Upload folder using huggingface_hub

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 6.59 +/- 3.29
+      value: 9.61 +/- 3.87
       name: mean_reward
       verified: false
 ---

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d40d2c1f9be6c9ab846ede0cfe1dfc8111f3fb12d8ce097ea2f8ac0be13c286
-size 12260307
+oid sha256:79e97b3367ce9dc9128f480a280398d788ff31931d788a343c074eb468f8127b
+size 18296242

sf_log.txt

@@ -1205,3 +1205,142 @@ main_loop: 1077.6373
 [2024-11-06 21:59:35,953][00300] Avg episode rewards: #0: 12.392, true rewards: #0: 6.592
 [2024-11-06 21:59:35,954][00300] Avg episode reward: 12.392, avg true_objective: 6.592
 [2024-11-06 22:00:16,452][00300] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-11-06 22:00:27,843][00300] The model has been pushed to https://huggingface.co/mnneely/rl_course_vizdoom_health_gathering_supreme
+[2024-11-06 22:03:47,970][00300] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-11-06 22:03:47,972][00300] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-11-06 22:03:47,974][00300] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-11-06 22:03:47,976][00300] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-11-06 22:03:47,978][00300] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-11-06 22:03:47,980][00300] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-11-06 22:03:47,981][00300] Adding new argument 'max_num_frames'=1000000 that is not in the saved config file!
+[2024-11-06 22:03:47,982][00300] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-11-06 22:03:47,983][00300] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-11-06 22:03:47,984][00300] Adding new argument 'hf_repository'='mnneely/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-11-06 22:03:47,985][00300] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-11-06 22:03:47,987][00300] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-11-06 22:03:47,988][00300] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-11-06 22:03:47,989][00300] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-11-06 22:03:47,990][00300] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-11-06 22:03:48,002][00300] RunningMeanStd input shape: (3, 72, 128)
+[2024-11-06 22:03:48,004][00300] RunningMeanStd input shape: (1,)
+[2024-11-06 22:03:48,020][00300] ConvEncoder: input_channels=3
+[2024-11-06 22:03:48,058][00300] Conv encoder output size: 512
+[2024-11-06 22:03:48,060][00300] Policy head output size: 512
+[2024-11-06 22:03:48,077][00300] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-11-06 22:03:48,578][00300] Num frames 100...
+[2024-11-06 22:03:48,746][00300] Num frames 200...
+[2024-11-06 22:03:48,906][00300] Num frames 300...
+[2024-11-06 22:03:49,064][00300] Num frames 400...
+[2024-11-06 22:03:49,227][00300] Num frames 500...
+[2024-11-06 22:03:49,390][00300] Num frames 600...
+[2024-11-06 22:03:49,555][00300] Num frames 700...
+[2024-11-06 22:03:49,711][00300] Num frames 800...
+[2024-11-06 22:03:49,869][00300] Num frames 900...
+[2024-11-06 22:03:50,030][00300] Num frames 1000...
+[2024-11-06 22:03:50,194][00300] Num frames 1100...
+[2024-11-06 22:03:50,356][00300] Avg episode rewards: #0: 25.550, true rewards: #0: 11.550
+[2024-11-06 22:03:50,358][00300] Avg episode reward: 25.550, avg true_objective: 11.550
+[2024-11-06 22:03:50,447][00300] Num frames 1200...
+[2024-11-06 22:03:50,610][00300] Num frames 1300...
+[2024-11-06 22:03:50,780][00300] Num frames 1400...
+[2024-11-06 22:03:50,948][00300] Num frames 1500...
+[2024-11-06 22:03:51,097][00300] Num frames 1600...
+[2024-11-06 22:03:51,215][00300] Num frames 1700...
+[2024-11-06 22:03:51,387][00300] Avg episode rewards: #0: 18.475, true rewards: #0: 8.975
+[2024-11-06 22:03:51,390][00300] Avg episode reward: 18.475, avg true_objective: 8.975
+[2024-11-06 22:03:51,399][00300] Num frames 1800...
