Hugging Face's logo

ojaffe
/
world-model

Model card Files
xet
 Community
ojaffe commited on
Commit
3cac80b
·
verified ·
1 Parent(s): f852b2a

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. __pycache__/predict.cpython-311.pyc +0 -0
  2. model_pole_position.pt +1 -1
  3. model_pong.pt +2 -2
  4. model_sonic.pt +1 -1
  5. predict.py +61 -82
  6. train.log +152 -118
__pycache__/predict.cpython-311.pyc CHANGED
Binary files a/__pycache__/predict.cpython-311.pyc and b/__pycache__/predict.cpython-311.pyc differ
 
model_pole_position.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27d26875071b536cc75cac27a0840b50cd6c9a8e1956c94f1cd08feacc49621f
3
  size 2971526
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e0affcef8e533a29037751e27948a3eb0f2fda2792ce2b3dfc876cadb09e281
3
  size 2971526
model_pong.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6c8b9235347bea94e7e5f5f0f225d4c1dbd13a749d5e28920c75c91902ecb11
3
- size 2435368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab8070ddcde00333d7b52c89a0da9a61eece1e67c46163cd011ce4cd3c422f0c
3
+ size 2436712
model_sonic.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9035098568ea4789c5dda58d685af07b4b5a0cdf300848f79ed6d96ad901da34
3
  size 6182614
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e17327a6f03cb72a35bd3c48d481b4eebea5db6572ed2b3fa290b330bca304
3
  size 6182614
predict.py CHANGED
@@ -1,4 +1,4 @@
1
- """Hybrid v4: AR for Pong, direct 8-frame for Sonic/PP with TTA."""
2
  import sys
3
  import os
4
  import numpy as np
@@ -11,6 +11,12 @@ CONTEXT_FRAMES = 8
11
  PRED_FRAMES = 8
12
  DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
13
 
 
 
 
 
 
 
14
 
15
  def detect_game(context_frames: np.ndarray) -> str:
16
  first_8 = context_frames[:CONTEXT_FRAMES]
@@ -26,65 +32,56 @@ def detect_game(context_frames: np.ndarray) -> str:
26
  return "sonic"
27
 
28
 
29
- class HybridModels:
30
- def __init__(self):
31
- self.models = {}
32
- self.direct_cache = None # Cache for direct 8-frame predictions
33
  self.cache_step = 0
34
 
35
  def reset_cache(self):
36
- self.direct_cache = None
37
  self.cache_step = 0
38
 
39
 
40
  def load_model(model_dir: str):
41
- hybrid = HybridModels()
42
-
43
- # Pong: AR model (3 outputs)
44
- pong = UNet(in_channels=24, out_channels=3,
45
- enc_channels=(32, 64, 128), bottleneck_channels=128,
46
- upsample_mode="bilinear").to(DEVICE)
47
- sd = torch.load(os.path.join(model_dir, "model_pong.pt"),
48
- map_location=DEVICE, weights_only=True)
49
- pong.load_state_dict({k: v.float() for k, v in sd.items()})
50
- pong.eval()
51
- hybrid.models["pong"] = pong
52
-
53
- # Sonic: direct 8-frame model (24 outputs)
54
- sonic = UNet(in_channels=24, out_channels=24,
55
- enc_channels=(48, 96, 192), bottleneck_channels=256,
56
- upsample_mode="bilinear").to(DEVICE)
57
- sd = torch.load(os.path.join(model_dir, "model_sonic.pt"),
58
- map_location=DEVICE, weights_only=True)
59
- sonic.load_state_dict({k: v.float() for k, v in sd.items()})
60
- sonic.eval()
61
- hybrid.models["sonic"] = sonic
62
-
63
- # PP: direct 8-frame model (24 outputs)
64
- pp = UNet(in_channels=24, out_channels=24,
65
- enc_channels=(32, 64, 128), bottleneck_channels=192,
66
- upsample_mode="bilinear").to(DEVICE)
67
- sd = torch.load(os.path.join(model_dir, "model_pole_position.pt"),
68
- map_location=DEVICE, weights_only=True)
69
- pp.load_state_dict({k: v.float() for k, v in sd.items()})
70
- pp.eval()
71
- hybrid.models["pole_position"] = pp
72
-
73
- return hybrid
74
 
75
 
76
  def _predict_8frames(model, context_tensor, last_tensor):
77
  output = model(context_tensor) # (1, 24, 64, 64)
78
  residuals = output.reshape(1, PRED_FRAMES, 3, 64, 64)
79
  last_expanded = last_tensor.unsqueeze(1).expand_as(residuals)
80
- return torch.clamp(last_expanded + residuals, 0, 1)
81
 
82
 
83
- def predict_next_frame(hybrid, context_frames: np.ndarray) -> np.ndarray:
84
- game = detect_game(context_frames)
85
- model = hybrid.models[game]
86
  n = len(context_frames)
87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  if n < CONTEXT_FRAMES:
89
  padding = np.stack([context_frames[0]] * (CONTEXT_FRAMES - n), axis=0)
90
  frames = np.concatenate([padding, context_frames], axis=0)
@@ -98,50 +95,32 @@ def predict_next_frame(hybrid, context_frames: np.ndarray) -> np.ndarray:
98
  last_frame = frames_norm[-1]
99
  last_frame_t = np.transpose(last_frame, (2, 0, 1))[np.newaxis]
100
 
101
- if game == "pong":
102
- # AR prediction for Pong (no TTA, no caching)
103
- with torch.no_grad():
104
- context_tensor = torch.from_numpy(context).to(DEVICE)
105
- last_tensor = torch.from_numpy(last_frame_t).to(DEVICE)
106
- residual = model(context_tensor)
107
- predicted = torch.clamp(last_tensor + residual, 0, 1)
108
 
109
- predicted_np = predicted[0].cpu().numpy()
110
- predicted_np = np.transpose(predicted_np, (1, 2, 0))
111
- predicted_np = (predicted_np * 255).clip(0, 255).astype(np.uint8)
112
- return predicted_np
113
 
