Hugging Face's logo

kiatkock
/
MV-Time-MOE

Time Series Forecasting
TensorBoard
Safetensors
English
time_moe
custom_code
Model card Files
xet
 Metrics Community
kiatkock commited on
Commit
b533f03
·
verified ·
1 Parent(s): 6ae5f5a

Upload folder using huggingface_hub

Browse files
Files changed (37) hide show
  1. checkpoint-19/config.json +61 -0
  2. checkpoint-19/generation_config.json +4 -0
  3. checkpoint-19/model.safetensors +3 -0
  4. checkpoint-19/optimizer.pt +3 -0
  5. checkpoint-19/rng_state.pth +3 -0
  6. checkpoint-19/scheduler.pt +3 -0
  7. checkpoint-19/trainer_state.json +162 -0
  8. checkpoint-19/training_args.bin +3 -0
  9. checkpoint-38/config.json +61 -0
  10. checkpoint-38/generation_config.json +4 -0
  11. checkpoint-38/model.safetensors +3 -0
  12. checkpoint-38/optimizer.pt +3 -0
  13. checkpoint-38/rng_state.pth +3 -0
  14. checkpoint-38/scheduler.pt +3 -0
  15. checkpoint-38/trainer_state.json +311 -0
  16. checkpoint-38/training_args.bin +3 -0
  17. config.json +23 -0
  18. model.safetensors +2 -2
  19. tb_logs/events.out.tfevents.1759808955.Kiat.20684.0 +3 -0
  20. tb_logs/events.out.tfevents.1759916316.Kiat.6776.0 +3 -0
  21. tb_logs/events.out.tfevents.1759916698.Kiat.40236.0 +3 -0
  22. tb_logs/events.out.tfevents.1759916873.Kiat.48352.0 +3 -0
  23. tb_logs/events.out.tfevents.1759917219.Kiat.43332.0 +3 -0
  24. tb_logs/events.out.tfevents.1759917367.Kiat.46368.0 +3 -0
  25. tb_logs/events.out.tfevents.1759917837.Kiat.42516.0 +3 -0
  26. tb_logs/events.out.tfevents.1759918617.Kiat.10048.0 +3 -0
  27. tb_logs/events.out.tfevents.1759918780.Kiat.48404.0 +3 -0
  28. tb_logs/events.out.tfevents.1759919238.Kiat.9720.0 +3 -0
  29. tb_logs/events.out.tfevents.1759919362.Kiat.16920.0 +3 -0
  30. tb_logs/events.out.tfevents.1759922184.Kiat.31428.0 +3 -0
  31. tb_logs/events.out.tfevents.1759922500.Kiat.41916.0 +3 -0
  32. tb_logs/events.out.tfevents.1759922906.Kiat.45284.0 +3 -0
  33. tb_logs/events.out.tfevents.1760147369.Kiat.19368.0 +3 -0
  34. tb_logs/events.out.tfevents.1760149649.Kiat.39916.0 +3 -0
  35. tb_logs/events.out.tfevents.1760150112.Kiat.14768.0 +3 -0
  36. tb_logs/events.out.tfevents.1760150835.Kiat.29752.0 +3 -0
  37. training_args.bin +1 -1
checkpoint-19/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "time_moe_50m",
3
+ "apply_aux_loss": true,
4
+ "architectures": [
5
+ "TimeMoeForPrediction"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "Maple728/TimeMoE-50M--configuration_time_moe.TimeMoeConfig",
10
+ "AutoModelForCausalLM": "Maple728/TimeMoE-50M--modeling_time_moe.TimeMoeForPrediction"
11
+ },
12
+ "channel_configs": [
13
+ [
14
+ 63,
15
+ 1,
16
+ 1
17
+ ],
18
+ [
19
+ 6,
20
+ 1,
21
+ 4
22
+ ],
23
+ [
24
+ 5,
25
+ 1,
26
+ 1
27
+ ],
28
+ [
29
+ 5,
30
+ 1,
31
+ 1
32
+ ]
33
+ ],
34
+ "embedding_hidden_size": 128,
35
+ "hidden_act": "silu",
36
+ "hidden_size": 384,
37
+ "horizon_lengths": [
38
+ 1,
39
+ 8,
40
+ 32,
41
+ 64
42
+ ],
43
+ "initializer_range": 0.02,
44
+ "input_size": 42,
45
+ "intermediate_size": 1536,
46
+ "max_position_embeddings": 4096,
47
+ "model_type": "time_moe",
48
+ "num_attention_heads": 12,
49
+ "num_experts": 8,
50
+ "num_experts_per_tok": 2,
51
+ "num_hidden_layers": 12,
52
+ "num_key_value_heads": 12,
53
+ "rms_norm_eps": 1e-06,
54
+ "rope_theta": 10000,
55
+ "router_aux_loss_factor": 0.02,
56
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.40.1",
59
+ "use_cache": true,
60
+ "use_dense": false
61
+ }
checkpoint-19/generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.40.1"
4
+ }
checkpoint-19/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06a04b5042cf658f8d9adae85808fed850cb0f980fa3e2d6ff9abcfdb035bc32
3
+ size 484301192
checkpoint-19/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bbde949aae64f116f8457e11a0d8dbb574f18db6b9af1c01f5bc566c2c6d7f5
