Hugging Face's logo

SUPER321
/
jevflash-doom-basic-0.6b

Text Generation
vizdoom
reinforcement-learning-adjacent
decision-model
behavior-cloning
Model card Files
xet
 Community
SUPER321 commited on
Commit
b4734ad
·
verified ·
1 Parent(s): c823c11

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. backbone_config/config.json +63 -0
  3. best.safetensors +3 -0
  4. config.json +34 -0
  5. summary.json +13 -0
  6. target_audit.json +2592 -0
  7. timing.json +32 -0
  8. tokenizer/chat_template.jinja +85 -0
  9. tokenizer/tokenizer.json +3 -0
  10. tokenizer/tokenizer_config.json +30 -0
  11. train_log.json +829 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
backbone_config/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "float32",
9
+ "eos_token_id": 151643,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention"
44
+ ],
45
+ "max_position_embeddings": 32768,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 8,
51
+ "pad_token_id": null,
52
+ "rms_norm_eps": 1e-06,
53
+ "rope_parameters": {
54
+ "rope_theta": 1000000,
55
+ "rope_type": "default"
56
+ },
57
+ "sliding_window": null,
58
+ "tie_word_embeddings": true,
59
+ "transformers_version": "5.17.0",
60
+ "use_cache": false,
61
+ "use_sliding_window": false,
62
+ "vocab_size": 151936
63
+ }
best.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:923e2ffeb2e04ef675e50413102d694e155917ab6e299f602ef2fe7997f58414
3
+ size 2385039280
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "input": "data/doom_basic_v1/all.jsonl",
3
+ "output_dir": "runs/doom_basic_0.6b",
4
+ "model": "Qwen/Qwen3-0.6B-Base",
5
+ "revision": "main",
6
+ "objective": "gold",
7
+ "set_head": "attention",
8
+ "steps": 120,
9
+ "head_steps": 12,
10
+ "batch_questions": 6,
11
+ "eval_every": 24,
12
+ "max_length": 512,
13
+ "seed": 17,
14
+ "backbone_lr": 2e-05,
15
+ "head_lr": 0.0002,
16
+ "device": "cpu",
17
+ "skip_native_baseline": true,
18
+ "resolved_model_revision": "da87bfb608c14b7cf20ba1ce41287e8de496c0cd",
19
+ "data_sha256": "fd9ebd9ff4573a101ab1ae84ca560c3ba8789f11ad0bbeeaf13161582804e176",
20
+ "deps": {
21
+ "torch": "2.14.0",
22
+ "transformers": "5.17.0",
23
+ "safetensors": "0.8.0",
24
+ "numpy": "2.5.3"
25
+ },
26
+ "gpu": "cpu",
27
+ "train_questions": 110,
28
+ "all_train_questions": 110,
29
+ "parameter_storage": "float32",
30
+ "forward_autocast": "fp32",
31
+ "teacher_target": "one-hot gold label",
32
+ "parallelism": "flat complete candidate paths in one backbone forward; no prefix sharing",
33
+ "parameter_count": 596250498
34
+ }
summary.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_step": 108,
3
+ "selected_on": "dev gold NLL",
4
+ "training_seconds": 5418.03064266697,
5
+ "final_all_eval": {
6
+ "accuracy": 0.48322147651006714,
7
+ "gold_nll": 0.9058935200088422,
8
+ "teacher_ce": null,
9
+ "questions": 149,
10
+ "teacher_eligible": 0
11
+ },
12
+ "max_gpu_allocated_gb": null
13
+ }
target_audit.json ADDED
@@ -0,0 +1,2592 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "id": "doom:basic:0:0:action",
4
+ "split": "train",
5
+ "type": "choice",
6
+ "k": 4,
7
+ "teacher_raw_sum": null,
8
+ "teacher_proxy_usable": false,
9
+ "teacher_argmax_matches_gold": null,
10
+ "target_transform": "no_teacher"
11
+ },
12
+ {
13
+ "id": "doom:basic:0:1:action",
14
+ "split": "train",
15
+ "type": "choice",
16
+ "k": 4,
17
+ "teacher_raw_sum": null,
18
+ "teacher_proxy_usable": false,
19
+ "teacher_argmax_matches_gold": null,
20
+ "target_transform": "no_teacher"
21
+ },
22
+ {
23
+ "id": "doom:basic:0:2:action",
24
+ "split": "train",
25
+ "type": "choice",
26
+ "k": 4,
27
+ "teacher_raw_sum": null,
28
+ "teacher_proxy_usable": false,
29
+ "teacher_argmax_matches_gold": null,
30
+ "target_transform": "no_teacher"
31
+ },
32
+ {
33
+ "id": "doom:basic:0:3:action",
34
+ "split": "train",
35
+ "type": "choice",
36
+ "k": 4,
37
+ "teacher_raw_sum": null,
38
+ "teacher_proxy_usable": false,
39
+ "teacher_argmax_matches_gold": null,
40
+ "target_transform": "no_teacher"
41
+ },
42
+ {
43
+ "id": "doom:basic:0:4:action",
44
+ "split": "train",
45
+ "type": "choice",
46
+ "k": 4,
47
+ "teacher_raw_sum": null,
48
+ "teacher_proxy_usable": false,
49
+ "teacher_argmax_matches_gold": null,
50
+ "target_transform": "no_teacher"
51
+ },
52
+ {
53
+ "id": "doom:basic:1:0:action",
54
+ "split": "train",
55
+ "type": "choice",
56
+ "k": 4,
57
+ "teacher_raw_sum": null,
58
+ "teacher_proxy_usable": false,
59
+ "teacher_argmax_matches_gold": null,
60
+ "target_transform": "no_teacher"
61
+ },
62
+ {
63
+ "id": "doom:basic:1:1:action",
64
+ "split": "train",
65
+ "type": "choice",
66
+ "k": 4,
67
+ "teacher_raw_sum": null,
68
+ "teacher_proxy_usable": false,
69
+ "teacher_argmax_matches_gold": null,
70
+ "target_transform": "no_teacher"
71
+ },
72
+ {
73
+ "id": "doom:basic:1:2:action",
74
+ "split": "train",
75
+ "type": "choice",
76
+ "k": 4,
77
+ "teacher_raw_sum": null,
78
+ "teacher_proxy_usable": false,
79
+ "teacher_argmax_matches_gold": null,
80
+ "target_transform": "no_teacher"
81
+ },
82
+ {
83
+ "id": "doom:basic:1:3:action",
84
+ "split": "train",
85
+ "type": "choice",
86
+ "k": 4,
87
+ "teacher_raw_sum": null,
88
+ "teacher_proxy_usable": false,
89
+ "teacher_argmax_matches_gold": null,
90
+ "target_transform": "no_teacher"
91
+ },
92
+ {
93
+ "id": "doom:basic:1:4:action",
94
+ "split": "train",
95
+ "type": "choice",
96
+ "k": 4,
97
+ "teacher_raw_sum": null,
98
+ "teacher_proxy_usable": false,
99
+ "teacher_argmax_matches_gold": null,
100
+ "target_transform": "no_teacher"
101
+ },
102
+ {
103
+ "id": "doom:basic:1:5:action",
104
+ "split": "train",
105
+ "type": "choice",
106
+ "k": 4,
107
+ "teacher_raw_sum": null,
108
+ "teacher_proxy_usable": false,
109
+ "teacher_argmax_matches_gold": null,
110
+ "target_transform": "no_teacher"
111
+ },
112
+ {
113
+ "id": "doom:basic:1:6:action",
114
+ "split": "train",
115
+ "type": "choice",
116
+ "k": 4,
117
+ "teacher_raw_sum": null,
118
+ "teacher_proxy_usable": false,
119
+ "teacher_argmax_matches_gold": null,
120
+ "target_transform": "no_teacher"
121
+ },
122
+ {
123
+ "id": "doom:basic:2:0:action",
124
+ "split": "train",
125
+ "type": "choice",
126
+ "k": 4,
127
+ "teacher_raw_sum": null,
128
+ "teacher_proxy_usable": false,
129
+ "teacher_argmax_matches_gold": null,
130
+ "target_transform": "no_teacher"
131
+ },
132
+ {
133
+ "id": "doom:basic:2:1:action",
134
+ "split": "train",
135
+ "type": "choice",
136
+ "k": 4,
137
+ "teacher_raw_sum": null,
138
+ "teacher_proxy_usable": false,
139
+ "teacher_argmax_matches_gold": null,
140
+ "target_transform": "no_teacher"
141
+ },
142
+ {
143
+ "id": "doom:basic:2:2:action",
144
+ "split": "train",
145
+ "type": "choice",
146
+ "k": 4,
147
+ "teacher_raw_sum": null,
148
+ "teacher_proxy_usable": false,
149
+ "teacher_argmax_matches_gold": null,
150
+ "target_transform": "no_teacher"
151
+ },
152
+ {
153
+ "id": "doom:basic:2:3:action",
154
+ "split": "train",
155
+ "type": "choice",
156
+ "k": 4,
157
+ "teacher_raw_sum": null,
158
+ "teacher_proxy_usable": false,
159
+ "teacher_argmax_matches_gold": null,
160
+ "target_transform": "no_teacher"
161
+ },
162
+ {
163
+ "id": "doom:basic:2:4:action",
164
+ "split": "train",
165
+ "type": "choice",
166
+ "k": 4,
167
+ "teacher_raw_sum": null,
168
+ "teacher_proxy_usable": false,
169
+ "teacher_argmax_matches_gold": null,
170
+ "target_transform": "no_teacher"
171
+ },
172
+ {
173
+ "id": "doom:basic:2:5:action",
174
+ "split": "train",
175
+ "type": "choice",
176
+ "k": 4,
177
+ "teacher_raw_sum": null,
178
+ "teacher_proxy_usable": false,
179
+ "teacher_argmax_matches_gold": null,
180
+ "target_transform": "no_teacher"
181
+ },
182
+ {
183
+ "id": "doom:basic:2:6:action",
184
+ "split": "train",
185
+ "type": "choice",
186
+ "k": 4,
187
+ "teacher_raw_sum": null,
188
+ "teacher_proxy_usable": false,
189
+ "teacher_argmax_matches_gold": null,
190
+ "target_transform": "no_teacher"
191
+ },
192
+ {
193
+ "id": "doom:basic:2:7:action",
194
+ "split": "train",
195
+ "type": "choice",
196
+ "k": 4,
197
+ "teacher_raw_sum": null,
198
+ "teacher_proxy_usable": false,
199
+ "teacher_argmax_matches_gold": null,
200
+ "target_transform": "no_teacher"
201
+ },
202
+ {
203
+ "id": "doom:basic:2:8:action",
204
+ "split": "train",
205
+ "type": "choice",
206
+ "k": 4,
207
+ "teacher_raw_sum": null,
208
+ "teacher_proxy_usable": false,
209
+ "teacher_argmax_matches_gold": null,
210
+ "target_transform": "no_teacher"
211
+ },
212
+ {
213
+ "id": "doom:basic:2:9:action",
214
+ "split": "train",
215
+ "type": "choice",
216
+ "k": 4,
217
+ "teacher_raw_sum": null,
218
+ "teacher_proxy_usable": false,
219
+ "teacher_argmax_matches_gold": null,
220
+ "target_transform": "no_teacher"
221
+ },
222
+ {
223
+ "id": "doom:basic:2:10:action",
224
+ "split": "train",
225
+ "type": "choice",
226
+ "k": 4,
227
+ "teacher_raw_sum": null,
228
+ "teacher_proxy_usable": false,
229
+ "teacher_argmax_matches_gold": null,
230
+ "target_transform": "no_teacher"
231
+ },
232
+ {
233
+ "id": "doom:basic:2:11:action",
234
+ "split": "train",
235
+ "type": "choice",
236
+ "k": 4,
237
+ "teacher_raw_sum": null,
238
+ "teacher_proxy_usable": false,
239
+ "teacher_argmax_matches_gold": null,
240
+ "target_transform": "no_teacher"
241
+ },
242
+ {
243
+ "id": "doom:basic:3:0:action",
244
+ "split": "train",
245
+ "type": "choice",
246
+ "k": 4,
247
+ "teacher_raw_sum": null,
248
+ "teacher_proxy_usable": false,
249
+ "teacher_argmax_matches_gold": null,
250
+ "target_transform": "no_teacher"
251
+ },
252
+ {
253
+ "id": "doom:basic:3:1:action",
254
+ "split": "train",
255
+ "type": "choice",
256
+ "k": 4,
257
+ "teacher_raw_sum": null,
258
+ "teacher_proxy_usable": false,
259
+ "teacher_argmax_matches_gold": null,
260
+ "target_transform": "no_teacher"
261
+ },
262
+ {
263
+ "id": "doom:basic:3:2:action",
264
+ "split": "train",
265
+ "type": "choice",
266
+ "k": 4,
267
+ "teacher_raw_sum": null,
268
+ "teacher_proxy_usable": false,
269
+ "teacher_argmax_matches_gold": null,
270
+ "target_transform": "no_teacher"
271
+ },
272
+ {
273
+ "id": "doom:basic:3:3:action",
274
+ "split": "train",
275
+ "type": "choice",
276
+ "k": 4,
277
+ "teacher_raw_sum": null,
278
+ "teacher_proxy_usable": false,
279
+ "teacher_argmax_matches_gold": null,
280
+ "target_transform": "no_teacher"
281
+ },
282
+ {
283
+ "id": "doom:basic:3:4:action",
284
+ "split": "train",
285
+ "type": "choice",
286
+ "k": 4,
287
+ "teacher_raw_sum": null,
288
+ "teacher_proxy_usable": false,
289
+ "teacher_argmax_matches_gold": null,
290
+ "target_transform": "no_teacher"
291
+ },
292
+ {
293
+ "id": "doom:basic:4:0:action",
294
+ "split": "train",
295
+ "type": "choice",
296
+ "k": 4,
297
+ "teacher_raw_sum": null,
298
+ "teacher_proxy_usable": false,
299
+ "teacher_argmax_matches_gold": null,
300
+ "target_transform": "no_teacher"
301
+ },
302
+ {
303
+ "id": "doom:basic:4:1:action",
304
+ "split": "train",
305
+ "type": "choice",
306
+ "k": 4,
307
+ "teacher_raw_sum": null,
308
+ "teacher_proxy_usable": false,
309
+ "teacher_argmax_matches_gold": null,
310
+ "target_transform": "no_teacher"
311
+ },
312
+ {
313
+ "id": "doom:basic:4:2:action",
314
+ "split": "train",
315
+ "type": "choice",
316
+ "k": 4,
317
+ "teacher_raw_sum": null,
318
+ "teacher_proxy_usable": false,
319
+ "teacher_argmax_matches_gold": null,
320
+ "target_transform": "no_teacher"
321
+ },
322
+ {
323
+ "id": "doom:basic:4:3:action",
324
+ "split": "train",
325
+ "type": "choice",
326
+ "k": 4,
327
+ "teacher_raw_sum": null,
328
+ "teacher_proxy_usable": false,
329
+ "teacher_argmax_matches_gold": null,
330
+ "target_transform": "no_teacher"
331
+ },
332
+ {
333
+ "id": "doom:basic:4:4:action",