114
- else:
115
- # Direct 8-frame for Sonic and PP with caching
116
- if hybrid.direct_cache is not None and n > CONTEXT_FRAMES and hybrid.cache_step < PRED_FRAMES:
117
- result = hybrid.direct_cache[hybrid.cache_step]
118
- hybrid.cache_step += 1
119
- if hybrid.cache_step >= PRED_FRAMES:
120
- hybrid.reset_cache()
121
- return result
122
-
123
- # New window: predict all 8 frames with TTA
124
- hybrid.reset_cache()
125
- with torch.no_grad():
126
- context_tensor = torch.from_numpy(context).to(DEVICE)
127
- last_tensor = torch.from_numpy(last_frame_t).to(DEVICE)
128
-
129
- predicted_orig = _predict_8frames(model, context_tensor, last_tensor)
130
-
131
- # TTA: horizontal flip
132
  context_flipped = torch.flip(context_tensor, dims=[3])
133
  last_flipped = torch.flip(last_tensor, dims=[3])
134
  predicted_flipped = _predict_8frames(model, context_flipped, last_flipped)
135
- predicted_flipped = torch.flip(predicted_flipped, dims=[4]) # flip width in (1,8,3,H,W)
 
136
  predicted = (predicted_orig + predicted_flipped) / 2.0
137
 
138
- predicted_np = predicted[0].cpu().numpy() # (8, 3, 64, 64)
139
- hybrid.direct_cache = []
140
- for i in range(PRED_FRAMES):
141
- frame = np.transpose(predicted_np[i], (1, 2, 0))
142
- frame = (frame * 255).clip(0, 255).astype(np.uint8)
143
- hybrid.direct_cache.append(frame)
144
 
145
- result = hybrid.direct_cache[hybrid.cache_step]
146
- hybrid.cache_step += 1
147
- return result
 
1
+ """Direct 8-frame prediction for all games with TTA."""
2
  import sys
3
  import os
4
  import numpy as np
 
11
  PRED_FRAMES = 8
12
  DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
13
 
14
+ GAME_CONFIGS = {
15
+ "pong": {"enc_channels": (32, 64, 128), "bottleneck": 128},
16
+ "sonic": {"enc_channels": (48, 96, 192), "bottleneck": 256},
17
+ "pole_position": {"enc_channels": (32, 64, 128), "bottleneck": 192},
18
+ }
19
+
20
 
21
  def detect_game(context_frames: np.ndarray) -> str:
22
  first_8 = context_frames[:CONTEXT_FRAMES]
 
32
  return "sonic"
33
 
34
 
35
+ class ModelCache:
36
+ def __init__(self, models):
37
+ self.models = models
38
+ self.cached_predictions = None
39
  self.cache_step = 0
40
 
41
  def reset_cache(self):
42
+ self.cached_predictions = None
43
  self.cache_step = 0
44
 
45
 
46
  def load_model(model_dir: str):
47
+ models = {}
48
+ for game, cfg in GAME_CONFIGS.items():
49
+ model = UNet(in_channels=24, out_channels=24,
50
+ enc_channels=cfg["enc_channels"],
51
+ bottleneck_channels=cfg["bottleneck"],
52
+ upsample_mode="bilinear").to(DEVICE)
53
+ state_dict = torch.load(os.path.join(model_dir, f"model_{game}.pt"),
54
+ map_location=DEVICE, weights_only=True)
55
+ state_dict = {k: v.float() for k, v in state_dict.items()}
56
+ model.load_state_dict(state_dict)
57
+ model.eval()
58
+ models[game] = model
59
+ return ModelCache(models)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  def _predict_8frames(model, context_tensor, last_tensor):
63
  output = model(context_tensor) # (1, 24, 64, 64)
64
  residuals = output.reshape(1, PRED_FRAMES, 3, 64, 64)
65
  last_expanded = last_tensor.unsqueeze(1).expand_as(residuals)
66
+ return torch.clamp(last_expanded + residuals, 0, 1) # (1, 8, 3, 64, 64)
67
 
68
 
69
+ def predict_next_frame(cache, context_frames: np.ndarray) -> np.ndarray:
 
 
70
  n = len(context_frames)
71
 
72
+ # If cache exists and context grew (AR rollout), return next cached frame
73
+ if cache.cached_predictions is not None and n > CONTEXT_FRAMES and cache.cache_step < PRED_FRAMES:
74
+ result = cache.cached_predictions[cache.cache_step]
75
+ cache.cache_step += 1
76
+ if cache.cache_step >= PRED_FRAMES:
77
+ cache.reset_cache()
78
+ return result
79
+
80
+ # New window: predict all 8 frames
81
+ cache.reset_cache()
82
+ game = detect_game(context_frames)
83
+ model = cache.models[game]
84
+
85
  if n < CONTEXT_FRAMES:
86
  padding = np.stack([context_frames[0]] * (CONTEXT_FRAMES - n), axis=0)
87
  frames = np.concatenate([padding, context_frames], axis=0)
 
95
  last_frame = frames_norm[-1]
96
  last_frame_t = np.transpose(last_frame, (2, 0, 1))[np.newaxis]
97
 
98
+ with torch.no_grad():
99
+ context_tensor = torch.from_numpy(context).to(DEVICE)
100
+ last_tensor = torch.from_numpy(last_frame_t).to(DEVICE)
 
 
 
 
101
 
102
+ predicted_orig = _predict_8frames(model, context_tensor, last_tensor)
 
 
 
103
 
104
+ if game == "pong":
105
+ # Pong: no TTA (asymmetric)
106
+ predicted = predicted_orig
107
+ else:
108
+ # TTA: horizontal flip (dim=3 is width for (B, T, C, H, W) reshaped from (B, 24, H, W))
109
+ # But we work on (1, 24, H, W) context - flip along dim 3 (width)
 
 
 
 
 
 
 
 
 
 
 
 
110
  context_flipped = torch.flip(context_tensor, dims=[3])
111
  last_flipped = torch.flip(last_tensor, dims=[3])
112
  predicted_flipped = _predict_8frames(model, context_flipped, last_flipped)
113
+ # Flip back: predicted_flipped is (1, 8, 3, H, W), flip width dim=4
114
+ predicted_flipped = torch.flip(predicted_flipped, dims=[4])
115
  predicted = (predicted_orig + predicted_flipped) / 2.0
116
 
117
+ predicted_np = predicted[0].cpu().numpy() # (8, 3, 64, 64)
118
+ cache.cached_predictions = []
119
+ for i in range(PRED_FRAMES):
120
+ frame = np.transpose(predicted_np[i], (1, 2, 0))
121
+ frame = (frame * 255).clip(0, 255).astype(np.uint8)
122
+ cache.cached_predictions.append(frame)
123
 
