The view-size sweep of Table A6: nine checkpoints; the plan and the card follow the appendix's table numbers
Browse filesI-CE with each review view drawn until it holds at least 8, 32 or 64 sentences (the recipe stops at 16), folds 0 to 2 on the 512-sentence packs, each at the epoch the validation rank rule selects. rank_ckpt_plan.json lists them (166 runs). The appendix's new Table A6 moved every later table one place, so the card's table numbers follow: the old Tables A6 to A18 are A7 to A19.
- README.md +29 -21
- ckpt_w9cv_wcle_i2ce_icetf_fold0_w32_d512_fp_ep1700.pt +3 -0
- ckpt_w9cv_wcle_i2ce_icetf_fold0_w64_d512_fp_ep2000.pt +3 -0
- ckpt_w9cv_wcle_i2ce_icetf_fold0_w8_d512_fp_ep1850.pt +3 -0
- ckpt_w9cv_wcle_i2ce_icetf_fold1_w32_d512_fp_ep1300.pt +3 -0
- ckpt_w9cv_wcle_i2ce_icetf_fold1_w64_d512_fp_ep950.pt +3 -0
- ckpt_w9cv_wcle_i2ce_icetf_fold1_w8_d512_fp_ep1800.pt +3 -0
- ckpt_w9cv_wcle_i2ce_icetf_fold2_w32_d512_fp_ep1550.pt +3 -0
- ckpt_w9cv_wcle_i2ce_icetf_fold2_w64_d512_fp_ep1750.pt +3 -0
- ckpt_w9cv_wcle_i2ce_icetf_fold2_w8_d512_fp_ep1850.pt +3 -0
- rank_ckpt_plan.json +90 -0
README.md
CHANGED
|
@@ -24,11 +24,11 @@ reviews (Qwen3-Embedding-0.6B, 1,024-d) and an MLP maps the pooled result to one
|
|
| 24 |
|
| 25 |
## Contents
|
| 26 |
|
| 27 |
-
|
| 28 |
|
| 29 |
| Listed in | Checkpoints | What they are |
|
| 30 |
|---|---|---|
|
| 31 |
-
| `rank_ckpt_plan.json` |
|
| 32 |
| `i2bce_sel_pool.json` | 5 | I + SimCLR on the five folds (Figure 8, Appendix L), selected by the same rule |
|
| 33 |
| `fixed_split_ckpt_plan.json` | 69 | the fixed-split runs: 15 runs at their selected epochs, two of them with an earlier checkpoint kept beside the selected one, and 52 more checkpoints of two runs that the paper reads across their epochs (field `trajectory`) |
|
| 34 |
| `rank_ckpt_plan.json`, field `init_ckpt` | 5 | the BYOL checkpoints the five two-stage runs started from |
|
|
@@ -43,8 +43,8 @@ Every tower that a number or a figure of the paper reads is here, at the checkpo
|
|
| 43 |
at. A run saved a checkpoint every 50 epochs and the rank rule chose among them; the ones it did
|
| 44 |
not choose are not here, except for the two runs listed under `trajectory`. The other passages
|
| 45 |
that follow runs over training quote what the workers logged at each checkpoint: the learnable
|
| 46 |
-
temperature and the view-count
|
| 47 |
-
after epoch 50 in Supplement A.
|
| 48 |
|
| 49 |
## File names
|
| 50 |
|
|
@@ -57,33 +57,36 @@ after epoch 50 in Supplement A.
|
|
| 57 |
whole 2,048-sentence review pool (a median of 2,068 sentences). The paper calls `_g2048` and
|
| 58 |
`_gpool` alike its 2,048-sentence budget; the main five-fold towers are the `_gpool` runs.
|
| 59 |
- `<suffix>`: `_wllm` for LLM-rewritten documents as the document view, `_bw` for a run
|
| 60 |
-
initialized from a BYOL tower, `
|
|
|
|
|
|
|
| 61 |
- `_fp`: the strong views were drawn from the full review pool. `ep<N>` is the epoch.
|
| 62 |
|
| 63 |
## The five-fold runs
|
| 64 |
|
| 65 |
-
Table and figure numbers are those of the paper, its appendices (Tables A1 to
|
| 66 |
supplement (Tables S1 to S4). The last column comes from the provenance table of the code
|
| 67 |
repository, `contrast_experiment/w9/Pod/w9_profiles.py`, which cites by cell: a table named for a
|
| 68 |
row reads at least one of the row's runs. That file also names the notebook that trains each cell.