334
+ "split": "train",
335
+ "type": "choice",
336
+ "k": 4,
337
+ "teacher_raw_sum": null,
338
+ "teacher_proxy_usable": false,
339
+ "teacher_argmax_matches_gold": null,
340
+ "target_transform": "no_teacher"
341
+ },
342
+ {
343
+ "id": "doom:basic:4:5:action",
344
+ "split": "train",
345
+ "type": "choice",
346
+ "k": 4,
347
+ "teacher_raw_sum": null,
348
+ "teacher_proxy_usable": false,
349
+ "teacher_argmax_matches_gold": null,
350
+ "target_transform": "no_teacher"
351
+ },
352
+ {
353
+ "id": "doom:basic:4:6:action",
354
+ "split": "train",
355
+ "type": "choice",
356
+ "k": 4,
357
+ "teacher_raw_sum": null,
358
+ "teacher_proxy_usable": false,
359
+ "teacher_argmax_matches_gold": null,
360
+ "target_transform": "no_teacher"
361
+ },
362
+ {
363
+ "id": "doom:basic:4:7:action",
364
+ "split": "train",
365
+ "type": "choice",
366
+ "k": 4,
367
+ "teacher_raw_sum": null,
368
+ "teacher_proxy_usable": false,
369
+ "teacher_argmax_matches_gold": null,
370
+ "target_transform": "no_teacher"
371
+ },
372
+ {
373
+ "id": "doom:basic:4:8:action",
374
+ "split": "train",
375
+ "type": "choice",
376
+ "k": 4,
377
+ "teacher_raw_sum": null,
378
+ "teacher_proxy_usable": false,
379
+ "teacher_argmax_matches_gold": null,
380
+ "target_transform": "no_teacher"
381
+ },
382
+ {
383
+ "id": "doom:basic:5:0:action",
384
+ "split": "train",
385
+ "type": "choice",
386
+ "k": 4,
387
+ "teacher_raw_sum": null,
388
+ "teacher_proxy_usable": false,
389
+ "teacher_argmax_matches_gold": null,
390
+ "target_transform": "no_teacher"
391
+ },
392
+ {
393
+ "id": "doom:basic:5:1:action",
394
+ "split": "train",
395
+ "type": "choice",
396
+ "k": 4,
397
+ "teacher_raw_sum": null,
398
+ "teacher_proxy_usable": false,
399
+ "teacher_argmax_matches_gold": null,
400
+ "target_transform": "no_teacher"
401
+ },
402
+ {
403
+ "id": "doom:basic:5:2:action",
404
+ "split": "train",
405
+ "type": "choice",
406
+ "k": 4,
407
+ "teacher_raw_sum": null,
408
+ "teacher_proxy_usable": false,
409
+ "teacher_argmax_matches_gold": null,
410
+ "target_transform": "no_teacher"
411
+ },
412
+ {
413
+ "id": "doom:basic:5:3:action",
414
+ "split": "train",
415
+ "type": "choice",
416
+ "k": 4,
417
+ "teacher_raw_sum": null,
418
+ "teacher_proxy_usable": false,
419
+ "teacher_argmax_matches_gold": null,
420
+ "target_transform": "no_teacher"
421
+ },
422
+ {
423
+ "id": "doom:basic:5:4:action",
424
+ "split": "train",
425
+ "type": "choice",
426
+ "k": 4,
427
+ "teacher_raw_sum": null,
428
+ "teacher_proxy_usable": false,
429
+ "teacher_argmax_matches_gold": null,
430
+ "target_transform": "no_teacher"
431
+ },
432
+ {
433
+ "id": "doom:basic:5:5:action",
434
+ "split": "train",
435
+ "type": "choice",
436
+ "k": 4,
437
+ "teacher_raw_sum": null,
438
+ "teacher_proxy_usable": false,
439
+ "teacher_argmax_matches_gold": null,
440
+ "target_transform": "no_teacher"
441
+ },
442
+ {
443
+ "id": "doom:basic:6:0:action",
444
+ "split": "train",
445
+ "type": "choice",
446
+ "k": 4,
447
+ "teacher_raw_sum": null,
448
+ "teacher_proxy_usable": false,
449
+ "teacher_argmax_matches_gold": null,
450
+ "target_transform": "no_teacher"
451
+ },
452
+ {
453
+ "id": "doom:basic:6:1:action",
454
+ "split": "train",
455
+ "type": "choice",
456
+ "k": 4,
457
+ "teacher_raw_sum": null,
458
+ "teacher_proxy_usable": false,
459
+ "teacher_argmax_matches_gold": null,
460
+ "target_transform": "no_teacher"
461
+ },
462
+ {
463
+ "id": "doom:basic:6:2:action",
464
+ "split": "train",
465
+ "type": "choice",
466
+ "k": 4,
467
+ "teacher_raw_sum": null,
468
+ "teacher_proxy_usable": false,
469
+ "teacher_argmax_matches_gold": null,
470
+ "target_transform": "no_teacher"
471
+ },
472
+ {
473
+ "id": "doom:basic:6:3:action",
474
+ "split": "train",
475
+ "type": "choice",
476
+ "k": 4,
477
+ "teacher_raw_sum": null,
478
+ "teacher_proxy_usable": false,
479
+ "teacher_argmax_matches_gold": null,
480
+ "target_transform": "no_teacher"
481
+ },
482
+ {
483
+ "id": "doom:basic:6:4:action",
484
+ "split": "train",
485
+ "type": "choice",
486
+ "k": 4,
487
+ "teacher_raw_sum": null,
488
+ "teacher_proxy_usable": false,
489
+ "teacher_argmax_matches_gold": null,
490
+ "target_transform": "no_teacher"
491
+ },
492
+ {
493
+ "id": "doom:basic:6:5:action",
494
+ "split": "train",
495
+ "type": "choice",
496
+ "k": 4,
497
+ "teacher_raw_sum": null,
498
+ "teacher_proxy_usable": false,
499
+ "teacher_argmax_matches_gold": null,
500
+ "target_transform": "no_teacher"
501
+ },
502
+ {
503
+ "id": "doom:basic:6:6:action",
504
+ "split": "train",
505
+ "type": "choice",
506
+ "k": 4,
507
+ "teacher_raw_sum": null,
508
+ "teacher_proxy_usable": false,
509
+ "teacher_argmax_matches_gold": null,
510
+ "target_transform": "no_teacher"
511
+ },
512
+ {
513
+ "id": "doom:basic:6:7:action",
514
+ "split": "train",
515
+ "type": "choice",
516
+ "k": 4,
517
+ "teacher_raw_sum": null,
518
+ "teacher_proxy_usable": false,
519
+ "teacher_argmax_matches_gold": null,
520
+ "target_transform": "no_teacher"
521
+ },
522
+ {
523
+ "id": "doom:basic:7:0:action",
524
+ "split": "train",
525
+ "type": "choice",
526
+ "k": 4,
527
+ "teacher_raw_sum": null,
528
+ "teacher_proxy_usable": false,
529
+ "teacher_argmax_matches_gold": null,
530
+ "target_transform": "no_teacher"
531
+ },
532
+ {
533
+ "id": "doom:basic:7:1:action",
534
+ "split": "train",
535
+ "type": "choice",
536
+ "k": 4,
537
+ "teacher_raw_sum": null,
538
+ "teacher_proxy_usable": false,
539
+ "teacher_argmax_matches_gold": null,
540
+ "target_transform": "no_teacher"
541
+ },
542
+ {
543
+ "id": "doom:basic:7:2:action",
544
+ "split": "train",
545
+ "type": "choice",
546
+ "k": 4,
547
+ "teacher_raw_sum": null,
548
+ "teacher_proxy_usable": false,
549
+ "teacher_argmax_matches_gold": null,
550
+ "target_transform": "no_teacher"
551
+ },
552
+ {
553
+ "id": "doom:basic:7:3:action",
554
+ "split": "train",
555
+ "type": "choice",
556
+ "k": 4,
557
+ "teacher_raw_sum": null,
558
+ "teacher_proxy_usable": false,
559
+ "teacher_argmax_matches_gold": null,
560
+ "target_transform": "no_teacher"
561
+ },
562
+ {
563
+ "id": "doom:basic:7:4:action",
564
+ "split": "train",
565
+ "type": "choice",
566
+ "k": 4,
567
+ "teacher_raw_sum": null,
568
+ "teacher_proxy_usable": false,
569
+ "teacher_argmax_matches_gold": null,
570
+ "target_transform": "no_teacher"
571
+ },
572
+ {
573
+ "id": "doom:basic:8:0:action",
574
+ "split": "train",
575
+ "type": "choice",
576
+ "k": 4,
577
+ "teacher_raw_sum": null,
578
+ "teacher_proxy_usable": false,
579
+ "teacher_argmax_matches_gold": null,
580
+ "target_transform": "no_teacher"
581
+ },
582
+ {
583
+ "id": "doom:basic:8:1:action",
584
+ "split": "train",
585
+ "type": "choice",
586
+ "k": 4,
587
+ "teacher_raw_sum": null,
588
+ "teacher_proxy_usable": false,
589
+ "teacher_argmax_matches_gold": null,
590
+ "target_transform": "no_teacher"
591
+ },
592
+ {
593
+ "id": "doom:basic:9:0:action",
594
+ "split": "train",
595
+ "type": "choice",
596
+ "k": 4,
597
+ "teacher_raw_sum": null,
598
+ "teacher_proxy_usable": false,
599
+ "teacher_argmax_matches_gold": null,
600
+ "target_transform": "no_teacher"
601
+ },
602
+ {
603
+ "id": "doom:basic:9:1:action",
604
+ "split": "train",
605
+ "type": "choice",
606
+ "k": 4,
607
+ "teacher_raw_sum": null,
608
+ "teacher_proxy_usable": false,
609
+ "teacher_argmax_matches_gold": null,
610
+ "target_transform": "no_teacher"
611
+ },
612
+ {
613
+ "id": "doom:basic:9:2:action",
614
+ "split": "train",
615
+ "type": "choice",
616
+ "k": 4,
617
+ "teacher_raw_sum": null,
618
+ "teacher_proxy_usable": false,
619
+ "teacher_argmax_matches_gold": null,
620
+ "target_transform": "no_teacher"
621
+ },
622
+ {
623
+ "id": "doom:basic:9:3:action",
624
+ "split": "train",
625
+ "type": "choice",
626
+ "k": 4,
627
+ "teacher_raw_sum": null,
628
+ "teacher_proxy_usable": false,
629
+ "teacher_argmax_matches_gold": null,
630
+ "target_transform": "no_teacher"
631
+ },
632
+ {
633
+ "id": "doom:basic:9:4:action",
634
+ "split": "train",
635
+ "type": "choice",
636
+ "k": 4,
637
+ "teacher_raw_sum": null,
638
+ "teacher_proxy_usable": false,
639
+ "teacher_argmax_matches_gold": null,
640
+ "target_transform": "no_teacher"
641
+ },
642
+ {
643
+ "id": "doom:basic:9:5:action",
644
+ "split": "train",
645
+ "type": "choice",
646
+ "k": 4,
647
+ "teacher_raw_sum": null,
648
+ "teacher_proxy_usable": false,
649
+ "teacher_argmax_matches_gold": null,
650
+ "target_transform": "no_teacher"
651
+ },
652
+ {
653
+ "id": "doom:basic:9:6:action",
654
+ "split": "train",
655
+ "type": "choice",
656
+ "k": 4,
657
+ "teacher_raw_sum": null,
658
+ "teacher_proxy_usable": false,
659
+ "teacher_argmax_matches_gold": null,
660
+ "target_transform": "no_teacher"
661
+ },
662
+ {
663
+ "id": "doom:basic:9:7:action",
664
+ "split": "train",
665
+ "type": "choice",
666
+ "k": 4,
667
+ "teacher_raw_sum": null,
668
+ "teacher_proxy_usable": false,
669
+ "teacher_argmax_matches_gold": null,
670
+ "target_transform": "no_teacher"
671
+ },
672
+ {
673
+ "id": "doom:basic:9:8:action",
674
+ "split": "train",
675
+ "type": "choice",
676
+ "k": 4,
677
+ "teacher_raw_sum": null,
678
+ "teacher_proxy_usable": false,
679
+ "teacher_argmax_matches_gold": null,
680
+ "target_transform": "no_teacher"
681
+ },
682
+ {
683
+ "id": "doom:basic:10:0:action",
684
+ "split": "train",
685
+ "type": "choice",
686
+ "k": 4,
687
+ "teacher_raw_sum": null,
688
+ "teacher_proxy_usable": false,
689
+ "teacher_argmax_matches_gold": null,
690
+ "target_transform": "no_teacher"
691
+ },
692
+ {
693
+ "id": "doom:basic:10:1:action",
694
+ "split": "train",
695
+ "type": "choice",
696
+ "k": 4,
697
+ "teacher_raw_sum": null,
698
+ "teacher_proxy_usable": false,
699
+ "teacher_argmax_matches_gold": null,
700
+ "target_transform": "no_teacher"
701
+ },
702
+ {
703
+ "id": "doom:basic:10:2:action",
704
+ "split": "train",
705
+ "type": "choice",
706
+ "k": 4,
707
+ "teacher_raw_sum": null,
708
+ "teacher_proxy_usable": false,
709
+ "teacher_argmax_matches_gold": null,
710
+ "target_transform": "no_teacher"
711
+ },
712
+ {
713
+ "id": "doom:basic:10:3:action",
714
+ "split": "train",
715
+ "type": "choice",
716
+ "k": 4,
717
+ "teacher_raw_sum": null,
718
+ "teacher_proxy_usable": false,
719
+ "teacher_argmax_matches_gold": null,
720
+ "target_transform": "no_teacher"
721
+ },
722
+ {
723
+ "id": "doom:basic:10:4:action",
724
+ "split": "train",
725
+ "type": "choice",
726
+ "k": 4,
727
+ "teacher_raw_sum": null,
728
+ "teacher_proxy_usable": false,
729
+ "teacher_argmax_matches_gold": null,
730
+ "target_transform": "no_teacher"
731
+ },
732
+ {
733
+ "id": "doom:basic:10:5:action",
734
+ "split": "train",
735
+ "type": "choice",
736
+ "k": 4,
737
+ "teacher_raw_sum": null,
738
+ "teacher_proxy_usable": false,
739
+ "teacher_argmax_matches_gold": null,
740
+ "target_transform": "no_teacher"
741
+ },
742
+ {
743
+ "id": "doom:basic:11:0:action",
744
+ "split": "train",
745
+ "type": "choice",
746
+ "k": 4,
747
+ "teacher_raw_sum": null,
748
+ "teacher_proxy_usable": false,
749
+ "teacher_argmax_matches_gold": null,
750
+ "target_transform": "no_teacher"
751
+ },
752
+ {
753
+ "id": "doom:basic:11:1:action",
754
+ "split": "train",
755
+ "type": "choice",
756
+ "k": 4,
757
+ "teacher_raw_sum": null,
758
+ "teacher_proxy_usable": false,
759
+ "teacher_argmax_matches_gold": null,
760
+ "target_transform": "no_teacher"
761
+ },
762
+ {
763
+ "id": "doom:basic:11:2:action",
764
+ "split": "train",
765
+ "type": "choice",
766
+ "k": 4,
767
+ "teacher_raw_sum": null,
768
+ "teacher_proxy_usable": false,
769
+ "teacher_argmax_matches_gold": null,
770
+ "target_transform": "no_teacher"
771
+ },
772
+ {
773
+ "id": "doom:basic:11:3:action",
