sequences": 1,
52
+ "output_scores": false,
53
+ "return_dict_in_generate": false,
54
+ "forced_bos_token_id": null,
55
+ "forced_eos_token_id": null,
56
+ "remove_invalid_values": false,
57
+ "exponential_decay_length_penalty": null,
58
+ "suppress_tokens": null,
59
+ "begin_suppress_tokens": null,
60
+ "architectures": [
61
+ "LlamaForCausalLM"
62
+ ],
63
+ "finetuning_task": null,
64
+ "id2label": {
65
+ "0": "LABEL_0",
66
+ "1": "LABEL_1"
67
+ },
68
+ "label2id": {
69
+ "LABEL_0": 0,
70
+ "LABEL_1": 1
71
+ },
72
+ "tokenizer_class": null,
73
+ "prefix": null,
74
+ "bos_token_id": 1,
75
+ "pad_token_id": null,
76
+ "eos_token_id": 2,
77
+ "sep_token_id": null,
78
+ "decoder_start_token_id": null,
79
+ "task_specific_params": null,
80
+ "problem_type": null,
81
+ "_name_or_path": "./llama",
82
+ "_attn_implementation_autoset": true,
83
+ "transformers_version": "4.48.3",
84
+ "model_type": "llama"
85
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b6b170f7f87e8dacc0ed7bd7158f741f4857f34eb06e96295c4606c2ba5a56a
3
+ size 13498280268