124
+ result = cache.cached_predictions[cache.cache_step]
125
+ cache.cache_step += 1
126
+ return result
train.log CHANGED
@@ -1,118 +1,152 @@
1
- [2026-04-11 17:22:57] Starting direct 8-frame training for 2026-04-11-180000-direct-8frame
2
- [2026-04-11 17:22:57] Device: cuda
3
- [2026-04-11 17:22:57] === pong ===
4
- [2026-04-11 17:22:57] pong: 1,199,224 params (2.3 MB fp16)
5
- [2026-04-11 17:22:58] pong train: 8194 seqs (len=16)
6
- [2026-04-11 17:22:58] pong val: 964 seqs (len=16)
7
- [2026-04-11 17:23:19] pong E1/100 | T:0.261624(S:0.6295) V:0.246500(S:0.6510) LR:3.00e-04
8
- [2026-04-11 17:23:38] pong E2/100 | T:0.222204(S:0.6854) V:0.215782(S:0.6944) LR:3.00e-04
9
- [2026-04-11 17:23:58] pong E3/100 | T:0.189432(S:0.7318) V:0.196561(S:0.7216) LR:2.99e-04
10
- [2026-04-11 17:24:16] pong E4/100 | T:0.165138(S:0.7663) V:0.181374(S:0.7430) LR:2.99e-04
11
- [2026-04-11 17:24:35] pong E5/100 | T:0.146892(S:0.7921) V:0.168277(S:0.7617) LR:2.98e-04
12
- [2026-04-11 17:24:55] pong E6/100 | T:0.133788(S:0.8107) V:0.160231(S:0.7730) LR:2.97e-04
13
- [2026-04-11 17:25:16] pong E7/100 | T:0.122975(S:0.8260) V:0.151815(S:0.7850) LR:2.96e-04
14
- [2026-04-11 17:25:55] pong E9/100 | T:0.108118(S:0.8471) V:0.145642(S:0.7936) LR:2.94e-04
15
- [2026-04-11 17:26:16] pong E10/100 | T:0.102042(S:0.8557) V:0.145171(S:0.7944) LR:2.93e-04
16
- [2026-04-11 17:26:35] pong E11/100 | T:0.097010(S:0.8628) V:0.137783(S:0.8048) LR:2.91e-04
17
- [2026-04-11 17:27:16] pong E13/100 | T:0.088259(S:0.8752) V:0.133496(S:0.8109) LR:2.88e-04
18
- [2026-04-11 17:27:36] pong E14/100 | T:0.085017(S:0.8798) V:0.128416(S:0.8181) LR:2.86e-04
19
- [2026-04-11 17:28:54] pong E18/100 | T:0.073576(S:0.8960) V:0.125769(S:0.8218) LR:2.77e-04
20
- [2026-04-11 17:29:34] pong E20/100 | T:0.069607(S:0.9016) V:0.125478(S:0.8222) LR:2.71e-04
21
- [2026-04-11 17:30:34] pong E23/100 | T:0.064038(S:0.9095) V:0.123089(S:0.8256) LR:2.63e-04
22
- [2026-04-11 17:31:15] pong E25/100 | T:0.061200(S:0.9135) V:0.121373(S:0.8280) LR:2.56e-04
23
- [2026-04-11 17:31:34] pong E26/100 | T:0.060173(S:0.9150) V:0.120411(S:0.8294) LR:2.53e-04
24
- [2026-04-11 17:31:53] pong E27/100 | T:0.058330(S:0.9176) V:0.119902(S:0.8300) LR:2.49e-04
25
- [2026-04-11 17:32:33] pong E29/100 | T:0.056276(S:0.9205) V:0.118473(S:0.8321) LR:2.42e-04
26
- [2026-04-11 17:32:53] pong E30/100 | T:0.054990(S:0.9223) V:0.117756(S:0.8331) LR:2.38e-04
27
- [2026-04-11 17:33:56] pong E33/100 | T:0.051766(S:0.9269) V:0.116454(S:0.8349) LR:2.27e-04
28
- [2026-04-11 17:34:37] pong E35/100 | T:0.050350(S:0.9289) V:0.116344(S:0.8351) LR:2.18e-04
29
- [2026-04-11 17:34:58] pong E36/100 | T:0.048892(S:0.9309) V:0.115702(S:0.8360) LR:2.14e-04
30
- [2026-04-11 17:35:41] pong E38/100 | T:0.047967(S:0.9322) V:0.115106(S:0.8368) LR:2.06e-04
31
- [2026-04-11 17:36:23] pong E40/100 | T:0.045971(S:0.9351) V:0.113090(S:0.8397) LR:1.97e-04
32
- [2026-04-11 17:36:42] pong E41/100 | T:0.045044(S:0.9364) V:0.112823(S:0.8400) LR:1.92e-04
33
- [2026-04-11 17:37:03] pong E42/100 | T:0.044532(S:0.9371) V:0.112635(S:0.8403) LR:1.88e-04
34
- [2026-04-11 17:38:03] pong E45/100 | T:0.042640(S:0.9398) V:0.111960(S:0.8413) LR:1.74e-04
35
- [2026-04-11 17:38:42] pong E47/100 | T:0.041282(S:0.9417) V:0.111201(S:0.8423) LR:1.65e-04
36
- [2026-04-11 17:39:02] pong E48/100 | T:0.040975(S:0.9421) V:0.111088(S:0.8425) LR:1.60e-04
37
- [2026-04-11 17:39:42] pong E50/100 | T:0.039824(S:0.9438) V:0.110872(S:0.8428) LR:1.50e-04
38
- [2026-04-11 17:40:22] pong E52/100 | T:0.038633(S:0.9455) V:0.109695(S:0.8445) LR:1.41e-04
39
- [2026-04-11 17:41:02] pong E54/100 | T:0.037921(S:0.9465) V:0.109453(S:0.8448) LR:1.32e-04
40
- [2026-04-11 17:41:56] pong E57/100 | T:0.036545(S:0.9484) V:0.109087(S:0.8453) LR:1.18e-04
41
- [2026-04-11 17:42:17] pong E58/100 | T:0.035855(S:0.9494) V:0.109036(S:0.8454) LR:1.13e-04
42
- [2026-04-11 17:42:36] pong E59/100 | T:0.035576(S:0.9498) V:0.108473(S:0.8462) LR:1.09e-04
43
- [2026-04-11 17:42:56] pong E60/100 | T:0.035289(S:0.9502) V:0.108379(S:0.8463) LR:1.04e-04
44
- [2026-04-11 17:43:35] pong E62/100 | T:0.034419(S:0.9514) V:0.108306(S:0.8464) LR:9.55e-05
45