774
+ "split": "train",
775
+ "type": "choice",
776
+ "k": 4,
777
+ "teacher_raw_sum": null,
778
+ "teacher_proxy_usable": false,
779
+ "teacher_argmax_matches_gold": null,
780
+ "target_transform": "no_teacher"
781
+ },
782
+ {
783
+ "id": "doom:basic:11:4:action",
784
+ "split": "train",
785
+ "type": "choice",
786
+ "k": 4,
787
+ "teacher_raw_sum": null,
788
+ "teacher_proxy_usable": false,
789
+ "teacher_argmax_matches_gold": null,
790
+ "target_transform": "no_teacher"
791
+ },
792
+ {
793
+ "id": "doom:basic:11:5:action",
794
+ "split": "train",
795
+ "type": "choice",
796
+ "k": 4,
797
+ "teacher_raw_sum": null,
798
+ "teacher_proxy_usable": false,
799
+ "teacher_argmax_matches_gold": null,
800
+ "target_transform": "no_teacher"
801
+ },
802
+ {
803
+ "id": "doom:basic:11:6:action",
804
+ "split": "train",
805
+ "type": "choice",
806
+ "k": 4,
807
+ "teacher_raw_sum": null,
808
+ "teacher_proxy_usable": false,
809
+ "teacher_argmax_matches_gold": null,
810
+ "target_transform": "no_teacher"
811
+ },
812
+ {
813
+ "id": "doom:basic:11:7:action",
814
+ "split": "train",
815
+ "type": "choice",
816
+ "k": 4,
817
+ "teacher_raw_sum": null,
818
+ "teacher_proxy_usable": false,
819
+ "teacher_argmax_matches_gold": null,
820
+ "target_transform": "no_teacher"
821
+ },
822
+ {
823
+ "id": "doom:basic:11:8:action",
824
+ "split": "train",
825
+ "type": "choice",
826
+ "k": 4,
827
+ "teacher_raw_sum": null,
828
+ "teacher_proxy_usable": false,
829
+ "teacher_argmax_matches_gold": null,
830
+ "target_transform": "no_teacher"
831
+ },
832
+ {
833
+ "id": "doom:basic:11:9:action",
834
+ "split": "train",
835
+ "type": "choice",
836
+ "k": 4,
837
+ "teacher_raw_sum": null,
838
+ "teacher_proxy_usable": false,
839
+ "teacher_argmax_matches_gold": null,
840
+ "target_transform": "no_teacher"
841
+ },
842
+ {
843
+ "id": "doom:basic:11:10:action",
844
+ "split": "train",
845
+ "type": "choice",
846
+ "k": 4,
847
+ "teacher_raw_sum": null,
848
+ "teacher_proxy_usable": false,
849
+ "teacher_argmax_matches_gold": null,
850
+ "target_transform": "no_teacher"
851
+ },
852
+ {
853
+ "id": "doom:basic:11:11:action",
854
+ "split": "train",
855
+ "type": "choice",
856
+ "k": 4,
857
+ "teacher_raw_sum": null,
858
+ "teacher_proxy_usable": false,
859
+ "teacher_argmax_matches_gold": null,
860
+ "target_transform": "no_teacher"
861
+ },
862
+ {
863
+ "id": "doom:basic:12:0:action",
864
+ "split": "train",
865
+ "type": "choice",
866
+ "k": 4,
867
+ "teacher_raw_sum": null,
868
+ "teacher_proxy_usable": false,
869
+ "teacher_argmax_matches_gold": null,
870
+ "target_transform": "no_teacher"
871
+ },
872
+ {
873
+ "id": "doom:basic:12:1:action",
874
+ "split": "train",
875
+ "type": "choice",
876
+ "k": 4,
877
+ "teacher_raw_sum": null,
878
+ "teacher_proxy_usable": false,
879
+ "teacher_argmax_matches_gold": null,
880
+ "target_transform": "no_teacher"
881
+ },
882
+ {
883
+ "id": "doom:basic:12:2:action",
884
+ "split": "train",
885
+ "type": "choice",
886
+ "k": 4,
887
+ "teacher_raw_sum": null,
888
+ "teacher_proxy_usable": false,
889
+ "teacher_argmax_matches_gold": null,
890
+ "target_transform": "no_teacher"
891
+ },
892
+ {
893
+ "id": "doom:basic:12:3:action",
894
+ "split": "train",
895
+ "type": "choice",
896
+ "k": 4,
897
+ "teacher_raw_sum": null,
898
+ "teacher_proxy_usable": false,
899
+ "teacher_argmax_matches_gold": null,
900
+ "target_transform": "no_teacher"
901
+ },
902
+ {
903
+ "id": "doom:basic:12:4:action",
904
+ "split": "train",
905
+ "type": "choice",
906
+ "k": 4,
907
+ "teacher_raw_sum": null,
908
+ "teacher_proxy_usable": false,
909
+ "teacher_argmax_matches_gold": null,
910
+ "target_transform": "no_teacher"
911
+ },
912
+ {
913
+ "id": "doom:basic:13:0:action",
914
+ "split": "train",
915
+ "type": "choice",
916
+ "k": 4,
917
+ "teacher_raw_sum": null,
918
+ "teacher_proxy_usable": false,
919
+ "teacher_argmax_matches_gold": null,
920
+ "target_transform": "no_teacher"
921
+ },
922
+ {
923
+ "id": "doom:basic:13:1:action",
924
+ "split": "train",
925
+ "type": "choice",
926
+ "k": 4,
927
+ "teacher_raw_sum": null,
928
+ "teacher_proxy_usable": false,
929
+ "teacher_argmax_matches_gold": null,
930
+ "target_transform": "no_teacher"
931
+ },
932
+ {
933
+ "id": "doom:basic:13:2:action",
934
+ "split": "train",
935
+ "type": "choice",
936
+ "k": 4,
937
+ "teacher_raw_sum": null,
938
+ "teacher_proxy_usable": false,
939
+ "teacher_argmax_matches_gold": null,
940
+ "target_transform": "no_teacher"
941
+ },
942
+ {
943
+ "id": "doom:basic:13:3:action",
944
+ "split": "train",
945
+ "type": "choice",
946
+ "k": 4,
947
+ "teacher_raw_sum": null,
948
+ "teacher_proxy_usable": false,
949
+ "teacher_argmax_matches_gold": null,
950
+ "target_transform": "no_teacher"
951
+ },
952
+ {
953
+ "id": "doom:basic:13:4:action",
954
+ "split": "train",
955
+ "type": "choice",
956
+ "k": 4,
957
+ "teacher_raw_sum": null,
958
+ "teacher_proxy_usable": false,
959
+ "teacher_argmax_matches_gold": null,
960
+ "target_transform": "no_teacher"
961
+ },
962
+ {
963
+ "id": "doom:basic:13:5:action",
964
+ "split": "train",
965
+ "type": "choice",
966
+ "k": 4,
967
+ "teacher_raw_sum": null,
968
+ "teacher_proxy_usable": false,
969
+ "teacher_argmax_matches_gold": null,
970
+ "target_transform": "no_teacher"
971
+ },
972
+ {
973
+ "id": "doom:basic:13:6:action",
974
+ "split": "train",
975
+ "type": "choice",
976
+ "k": 4,
977
+ "teacher_raw_sum": null,
978
+ "teacher_proxy_usable": false,
979
+ "teacher_argmax_matches_gold": null,
980
+ "target_transform": "no_teacher"
981
+ },
982
+ {
983
+ "id": "doom:basic:14:0:action",
984
+ "split": "train",
985
+ "type": "choice",
986
+ "k": 4,
987
+ "teacher_raw_sum": null,
988
+ "teacher_proxy_usable": false,
989
+ "teacher_argmax_matches_gold": null,
990
+ "target_transform": "no_teacher"
991
+ },
992
+ {
993
+ "id": "doom:basic:14:1:action",
994
+ "split": "train",
995
+ "type": "choice",
996
+ "k": 4,
997
+ "teacher_raw_sum": null,
998
+ "teacher_proxy_usable": false,
999
+ "teacher_argmax_matches_gold": null,
1000
+ "target_transform": "no_teacher"
1001
+ },
1002
+ {
1003
+ "id": "doom:basic:14:2:action",
1004
+ "split": "train",
1005
+ "type": "choice",
1006
+ "k": 4,
1007
+ "teacher_raw_sum": null,
1008
+ "teacher_proxy_usable": false,
1009
+ "teacher_argmax_matches_gold": null,
1010
+ "target_transform": "no_teacher"
1011
+ },
1012
+ {
1013
+ "id": "doom:basic:14:3:action",
1014
+ "split": "train",
1015
+ "type": "choice",
1016
+ "k": 4,
1017
+ "teacher_raw_sum": null,
1018
+ "teacher_proxy_usable": false,
1019
+ "teacher_argmax_matches_gold": null,
1020
+ "target_transform": "no_teacher"
1021
+ },
1022
+ {
1023
+ "id": "doom:basic:14:4:action",
1024
+ "split": "train",
1025
+ "type": "choice",
1026
+ "k": 4,
1027
+ "teacher_raw_sum": null,
1028
+ "teacher_proxy_usable": false,
1029
+ "teacher_argmax_matches_gold": null,
1030
+ "target_transform": "no_teacher"
1031
+ },
1032
+ {
1033
+ "id": "doom:basic:14:5:action",
1034
+ "split": "train",
1035
+ "type": "choice",
1036
+ "k": 4,
1037
+ "teacher_raw_sum": null,
1038
+ "teacher_proxy_usable": false,
1039
+ "teacher_argmax_matches_gold": null,
1040
+ "target_transform": "no_teacher"
1041
+ },
1042
+ {
1043
+ "id": "doom:basic:14:6:action",
1044
+ "split": "train",
1045
+ "type": "choice",
1046
+ "k": 4,
1047
+ "teacher_raw_sum": null,
1048
+ "teacher_proxy_usable": false,
1049
+ "teacher_argmax_matches_gold": null,
1050
+ "target_transform": "no_teacher"
1051
+ },
1052
+ {
1053
+ "id": "doom:basic:14:7:action",
1054
+ "split": "train",
1055
+ "type": "choice",
1056
+ "k": 4,
1057
+ "teacher_raw_sum": null,
1058
+ "teacher_proxy_usable": false,
1059
+ "teacher_argmax_matches_gold": null,
1060
+ "target_transform": "no_teacher"
1061
+ },
1062
+ {
1063
+ "id": "doom:basic:15:0:action",
1064
+ "split": "train",
1065
+ "type": "choice",
1066
+ "k": 4,
1067
+ "teacher_raw_sum": null,
1068
+ "teacher_proxy_usable": false,
1069
+ "teacher_argmax_matches_gold": null,
1070
+ "target_transform": "no_teacher"
1071
+ },
1072
+ {
1073
+ "id": "doom:basic:15:1:action",
1074
+ "split": "train",
1075
+ "type": "choice",
1076
+ "k": 4,
1077
+ "teacher_raw_sum": null,
1078
+ "teacher_proxy_usable": false,
1079
+ "teacher_argmax_matches_gold": null,
1080
+ "target_transform": "no_teacher"
1081
+ },
1082
+ {
1083
+ "id": "doom:basic:15:2:action",
1084
+ "split": "train",
1085
+ "type": "choice",
1086
+ "k": 4,
1087
+ "teacher_raw_sum": null,
1088
+ "teacher_proxy_usable": false,
1089
+ "teacher_argmax_matches_gold": null,
1090
+ "target_transform": "no_teacher"
1091
+ },
1092
+ {
1093
+ "id": "doom:basic:15:3:action",
1094
+ "split": "train",
1095
+ "type": "choice",
1096
+ "k": 4,
1097
+ "teacher_raw_sum": null,
1098
+ "teacher_proxy_usable": false,
1099
+ "teacher_argmax_matches_gold": null,
1100
+ "target_transform": "no_teacher"
1101
+ },
1102
+ {
1103
+ "id": "doom:basic:1000:0:action",
1104
+ "split": "dev",
1105
+ "type": "choice",
1106
+ "k": 4,
1107
+ "teacher_raw_sum": null,
1108
+ "teacher_proxy_usable": false,
1109
+ "teacher_argmax_matches_gold": null,
1110
+ "target_transform": "no_teacher"
1111
+ },
1112
+ {
1113
+ "id": "doom:basic:1000:1:action",
1114
+ "split": "dev",
1115
+ "type": "choice",
1116
+ "k": 4,
1117
+ "teacher_raw_sum": null,
1118
+ "teacher_proxy_usable": false,
1119
+ "teacher_argmax_matches_gold": null,
1120
+ "target_transform": "no_teacher"
1121
+ },
1122
+ {
1123
+ "id": "doom:basic:1000:2:action",
1124
+ "split": "dev",
1125
+ "type": "choice",
1126
+ "k": 4,
1127
+ "teacher_raw_sum": null,
1128
+ "teacher_proxy_usable": false,
1129
+ "teacher_argmax_matches_gold": null,
1130
+ "target_transform": "no_teacher"
1131
+ },
1132
+ {
1133
+ "id": "doom:basic:1000:3:action",
1134
+ "split": "dev",
1135
+ "type": "choice",
1136
+ "k": 4,
1137
+ "teacher_raw_sum": null,
1138
+ "teacher_proxy_usable": false,
1139
+ "teacher_argmax_matches_gold": null,
1140
+ "target_transform": "no_teacher"
1141
+ },
1142
+ {
1143
+ "id": "doom:basic:1000:4:action",
1144
+ "split": "dev",
1145
+ "type": "choice",
1146
+ "k": 4,
1147
+ "teacher_raw_sum": null,
1148
+ "teacher_proxy_usable": false,
1149
+ "teacher_argmax_matches_gold": null,
1150
+ "target_transform": "no_teacher"
1151
+ },
1152
+ {
1153
+ "id": "doom:basic:1000:5:action",
1154
+ "split": "dev",
1155
+ "type": "choice",
1156
+ "k": 4,
1157
+ "teacher_raw_sum": null,
1158
+ "teacher_proxy_usable": false,
1159
+ "teacher_argmax_matches_gold": null,
1160
+ "target_transform": "no_teacher"
1161
+ },
1162
+ {
1163
+ "id": "doom:basic:1000:6:action",
1164
+ "split": "dev",
1165
+ "type": "choice",
1166
+ "k": 4,
1167
+ "teacher_raw_sum": null,
1168
+ "teacher_proxy_usable": false,
1169
+ "teacher_argmax_matches_gold": null,
1170
+ "target_transform": "no_teacher"
1171
+ },
1172
+ {
1173
+ "id": "doom:basic:1001:0:action",
1174
+ "split": "dev",
1175
+ "type": "choice",
1176
+ "k": 4,
1177
+ "teacher_raw_sum": null,
1178
+ "teacher_proxy_usable": false,
1179
+ "teacher_argmax_matches_gold": null,
1180
+ "target_transform": "no_teacher"
1181
+ },
1182
+ {
1183
+ "id": "doom:basic:1001:1:action",
1184
+ "split": "dev",
1185
+ "type": "choice",
1186
+ "k": 4,
1187
+ "teacher_raw_sum": null,
1188
+ "teacher_proxy_usable": false,
1189
+ "teacher_argmax_matches_gold": null,
1190
+ "target_transform": "no_teacher"
1191
+ },
1192
+ {
1193
+ "id": "doom:basic:1001:2:action",
1194
+ "split": "dev",
1195
+ "type": "choice",
1196
+ "k": 4,
1197
+ "teacher_raw_sum": null,
1198
+ "teacher_proxy_usable": false,
1199
+ "teacher_argmax_matches_gold": null,
1200
+ "target_transform": "no_teacher"
1201
+ },
1202
+ {
1203
+ "id": "doom:basic:1001:3:action",
1204