3
+ size 968903096
checkpoint-19/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e84bed71f4a9bc9d5acc05fc4efa4b2c7fdbf0c467e88885c07eb731c105c03
3
+ size 14391
checkpoint-19/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e794c7d6be1e9d0bb5078467209c7377bdb6d9dc7eba7705aed948b9d94d4d2
3
+ size 1465
checkpoint-19/trainer_state.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.987012987012987,
5
+ "eval_steps": 10,
6
+ "global_step": 19,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05194805194805195,
13
+ "grad_norm": 1.6432675123214722,
14
+ "learning_rate": 9.991461232516675e-05,
15
+ "loss": 0.5031,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.1038961038961039,
20
+ "grad_norm": 0.5562512874603271,
21
+ "learning_rate": 9.965903258506806e-05,
22
+ "loss": 0.4653,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.15584415584415584,
27
+ "grad_norm": 1.6149150133132935,
28
+ "learning_rate": 9.923500664848326e-05,
29
+ "loss": 0.4633,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.2077922077922078,
34
+ "grad_norm": 0.3160852789878845,
35
+ "learning_rate": 9.864543104251586e-05,
36
+ "loss": 0.4441,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.2597402597402597,
41
+ "grad_norm": 0.5903643369674683,
42
+ "learning_rate": 9.789433316637644e-05,
43
+ "loss": 0.4321,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.3116883116883117,
48
+ "grad_norm": 0.5757947564125061,
49
+ "learning_rate": 9.698684378016223e-05,
50
+ "loss": 0.428,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.36363636363636365,
55
+ "grad_norm": 0.23386144638061523,
56
+ "learning_rate": 9.592916195656321e-05,
57
+ "loss": 0.4236,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.4155844155844156,
62
+ "grad_norm": 0.4889293611049652,
63
+ "learning_rate": 9.472851273490985e-05,
64
+ "loss": 0.4094,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.4675324675324675,
69
+ "grad_norm": 0.39676418900489807,
70
+ "learning_rate": 9.33930977668283e-05,
71
+ "loss": 0.4022,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.5194805194805194,
76
+ "grad_norm": 0.1289692521095276,
77
+ "learning_rate": 9.193203929064353e-05,
78
+ "loss": 0.4116,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.5194805194805194,
83
+ "eval_loss": 0.40595975518226624,
84
+ "eval_runtime": 158.3006,
85
+ "eval_samples_per_second": 5.553,
86
+ "eval_steps_per_second": 0.347,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.5714285714285714,
91
+ "grad_norm": 0.3013388216495514,
92
+ "learning_rate": 9.03553178172417e-05,
93
+ "loss": 0.4119,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.6233766233766234,
98
+ "grad_norm": 0.3328374922275543,
99
+ "learning_rate": 8.867370395306068e-05,
100
+ "loss": 0.4067,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.6753246753246753,
105
+ "grad_norm": 0.21512869000434875,
106
+ "learning_rate": 8.689868482592685e-05,
107
+ "loss": 0.4027,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.7272727272727273,
112
+ "grad_norm": 0.18570910394191742,
113
+ "learning_rate": 8.504238561632425e-05,
114
+ "loss": 0.3942,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.7792207792207793,
119
+ "grad_norm": 0.23511634767055511,
120
+ "learning_rate": 8.31174867301171e-05,
121
+ "loss": 0.4071,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.8311688311688312,
126
+ "grad_norm": 0.20484352111816406,
127
+ "learning_rate": 8.113713717851999e-05,
128
+ "loss": 0.394,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.8831168831168831,
133
+ "grad_norm": 0.09572683274745941,
134
+ "learning_rate": 7.911486475701834e-05,
135
+ "loss": 0.3967,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.935064935064935,
140
+ "grad_norm": 0.1649264693260193,
141