|
| 69 |
|
| 70 |
| Runs | What they are | Pack | Folds | Read by |
|
| 71 |
|---|---|---|---|---|
|
| 72 |
-
| `ai2ce_icetf_d512` | CE + anchor-in-I | 512 | 5 | Table 2, Section 6.2, Table
|
| 73 |
-
| `ce_cetf_d512`, `i2ce_icetf_d512` | CE; I-CE, the recipe | 512 | 5 | Table 2, Table A2, Table A3, Table A4, Table A5, Table A6, Table
|
| 74 |
| `d1r2_i2ce_icetf_d512`, `d1r4_i2ce_icetf_d512`, `d1r5_i2ce_icetf_d512`, `d1r5_i3ce_icetf_d512`, `d1r6_i2ce_icetf_d512` | I-CE, V = 3; I-CE, V = 5; I-CE, V = 6; I-CE, V = 6 with λ = 3; I-CE, V = 7 | 512 | 0 to 2 | Table A5 |
|
| 75 |
-
| `
|
|
|
|
| 76 |
| `i2cet05_icetf_d512`, `i2cet10_icetf_d512` | I-CE, τ = 0.05; I-CE, τ = 0.10 | 512 | 5 | Table A3 |
|
| 77 |
| `i3ce_icetf_d512`, `i4ce_icetf_d512`, `ice_icetf_d512` | I-CE, λ = 3; I-CE, λ = 4; I-CE, λ = 1 | 512 | 0 to 2 | Table A4 |
|
| 78 |
-
| `slot16i2cemean_icetf_d512`, `slot1i2cemean_icetf_d512`, `slot2i2cemean_icetf_d512`, `slot8i2cemean_icetf_d512` | I-CE, 16 latent queries; I-CE, 1 latent query; I-CE, 2 latent queries; I-CE, 8 latent queries | 512 | 0 to 2 | Table
|
| 79 |
| `vfai2ce_icetf_d512` | I-CE, views-first anchors | 512 | 5 | Table S1 |
|
| 80 |
-
| `ce_cetf_g1024`, `i2ce_icetf_g1024` | CE; I-CE, the recipe | 1,024 | 5 | Table A2, Table
|
| 81 |
-
| `ce_cetf_g2048`, `i2ce_icetf_g2048` | CE; I-CE, the recipe | 2,048 | 5 | Table A3, Table
|
| 82 |
| `i2ce_icetl_g2048`, `i2cet05_icetf_g2048`, `i2cet10_icetf_g2048` | I-CE, learnable τ; I-CE, τ = 0.05; I-CE, τ = 0.10 | 2,048 | 5 | Table A3 |
|
| 83 |
-
| `bce_cetf_gpool`, `byol_bytf_gpool`, `epd_v20i10c20_cetf_gpool`, `mq3072i2ce_icetf_gpool` | SimCLR-style; BYOL; VICReg (batch 192); I-CE with an EMA teacher and a memory bank | pool | 5 | Figure 7, Figure 8, Table 2, Section 3.2, Table A1, Table
|
| 84 |
-
| `ce_cetf_gpool`, `i2ce_icetf_gpool` | CE; I-CE, the recipe | pool | 5 | Figure 7, Figure 8, Table 2, Section 6.1, Table A1, Table A2, Table
|
| 85 |
-
| `slot8i2cemean_icetf_gpool` | I-CE, 8 latent queries | pool | 5 | Table
|
| 86 |
-
| `swin168step84loop2i2ce_icetf_gpool`, `swin168step84loop2i2ce_icetf_gpool_bw` | I-CE with the windowed teacher; I-CE, two-stage: BYOL warm start, then the windowed teacher | pool | 5 | Table
|
| 87 |
| `dino_dntf_gpool` | DINO at its published settings, the control of Section 4.3 | pool | 0 only | Table A1 |
|
| 88 |
|
| 89 |
I + SimCLR (`i2bce_icetf`, files without a pack or a suffix, five folds) backs Figure 8 and the
|
|
@@ -97,10 +100,10 @@ it carries the two prototype heads (see Format).
