Hugging Face's logo

Interplay-LM-Reasoning
/
extrapolation_midtrain

Transformers
Safetensors
reasoning
mid-training
extrapolation
synthetic-data
Model card Files
xet
 Community
1
Clockz commited on
Commit
adbdf99
·
verified ·
1 Parent(s): 63c3f5d

Add files using upload-large-folder tool

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -21,6 +21,7 @@ For pretraining, only `cpt0.2-uniform_0.8-11-14_plus` is included. For RL, only
21
  | --- | --- | --- |
22
  | `id2-10_0.2easy_0.3medium_0.5hard/midtrain/cpt0.2-uniform_0.8-11-14_plus/checkpoint-387` | checkpoint-387 | 50step/0.2 |
23
  | `id2-10_0.2easy_0.3medium_0.5hard/midtrain/cpt0.2-uniform_0.8-11-14_plus/checkpoint-774` | checkpoint-774 | 100step/0.2 |
 
24
  | `id2-10_0.2easy_0.3medium_0.5hard/midtrain/cpt0.2-uniform_0.8-11-14_plus/checkpoint-1548` | checkpoint-1548 | 200step/0.2 |
25
  | `id2-10_0.2easy_0.3medium_0.5hard/midtrain/cpt0.2-uniform_0.8-11-14_plus/checkpoint-1935` | checkpoint-1935 | 100step/0.5 |
26
  | `id2-10_0.2easy_0.3medium_0.5hard/midtrain/cpt0.2-uniform_0.8-11-14_plus/checkpoint-3096` | checkpoint-3096 | 100step/0.8, 400step/0.2 |
@@ -43,9 +44,13 @@ For pretraining, only `cpt0.2-uniform_0.8-11-14_plus` is included. For RL, only
43
  | Path | Nominal step | CPT epoch | Source CPT checkpoint | Uploaded checkpoint |
44
  | --- | --- | --- | --- | --- |
45
  | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.2-rl-op11-14_uniform-50step-0.8RL` | 50 | 0.2 | checkpoint-387 | `global_step_40` |
 
 
46
  | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.8-rl-op11-14_uniform-100step-0.2RL` | 100 | 0.8 | checkpoint-3096 | `global_step_19` |
47
  | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.5-rl-op11-14_uniform-100step-0.5RL` | 100 | 0.5 | checkpoint-1935 | `global_step_50` |
48
  | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.2-rl-op11-14_uniform-100step-0.8RL` | 100 | 0.2 | checkpoint-774 | `global_step_80` |
 
 
49
  | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.2-rl-op11-14_uniform-200step-0.8RL` | 200 | 0.2 | checkpoint-1548 | `global_step_160` |
50
 
51
  ## Load
 
21
  | --- | --- | --- |
22
  | `id2-10_0.2easy_0.3medium_0.5hard/midtrain/cpt0.2-uniform_0.8-11-14_plus/checkpoint-387` | checkpoint-387 | 50step/0.2 |
23
  | `id2-10_0.2easy_0.3medium_0.5hard/midtrain/cpt0.2-uniform_0.8-11-14_plus/checkpoint-774` | checkpoint-774 | 100step/0.2 |
24
+ | `id2-10_0.2easy_0.3medium_0.5hard/midtrain/cpt0.2-uniform_0.8-11-14_plus/checkpoint-1161` | checkpoint-1161 | 50step/0.5 |
25
  | `id2-10_0.2easy_0.3medium_0.5hard/midtrain/cpt0.2-uniform_0.8-11-14_plus/checkpoint-1548` | checkpoint-1548 | 200step/0.2 |
26
  | `id2-10_0.2easy_0.3medium_0.5hard/midtrain/cpt0.2-uniform_0.8-11-14_plus/checkpoint-1935` | checkpoint-1935 | 100step/0.5 |
27
  | `id2-10_0.2easy_0.3medium_0.5hard/midtrain/cpt0.2-uniform_0.8-11-14_plus/checkpoint-3096` | checkpoint-3096 | 100step/0.8, 400step/0.2 |
 
44
  | Path | Nominal step | CPT epoch | Source CPT checkpoint | Uploaded checkpoint |
45
  | --- | --- | --- | --- | --- |
46
  | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.2-rl-op11-14_uniform-50step-0.8RL` | 50 | 0.2 | checkpoint-387 | `global_step_40` |
47
+ | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.5-rl-op11-14_uniform-50step-0.5RL` | 50 | 0.5 | checkpoint-1161 | `global_step_25` |
48
+ | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.8-rl-op11-14_uniform-50step-0.2RL` | 50 | 0.8 | checkpoint-1548 | `global_step_9` |
49
  | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.8-rl-op11-14_uniform-100step-0.2RL` | 100 | 0.8 | checkpoint-3096 | `global_step_19` |
50
  | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.5-rl-op11-14_uniform-100step-0.5RL` | 100 | 0.5 | checkpoint-1935 | `global_step_50` |
51
  | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.2-rl-op11-14_uniform-100step-0.8RL` | 100 | 0.2 | checkpoint-774 | `global_step_80` |
52
+ | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.8-rl-op11-14_uniform-200step-0.2RL` | 200 | 0.8 | checkpoint-6579 | `global_step_39` |
53
+ | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.5-rl-op11-14_uniform-200step-0.5RL` | 200 | 0.5 | checkpoint-3870 | `global_step_100` |
54
  | `id2-10_0.2easy_0.3medium_0.5hard/rl/cpt0.2-rl-op11-14_uniform-200step-0.8RL` | 200 | 0.2 | checkpoint-1548 | `global_step_160` |
55
 
56
  ## Load