- [2026-04-11 17:43:55] pong E63/100 | T:0.034142(S:0.9518) V:0.107726(S:0.8472) LR:9.11e-05
46
- [2026-04-11 17:44:33] pong E65/100 | T:0.033535(S:0.9527) V:0.107617(S:0.8474) LR:8.26e-05
47
- [2026-04-11 17:45:48] pong E69/100 | T:0.032286(S:0.9544) V:0.107517(S:0.8475) LR:6.65e-05
48
- [2026-04-11 17:46:06] pong E70/100 | T:0.031978(S:0.9549) V:0.107445(S:0.8476) LR:6.26e-05
49
- [2026-04-11 17:46:27] pong E71/100 | T:0.031772(S:0.9552) V:0.107240(S:0.8479) LR:5.89e-05
50
- [2026-04-11 17:46:46] pong E72/100 | T:0.031589(S:0.9554) V:0.106995(S:0.8483) LR:5.52e-05
51
- [2026-04-11 17:47:06] pong E73/100 | T:0.031315(S:0.9558) V:0.106564(S:0.8489) LR:5.16e-05
52
- [2026-04-11 17:49:21] pong E80/100 | T:0.030090(S:0.9576) V:0.106367(S:0.8492) LR:2.96e-05
53
- [2026-04-11 17:50:40] pong E84/100 | T:0.029537(S:0.9583) V:0.106164(S:0.8494) LR:1.95e-05
54
- [2026-04-11 17:51:00] pong E85/100 | T:0.029495(S:0.9584) V:0.106157(S:0.8494) LR:1.73e-05
55
- [2026-04-11 17:51:40] pong E87/100 | T:0.029253(S:0.9587) V:0.106032(S:0.8496) LR:1.33e-05
56
- [2026-04-11 17:52:00] pong E88/100 | T:0.029200(S:0.9588) V:0.105951(S:0.8497) LR:1.15e-05
57
- [2026-04-11 17:52:39] pong E90/100 | T:0.029051(S:0.9590) V:0.106003(S:0.8497) LR:8.32e-06
58
- [2026-04-11 17:53:00] pong E91/100 | T:0.028990(S:0.9591) V:0.105951(S:0.8497) LR:6.94e-06
59
- [2026-04-11 17:55:39] pong E99/100 | T:0.028765(S:0.9594) V:0.105859(S:0.8499) LR:1.07e-06
60
- [2026-04-11 17:55:59] pong E100/100 | T:0.028750(S:0.9595) V:0.106039(S:0.8496) LR:1.00e-06
61
- [2026-04-11 17:55:59] pong done. Best: 0.105859
62
- [2026-04-11 17:55:59] === pole_position ===
63
- [2026-04-11 17:55:59] pole_position: 1,465,848 params (2.8 MB fp16)
64
- [2026-04-11 17:56:00] pole_position train: 4097 seqs (len=16)
65
- [2026-04-11 17:56:00] pole_position val: 482 seqs (len=16)
66
- [2026-04-11 17:56:10] pole_position E1/100 | T:0.075590(S:0.9035) V:0.057663(S:0.9277) LR:3.00e-04
67
- [2026-04-11 17:56:20] pole_position E2/100 | T:0.064522(S:0.9184) V:0.053095(S:0.9336) LR:3.00e-04
68
- [2026-04-11 17:56:30] pole_position E3/100 | T:0.060081(S:0.9243) V:0.051676(S:0.9352) LR:2.99e-04
69
- [2026-04-11 17:56:40] pole_position E4/100 | T:0.057492(S:0.9276) V:0.049574(S:0.9381) LR:2.99e-04
70
- [2026-04-11 17:56:50] pole_position E5/100 | T:0.055706(S:0.9299) V:0.049319(S:0.9386) LR:2.98e-04
71
- [2026-04-11 17:57:01] pole_position E6/100 | T:0.053870(S:0.9323) V:0.046328(S:0.9425) LR:2.97e-04
72
- [2026-04-11 17:57:21] pole_position E8/100 | T:0.050747(S:0.9364) V:0.045251(S:0.9438) LR:2.95e-04
73
- [2026-04-11 17:57:31] pole_position E9/100 | T:0.049606(S:0.9379) V:0.044027(S:0.9455) LR:2.94e-04
74
- [2026-04-11 17:57:41] pole_position E10/100 | T:0.048376(S:0.9395) V:0.048385(S:0.9398) LR:2.93e-04
75
- [2026-04-11 17:58:02] pole_position E12/100 | T:0.046456(S:0.9420) V:0.043792(S:0.9456) LR:2.90e-04
76
- [2026-04-11 17:58:23] pole_position E14/100 | T:0.044549(S:0.9445) V:0.042208(S:0.9474) LR:2.86e-04
77
- [2026-04-11 17:58:53] pole_position E17/100 | T:0.042305(S:0.9475) V:0.041426(S:0.9485) LR:2.79e-04
78
- [2026-04-11 17:59:24] pole_position E20/100 | T:0.040529(S:0.9498) V:0.042968(S:0.9464) LR:2.71e-04
79
- [2026-04-11 18:01:03] pole_position E30/100 | T:0.036013(S:0.9557) V:0.042198(S:0.9472) LR:2.38e-04
80
- [2026-04-11 18:02:43] pole_position E40/100 | T:0.033191(S:0.9594) V:0.042161(S:0.9472) LR:1.97e-04
81
- [2026-04-11 18:04:25] pole_position E50/100 | T:0.030915(S:0.9624) V:0.042456(S:0.9467) LR:1.50e-04
82
- [2026-04-11 18:06:07] pole_position E60/100 | T:0.029315(S:0.9645) V:0.042134(S:0.9472) LR:1.04e-04
83
- [2026-04-11 18:07:47] pole_position E70/100 | T:0.028091(S:0.9661) V:0.042533(S:0.9466) LR:6.26e-05
84
- [2026-04-11 18:09:29] pole_position E80/100 | T:0.027237(S:0.9672) V:0.042501(S:0.9466) LR:2.96e-05
85
- [2026-04-11 18:11:08] pole_position E90/100 | T:0.026795(S:0.9678) V:0.042639(S:0.9464) LR:8.32e-06
86
- [2026-04-11 18:12:49] pole_position E100/100 | T:0.026658(S:0.9680) V:0.042839(S:0.9462) LR:1.00e-06
87
- [2026-04-11 18:12:49] pole_position done. Best: 0.041426
88
- [2026-04-11 18:12:49] === sonic ===
89