+ "split": "dev",
1205
+ "type": "choice",
1206
+ "k": 4,
1207
+ "teacher_raw_sum": null,
1208
+ "teacher_proxy_usable": false,
1209
+ "teacher_argmax_matches_gold": null,
1210
+ "target_transform": "no_teacher"
1211
+ },
1212
+ {
1213
+ "id": "doom:basic:1001:4:action",
1214
+ "split": "dev",
1215
+ "type": "choice",
1216
+ "k": 4,
1217
+ "teacher_raw_sum": null,
1218
+ "teacher_proxy_usable": false,
1219
+ "teacher_argmax_matches_gold": null,
1220
+ "target_transform": "no_teacher"
1221
+ },
1222
+ {
1223
+ "id": "doom:basic:1001:5:action",
1224
+ "split": "dev",
1225
+ "type": "choice",
1226
+ "k": 4,
1227
+ "teacher_raw_sum": null,
1228
+ "teacher_proxy_usable": false,
1229
+ "teacher_argmax_matches_gold": null,
1230
+ "target_transform": "no_teacher"
1231
+ },
1232
+ {
1233
+ "id": "doom:basic:1001:6:action",
1234
+ "split": "dev",
1235
+ "type": "choice",
1236
+ "k": 4,
1237
+ "teacher_raw_sum": null,
1238
+ "teacher_proxy_usable": false,
1239
+ "teacher_argmax_matches_gold": null,
1240
+ "target_transform": "no_teacher"
1241
+ },
1242
+ {
1243
+ "id": "doom:basic:1002:0:action",
1244
+ "split": "dev",
1245
+ "type": "choice",
1246
+ "k": 4,
1247
+ "teacher_raw_sum": null,
1248
+ "teacher_proxy_usable": false,
1249
+ "teacher_argmax_matches_gold": null,
1250
+ "target_transform": "no_teacher"
1251
+ },
1252
+ {
1253
+ "id": "doom:basic:1002:1:action",
1254
+ "split": "dev",
1255
+ "type": "choice",
1256
+ "k": 4,
1257
+ "teacher_raw_sum": null,
1258
+ "teacher_proxy_usable": false,
1259
+ "teacher_argmax_matches_gold": null,
1260
+ "target_transform": "no_teacher"
1261
+ },
1262
+ {
1263
+ "id": "doom:basic:1002:2:action",
1264
+ "split": "dev",
1265
+ "type": "choice",
1266
+ "k": 4,
1267
+ "teacher_raw_sum": null,
1268
+ "teacher_proxy_usable": false,
1269
+ "teacher_argmax_matches_gold": null,
1270
+ "target_transform": "no_teacher"
1271
+ },
1272
+ {
1273
+ "id": "doom:basic:1002:3:action",
1274
+ "split": "dev",
1275
+ "type": "choice",
1276
+ "k": 4,
1277
+ "teacher_raw_sum": null,
1278
+ "teacher_proxy_usable": false,
1279
+ "teacher_argmax_matches_gold": null,
1280
+ "target_transform": "no_teacher"
1281
+ },
1282
+ {
1283
+ "id": "doom:basic:1002:4:action",
1284
+ "split": "dev",
1285
+ "type": "choice",
1286
+ "k": 4,
1287
+ "teacher_raw_sum": null,
1288
+ "teacher_proxy_usable": false,
1289
+ "teacher_argmax_matches_gold": null,
1290
+ "target_transform": "no_teacher"
1291
+ },
1292
+ {
1293
+ "id": "doom:basic:1002:5:action",
1294
+ "split": "dev",
1295
+ "type": "choice",
1296
+ "k": 4,
1297
+ "teacher_raw_sum": null,
1298
+ "teacher_proxy_usable": false,
1299
+ "teacher_argmax_matches_gold": null,
1300
+ "target_transform": "no_teacher"
1301
+ },
1302
+ {
1303
+ "id": "doom:basic:1002:6:action",
1304
+ "split": "dev",
1305
+ "type": "choice",
1306
+ "k": 4,
1307
+ "teacher_raw_sum": null,
1308
+ "teacher_proxy_usable": false,
1309
+ "teacher_argmax_matches_gold": null,
1310
+ "target_transform": "no_teacher"
1311
+ },
1312
+ {
1313
+ "id": "doom:basic:1002:7:action",
1314
+ "split": "dev",
1315
+ "type": "choice",
1316
+ "k": 4,
1317
+ "teacher_raw_sum": null,
1318
+ "teacher_proxy_usable": false,
1319
+ "teacher_argmax_matches_gold": null,
1320
+ "target_transform": "no_teacher"
1321
+ },
1322
+ {
1323
+ "id": "doom:basic:1003:0:action",
1324
+ "split": "dev",
1325
+ "type": "choice",
1326
+ "k": 4,
1327
+ "teacher_raw_sum": null,
1328
+ "teacher_proxy_usable": false,
1329
+ "teacher_argmax_matches_gold": null,
1330
+ "target_transform": "no_teacher"
1331
+ },
1332
+ {
1333
+ "id": "doom:basic:1003:1:action",
1334
+ "split": "dev",
1335
+ "type": "choice",
1336
+ "k": 4,
1337
+ "teacher_raw_sum": null,
1338
+ "teacher_proxy_usable": false,
1339
+ "teacher_argmax_matches_gold": null,
1340
+ "target_transform": "no_teacher"
1341
+ },
1342
+ {
1343
+ "id": "doom:basic:1003:2:action",
1344
+ "split": "dev",
1345
+ "type": "choice",
1346
+ "k": 4,
1347
+ "teacher_raw_sum": null,
1348
+ "teacher_proxy_usable": false,
1349
+ "teacher_argmax_matches_gold": null,
1350
+ "target_transform": "no_teacher"
1351
+ },
1352
+ {
1353
+ "id": "doom:basic:1003:3:action",
1354
+ "split": "dev",
1355
+ "type": "choice",
1356
+ "k": 4,
1357
+ "teacher_raw_sum": null,
1358
+ "teacher_proxy_usable": false,
1359
+ "teacher_argmax_matches_gold": null,
1360
+ "target_transform": "no_teacher"
1361
+ },
1362
+ {
1363
+ "id": "doom:basic:1003:4:action",
1364
+ "split": "dev",
1365
+ "type": "choice",
1366
+ "k": 4,
1367
+ "teacher_raw_sum": null,
1368
+ "teacher_proxy_usable": false,
1369
+ "teacher_argmax_matches_gold": null,
1370
+ "target_transform": "no_teacher"
1371
+ },
1372
+ {
1373
+ "id": "doom:basic:1003:5:action",
1374
+ "split": "dev",
1375
+ "type": "choice",
1376
+ "k": 4,
1377
+ "teacher_raw_sum": null,
1378
+ "teacher_proxy_usable": false,
1379
+ "teacher_argmax_matches_gold": null,
1380
+ "target_transform": "no_teacher"
1381
+ },
1382
+ {
1383
+ "id": "doom:basic:1003:6:action",
1384
+ "split": "dev",
1385
+ "type": "choice",
1386
+ "k": 4,
1387
+ "teacher_raw_sum": null,
1388
+ "teacher_proxy_usable": false,
1389
+ "teacher_argmax_matches_gold": null,
1390
+ "target_transform": "no_teacher"
1391
+ },
1392
+ {
1393
+ "id": "doom:basic:1003:7:action",
1394
+ "split": "dev",
1395
+ "type": "choice",
1396
+ "k": 4,
1397
+ "teacher_raw_sum": null,
1398
+ "teacher_proxy_usable": false,
1399
+ "teacher_argmax_matches_gold": null,
1400
+ "target_transform": "no_teacher"
1401
+ },
1402
+ {
1403
+ "id": "doom:basic:2000:0:action",
1404
+ "split": "calibration",
1405
+ "type": "choice",
1406
+ "k": 4,
1407
+ "teacher_raw_sum": null,
1408
+ "teacher_proxy_usable": false,
1409
+ "teacher_argmax_matches_gold": null,
1410
+ "target_transform": "no_teacher"
1411
+ },
1412
+ {
1413
+ "id": "doom:basic:2000:1:action",
1414
+ "split": "calibration",
1415
+ "type": "choice",
1416
+ "k": 4,
1417
+ "teacher_raw_sum": null,
1418
+ "teacher_proxy_usable": false,
1419
+ "teacher_argmax_matches_gold": null,
1420
+ "target_transform": "no_teacher"
1421
+ },
1422
+ {
1423
+ "id": "doom:basic:2000:2:action",
1424
+ "split": "calibration",
1425
+ "type": "choice",
1426
+ "k": 4,
1427
+ "teacher_raw_sum": null,
1428
+ "teacher_proxy_usable": false,
1429
+ "teacher_argmax_matches_gold": null,
1430
+ "target_transform": "no_teacher"
1431
+ },
1432
+ {
1433
+ "id": "doom:basic:2000:3:action",
1434
+ "split": "calibration",
1435
+ "type": "choice",
1436
+ "k": 4,
1437
+ "teacher_raw_sum": null,
1438
+ "teacher_proxy_usable": false,
1439
+ "teacher_argmax_matches_gold": null,
1440
+ "target_transform": "no_teacher"
1441
+ },
1442
+ {
1443
+ "id": "doom:basic:2000:4:action",
1444
+ "split": "calibration",
1445
+ "type": "choice",
1446
+ "k": 4,
1447
+ "teacher_raw_sum": null,
1448
+ "teacher_proxy_usable": false,
1449
+ "teacher_argmax_matches_gold": null,
1450
+ "target_transform": "no_teacher"
1451
+ },
1452
+ {
1453
+ "id": "doom:basic:2001:0:action",
1454
+ "split": "calibration",
1455
+ "type": "choice",
1456
+ "k": 4,
1457
+ "teacher_raw_sum": null,
1458
+ "teacher_proxy_usable": false,
1459
+ "teacher_argmax_matches_gold": null,
1460
+ "target_transform": "no_teacher"
1461
+ },
1462
+ {
1463
+ "id": "doom:basic:2001:1:action",
1464
+ "split": "calibration",
1465
+ "type": "choice",
1466
+ "k": 4,
1467
+ "teacher_raw_sum": null,
1468
+ "teacher_proxy_usable": false,
1469
+ "teacher_argmax_matches_gold": null,
1470
+ "target_transform": "no_teacher"
1471
+ },
1472
+ {
1473
+ "id": "doom:basic:2001:2:action",
1474
+ "split": "calibration",
1475
+ "type": "choice",
1476
+ "k": 4,
1477
+ "teacher_raw_sum": null,
1478
+ "teacher_proxy_usable": false,
1479
+ "teacher_argmax_matches_gold": null,
1480
+ "target_transform": "no_teacher"
1481
+ },
1482
+ {
1483
+ "id": "doom:basic:2001:3:action",
1484
+ "split": "calibration",
1485
+ "type": "choice",
1486
+ "k": 4,
1487
+ "teacher_raw_sum": null,
1488
+ "teacher_proxy_usable": false,
1489
+ "teacher_argmax_matches_gold": null,
1490
+ "target_transform": "no_teacher"
1491
+ },
1492
+ {
1493
+ "id": "doom:basic:2001:4:action",
1494
+ "split": "calibration",
1495
+ "type": "choice",
1496
+ "k": 4,
1497
+ "teacher_raw_sum": null,
1498
+ "teacher_proxy_usable": false,
1499
+ "teacher_argmax_matches_gold": null,
1500
+ "target_transform": "no_teacher"
1501
+ },
1502
+ {
1503
+ "id": "doom:basic:2001:5:action",
1504
+ "split": "calibration",
1505
+ "type": "choice",
1506
+ "k": 4,
1507
+ "teacher_raw_sum": null,
1508
+ "teacher_proxy_usable": false,
1509
+ "teacher_argmax_matches_gold": null,
1510
+ "target_transform": "no_teacher"
1511
+ },
1512
+ {
1513
+ "id": "doom:basic:2001:6:action",
1514
+ "split": "calibration",
1515
+ "type": "choice",
1516
+ "k": 4,
1517
+ "teacher_raw_sum": null,
1518
+ "teacher_proxy_usable": false,
1519
+ "teacher_argmax_matches_gold": null,
1520
+ "target_transform": "no_teacher"
1521
+ },
1522
+ {
1523
+ "id": "doom:basic:2001:7:action",
1524
+ "split": "calibration",
1525
+ "type": "choice",
1526
+ "k": 4,
1527
+ "teacher_raw_sum": null,
1528
+ "teacher_proxy_usable": false,
1529
+ "teacher_argmax_matches_gold": null,
1530
+ "target_transform": "no_teacher"
1531
+ },
1532
+ {
1533
+ "id": "doom:basic:2002:0:action",
1534
+ "split": "calibration",
1535
+ "type": "choice",
1536
+ "k": 4,
1537
+ "teacher_raw_sum": null,
1538
+ "teacher_proxy_usable": false,
1539
+ "teacher_argmax_matches_gold": null,
1540
+ "target_transform": "no_teacher"
1541
+ },
1542
+ {
1543
+ "id": "doom:basic:2002:1:action",
1544
+ "split": "calibration",
1545
+ "type": "choice",
1546
+ "k": 4,
1547
+ "teacher_raw_sum": null,
1548
+ "teacher_proxy_usable": false,
1549
+ "teacher_argmax_matches_gold": null,
1550
+ "target_transform": "no_teacher"
1551
+ },
1552
+ {
1553
+ "id": "doom:basic:2002:2:action",
1554
+ "split": "calibration",
1555
+ "type": "choice",
1556
+ "k": 4,
1557
+ "teacher_raw_sum": null,
1558
+ "teacher_proxy_usable": false,
1559
+ "teacher_argmax_matches_gold": null,
1560
+ "target_transform": "no_teacher"
1561
+ },
1562
+ {
1563
+ "id": "doom:basic:2002:3:action",
1564
+ "split": "calibration",
1565
+ "type": "choice",
1566
+ "k": 4,
1567
+ "teacher_raw_sum": null,
1568
+ "teacher_proxy_usable": false,
1569
+ "teacher_argmax_matches_gold": null,
1570
+ "target_transform": "no_teacher"
1571
+ },
1572
+ {
1573
+ "id": "doom:basic:2002:4:action",
1574
+ "split": "calibration",
1575
+ "type": "choice",
1576
+ "k": 4,
1577
+ "teacher_raw_sum": null,
1578
+ "teacher_proxy_usable": false,
1579
+ "teacher_argmax_matches_gold": null,
1580
+ "target_transform": "no_teacher"
1581
+ },
1582
+ {
1583
+ "id": "doom:basic:2002:5:action",
1584
+ "split": "calibration",
1585
+ "type": "choice",
1586
+ "k": 4,
1587
+ "teacher_raw_sum": null,
1588
+ "teacher_proxy_usable": false,
1589
+ "teacher_argmax_matches_gold": null,
1590
+ "target_transform": "no_teacher"
1591
+ },
1592
+ {
1593
+ "id": "doom:basic:2002:6:action",
1594
+ "split": "calibration",
1595
+ "type": "choice",
1596
+ "k": 4,
1597
+ "teacher_raw_sum": null,
1598
+ "teacher_proxy_usable": false,
1599
+ "teacher_argmax_matches_gold": null,
1600
+ "target_transform": "no_teacher"
1601
+ },
1602
+ {
1603
+ "id": "doom:basic:2002:7:action",
1604
+ "split": "calibration",
1605
+ "type": "choice",
1606
+ "k": 4,
1607
+ "teacher_raw_sum": null,
1608
+ "teacher_proxy_usable": false,
1609
+ "teacher_argmax_matches_gold": null,
1610
+ "target_transform": "no_teacher"
1611
+ },
1612
+ {
1613
+ "id": "doom:basic:2002:8:action",
1614
+ "split": "calibration",
1615
+ "type": "choice",
1616
+ "k": 4,
1617
+ "teacher_raw_sum": null,
1618
+ "teacher_proxy_usable": false,
1619
+ "teacher_argmax_matches_gold": null,
