Upload folder using huggingface_hub
Browse files- robocasa/turn_off_sink_faucet/baseline_seed10000/eval_log.json +11 -0
- robocasa/turn_off_sink_faucet/baseline_seed10001/eval_log.json +11 -0
- robocasa/turn_off_sink_faucet/baseline_seed10002/eval_log.json +11 -0
- robocasa/turn_off_sink_faucet/baseline_seed10003/eval_log.json +11 -0
- robocasa/turn_off_sink_faucet/baseline_seed10004/eval_log.json +11 -0
- robocasa/turn_off_sink_faucet/bon_n8_seed10000/eval_log.json +11 -0
- robocasa/turn_off_sink_faucet/bon_n8_seed10001/eval_log.json +11 -0
- robocasa/turn_off_sink_faucet/bon_n8_seed10002/eval_log.json +11 -0
- robocasa/turn_off_sink_faucet/bon_n8_seed10003/eval_log.json +11 -0
- robocasa/turn_off_sink_faucet/bon_n8_seed10004/eval_log.json +11 -0
- robocasa/turn_off_sink_faucet/summary_literal5.json +64 -0
robocasa/turn_off_sink_faucet/baseline_seed10000/eval_log.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "/workspace/oat/my_models/robocasa_turn_off_sink_faucet_topk_ep0500_sr0.580.ckpt",
|
| 3 |
+
"mean_success_rate_mean": 0.52,
|
| 4 |
+
"mean_tokens_used_mean": 8.0,
|
| 5 |
+
"num_exp": 1,
|
| 6 |
+
"turn_off_sink_faucet/mean_success_rate_mean": 0.52,
|
| 7 |
+
"turn_off_sink_faucet/video_10000_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10000/media/turn_off_sink_faucet/tjoome9z.mp4",
|
| 8 |
+
"turn_off_sink_faucet/video_10001_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10000/media/turn_off_sink_faucet/tfcltkoa.mp4",
|
| 9 |
+
"turn_off_sink_faucet/video_10002_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10000/media/turn_off_sink_faucet/8bh9ekuf.mp4",
|
| 10 |
+
"turn_off_sink_faucet/video_10003_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10000/media/turn_off_sink_faucet/bolwj8pa.mp4"
|
| 11 |
+
}
|
robocasa/turn_off_sink_faucet/baseline_seed10001/eval_log.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "/workspace/oat/my_models/robocasa_turn_off_sink_faucet_topk_ep0500_sr0.580.ckpt",
|
| 3 |
+
"mean_success_rate_mean": 0.58,
|
| 4 |
+
"mean_tokens_used_mean": 8.0,
|
| 5 |
+
"num_exp": 1,
|
| 6 |
+
"turn_off_sink_faucet/mean_success_rate_mean": 0.58,
|
| 7 |
+
"turn_off_sink_faucet/video_10001_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10001/media/turn_off_sink_faucet/l6zugavg.mp4",
|
| 8 |
+
"turn_off_sink_faucet/video_10002_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10001/media/turn_off_sink_faucet/s1tetsfc.mp4",
|
| 9 |
+
"turn_off_sink_faucet/video_10003_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10001/media/turn_off_sink_faucet/qhni49ba.mp4",
|
| 10 |
+
"turn_off_sink_faucet/video_10004_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10001/media/turn_off_sink_faucet/hhzvooix.mp4"
|
| 11 |
+
}
|
robocasa/turn_off_sink_faucet/baseline_seed10002/eval_log.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "/workspace/oat/my_models/robocasa_turn_off_sink_faucet_topk_ep0500_sr0.580.ckpt",
|
| 3 |
+
"mean_success_rate_mean": 0.58,
|
| 4 |
+
"mean_tokens_used_mean": 8.0,
|
| 5 |
+
"num_exp": 1,
|
| 6 |
+
"turn_off_sink_faucet/mean_success_rate_mean": 0.58,
|
| 7 |
+
"turn_off_sink_faucet/video_10002_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10002/media/turn_off_sink_faucet/cfle2d3d.mp4",