- [2026-04-11 18:12:49] sonic: 3,071,016 params (5.9 MB fp16)
90
- [2026-04-11 18:12:54] sonic train: 30848 seqs (len=16)
91
- [2026-04-11 18:12:54] sonic val: 3856 seqs (len=16)
92
- [2026-04-11 18:14:11] sonic E1/100 | T:0.175591(S:0.7765) V:0.157856(S:0.8006) LR:3.00e-04
93
- [2026-04-11 18:15:26] sonic E2/100 | T:0.159479(S:0.7978) V:0.149752(S:0.8110) LR:3.00e-04
94
- [2026-04-11 18:16:41] sonic E3/100 | T:0.153539(S:0.8056) V:0.147334(S:0.8155) LR:2.99e-04
95
- [2026-04-11 18:17:56] sonic E4/100 | T:0.149574(S:0.8108) V:0.144793(S:0.8177) LR:2.99e-04
96
- [2026-04-11 18:19:11] sonic E5/100 | T:0.145852(S:0.8157) V:0.143262(S:0.8198) LR:2.98e-04
97
- [2026-04-11 18:20:26] sonic E6/100 | T:0.142932(S:0.8196) V:0.142910(S:0.8208) LR:2.97e-04
98
- [2026-04-11 18:22:55] sonic E8/100 | T:0.137437(S:0.8268) V:0.140100(S:0.8241) LR:2.95e-04
99
- [2026-04-11 18:25:24] sonic E10/100 | T:0.132863(S:0.8329) V:0.137565(S:0.8273) LR:2.93e-04
100
- [2026-04-11 18:31:35] sonic E15/100 | T:0.123970(S:0.8445) V:0.137460(S:0.8275) LR:2.84e-04
101
- [2026-04-11 18:35:22] sonic E18/100 | T:0.119989(S:0.8498) V:0.137060(S:0.8281) LR:2.77e-04
102
- [2026-04-11 18:36:34] sonic E19/100 | T:0.118824(S:0.8513) V:0.137037(S:0.8283) LR:2.75e-04
103
- [2026-04-11 18:37:49] sonic E20/100 | T:0.117435(S:0.8531) V:0.137332(S:0.8278) LR:2.72e-04
104
- [2026-04-11 18:39:04] sonic E21/100 | T:0.116390(S:0.8545) V:0.135734(S:0.8299) LR:2.70e-04
105
- [2026-04-11 18:50:11] sonic E30/100 | T:0.108528(S:0.8649) V:0.139606(S:0.8249) LR:2.40e-04
106
- [2026-04-11 19:02:35] sonic E40/100 | T:0.102536(S:0.8727) V:0.138633(S:0.8262) LR:2.00e-04
107
- [2026-04-11 19:14:57] sonic E50/100 | T:0.098295(S:0.8783) V:0.139113(S:0.8252) LR:1.55e-04
108
- [2026-04-11 19:27:10] sonic E60/100 | T:0.095048(S:0.8826) V:0.138777(S:0.8255) LR:1.10e-04
109
- [2026-04-11 19:39:39] sonic E70/100 | T:0.092648(S:0.8857) V:0.141122(S:0.8224) LR:6.98e-05
110
- [2026-04-11 19:52:02] sonic E80/100 | T:0.091056(S:0.8878) V:0.140701(S:0.8231) LR:3.77e-05
111
- [2026-04-11 20:04:24] sonic E90/100 | T:0.090060(S:0.8891) V:0.141902(S:0.8214) LR:1.71e-05
112
- [2026-04-11 20:16:49] sonic E100/100 | T:0.089632(S:0.8897) V:0.141938(S:0.8214) LR:1.00e-05
113
- [2026-04-11 20:16:49] sonic done. Best: 0.135734
114
- [2026-04-11 20:16:49] pong: 2.3 MB
115
- [2026-04-11 20:16:49] pole_position: 2.8 MB
116
- [2026-04-11 20:16:49] sonic: 5.9 MB
117
- [2026-04-11 20:16:49] Total: 11.1 MB
118
- [2026-04-11 20:16:49] Training complete!
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2026-04-11 20:37:53] Starting improved direct 8-frame training for 2026-04-11-210000-direct-improved
2
+ [2026-04-11 20:37:53] Device: cuda
3
+ [2026-04-11 20:37:53] === pong ===
4
+ [2026-04-11 20:37:53] pong: 1,199,224 params (2.3 MB fp16)
5
+ [2026-04-11 20:37:54] pong train: 8194 seqs (len=16)
6
+ [2026-04-11 20:37:54] pong val: 964 seqs (len=16)
7
+ [2026-04-11 20:38:15] pong E1/150 | T:0.245151(S:0.6311) V:0.225469(S:0.6589) LR:2.00e-04
8
+ [2026-04-11 20:38:35] pong E2/150 | T:0.207902(S:0.6846) V:0.207636(S:0.6836) LR:2.00e-04
9
+ [2026-04-11 20:38:55] pong E3/150 | T:0.183334(S:0.7217) V:0.184517(S:0.7193) LR:2.00e-04
10
+ [2026-04-11 20:39:15] pong E4/150 | T:0.162890(S:0.7525) V:0.170139(S:0.7405) LR:2.00e-04
11
+ [2026-04-11 20:39:35] pong E5/150 | T:0.148245(S:0.7747) V:0.168455(S:0.7455) LR:1.99e-04
12
+ [2026-04-11 20:39:54] pong E6/150 | T:0.134784(S:0.7951) V:0.155488(S:0.7639) LR:1.99e-04
13
+ [2026-04-11 20:40:15] pong E7/150 | T:0.125337(S:0.8093) V:0.153139(S:0.7670) LR:1.99e-04
14
+ [2026-04-11 20:40:35] pong E8/150 | T:0.117548(S:0.8213) V:0.140387(S:0.7865) LR:1.99e-04
15
+ [2026-04-11 20:40:55] pong E9/150 | T:0.110727(S:0.8316) V:0.139567(S:0.7879) LR:1.98e-04
16
+ [2026-04-11 20:41:15] pong E10/150 | T:0.105040(S:0.8404) V:0.135133(S:0.7943) LR:1.98e-04
17
+ [2026-04-11 20:41:55] pong E12/150 | T:0.096706(S:0.8530) V:0.133117(S:0.7976) LR:1.97e-04
18
+ [2026-04-11 20:42:15] pong E13/150 | T:0.093069(S:0.8586) V:0.128657(S:0.8049) LR:1.96e-04
19
+ [2026-04-11 20:42:35] pong E14/150 | T:0.089584(S:0.8641) V:0.127223(S:0.8071) LR:1.96e-04
20