|
|
| 97 |
| Runs | What they are | Pack | Folds | Read by |
|
| 98 |
|---|---|---|---|---|
|
| 99 |
| `ai25auni2_icetf_d512`, `ai2auni25_icetf_d512`, `ai4auni2_icetf_d512`, `ai6auni2_icetf_d512`, `i4uni2_icetf` | alignment + uniformity aimed at the anchor gallery, the four settings of Section 6.2 (`ai25auni2` is Table 3's a+u @ gallery row); alignment + uniformity aimed at the batch views (Table 3's a+u @ views row) | 512 | fixed split | Table 3, Section 6.2, Appendix L |
|
| 100 |
-
| `ai2ce_icetf_d512`, `ce_cetf_d512`, `i2ce_icetf_d512` | CE + anchor-in-I; CE; I-CE, the recipe | 512 | fixed split | Table 3, Section 6.2, Table
|
| 101 |
| `ce_cetf_g2048`, `i2ce_icetf_g2048` | CE; I-CE, the recipe | 2,048 | fixed split | Figure 9, Figure A1, Figure A3, Appendix L |
|
| 102 |
-
| `bce_cetf`, `i2bce_icetf`, `epd_v20i10c20_cetf` | SimCLR-style; I + SimCLR; VICReg, v/i/c = 20/10/20 (the recipe weights) | 512 | fixed split | Figure 9, Figure A3, Appendix L, Table
|
| 103 |
-
| `epd_v25i25c1_cetf`, `epd_v20i10c15_cetf` | VICReg, v/i/c = 25/25/1; VICReg, v/i/c = 20/10/15 | 512 | fixed split | Table
|
| 104 |
|
| 105 |
Figure 9, Figure A3 and the neighborhood statistics of Appendix L read six encoders on the fixed
|
| 106 |
split: the frozen embedder, which has no checkpoint, and five towers, namely `i2ce_icetf_g2048`
|
|
@@ -162,7 +165,7 @@ python contrast_experiment/w9/eval/k10_eval.py score cells.json draws.npz score
|
|
| 162 |
python contrast_experiment/w9/eval/k10_eval.py table scores.json
|
| 163 |
```
|
| 164 |
|
| 165 |
-
`cells` takes the
|
| 166 |
`--only <regex>` keeps a subset, for example `--only "_d512$"` for the 512-sentence runs. In its
|
| 167 |
table the five families of the main comparison go by the paper's names (`I-CE`, `CE`, `SimCLR`,
|
| 168 |
`VICReg`, `BYOL`) and every other family by its plan key without the fold; a family with one
|
|
@@ -176,7 +179,7 @@ python contrast_experiment/w9/eval/fixed_split_eval.py --ckpt-dir checkpoints
|
|
| 176 |
|
| 177 |
It reads every run of `fixed_split_ckpt_plan.json` at its selected checkpoint and prints each
|
| 178 |
reading beside the number the paper prints: Table 3, the gallery-aimed settings of Section 6.2
|
| 179 |
-
and Table
|
| 180 |
curve of Appendix L, the latent queries of Figure A1, and, through `k10_eval.py`, the towers of
|
| 181 |
Figure 9 against the ten draws. A near tie can move a cell by one query of 204 (0.005), and the
|
| 182 |
collapsed a+u @ gallery row by about 0.01.
|
|
@@ -230,6 +233,11 @@ dataset keeps the first packs as `wscan_gal_rev_rawprefix.npz`; the workers read
|
|
| 230 |
|
| 231 |
## Changes
|
| 232 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 233 |
- 2026-11-12. The code repository gained `figures/neighborhoods/`, the scripts that drew
|
| 234 |
Figures 8, 9 and A3.