1620
+ "target_transform": "no_teacher"
1621
+ },
1622
+ {
1623
+ "id": "doom:basic:2003:0:action",
1624
+ "split": "calibration",
1625
+ "type": "choice",
1626
+ "k": 4,
1627
+ "teacher_raw_sum": null,
1628
+ "teacher_proxy_usable": false,
1629
+ "teacher_argmax_matches_gold": null,
1630
+ "target_transform": "no_teacher"
1631
+ },
1632
+ {
1633
+ "id": "doom:basic:2003:1:action",
1634
+ "split": "calibration",
1635
+ "type": "choice",
1636
+ "k": 4,
1637
+ "teacher_raw_sum": null,
1638
+ "teacher_proxy_usable": false,
1639
+ "teacher_argmax_matches_gold": null,
1640
+ "target_transform": "no_teacher"
1641
+ },
1642
+ {
1643
+ "id": "doom:basic:2003:2:action",
1644
+ "split": "calibration",
1645
+ "type": "choice",
1646
+ "k": 4,
1647
+ "teacher_raw_sum": null,
1648
+ "teacher_proxy_usable": false,
1649
+ "teacher_argmax_matches_gold": null,
1650
+ "target_transform": "no_teacher"
1651
+ },
1652
+ {
1653
+ "id": "doom:basic:2003:3:action",
1654
+ "split": "calibration",
1655
+ "type": "choice",
1656
+ "k": 4,
1657
+ "teacher_raw_sum": null,
1658
+ "teacher_proxy_usable": false,
1659
+ "teacher_argmax_matches_gold": null,
1660
+ "target_transform": "no_teacher"
1661
+ },
1662
+ {
1663
+ "id": "doom:basic:2003:4:action",
1664
+ "split": "calibration",
1665
+ "type": "choice",
1666
+ "k": 4,
1667
+ "teacher_raw_sum": null,
1668
+ "teacher_proxy_usable": false,
1669
+ "teacher_argmax_matches_gold": null,
1670
+ "target_transform": "no_teacher"
1671
+ },
1672
+ {
1673
+ "id": "doom:basic:2003:5:action",
1674
+ "split": "calibration",
1675
+ "type": "choice",
1676
+ "k": 4,
1677
+ "teacher_raw_sum": null,
1678
+ "teacher_proxy_usable": false,
1679
+ "teacher_argmax_matches_gold": null,
1680
+ "target_transform": "no_teacher"
1681
+ },
1682
+ {
1683
+ "id": "doom:basic:2003:6:action",
1684
+ "split": "calibration",
1685
+ "type": "choice",
1686
+ "k": 4,
1687
+ "teacher_raw_sum": null,
1688
+ "teacher_proxy_usable": false,
1689
+ "teacher_argmax_matches_gold": null,
1690
+ "target_transform": "no_teacher"
1691
+ },
1692
+ {
1693
+ "id": "doom:basic:2003:7:action",
1694
+ "split": "calibration",
1695
+ "type": "choice",
1696
+ "k": 4,
1697
+ "teacher_raw_sum": null,
1698
+ "teacher_proxy_usable": false,
1699
+ "teacher_argmax_matches_gold": null,
1700
+ "target_transform": "no_teacher"
1701
+ },
1702
+ {
1703
+ "id": "doom:basic:3000:0:action",
1704
+ "split": "test",
1705
+ "type": "choice",
1706
+ "k": 4,
1707
+ "teacher_raw_sum": null,
1708
+ "teacher_proxy_usable": false,
1709
+ "teacher_argmax_matches_gold": null,
1710
+ "target_transform": "no_teacher"
1711
+ },
1712
+ {
1713
+ "id": "doom:basic:3000:1:action",
1714
+ "split": "test",
1715
+ "type": "choice",
1716
+ "k": 4,
1717
+ "teacher_raw_sum": null,
1718
+ "teacher_proxy_usable": false,
1719
+ "teacher_argmax_matches_gold": null,
1720
+ "target_transform": "no_teacher"
1721
+ },
1722
+ {
1723
+ "id": "doom:basic:3001:0:action",
1724
+ "split": "test",
1725
+ "type": "choice",
1726
+ "k": 4,
1727
+ "teacher_raw_sum": null,
1728
+ "teacher_proxy_usable": false,
1729
+ "teacher_argmax_matches_gold": null,
1730
+ "target_transform": "no_teacher"
1731
+ },
1732
+ {
1733
+ "id": "doom:basic:3001:1:action",
1734
+ "split": "test",
1735
+ "type": "choice",
1736
+ "k": 4,
1737
+ "teacher_raw_sum": null,
1738
+ "teacher_proxy_usable": false,
1739
+ "teacher_argmax_matches_gold": null,
1740
+ "target_transform": "no_teacher"
1741
+ },
1742
+ {
1743
+ "id": "doom:basic:3001:2:action",
1744
+ "split": "test",
1745
+ "type": "choice",
1746
+ "k": 4,
1747
+ "teacher_raw_sum": null,
1748
+ "teacher_proxy_usable": false,
1749
+ "teacher_argmax_matches_gold": null,
1750
+ "target_transform": "no_teacher"
1751
+ },
1752
+ {
1753
+ "id": "doom:basic:3001:3:action",
1754
+ "split": "test",
1755
+ "type": "choice",
1756
+ "k": 4,
1757
+ "teacher_raw_sum": null,
1758
+ "teacher_proxy_usable": false,
1759
+ "teacher_argmax_matches_gold": null,
1760
+ "target_transform": "no_teacher"
1761
+ },
1762
+ {
1763
+ "id": "doom:basic:3001:4:action",
1764
+ "split": "test",
1765
+ "type": "choice",
1766
+ "k": 4,
1767
+ "teacher_raw_sum": null,
1768
+ "teacher_proxy_usable": false,
1769
+ "teacher_argmax_matches_gold": null,
1770
+ "target_transform": "no_teacher"
1771
+ },
1772
+ {
1773
+ "id": "doom:basic:3002:0:action",
1774
+ "split": "test",
1775
+ "type": "choice",
1776
+ "k": 4,
1777
+ "teacher_raw_sum": null,
1778
+ "teacher_proxy_usable": false,
1779
+ "teacher_argmax_matches_gold": null,
1780
+ "target_transform": "no_teacher"
1781
+ },
1782
+ {
1783
+ "id": "doom:basic:3002:1:action",
1784
+ "split": "test",
1785
+ "type": "choice",
1786
+ "k": 4,
1787
+ "teacher_raw_sum": null,
1788
+ "teacher_proxy_usable": false,
1789
+ "teacher_argmax_matches_gold": null,
1790
+ "target_transform": "no_teacher"
1791
+ },
1792
+ {
1793
+ "id": "doom:basic:3002:2:action",
1794
+ "split": "test",
1795
+ "type": "choice",
1796
+ "k": 4,
1797
+ "teacher_raw_sum": null,
1798
+ "teacher_proxy_usable": false,
1799
+ "teacher_argmax_matches_gold": null,
1800
+ "target_transform": "no_teacher"
1801
+ },
1802
+ {
1803
+ "id": "doom:basic:3002:3:action",
1804
+ "split": "test",
1805
+ "type": "choice",
1806
+ "k": 4,
1807
+ "teacher_raw_sum": null,
1808
+ "teacher_proxy_usable": false,
1809
+ "teacher_argmax_matches_gold": null,
1810
+ "target_transform": "no_teacher"
1811
+ },
1812
+ {
1813
+ "id": "doom:basic:3002:4:action",
1814
+ "split": "test",
1815
+ "type": "choice",
1816
+ "k": 4,
1817
+ "teacher_raw_sum": null,
1818
+ "teacher_proxy_usable": false,
1819
+ "teacher_argmax_matches_gold": null,
1820
+ "target_transform": "no_teacher"
1821
+ },
1822
+ {
1823
+ "id": "doom:basic:3002:5:action",
1824
+ "split": "test",
1825
+ "type": "choice",
1826
+ "k": 4,
1827
+ "teacher_raw_sum": null,
1828
+ "teacher_proxy_usable": false,
1829
+ "teacher_argmax_matches_gold": null,
1830
+ "target_transform": "no_teacher"
1831
+ },
1832
+ {
1833
+ "id": "doom:basic:3002:6:action",
1834
+ "split": "test",
1835
+ "type": "choice",
1836
+ "k": 4,
1837
+ "teacher_raw_sum": null,
1838
+ "teacher_proxy_usable": false,
1839
+ "teacher_argmax_matches_gold": null,
1840
+ "target_transform": "no_teacher"
1841
+ },
1842
+ {
1843
+ "id": "doom:basic:3002:7:action",
1844
+ "split": "test",
1845
+ "type": "choice",
1846
+ "k": 4,
1847
+ "teacher_raw_sum": null,
1848
+ "teacher_proxy_usable": false,
1849
+ "teacher_argmax_matches_gold": null,
1850
+ "target_transform": "no_teacher"
1851
+ },
1852
+ {
1853
+ "id": "doom:basic:3003:0:action",
1854
+ "split": "test",
1855
+ "type": "choice",
1856
+ "k": 4,
1857
+ "teacher_raw_sum": null,
1858
+ "teacher_proxy_usable": false,
1859
+ "teacher_argmax_matches_gold": null,
1860
+ "target_transform": "no_teacher"
1861
+ },
1862
+ {
1863
+ "id": "doom:basic:3003:1:action",
1864
+ "split": "test",
1865
+ "type": "choice",
1866
+ "k": 4,
1867
+ "teacher_raw_sum": null,
1868
+ "teacher_proxy_usable": false,
1869
+ "teacher_argmax_matches_gold": null,
1870
+ "target_transform": "no_teacher"
1871
+ },
1872
+ {
1873
+ "id": "doom:basic:3003:2:action",
1874
+ "split": "test",
1875
+ "type": "choice",
1876
+ "k": 4,
1877
+ "teacher_raw_sum": null,
1878
+ "teacher_proxy_usable": false,
1879
+ "teacher_argmax_matches_gold": null,
1880
+ "target_transform": "no_teacher"
1881
+ },
1882
+ {
1883
+ "id": "doom:basic:3003:3:action",
1884
+ "split": "test",
1885
+ "type": "choice",
1886
+ "k": 4,
1887
+ "teacher_raw_sum": null,
1888
+ "teacher_proxy_usable": false,
1889
+ "teacher_argmax_matches_gold": null,
1890
+ "target_transform": "no_teacher"
1891
+ },
1892
+ {
1893
+ "id": "doom:basic:3003:4:action",
1894
+ "split": "test",
1895
+ "type": "choice",
1896
+ "k": 4,
1897
+ "teacher_raw_sum": null,
1898
+ "teacher_proxy_usable": false,
1899
+ "teacher_argmax_matches_gold": null,
1900
+ "target_transform": "no_teacher"
1901
+ },
1902
+ {
1903
+ "id": "doom:basic:3004:0:action",
1904
+ "split": "test",
1905
+ "type": "choice",
1906
+ "k": 4,
1907
+ "teacher_raw_sum": null,
1908
+ "teacher_proxy_usable": false,
1909
+ "teacher_argmax_matches_gold": null,
1910
+ "target_transform": "no_teacher"
1911
+ },
1912
+ {
1913
+ "id": "doom:basic:3004:1:action",
1914
+ "split": "test",
1915
+ "type": "choice",
1916
+ "k": 4,
1917
+ "teacher_raw_sum": null,
1918
+ "teacher_proxy_usable": false,
1919
+ "teacher_argmax_matches_gold": null,
1920
+ "target_transform": "no_teacher"
1921
+ },
1922
+ {
1923
+ "id": "doom:basic:3004:2:action",
1924
+ "split": "test",
1925
+ "type": "choice",
1926
+ "k": 4,
1927
+ "teacher_raw_sum": null,
1928
+ "teacher_proxy_usable": false,
1929
+ "teacher_argmax_matches_gold": null,
1930
+ "target_transform": "no_teacher"
1931
+ },
1932
+ {
1933
+ "id": "doom:basic:3004:3:action",
1934
+ "split": "test",
1935
+ "type": "choice",
1936
+ "k": 4,
1937
+ "teacher_raw_sum": null,
1938
+ "teacher_proxy_usable": false,
1939
+ "teacher_argmax_matches_gold": null,
1940
+ "target_transform": "no_teacher"
1941
+ },
1942
+ {
1943
+ "id": "doom:basic:3004:4:action",
1944
+ "split": "test",
1945
+ "type": "choice",
1946
+ "k": 4,
1947
+ "teacher_raw_sum": null,
1948
+ "teacher_proxy_usable": false,
1949
+ "teacher_argmax_matches_gold": null,
1950
+ "target_transform": "no_teacher"
1951
+ },
1952
+ {
1953
+ "id": "doom:basic:3004:5:action",
1954
+ "split": "test",
1955
+ "type": "choice",
1956
+ "k": 4,
1957
+ "teacher_raw_sum": null,
1958
+ "teacher_proxy_usable": false,
1959
+ "teacher_argmax_matches_gold": null,
1960
+ "target_transform": "no_teacher"
1961
+ },
1962
+ {
1963
+ "id": "doom:basic:3005:0:action",
1964
+ "split": "test",
1965
+ "type": "choice",
1966
+ "k": 4,
1967
+ "teacher_raw_sum": null,
1968
+ "teacher_proxy_usable": false,
1969
+ "teacher_argmax_matches_gold": null,
1970
+ "target_transform": "no_teacher"
1971
+ },
1972
+ {
1973
+ "id": "doom:basic:3005:1:action",
1974
+ "split": "test",
1975
+ "type": "choice",
1976
+ "k": 4,
1977
+ "teacher_raw_sum": null,
1978
+ "teacher_proxy_usable": false,
1979
+ "teacher_argmax_matches_gold": null,
1980
+ "target_transform": "no_teacher"
1981
+ },
1982
+ {
1983
+ "id": "doom:basic:3005:2:action",
1984
+ "split": "test",
1985
+ "type": "choice",
1986
+ "k": 4,
1987
+ "teacher_raw_sum": null,
1988
+ "teacher_proxy_usable": false,
1989
+ "teacher_argmax_matches_gold": null,
1990
+ "target_transform": "no_teacher"
1991
+ },
1992
+ {
1993
+ "id": "doom:basic:3005:3:action",
1994
+ "split": "test",
1995
+ "type": "choice",
1996
+ "k": 4,
1997
+ "teacher_raw_sum": null,
1998
+ "teacher_proxy_usable": false,
1999
+ "teacher_argmax_matches_gold": null,
2000
+ "target_transform": "no_teacher"
2001
+ },
2002
+ {
2003
+ "id": "doom:basic:3005:4:action",
2004
+ "split": "test",
2005
+ "type": "choice",
2006
+ "k": 4,
2007
+ "teacher_raw_sum": null,
2008
+ "teacher_proxy_usable": false,
2009
+ "teacher_argmax_matches_gold": null,
2010
+ "target_transform": "no_teacher"
2011
+ },
2012
+ {
2013
+ "id": "doom:basic:3005:5:action",
2014
+ "split": "test",
2015
+ "type": "choice",
2016
+ "k": 4,
2017
+ "teacher_raw_sum": null,
2018
+ "teacher_proxy_usable": false,
2019
+ "teacher_argmax_matches_gold": null,
2020
+ "target_transform": "no_teacher"
2021
+ },
2022
+ {
2023
+ "id": "doom:basic:3005:6:action",
2024
+ "split": "test",
2025
+ "type": "choice",
2026
+ "k": 4,
2027
+ "teacher_raw_sum": null,
2028
+ "teacher_proxy_usable": false,
2029
+ "teacher_argmax_matches_gold": null,
2030
+ "target_transform": "no_teacher"
2031
+ },
2032
+ {
2033
+ "id": "doom:basic:3005:7:action",
2034
+ "split": "test",
2035
+ "type": "choice",
2036
+ "k": 4,
2037
+ "teacher_raw_sum": null,
2038
+ "teacher_proxy_usable": false,
2039