|
| 8 |
+
"turn_off_sink_faucet/video_10003_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10002/media/turn_off_sink_faucet/wm08fc27.mp4",
|
| 9 |
+
"turn_off_sink_faucet/video_10004_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10002/media/turn_off_sink_faucet/03m3ip8j.mp4",
|
| 10 |
+
"turn_off_sink_faucet/video_10005_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10002/media/turn_off_sink_faucet/4igjx69a.mp4"
|
| 11 |
+
}
|
robocasa/turn_off_sink_faucet/baseline_seed10003/eval_log.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "/workspace/oat/my_models/robocasa_turn_off_sink_faucet_topk_ep0500_sr0.580.ckpt",
|
| 3 |
+
"mean_success_rate_mean": 0.46,
|
| 4 |
+
"mean_tokens_used_mean": 8.0,
|
| 5 |
+
"num_exp": 1,
|
| 6 |
+
"turn_off_sink_faucet/mean_success_rate_mean": 0.46,
|
| 7 |
+
"turn_off_sink_faucet/video_10003_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10003/media/turn_off_sink_faucet/qt47bmvy.mp4",
|
| 8 |
+
"turn_off_sink_faucet/video_10004_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10003/media/turn_off_sink_faucet/3ubtjar2.mp4",
|
| 9 |
+
"turn_off_sink_faucet/video_10005_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10003/media/turn_off_sink_faucet/ulxdwupd.mp4",
|
| 10 |
+
"turn_off_sink_faucet/video_10006_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10003/media/turn_off_sink_faucet/j2voa8iq.mp4"
|
| 11 |
+
}
|
robocasa/turn_off_sink_faucet/baseline_seed10004/eval_log.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "/workspace/oat/my_models/robocasa_turn_off_sink_faucet_topk_ep0500_sr0.580.ckpt",
|
| 3 |
+
"mean_success_rate_mean": 0.48,
|
| 4 |
+
"mean_tokens_used_mean": 8.0,
|
| 5 |
+
"num_exp": 1,
|
| 6 |
+
"turn_off_sink_faucet/mean_success_rate_mean": 0.48,
|
| 7 |
+
"turn_off_sink_faucet/video_10004_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10004/media/turn_off_sink_faucet/1hqj9ezd.mp4",
|
| 8 |
+
"turn_off_sink_faucet/video_10005_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10004/media/turn_off_sink_faucet/lir5oqnt.mp4",
|
| 9 |
+
"turn_off_sink_faucet/video_10006_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10004/media/turn_off_sink_faucet/tsq4ruxy.mp4",
|
| 10 |
+
"turn_off_sink_faucet/video_10007_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10004/media/turn_off_sink_faucet/g96xwu0j.mp4"
|
| 11 |
+
}
|
robocasa/turn_off_sink_faucet/bon_n8_seed10000/eval_log.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "/workspace/oat/my_models/robocasa_turn_off_sink_faucet_topk_ep0500_sr0.580.ckpt",
|
| 3 |
+
"mean_success_rate_mean": 0.54,
|
| 4 |
+
"mean_tokens_used_mean": 8.0,
|
| 5 |
+
"num_exp": 1,
|
| 6 |
+
"turn_off_sink_faucet/mean_success_rate_mean": 0.54,
|
| 7 |
+
"turn_off_sink_faucet/video_10000_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10000/media/turn_off_sink_faucet/1m4uh0f4.mp4",
|
| 8 |
+
"turn_off_sink_faucet/video_10001_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10000/media/turn_off_sink_faucet/j7oaey4j.mp4",
|
| 9 |
+
"turn_off_sink_faucet/video_10002_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10000/media/turn_off_sink_faucet/0hlsh6v7.mp4",
|
| 10 |
+