|
| 235 |
- 2026-11-11, at night. The code repository gained `fixed_split_eval.py`, which reads the
|
|
|
|
| 24 |
|
| 25 |
## Contents
|
| 26 |
|
| 27 |
+
275 checkpoints, about 593 MiB, and four JSON files that list every one of them:
|
| 28 |
|
| 29 |
| Listed in | Checkpoints | What they are |
|
| 30 |
|---|---|---|
|
| 31 |
+
| `rank_ckpt_plan.json` | 166 | the five-fold runs behind the paper's numbers, each at the epoch the validation rank rule of Section 5 selects. One is the DINO-style control of Table A1, trained on fold 0 only; five, CE capped at 2,048 sentences, are the partners of I-CE runs the paper prints and are not printed themselves |
|
| 32 |
| `i2bce_sel_pool.json` | 5 | I + SimCLR on the five folds (Figure 8, Appendix L), selected by the same rule |
|
| 33 |
| `fixed_split_ckpt_plan.json` | 69 | the fixed-split runs: 15 runs at their selected epochs, two of them with an earlier checkpoint kept beside the selected one, and 52 more checkpoints of two runs that the paper reads across their epochs (field `trajectory`) |
|
| 34 |
| `rank_ckpt_plan.json`, field `init_ckpt` | 5 | the BYOL checkpoints the five two-stage runs started from |
|
|
|
|
| 43 |
at. A run saved a checkpoint every 50 epochs and the rank rule chose among them; the ones it did
|
| 44 |
not choose are not here, except for the two runs listed under `trajectory`. The other passages
|
| 45 |
that follow runs over training quote what the workers logged at each checkpoint: the learnable
|
| 46 |
+
temperature and the view-count and view-size sweeps in Appendix C, and the decline of the
|
| 47 |
+
views-first anchors after epoch 50 in Supplement A.
|
| 48 |
|
| 49 |
## File names
|
| 50 |
|
|
|
|
| 57 |
whole 2,048-sentence review pool (a median of 2,068 sentences). The paper calls `_g2048` and
|
| 58 |
`_gpool` alike its 2,048-sentence budget; the main five-fold towers are the `_gpool` runs.
|
| 59 |
- `<suffix>`: `_wllm` for LLM-rewritten documents as the document view, `_bw` for a run
|
| 60 |
+
initialized from a BYOL tower, `_w<N>` for review views drawn until they hold at least N
|
| 61 |
+
sentences (the recipe stops at 16), `_d512` for a run on the current 512-sentence packs (see
|
| 62 |
+
below).
|
| 63 |
- `_fp`: the strong views were drawn from the full review pool. `ep<N>` is the epoch.
|
| 64 |
|
| 65 |
## The five-fold runs
|
| 66 |
|
| 67 |
+
Table and figure numbers are those of the paper, its appendices (Tables A1 to A19) and its
|
| 68 |
supplement (Tables S1 to S4). The last column comes from the provenance table of the code
|
| 69 |
repository, `contrast_experiment/w9/Pod/w9_profiles.py`, which cites by cell: a table named for a
|
| 70 |
row reads at least one of the row's runs. That file also names the notebook that trains each cell.
|
| 71 |
|
| 72 |
| Runs | What they are | Pack | Folds | Read by |
|
| 73 |
|---|---|---|---|---|
|
| 74 |
+
| `ai2ce_icetf_d512` | CE + anchor-in-I | 512 | 5 | Table 2, Section 6.2, Table A15 |
|
| 75 |
+