+ "teacher_argmax_matches_gold": null,
2040
+ "target_transform": "no_teacher"
2041
+ },
2042
+ {
2043
+ "id": "doom:basic:3006:0:action",
2044
+ "split": "test",
2045
+ "type": "choice",
2046
+ "k": 4,
2047
+ "teacher_raw_sum": null,
2048
+ "teacher_proxy_usable": false,
2049
+ "teacher_argmax_matches_gold": null,
2050
+ "target_transform": "no_teacher"
2051
+ },
2052
+ {
2053
+ "id": "doom:basic:3006:1:action",
2054
+ "split": "test",
2055
+ "type": "choice",
2056
+ "k": 4,
2057
+ "teacher_raw_sum": null,
2058
+ "teacher_proxy_usable": false,
2059
+ "teacher_argmax_matches_gold": null,
2060
+ "target_transform": "no_teacher"
2061
+ },
2062
+ {
2063
+ "id": "doom:basic:3006:2:action",
2064
+ "split": "test",
2065
+ "type": "choice",
2066
+ "k": 4,
2067
+ "teacher_raw_sum": null,
2068
+ "teacher_proxy_usable": false,
2069
+ "teacher_argmax_matches_gold": null,
2070
+ "target_transform": "no_teacher"
2071
+ },
2072
+ {
2073
+ "id": "doom:basic:3006:3:action",
2074
+ "split": "test",
2075
+ "type": "choice",
2076
+ "k": 4,
2077
+ "teacher_raw_sum": null,
2078
+ "teacher_proxy_usable": false,
2079
+ "teacher_argmax_matches_gold": null,
2080
+ "target_transform": "no_teacher"
2081
+ },
2082
+ {
2083
+ "id": "doom:basic:3006:4:action",
2084
+ "split": "test",
2085
+ "type": "choice",
2086
+ "k": 4,
2087
+ "teacher_raw_sum": null,
2088
+ "teacher_proxy_usable": false,
2089
+ "teacher_argmax_matches_gold": null,
2090
+ "target_transform": "no_teacher"
2091
+ },
2092
+ {
2093
+ "id": "doom:basic:3006:5:action",
2094
+ "split": "test",
2095
+ "type": "choice",
2096
+ "k": 4,
2097
+ "teacher_raw_sum": null,
2098
+ "teacher_proxy_usable": false,
2099
+ "teacher_argmax_matches_gold": null,
2100
+ "target_transform": "no_teacher"
2101
+ },
2102
+ {
2103
+ "id": "doom:basic:3006:6:action",
2104
+ "split": "test",
2105
+ "type": "choice",
2106
+ "k": 4,
2107
+ "teacher_raw_sum": null,
2108
+ "teacher_proxy_usable": false,
2109
+ "teacher_argmax_matches_gold": null,
2110
+ "target_transform": "no_teacher"
2111
+ },
2112
+ {
2113
+ "id": "doom:basic:3006:7:action",
2114
+ "split": "test",
2115
+ "type": "choice",
2116
+ "k": 4,
2117
+ "teacher_raw_sum": null,
2118
+ "teacher_proxy_usable": false,
2119
+ "teacher_argmax_matches_gold": null,
2120
+ "target_transform": "no_teacher"
2121
+ },
2122
+ {
2123
+ "id": "doom:basic:3006:8:action",
2124
+ "split": "test",
2125
+ "type": "choice",
2126
+ "k": 4,
2127
+ "teacher_raw_sum": null,
2128
+ "teacher_proxy_usable": false,
2129
+ "teacher_argmax_matches_gold": null,
2130
+ "target_transform": "no_teacher"
2131
+ },
2132
+ {
2133
+ "id": "doom:basic:3006:9:action",
2134
+ "split": "test",
2135
+ "type": "choice",
2136
+ "k": 4,
2137
+ "teacher_raw_sum": null,
2138
+ "teacher_proxy_usable": false,
2139
+ "teacher_argmax_matches_gold": null,
2140
+ "target_transform": "no_teacher"
2141
+ },
2142
+ {
2143
+ "id": "doom:basic:3006:10:action",
2144
+ "split": "test",
2145
+ "type": "choice",
2146
+ "k": 4,
2147
+ "teacher_raw_sum": null,
2148
+ "teacher_proxy_usable": false,
2149
+ "teacher_argmax_matches_gold": null,
2150
+ "target_transform": "no_teacher"
2151
+ },
2152
+ {
2153
+ "id": "doom:basic:3006:11:action",
2154
+ "split": "test",
2155
+ "type": "choice",
2156
+ "k": 4,
2157
+ "teacher_raw_sum": null,
2158
+ "teacher_proxy_usable": false,
2159
+ "teacher_argmax_matches_gold": null,
2160
+ "target_transform": "no_teacher"
2161
+ },
2162
+ {
2163
+ "id": "doom:basic:3006:12:action",
2164
+ "split": "test",
2165
+ "type": "choice",
2166
+ "k": 4,
2167
+ "teacher_raw_sum": null,
2168
+ "teacher_proxy_usable": false,
2169
+ "teacher_argmax_matches_gold": null,
2170
+ "target_transform": "no_teacher"
2171
+ },
2172
+ {
2173
+ "id": "doom:basic:3006:13:action",
2174
+ "split": "test",
2175
+ "type": "choice",
2176
+ "k": 4,
2177
+ "teacher_raw_sum": null,
2178
+ "teacher_proxy_usable": false,
2179
+ "teacher_argmax_matches_gold": null,
2180
+ "target_transform": "no_teacher"
2181
+ },
2182
+ {
2183
+ "id": "doom:basic:3006:14:action",
2184
+ "split": "test",
2185
+ "type": "choice",
2186
+ "k": 4,
2187
+ "teacher_raw_sum": null,
2188
+ "teacher_proxy_usable": false,
2189
+ "teacher_argmax_matches_gold": null,
2190
+ "target_transform": "no_teacher"
2191
+ },
2192
+ {
2193
+ "id": "doom:basic:3006:15:action",
2194
+ "split": "test",
2195
+ "type": "choice",
2196
+ "k": 4,
2197
+ "teacher_raw_sum": null,
2198
+ "teacher_proxy_usable": false,
2199
+ "teacher_argmax_matches_gold": null,
2200
+ "target_transform": "no_teacher"
2201
+ },
2202
+ {
2203
+ "id": "doom:basic:3006:16:action",
2204
+ "split": "test",
2205
+ "type": "choice",
2206
+ "k": 4,
2207
+ "teacher_raw_sum": null,
2208
+ "teacher_proxy_usable": false,
2209
+ "teacher_argmax_matches_gold": null,
2210
+ "target_transform": "no_teacher"
2211
+ },
2212
+ {
2213
+ "id": "doom:basic:3006:17:action",
2214
+ "split": "test",
2215
+ "type": "choice",
2216
+ "k": 4,
2217
+ "teacher_raw_sum": null,
2218
+ "teacher_proxy_usable": false,
2219
+ "teacher_argmax_matches_gold": null,
2220
+ "target_transform": "no_teacher"
2221
+ },
2222
+ {
2223
+ "id": "doom:basic:3006:18:action",
2224
+ "split": "test",
2225
+ "type": "choice",
2226
+ "k": 4,
2227
+ "teacher_raw_sum": null,
2228
+ "teacher_proxy_usable": false,
2229
+ "teacher_argmax_matches_gold": null,
2230
+ "target_transform": "no_teacher"
2231
+ },
2232
+ {
2233
+ "id": "doom:basic:3006:19:action",
2234
+ "split": "test",
2235
+ "type": "choice",
2236
+ "k": 4,
2237
+ "teacher_raw_sum": null,
2238
+ "teacher_proxy_usable": false,
2239
+ "teacher_argmax_matches_gold": null,
2240
+ "target_transform": "no_teacher"
2241
+ },
2242
+ {
2243
+ "id": "doom:basic:3006:20:action",
2244
+ "split": "test",
2245
+ "type": "choice",
2246
+ "k": 4,
2247
+ "teacher_raw_sum": null,
2248
+ "teacher_proxy_usable": false,
2249
+ "teacher_argmax_matches_gold": null,
2250
+ "target_transform": "no_teacher"
2251
+ },
2252
+ {
2253
+ "id": "doom:basic:3006:21:action",
2254
+ "split": "test",
2255
+ "type": "choice",
2256
+ "k": 4,
2257
+ "teacher_raw_sum": null,
2258
+ "teacher_proxy_usable": false,
2259
+ "teacher_argmax_matches_gold": null,
2260
+ "target_transform": "no_teacher"
2261
+ },
2262
+ {
2263
+ "id": "doom:basic:3006:22:action",
2264
+ "split": "test",
2265
+ "type": "choice",
2266
+ "k": 4,
2267
+ "teacher_raw_sum": null,
2268
+ "teacher_proxy_usable": false,
2269
+ "teacher_argmax_matches_gold": null,
2270
+ "target_transform": "no_teacher"
2271
+ },
2272
+ {
2273
+ "id": "doom:basic:3007:0:action",
2274
+ "split": "test",
2275
+ "type": "choice",
2276
+ "k": 4,
2277
+ "teacher_raw_sum": null,
2278
+ "teacher_proxy_usable": false,
2279
+ "teacher_argmax_matches_gold": null,
2280
+ "target_transform": "no_teacher"
2281
+ },
2282
+ {
2283
+ "id": "doom:basic:3007:1:action",
2284
+ "split": "test",
2285
+ "type": "choice",
2286
+ "k": 4,
2287
+ "teacher_raw_sum": null,
2288
+ "teacher_proxy_usable": false,
2289
+ "teacher_argmax_matches_gold": null,
2290
+ "target_transform": "no_teacher"
2291
+ },
2292
+ {
2293
+ "id": "doom:basic:3007:2:action",
2294
+ "split": "test",
2295
+ "type": "choice",
2296
+ "k": 4,
2297
+ "teacher_raw_sum": null,
2298
+ "teacher_proxy_usable": false,
2299
+ "teacher_argmax_matches_gold": null,
2300
+ "target_transform": "no_teacher"
2301
+ },
2302
+ {
2303
+ "id": "doom:basic:3007:3:action",
2304
+ "split": "test",
2305
+ "type": "choice",
2306
+ "k": 4,
2307
+ "teacher_raw_sum": null,
2308
+ "teacher_proxy_usable": false,
2309
+ "teacher_argmax_matches_gold": null,
2310
+ "target_transform": "no_teacher"
2311
+ },
2312
+ {
2313
+ "id": "doom:basic:3007:4:action",
2314
+ "split": "test",
2315
+ "type": "choice",
2316
+ "k": 4,
2317
+ "teacher_raw_sum": null,
2318
+ "teacher_proxy_usable": false,
2319
+ "teacher_argmax_matches_gold": null,
2320
+ "target_transform": "no_teacher"
2321
+ },
2322
+ {
2323
+ "id": "doom:basic:3007:5:action",
2324
+ "split": "test",
2325
+ "type": "choice",
2326
+ "k": 4,
2327
+ "teacher_raw_sum": null,
2328
+ "teacher_proxy_usable": false,
2329
+ "teacher_argmax_matches_gold": null,
2330
+ "target_transform": "no_teacher"
2331
+ },
2332
+ {
2333
+ "id": "doom:basic:3007:6:action",
2334
+ "split": "test",
2335
+ "type": "choice",
2336
+ "k": 4,
2337
+ "teacher_raw_sum": null,
2338
+ "teacher_proxy_usable": false,
2339
+ "teacher_argmax_matches_gold": null,
2340
+ "target_transform": "no_teacher"
2341
+ },
2342
+ {
2343
+ "id": "doom:basic:3007:7:action",
2344
+ "split": "test",
2345
+ "type": "choice",
2346
+ "k": 4,
2347
+ "teacher_raw_sum": null,
2348
+ "teacher_proxy_usable": false,
2349
+ "teacher_argmax_matches_gold": null,
2350
+ "target_transform": "no_teacher"
2351
+ },
2352
+ {
2353
+ "id": "doom:basic:3007:8:action",
2354
+ "split": "test",
2355
+ "type": "choice",
2356
+ "k": 4,
2357
+ "teacher_raw_sum": null,
2358
+ "teacher_proxy_usable": false,
2359
+ "teacher_argmax_matches_gold": null,
2360
+ "target_transform": "no_teacher"
2361
+ },
2362
+ {
2363
+ "id": "doom:basic:4000:0:action",
2364
+ "split": "ood",
2365
+ "type": "choice",
2366
+ "k": 4,
2367
+ "teacher_raw_sum": null,
2368
+ "teacher_proxy_usable": false,
2369
+ "teacher_argmax_matches_gold": null,
2370
+ "target_transform": "no_teacher"
2371
+ },
2372
+ {
2373
+ "id": "doom:basic:4000:1:action",
2374
+ "split": "ood",
2375
+ "type": "choice",
2376
+ "k": 4,
2377
+ "teacher_raw_sum": null,
2378
+ "teacher_proxy_usable": false,
2379
+ "teacher_argmax_matches_gold": null,
2380
+ "target_transform": "no_teacher"
2381
+ },
2382
+ {
2383
+ "id": "doom:basic:4000:2:action",
2384
+ "split": "ood",
2385
+ "type": "choice",
2386
+ "k": 4,
2387
+ "teacher_raw_sum": null,
2388
+ "teacher_proxy_usable": false,
2389
+ "teacher_argmax_matches_gold": null,
2390
+ "target_transform": "no_teacher"
2391
+ },
2392
+ {
2393
+ "id": "doom:basic:4000:3:action",
2394
+ "split": "ood",
2395
+ "type": "choice",
2396
+ "k": 4,
2397
+ "teacher_raw_sum": null,
2398
+ "teacher_proxy_usable": false,
2399
+ "teacher_argmax_matches_gold": null,
2400
+ "target_transform": "no_teacher"
2401
+ },
2402
+ {
2403
+ "id": "doom:basic:4000:4:action",
2404
+ "split": "ood",
2405
+ "type": "choice",
2406
+ "k": 4,
2407
+ "teacher_raw_sum": null,
2408
+ "teacher_proxy_usable": false,
2409
+ "teacher_argmax_matches_gold": null,
2410
+ "target_transform": "no_teacher"
2411
+ },
2412
+ {
2413
+ "id": "doom:basic:4000:5:action",
2414
+ "split": "ood",
2415
+ "type": "choice",
2416
+ "k": 4,
2417
+ "teacher_raw_sum": null,
2418
+ "teacher_proxy_usable": false,
2419
+ "teacher_argmax_matches_gold": null,
2420
+ "target_transform": "no_teacher"
2421
+ },
2422
+ {
2423
+ "id": "doom:basic:4000:6:action",
2424
+ "split": "ood",
2425
+ "type": "choice",
2426
+ "k": 4,
2427
+ "teacher_raw_sum": null,
2428
+ "teacher_proxy_usable": false,
2429
+ "teacher_argmax_matches_gold": null,
2430
+ "target_transform": "no_teacher"
2431
+ },
2432
+ {
2433
+ "id": "doom:basic:4000:7:action",
2434
+ "split": "ood",
2435
+ "type": "choice",
2436
+ "k": 4,
2437
+ "teacher_raw_sum": null,
2438
+ "teacher_proxy_usable": false,
2439
+ "teacher_argmax_matches_gold": null,
2440
+ "target_transform": "no_teacher"
2441
+ },
2442
+ {
2443
+ "id": "doom:basic:4001:0:action",
2444
+ "split": "ood",
2445
+ "type": "choice",
2446
+ "k": 4,
2447
+ "teacher_raw_sum": null,
2448
+ "teacher_proxy_usable": false,
2449
+ "teacher_argmax_matches_gold": null,
2450
+ "target_transform": "no_teacher"
2451
+ },
2452
+ {
2453
+ "id": "doom:basic:4001:1:action",
2454
+ "split": "ood",
2455
+ "type": "choice",
2456
+ "k": 4,
2457
+ "teacher_raw_sum": null,
2458
+ "teacher_proxy_usable": false,
2459
+ "teacher_argmax_matches_gold": null,
2460