"turn_off_sink_faucet/video_10003_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10000/media/turn_off_sink_faucet/e4vw4vuq.mp4"
|
| 11 |
+
}
|
robocasa/turn_off_sink_faucet/bon_n8_seed10001/eval_log.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "/workspace/oat/my_models/robocasa_turn_off_sink_faucet_topk_ep0500_sr0.580.ckpt",
|
| 3 |
+
"mean_success_rate_mean": 0.58,
|
| 4 |
+
"mean_tokens_used_mean": 8.0,
|
| 5 |
+
"num_exp": 1,
|
| 6 |
+
"turn_off_sink_faucet/mean_success_rate_mean": 0.58,
|
| 7 |
+
"turn_off_sink_faucet/video_10001_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10001/media/turn_off_sink_faucet/s7ronezc.mp4",
|
| 8 |
+
"turn_off_sink_faucet/video_10002_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10001/media/turn_off_sink_faucet/gt977plu.mp4",
|
| 9 |
+
"turn_off_sink_faucet/video_10003_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10001/media/turn_off_sink_faucet/7gpj9iou.mp4",
|
| 10 |
+
"turn_off_sink_faucet/video_10004_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10001/media/turn_off_sink_faucet/be5mi7a1.mp4"
|
| 11 |
+
}
|
robocasa/turn_off_sink_faucet/bon_n8_seed10002/eval_log.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "/workspace/oat/my_models/robocasa_turn_off_sink_faucet_topk_ep0500_sr0.580.ckpt",
|
| 3 |
+
"mean_success_rate_mean": 0.64,
|
| 4 |
+
"mean_tokens_used_mean": 8.0,
|
| 5 |
+
"num_exp": 1,
|
| 6 |
+
"turn_off_sink_faucet/mean_success_rate_mean": 0.64,
|
| 7 |
+
"turn_off_sink_faucet/video_10002_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10002/media/turn_off_sink_faucet/smluism8.mp4",
|
| 8 |
+
"turn_off_sink_faucet/video_10003_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10002/media/turn_off_sink_faucet/aixvrsjc.mp4",
|
| 9 |
+
"turn_off_sink_faucet/video_10004_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10002/media/turn_off_sink_faucet/rgtmon9b.mp4",
|
| 10 |
+
"turn_off_sink_faucet/video_10005_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10002/media/turn_off_sink_faucet/q1ssycmw.mp4"
|
| 11 |
+
}
|
robocasa/turn_off_sink_faucet/bon_n8_seed10003/eval_log.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "/workspace/oat/my_models/robocasa_turn_off_sink_faucet_topk_ep0500_sr0.580.ckpt",
|
| 3 |
+
"mean_success_rate_mean": 0.6,
|
| 4 |
+
"mean_tokens_used_mean": 8.0,
|
| 5 |
+
"num_exp": 1,
|
| 6 |
+
"turn_off_sink_faucet/mean_success_rate_mean": 0.6,
|
| 7 |
+
"turn_off_sink_faucet/video_10003_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10003/media/turn_off_sink_faucet/mswy7vqg.mp4",
|
| 8 |
+
"turn_off_sink_faucet/video_10004_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10003/media/turn_off_sink_faucet/wl81rp7d.mp4",
|
| 9 |
+
"turn_off_sink_faucet/video_10005_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10003/media/turn_off_sink_faucet/24u3uk4t.mp4",
|
| 10 |
+
"turn_off_sink_faucet/video_10006_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10003/media/turn_off_sink_faucet/9pdrltty.mp4"
|
| 11 |
+
}
|
robocasa/turn_off_sink_faucet/bon_n8_seed10004/eval_log.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "/workspace/oat/my_models/robocasa_turn_off_sink_faucet_topk_ep0500_sr0.580.ckpt",
|
| 3 |
+