+[2024-11-06 22:03:51,527][00300] Num frames 1900...
+[2024-11-06 22:03:51,646][00300] Num frames 2000...
+[2024-11-06 22:03:51,761][00300] Num frames 2100...
+[2024-11-06 22:03:51,882][00300] Num frames 2200...
+[2024-11-06 22:03:52,001][00300] Num frames 2300...
+[2024-11-06 22:03:52,117][00300] Num frames 2400...
+[2024-11-06 22:03:52,236][00300] Num frames 2500...
+[2024-11-06 22:03:52,364][00300] Num frames 2600...
+[2024-11-06 22:03:52,491][00300] Num frames 2700...
+[2024-11-06 22:03:52,616][00300] Num frames 2800...
+[2024-11-06 22:03:52,734][00300] Num frames 2900...
+[2024-11-06 22:03:52,853][00300] Num frames 3000...
+[2024-11-06 22:03:52,978][00300] Num frames 3100...
+[2024-11-06 22:03:53,097][00300] Num frames 3200...
+[2024-11-06 22:03:53,216][00300] Num frames 3300...
+[2024-11-06 22:03:53,333][00300] Num frames 3400...
+[2024-11-06 22:03:53,443][00300] Avg episode rewards: #0: 27.467, true rewards: #0: 11.467
+[2024-11-06 22:03:53,444][00300] Avg episode reward: 27.467, avg true_objective: 11.467
+[2024-11-06 22:03:53,522][00300] Num frames 3500...
+[2024-11-06 22:03:53,639][00300] Num frames 3600...
+[2024-11-06 22:03:53,756][00300] Num frames 3700...
+[2024-11-06 22:03:53,873][00300] Num frames 3800...
+[2024-11-06 22:03:53,993][00300] Num frames 3900...
+[2024-11-06 22:03:54,108][00300] Num frames 4000...
+[2024-11-06 22:03:54,223][00300] Num frames 4100...
+[2024-11-06 22:03:54,340][00300] Num frames 4200...
+[2024-11-06 22:03:54,406][00300] Avg episode rewards: #0: 24.270, true rewards: #0: 10.520
+[2024-11-06 22:03:54,408][00300] Avg episode reward: 24.270, avg true_objective: 10.520
+[2024-11-06 22:03:54,526][00300] Num frames 4300...
+[2024-11-06 22:03:54,647][00300] Num frames 4400...
+[2024-11-06 22:03:54,761][00300] Num frames 4500...
+[2024-11-06 22:03:54,880][00300] Num frames 4600...
+[2024-11-06 22:03:54,999][00300] Num frames 4700...
+[2024-11-06 22:03:55,116][00300] Num frames 4800...
+[2024-11-06 22:03:55,234][00300] Num frames 4900...
+[2024-11-06 22:03:55,348][00300] Num frames 5000...
+[2024-11-06 22:03:55,487][00300] Num frames 5100...
+[2024-11-06 22:03:55,571][00300] Avg episode rewards: #0: 23.244, true rewards: #0: 10.244
+[2024-11-06 22:03:55,573][00300] Avg episode reward: 23.244, avg true_objective: 10.244
+[2024-11-06 22:03:55,665][00300] Num frames 5200...
+[2024-11-06 22:03:55,783][00300] Num frames 5300...
+[2024-11-06 22:03:55,898][00300] Num frames 5400...
+[2024-11-06 22:03:56,016][00300] Num frames 5500...
+[2024-11-06 22:03:56,115][00300] Avg episode rewards: #0: 20.397, true rewards: #0: 9.230
+[2024-11-06 22:03:56,116][00300] Avg episode reward: 20.397, avg true_objective: 9.230
+[2024-11-06 22:03:56,190][00300] Num frames 5600...
+[2024-11-06 22:03:56,305][00300] Num frames 5700...