| `ce_cetf_d512`, `i2ce_icetf_d512` | CE; I-CE, the recipe | 512 | 5 | Table 2, Table A2, Table A3, Table A4, Table A5, Table A6, Table A7, Table A11, Table A15, Table A19, Table S1 |
|
| 76 |
| `d1r2_i2ce_icetf_d512`, `d1r4_i2ce_icetf_d512`, `d1r5_i2ce_icetf_d512`, `d1r5_i3ce_icetf_d512`, `d1r6_i2ce_icetf_d512` | I-CE, V = 3; I-CE, V = 5; I-CE, V = 6; I-CE, V = 6 with λ = 3; I-CE, V = 7 | 512 | 0 to 2 | Table A5 |
|
| 77 |
+
| `i2ce_icetf_w8_d512`, `i2ce_icetf_w32_d512`, `i2ce_icetf_w64_d512` | I-CE, review views of at least 8 sentences; of at least 32; of at least 64 | 512 | 0 to 2 | Table A6 |
|
| 78 |
+
| `i2ce_icetf_wllm_d512`, `nodoc_i2ce_icetf_d512` | I-CE, LLM-rewritten documents; I-CE without the document view | 512 | 5 | Table A19 |
|
| 79 |
| `i2cet05_icetf_d512`, `i2cet10_icetf_d512` | I-CE, τ = 0.05; I-CE, τ = 0.10 | 512 | 5 | Table A3 |
|
| 80 |
| `i3ce_icetf_d512`, `i4ce_icetf_d512`, `ice_icetf_d512` | I-CE, λ = 3; I-CE, λ = 4; I-CE, λ = 1 | 512 | 0 to 2 | Table A4 |
|
| 81 |
+
| `slot16i2cemean_icetf_d512`, `slot1i2cemean_icetf_d512`, `slot2i2cemean_icetf_d512`, `slot8i2cemean_icetf_d512` | I-CE, 16 latent queries; I-CE, 1 latent query; I-CE, 2 latent queries; I-CE, 8 latent queries | 512 | 0 to 2 | Table A7 |
|
| 82 |
| `vfai2ce_icetf_d512` | I-CE, views-first anchors | 512 | 5 | Table S1 |
|
| 83 |
+
| `ce_cetf_g1024`, `i2ce_icetf_g1024` | CE; I-CE, the recipe | 1,024 | 5 | Table A2, Table A11, Table A15 |
|
| 84 |
+
| `ce_cetf_g2048`, `i2ce_icetf_g2048` | CE; I-CE, the recipe | 2,048 | 5 | Table A3, Table A11 |
|
| 85 |
| `i2ce_icetl_g2048`, `i2cet05_icetf_g2048`, `i2cet10_icetf_g2048` | I-CE, learnable τ; I-CE, τ = 0.05; I-CE, τ = 0.10 | 2,048 | 5 | Table A3 |
|
| 86 |
+
| `bce_cetf_gpool`, `byol_bytf_gpool`, `epd_v20i10c20_cetf_gpool`, `mq3072i2ce_icetf_gpool` | SimCLR-style; BYOL; VICReg (batch 192); I-CE with an EMA teacher and a memory bank | pool | 5 | Figure 7, Figure 8, Table 2, Section 3.2, Table A1, Table A13, Table A16, Table A17, Table A18, Figure A2, Table S2, Table S3, Table S4 |
|
| 87 |
+
| `ce_cetf_gpool`, `i2ce_icetf_gpool` | CE; I-CE, the recipe | pool | 5 | Figure 7, Figure 8, Table 2, Section 6.1, Table A1, Table A2, Table A7, Table A13, Table A14, Table A15, Table A16, Table A17, Table A18, Figure A2, Table S2, Table S3, Table S4 |
|
| 88 |
+
| `slot8i2cemean_icetf_gpool` | I-CE, 8 latent queries | pool | 5 | Table A7 |
|
| 89 |
+
| `swin168step84loop2i2ce_icetf_gpool`, `swin168step84loop2i2ce_icetf_gpool_bw` | I-CE with the windowed teacher; I-CE, two-stage: BYOL warm start, then the windowed teacher | pool | 5 | Table A13, Table S2, Table S3, Table S4 |
|
| 90 |
| `dino_dntf_gpool` | DINO at its published settings, the control of Section 4.3 | pool | 0 only | Table A1 |
|
| 91 |
|
| 92 |
I + SimCLR (`i2bce_icetf`, files without a pack or a suffix, five folds) backs Figure 8 and the
|
|
|
|
| 100 |
| Runs | What they are | Pack | Folds | Read by |
|
| 101 |
|---|---|---|---|---|
|
| 102 |