+ [2026-04-11 20:42:55] pong E15/150 | T:0.086566(S:0.8686) V:0.123897(S:0.8117) LR:1.95e-04
21
+ [2026-04-11 20:43:35] pong E17/150 | T:0.081673(S:0.8762) V:0.123559(S:0.8119) LR:1.94e-04
22
+ [2026-04-11 20:44:15] pong E19/150 | T:0.076816(S:0.8836) V:0.120578(S:0.8168) LR:1.92e-04
23
+ [2026-04-11 20:44:35] pong E20/150 | T:0.075138(S:0.8862) V:0.123831(S:0.8129) LR:1.91e-04
24
+ [2026-04-11 20:44:54] pong E21/150 | T:0.072953(S:0.8897) V:0.120207(S:0.8171) LR:1.91e-04
25
+ [2026-04-11 20:45:14] pong E22/150 | T:0.071339(S:0.8922) V:0.118498(S:0.8202) LR:1.90e-04
26
+ [2026-04-11 20:45:35] pong E23/150 | T:0.069781(S:0.8947) V:0.117458(S:0.8223) LR:1.89e-04
27
+ [2026-04-11 20:46:12] pong E25/150 | T:0.067305(S:0.8984) V:0.116407(S:0.8233) LR:1.87e-04
28
+ [2026-04-11 20:46:32] pong E26/150 | T:0.065223(S:0.9018) V:0.115602(S:0.8242) LR:1.86e-04
29
+ [2026-04-11 20:47:12] pong E28/150 | T:0.062886(S:0.9054) V:0.113464(S:0.8277) LR:1.83e-04
30
+ [2026-04-11 20:47:32] pong E29/150 | T:0.061637(S:0.9073) V:0.112811(S:0.8285) LR:1.82e-04
31
+ [2026-04-11 20:47:51] pong E30/150 | T:0.060839(S:0.9086) V:0.112722(S:0.8292) LR:1.81e-04
32
+ [2026-04-11 20:48:12] pong E31/150 | T:0.059712(S:0.9104) V:0.111062(S:0.8316) LR:1.80e-04
33
+ [2026-04-11 20:49:12] pong E34/150 | T:0.056734(S:0.9149) V:0.111023(S:0.8316) LR:1.76e-04
34
+ [2026-04-11 20:49:32] pong E35/150 | T:0.055712(S:0.9165) V:0.110123(S:0.8330) LR:1.74e-04
35
+ [2026-04-11 20:50:10] pong E37/150 | T:0.054400(S:0.9186) V:0.109606(S:0.8340) LR:1.72e-04
36
+ [2026-04-11 20:51:10] pong E40/150 | T:0.052566(S:0.9215) V:0.109744(S:0.8340) LR:1.67e-04
37
+ [2026-04-11 20:51:30] pong E41/150 | T:0.051662(S:0.9229) V:0.108173(S:0.8359) LR:1.66e-04
38
+ [2026-04-11 20:52:10] pong E43/150 | T:0.050829(S:0.9242) V:0.107573(S:0.8367) LR:1.62e-04
39
+ [2026-04-11 20:52:30] pong E44/150 | T:0.049584(S:0.9261) V:0.107344(S:0.8375) LR:1.61e-04
40
+ [2026-04-11 20:53:30] pong E47/150 | T:0.047870(S:0.9288) V:0.107087(S:0.8377) LR:1.56e-04
41
+ [2026-04-11 20:53:49] pong E48/150 | T:0.047106(S:0.9299) V:0.105825(S:0.8395) LR:1.54e-04
42
+ [2026-04-11 20:54:29] pong E50/150 | T:0.046352(S:0.9312) V:0.108601(S:0.8357) LR:1.50e-04
43
+ [2026-04-11 20:55:09] pong E52/150 | T:0.045529(S:0.9325) V:0.105138(S:0.8406) LR:1.47e-04
44
+ [2026-04-11 20:56:08] pong E55/150 | T:0.043897(S:0.9350) V:0.104684(S:0.8416) LR:1.41e-04
45
+ [2026-04-11 20:56:27] pong E56/150 | T:0.043453(S:0.9357) V:0.104668(S:0.8417) LR:1.39e-04
46
+ [2026-04-11 20:57:45] pong E60/150 | T:0.041694(S:0.9384) V:0.103771(S:0.8432) LR:1.31e-04
47
+ [2026-04-11 20:58:23] pong E62/150 | T:0.040995(S:0.9395) V:0.103378(S:0.8433) LR:1.27e-04
48
+ [2026-04-11 20:59:03] pong E64/150 | T:0.040430(S:0.9403) V:0.102376(S:0.8449) LR:1.23e-04
49
+ [2026-04-11 21:01:00] pong E70/150 | T:0.038175(S:0.9439) V:0.101971(S:0.8454) LR:1.11e-04
50
+ [2026-04-11 21:01:20] pong E71/150 | T:0.038048(S:0.9441) V:0.101782(S:0.8458) LR:1.09e-04
51
+ [2026-04-11 21:02:01] pong E73/150 | T:0.037274(S:0.9453) V:0.101483(S:0.8464) LR:1.05e-04
52
+ [2026-04-11 21:02:21] pong E74/150 | T:0.037082(S:0.9456) V:0.101132(S:0.8470) LR:1.03e-04
53
+ [2026-04-11 21:03:35] pong E78/150 | T:0.036125(S:0.9471) V:0.100967(S:0.8472) LR:9.43e-05
54
+ [2026-04-11 21:04:14] pong E80/150 | T:0.035617(S:0.9479) V:0.101149(S:0.8473) LR:9.01e-05
55
+ [2026-04-11 21:04:34] pong E81/150 | T:0.035287(S:0.9484) V:0.100887(S:0.8473) LR:8.80e-05
56
+ [2026-04-11 21:05:14] pong E83/150 | T:0.034890(S:0.9490) V:0.100673(S:0.8476) LR:8.39e-05
57
+ [2026-04-11 21:05:34] pong E84/150 | T:0.034546(S:0.9495) V:0.100503(S:0.8481) LR:8.19e-05
58
+ [2026-04-11 21:05:53] pong E85/150 | T:0.034332(S:0.9499) V:0.100085(S:0.8486) LR:7.98e-05
59
+ [2026-04-11 21:06:51] pong E88/150 | T:0.033905(S:0.9505) V:0.099703(S:0.8491) LR:7.37e-05
60
+ [2026-04-11 21:07:32] pong E90/150 | T:0.033352(S:0.9514) V:0.100154(S:0.8485) LR:6.98e-05
61
+ [2026-04-11 21:07:49] pong E91/150 | T:0.033275(S:0.9515) V:0.099463(S:0.8496) LR:6.78e-05
62
+ [2026-04-11 21:08:28] pong E93/150 | T:0.032808(S:0.9522) V:0.099426(S:0.8497) LR:6.39e-05
63