+ "learning_rate": 7.706448363680832e-05,
142
+ "loss": 0.3995,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.987012987012987,
147
+ "grad_norm": 0.21399255096912384,
148
+ "learning_rate": 7.500000000000001e-05,
149
+ "loss": 0.3955,
150
+ "step": 19
151
+ }
152
+ ],
153
+ "logging_steps": 1,
154
+ "max_steps": 38,
155
+ "num_input_tokens_seen": 0,
156
+ "num_train_epochs": 2,
157
+ "save_steps": 500,
158
+ "total_flos": 113649040834560.0,
159
+ "train_batch_size": 8,
160
+ "trial_name": null,
161
+ "trial_params": null
162
+ }
checkpoint-19/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f77884ddd41b5ba98022ed7940c5beac63484e3fee92ab74006e9bad8e19e3
3
+ size 5585
checkpoint-38/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "time_moe_50m",
3
+ "apply_aux_loss": true,
4
+ "architectures": [
5
+ "TimeMoeForPrediction"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "Maple728/TimeMoE-50M--configuration_time_moe.TimeMoeConfig",
10
+ "AutoModelForCausalLM": "Maple728/TimeMoE-50M--modeling_time_moe.TimeMoeForPrediction"
11
+ },
12
+ "channel_configs": [
13
+ [
14
+ 63,
15
+ 1,
16
+ 1
17
+ ],
18
+ [
19
+ 6,
20
+ 1,
21
+ 4
22
+ ],
23
+ [
24
+ 5,
25
+ 1,
26
+ 1
27
+ ],
28
+ [
29
+ 5,
30
+ 1,
31
+ 1
32
+ ]
33
+ ],
34
+ "embedding_hidden_size": 128,
35
+ "hidden_act": "silu",
36
+ "hidden_size": 384,
37
+ "horizon_lengths": [
38
+ 1,
39
+ 8,
40
+ 32,
41
+ 64
42
+ ],
43
+ "initializer_range": 0.02,
44
+ "input_size": 42,
45
+ "intermediate_size": 1536,
46
+ "max_position_embeddings": 4096,
47
+ "model_type": "time_moe",
48
+ "num_attention_heads": 12,
49
+ "num_experts": 8,
50
+ "num_experts_per_tok": 2,
51
+ "num_hidden_layers": 12,
52
+ "num_key_value_heads": 12,
53
+ "rms_norm_eps": 1e-06,
54
+ "rope_theta": 10000,
55
+ "router_aux_loss_factor": 0.02,
56
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.40.1",
59
+ "use_cache": true,
60
+ "use_dense": false
61
+ }
checkpoint-38/generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.40.1"
4
+ }
checkpoint-38/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b0f8d6a29a701a2e5f989864080355d3c8535d9fb4648d862d3c41cc38720ff
3
+ size 484301192
checkpoint-38/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbead1432fe13cb721a6119167c5455a6bad7d52c63d711fe17056202bad3729
3
+ size 968903096
checkpoint-38/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3218cf610f880af8f0315be96cd4dca1fd389a35925857970ec802aa36f26ce
3
+ size 14391
checkpoint-38/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdd0f69232bead07e49eac09a7a0c21d64acaf69cc031d21267e358e31f7816f
3
+ size 1465
checkpoint-38/trainer_state.json ADDED
@@ -0,0 +1,311 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.974025974025974,
5
+ "eval_steps": 10,
6
+ "global_step": 38,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05194805194805195,
13
+ "grad_norm": 1.6432675123214722,
14
+ "learning_rate": 9.991461232516675e-05,
15
+ "loss": 0.5031,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.1038961038961039,
20
+ "grad_norm": 0.5562512874603271,
21
+ "learning_rate": 9.965903258506806e-05,
22
+ "loss": 0.4653,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.15584415584415584,
27
+ "grad_norm": 1.6149150133132935,
28
+ "learning_rate": 9.923500664848326e-05,
29
+ "loss": 0.4633,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.2077922077922078,
34
+ "grad_norm": 0.3160852789878845,
35
+ "learning_rate": 9.864543104251586e-05,
36
+ "loss": 0.4441,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.2597402597402597,
41
+ "grad_norm": 0.5903643369674683,
42
+ "learning_rate": 9.789433316637644e-05,
43
+ "loss": 0.4321,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.3116883116883117,
48
+ "grad_norm": 0.5757947564125061,
49
+ "learning_rate": 9.698684378016223e-05,
50