| `ai25auni2_icetf_d512`, `ai2auni25_icetf_d512`, `ai4auni2_icetf_d512`, `ai6auni2_icetf_d512`, `i4uni2_icetf` | alignment + uniformity aimed at the anchor gallery, the four settings of Section 6.2 (`ai25auni2` is Table 3's a+u @ gallery row); alignment + uniformity aimed at the batch views (Table 3's a+u @ views row) | 512 | fixed split | Table 3, Section 6.2, Appendix L |
|
| 103 |
+
| `ai2ce_icetf_d512`, `ce_cetf_d512`, `i2ce_icetf_d512` | CE + anchor-in-I; CE; I-CE, the recipe | 512 | fixed split | Table 3, Section 6.2, Table A8 |
|
| 104 |
| `ce_cetf_g2048`, `i2ce_icetf_g2048` | CE; I-CE, the recipe | 2,048 | fixed split | Figure 9, Figure A1, Figure A3, Appendix L |
|
| 105 |
+
| `bce_cetf`, `i2bce_icetf`, `epd_v20i10c20_cetf` | SimCLR-style; I + SimCLR; VICReg, v/i/c = 20/10/20 (the recipe weights) | 512 | fixed split | Figure 9, Figure A3, Appendix L, Table A8 |
|
| 106 |
+
| `epd_v25i25c1_cetf`, `epd_v20i10c15_cetf` | VICReg, v/i/c = 25/25/1; VICReg, v/i/c = 20/10/15 | 512 | fixed split | Table A8 |
|
| 107 |
|
| 108 |
Figure 9, Figure A3 and the neighborhood statistics of Appendix L read six encoders on the fixed
|
| 109 |
split: the frozen embedder, which has no checkpoint, and five towers, namely `i2ce_icetf_g2048`
|
|
|
|
| 165 |
python contrast_experiment/w9/eval/k10_eval.py table scores.json
|
| 166 |
```
|
| 167 |
|
| 168 |
+
`cells` takes the 171 five-fold checkpoints of `rank_ckpt_plan.json` and `i2bce_sel_pool.json`;
|
| 169 |
`--only <regex>` keeps a subset, for example `--only "_d512$"` for the 512-sentence runs. In its
|
| 170 |
table the five families of the main comparison go by the paper's names (`I-CE`, `CE`, `SimCLR`,
|
| 171 |
`VICReg`, `BYOL`) and every other family by its plan key without the fold; a family with one
|
|
|
|
| 179 |
|
| 180 |
It reads every run of `fixed_split_ckpt_plan.json` at its selected checkpoint and prints each
|
| 181 |
reading beside the number the paper prints: Table 3, the gallery-aimed settings of Section 6.2
|
| 182 |
+
and Table A8 on the one 4,096-sentence anchor draw of the fixed split, the SimCLR-style test
|
| 183 |
curve of Appendix L, the latent queries of Figure A1, and, through `k10_eval.py`, the towers of
|
| 184 |
Figure 9 against the ten draws. A near tie can move a cell by one query of 204 (0.005), and the
|
| 185 |
collapsed a+u @ gallery row by about 0.01.
|
|
|
|
| 233 |
|
| 234 |
## Changes
|
| 235 |
|
| 236 |
+
- 2026-11-12, later that day. Nine checkpoints were added, the view-size sweep of the appendix's
|
| 237 |
+
new Table A6: I-CE with each review view drawn until it holds at least 8, 32 or 64 sentences
|
| 238 |
+
(`i2ce_icetf_fold<k>_w<N>_d512`, folds 0 to 2). `rank_ckpt_plan.json` lists them. The new table
|
| 239 |
+
moved every later appendix table one place, so the old Tables A6 to A18 are Tables A7 to A19
|
| 240 |
+
in the tables above; no earlier entry changed its checkpoint.
|
| 241 |
- 2026-11-12. The code repository gained `figures/neighborhoods/`, the scripts that drew
|
| 242 |
Figures 8, 9 and A3.
|