+ [2026-04-11 21:09:07] pong E95/150 | T:0.032401(S:0.9529) V:0.099274(S:0.8498) LR:6.00e-05
64
+ [2026-04-11 21:10:47] pong E100/150 | T:0.031693(S:0.9539) V:0.099102(S:0.8502) LR:5.07e-05
65
+ [2026-04-11 21:11:07] pong E101/150 | T:0.031556(S:0.9542) V:0.098989(S:0.8504) LR:4.90e-05
66
+ [2026-04-11 21:12:05] pong E104/150 | T:0.031188(S:0.9547) V:0.098818(S:0.8506) LR:4.37e-05
67
+ [2026-04-11 21:12:26] pong E105/150 | T:0.031013(S:0.9550) V:0.098630(S:0.8508) LR:4.20e-05
68
+ [2026-04-11 21:12:45] pong E106/150 | T:0.030918(S:0.9552) V:0.098413(S:0.8511) LR:4.03e-05
69
+ [2026-04-11 21:14:05] pong E110/150 | T:0.030445(S:0.9559) V:0.099033(S:0.8506) LR:3.39e-05
70
+ [2026-04-11 21:15:25] pong E114/150 | T:0.030015(S:0.9566) V:0.098366(S:0.8513) LR:2.80e-05
71
+ [2026-04-11 21:16:25] pong E117/150 | T:0.029792(S:0.9569) V:0.098095(S:0.8517) LR:2.38e-05
72
+ [2026-04-11 21:17:24] pong E120/150 | T:0.029565(S:0.9573) V:0.098241(S:0.8515) LR:2.00e-05
73
+ [2026-04-11 21:19:24] pong E126/150 | T:0.029172(S:0.9579) V:0.098066(S:0.8518) LR:1.33e-05
74
+ [2026-04-11 21:20:03] pong E128/150 | T:0.029068(S:0.9580) V:0.098040(S:0.8518) LR:1.14e-05
75
+ [2026-04-11 21:20:43] pong E130/150 | T:0.029001(S:0.9581) V:0.098031(S:0.8518) LR:9.60e-06
76
+ [2026-04-11 21:21:03] pong E131/150 | T:0.028939(S:0.9582) V:0.097892(S:0.8521) LR:8.77e-06
77
+ [2026-04-11 21:24:01] pong E140/150 | T:0.028630(S:0.9587) V:0.097958(S:0.8520) LR:3.17e-06
78
+ [2026-04-11 21:25:19] pong E144/150 | T:0.028567(S:0.9588) V:0.097818(S:0.8522) LR:1.78e-06
79
+ [2026-04-11 21:27:18] pong E150/150 | T:0.028536(S:0.9589) V:0.097904(S:0.8521) LR:1.00e-06
80
+ [2026-04-11 21:27:18] pong done. Best: 0.097818
81
+ [2026-04-11 21:27:18] === pole_position ===
82
+ [2026-04-11 21:27:18] pole_position: 1,465,848 params (2.8 MB fp16)
83
+ [2026-04-11 21:27:19] pole_position train: 4097 seqs (len=16)
84
+ [2026-04-11 21:27:19] pole_position val: 482 seqs (len=16)
85
+ [2026-04-11 21:27:29] pole_position E1/150 | T:0.072483(S:0.9013) V:0.055104(S:0.9272) LR:2.00e-04
86
+ [2026-04-11 21:27:39] pole_position E2/150 | T:0.060683(S:0.9178) V:0.049558(S:0.9337) LR:2.00e-04
87
+ [2026-04-11 21:27:49] pole_position E3/150 | T:0.056482(S:0.9234) V:0.049681(S:0.9330) LR:2.00e-04
88
+ [2026-04-11 21:28:00] pole_position E4/150 | T:0.053962(S:0.9268) V:0.047040(S:0.9371) LR:2.00e-04
89
+ [2026-04-11 21:28:09] pole_position E5/150 | T:0.051783(S:0.9298) V:0.043891(S:0.9410) LR:1.99e-04
90
+ [2026-04-11 21:28:39] pole_position E8/150 | T:0.047291(S:0.9360) V:0.042535(S:0.9431) LR:1.99e-04
91
+ [2026-04-11 21:28:48] pole_position E9/150 | T:0.046385(S:0.9372) V:0.041829(S:0.9440) LR:1.98e-04
92
+ [2026-04-11 21:28:58] pole_position E10/150 | T:0.045514(S:0.9385) V:0.042079(S:0.9438) LR:1.98e-04
93
+ [2026-04-11 21:29:09] pole_position E11/150 | T:0.044486(S:0.9399) V:0.040944(S:0.9449) LR:1.97e-04
94
+ [2026-04-11 21:29:47] pole_position E15/150 | T:0.041111(S:0.9447) V:0.039725(S:0.9465) LR:1.95e-04
95
+ [2026-04-11 21:30:37] pole_position E20/150 | T:0.038348(S:0.9487) V:0.038742(S:0.9477) LR:1.91e-04
96
+ [2026-04-11 21:30:46] pole_position E21/150 | T:0.037787(S:0.9495) V:0.038655(S:0.9481) LR:1.91e-04
97
+ [2026-04-11 21:31:18] pole_position E24/150 | T:0.036649(S:0.9511) V:0.038322(S:0.9481) LR:1.88e-04
98
+ [2026-04-11 21:32:18] pole_position E30/150 | T:0.034550(S:0.9541) V:0.038329(S:0.9484) LR:1.81e-04
99
+ [2026-04-11 21:33:18] pole_position E36/150 | T:0.033149(S:0.9561) V:0.038183(S:0.9480) LR:1.73e-04
100
+ [2026-04-11 21:33:59] pole_position E40/150 | T:0.032073(S:0.9577) V:0.038579(S:0.9475) LR:1.67e-04
101
+ [2026-04-11 21:34:09] pole_position E41/150 | T:0.031761(S:0.9581) V:0.037873(S:0.9485) LR:1.66e-04
102
+ [2026-04-11 21:34:19] pole_position E42/150 | T:0.031713(S:0.9582) V:0.036978(S:0.9498) LR:1.64e-04
103
+ [2026-04-11 21:35:39] pole_position E50/150 | T:0.030141(S:0.9604) V:0.038688(S:0.9470) LR:1.50e-04
104
+ [2026-04-11 21:37:19] pole_position E60/150 | T:0.028820(S:0.9623) V:0.038451(S:0.9473) LR:1.31e-04
105
+ [2026-04-11 21:39:00] pole_position E70/150 | T:0.027896(S:0.9636) V:0.038069(S:0.9478) LR:1.11e-04
106