+ "loss": 0.428,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.36363636363636365,
55
+ "grad_norm": 0.23386144638061523,
56
+ "learning_rate": 9.592916195656321e-05,
57
+ "loss": 0.4236,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.4155844155844156,
62
+ "grad_norm": 0.4889293611049652,
63
+ "learning_rate": 9.472851273490985e-05,
64
+ "loss": 0.4094,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.4675324675324675,
69
+ "grad_norm": 0.39676418900489807,
70
+ "learning_rate": 9.33930977668283e-05,
71
+ "loss": 0.4022,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.5194805194805194,
76
+ "grad_norm": 0.1289692521095276,
77
+ "learning_rate": 9.193203929064353e-05,
78
+ "loss": 0.4116,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.5194805194805194,
83
+ "eval_loss": 0.40595975518226624,
84
+ "eval_runtime": 158.3006,
85
+ "eval_samples_per_second": 5.553,
86
+ "eval_steps_per_second": 0.347,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.5714285714285714,
91
+ "grad_norm": 0.3013388216495514,
92
+ "learning_rate": 9.03553178172417e-05,
93
+ "loss": 0.4119,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.6233766233766234,
98
+ "grad_norm": 0.3328374922275543,
99
+ "learning_rate": 8.867370395306068e-05,
100
+ "loss": 0.4067,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.6753246753246753,
105
+ "grad_norm": 0.21512869000434875,
106
+ "learning_rate": 8.689868482592685e-05,
107
+ "loss": 0.4027,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.7272727272727273,
112
+ "grad_norm": 0.18570910394191742,
113
+ "learning_rate": 8.504238561632425e-05,
114
+ "loss": 0.3942,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.7792207792207793,
119
+ "grad_norm": 0.23511634767055511,
120
+ "learning_rate": 8.31174867301171e-05,
121
+ "loss": 0.4071,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.8311688311688312,
126
+ "grad_norm": 0.20484352111816406,
127
+ "learning_rate": 8.113713717851999e-05,
128
+ "loss": 0.394,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.8831168831168831,
133
+ "grad_norm": 0.09572683274745941,
134
+ "learning_rate": 7.911486475701834e-05,
135
+ "loss": 0.3967,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.935064935064935,
140
+ "grad_norm": 0.1649264693260193,
141
+ "learning_rate": 7.706448363680832e-05,
142
+ "loss": 0.3995,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.987012987012987,
147
+ "grad_norm": 0.21399255096912384,
148
+ "learning_rate": 7.500000000000001e-05,
149
+ "loss": 0.3955,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 1.0389610389610389,
154
+ "grad_norm": 0.14867942035198212,
155
+ "learning_rate": 7.293551636319169e-05,
156
+ "loss": 0.3945,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 1.0389610389610389,
161
+ "eval_loss": 0.39206692576408386,
162
+ "eval_runtime": 179.024,
163
+ "eval_samples_per_second": 4.91,
164
+ "eval_steps_per_second": 0.307,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 1.0909090909090908,
169
+ "grad_norm": 0.09991628676652908,
170
+ "learning_rate": 7.088513524298165e-05,
171
+ "loss": 0.3848,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 1.1428571428571428,
176
+ "grad_norm": 0.1252763867378235,
177
+ "learning_rate": 6.886286282148003e-05,
178
+ "loss": 0.3926,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 1.1948051948051948,
183
+ "grad_norm": 0.1419353038072586,
184
+ "learning_rate": 6.688251326988292e-05,
185
+ "loss": 0.3851,
186
+ "step": 23
187
+ },
188
+ {
189
+ "epoch": 1.2467532467532467,
190
+ "grad_norm": 0.13815397024154663,
191
+ "learning_rate": 6.495761438367577e-05,
192
+ "loss": 0.4086,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 1.2987012987012987,
197
+ "grad_norm": 0.0793849304318428,
198
+ "learning_rate": 6.310131517407316e-05,
199