+ "target_transform": "no_teacher"
2461
+ },
2462
+ {
2463
+ "id": "doom:basic:4002:0:action",
2464
+ "split": "ood",
2465
+ "type": "choice",
2466
+ "k": 4,
2467
+ "teacher_raw_sum": null,
2468
+ "teacher_proxy_usable": false,
2469
+ "teacher_argmax_matches_gold": null,
2470
+ "target_transform": "no_teacher"
2471
+ },
2472
+ {
2473
+ "id": "doom:basic:4002:1:action",
2474
+ "split": "ood",
2475
+ "type": "choice",
2476
+ "k": 4,
2477
+ "teacher_raw_sum": null,
2478
+ "teacher_proxy_usable": false,
2479
+ "teacher_argmax_matches_gold": null,
2480
+ "target_transform": "no_teacher"
2481
+ },
2482
+ {
2483
+ "id": "doom:basic:4002:2:action",
2484
+ "split": "ood",
2485
+ "type": "choice",
2486
+ "k": 4,
2487
+ "teacher_raw_sum": null,
2488
+ "teacher_proxy_usable": false,
2489
+ "teacher_argmax_matches_gold": null,
2490
+ "target_transform": "no_teacher"
2491
+ },
2492
+ {
2493
+ "id": "doom:basic:4002:3:action",
2494
+ "split": "ood",
2495
+ "type": "choice",
2496
+ "k": 4,
2497
+ "teacher_raw_sum": null,
2498
+ "teacher_proxy_usable": false,
2499
+ "teacher_argmax_matches_gold": null,
2500
+ "target_transform": "no_teacher"
2501
+ },
2502
+ {
2503
+ "id": "doom:basic:4002:4:action",
2504
+ "split": "ood",
2505
+ "type": "choice",
2506
+ "k": 4,
2507
+ "teacher_raw_sum": null,
2508
+ "teacher_proxy_usable": false,
2509
+ "teacher_argmax_matches_gold": null,
2510
+ "target_transform": "no_teacher"
2511
+ },
2512
+ {
2513
+ "id": "doom:basic:4003:0:action",
2514
+ "split": "ood",
2515
+ "type": "choice",
2516
+ "k": 4,
2517
+ "teacher_raw_sum": null,
2518
+ "teacher_proxy_usable": false,
2519
+ "teacher_argmax_matches_gold": null,
2520
+ "target_transform": "no_teacher"
2521
+ },
2522
+ {
2523
+ "id": "doom:basic:4003:1:action",
2524
+ "split": "ood",
2525
+ "type": "choice",
2526
+ "k": 4,
2527
+ "teacher_raw_sum": null,
2528
+ "teacher_proxy_usable": false,
2529
+ "teacher_argmax_matches_gold": null,
2530
+ "target_transform": "no_teacher"
2531
+ },
2532
+ {
2533
+ "id": "doom:basic:4003:2:action",
2534
+ "split": "ood",
2535
+ "type": "choice",
2536
+ "k": 4,
2537
+ "teacher_raw_sum": null,
2538
+ "teacher_proxy_usable": false,
2539
+ "teacher_argmax_matches_gold": null,
2540
+ "target_transform": "no_teacher"
2541
+ },
2542
+ {
2543
+ "id": "doom:basic:4003:3:action",
2544
+ "split": "ood",
2545
+ "type": "choice",
2546
+ "k": 4,
2547
+ "teacher_raw_sum": null,
2548
+ "teacher_proxy_usable": false,
2549
+ "teacher_argmax_matches_gold": null,
2550
+ "target_transform": "no_teacher"
2551
+ },
2552
+ {
2553
+ "id": "doom:basic:4003:4:action",
2554
+ "split": "ood",
2555
+ "type": "choice",
2556
+ "k": 4,
2557
+ "teacher_raw_sum": null,
2558
+ "teacher_proxy_usable": false,
2559
+ "teacher_argmax_matches_gold": null,
2560
+ "target_transform": "no_teacher"
2561
+ },
2562
+ {
2563
+ "id": "doom:basic:4003:5:action",
2564
+ "split": "ood",
2565
+ "type": "choice",
2566
+ "k": 4,
2567
+ "teacher_raw_sum": null,
2568
+ "teacher_proxy_usable": false,
2569
+ "teacher_argmax_matches_gold": null,
2570
+ "target_transform": "no_teacher"
2571
+ },
2572
+ {
2573
+ "id": "doom:basic:4003:6:action",
2574
+ "split": "ood",
2575
+ "type": "choice",
2576
+ "k": 4,
2577
+ "teacher_raw_sum": null,
2578
+ "teacher_proxy_usable": false,
2579
+ "teacher_argmax_matches_gold": null,
2580
+ "target_transform": "no_teacher"
2581
+ },
2582
+ {
2583
+ "id": "doom:basic:4003:7:action",
2584
+ "split": "ood",
2585
+ "type": "choice",
2586
+ "k": 4,
2587
+ "teacher_raw_sum": null,
2588
+ "teacher_proxy_usable": false,
2589
+ "teacher_argmax_matches_gold": null,
2590
+ "target_transform": "no_teacher"
2591
+ }
2592
+ ]
timing.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "scope": "warm inference including tensor assembly and device copies; excludes tokenization/network",
3
+ "device": "cpu",
4
+ "prefix_sharing": false,
5
+ "autoregressive_decode_steps": 0,
6
+ "results": [
7
+ {
8
+ "states": 1,
9
+ "questions": 1,
10
+ "candidate_paths": 4,
11
+ "median_ms": 749.0760830696672,
12
+ "questions_per_second": 1.3349778782177402,
13
+ "repeats": 6
14
+ },
15
+ {
16
+ "states": 4,
17
+ "questions": 4,
18
+ "candidate_paths": 16,
19
+ "median_ms": 4431.9372499594465,
20
+ "questions_per_second": 0.9025398543349414,
21
+ "repeats": 6
22
+ },
23
+ {
24
+ "states": 8,
25
+ "questions": 8,
26
+ "candidate_paths": 32,
27
+ "median_ms": 8881.860624998808,
28
+ "questions_per_second": 0.9007121748210357,
29
+ "repeats": 6
30
+ }
31
+ ]
32
+ }
tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "local_files_only": false,
25
+ "model_max_length": 131072,
26
+ "pad_token": "<|endoftext|>",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }
train_log.json ADDED
@@ -0,0 +1,829 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "step": 1,
4
+ "phase": "head",
5
+ "loss": 1.389875888824463,
6
+ "elapsed_seconds": 24.036056375014596
7
+ },
8
+ {
9
+ "step": 2,
10
+ "phase": "head",
11
+ "loss": 1.3899306058883667,
12
+ "elapsed_seconds": 51.83826920797583
13
+ },
14
+ {
15
+ "step": 3,
16
+ "phase": "head",
17
+ "loss": 1.3847476243972778,
18
+ "elapsed_seconds": 75.67506341694389
19
+ },
20
+ {
21
+ "step": 4,
22
+ "phase": "head",
23
+ "loss": 1.3841294050216675,
24
+ "elapsed_seconds": 103.51494587492198
25
+ },
26
+ {
27
+ "step": 5,
28
+ "phase": "head",
29
+ "loss": 1.3761035203933716,
30
+ "elapsed_seconds": 128.8655867499765
31
+ },
32
+ {
33
+ "step": 6,
34
+ "phase": "head",
35
+ "loss": 1.371416449546814,
36
+ "elapsed_seconds": 156.50373250001576
37
+ },
38
+ {
39
+ "step": 7,
40
+ "phase": "head",
41
+ "loss": 1.3587156534194946,
42
+ "elapsed_seconds": 180.95679600001313
43
+ },
44
+ {
45
+ "step": 8,
46
+ "phase": "head",
47
+ "loss": 1.3607333898544312,
48
+ "elapsed_seconds": 213.03849141695537
49
+ },
50
+ {
51
+ "step": 9,
52
+ "phase": "head",
53
+ "loss": 1.356319546699524,
54
+ "elapsed_seconds": 248.60717141698115
55
+ },
56
+ {
57
+ "step": 10,
58
+ "phase": "head",
59
+ "loss": 1.3405879735946655,
60
+ "elapsed_seconds": 283.24871591699775
61
+ },
62
+ {
63
+ "step": 11,
64
+ "phase": "head",
65
+ "loss": 1.3741987943649292,
66
+ "elapsed_seconds": 313.36158820800483
67
+ },
68
+ {
69
+ "step": 12,
70
+ "phase": "head",
71
+ "loss": 1.33858060836792,
72
+ "elapsed_seconds": 342.93681283295155
73
+ },
74
+ {
75
+ "step": 13,
76
+ "phase": "full",
77
+ "loss": 1.3587621450424194,
78
+ "elapsed_seconds": 384.6019146249164
79
+ },
80
+ {
81
+ "step": 14,
82
+ "phase": "full",
83
+ "loss": 1.428684115409851,
84
+ "elapsed_seconds": 426.0172651669709
85
+ },
86
+ {
87
+ "step": 15,
88
+ "phase": "full",
89
+ "loss": 1.387558102607727,
90
+ "elapsed_seconds": 467.7444519170094
91
+ },
92
+ {
93
+ "step": 16,
94
+ "phase": "full",
95
+ "loss": 1.258278489112854,
96
+ "elapsed_seconds": 517.226874792017
97
+ },
98
+ {
99
+ "step": 17,
100
+ "phase": "full",
101
+ "loss": 1.2076126337051392,
102
+ "elapsed_seconds": 567.4914127079537
103
+ },
104
+ {
105
+ "step": 18,
106
+ "phase": "full",
107
+ "loss": 1.263201355934143,
108
+ "elapsed_seconds": 613.6109309999738
109
+ },
110
+ {
111
+ "step": 19,
112
+ "phase": "full",
113
+ "loss": 1.2309261560440063,
114
+ "elapsed_seconds": 654.9368342079688
115
+ },
116
+ {
117
+ "step": 20,
118
+ "phase": "full",
119
+ "loss": 1.3187247514724731,
120
+ "elapsed_seconds": 704.1494179170113
121
+ },
122
+ {
123
+ "step": 21,
124
+ "phase": "full",
125
+ "loss": 1.0831807851791382,
126
+ "elapsed_seconds": 750.3077925000107
127
+ },
128
+ {
129
+ "step": 22,
130
+ "phase": "full",
131
+ "loss": 1.1131312847137451,
132
+ "elapsed_seconds": 799.1919025420211
133
+ },
134
+ {
135
+ "step": 23,
136
+ "phase": "full",
137
+ "loss": 1.087010145187378,
138
+ "elapsed_seconds": 845.7365699169459
139
+ },
140
+ {
141
+ "step": 24,
142
+ "phase": "full",
143
+ "loss": 0.7765540480613708,
144
+ "elapsed_seconds": 894.9434904999798
145
+ },
146
+ {
147
+ "step": 25,
148
+ "phase": "full",
149
+ "loss": 1.6143994331359863,
150
+ "elapsed_seconds": 942.6738252079813
151
+ },
152
+ {
153
+ "step": 26,
154
+ "phase": "full",
155
+ "loss": 1.198196530342102,
156
+ "elapsed_seconds": 988.8911674999399
157
+ },
158
+ {
159
+ "step": 27,
160
+ "phase": "full",
161
+ "loss": 1.0476421117782593,
162
+ "elapsed_seconds": 1042.1458481670124
163
+ },
164
+ {
165
+ "step": 28,
166
+ "phase": "full",
167
+ "loss": 1.5836149454116821,
168
+ "elapsed_seconds": 1098.0000711670145
169
+ },
170
+ {
171
+ "step": 29,
172
+ "phase": "full",
173
+ "loss": 0.9660083651542664,
174
+ "elapsed_seconds": 1153.3456672079628
175
+ },
176
+ {
177
+ "step": 30,
178
+ "phase": "full",
179
+ "loss": 0.7715900540351868,
180
+ "elapsed_seconds": 1207.2533249999397
181
+ },
182
+ {
183
+ "step": 31,
184
+ "phase": "full",
185
+ "loss": 0.9807355999946594,
186
+ "elapsed_seconds": 1256.4867347079562
187
+ },
188
+ {
189
+ "step": 32,
190
+ "phase": "full",
191
+ "loss": 0.7592965960502625,
192
+ "elapsed_seconds": 1312.8946129579563
193
+ },
194
+ {
195
+ "step": 33,
196
+ "phase": "full",
197
+ "loss": 1.1841686964035034,
198
+ "elapsed_seconds": 1360.8917293329723
199
+ },
200
+ {
201
+ "step": 34,
202
+ "phase": "full",
203
+ "loss": 1.1152573823928833,
204
+ "elapsed_seconds": 1408.8212129579624
205
+ },
206
+ {
207
+ "step": 35,
208
+ "phase": "full",
209
+ "loss": 1.1301876306533813,
210
+ "elapsed_seconds": 1452.673219166929
211
+ },
212
+ {
213
+ "step": 36,
214
+ "phase": "full",
215
+ "loss": 0.9746701121330261,
216
+ "elapsed_seconds": 1504.6409771249164,
217
+ "dev": {
218
+ "accuracy": 0.36666666666666664,
219
+ "gold_nll": 1.2829124261298002,
220
+ "teacher_ce": null,
221
+ "questions": 30,
222
+ "teacher_eligible": 0
223
+ }
224
+ },
225
+ {
226
+ "step": 37,
227
+ "phase": "full",
228
+ "loss": 1.360924243927002,
229
+ "elapsed_seconds": 1610.3167905419832
230
+ },
231
+ {
232
+ "step": 38,
233
+ "phase": "full",
234
+ "loss": 0.851578950881958,
235
+ "elapsed_seconds": 1662.4280314999633
236
+ },
237
+ {
238
+ "step": 39,
239
+ "phase": "full",
240
+ "loss": 0.8612701892852783,
241
+ "elapsed_seconds": 1708.1620074999519
242
+ },
243
+ {
244
+ "step": 40,
245
+ "phase": "full",
246
+ "loss": 0.8566731810569763,
247
+ "elapsed_seconds": 1760.34947799996
248
+ },
249
+ {
250
+ "step": 41,
251
+ "phase": "full",
252
+ "loss": 1.0750174522399902,
253
+ "elapsed_seconds": 1809.451338166953
254
+ },
255
+ {
256
+ "step": 42,
257
+ "phase": "full",
258
+ "loss": 1.1540437936782837,
259
+ "elapsed_seconds": 1861.8049840829335
260
+ },
261
+ {
262
+ "step": 43,
263
+ "phase": "full",
264
+ "loss": 1.114806056022644,
265
+ "elapsed_seconds": 1908.0351864999393
266
+ },
267
+ {
268
+ "step": 44,
269
+ "phase": "full",
270
+ "loss": 1.0048785209655762,
271
+ "elapsed_seconds": 1960.2698532500071
272
+ },
273
+ {
274
+ "step": 45,
275
+ "phase": "full",
276
+ "loss": 1.0063434839248657,
277
+ "elapsed_seconds": 2012.4605407079216
278
+ },
279
+ {
280
+ "step": 46,
281
+ "phase": "full",
282
+ "loss": 0.9128134846687317,
283
+ "elapsed_seconds": 2058.231288457988
284
+ },
285
+ {
286
+ "step": 47,
287
+ "phase": "full",
288
+ "loss": 0.5638367533683777,
289
+ "elapsed_seconds": 2107.437953333021
290
+ },
291
+ {
292
+ "step": 48,
293
+ "phase": "full",
294
+ "loss": 0.972628116607666,
295
+ "elapsed_seconds": 2156.1096237079473
296
+ },
297
+ {
298
+ "step": 49,
299
+ "phase": "full",
300
+ "loss": 1.7008213996887207,
301
+ "elapsed_seconds": 2199.5863788749557
302
+ },
303
+ {
304
+ "step": 50,
305
+ "phase": "full",
306
+ "loss": 1.4777722358703613,
307
+ "elapsed_seconds": 2243.9505585419247
308
+ },
309
+ {
310
+ "step": 51,
311
+ "phase": "full",
312
+ "loss": 1.0380996465682983,
313
+ "elapsed_seconds": 2289.6339176249458