| 243 |
- 2026-11-11, at night. The code repository gained `fixed_split_eval.py`, which reads the
|
ckpt_w9cv_wcle_i2ce_icetf_fold0_w32_d512_fp_ep1700.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfafb905c3989ae34474a24f6d1841bc1efb1e1b44f823e91aca0d2b887eee4e
|
| 3 |
+
size 1452509
|
ckpt_w9cv_wcle_i2ce_icetf_fold0_w64_d512_fp_ep2000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16c295bd3ca867035e98aeeb6bf6d1bebb3baadf94a62787a6648384cd308754
|
| 3 |
+
size 1452509
|
ckpt_w9cv_wcle_i2ce_icetf_fold0_w8_d512_fp_ep1850.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:709f72276caec20a72b9fc10667b8bb26c75d40058f1f8ed7a5bf2eba1f2f438
|
| 3 |
+
size 1452492
|
ckpt_w9cv_wcle_i2ce_icetf_fold1_w32_d512_fp_ep1300.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18c4155b1414c7783ee710b7306a9fde9a65f423da64747a29b9507d68254eb1
|
| 3 |
+
size 1452509
|
ckpt_w9cv_wcle_i2ce_icetf_fold1_w64_d512_fp_ep950.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a5aebdeaed6d016b0f4b85dc53e369cf3363991a874fc34a9deb82c29694bba
|
| 3 |
+
size 1452492
|
ckpt_w9cv_wcle_i2ce_icetf_fold1_w8_d512_fp_ep1800.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bca75f8340c9786ebc021db8a21d662fc6b3d6cdc3a34ad50c7c8d22a709c58f
|
| 3 |
+
size 1452492
|
ckpt_w9cv_wcle_i2ce_icetf_fold2_w32_d512_fp_ep1550.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b24af1da78dc89c11d49ba62f450d67f8d2d07be8ec89d5d1582ecda6695365
|
| 3 |
+
size 1452509
|
ckpt_w9cv_wcle_i2ce_icetf_fold2_w64_d512_fp_ep1750.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb19e080fb423c8d032e62f9f0b6e527dc3909498f3c8b0bb033f6fdbff07708
|
| 3 |
+
size 1452509
|
ckpt_w9cv_wcle_i2ce_icetf_fold2_w8_d512_fp_ep1850.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cffc1869a3b2bab8beec44f48a501e0dc522cb79026f72aff3a438697997e6a4
|
| 3 |
+
size 1452492
|
rank_ckpt_plan.json
CHANGED
|
@@ -339,6 +339,96 @@
|
|
| 339 |
"sha256": "1f565f77cecf8a283d8323ecfd7793fc1c155823187518f4e15e35e6cc85a73d",
|
| 340 |
"ranksel": 103.3357064881622
|
| 341 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 342 |
"i2cet05_icetf_fold0_d512": {
|
| 343 |
"arm": "i2cet05_icetf",
|
| 344 |
"fold": 0,
|
|
|
|
| 339 |
"sha256": "1f565f77cecf8a283d8323ecfd7793fc1c155823187518f4e15e35e6cc85a73d",
|
| 340 |
"ranksel": 103.3357064881622
|
| 341 |
},
|
| 342 |
+
"i2ce_icetf_fold0_w8_d512": {
|
| 343 |
+
"arm": "i2ce_icetf",
|
| 344 |
+
"fold": 0,
|
| 345 |
+
"cap": "",
|
| 346 |
+
"sfx": "_w8_d512",
|
| 347 |
+
"ep": 1850,
|
| 348 |
+
"ckpt": "ckpt_w9cv_wcle_i2ce_icetf_fold0_w8_d512_fp_ep1850.pt",
|
| 349 |
+
"sha256": "709f72276caec20a72b9fc10667b8bb26c75d40058f1f8ed7a5bf2eba1f2f438",
|
| 350 |
+
"ranksel": 102.15828396294594
|
| 351 |
+
},
|
| 352 |
+
"i2ce_icetf_fold1_w8_d512": {
|
| 353 |
+
"arm": "i2ce_icetf",
|
| 354 |
+
"fold": 1,
|
| 355 |
+
"cap": "",
|
| 356 |
+
"sfx": "_w8_d512",
|
| 357 |
+
"ep": 1800,
|
| 358 |
+
"ckpt": "ckpt_w9cv_wcle_i2ce_icetf_fold1_w8_d512_fp_ep1800.pt",
|
| 359 |
+