+ "loss": 0.3715,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 1.3506493506493507,
204
+ "grad_norm": 0.13267183303833008,
205
+ "learning_rate": 6.132629604693934e-05,
206
+ "loss": 0.3743,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 1.4025974025974026,
211
+ "grad_norm": 0.10902910679578781,
212
+ "learning_rate": 5.964468218275831e-05,
213
+ "loss": 0.384,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 1.4545454545454546,
218
+ "grad_norm": 0.13299435377120972,
219
+ "learning_rate": 5.806796070935648e-05,
220
+ "loss": 0.3818,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 1.5064935064935066,
225
+ "grad_norm": 0.0626634806394577,
226
+ "learning_rate": 5.660690223317171e-05,
227
+ "loss": 0.3743,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 1.5584415584415585,
232
+ "grad_norm": 0.12969431281089783,
233
+ "learning_rate": 5.5271487265090174e-05,
234
+ "loss": 0.3796,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 1.5584415584415585,
239
+ "eval_loss": 0.38425013422966003,
240
+ "eval_runtime": 144.0451,
241
+ "eval_samples_per_second": 6.102,
242
+ "eval_steps_per_second": 0.382,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 1.6103896103896105,
247
+ "grad_norm": 0.09089459478855133,
248
+ "learning_rate": 5.4070838043436786e-05,
249
+ "loss": 0.3696,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 1.6623376623376624,
254
+ "grad_norm": 0.06643843650817871,
255
+ "learning_rate": 5.301315621983778e-05,
256
+ "loss": 0.3869,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 1.7142857142857144,
261
+ "grad_norm": 0.05322933569550514,
262
+ "learning_rate": 5.210566683362357e-05,
263
+ "loss": 0.3704,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 1.7662337662337664,
268
+ "grad_norm": 0.11062971502542496,
269
+ "learning_rate": 5.1354568957484136e-05,
270
+ "loss": 0.363,
271
+ "step": 34
272
+ },
273
+ {
274
+ "epoch": 1.8181818181818183,
275
+ "grad_norm": 0.08682668954133987,
276
+ "learning_rate": 5.076499335151674e-05,
277
+ "loss": 0.3677,
278
+ "step": 35
279
+ },
280
+ {
281
+ "epoch": 1.87012987012987,
282
+ "grad_norm": 0.07694629579782486,
283
+ "learning_rate": 5.034096741493195e-05,
284
+ "loss": 0.378,
285
+ "step": 36
286
+ },
287
+ {
288
+ "epoch": 1.922077922077922,
289
+ "grad_norm": 0.08460162580013275,
290
+ "learning_rate": 5.008538767483326e-05,
291
+ "loss": 0.3814,
292
+ "step": 37
293
+ },
294
+ {
295
+ "epoch": 1.974025974025974,
296
+ "grad_norm": 0.11470505595207214,
297
+ "learning_rate": 5e-05,
298
+ "loss": 0.3846,
299
+ "step": 38
300
+ }
301
+ ],
302
+ "logging_steps": 1,
303
+ "max_steps": 38,
304
+ "num_input_tokens_seen": 0,
305
+ "num_train_epochs": 2,
306
+ "save_steps": 500,
307
+ "total_flos": 224346158530560.0,
308
+ "train_batch_size": 8,
309
+ "trial_name": null,
310
+ "trial_params": null
311
+ }
checkpoint-38/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f77884ddd41b5ba98022ed7940c5beac63484e3fee92ab74006e9bad8e19e3
3
+ size 5585
config.json CHANGED
@@ -9,6 +9,29 @@
9
  "AutoConfig": "Maple728/TimeMoE-50M--configuration_time_moe.TimeMoeConfig",
10
  "AutoModelForCausalLM": "Maple728/TimeMoE-50M--modeling_time_moe.TimeMoeForPrediction"
11
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  "hidden_act": "silu",
13
  "hidden_size": 384,
14
  "horizon_lengths": [
 
9
  "AutoConfig": "Maple728/TimeMoE-50M--configuration_time_moe.TimeMoeConfig",
10
  "AutoModelForCausalLM": "Maple728/TimeMoE-50M--modeling_time_moe.TimeMoeForPrediction"
11
  },
12
+ "channel_configs": [
13
+ [
14
+ 63,
15
+ 1,
16
+ 1
17
+ ],
18
+ [
19
+ 6,
20
+ 1,
21
+ 4
22
+ ],
23
+ [
24
+ 5,
25
+ 1,
26
+ 1
27
+ ],
28
+ [
29
+ 5,
30
+ 1,
31
+ 1
32
+ ]
33
+ ],
34
+ "embedding_hidden_size": 128,
35
  "hidden_act": "silu",
36
  "hidden_size": 384,
37
  "horizon_lengths": [