314
+ },
315
+ {
316
+ "step": 52,
317
+ "phase": "full",
318
+ "loss": 1.0119708776474,
319
+ "elapsed_seconds": 2341.626463416964
320
+ },
321
+ {
322
+ "step": 53,
323
+ "phase": "full",
324
+ "loss": 0.9252007603645325,
325
+ "elapsed_seconds": 2386.3734446669696
326
+ },
327
+ {
328
+ "step": 54,
329
+ "phase": "full",
330
+ "loss": 1.1225104331970215,
331
+ "elapsed_seconds": 2427.864223332959
332
+ },
333
+ {
334
+ "step": 55,
335
+ "phase": "full",
336
+ "loss": 0.7720308303833008,
337
+ "elapsed_seconds": 2464.81896437495
338
+ },
339
+ {
340
+ "step": 56,
341
+ "phase": "full",
342
+ "loss": 1.4780453443527222,
343
+ "elapsed_seconds": 2497.865731208003
344
+ },
345
+ {
346
+ "step": 57,
347
+ "phase": "full",
348
+ "loss": 0.6569619178771973,
349
+ "elapsed_seconds": 2536.904357707943
350
+ },
351
+ {
352
+ "step": 58,
353
+ "phase": "full",
354
+ "loss": 0.6820977330207825,
355
+ "elapsed_seconds": 2576.7641504579224
356
+ },
357
+ {
358
+ "step": 59,
359
+ "phase": "full",
360
+ "loss": 0.888839066028595,
361
+ "elapsed_seconds": 2611.5178874999983
362
+ },
363
+ {
364
+ "step": 60,
365
+ "phase": "full",
366
+ "loss": 0.4659762680530548,
367
+ "elapsed_seconds": 2643.713472082978,
368
+ "dev": {
369
+ "accuracy": 0.36666666666666664,
370
+ "gold_nll": 1.3948078787998122,
371
+ "teacher_ce": null,
372
+ "questions": 30,
373
+ "teacher_eligible": 0
374
+ }
375
+ },
376
+ {
377
+ "step": 61,
378
+ "phase": "full",
379
+ "loss": 1.1238030195236206,
380
+ "elapsed_seconds": 2711.114089916926
381
+ },
382
+ {
383
+ "step": 62,
384
+ "phase": "full",
385
+ "loss": 0.39054176211357117,
386
+ "elapsed_seconds": 2745.630997291999
387
+ },
388
+ {
389
+ "step": 63,
390
+ "phase": "full",
391
+ "loss": 0.9070367813110352,
392
+ "elapsed_seconds": 2776.764110832941
393
+ },
394
+ {
395
+ "step": 64,
396
+ "phase": "full",
397
+ "loss": 1.1334701776504517,
398
+ "elapsed_seconds": 2810.946477832971
399
+ },
400
+ {
401
+ "step": 65,
402
+ "phase": "full",
403
+ "loss": 0.5846802592277527,
404
+ "elapsed_seconds": 2841.307629749994
405
+ },
406
+ {
407
+ "step": 66,
408
+ "phase": "full",
409
+ "loss": 0.862031877040863,
410
+ "elapsed_seconds": 2877.494622749975
411
+ },
412
+ {
413
+ "step": 67,
414
+ "phase": "full",
415
+ "loss": 0.8375713229179382,
416
+ "elapsed_seconds": 2913.8502382920124
417
+ },
418
+ {
419
+ "step": 68,
420
+ "phase": "full",
421
+ "loss": 1.270970344543457,
422
+ "elapsed_seconds": 2949.4322621249594
423
+ },
424
+ {
425
+ "step": 69,
426
+ "phase": "full",
427
+ "loss": 0.8660920262336731,
428
+ "elapsed_seconds": 2983.8088394999504
429
+ },
430
+ {
431
+ "step": 70,
432
+ "phase": "full",
433
+ "loss": 0.7770584225654602,
434
+ "elapsed_seconds": 3015.7807882080087
435
+ },
436
+ {
437
+ "step": 71,
438
+ "phase": "full",
439
+ "loss": 0.7508067488670349,
440
+ "elapsed_seconds": 3049.549009999959
441
+ },
442
+ {
443
+ "step": 72,
444
+ "phase": "full",
445
+ "loss": 1.3410826921463013,
446
+ "elapsed_seconds": 3079.78262629197
447
+ },
448
+ {
449
+ "step": 73,
450
+ "phase": "full",
451
+ "loss": 0.9446380734443665,
452
+ "elapsed_seconds": 3114.458729374921
453
+ },
454
+ {
455
+ "step": 74,
456
+ "phase": "full",
457
+ "loss": 0.9398682117462158,
458
+ "elapsed_seconds": 3144.041182457935
459
+ },
460
+ {
461
+ "step": 75,
462
+ "phase": "full",
463
+ "loss": 1.0883415937423706,
464
+ "elapsed_seconds": 3173.216488707927
465
+ },
466
+ {
467
+ "step": 76,
468
+ "phase": "full",
469
+ "loss": 0.7588968276977539,
470
+ "elapsed_seconds": 3205.453624750022
471
+ },
472
+ {
473
+ "step": 77,
474
+ "phase": "full",
475
+ "loss": 0.9076502919197083,
476
+ "elapsed_seconds": 3236.071140832966
477
+ },
478
+ {
479
+ "step": 78,
480
+ "phase": "full",
481
+ "loss": 1.076284408569336,
482
+ "elapsed_seconds": 3263.6760006250115
483
+ },
484
+ {
485
+ "step": 79,
486
+ "phase": "full",
487
+ "loss": 0.8104545474052429,
488
+ "elapsed_seconds": 3297.3259451669874
489
+ },
490
+ {
491
+ "step": 80,
492
+ "phase": "full",
493
+ "loss": 0.9220348000526428,
494
+ "elapsed_seconds": 3329.042382000014
495
+ },
496
+ {
497
+ "step": 81,
498
+ "phase": "full",
499
+ "loss": 0.8356162905693054,
500
+ "elapsed_seconds": 3364.9220760830212
501
+ },
502
+ {
503
+ "step": 82,
504
+ "phase": "full",
505
+ "loss": 0.6157140731811523,
506
+ "elapsed_seconds": 3402.440288666985
507
+ },
508
+ {
509
+ "step": 83,
510
+ "phase": "full",
511
+ "loss": 0.7122819423675537,
512
+ "elapsed_seconds": 3435.014253832982
513
+ },
514
+ {
515
+ "step": 84,
516
+ "phase": "full",
517
+ "loss": 1.067466139793396,
518
+ "elapsed_seconds": 3464.723170000012,
519
+ "dev": {
520
+ "accuracy": 0.4666666666666667,
521
+ "gold_nll": 1.264403687169444,
522
+ "teacher_ce": null,
523
+ "questions": 30,
524
+ "teacher_eligible": 0
525
+ }
526
+ },
527
+ {
528
+ "step": 85,
529
+ "phase": "full",
530
+ "loss": 1.3165994882583618,
531
+ "elapsed_seconds": 3536.887222166988
532
+ },
533
+ {
534
+ "step": 86,
535
+ "phase": "full",
536
+ "loss": 0.8801708221435547,
537
+ "elapsed_seconds": 3571.040540124988
538
+ },
539
+ {
540
+ "step": 87,
541
+ "phase": "full",
542
+ "loss": 0.6419305801391602,
543
+ "elapsed_seconds": 3604.1917615829734
544
+ },
545
+ {
546
+ "step": 88,
547
+ "phase": "full",
548
+ "loss": 0.5378435850143433,
549
+ "elapsed_seconds": 3638.087013082928
550
+ },
551
+ {
552
+ "step": 89,
553
+ "phase": "full",
554
+ "loss": 0.5620748996734619,
555
+ "elapsed_seconds": 3669.599138416932
556
+ },
557
+ {
558
+ "step": 90,
559
+ "phase": "full",
560
+ "loss": 0.4298192262649536,
561
+ "elapsed_seconds": 3703.9810939999297
562
+ },
563
+ {
564
+ "step": 91,
565
+ "phase": "full",
566
+ "loss": 2.150527238845825,
567
+ "elapsed_seconds": 3733.915227917023
568
+ },
569
+ {
570
+ "step": 92,
571
+ "phase": "full",
572
+ "loss": 0.5556487441062927,
573
+ "elapsed_seconds": 3765.1823088750243
574
+ },
575
+ {
576
+ "step": 93,
577
+ "phase": "full",
578
+ "loss": 0.3985157907009125,
579
+ "elapsed_seconds": 3798.131275374908
580
+ },
581
+ {
582
+ "step": 94,
583
+ "phase": "full",
584
+ "loss": 0.9726573824882507,
585
+ "elapsed_seconds": 3830.877737957984
586
+ },
587
+ {
588
+ "step": 95,
589
+ "phase": "full",
590
+ "loss": 0.8111466765403748,
591
+ "elapsed_seconds": 3859.4745412080083
592
+ },
593
+ {
594
+ "step": 96,
595
+ "phase": "full",
596
+ "loss": 1.051352620124817,
597
+ "elapsed_seconds": 3887.992824999965
598
+ },
599
+ {
600
+ "step": 97,
601
+ "phase": "full",
602
+ "loss": 1.014853835105896,
603
+ "elapsed_seconds": 3918.731486874982
604
+ },
605
+ {
606
+ "step": 98,
607
+ "phase": "full",
608
+ "loss": 0.7830702662467957,
609
+ "elapsed_seconds": 3952.276105582947
610
+ },
611
+ {
612
+ "step": 99,
613
+ "phase": "full",
614
+ "loss": 0.7837496399879456,
615
+ "elapsed_seconds": 3984.9619172919774
616
+ },
617
+ {
618
+ "step": 100,
619
+ "phase": "full",
620
+ "loss": 0.8402023315429688,
621
+ "elapsed_seconds": 4014.338328792015
622
+ },
623
+ {
624
+ "step": 101,
625
+ "phase": "full",
626
+ "loss": 0.37576615810394287,
627
+ "elapsed_seconds": 4044.6040538749658
628
+ },
629
+ {
630
+ "step": 102,
631
+ "phase": "full",
632
+ "loss": 1.3958314657211304,
633
+ "elapsed_seconds": 4073.605408707983
634
+ },
635
+ {
636
+ "step": 103,
637
+ "phase": "full",
638
+ "loss": 0.5992537140846252,
639
+ "elapsed_seconds": 4104.19275412499
640
+ },
641
+ {
642
+ "step": 104,
643
+ "phase": "full",
644
+ "loss": 0.9771134853363037,
645
+ "elapsed_seconds": 4138.6911674999865
646
+ },
647
+ {
648
+ "step": 105,
649
+ "phase": "full",
650
+ "loss": 0.9111394882202148,
651
+ "elapsed_seconds": 4173.2863762499765
652
+ },
653
+ {
654
+ "step": 106,
655
+ "phase": "full",
656
+ "loss": 1.0075865983963013,
657
+ "elapsed_seconds": 4205.628115249914
658
+ },
659
+ {
660
+ "step": 107,
661
+ "phase": "full",
662
+ "loss": 1.112038254737854,
663
+ "elapsed_seconds": 4235.550061458023
664
+ },
665
+ {
666
+ "step": 108,
667
+ "phase": "full",
668
+ "loss": 0.7502264380455017,
669
+ "elapsed_seconds": 4270.189222957939,
670
+ "dev": {
671
+ "accuracy": 0.4666666666666667,
672
+ "gold_nll": 0.9716313769208788,
673
+ "teacher_ce": null,
674
+ "questions": 30,
675
+ "teacher_eligible": 0
676
+ }
677
+ },
678
+ {
679
+ "step": 109,
680
+ "phase": "full",
681
+ "loss": 0.5051252245903015,
682
+ "elapsed_seconds": 4340.916494791978
683
+ },
684
+ {
685
+ "step": 110,
686
+ "phase": "full",
687
+ "loss": 0.6844400763511658,
688
+ "elapsed_seconds": 4374.49156204192
689
+ },
690
+ {
691
+ "step": 111,
692
+ "phase": "full",
693
+ "loss": 0.8545079827308655,
694
+ "elapsed_seconds": 4407.191025582957
695
+ },
696
+ {
697
+ "step": 112,
698
+ "phase": "full",
699
+ "loss": 0.9379212260246277,
700
+ "elapsed_seconds": 4440.875409832923
701
+ },
702
+ {
703
+ "step": 113,
704
+ "phase": "full",
705
+ "loss": 0.9917354583740234,
706
+ "elapsed_seconds": 4469.909892207943
707
+ },
708
+ {
709
+ "step": 114,
710
+ "phase": "full",
711
+ "loss": 0.8366888165473938,
712
+ "elapsed_seconds": 4498.511969082989
713
+ },
714
+ {
715
+ "step": 115,
716
+ "phase": "full",
717
+ "loss": 0.6648092865943909,
718
+ "elapsed_seconds": 4527.161485999939
719
+ },
720
+ {
721
+ "step": 116,
722
+ "phase": "full",
723
+ "loss": 0.3770482540130615,
724
+ "elapsed_seconds": 4560.622755500022
725
+ },
726
+ {
727
+ "step": 117,
728
+ "phase": "full",
729
+ "loss": 2.4855356216430664,
730
+ "elapsed_seconds": 4594.997954666964
731
+ },
732
+ {
733
+ "step": 118,
734
+ "phase": "full",
735
+ "loss": 1.3306984901428223,
736
+ "elapsed_seconds": 4628.124366374919
737
+ },
738
+ {
739
+ "step": 119,
740
+ "phase": "full",
741
+ "loss": 1.012333631515503,
742
+ "elapsed_seconds": 4657.820481041912
743
+ },
744
+ {
745
+ "step": 120,
746
+ "phase": "full",
747
+ "loss": 0.7231154441833496,
748
+ "elapsed_seconds": 4690.885806332924
749
+ },
750
+ {
751
+ "step": 121,
752
+ "phase": "full",
753
+ "loss": 0.8544103503227234,
754
+ "elapsed_seconds": 4722.287242166931
755
+ },
756
+ {
757
+ "step": 122,
758
+ "phase": "full",
759
+ "loss": 1.1619356870651245,
760
+ "elapsed_seconds": 4750.897184374975
761
+ },
762
+ {
763
+ "step": 123,
764
+ "phase": "full",
765
+ "loss": 0.9404104351997375,
766
+ "elapsed_seconds": 4779.395677457913
767
+ },
768
+ {
769
+ "step": 124,
770
+ "phase": "full",
771
+ "loss": 0.7814939022064209,
772
+ "elapsed_seconds": 4814.453839167021
773
+ },
774
+ {
775
+ "step": 125,
776
+ "phase": "full",
777
+ "loss": 1.2301113605499268,
778
+ "elapsed_seconds": 4849.413407291984
779
+ },
780
+ {
781
+ "step": 126,
782
+ "phase": "full",
783
+ "loss": 0.6965911984443665,
784
+ "elapsed_seconds": 4882.867009292007
785
+ },
786
+ {
787
+ "step": 127,
788
+ "phase": "full",
789
+ "loss": 1.0889142751693726,
790
+ "elapsed_seconds": 4913.634412874933
791
+ },
792
+ {
793
+ "step": 128,
794
+ "phase": "full",
795
+ "loss": 0.4494098722934723,
796
+ "elapsed_seconds": 4949.979502666974
797
+ },
798
+ {
799
+ "step": 129,
800
+ "phase": "full",
801
+ "loss": 0.9778596758842468,
802
+ "elapsed_seconds": 4985.751069707912
803
+ },
804
+ {
805
+ "step": 130,
806
+ "phase": "full",
807
+ "loss": 0.8332850337028503,
808
+ "elapsed_seconds": 5020.185354916961
809
+ },
810
+ {
811
+ "step": 131,
812
+ "phase": "full",
813
+ "loss": 0.8363568186759949,
814
+ "elapsed_seconds": 5056.574783166987
815
+ },
816
+ {
817
+ "step": 132,
818
+ "phase": "full",
819
+ "loss": 0.8865575194358826,
820
+ "elapsed_seconds": 5092.938388249953,
821
+ "dev": {
822
+ "accuracy": 0.4666666666666667,
823
+ "gold_nll": 0.9997109714955453,
824
+ "teacher_ce": null,
825
+ "questions": 30,
826
+ "teacher_eligible": 0
827
+ }
828
+ }
829
+ ]