"sha256": "bca75f8340c9786ebc021db8a21d662fc6b3d6cdc3a34ad50c7c8d22a709c58f",
|
| 360 |
+
"ranksel": 100.92692735919152
|
| 361 |
+
},
|
| 362 |
+
"i2ce_icetf_fold2_w8_d512": {
|
| 363 |
+
"arm": "i2ce_icetf",
|
| 364 |
+
"fold": 2,
|
| 365 |
+
"cap": "",
|
| 366 |
+
"sfx": "_w8_d512",
|
| 367 |
+
"ep": 1850,
|
| 368 |
+
"ckpt": "ckpt_w9cv_wcle_i2ce_icetf_fold2_w8_d512_fp_ep1850.pt",
|
| 369 |
+
"sha256": "cffc1869a3b2bab8beec44f48a501e0dc522cb79026f72aff3a438697997e6a4",
|
| 370 |
+
"ranksel": 104.10870524765727
|
| 371 |
+
},
|
| 372 |
+
"i2ce_icetf_fold0_w32_d512": {
|
| 373 |
+
"arm": "i2ce_icetf",
|
| 374 |
+
"fold": 0,
|
| 375 |
+
"cap": "",
|
| 376 |
+
"sfx": "_w32_d512",
|
| 377 |
+
"ep": 1700,
|
| 378 |
+
"ckpt": "ckpt_w9cv_wcle_i2ce_icetf_fold0_w32_d512_fp_ep1700.pt",
|
| 379 |
+
"sha256": "bfafb905c3989ae34474a24f6d1841bc1efb1e1b44f823e91aca0d2b887eee4e",
|
| 380 |
+
"ranksel": 102.08490009321653
|
| 381 |
+
},
|
| 382 |
+
"i2ce_icetf_fold1_w32_d512": {
|
| 383 |
+
"arm": "i2ce_icetf",
|
| 384 |
+
"fold": 1,
|
| 385 |
+
"cap": "",
|
| 386 |
+
"sfx": "_w32_d512",
|
| 387 |
+
"ep": 1300,
|
| 388 |
+
"ckpt": "ckpt_w9cv_wcle_i2ce_icetf_fold1_w32_d512_fp_ep1300.pt",
|
| 389 |
+
"sha256": "18c4155b1414c7783ee710b7306a9fde9a65f423da64747a29b9507d68254eb1",
|
| 390 |
+
"ranksel": 100.07076937461179
|
| 391 |
+
},
|
| 392 |
+
"i2ce_icetf_fold2_w32_d512": {
|
| 393 |
+
"arm": "i2ce_icetf",
|
| 394 |
+
"fold": 2,
|
| 395 |
+
"cap": "",
|
| 396 |
+
"sfx": "_w32_d512",
|
| 397 |
+
"ep": 1550,
|
| 398 |
+
"ckpt": "ckpt_w9cv_wcle_i2ce_icetf_fold2_w32_d512_fp_ep1550.pt",
|
| 399 |
+
"sha256": "1b24af1da78dc89c11d49ba62f450d67f8d2d07be8ec89d5d1582ecda6695365",
|
| 400 |
+
"ranksel": 102.88761013766694
|
| 401 |
+
},
|
| 402 |
+
"i2ce_icetf_fold0_w64_d512": {
|
| 403 |
+
"arm": "i2ce_icetf",
|
| 404 |
+
"fold": 0,
|
| 405 |
+
"cap": "",
|
| 406 |
+
"sfx": "_w64_d512",
|
| 407 |
+
"ep": 2000,
|
| 408 |
+
"ckpt": "ckpt_w9cv_wcle_i2ce_icetf_fold0_w64_d512_fp_ep2000.pt",
|
| 409 |
+
"sha256": "16c295bd3ca867035e98aeeb6bf6d1bebb3baadf94a62787a6648384cd308754",
|
| 410 |
+
"ranksel": 98.52861143847147
|
| 411 |
+
},
|
| 412 |
+
"i2ce_icetf_fold1_w64_d512": {
|
| 413 |
+
"arm": "i2ce_icetf",
|
| 414 |
+
"fold": 1,
|
| 415 |
+
"cap": "",
|
| 416 |
+
"sfx": "_w64_d512",
|
| 417 |
+
"ep": 950,
|
| 418 |
+
"ckpt": "ckpt_w9cv_wcle_i2ce_icetf_fold1_w64_d512_fp_ep950.pt",
|
| 419 |
+
"sha256": "9a5aebdeaed6d016b0f4b85dc53e369cf3363991a874fc34a9deb82c29694bba",
|
| 420 |
+
"ranksel": 96.14252478109898
|
| 421 |
+
},
|
| 422 |
+
"i2ce_icetf_fold2_w64_d512": {
|
| 423 |
+
"arm": "i2ce_icetf",
|
| 424 |
+
"fold": 2,
|
| 425 |
+
"cap": "",
|
| 426 |
+
"sfx": "_w64_d512",
|
| 427 |
+
"ep": 1750,
|
| 428 |
+
"ckpt": "ckpt_w9cv_wcle_i2ce_icetf_fold2_w64_d512_fp_ep1750.pt",
|
| 429 |
+
"sha256": "fb19e080fb423c8d032e62f9f0b6e527dc3909498f3c8b0bb033f6fdbff07708",
|
| 430 |
+
"ranksel": 102.6732653888046
|
| 431 |
+
},
|
| 432 |
"i2cet05_icetf_fold0_d512": {
|
| 433 |
"arm": "i2cet05_icetf",
|
| 434 |
"fold": 0,
|