"mean_success_rate_mean": 0.44,
|
| 4 |
+
"mean_tokens_used_mean": 8.0,
|
| 5 |
+
"num_exp": 1,
|
| 6 |
+
"turn_off_sink_faucet/mean_success_rate_mean": 0.44,
|
| 7 |
+
"turn_off_sink_faucet/video_10004_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10004/media/turn_off_sink_faucet/x4e7bv8l.mp4",
|
| 8 |
+
"turn_off_sink_faucet/video_10005_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10004/media/turn_off_sink_faucet/q1skn86j.mp4",
|
| 9 |
+
"turn_off_sink_faucet/video_10006_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10004/media/turn_off_sink_faucet/9jsouygy.mp4",
|
| 10 |
+
"turn_off_sink_faucet/video_10007_0": "/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10004/media/turn_off_sink_faucet/k21ci3z6.mp4"
|
| 11 |
+
}
|
robocasa/turn_off_sink_faucet/summary_literal5.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"protocol": {
|
| 3 |
+
"layout": "literal_5_seeds",
|
| 4 |
+
"seeds": [
|
| 5 |
+
10000,
|
| 6 |
+
10001,
|
| 7 |
+
10002,
|
| 8 |
+
10003,
|
| 9 |
+
10004
|
| 10 |
+
],
|
| 11 |
+
"n_test": 50,
|
| 12 |
+
"n_exp_per_seed": 1,
|
| 13 |
+
"aggregation": "mean over seeds; primary uncertainty SEM; also SD",
|
| 14 |
+
"delta": "mean(method)-mean(baseline); SEM_delta=sqrt(SEM_m^2+SEM_b^2) unpaired/conservative (paired SEM of diffs optional later)"
|
| 15 |
+
},
|
| 16 |
+
"methods": {
|
| 17 |
+
"baseline": {
|
| 18 |
+
"per_seed_sr": {
|
| 19 |
+
"10000": 0.52,
|
| 20 |
+
"10001": 0.58,
|
| 21 |
+
"10002": 0.58,
|
| 22 |
+
"10003": 0.46,
|
| 23 |
+
"10004": 0.48
|
| 24 |
+
},
|
| 25 |
+
"mean": 0.524,
|
| 26 |
+
"sd": 0.055497747702046414,
|
| 27 |
+
"sem": 0.024819347291981705,
|
| 28 |
+
"n_seeds": 5,
|
| 29 |
+
"eval_logs": [
|
| 30 |
+
"/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10000/eval_log.json",
|
| 31 |
+
"/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10001/eval_log.json",
|
| 32 |
+
"/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10002/eval_log.json",
|
| 33 |
+
"/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10003/eval_log.json",
|
| 34 |
+
"/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/baseline_seed10004/eval_log.json"
|
| 35 |
+
]
|
| 36 |
+
},
|
| 37 |
+
"bon_n8": {
|
| 38 |
+
"per_seed_sr": {
|
| 39 |
+
"10000": 0.54,
|
| 40 |
+
"10001": 0.58,
|
| 41 |
+
"10002": 0.64,
|
| 42 |
+
"10003": 0.6,
|
| 43 |
+
"10004": 0.44
|
| 44 |
+
},
|
| 45 |
+
"mean": 0.56,
|
| 46 |
+
"sd": 0.07615773105863909,
|
| 47 |
+
"sem": 0.0340587727318528,
|
| 48 |
+
"n_seeds": 5,
|
| 49 |
+
"eval_logs": [
|
| 50 |
+
"/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10000/eval_log.json",
|
| 51 |
+
"/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10001/eval_log.json",
|
| 52 |
+
"/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10002/eval_log.json",
|
| 53 |
+
"/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10003/eval_log.json",
|
| 54 |
+
"/workspace/oat/output/eval/matched_s10000/robocasa/turn_off_sink_faucet/bon_n8_seed10004/eval_log.json"
|
| 55 |
+
]
|
| 56 |
+
}
|
| 57 |
+
},
|
| 58 |
+
"deltas": {
|
| 59 |
+
"delta_bon_n8_minus_baseline": {
|
| 60 |
+
"delta": 0.03600000000000003,
|
| 61 |
+
"sem_delta": 0.04214261501141095
|
| 62 |
+
}
|
| 63 |
+
}
|
| 64 |
+
}
|