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a235d1233b2617ecb3a0c5e9a55a0a05b59fc7c03b38a65af3083fbad9a4cfb
3
- size 453590368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b0f8d6a29a701a2e5f989864080355d3c8535d9fb4648d862d3c41cc38720ff
3
+ size 484301192
tb_logs/events.out.tfevents.1759808955.Kiat.20684.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec34ec5e2381742e47e2dc6761a999da10b3f25d08372032157ee88f5f513f68
3
+ size 5294
tb_logs/events.out.tfevents.1759916316.Kiat.6776.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac5333f9dfdb0cec78959a1b611defde2f05f3be72865641fe39b350445b9f83
3
+ size 5362
tb_logs/events.out.tfevents.1759916698.Kiat.40236.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:152b1e7d6193d8f4e7f9cc3f5b12d73dcca24ed45e80c2da02d3702af0914195
3
+ size 5362
tb_logs/events.out.tfevents.1759916873.Kiat.48352.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c60e37f315e37da69049de09783627297c0582d9583a537f93176e51f26010de
3
+ size 5362
tb_logs/events.out.tfevents.1759917219.Kiat.43332.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e140140f33ab264832449f62c9bd3e04abc5e4952d98ecad7e921c90021140
3
+ size 5362
tb_logs/events.out.tfevents.1759917367.Kiat.46368.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f2953a7e62e0ca4fa2bcf6b8f4916a94feafbc9a607698cd2adf7c7ccf18676
3
+ size 5362
tb_logs/events.out.tfevents.1759917837.Kiat.42516.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b50c31f05ea7a3496881d36b85d66b476bff1eba793a40a34cd2914ad91192
3
+ size 5362
tb_logs/events.out.tfevents.1759918617.Kiat.10048.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91278a687c56d108cf8c3ca31b2ffdb8622b620916f844abbb56f6483f4ce006
3
+ size 5362
tb_logs/events.out.tfevents.1759918780.Kiat.48404.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41fa46c3aecd101f4c3b9e2e0bfc812a84bf5ec995024c10bf69ecb3b7ae4f9d
3
+ size 5362
tb_logs/events.out.tfevents.1759919238.Kiat.9720.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d10e28dbdb7edaf6b01c49f467d1836ce8b760e37983549afda2178a382682
3
+ size 5362
tb_logs/events.out.tfevents.1759919362.Kiat.16920.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c98730ad72072a2ca30c1b6ce2f3d5979dbe7ebd89acff9b81b644f0175f0e66
3
+ size 5362
tb_logs/events.out.tfevents.1759922184.Kiat.31428.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dd8b42baf0b2977d6c3ce21803153f0dbca08cdbbbe2ff65c464b73e115dc75
3
+ size 5362
tb_logs/events.out.tfevents.1759922500.Kiat.41916.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27ee278a825d55afc8cdf401c06f2d472528f9a4ac9a5abc0deb1b99df86ea3
3
+ size 5362
tb_logs/events.out.tfevents.1759922906.Kiat.45284.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:205bb2382241ef10dc105b75c5159020e558e117607eb7b940dcbc4d5ec1815c
3
+ size 6397
tb_logs/events.out.tfevents.1760147369.Kiat.19368.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b2d7e3b4db6c8f655a929fec368ab8c7a49c4cc55f15a31629cc91c7a37dc2
3
+ size 14374
tb_logs/events.out.tfevents.1760149649.Kiat.39916.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed5f81ca2cd655114408b0b40d642a39a173da71e09c13688b4a9ca13adc446
3
+ size 5362
tb_logs/events.out.tfevents.1760150112.Kiat.14768.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d29a147efba4de9a07397a3f7d4dcf24be94fe357b12016f0def205cc8307c
3
+ size 6604
tb_logs/events.out.tfevents.1760150835.Kiat.29752.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b784aa713dbb47fbec9aa0253ba68787677987e8b76e0e46f2e1dfe2a4aa8643
3
+ size 14374
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e0ba8f7d1f4055031a314da1e69102ba7c77e6973eace7a1dfdc9edcc67a662
3
  size 5585
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f77884ddd41b5ba98022ed7940c5beac63484e3fee92ab74006e9bad8e19e3
3
  size 5585