+ [2026-04-11 21:40:41] pole_position E80/150 | T:0.026692(S:0.9653) V:0.038111(S:0.9476) LR:9.01e-05
107
+ [2026-04-11 21:42:22] pole_position E90/150 | T:0.025885(S:0.9665) V:0.037698(S:0.9482) LR:6.98e-05
108
+ [2026-04-11 21:44:01] pole_position E100/150 | T:0.025252(S:0.9674) V:0.038106(S:0.9475) LR:5.07e-05
109
+ [2026-04-11 21:45:42] pole_position E110/150 | T:0.024739(S:0.9681) V:0.037902(S:0.9479) LR:3.39e-05
110
+ [2026-04-11 21:47:24] pole_position E120/150 | T:0.024433(S:0.9685) V:0.037644(S:0.9482) LR:2.00e-05
111
+ [2026-04-11 21:49:05] pole_position E130/150 | T:0.024134(S:0.9690) V:0.037839(S:0.9479) LR:9.60e-06
112
+ [2026-04-11 21:50:45] pole_position E140/150 | T:0.024041(S:0.9691) V:0.037827(S:0.9479) LR:3.17e-06
113
+ [2026-04-11 21:52:25] pole_position E150/150 | T:0.023978(S:0.9692) V:0.037890(S:0.9478) LR:1.00e-06
114
+ [2026-04-11 21:52:25] pole_position done. Best: 0.036978
115
+ [2026-04-11 21:52:25] === sonic ===
116
+ [2026-04-11 21:52:25] sonic: 3,071,016 params (5.9 MB fp16)
117
+ [2026-04-11 21:52:29] sonic train: 30848 seqs (len=16)
118
+ [2026-04-11 21:52:30] sonic val: 3856 seqs (len=16)
119
+ [2026-04-11 21:53:45] sonic E1/150 | T:0.162348(S:0.7775) V:0.144778(S:0.8026) LR:2.00e-04
120
+ [2026-04-11 21:54:58] sonic E2/150 | T:0.146694(S:0.7991) V:0.136146(S:0.8135) LR:2.00e-04
121
+ [2026-04-11 21:56:13] sonic E3/150 | T:0.140699(S:0.8074) V:0.134994(S:0.8151) LR:2.00e-04
122
+ [2026-04-11 21:57:28] sonic E4/150 | T:0.136883(S:0.8127) V:0.131966(S:0.8195) LR:2.00e-04
123
+ [2026-04-11 21:58:43] sonic E5/150 | T:0.133509(S:0.8175) V:0.129399(S:0.8230) LR:1.99e-04
124
+ [2026-04-11 21:59:57] sonic E6/150 | T:0.130435(S:0.8218) V:0.128735(S:0.8233) LR:1.99e-04
125
+ [2026-04-11 22:01:14] sonic E7/150 | T:0.127966(S:0.8254) V:0.126909(S:0.8259) LR:1.99e-04
126
+ [2026-04-11 22:04:57] sonic E10/150 | T:0.121944(S:0.8340) V:0.124331(S:0.8295) LR:1.98e-04
127
+ [2026-04-11 22:06:11] sonic E11/150 | T:0.120293(S:0.8364) V:0.123743(S:0.8304) LR:1.97e-04
128
+ [2026-04-11 22:08:39] sonic E13/150 | T:0.117218(S:0.8409) V:0.122889(S:0.8311) LR:1.97e-04
129
+ [2026-04-11 22:14:48] sonic E18/150 | T:0.111090(S:0.8498) V:0.122588(S:0.8317) LR:1.93e-04
130
+ [2026-04-11 22:17:15] sonic E20/150 | T:0.109268(S:0.8525) V:0.125544(S:0.8273) LR:1.92e-04
131
+ [2026-04-11 22:20:54] sonic E23/150 | T:0.106768(S:0.8561) V:0.121705(S:0.8325) LR:1.89e-04
132
+ [2026-04-11 22:23:25] sonic E25/150 | T:0.105207(S:0.8584) V:0.121577(S:0.8323) LR:1.87e-04
133
+ [2026-04-11 22:27:00] sonic E28/150 | T:0.103225(S:0.8613) V:0.120523(S:0.8339) LR:1.84e-04
134
+ [2026-04-11 22:29:26] sonic E30/150 | T:0.102327(S:0.8626) V:0.123279(S:0.8299) LR:1.82e-04
135
+ [2026-04-11 22:41:41] sonic E40/150 | T:0.097330(S:0.8698) V:0.123097(S:0.8299) LR:1.69e-04
136
+ [2026-04-11 22:53:59] sonic E50/150 | T:0.093990(S:0.8746) V:0.124820(S:0.8272) LR:1.53e-04
137
+ [2026-04-11 23:06:25] sonic E60/150 | T:0.091507(S:0.8782) V:0.124273(S:0.8274) LR:1.34e-04
138
+ [2026-04-11 23:18:48] sonic E70/150 | T:0.089327(S:0.8813) V:0.123787(S:0.8284) LR:1.15e-04
139
+ [2026-04-11 23:31:12] sonic E80/150 | T:0.087458(S:0.8839) V:0.122982(S:0.8295) LR:9.51e-05
140
+ [2026-04-11 23:44:30] sonic E90/150 | T:0.085960(S:0.8861) V:0.123807(S:0.8280) LR:7.56e-05
141
+ [2026-04-11 23:57:54] sonic E100/150 | T:0.084800(S:0.8877) V:0.124093(S:0.8276) LR:5.75e-05
142
+ [2026-04-12 00:11:21] sonic E110/150 | T:0.083786(S:0.8892) V:0.124339(S:0.8272) LR:4.14e-05
143
+ [2026-04-12 00:25:17] sonic E120/150 | T:0.083098(S:0.8902) V:0.125028(S:0.8261) LR:2.81e-05
144
+ [2026-04-12 00:39:13] sonic E130/150 | T:0.082543(S:0.8910) V:0.124983(S:0.8261) LR:1.82e-05
145
+ [2026-04-12 00:53:09] sonic E140/150 | T:0.082184(S:0.8915) V:0.125446(S:0.8255) LR:1.21e-05
146
+ [2026-04-12 01:06:48] sonic E150/150 | T:0.082048(S:0.8917) V:0.124580(S:0.8267) LR:1.00e-05
147
+ [2026-04-12 01:06:48] sonic done. Best: 0.120523
148
+ [2026-04-12 01:06:48] pong: 2.3 MB
149
+ [2026-04-12 01:06:48] pole_position: 2.8 MB
150
+ [2026-04-12 01:06:48] sonic: 5.9 MB
151
+ [2026-04-12 01:06:48] Total: 11.1 MB
152
+ [2026-04-12 01:06:48] Training complete!