+[2024-11-06 22:03:56,450][00300] Num frames 5800...
+[2024-11-06 22:03:56,574][00300] Num frames 5900...
+[2024-11-06 22:03:56,692][00300] Num frames 6000...
+[2024-11-06 22:03:56,817][00300] Num frames 6100...
+[2024-11-06 22:03:56,939][00300] Num frames 6200...
+[2024-11-06 22:03:57,059][00300] Num frames 6300...
+[2024-11-06 22:03:57,178][00300] Num frames 6400...
+[2024-11-06 22:03:57,303][00300] Num frames 6500...
+[2024-11-06 22:03:57,429][00300] Num frames 6600...
+[2024-11-06 22:03:57,494][00300] Avg episode rewards: #0: 21.579, true rewards: #0: 9.436
+[2024-11-06 22:03:57,496][00300] Avg episode reward: 21.579, avg true_objective: 9.436
+[2024-11-06 22:03:57,610][00300] Num frames 6700...
+[2024-11-06 22:03:57,726][00300] Num frames 6800...
+[2024-11-06 22:03:57,842][00300] Num frames 6900...
+[2024-11-06 22:03:57,961][00300] Num frames 7000...
+[2024-11-06 22:03:58,079][00300] Avg episode rewards: #0: 19.941, true rewards: #0: 8.816
+[2024-11-06 22:03:58,080][00300] Avg episode reward: 19.941, avg true_objective: 8.816
+[2024-11-06 22:03:58,136][00300] Num frames 7100...
+[2024-11-06 22:03:58,252][00300] Num frames 7200...
+[2024-11-06 22:03:58,373][00300] Num frames 7300...
+[2024-11-06 22:03:58,512][00300] Num frames 7400...
+[2024-11-06 22:03:58,631][00300] Num frames 7500...
+[2024-11-06 22:03:58,756][00300] Num frames 7600...
+[2024-11-06 22:03:58,875][00300] Num frames 7700...
+[2024-11-06 22:03:58,994][00300] Num frames 7800...
+[2024-11-06 22:03:59,110][00300] Num frames 7900...
+[2024-11-06 22:03:59,232][00300] Num frames 8000...
+[2024-11-06 22:03:59,349][00300] Num frames 8100...
+[2024-11-06 22:03:59,453][00300] Avg episode rewards: #0: 20.157, true rewards: #0: 9.046
+[2024-11-06 22:03:59,455][00300] Avg episode reward: 20.157, avg true_objective: 9.046
+[2024-11-06 22:03:59,533][00300] Num frames 8200...
+[2024-11-06 22:03:59,648][00300] Num frames 8300...
+[2024-11-06 22:03:59,768][00300] Num frames 8400...
+[2024-11-06 22:03:59,888][00300] Num frames 8500...
+[2024-11-06 22:04:00,006][00300] Num frames 8600...
+[2024-11-06 22:04:00,122][00300] Num frames 8700...
+[2024-11-06 22:04:00,242][00300] Num frames 8800...
+[2024-11-06 22:04:00,364][00300] Num frames 8900...
+[2024-11-06 22:04:00,493][00300] Num frames 9000...
+[2024-11-06 22:04:00,623][00300] Num frames 9100...
+[2024-11-06 22:04:00,742][00300] Num frames 9200...
+[2024-11-06 22:04:00,860][00300] Num frames 9300...
+[2024-11-06 22:04:00,981][00300] Num frames 9400...
+[2024-11-06 22:04:01,125][00300] Num frames 9500...
+[2024-11-06 22:04:01,295][00300] Num frames 9600...
+[2024-11-06 22:04:01,371][00300] Avg episode rewards: #0: 21.811, true rewards: #0: 9.611
+[2024-11-06 22:04:01,373][00300] Avg episode reward: 21.811, avg true_objective: 9.611
+[2024-11-06 22:04:58,942][00300] Replay video saved to /content/train_dir/default_experiment/replay.mp4!